diff options
Diffstat (limited to 'Lib')
378 files changed, 22020 insertions, 13190 deletions
diff --git a/Lib/_collections_abc.py b/Lib/_collections_abc.py index 33b59ab..3d3f07b 100644 --- a/Lib/_collections_abc.py +++ b/Lib/_collections_abc.py @@ -453,6 +453,8 @@ Mapping.register(mappingproxy) class MappingView(Sized): + __slots__ = '_mapping', + def __init__(self, mapping): self._mapping = mapping @@ -465,6 +467,8 @@ class MappingView(Sized): class KeysView(MappingView, Set): + __slots__ = () + @classmethod def _from_iterable(self, it): return set(it) @@ -480,6 +484,8 @@ KeysView.register(dict_keys) class ItemsView(MappingView, Set): + __slots__ = () + @classmethod def _from_iterable(self, it): return set(it) @@ -502,6 +508,8 @@ ItemsView.register(dict_items) class ValuesView(MappingView): + __slots__ = () + def __contains__(self, value): for key in self._mapping: if value == self._mapping[key]: diff --git a/Lib/_dummy_thread.py b/Lib/_dummy_thread.py index b67cfb9..36e5f38 100644 --- a/Lib/_dummy_thread.py +++ b/Lib/_dummy_thread.py @@ -140,6 +140,14 @@ class LockType(object): def locked(self): return self.locked_status + def __repr__(self): + return "<%s %s.%s object at %s>" % ( + "locked" if self.locked_status else "unlocked", + self.__class__.__module__, + self.__class__.__qualname__, + hex(id(self)) + ) + # Used to signal that interrupt_main was called in a "thread" _interrupt = False # True when not executing in a "thread" diff --git a/Lib/_pydecimal.py b/Lib/_pydecimal.py new file mode 100644 index 0000000..88222be --- /dev/null +++ b/Lib/_pydecimal.py @@ -0,0 +1,6381 @@ +# Copyright (c) 2004 Python Software Foundation. +# All rights reserved. + +# Written by Eric Price <eprice at tjhsst.edu> +# and Facundo Batista <facundo at taniquetil.com.ar> +# and Raymond Hettinger <python at rcn.com> +# and Aahz <aahz at pobox.com> +# and Tim Peters + +# This module should be kept in sync with the latest updates of the +# IBM specification as it evolves. Those updates will be treated +# as bug fixes (deviation from the spec is a compatibility, usability +# bug) and will be backported. At this point the spec is stabilizing +# and the updates are becoming fewer, smaller, and less significant. + +""" +This is an implementation of decimal floating point arithmetic based on +the General Decimal Arithmetic Specification: + + http://speleotrove.com/decimal/decarith.html + +and IEEE standard 854-1987: + + http://en.wikipedia.org/wiki/IEEE_854-1987 + +Decimal floating point has finite precision with arbitrarily large bounds. + +The purpose of this module is to support arithmetic using familiar +"schoolhouse" rules and to avoid some of the tricky representation +issues associated with binary floating point. The package is especially +useful for financial applications or for contexts where users have +expectations that are at odds with binary floating point (for instance, +in binary floating point, 1.00 % 0.1 gives 0.09999999999999995 instead +of 0.0; Decimal('1.00') % Decimal('0.1') returns the expected +Decimal('0.00')). + +Here are some examples of using the decimal module: + +>>> from decimal import * +>>> setcontext(ExtendedContext) +>>> Decimal(0) +Decimal('0') +>>> Decimal('1') +Decimal('1') +>>> Decimal('-.0123') +Decimal('-0.0123') +>>> Decimal(123456) +Decimal('123456') +>>> Decimal('123.45e12345678') +Decimal('1.2345E+12345680') +>>> Decimal('1.33') + Decimal('1.27') +Decimal('2.60') +>>> Decimal('12.34') + Decimal('3.87') - Decimal('18.41') +Decimal('-2.20') +>>> dig = Decimal(1) +>>> print(dig / Decimal(3)) +0.333333333 +>>> getcontext().prec = 18 +>>> print(dig / Decimal(3)) +0.333333333333333333 +>>> print(dig.sqrt()) +1 +>>> print(Decimal(3).sqrt()) +1.73205080756887729 +>>> print(Decimal(3) ** 123) +4.85192780976896427E+58 +>>> inf = Decimal(1) / Decimal(0) +>>> print(inf) +Infinity +>>> neginf = Decimal(-1) / Decimal(0) +>>> print(neginf) +-Infinity +>>> print(neginf + inf) +NaN +>>> print(neginf * inf) +-Infinity +>>> print(dig / 0) +Infinity +>>> getcontext().traps[DivisionByZero] = 1 +>>> print(dig / 0) +Traceback (most recent call last): + ... + ... + ... +decimal.DivisionByZero: x / 0 +>>> c = Context() +>>> c.traps[InvalidOperation] = 0 +>>> print(c.flags[InvalidOperation]) +0 +>>> c.divide(Decimal(0), Decimal(0)) +Decimal('NaN') +>>> c.traps[InvalidOperation] = 1 +>>> print(c.flags[InvalidOperation]) +1 +>>> c.flags[InvalidOperation] = 0 +>>> print(c.flags[InvalidOperation]) +0 +>>> print(c.divide(Decimal(0), Decimal(0))) +Traceback (most recent call last): + ... + ... + ... +decimal.InvalidOperation: 0 / 0 +>>> print(c.flags[InvalidOperation]) +1 +>>> c.flags[InvalidOperation] = 0 +>>> c.traps[InvalidOperation] = 0 +>>> print(c.divide(Decimal(0), Decimal(0))) +NaN +>>> print(c.flags[InvalidOperation]) +1 +>>> +""" + +__all__ = [ + # Two major classes + 'Decimal', 'Context', + + # Named tuple representation + 'DecimalTuple', + + # Contexts + 'DefaultContext', 'BasicContext', 'ExtendedContext', + + # Exceptions + 'DecimalException', 'Clamped', 'InvalidOperation', 'DivisionByZero', + 'Inexact', 'Rounded', 'Subnormal', 'Overflow', 'Underflow', + 'FloatOperation', + + # Exceptional conditions that trigger InvalidOperation + 'DivisionImpossible', 'InvalidContext', 'ConversionSyntax', 'DivisionUndefined', + + # Constants for use in setting up contexts + 'ROUND_DOWN', 'ROUND_HALF_UP', 'ROUND_HALF_EVEN', 'ROUND_CEILING', + 'ROUND_FLOOR', 'ROUND_UP', 'ROUND_HALF_DOWN', 'ROUND_05UP', + + # Functions for manipulating contexts + 'setcontext', 'getcontext', 'localcontext', + + # Limits for the C version for compatibility + 'MAX_PREC', 'MAX_EMAX', 'MIN_EMIN', 'MIN_ETINY', + + # C version: compile time choice that enables the thread local context + 'HAVE_THREADS' +] + +__xname__ = __name__ # sys.modules lookup (--without-threads) +__name__ = 'decimal' # For pickling +__version__ = '1.70' # Highest version of the spec this complies with + # See http://speleotrove.com/decimal/ +__libmpdec_version__ = "2.4.1" # compatible libmpdec version + +import math as _math +import numbers as _numbers +import sys + +try: + from collections import namedtuple as _namedtuple + DecimalTuple = _namedtuple('DecimalTuple', 'sign digits exponent') +except ImportError: + DecimalTuple = lambda *args: args + +# Rounding +ROUND_DOWN = 'ROUND_DOWN' +ROUND_HALF_UP = 'ROUND_HALF_UP' +ROUND_HALF_EVEN = 'ROUND_HALF_EVEN' +ROUND_CEILING = 'ROUND_CEILING' +ROUND_FLOOR = 'ROUND_FLOOR' +ROUND_UP = 'ROUND_UP' +ROUND_HALF_DOWN = 'ROUND_HALF_DOWN' +ROUND_05UP = 'ROUND_05UP' + +# Compatibility with the C version +HAVE_THREADS = True +if sys.maxsize == 2**63-1: + MAX_PREC = 999999999999999999 + MAX_EMAX = 999999999999999999 + MIN_EMIN = -999999999999999999 +else: + MAX_PREC = 425000000 + MAX_EMAX = 425000000 + MIN_EMIN = -425000000 + +MIN_ETINY = MIN_EMIN - (MAX_PREC-1) + +# Errors + +class DecimalException(ArithmeticError): + """Base exception class. + + Used exceptions derive from this. + If an exception derives from another exception besides this (such as + Underflow (Inexact, Rounded, Subnormal) that indicates that it is only + called if the others are present. This isn't actually used for + anything, though. + + handle -- Called when context._raise_error is called and the + trap_enabler is not set. First argument is self, second is the + context. More arguments can be given, those being after + the explanation in _raise_error (For example, + context._raise_error(NewError, '(-x)!', self._sign) would + call NewError().handle(context, self._sign).) + + To define a new exception, it should be sufficient to have it derive + from DecimalException. + """ + def handle(self, context, *args): + pass + + +class Clamped(DecimalException): + """Exponent of a 0 changed to fit bounds. + + This occurs and signals clamped if the exponent of a result has been + altered in order to fit the constraints of a specific concrete + representation. This may occur when the exponent of a zero result would + be outside the bounds of a representation, or when a large normal + number would have an encoded exponent that cannot be represented. In + this latter case, the exponent is reduced to fit and the corresponding + number of zero digits are appended to the coefficient ("fold-down"). + """ + +class InvalidOperation(DecimalException): + """An invalid operation was performed. + + Various bad things cause this: + + Something creates a signaling NaN + -INF + INF + 0 * (+-)INF + (+-)INF / (+-)INF + x % 0 + (+-)INF % x + x._rescale( non-integer ) + sqrt(-x) , x > 0 + 0 ** 0 + x ** (non-integer) + x ** (+-)INF + An operand is invalid + + The result of the operation after these is a quiet positive NaN, + except when the cause is a signaling NaN, in which case the result is + also a quiet NaN, but with the original sign, and an optional + diagnostic information. + """ + def handle(self, context, *args): + if args: + ans = _dec_from_triple(args[0]._sign, args[0]._int, 'n', True) + return ans._fix_nan(context) + return _NaN + +class ConversionSyntax(InvalidOperation): + """Trying to convert badly formed string. + + This occurs and signals invalid-operation if an string is being + converted to a number and it does not conform to the numeric string + syntax. The result is [0,qNaN]. + """ + def handle(self, context, *args): + return _NaN + +class DivisionByZero(DecimalException, ZeroDivisionError): + """Division by 0. + + This occurs and signals division-by-zero if division of a finite number + by zero was attempted (during a divide-integer or divide operation, or a + power operation with negative right-hand operand), and the dividend was + not zero. + + The result of the operation is [sign,inf], where sign is the exclusive + or of the signs of the operands for divide, or is 1 for an odd power of + -0, for power. + """ + + def handle(self, context, sign, *args): + return _SignedInfinity[sign] + +class DivisionImpossible(InvalidOperation): + """Cannot perform the division adequately. + + This occurs and signals invalid-operation if the integer result of a + divide-integer or remainder operation had too many digits (would be + longer than precision). The result is [0,qNaN]. + """ + + def handle(self, context, *args): + return _NaN + +class DivisionUndefined(InvalidOperation, ZeroDivisionError): + """Undefined result of division. + + This occurs and signals invalid-operation if division by zero was + attempted (during a divide-integer, divide, or remainder operation), and + the dividend is also zero. The result is [0,qNaN]. + """ + + def handle(self, context, *args): + return _NaN + +class Inexact(DecimalException): + """Had to round, losing information. + + This occurs and signals inexact whenever the result of an operation is + not exact (that is, it needed to be rounded and any discarded digits + were non-zero), or if an overflow or underflow condition occurs. The + result in all cases is unchanged. + + The inexact signal may be tested (or trapped) to determine if a given + operation (or sequence of operations) was inexact. + """ + +class InvalidContext(InvalidOperation): + """Invalid context. Unknown rounding, for example. + + This occurs and signals invalid-operation if an invalid context was + detected during an operation. This can occur if contexts are not checked + on creation and either the precision exceeds the capability of the + underlying concrete representation or an unknown or unsupported rounding + was specified. These aspects of the context need only be checked when + the values are required to be used. The result is [0,qNaN]. + """ + + def handle(self, context, *args): + return _NaN + +class Rounded(DecimalException): + """Number got rounded (not necessarily changed during rounding). + + This occurs and signals rounded whenever the result of an operation is + rounded (that is, some zero or non-zero digits were discarded from the + coefficient), or if an overflow or underflow condition occurs. The + result in all cases is unchanged. + + The rounded signal may be tested (or trapped) to determine if a given + operation (or sequence of operations) caused a loss of precision. + """ + +class Subnormal(DecimalException): + """Exponent < Emin before rounding. + + This occurs and signals subnormal whenever the result of a conversion or + operation is subnormal (that is, its adjusted exponent is less than + Emin, before any rounding). The result in all cases is unchanged. + + The subnormal signal may be tested (or trapped) to determine if a given + or operation (or sequence of operations) yielded a subnormal result. + """ + +class Overflow(Inexact, Rounded): + """Numerical overflow. + + This occurs and signals overflow if the adjusted exponent of a result + (from a conversion or from an operation that is not an attempt to divide + by zero), after rounding, would be greater than the largest value that + can be handled by the implementation (the value Emax). + + The result depends on the rounding mode: + + For round-half-up and round-half-even (and for round-half-down and + round-up, if implemented), the result of the operation is [sign,inf], + where sign is the sign of the intermediate result. For round-down, the + result is the largest finite number that can be represented in the + current precision, with the sign of the intermediate result. For + round-ceiling, the result is the same as for round-down if the sign of + the intermediate result is 1, or is [0,inf] otherwise. For round-floor, + the result is the same as for round-down if the sign of the intermediate + result is 0, or is [1,inf] otherwise. In all cases, Inexact and Rounded + will also be raised. + """ + + def handle(self, context, sign, *args): + if context.rounding in (ROUND_HALF_UP, ROUND_HALF_EVEN, + ROUND_HALF_DOWN, ROUND_UP): + return _SignedInfinity[sign] + if sign == 0: + if context.rounding == ROUND_CEILING: + return _SignedInfinity[sign] + return _dec_from_triple(sign, '9'*context.prec, + context.Emax-context.prec+1) + if sign == 1: + if context.rounding == ROUND_FLOOR: + return _SignedInfinity[sign] + return _dec_from_triple(sign, '9'*context.prec, + context.Emax-context.prec+1) + + +class Underflow(Inexact, Rounded, Subnormal): + """Numerical underflow with result rounded to 0. + + This occurs and signals underflow if a result is inexact and the + adjusted exponent of the result would be smaller (more negative) than + the smallest value that can be handled by the implementation (the value + Emin). That is, the result is both inexact and subnormal. + + The result after an underflow will be a subnormal number rounded, if + necessary, so that its exponent is not less than Etiny. This may result + in 0 with the sign of the intermediate result and an exponent of Etiny. + + In all cases, Inexact, Rounded, and Subnormal will also be raised. + """ + +class FloatOperation(DecimalException, TypeError): + """Enable stricter semantics for mixing floats and Decimals. + + If the signal is not trapped (default), mixing floats and Decimals is + permitted in the Decimal() constructor, context.create_decimal() and + all comparison operators. Both conversion and comparisons are exact. + Any occurrence of a mixed operation is silently recorded by setting + FloatOperation in the context flags. Explicit conversions with + Decimal.from_float() or context.create_decimal_from_float() do not + set the flag. + + Otherwise (the signal is trapped), only equality comparisons and explicit + conversions are silent. All other mixed operations raise FloatOperation. + """ + +# List of public traps and flags +_signals = [Clamped, DivisionByZero, Inexact, Overflow, Rounded, + Underflow, InvalidOperation, Subnormal, FloatOperation] + +# Map conditions (per the spec) to signals +_condition_map = {ConversionSyntax:InvalidOperation, + DivisionImpossible:InvalidOperation, + DivisionUndefined:InvalidOperation, + InvalidContext:InvalidOperation} + +# Valid rounding modes +_rounding_modes = (ROUND_DOWN, ROUND_HALF_UP, ROUND_HALF_EVEN, ROUND_CEILING, + ROUND_FLOOR, ROUND_UP, ROUND_HALF_DOWN, ROUND_05UP) + +##### Context Functions ################################################## + +# The getcontext() and setcontext() function manage access to a thread-local +# current context. Py2.4 offers direct support for thread locals. If that +# is not available, use threading.current_thread() which is slower but will +# work for older Pythons. If threads are not part of the build, create a +# mock threading object with threading.local() returning the module namespace. + +try: + import threading +except ImportError: + # Python was compiled without threads; create a mock object instead + class MockThreading(object): + def local(self, sys=sys): + return sys.modules[__xname__] + threading = MockThreading() + del MockThreading + +try: + threading.local + +except AttributeError: + + # To fix reloading, force it to create a new context + # Old contexts have different exceptions in their dicts, making problems. + if hasattr(threading.current_thread(), '__decimal_context__'): + del threading.current_thread().__decimal_context__ + + def setcontext(context): + """Set this thread's context to context.""" + if context in (DefaultContext, BasicContext, ExtendedContext): + context = context.copy() + context.clear_flags() + threading.current_thread().__decimal_context__ = context + + def getcontext(): + """Returns this thread's context. + + If this thread does not yet have a context, returns + a new context and sets this thread's context. + New contexts are copies of DefaultContext. + """ + try: + return threading.current_thread().__decimal_context__ + except AttributeError: + context = Context() + threading.current_thread().__decimal_context__ = context + return context + +else: + + local = threading.local() + if hasattr(local, '__decimal_context__'): + del local.__decimal_context__ + + def getcontext(_local=local): + """Returns this thread's context. + + If this thread does not yet have a context, returns + a new context and sets this thread's context. + New contexts are copies of DefaultContext. + """ + try: + return _local.__decimal_context__ + except AttributeError: + context = Context() + _local.__decimal_context__ = context + return context + + def setcontext(context, _local=local): + """Set this thread's context to context.""" + if context in (DefaultContext, BasicContext, ExtendedContext): + context = context.copy() + context.clear_flags() + _local.__decimal_context__ = context + + del threading, local # Don't contaminate the namespace + +def localcontext(ctx=None): + """Return a context manager for a copy of the supplied context + + Uses a copy of the current context if no context is specified + The returned context manager creates a local decimal context + in a with statement: + def sin(x): + with localcontext() as ctx: + ctx.prec += 2 + # Rest of sin calculation algorithm + # uses a precision 2 greater than normal + return +s # Convert result to normal precision + + def sin(x): + with localcontext(ExtendedContext): + # Rest of sin calculation algorithm + # uses the Extended Context from the + # General Decimal Arithmetic Specification + return +s # Convert result to normal context + + >>> setcontext(DefaultContext) + >>> print(getcontext().prec) + 28 + >>> with localcontext(): + ... ctx = getcontext() + ... ctx.prec += 2 + ... print(ctx.prec) + ... + 30 + >>> with localcontext(ExtendedContext): + ... print(getcontext().prec) + ... + 9 + >>> print(getcontext().prec) + 28 + """ + if ctx is None: ctx = getcontext() + return _ContextManager(ctx) + + +##### Decimal class ####################################################### + +# Do not subclass Decimal from numbers.Real and do not register it as such +# (because Decimals are not interoperable with floats). See the notes in +# numbers.py for more detail. + +class Decimal(object): + """Floating point class for decimal arithmetic.""" + + __slots__ = ('_exp','_int','_sign', '_is_special') + # Generally, the value of the Decimal instance is given by + # (-1)**_sign * _int * 10**_exp + # Special values are signified by _is_special == True + + # We're immutable, so use __new__ not __init__ + def __new__(cls, value="0", context=None): + """Create a decimal point instance. + + >>> Decimal('3.14') # string input + Decimal('3.14') + >>> Decimal((0, (3, 1, 4), -2)) # tuple (sign, digit_tuple, exponent) + Decimal('3.14') + >>> Decimal(314) # int + Decimal('314') + >>> Decimal(Decimal(314)) # another decimal instance + Decimal('314') + >>> Decimal(' 3.14 \\n') # leading and trailing whitespace okay + Decimal('3.14') + """ + + # Note that the coefficient, self._int, is actually stored as + # a string rather than as a tuple of digits. This speeds up + # the "digits to integer" and "integer to digits" conversions + # that are used in almost every arithmetic operation on + # Decimals. This is an internal detail: the as_tuple function + # and the Decimal constructor still deal with tuples of + # digits. + + self = object.__new__(cls) + + # From a string + # REs insist on real strings, so we can too. + if isinstance(value, str): + m = _parser(value.strip()) + if m is None: + if context is None: + context = getcontext() + return context._raise_error(ConversionSyntax, + "Invalid literal for Decimal: %r" % value) + + if m.group('sign') == "-": + self._sign = 1 + else: + self._sign = 0 + intpart = m.group('int') + if intpart is not None: + # finite number + fracpart = m.group('frac') or '' + exp = int(m.group('exp') or '0') + self._int = str(int(intpart+fracpart)) + self._exp = exp - len(fracpart) + self._is_special = False + else: + diag = m.group('diag') + if diag is not None: + # NaN + self._int = str(int(diag or '0')).lstrip('0') + if m.group('signal'): + self._exp = 'N' + else: + self._exp = 'n' + else: + # infinity + self._int = '0' + self._exp = 'F' + self._is_special = True + return self + + # From an integer + if isinstance(value, int): + if value >= 0: + self._sign = 0 + else: + self._sign = 1 + self._exp = 0 + self._int = str(abs(value)) + self._is_special = False + return self + + # From another decimal + if isinstance(value, Decimal): + self._exp = value._exp + self._sign = value._sign + self._int = value._int + self._is_special = value._is_special + return self + + # From an internal working value + if isinstance(value, _WorkRep): + self._sign = value.sign + self._int = str(value.int) + self._exp = int(value.exp) + self._is_special = False + return self + + # tuple/list conversion (possibly from as_tuple()) + if isinstance(value, (list,tuple)): + if len(value) != 3: + raise ValueError('Invalid tuple size in creation of Decimal ' + 'from list or tuple. The list or tuple ' + 'should have exactly three elements.') + # process sign. The isinstance test rejects floats + if not (isinstance(value[0], int) and value[0] in (0,1)): + raise ValueError("Invalid sign. The first value in the tuple " + "should be an integer; either 0 for a " + "positive number or 1 for a negative number.") + self._sign = value[0] + if value[2] == 'F': + # infinity: value[1] is ignored + self._int = '0' + self._exp = value[2] + self._is_special = True + else: + # process and validate the digits in value[1] + digits = [] + for digit in value[1]: + if isinstance(digit, int) and 0 <= digit <= 9: + # skip leading zeros + if digits or digit != 0: + digits.append(digit) + else: + raise ValueError("The second value in the tuple must " + "be composed of integers in the range " + "0 through 9.") + if value[2] in ('n', 'N'): + # NaN: digits form the diagnostic + self._int = ''.join(map(str, digits)) + self._exp = value[2] + self._is_special = True + elif isinstance(value[2], int): + # finite number: digits give the coefficient + self._int = ''.join(map(str, digits or [0])) + self._exp = value[2] + self._is_special = False + else: + raise ValueError("The third value in the tuple must " + "be an integer, or one of the " + "strings 'F', 'n', 'N'.") + return self + + if isinstance(value, float): + if context is None: + context = getcontext() + context._raise_error(FloatOperation, + "strict semantics for mixing floats and Decimals are " + "enabled") + value = Decimal.from_float(value) + self._exp = value._exp + self._sign = value._sign + self._int = value._int + self._is_special = value._is_special + return self + + raise TypeError("Cannot convert %r to Decimal" % value) + + @classmethod + def from_float(cls, f): + """Converts a float to a decimal number, exactly. + + Note that Decimal.from_float(0.1) is not the same as Decimal('0.1'). + Since 0.1 is not exactly representable in binary floating point, the + value is stored as the nearest representable value which is + 0x1.999999999999ap-4. The exact equivalent of the value in decimal + is 0.1000000000000000055511151231257827021181583404541015625. + + >>> Decimal.from_float(0.1) + Decimal('0.1000000000000000055511151231257827021181583404541015625') + >>> Decimal.from_float(float('nan')) + Decimal('NaN') + >>> Decimal.from_float(float('inf')) + Decimal('Infinity') + >>> Decimal.from_float(-float('inf')) + Decimal('-Infinity') + >>> Decimal.from_float(-0.0) + Decimal('-0') + + """ + if isinstance(f, int): # handle integer inputs + return cls(f) + if not isinstance(f, float): + raise TypeError("argument must be int or float.") + if _math.isinf(f) or _math.isnan(f): + return cls(repr(f)) + if _math.copysign(1.0, f) == 1.0: + sign = 0 + else: + sign = 1 + n, d = abs(f).as_integer_ratio() + k = d.bit_length() - 1 + result = _dec_from_triple(sign, str(n*5**k), -k) + if cls is Decimal: + return result + else: + return cls(result) + + def _isnan(self): + """Returns whether the number is not actually one. + + 0 if a number + 1 if NaN + 2 if sNaN + """ + if self._is_special: + exp = self._exp + if exp == 'n': + return 1 + elif exp == 'N': + return 2 + return 0 + + def _isinfinity(self): + """Returns whether the number is infinite + + 0 if finite or not a number + 1 if +INF + -1 if -INF + """ + if self._exp == 'F': + if self._sign: + return -1 + return 1 + return 0 + + def _check_nans(self, other=None, context=None): + """Returns whether the number is not actually one. + + if self, other are sNaN, signal + if self, other are NaN return nan + return 0 + + Done before operations. + """ + + self_is_nan = self._isnan() + if other is None: + other_is_nan = False + else: + other_is_nan = other._isnan() + + if self_is_nan or other_is_nan: + if context is None: + context = getcontext() + + if self_is_nan == 2: + return context._raise_error(InvalidOperation, 'sNaN', + self) + if other_is_nan == 2: + return context._raise_error(InvalidOperation, 'sNaN', + other) + if self_is_nan: + return self._fix_nan(context) + + return other._fix_nan(context) + return 0 + + def _compare_check_nans(self, other, context): + """Version of _check_nans used for the signaling comparisons + compare_signal, __le__, __lt__, __ge__, __gt__. + + Signal InvalidOperation if either self or other is a (quiet + or signaling) NaN. Signaling NaNs take precedence over quiet + NaNs. + + Return 0 if neither operand is a NaN. + + """ + if context is None: + context = getcontext() + + if self._is_special or other._is_special: + if self.is_snan(): + return context._raise_error(InvalidOperation, + 'comparison involving sNaN', + self) + elif other.is_snan(): + return context._raise_error(InvalidOperation, + 'comparison involving sNaN', + other) + elif self.is_qnan(): + return context._raise_error(InvalidOperation, + 'comparison involving NaN', + self) + elif other.is_qnan(): + return context._raise_error(InvalidOperation, + 'comparison involving NaN', + other) + return 0 + + def __bool__(self): + """Return True if self is nonzero; otherwise return False. + + NaNs and infinities are considered nonzero. + """ + return self._is_special or self._int != '0' + + def _cmp(self, other): + """Compare the two non-NaN decimal instances self and other. + + Returns -1 if self < other, 0 if self == other and 1 + if self > other. This routine is for internal use only.""" + + if self._is_special or other._is_special: + self_inf = self._isinfinity() + other_inf = other._isinfinity() + if self_inf == other_inf: + return 0 + elif self_inf < other_inf: + return -1 + else: + return 1 + + # check for zeros; Decimal('0') == Decimal('-0') + if not self: + if not other: + return 0 + else: + return -((-1)**other._sign) + if not other: + return (-1)**self._sign + + # If different signs, neg one is less + if other._sign < self._sign: + return -1 + if self._sign < other._sign: + return 1 + + self_adjusted = self.adjusted() + other_adjusted = other.adjusted() + if self_adjusted == other_adjusted: + self_padded = self._int + '0'*(self._exp - other._exp) + other_padded = other._int + '0'*(other._exp - self._exp) + if self_padded == other_padded: + return 0 + elif self_padded < other_padded: + return -(-1)**self._sign + else: + return (-1)**self._sign + elif self_adjusted > other_adjusted: + return (-1)**self._sign + else: # self_adjusted < other_adjusted + return -((-1)**self._sign) + + # Note: The Decimal standard doesn't cover rich comparisons for + # Decimals. In particular, the specification is silent on the + # subject of what should happen for a comparison involving a NaN. + # We take the following approach: + # + # == comparisons involving a quiet NaN always return False + # != comparisons involving a quiet NaN always return True + # == or != comparisons involving a signaling NaN signal + # InvalidOperation, and return False or True as above if the + # InvalidOperation is not trapped. + # <, >, <= and >= comparisons involving a (quiet or signaling) + # NaN signal InvalidOperation, and return False if the + # InvalidOperation is not trapped. + # + # This behavior is designed to conform as closely as possible to + # that specified by IEEE 754. + + def __eq__(self, other, context=None): + self, other = _convert_for_comparison(self, other, equality_op=True) + if other is NotImplemented: + return other + if self._check_nans(other, context): + return False + return self._cmp(other) == 0 + + def __lt__(self, other, context=None): + self, other = _convert_for_comparison(self, other) + if other is NotImplemented: + return other + ans = self._compare_check_nans(other, context) + if ans: + return False + return self._cmp(other) < 0 + + def __le__(self, other, context=None): + self, other = _convert_for_comparison(self, other) + if other is NotImplemented: + return other + ans = self._compare_check_nans(other, context) + if ans: + return False + return self._cmp(other) <= 0 + + def __gt__(self, other, context=None): + self, other = _convert_for_comparison(self, other) + if other is NotImplemented: + return other + ans = self._compare_check_nans(other, context) + if ans: + return False + return self._cmp(other) > 0 + + def __ge__(self, other, context=None): + self, other = _convert_for_comparison(self, other) + if other is NotImplemented: + return other + ans = self._compare_check_nans(other, context) + if ans: + return False + return self._cmp(other) >= 0 + + def compare(self, other, context=None): + """Compares one to another. + + -1 => a < b + 0 => a = b + 1 => a > b + NaN => one is NaN + Like __cmp__, but returns Decimal instances. + """ + other = _convert_other(other, raiseit=True) + + # Compare(NaN, NaN) = NaN + if (self._is_special or other and other._is_special): + ans = self._check_nans(other, context) + if ans: + return ans + + return Decimal(self._cmp(other)) + + def __hash__(self): + """x.__hash__() <==> hash(x)""" + + # In order to make sure that the hash of a Decimal instance + # agrees with the hash of a numerically equal integer, float + # or Fraction, we follow the rules for numeric hashes outlined + # in the documentation. (See library docs, 'Built-in Types'). + if self._is_special: + if self.is_snan(): + raise TypeError('Cannot hash a signaling NaN value.') + elif self.is_nan(): + return _PyHASH_NAN + else: + if self._sign: + return -_PyHASH_INF + else: + return _PyHASH_INF + + if self._exp >= 0: + exp_hash = pow(10, self._exp, _PyHASH_MODULUS) + else: + exp_hash = pow(_PyHASH_10INV, -self._exp, _PyHASH_MODULUS) + hash_ = int(self._int) * exp_hash % _PyHASH_MODULUS + ans = hash_ if self >= 0 else -hash_ + return -2 if ans == -1 else ans + + def as_tuple(self): + """Represents the number as a triple tuple. + + To show the internals exactly as they are. + """ + return DecimalTuple(self._sign, tuple(map(int, self._int)), self._exp) + + def __repr__(self): + """Represents the number as an instance of Decimal.""" + # Invariant: eval(repr(d)) == d + return "Decimal('%s')" % str(self) + + def __str__(self, eng=False, context=None): + """Return string representation of the number in scientific notation. + + Captures all of the information in the underlying representation. + """ + + sign = ['', '-'][self._sign] + if self._is_special: + if self._exp == 'F': + return sign + 'Infinity' + elif self._exp == 'n': + return sign + 'NaN' + self._int + else: # self._exp == 'N' + return sign + 'sNaN' + self._int + + # number of digits of self._int to left of decimal point + leftdigits = self._exp + len(self._int) + + # dotplace is number of digits of self._int to the left of the + # decimal point in the mantissa of the output string (that is, + # after adjusting the exponent) + if self._exp <= 0 and leftdigits > -6: + # no exponent required + dotplace = leftdigits + elif not eng: + # usual scientific notation: 1 digit on left of the point + dotplace = 1 + elif self._int == '0': + # engineering notation, zero + dotplace = (leftdigits + 1) % 3 - 1 + else: + # engineering notation, nonzero + dotplace = (leftdigits - 1) % 3 + 1 + + if dotplace <= 0: + intpart = '0' + fracpart = '.' + '0'*(-dotplace) + self._int + elif dotplace >= len(self._int): + intpart = self._int+'0'*(dotplace-len(self._int)) + fracpart = '' + else: + intpart = self._int[:dotplace] + fracpart = '.' + self._int[dotplace:] + if leftdigits == dotplace: + exp = '' + else: + if context is None: + context = getcontext() + exp = ['e', 'E'][context.capitals] + "%+d" % (leftdigits-dotplace) + + return sign + intpart + fracpart + exp + + def to_eng_string(self, context=None): + """Convert to engineering-type string. + + Engineering notation has an exponent which is a multiple of 3, so there + are up to 3 digits left of the decimal place. + + Same rules for when in exponential and when as a value as in __str__. + """ + return self.__str__(eng=True, context=context) + + def __neg__(self, context=None): + """Returns a copy with the sign switched. + + Rounds, if it has reason. + """ + if self._is_special: + ans = self._check_nans(context=context) + if ans: + return ans + + if context is None: + context = getcontext() + + if not self and context.rounding != ROUND_FLOOR: + # -Decimal('0') is Decimal('0'), not Decimal('-0'), except + # in ROUND_FLOOR rounding mode. + ans = self.copy_abs() + else: + ans = self.copy_negate() + + return ans._fix(context) + + def __pos__(self, context=None): + """Returns a copy, unless it is a sNaN. + + Rounds the number (if more then precision digits) + """ + if self._is_special: + ans = self._check_nans(context=context) + if ans: + return ans + + if context is None: + context = getcontext() + + if not self and context.rounding != ROUND_FLOOR: + # + (-0) = 0, except in ROUND_FLOOR rounding mode. + ans = self.copy_abs() + else: + ans = Decimal(self) + + return ans._fix(context) + + def __abs__(self, round=True, context=None): + """Returns the absolute value of self. + + If the keyword argument 'round' is false, do not round. The + expression self.__abs__(round=False) is equivalent to + self.copy_abs(). + """ + if not round: + return self.copy_abs() + + if self._is_special: + ans = self._check_nans(context=context) + if ans: + return ans + + if self._sign: + ans = self.__neg__(context=context) + else: + ans = self.__pos__(context=context) + + return ans + + def __add__(self, other, context=None): + """Returns self + other. + + -INF + INF (or the reverse) cause InvalidOperation errors. + """ + other = _convert_other(other) + if other is NotImplemented: + return other + + if context is None: + context = getcontext() + + if self._is_special or other._is_special: + ans = self._check_nans(other, context) + if ans: + return ans + + if self._isinfinity(): + # If both INF, same sign => same as both, opposite => error. + if self._sign != other._sign and other._isinfinity(): + return context._raise_error(InvalidOperation, '-INF + INF') + return Decimal(self) + if other._isinfinity(): + return Decimal(other) # Can't both be infinity here + + exp = min(self._exp, other._exp) + negativezero = 0 + if context.rounding == ROUND_FLOOR and self._sign != other._sign: + # If the answer is 0, the sign should be negative, in this case. + negativezero = 1 + + if not self and not other: + sign = min(self._sign, other._sign) + if negativezero: + sign = 1 + ans = _dec_from_triple(sign, '0', exp) + ans = ans._fix(context) + return ans + if not self: + exp = max(exp, other._exp - context.prec-1) + ans = other._rescale(exp, context.rounding) + ans = ans._fix(context) + return ans + if not other: + exp = max(exp, self._exp - context.prec-1) + ans = self._rescale(exp, context.rounding) + ans = ans._fix(context) + return ans + + op1 = _WorkRep(self) + op2 = _WorkRep(other) + op1, op2 = _normalize(op1, op2, context.prec) + + result = _WorkRep() + if op1.sign != op2.sign: + # Equal and opposite + if op1.int == op2.int: + ans = _dec_from_triple(negativezero, '0', exp) + ans = ans._fix(context) + return ans + if op1.int < op2.int: + op1, op2 = op2, op1 + # OK, now abs(op1) > abs(op2) + if op1.sign == 1: + result.sign = 1 + op1.sign, op2.sign = op2.sign, op1.sign + else: + result.sign = 0 + # So we know the sign, and op1 > 0. + elif op1.sign == 1: + result.sign = 1 + op1.sign, op2.sign = (0, 0) + else: + result.sign = 0 + # Now, op1 > abs(op2) > 0 + + if op2.sign == 0: + result.int = op1.int + op2.int + else: + result.int = op1.int - op2.int + + result.exp = op1.exp + ans = Decimal(result) + ans = ans._fix(context) + return ans + + __radd__ = __add__ + + def __sub__(self, other, context=None): + """Return self - other""" + other = _convert_other(other) + if other is NotImplemented: + return other + + if self._is_special or other._is_special: + ans = self._check_nans(other, context=context) + if ans: + return ans + + # self - other is computed as self + other.copy_negate() + return self.__add__(other.copy_negate(), context=context) + + def __rsub__(self, other, context=None): + """Return other - self""" + other = _convert_other(other) + if other is NotImplemented: + return other + + return other.__sub__(self, context=context) + + def __mul__(self, other, context=None): + """Return self * other. + + (+-) INF * 0 (or its reverse) raise InvalidOperation. + """ + other = _convert_other(other) + if other is NotImplemented: + return other + + if context is None: + context = getcontext() + + resultsign = self._sign ^ other._sign + + if self._is_special or other._is_special: + ans = self._check_nans(other, context) + if ans: + return ans + + if self._isinfinity(): + if not other: + return context._raise_error(InvalidOperation, '(+-)INF * 0') + return _SignedInfinity[resultsign] + + if other._isinfinity(): + if not self: + return context._raise_error(InvalidOperation, '0 * (+-)INF') + return _SignedInfinity[resultsign] + + resultexp = self._exp + other._exp + + # Special case for multiplying by zero + if not self or not other: + ans = _dec_from_triple(resultsign, '0', resultexp) + # Fixing in case the exponent is out of bounds + ans = ans._fix(context) + return ans + + # Special case for multiplying by power of 10 + if self._int == '1': + ans = _dec_from_triple(resultsign, other._int, resultexp) + ans = ans._fix(context) + return ans + if other._int == '1': + ans = _dec_from_triple(resultsign, self._int, resultexp) + ans = ans._fix(context) + return ans + + op1 = _WorkRep(self) + op2 = _WorkRep(other) + + ans = _dec_from_triple(resultsign, str(op1.int * op2.int), resultexp) + ans = ans._fix(context) + + return ans + __rmul__ = __mul__ + + def __truediv__(self, other, context=None): + """Return self / other.""" + other = _convert_other(other) + if other is NotImplemented: + return NotImplemented + + if context is None: + context = getcontext() + + sign = self._sign ^ other._sign + + if self._is_special or other._is_special: + ans = self._check_nans(other, context) + if ans: + return ans + + if self._isinfinity() and other._isinfinity(): + return context._raise_error(InvalidOperation, '(+-)INF/(+-)INF') + + if self._isinfinity(): + return _SignedInfinity[sign] + + if other._isinfinity(): + context._raise_error(Clamped, 'Division by infinity') + return _dec_from_triple(sign, '0', context.Etiny()) + + # Special cases for zeroes + if not other: + if not self: + return context._raise_error(DivisionUndefined, '0 / 0') + return context._raise_error(DivisionByZero, 'x / 0', sign) + + if not self: + exp = self._exp - other._exp + coeff = 0 + else: + # OK, so neither = 0, INF or NaN + shift = len(other._int) - len(self._int) + context.prec + 1 + exp = self._exp - other._exp - shift + op1 = _WorkRep(self) + op2 = _WorkRep(other) + if shift >= 0: + coeff, remainder = divmod(op1.int * 10**shift, op2.int) + else: + coeff, remainder = divmod(op1.int, op2.int * 10**-shift) + if remainder: + # result is not exact; adjust to ensure correct rounding + if coeff % 5 == 0: + coeff += 1 + else: + # result is exact; get as close to ideal exponent as possible + ideal_exp = self._exp - other._exp + while exp < ideal_exp and coeff % 10 == 0: + coeff //= 10 + exp += 1 + + ans = _dec_from_triple(sign, str(coeff), exp) + return ans._fix(context) + + def _divide(self, other, context): + """Return (self // other, self % other), to context.prec precision. + + Assumes that neither self nor other is a NaN, that self is not + infinite and that other is nonzero. + """ + sign = self._sign ^ other._sign + if other._isinfinity(): + ideal_exp = self._exp + else: + ideal_exp = min(self._exp, other._exp) + + expdiff = self.adjusted() - other.adjusted() + if not self or other._isinfinity() or expdiff <= -2: + return (_dec_from_triple(sign, '0', 0), + self._rescale(ideal_exp, context.rounding)) + if expdiff <= context.prec: + op1 = _WorkRep(self) + op2 = _WorkRep(other) + if op1.exp >= op2.exp: + op1.int *= 10**(op1.exp - op2.exp) + else: + op2.int *= 10**(op2.exp - op1.exp) + q, r = divmod(op1.int, op2.int) + if q < 10**context.prec: + return (_dec_from_triple(sign, str(q), 0), + _dec_from_triple(self._sign, str(r), ideal_exp)) + + # Here the quotient is too large to be representable + ans = context._raise_error(DivisionImpossible, + 'quotient too large in //, % or divmod') + return ans, ans + + def __rtruediv__(self, other, context=None): + """Swaps self/other and returns __truediv__.""" + other = _convert_other(other) + if other is NotImplemented: + return other + return other.__truediv__(self, context=context) + + def __divmod__(self, other, context=None): + """ + Return (self // other, self % other) + """ + other = _convert_other(other) + if other is NotImplemented: + return other + + if context is None: + context = getcontext() + + ans = self._check_nans(other, context) + if ans: + return (ans, ans) + + sign = self._sign ^ other._sign + if self._isinfinity(): + if other._isinfinity(): + ans = context._raise_error(InvalidOperation, 'divmod(INF, INF)') + return ans, ans + else: + return (_SignedInfinity[sign], + context._raise_error(InvalidOperation, 'INF % x')) + + if not other: + if not self: + ans = context._raise_error(DivisionUndefined, 'divmod(0, 0)') + return ans, ans + else: + return (context._raise_error(DivisionByZero, 'x // 0', sign), + context._raise_error(InvalidOperation, 'x % 0')) + + quotient, remainder = self._divide(other, context) + remainder = remainder._fix(context) + return quotient, remainder + + def __rdivmod__(self, other, context=None): + """Swaps self/other and returns __divmod__.""" + other = _convert_other(other) + if other is NotImplemented: + return other + return other.__divmod__(self, context=context) + + def __mod__(self, other, context=None): + """ + self % other + """ + other = _convert_other(other) + if other is NotImplemented: + return other + + if context is None: + context = getcontext() + + ans = self._check_nans(other, context) + if ans: + return ans + + if self._isinfinity(): + return context._raise_error(InvalidOperation, 'INF % x') + elif not other: + if self: + return context._raise_error(InvalidOperation, 'x % 0') + else: + return context._raise_error(DivisionUndefined, '0 % 0') + + remainder = self._divide(other, context)[1] + remainder = remainder._fix(context) + return remainder + + def __rmod__(self, other, context=None): + """Swaps self/other and returns __mod__.""" + other = _convert_other(other) + if other is NotImplemented: + return other + return other.__mod__(self, context=context) + + def remainder_near(self, other, context=None): + """ + Remainder nearest to 0- abs(remainder-near) <= other/2 + """ + if context is None: + context = getcontext() + + other = _convert_other(other, raiseit=True) + + ans = self._check_nans(other, context) + if ans: + return ans + + # self == +/-infinity -> InvalidOperation + if self._isinfinity(): + return context._raise_error(InvalidOperation, + 'remainder_near(infinity, x)') + + # other == 0 -> either InvalidOperation or DivisionUndefined + if not other: + if self: + return context._raise_error(InvalidOperation, + 'remainder_near(x, 0)') + else: + return context._raise_error(DivisionUndefined, + 'remainder_near(0, 0)') + + # other = +/-infinity -> remainder = self + if other._isinfinity(): + ans = Decimal(self) + return ans._fix(context) + + # self = 0 -> remainder = self, with ideal exponent + ideal_exponent = min(self._exp, other._exp) + if not self: + ans = _dec_from_triple(self._sign, '0', ideal_exponent) + return ans._fix(context) + + # catch most cases of large or small quotient + expdiff = self.adjusted() - other.adjusted() + if expdiff >= context.prec + 1: + # expdiff >= prec+1 => abs(self/other) > 10**prec + return context._raise_error(DivisionImpossible) + if expdiff <= -2: + # expdiff <= -2 => abs(self/other) < 0.1 + ans = self._rescale(ideal_exponent, context.rounding) + return ans._fix(context) + + # adjust both arguments to have the same exponent, then divide + op1 = _WorkRep(self) + op2 = _WorkRep(other) + if op1.exp >= op2.exp: + op1.int *= 10**(op1.exp - op2.exp) + else: + op2.int *= 10**(op2.exp - op1.exp) + q, r = divmod(op1.int, op2.int) + # remainder is r*10**ideal_exponent; other is +/-op2.int * + # 10**ideal_exponent. Apply correction to ensure that + # abs(remainder) <= abs(other)/2 + if 2*r + (q&1) > op2.int: + r -= op2.int + q += 1 + + if q >= 10**context.prec: + return context._raise_error(DivisionImpossible) + + # result has same sign as self unless r is negative + sign = self._sign + if r < 0: + sign = 1-sign + r = -r + + ans = _dec_from_triple(sign, str(r), ideal_exponent) + return ans._fix(context) + + def __floordiv__(self, other, context=None): + """self // other""" + other = _convert_other(other) + if other is NotImplemented: + return other + + if context is None: + context = getcontext() + + ans = self._check_nans(other, context) + if ans: + return ans + + if self._isinfinity(): + if other._isinfinity(): + return context._raise_error(InvalidOperation, 'INF // INF') + else: + return _SignedInfinity[self._sign ^ other._sign] + + if not other: + if self: + return context._raise_error(DivisionByZero, 'x // 0', + self._sign ^ other._sign) + else: + return context._raise_error(DivisionUndefined, '0 // 0') + + return self._divide(other, context)[0] + + def __rfloordiv__(self, other, context=None): + """Swaps self/other and returns __floordiv__.""" + other = _convert_other(other) + if other is NotImplemented: + return other + return other.__floordiv__(self, context=context) + + def __float__(self): + """Float representation.""" + if self._isnan(): + if self.is_snan(): + raise ValueError("Cannot convert signaling NaN to float") + s = "-nan" if self._sign else "nan" + else: + s = str(self) + return float(s) + + def __int__(self): + """Converts self to an int, truncating if necessary.""" + if self._is_special: + if self._isnan(): + raise ValueError("Cannot convert NaN to integer") + elif self._isinfinity(): + raise OverflowError("Cannot convert infinity to integer") + s = (-1)**self._sign + if self._exp >= 0: + return s*int(self._int)*10**self._exp + else: + return s*int(self._int[:self._exp] or '0') + + __trunc__ = __int__ + + def real(self): + return self + real = property(real) + + def imag(self): + return Decimal(0) + imag = property(imag) + + def conjugate(self): + return self + + def __complex__(self): + return complex(float(self)) + + def _fix_nan(self, context): + """Decapitate the payload of a NaN to fit the context""" + payload = self._int + + # maximum length of payload is precision if clamp=0, + # precision-1 if clamp=1. + max_payload_len = context.prec - context.clamp + if len(payload) > max_payload_len: + payload = payload[len(payload)-max_payload_len:].lstrip('0') + return _dec_from_triple(self._sign, payload, self._exp, True) + return Decimal(self) + + def _fix(self, context): + """Round if it is necessary to keep self within prec precision. + + Rounds and fixes the exponent. Does not raise on a sNaN. + + Arguments: + self - Decimal instance + context - context used. + """ + + if self._is_special: + if self._isnan(): + # decapitate payload if necessary + return self._fix_nan(context) + else: + # self is +/-Infinity; return unaltered + return Decimal(self) + + # if self is zero then exponent should be between Etiny and + # Emax if clamp==0, and between Etiny and Etop if clamp==1. + Etiny = context.Etiny() + Etop = context.Etop() + if not self: + exp_max = [context.Emax, Etop][context.clamp] + new_exp = min(max(self._exp, Etiny), exp_max) + if new_exp != self._exp: + context._raise_error(Clamped) + return _dec_from_triple(self._sign, '0', new_exp) + else: + return Decimal(self) + + # exp_min is the smallest allowable exponent of the result, + # equal to max(self.adjusted()-context.prec+1, Etiny) + exp_min = len(self._int) + self._exp - context.prec + if exp_min > Etop: + # overflow: exp_min > Etop iff self.adjusted() > Emax + ans = context._raise_error(Overflow, 'above Emax', self._sign) + context._raise_error(Inexact) + context._raise_error(Rounded) + return ans + + self_is_subnormal = exp_min < Etiny + if self_is_subnormal: + exp_min = Etiny + + # round if self has too many digits + if self._exp < exp_min: + digits = len(self._int) + self._exp - exp_min + if digits < 0: + self = _dec_from_triple(self._sign, '1', exp_min-1) + digits = 0 + rounding_method = self._pick_rounding_function[context.rounding] + changed = rounding_method(self, digits) + coeff = self._int[:digits] or '0' + if changed > 0: + coeff = str(int(coeff)+1) + if len(coeff) > context.prec: + coeff = coeff[:-1] + exp_min += 1 + + # check whether the rounding pushed the exponent out of range + if exp_min > Etop: + ans = context._raise_error(Overflow, 'above Emax', self._sign) + else: + ans = _dec_from_triple(self._sign, coeff, exp_min) + + # raise the appropriate signals, taking care to respect + # the precedence described in the specification + if changed and self_is_subnormal: + context._raise_error(Underflow) + if self_is_subnormal: + context._raise_error(Subnormal) + if changed: + context._raise_error(Inexact) + context._raise_error(Rounded) + if not ans: + # raise Clamped on underflow to 0 + context._raise_error(Clamped) + return ans + + if self_is_subnormal: + context._raise_error(Subnormal) + + # fold down if clamp == 1 and self has too few digits + if context.clamp == 1 and self._exp > Etop: + context._raise_error(Clamped) + self_padded = self._int + '0'*(self._exp - Etop) + return _dec_from_triple(self._sign, self_padded, Etop) + + # here self was representable to begin with; return unchanged + return Decimal(self) + + # for each of the rounding functions below: + # self is a finite, nonzero Decimal + # prec is an integer satisfying 0 <= prec < len(self._int) + # + # each function returns either -1, 0, or 1, as follows: + # 1 indicates that self should be rounded up (away from zero) + # 0 indicates that self should be truncated, and that all the + # digits to be truncated are zeros (so the value is unchanged) + # -1 indicates that there are nonzero digits to be truncated + + def _round_down(self, prec): + """Also known as round-towards-0, truncate.""" + if _all_zeros(self._int, prec): + return 0 + else: + return -1 + + def _round_up(self, prec): + """Rounds away from 0.""" + return -self._round_down(prec) + + def _round_half_up(self, prec): + """Rounds 5 up (away from 0)""" + if self._int[prec] in '56789': + return 1 + elif _all_zeros(self._int, prec): + return 0 + else: + return -1 + + def _round_half_down(self, prec): + """Round 5 down""" + if _exact_half(self._int, prec): + return -1 + else: + return self._round_half_up(prec) + + def _round_half_even(self, prec): + """Round 5 to even, rest to nearest.""" + if _exact_half(self._int, prec) and \ + (prec == 0 or self._int[prec-1] in '02468'): + return -1 + else: + return self._round_half_up(prec) + + def _round_ceiling(self, prec): + """Rounds up (not away from 0 if negative.)""" + if self._sign: + return self._round_down(prec) + else: + return -self._round_down(prec) + + def _round_floor(self, prec): + """Rounds down (not towards 0 if negative)""" + if not self._sign: + return self._round_down(prec) + else: + return -self._round_down(prec) + + def _round_05up(self, prec): + """Round down unless digit prec-1 is 0 or 5.""" + if prec and self._int[prec-1] not in '05': + return self._round_down(prec) + else: + return -self._round_down(prec) + + _pick_rounding_function = dict( + ROUND_DOWN = _round_down, + ROUND_UP = _round_up, + ROUND_HALF_UP = _round_half_up, + ROUND_HALF_DOWN = _round_half_down, + ROUND_HALF_EVEN = _round_half_even, + ROUND_CEILING = _round_ceiling, + ROUND_FLOOR = _round_floor, + ROUND_05UP = _round_05up, + ) + + def __round__(self, n=None): + """Round self to the nearest integer, or to a given precision. + + If only one argument is supplied, round a finite Decimal + instance self to the nearest integer. If self is infinite or + a NaN then a Python exception is raised. If self is finite + and lies exactly halfway between two integers then it is + rounded to the integer with even last digit. + + >>> round(Decimal('123.456')) + 123 + >>> round(Decimal('-456.789')) + -457 + >>> round(Decimal('-3.0')) + -3 + >>> round(Decimal('2.5')) + 2 + >>> round(Decimal('3.5')) + 4 + >>> round(Decimal('Inf')) + Traceback (most recent call last): + ... + OverflowError: cannot round an infinity + >>> round(Decimal('NaN')) + Traceback (most recent call last): + ... + ValueError: cannot round a NaN + + If a second argument n is supplied, self is rounded to n + decimal places using the rounding mode for the current + context. + + For an integer n, round(self, -n) is exactly equivalent to + self.quantize(Decimal('1En')). + + >>> round(Decimal('123.456'), 0) + Decimal('123') + >>> round(Decimal('123.456'), 2) + Decimal('123.46') + >>> round(Decimal('123.456'), -2) + Decimal('1E+2') + >>> round(Decimal('-Infinity'), 37) + Decimal('NaN') + >>> round(Decimal('sNaN123'), 0) + Decimal('NaN123') + + """ + if n is not None: + # two-argument form: use the equivalent quantize call + if not isinstance(n, int): + raise TypeError('Second argument to round should be integral') + exp = _dec_from_triple(0, '1', -n) + return self.quantize(exp) + + # one-argument form + if self._is_special: + if self.is_nan(): + raise ValueError("cannot round a NaN") + else: + raise OverflowError("cannot round an infinity") + return int(self._rescale(0, ROUND_HALF_EVEN)) + + def __floor__(self): + """Return the floor of self, as an integer. + + For a finite Decimal instance self, return the greatest + integer n such that n <= self. If self is infinite or a NaN + then a Python exception is raised. + + """ + if self._is_special: + if self.is_nan(): + raise ValueError("cannot round a NaN") + else: + raise OverflowError("cannot round an infinity") + return int(self._rescale(0, ROUND_FLOOR)) + + def __ceil__(self): + """Return the ceiling of self, as an integer. + + For a finite Decimal instance self, return the least integer n + such that n >= self. If self is infinite or a NaN then a + Python exception is raised. + + """ + if self._is_special: + if self.is_nan(): + raise ValueError("cannot round a NaN") + else: + raise OverflowError("cannot round an infinity") + return int(self._rescale(0, ROUND_CEILING)) + + def fma(self, other, third, context=None): + """Fused multiply-add. + + Returns self*other+third with no rounding of the intermediate + product self*other. + + self and other are multiplied together, with no rounding of + the result. The third operand is then added to the result, + and a single final rounding is performed. + """ + + other = _convert_other(other, raiseit=True) + third = _convert_other(third, raiseit=True) + + # compute product; raise InvalidOperation if either operand is + # a signaling NaN or if the product is zero times infinity. + if self._is_special or other._is_special: + if context is None: + context = getcontext() + if self._exp == 'N': + return context._raise_error(InvalidOperation, 'sNaN', self) + if other._exp == 'N': + return context._raise_error(InvalidOperation, 'sNaN', other) + if self._exp == 'n': + product = self + elif other._exp == 'n': + product = other + elif self._exp == 'F': + if not other: + return context._raise_error(InvalidOperation, + 'INF * 0 in fma') + product = _SignedInfinity[self._sign ^ other._sign] + elif other._exp == 'F': + if not self: + return context._raise_error(InvalidOperation, + '0 * INF in fma') + product = _SignedInfinity[self._sign ^ other._sign] + else: + product = _dec_from_triple(self._sign ^ other._sign, + str(int(self._int) * int(other._int)), + self._exp + other._exp) + + return product.__add__(third, context) + + def _power_modulo(self, other, modulo, context=None): + """Three argument version of __pow__""" + + other = _convert_other(other) + if other is NotImplemented: + return other + modulo = _convert_other(modulo) + if modulo is NotImplemented: + return modulo + + if context is None: + context = getcontext() + + # deal with NaNs: if there are any sNaNs then first one wins, + # (i.e. behaviour for NaNs is identical to that of fma) + self_is_nan = self._isnan() + other_is_nan = other._isnan() + modulo_is_nan = modulo._isnan() + if self_is_nan or other_is_nan or modulo_is_nan: + if self_is_nan == 2: + return context._raise_error(InvalidOperation, 'sNaN', + self) + if other_is_nan == 2: + return context._raise_error(InvalidOperation, 'sNaN', + other) + if modulo_is_nan == 2: + return context._raise_error(InvalidOperation, 'sNaN', + modulo) + if self_is_nan: + return self._fix_nan(context) + if other_is_nan: + return other._fix_nan(context) + return modulo._fix_nan(context) + + # check inputs: we apply same restrictions as Python's pow() + if not (self._isinteger() and + other._isinteger() and + modulo._isinteger()): + return context._raise_error(InvalidOperation, + 'pow() 3rd argument not allowed ' + 'unless all arguments are integers') + if other < 0: + return context._raise_error(InvalidOperation, + 'pow() 2nd argument cannot be ' + 'negative when 3rd argument specified') + if not modulo: + return context._raise_error(InvalidOperation, + 'pow() 3rd argument cannot be 0') + + # additional restriction for decimal: the modulus must be less + # than 10**prec in absolute value + if modulo.adjusted() >= context.prec: + return context._raise_error(InvalidOperation, + 'insufficient precision: pow() 3rd ' + 'argument must not have more than ' + 'precision digits') + + # define 0**0 == NaN, for consistency with two-argument pow + # (even though it hurts!) + if not other and not self: + return context._raise_error(InvalidOperation, + 'at least one of pow() 1st argument ' + 'and 2nd argument must be nonzero ;' + '0**0 is not defined') + + # compute sign of result + if other._iseven(): + sign = 0 + else: + sign = self._sign + + # convert modulo to a Python integer, and self and other to + # Decimal integers (i.e. force their exponents to be >= 0) + modulo = abs(int(modulo)) + base = _WorkRep(self.to_integral_value()) + exponent = _WorkRep(other.to_integral_value()) + + # compute result using integer pow() + base = (base.int % modulo * pow(10, base.exp, modulo)) % modulo + for i in range(exponent.exp): + base = pow(base, 10, modulo) + base = pow(base, exponent.int, modulo) + + return _dec_from_triple(sign, str(base), 0) + + def _power_exact(self, other, p): + """Attempt to compute self**other exactly. + + Given Decimals self and other and an integer p, attempt to + compute an exact result for the power self**other, with p + digits of precision. Return None if self**other is not + exactly representable in p digits. + + Assumes that elimination of special cases has already been + performed: self and other must both be nonspecial; self must + be positive and not numerically equal to 1; other must be + nonzero. For efficiency, other._exp should not be too large, + so that 10**abs(other._exp) is a feasible calculation.""" + + # In the comments below, we write x for the value of self and y for the + # value of other. Write x = xc*10**xe and abs(y) = yc*10**ye, with xc + # and yc positive integers not divisible by 10. + + # The main purpose of this method is to identify the *failure* + # of x**y to be exactly representable with as little effort as + # possible. So we look for cheap and easy tests that + # eliminate the possibility of x**y being exact. Only if all + # these tests are passed do we go on to actually compute x**y. + + # Here's the main idea. Express y as a rational number m/n, with m and + # n relatively prime and n>0. Then for x**y to be exactly + # representable (at *any* precision), xc must be the nth power of a + # positive integer and xe must be divisible by n. If y is negative + # then additionally xc must be a power of either 2 or 5, hence a power + # of 2**n or 5**n. + # + # There's a limit to how small |y| can be: if y=m/n as above + # then: + # + # (1) if xc != 1 then for the result to be representable we + # need xc**(1/n) >= 2, and hence also xc**|y| >= 2. So + # if |y| <= 1/nbits(xc) then xc < 2**nbits(xc) <= + # 2**(1/|y|), hence xc**|y| < 2 and the result is not + # representable. + # + # (2) if xe != 0, |xe|*(1/n) >= 1, so |xe|*|y| >= 1. Hence if + # |y| < 1/|xe| then the result is not representable. + # + # Note that since x is not equal to 1, at least one of (1) and + # (2) must apply. Now |y| < 1/nbits(xc) iff |yc|*nbits(xc) < + # 10**-ye iff len(str(|yc|*nbits(xc)) <= -ye. + # + # There's also a limit to how large y can be, at least if it's + # positive: the normalized result will have coefficient xc**y, + # so if it's representable then xc**y < 10**p, and y < + # p/log10(xc). Hence if y*log10(xc) >= p then the result is + # not exactly representable. + + # if len(str(abs(yc*xe)) <= -ye then abs(yc*xe) < 10**-ye, + # so |y| < 1/xe and the result is not representable. + # Similarly, len(str(abs(yc)*xc_bits)) <= -ye implies |y| + # < 1/nbits(xc). + + x = _WorkRep(self) + xc, xe = x.int, x.exp + while xc % 10 == 0: + xc //= 10 + xe += 1 + + y = _WorkRep(other) + yc, ye = y.int, y.exp + while yc % 10 == 0: + yc //= 10 + ye += 1 + + # case where xc == 1: result is 10**(xe*y), with xe*y + # required to be an integer + if xc == 1: + xe *= yc + # result is now 10**(xe * 10**ye); xe * 10**ye must be integral + while xe % 10 == 0: + xe //= 10 + ye += 1 + if ye < 0: + return None + exponent = xe * 10**ye + if y.sign == 1: + exponent = -exponent + # if other is a nonnegative integer, use ideal exponent + if other._isinteger() and other._sign == 0: + ideal_exponent = self._exp*int(other) + zeros = min(exponent-ideal_exponent, p-1) + else: + zeros = 0 + return _dec_from_triple(0, '1' + '0'*zeros, exponent-zeros) + + # case where y is negative: xc must be either a power + # of 2 or a power of 5. + if y.sign == 1: + last_digit = xc % 10 + if last_digit in (2,4,6,8): + # quick test for power of 2 + if xc & -xc != xc: + return None + # now xc is a power of 2; e is its exponent + e = _nbits(xc)-1 + + # We now have: + # + # x = 2**e * 10**xe, e > 0, and y < 0. + # + # The exact result is: + # + # x**y = 5**(-e*y) * 10**(e*y + xe*y) + # + # provided that both e*y and xe*y are integers. Note that if + # 5**(-e*y) >= 10**p, then the result can't be expressed + # exactly with p digits of precision. + # + # Using the above, we can guard against large values of ye. + # 93/65 is an upper bound for log(10)/log(5), so if + # + # ye >= len(str(93*p//65)) + # + # then + # + # -e*y >= -y >= 10**ye > 93*p/65 > p*log(10)/log(5), + # + # so 5**(-e*y) >= 10**p, and the coefficient of the result + # can't be expressed in p digits. + + # emax >= largest e such that 5**e < 10**p. + emax = p*93//65 + if ye >= len(str(emax)): + return None + + # Find -e*y and -xe*y; both must be integers + e = _decimal_lshift_exact(e * yc, ye) + xe = _decimal_lshift_exact(xe * yc, ye) + if e is None or xe is None: + return None + + if e > emax: + return None + xc = 5**e + + elif last_digit == 5: + # e >= log_5(xc) if xc is a power of 5; we have + # equality all the way up to xc=5**2658 + e = _nbits(xc)*28//65 + xc, remainder = divmod(5**e, xc) + if remainder: + return None + while xc % 5 == 0: + xc //= 5 + e -= 1 + + # Guard against large values of ye, using the same logic as in + # the 'xc is a power of 2' branch. 10/3 is an upper bound for + # log(10)/log(2). + emax = p*10//3 + if ye >= len(str(emax)): + return None + + e = _decimal_lshift_exact(e * yc, ye) + xe = _decimal_lshift_exact(xe * yc, ye) + if e is None or xe is None: + return None + + if e > emax: + return None + xc = 2**e + else: + return None + + if xc >= 10**p: + return None + xe = -e-xe + return _dec_from_triple(0, str(xc), xe) + + # now y is positive; find m and n such that y = m/n + if ye >= 0: + m, n = yc*10**ye, 1 + else: + if xe != 0 and len(str(abs(yc*xe))) <= -ye: + return None + xc_bits = _nbits(xc) + if xc != 1 and len(str(abs(yc)*xc_bits)) <= -ye: + return None + m, n = yc, 10**(-ye) + while m % 2 == n % 2 == 0: + m //= 2 + n //= 2 + while m % 5 == n % 5 == 0: + m //= 5 + n //= 5 + + # compute nth root of xc*10**xe + if n > 1: + # if 1 < xc < 2**n then xc isn't an nth power + if xc != 1 and xc_bits <= n: + return None + + xe, rem = divmod(xe, n) + if rem != 0: + return None + + # compute nth root of xc using Newton's method + a = 1 << -(-_nbits(xc)//n) # initial estimate + while True: + q, r = divmod(xc, a**(n-1)) + if a <= q: + break + else: + a = (a*(n-1) + q)//n + if not (a == q and r == 0): + return None + xc = a + + # now xc*10**xe is the nth root of the original xc*10**xe + # compute mth power of xc*10**xe + + # if m > p*100//_log10_lb(xc) then m > p/log10(xc), hence xc**m > + # 10**p and the result is not representable. + if xc > 1 and m > p*100//_log10_lb(xc): + return None + xc = xc**m + xe *= m + if xc > 10**p: + return None + + # by this point the result *is* exactly representable + # adjust the exponent to get as close as possible to the ideal + # exponent, if necessary + str_xc = str(xc) + if other._isinteger() and other._sign == 0: + ideal_exponent = self._exp*int(other) + zeros = min(xe-ideal_exponent, p-len(str_xc)) + else: + zeros = 0 + return _dec_from_triple(0, str_xc+'0'*zeros, xe-zeros) + + def __pow__(self, other, modulo=None, context=None): + """Return self ** other [ % modulo]. + + With two arguments, compute self**other. + + With three arguments, compute (self**other) % modulo. For the + three argument form, the following restrictions on the + arguments hold: + + - all three arguments must be integral + - other must be nonnegative + - either self or other (or both) must be nonzero + - modulo must be nonzero and must have at most p digits, + where p is the context precision. + + If any of these restrictions is violated the InvalidOperation + flag is raised. + + The result of pow(self, other, modulo) is identical to the + result that would be obtained by computing (self**other) % + modulo with unbounded precision, but is computed more + efficiently. It is always exact. + """ + + if modulo is not None: + return self._power_modulo(other, modulo, context) + + other = _convert_other(other) + if other is NotImplemented: + return other + + if context is None: + context = getcontext() + + # either argument is a NaN => result is NaN + ans = self._check_nans(other, context) + if ans: + return ans + + # 0**0 = NaN (!), x**0 = 1 for nonzero x (including +/-Infinity) + if not other: + if not self: + return context._raise_error(InvalidOperation, '0 ** 0') + else: + return _One + + # result has sign 1 iff self._sign is 1 and other is an odd integer + result_sign = 0 + if self._sign == 1: + if other._isinteger(): + if not other._iseven(): + result_sign = 1 + else: + # -ve**noninteger = NaN + # (-0)**noninteger = 0**noninteger + if self: + return context._raise_error(InvalidOperation, + 'x ** y with x negative and y not an integer') + # negate self, without doing any unwanted rounding + self = self.copy_negate() + + # 0**(+ve or Inf)= 0; 0**(-ve or -Inf) = Infinity + if not self: + if other._sign == 0: + return _dec_from_triple(result_sign, '0', 0) + else: + return _SignedInfinity[result_sign] + + # Inf**(+ve or Inf) = Inf; Inf**(-ve or -Inf) = 0 + if self._isinfinity(): + if other._sign == 0: + return _SignedInfinity[result_sign] + else: + return _dec_from_triple(result_sign, '0', 0) + + # 1**other = 1, but the choice of exponent and the flags + # depend on the exponent of self, and on whether other is a + # positive integer, a negative integer, or neither + if self == _One: + if other._isinteger(): + # exp = max(self._exp*max(int(other), 0), + # 1-context.prec) but evaluating int(other) directly + # is dangerous until we know other is small (other + # could be 1e999999999) + if other._sign == 1: + multiplier = 0 + elif other > context.prec: + multiplier = context.prec + else: + multiplier = int(other) + + exp = self._exp * multiplier + if exp < 1-context.prec: + exp = 1-context.prec + context._raise_error(Rounded) + else: + context._raise_error(Inexact) + context._raise_error(Rounded) + exp = 1-context.prec + + return _dec_from_triple(result_sign, '1'+'0'*-exp, exp) + + # compute adjusted exponent of self + self_adj = self.adjusted() + + # self ** infinity is infinity if self > 1, 0 if self < 1 + # self ** -infinity is infinity if self < 1, 0 if self > 1 + if other._isinfinity(): + if (other._sign == 0) == (self_adj < 0): + return _dec_from_triple(result_sign, '0', 0) + else: + return _SignedInfinity[result_sign] + + # from here on, the result always goes through the call + # to _fix at the end of this function. + ans = None + exact = False + + # crude test to catch cases of extreme overflow/underflow. If + # log10(self)*other >= 10**bound and bound >= len(str(Emax)) + # then 10**bound >= 10**len(str(Emax)) >= Emax+1 and hence + # self**other >= 10**(Emax+1), so overflow occurs. The test + # for underflow is similar. + bound = self._log10_exp_bound() + other.adjusted() + if (self_adj >= 0) == (other._sign == 0): + # self > 1 and other +ve, or self < 1 and other -ve + # possibility of overflow + if bound >= len(str(context.Emax)): + ans = _dec_from_triple(result_sign, '1', context.Emax+1) + else: + # self > 1 and other -ve, or self < 1 and other +ve + # possibility of underflow to 0 + Etiny = context.Etiny() + if bound >= len(str(-Etiny)): + ans = _dec_from_triple(result_sign, '1', Etiny-1) + + # try for an exact result with precision +1 + if ans is None: + ans = self._power_exact(other, context.prec + 1) + if ans is not None: + if result_sign == 1: + ans = _dec_from_triple(1, ans._int, ans._exp) + exact = True + + # usual case: inexact result, x**y computed directly as exp(y*log(x)) + if ans is None: + p = context.prec + x = _WorkRep(self) + xc, xe = x.int, x.exp + y = _WorkRep(other) + yc, ye = y.int, y.exp + if y.sign == 1: + yc = -yc + + # compute correctly rounded result: start with precision +3, + # then increase precision until result is unambiguously roundable + extra = 3 + while True: + coeff, exp = _dpower(xc, xe, yc, ye, p+extra) + if coeff % (5*10**(len(str(coeff))-p-1)): + break + extra += 3 + + ans = _dec_from_triple(result_sign, str(coeff), exp) + + # unlike exp, ln and log10, the power function respects the + # rounding mode; no need to switch to ROUND_HALF_EVEN here + + # There's a difficulty here when 'other' is not an integer and + # the result is exact. In this case, the specification + # requires that the Inexact flag be raised (in spite of + # exactness), but since the result is exact _fix won't do this + # for us. (Correspondingly, the Underflow signal should also + # be raised for subnormal results.) We can't directly raise + # these signals either before or after calling _fix, since + # that would violate the precedence for signals. So we wrap + # the ._fix call in a temporary context, and reraise + # afterwards. + if exact and not other._isinteger(): + # pad with zeros up to length context.prec+1 if necessary; this + # ensures that the Rounded signal will be raised. + if len(ans._int) <= context.prec: + expdiff = context.prec + 1 - len(ans._int) + ans = _dec_from_triple(ans._sign, ans._int+'0'*expdiff, + ans._exp-expdiff) + + # create a copy of the current context, with cleared flags/traps + newcontext = context.copy() + newcontext.clear_flags() + for exception in _signals: + newcontext.traps[exception] = 0 + + # round in the new context + ans = ans._fix(newcontext) + + # raise Inexact, and if necessary, Underflow + newcontext._raise_error(Inexact) + if newcontext.flags[Subnormal]: + newcontext._raise_error(Underflow) + + # propagate signals to the original context; _fix could + # have raised any of Overflow, Underflow, Subnormal, + # Inexact, Rounded, Clamped. Overflow needs the correct + # arguments. Note that the order of the exceptions is + # important here. + if newcontext.flags[Overflow]: + context._raise_error(Overflow, 'above Emax', ans._sign) + for exception in Underflow, Subnormal, Inexact, Rounded, Clamped: + if newcontext.flags[exception]: + context._raise_error(exception) + + else: + ans = ans._fix(context) + + return ans + + def __rpow__(self, other, context=None): + """Swaps self/other and returns __pow__.""" + other = _convert_other(other) + if other is NotImplemented: + return other + return other.__pow__(self, context=context) + + def normalize(self, context=None): + """Normalize- strip trailing 0s, change anything equal to 0 to 0e0""" + + if context is None: + context = getcontext() + + if self._is_special: + ans = self._check_nans(context=context) + if ans: + return ans + + dup = self._fix(context) + if dup._isinfinity(): + return dup + + if not dup: + return _dec_from_triple(dup._sign, '0', 0) + exp_max = [context.Emax, context.Etop()][context.clamp] + end = len(dup._int) + exp = dup._exp + while dup._int[end-1] == '0' and exp < exp_max: + exp += 1 + end -= 1 + return _dec_from_triple(dup._sign, dup._int[:end], exp) + + def quantize(self, exp, rounding=None, context=None): + """Quantize self so its exponent is the same as that of exp. + + Similar to self._rescale(exp._exp) but with error checking. + """ + exp = _convert_other(exp, raiseit=True) + + if context is None: + context = getcontext() + if rounding is None: + rounding = context.rounding + + if self._is_special or exp._is_special: + ans = self._check_nans(exp, context) + if ans: + return ans + + if exp._isinfinity() or self._isinfinity(): + if exp._isinfinity() and self._isinfinity(): + return Decimal(self) # if both are inf, it is OK + return context._raise_error(InvalidOperation, + 'quantize with one INF') + + # exp._exp should be between Etiny and Emax + if not (context.Etiny() <= exp._exp <= context.Emax): + return context._raise_error(InvalidOperation, + 'target exponent out of bounds in quantize') + + if not self: + ans = _dec_from_triple(self._sign, '0', exp._exp) + return ans._fix(context) + + self_adjusted = self.adjusted() + if self_adjusted > context.Emax: + return context._raise_error(InvalidOperation, + 'exponent of quantize result too large for current context') + if self_adjusted - exp._exp + 1 > context.prec: + return context._raise_error(InvalidOperation, + 'quantize result has too many digits for current context') + + ans = self._rescale(exp._exp, rounding) + if ans.adjusted() > context.Emax: + return context._raise_error(InvalidOperation, + 'exponent of quantize result too large for current context') + if len(ans._int) > context.prec: + return context._raise_error(InvalidOperation, + 'quantize result has too many digits for current context') + + # raise appropriate flags + if ans and ans.adjusted() < context.Emin: + context._raise_error(Subnormal) + if ans._exp > self._exp: + if ans != self: + context._raise_error(Inexact) + context._raise_error(Rounded) + + # call to fix takes care of any necessary folddown, and + # signals Clamped if necessary + ans = ans._fix(context) + return ans + + def same_quantum(self, other, context=None): + """Return True if self and other have the same exponent; otherwise + return False. + + If either operand is a special value, the following rules are used: + * return True if both operands are infinities + * return True if both operands are NaNs + * otherwise, return False. + """ + other = _convert_other(other, raiseit=True) + if self._is_special or other._is_special: + return (self.is_nan() and other.is_nan() or + self.is_infinite() and other.is_infinite()) + return self._exp == other._exp + + def _rescale(self, exp, rounding): + """Rescale self so that the exponent is exp, either by padding with zeros + or by truncating digits, using the given rounding mode. + + Specials are returned without change. This operation is + quiet: it raises no flags, and uses no information from the + context. + + exp = exp to scale to (an integer) + rounding = rounding mode + """ + if self._is_special: + return Decimal(self) + if not self: + return _dec_from_triple(self._sign, '0', exp) + + if self._exp >= exp: + # pad answer with zeros if necessary + return _dec_from_triple(self._sign, + self._int + '0'*(self._exp - exp), exp) + + # too many digits; round and lose data. If self.adjusted() < + # exp-1, replace self by 10**(exp-1) before rounding + digits = len(self._int) + self._exp - exp + if digits < 0: + self = _dec_from_triple(self._sign, '1', exp-1) + digits = 0 + this_function = self._pick_rounding_function[rounding] + changed = this_function(self, digits) + coeff = self._int[:digits] or '0' + if changed == 1: + coeff = str(int(coeff)+1) + return _dec_from_triple(self._sign, coeff, exp) + + def _round(self, places, rounding): + """Round a nonzero, nonspecial Decimal to a fixed number of + significant figures, using the given rounding mode. + + Infinities, NaNs and zeros are returned unaltered. + + This operation is quiet: it raises no flags, and uses no + information from the context. + + """ + if places <= 0: + raise ValueError("argument should be at least 1 in _round") + if self._is_special or not self: + return Decimal(self) + ans = self._rescale(self.adjusted()+1-places, rounding) + # it can happen that the rescale alters the adjusted exponent; + # for example when rounding 99.97 to 3 significant figures. + # When this happens we end up with an extra 0 at the end of + # the number; a second rescale fixes this. + if ans.adjusted() != self.adjusted(): + ans = ans._rescale(ans.adjusted()+1-places, rounding) + return ans + + def to_integral_exact(self, rounding=None, context=None): + """Rounds to a nearby integer. + + If no rounding mode is specified, take the rounding mode from + the context. This method raises the Rounded and Inexact flags + when appropriate. + + See also: to_integral_value, which does exactly the same as + this method except that it doesn't raise Inexact or Rounded. + """ + if self._is_special: + ans = self._check_nans(context=context) + if ans: + return ans + return Decimal(self) + if self._exp >= 0: + return Decimal(self) + if not self: + return _dec_from_triple(self._sign, '0', 0) + if context is None: + context = getcontext() + if rounding is None: + rounding = context.rounding + ans = self._rescale(0, rounding) + if ans != self: + context._raise_error(Inexact) + context._raise_error(Rounded) + return ans + + def to_integral_value(self, rounding=None, context=None): + """Rounds to the nearest integer, without raising inexact, rounded.""" + if context is None: + context = getcontext() + if rounding is None: + rounding = context.rounding + if self._is_special: + ans = self._check_nans(context=context) + if ans: + return ans + return Decimal(self) + if self._exp >= 0: + return Decimal(self) + else: + return self._rescale(0, rounding) + + # the method name changed, but we provide also the old one, for compatibility + to_integral = to_integral_value + + def sqrt(self, context=None): + """Return the square root of self.""" + if context is None: + context = getcontext() + + if self._is_special: + ans = self._check_nans(context=context) + if ans: + return ans + + if self._isinfinity() and self._sign == 0: + return Decimal(self) + + if not self: + # exponent = self._exp // 2. sqrt(-0) = -0 + ans = _dec_from_triple(self._sign, '0', self._exp // 2) + return ans._fix(context) + + if self._sign == 1: + return context._raise_error(InvalidOperation, 'sqrt(-x), x > 0') + + # At this point self represents a positive number. Let p be + # the desired precision and express self in the form c*100**e + # with c a positive real number and e an integer, c and e + # being chosen so that 100**(p-1) <= c < 100**p. Then the + # (exact) square root of self is sqrt(c)*10**e, and 10**(p-1) + # <= sqrt(c) < 10**p, so the closest representable Decimal at + # precision p is n*10**e where n = round_half_even(sqrt(c)), + # the closest integer to sqrt(c) with the even integer chosen + # in the case of a tie. + # + # To ensure correct rounding in all cases, we use the + # following trick: we compute the square root to an extra + # place (precision p+1 instead of precision p), rounding down. + # Then, if the result is inexact and its last digit is 0 or 5, + # we increase the last digit to 1 or 6 respectively; if it's + # exact we leave the last digit alone. Now the final round to + # p places (or fewer in the case of underflow) will round + # correctly and raise the appropriate flags. + + # use an extra digit of precision + prec = context.prec+1 + + # write argument in the form c*100**e where e = self._exp//2 + # is the 'ideal' exponent, to be used if the square root is + # exactly representable. l is the number of 'digits' of c in + # base 100, so that 100**(l-1) <= c < 100**l. + op = _WorkRep(self) + e = op.exp >> 1 + if op.exp & 1: + c = op.int * 10 + l = (len(self._int) >> 1) + 1 + else: + c = op.int + l = len(self._int)+1 >> 1 + + # rescale so that c has exactly prec base 100 'digits' + shift = prec-l + if shift >= 0: + c *= 100**shift + exact = True + else: + c, remainder = divmod(c, 100**-shift) + exact = not remainder + e -= shift + + # find n = floor(sqrt(c)) using Newton's method + n = 10**prec + while True: + q = c//n + if n <= q: + break + else: + n = n + q >> 1 + exact = exact and n*n == c + + if exact: + # result is exact; rescale to use ideal exponent e + if shift >= 0: + # assert n % 10**shift == 0 + n //= 10**shift + else: + n *= 10**-shift + e += shift + else: + # result is not exact; fix last digit as described above + if n % 5 == 0: + n += 1 + + ans = _dec_from_triple(0, str(n), e) + + # round, and fit to current context + context = context._shallow_copy() + rounding = context._set_rounding(ROUND_HALF_EVEN) + ans = ans._fix(context) + context.rounding = rounding + + return ans + + def max(self, other, context=None): + """Returns the larger value. + + Like max(self, other) except if one is not a number, returns + NaN (and signals if one is sNaN). Also rounds. + """ + other = _convert_other(other, raiseit=True) + + if context is None: + context = getcontext() + + if self._is_special or other._is_special: + # If one operand is a quiet NaN and the other is number, then the + # number is always returned + sn = self._isnan() + on = other._isnan() + if sn or on: + if on == 1 and sn == 0: + return self._fix(context) + if sn == 1 and on == 0: + return other._fix(context) + return self._check_nans(other, context) + + c = self._cmp(other) + if c == 0: + # If both operands are finite and equal in numerical value + # then an ordering is applied: + # + # If the signs differ then max returns the operand with the + # positive sign and min returns the operand with the negative sign + # + # If the signs are the same then the exponent is used to select + # the result. This is exactly the ordering used in compare_total. + c = self.compare_total(other) + + if c == -1: + ans = other + else: + ans = self + + return ans._fix(context) + + def min(self, other, context=None): + """Returns the smaller value. + + Like min(self, other) except if one is not a number, returns + NaN (and signals if one is sNaN). Also rounds. + """ + other = _convert_other(other, raiseit=True) + + if context is None: + context = getcontext() + + if self._is_special or other._is_special: + # If one operand is a quiet NaN and the other is number, then the + # number is always returned + sn = self._isnan() + on = other._isnan() + if sn or on: + if on == 1 and sn == 0: + return self._fix(context) + if sn == 1 and on == 0: + return other._fix(context) + return self._check_nans(other, context) + + c = self._cmp(other) + if c == 0: + c = self.compare_total(other) + + if c == -1: + ans = self + else: + ans = other + + return ans._fix(context) + + def _isinteger(self): + """Returns whether self is an integer""" + if self._is_special: + return False + if self._exp >= 0: + return True + rest = self._int[self._exp:] + return rest == '0'*len(rest) + + def _iseven(self): + """Returns True if self is even. Assumes self is an integer.""" + if not self or self._exp > 0: + return True + return self._int[-1+self._exp] in '02468' + + def adjusted(self): + """Return the adjusted exponent of self""" + try: + return self._exp + len(self._int) - 1 + # If NaN or Infinity, self._exp is string + except TypeError: + return 0 + + def canonical(self): + """Returns the same Decimal object. + + As we do not have different encodings for the same number, the + received object already is in its canonical form. + """ + return self + + def compare_signal(self, other, context=None): + """Compares self to the other operand numerically. + + It's pretty much like compare(), but all NaNs signal, with signaling + NaNs taking precedence over quiet NaNs. + """ + other = _convert_other(other, raiseit = True) + ans = self._compare_check_nans(other, context) + if ans: + return ans + return self.compare(other, context=context) + + def compare_total(self, other, context=None): + """Compares self to other using the abstract representations. + + This is not like the standard compare, which use their numerical + value. Note that a total ordering is defined for all possible abstract + representations. + """ + other = _convert_other(other, raiseit=True) + + # if one is negative and the other is positive, it's easy + if self._sign and not other._sign: + return _NegativeOne + if not self._sign and other._sign: + return _One + sign = self._sign + + # let's handle both NaN types + self_nan = self._isnan() + other_nan = other._isnan() + if self_nan or other_nan: + if self_nan == other_nan: + # compare payloads as though they're integers + self_key = len(self._int), self._int + other_key = len(other._int), other._int + if self_key < other_key: + if sign: + return _One + else: + return _NegativeOne + if self_key > other_key: + if sign: + return _NegativeOne + else: + return _One + return _Zero + + if sign: + if self_nan == 1: + return _NegativeOne + if other_nan == 1: + return _One + if self_nan == 2: + return _NegativeOne + if other_nan == 2: + return _One + else: + if self_nan == 1: + return _One + if other_nan == 1: + return _NegativeOne + if self_nan == 2: + return _One + if other_nan == 2: + return _NegativeOne + + if self < other: + return _NegativeOne + if self > other: + return _One + + if self._exp < other._exp: + if sign: + return _One + else: + return _NegativeOne + if self._exp > other._exp: + if sign: + return _NegativeOne + else: + return _One + return _Zero + + + def compare_total_mag(self, other, context=None): + """Compares self to other using abstract repr., ignoring sign. + + Like compare_total, but with operand's sign ignored and assumed to be 0. + """ + other = _convert_other(other, raiseit=True) + + s = self.copy_abs() + o = other.copy_abs() + return s.compare_total(o) + + def copy_abs(self): + """Returns a copy with the sign set to 0. """ + return _dec_from_triple(0, self._int, self._exp, self._is_special) + + def copy_negate(self): + """Returns a copy with the sign inverted.""" + if self._sign: + return _dec_from_triple(0, self._int, self._exp, self._is_special) + else: + return _dec_from_triple(1, self._int, self._exp, self._is_special) + + def copy_sign(self, other, context=None): + """Returns self with the sign of other.""" + other = _convert_other(other, raiseit=True) + return _dec_from_triple(other._sign, self._int, + self._exp, self._is_special) + + def exp(self, context=None): + """Returns e ** self.""" + + if context is None: + context = getcontext() + + # exp(NaN) = NaN + ans = self._check_nans(context=context) + if ans: + return ans + + # exp(-Infinity) = 0 + if self._isinfinity() == -1: + return _Zero + + # exp(0) = 1 + if not self: + return _One + + # exp(Infinity) = Infinity + if self._isinfinity() == 1: + return Decimal(self) + + # the result is now guaranteed to be inexact (the true + # mathematical result is transcendental). There's no need to + # raise Rounded and Inexact here---they'll always be raised as + # a result of the call to _fix. + p = context.prec + adj = self.adjusted() + + # we only need to do any computation for quite a small range + # of adjusted exponents---for example, -29 <= adj <= 10 for + # the default context. For smaller exponent the result is + # indistinguishable from 1 at the given precision, while for + # larger exponent the result either overflows or underflows. + if self._sign == 0 and adj > len(str((context.Emax+1)*3)): + # overflow + ans = _dec_from_triple(0, '1', context.Emax+1) + elif self._sign == 1 and adj > len(str((-context.Etiny()+1)*3)): + # underflow to 0 + ans = _dec_from_triple(0, '1', context.Etiny()-1) + elif self._sign == 0 and adj < -p: + # p+1 digits; final round will raise correct flags + ans = _dec_from_triple(0, '1' + '0'*(p-1) + '1', -p) + elif self._sign == 1 and adj < -p-1: + # p+1 digits; final round will raise correct flags + ans = _dec_from_triple(0, '9'*(p+1), -p-1) + # general case + else: + op = _WorkRep(self) + c, e = op.int, op.exp + if op.sign == 1: + c = -c + + # compute correctly rounded result: increase precision by + # 3 digits at a time until we get an unambiguously + # roundable result + extra = 3 + while True: + coeff, exp = _dexp(c, e, p+extra) + if coeff % (5*10**(len(str(coeff))-p-1)): + break + extra += 3 + + ans = _dec_from_triple(0, str(coeff), exp) + + # at this stage, ans should round correctly with *any* + # rounding mode, not just with ROUND_HALF_EVEN + context = context._shallow_copy() + rounding = context._set_rounding(ROUND_HALF_EVEN) + ans = ans._fix(context) + context.rounding = rounding + + return ans + + def is_canonical(self): + """Return True if self is canonical; otherwise return False. + + Currently, the encoding of a Decimal instance is always + canonical, so this method returns True for any Decimal. + """ + return True + + def is_finite(self): + """Return True if self is finite; otherwise return False. + + A Decimal instance is considered finite if it is neither + infinite nor a NaN. + """ + return not self._is_special + + def is_infinite(self): + """Return True if self is infinite; otherwise return False.""" + return self._exp == 'F' + + def is_nan(self): + """Return True if self is a qNaN or sNaN; otherwise return False.""" + return self._exp in ('n', 'N') + + def is_normal(self, context=None): + """Return True if self is a normal number; otherwise return False.""" + if self._is_special or not self: + return False + if context is None: + context = getcontext() + return context.Emin <= self.adjusted() + + def is_qnan(self): + """Return True if self is a quiet NaN; otherwise return False.""" + return self._exp == 'n' + + def is_signed(self): + """Return True if self is negative; otherwise return False.""" + return self._sign == 1 + + def is_snan(self): + """Return True if self is a signaling NaN; otherwise return False.""" + return self._exp == 'N' + + def is_subnormal(self, context=None): + """Return True if self is subnormal; otherwise return False.""" + if self._is_special or not self: + return False + if context is None: + context = getcontext() + return self.adjusted() < context.Emin + + def is_zero(self): + """Return True if self is a zero; otherwise return False.""" + return not self._is_special and self._int == '0' + + def _ln_exp_bound(self): + """Compute a lower bound for the adjusted exponent of self.ln(). + In other words, compute r such that self.ln() >= 10**r. Assumes + that self is finite and positive and that self != 1. + """ + + # for 0.1 <= x <= 10 we use the inequalities 1-1/x <= ln(x) <= x-1 + adj = self._exp + len(self._int) - 1 + if adj >= 1: + # argument >= 10; we use 23/10 = 2.3 as a lower bound for ln(10) + return len(str(adj*23//10)) - 1 + if adj <= -2: + # argument <= 0.1 + return len(str((-1-adj)*23//10)) - 1 + op = _WorkRep(self) + c, e = op.int, op.exp + if adj == 0: + # 1 < self < 10 + num = str(c-10**-e) + den = str(c) + return len(num) - len(den) - (num < den) + # adj == -1, 0.1 <= self < 1 + return e + len(str(10**-e - c)) - 1 + + + def ln(self, context=None): + """Returns the natural (base e) logarithm of self.""" + + if context is None: + context = getcontext() + + # ln(NaN) = NaN + ans = self._check_nans(context=context) + if ans: + return ans + + # ln(0.0) == -Infinity + if not self: + return _NegativeInfinity + + # ln(Infinity) = Infinity + if self._isinfinity() == 1: + return _Infinity + + # ln(1.0) == 0.0 + if self == _One: + return _Zero + + # ln(negative) raises InvalidOperation + if self._sign == 1: + return context._raise_error(InvalidOperation, + 'ln of a negative value') + + # result is irrational, so necessarily inexact + op = _WorkRep(self) + c, e = op.int, op.exp + p = context.prec + + # correctly rounded result: repeatedly increase precision by 3 + # until we get an unambiguously roundable result + places = p - self._ln_exp_bound() + 2 # at least p+3 places + while True: + coeff = _dlog(c, e, places) + # assert len(str(abs(coeff)))-p >= 1 + if coeff % (5*10**(len(str(abs(coeff)))-p-1)): + break + places += 3 + ans = _dec_from_triple(int(coeff<0), str(abs(coeff)), -places) + + context = context._shallow_copy() + rounding = context._set_rounding(ROUND_HALF_EVEN) + ans = ans._fix(context) + context.rounding = rounding + return ans + + def _log10_exp_bound(self): + """Compute a lower bound for the adjusted exponent of self.log10(). + In other words, find r such that self.log10() >= 10**r. + Assumes that self is finite and positive and that self != 1. + """ + + # For x >= 10 or x < 0.1 we only need a bound on the integer + # part of log10(self), and this comes directly from the + # exponent of x. For 0.1 <= x <= 10 we use the inequalities + # 1-1/x <= log(x) <= x-1. If x > 1 we have |log10(x)| > + # (1-1/x)/2.31 > 0. If x < 1 then |log10(x)| > (1-x)/2.31 > 0 + + adj = self._exp + len(self._int) - 1 + if adj >= 1: + # self >= 10 + return len(str(adj))-1 + if adj <= -2: + # self < 0.1 + return len(str(-1-adj))-1 + op = _WorkRep(self) + c, e = op.int, op.exp + if adj == 0: + # 1 < self < 10 + num = str(c-10**-e) + den = str(231*c) + return len(num) - len(den) - (num < den) + 2 + # adj == -1, 0.1 <= self < 1 + num = str(10**-e-c) + return len(num) + e - (num < "231") - 1 + + def log10(self, context=None): + """Returns the base 10 logarithm of self.""" + + if context is None: + context = getcontext() + + # log10(NaN) = NaN + ans = self._check_nans(context=context) + if ans: + return ans + + # log10(0.0) == -Infinity + if not self: + return _NegativeInfinity + + # log10(Infinity) = Infinity + if self._isinfinity() == 1: + return _Infinity + + # log10(negative or -Infinity) raises InvalidOperation + if self._sign == 1: + return context._raise_error(InvalidOperation, + 'log10 of a negative value') + + # log10(10**n) = n + if self._int[0] == '1' and self._int[1:] == '0'*(len(self._int) - 1): + # answer may need rounding + ans = Decimal(self._exp + len(self._int) - 1) + else: + # result is irrational, so necessarily inexact + op = _WorkRep(self) + c, e = op.int, op.exp + p = context.prec + + # correctly rounded result: repeatedly increase precision + # until result is unambiguously roundable + places = p-self._log10_exp_bound()+2 + while True: + coeff = _dlog10(c, e, places) + # assert len(str(abs(coeff)))-p >= 1 + if coeff % (5*10**(len(str(abs(coeff)))-p-1)): + break + places += 3 + ans = _dec_from_triple(int(coeff<0), str(abs(coeff)), -places) + + context = context._shallow_copy() + rounding = context._set_rounding(ROUND_HALF_EVEN) + ans = ans._fix(context) + context.rounding = rounding + return ans + + def logb(self, context=None): + """ Returns the exponent of the magnitude of self's MSD. + + The result is the integer which is the exponent of the magnitude + of the most significant digit of self (as though it were truncated + to a single digit while maintaining the value of that digit and + without limiting the resulting exponent). + """ + # logb(NaN) = NaN + ans = self._check_nans(context=context) + if ans: + return ans + + if context is None: + context = getcontext() + + # logb(+/-Inf) = +Inf + if self._isinfinity(): + return _Infinity + + # logb(0) = -Inf, DivisionByZero + if not self: + return context._raise_error(DivisionByZero, 'logb(0)', 1) + + # otherwise, simply return the adjusted exponent of self, as a + # Decimal. Note that no attempt is made to fit the result + # into the current context. + ans = Decimal(self.adjusted()) + return ans._fix(context) + + def _islogical(self): + """Return True if self is a logical operand. + + For being logical, it must be a finite number with a sign of 0, + an exponent of 0, and a coefficient whose digits must all be + either 0 or 1. + """ + if self._sign != 0 or self._exp != 0: + return False + for dig in self._int: + if dig not in '01': + return False + return True + + def _fill_logical(self, context, opa, opb): + dif = context.prec - len(opa) + if dif > 0: + opa = '0'*dif + opa + elif dif < 0: + opa = opa[-context.prec:] + dif = context.prec - len(opb) + if dif > 0: + opb = '0'*dif + opb + elif dif < 0: + opb = opb[-context.prec:] + return opa, opb + + def logical_and(self, other, context=None): + """Applies an 'and' operation between self and other's digits.""" + if context is None: + context = getcontext() + + other = _convert_other(other, raiseit=True) + + if not self._islogical() or not other._islogical(): + return context._raise_error(InvalidOperation) + + # fill to context.prec + (opa, opb) = self._fill_logical(context, self._int, other._int) + + # make the operation, and clean starting zeroes + result = "".join([str(int(a)&int(b)) for a,b in zip(opa,opb)]) + return _dec_from_triple(0, result.lstrip('0') or '0', 0) + + def logical_invert(self, context=None): + """Invert all its digits.""" + if context is None: + context = getcontext() + return self.logical_xor(_dec_from_triple(0,'1'*context.prec,0), + context) + + def logical_or(self, other, context=None): + """Applies an 'or' operation between self and other's digits.""" + if context is None: + context = getcontext() + + other = _convert_other(other, raiseit=True) + + if not self._islogical() or not other._islogical(): + return context._raise_error(InvalidOperation) + + # fill to context.prec + (opa, opb) = self._fill_logical(context, self._int, other._int) + + # make the operation, and clean starting zeroes + result = "".join([str(int(a)|int(b)) for a,b in zip(opa,opb)]) + return _dec_from_triple(0, result.lstrip('0') or '0', 0) + + def logical_xor(self, other, context=None): + """Applies an 'xor' operation between self and other's digits.""" + if context is None: + context = getcontext() + + other = _convert_other(other, raiseit=True) + + if not self._islogical() or not other._islogical(): + return context._raise_error(InvalidOperation) + + # fill to context.prec + (opa, opb) = self._fill_logical(context, self._int, other._int) + + # make the operation, and clean starting zeroes + result = "".join([str(int(a)^int(b)) for a,b in zip(opa,opb)]) + return _dec_from_triple(0, result.lstrip('0') or '0', 0) + + def max_mag(self, other, context=None): + """Compares the values numerically with their sign ignored.""" + other = _convert_other(other, raiseit=True) + + if context is None: + context = getcontext() + + if self._is_special or other._is_special: + # If one operand is a quiet NaN and the other is number, then the + # number is always returned + sn = self._isnan() + on = other._isnan() + if sn or on: + if on == 1 and sn == 0: + return self._fix(context) + if sn == 1 and on == 0: + return other._fix(context) + return self._check_nans(other, context) + + c = self.copy_abs()._cmp(other.copy_abs()) + if c == 0: + c = self.compare_total(other) + + if c == -1: + ans = other + else: + ans = self + + return ans._fix(context) + + def min_mag(self, other, context=None): + """Compares the values numerically with their sign ignored.""" + other = _convert_other(other, raiseit=True) + + if context is None: + context = getcontext() + + if self._is_special or other._is_special: + # If one operand is a quiet NaN and the other is number, then the + # number is always returned + sn = self._isnan() + on = other._isnan() + if sn or on: + if on == 1 and sn == 0: + return self._fix(context) + if sn == 1 and on == 0: + return other._fix(context) + return self._check_nans(other, context) + + c = self.copy_abs()._cmp(other.copy_abs()) + if c == 0: + c = self.compare_total(other) + + if c == -1: + ans = self + else: + ans = other + + return ans._fix(context) + + def next_minus(self, context=None): + """Returns the largest representable number smaller than itself.""" + if context is None: + context = getcontext() + + ans = self._check_nans(context=context) + if ans: + return ans + + if self._isinfinity() == -1: + return _NegativeInfinity + if self._isinfinity() == 1: + return _dec_from_triple(0, '9'*context.prec, context.Etop()) + + context = context.copy() + context._set_rounding(ROUND_FLOOR) + context._ignore_all_flags() + new_self = self._fix(context) + if new_self != self: + return new_self + return self.__sub__(_dec_from_triple(0, '1', context.Etiny()-1), + context) + + def next_plus(self, context=None): + """Returns the smallest representable number larger than itself.""" + if context is None: + context = getcontext() + + ans = self._check_nans(context=context) + if ans: + return ans + + if self._isinfinity() == 1: + return _Infinity + if self._isinfinity() == -1: + return _dec_from_triple(1, '9'*context.prec, context.Etop()) + + context = context.copy() + context._set_rounding(ROUND_CEILING) + context._ignore_all_flags() + new_self = self._fix(context) + if new_self != self: + return new_self + return self.__add__(_dec_from_triple(0, '1', context.Etiny()-1), + context) + + def next_toward(self, other, context=None): + """Returns the number closest to self, in the direction towards other. + + The result is the closest representable number to self + (excluding self) that is in the direction towards other, + unless both have the same value. If the two operands are + numerically equal, then the result is a copy of self with the + sign set to be the same as the sign of other. + """ + other = _convert_other(other, raiseit=True) + + if context is None: + context = getcontext() + + ans = self._check_nans(other, context) + if ans: + return ans + + comparison = self._cmp(other) + if comparison == 0: + return self.copy_sign(other) + + if comparison == -1: + ans = self.next_plus(context) + else: # comparison == 1 + ans = self.next_minus(context) + + # decide which flags to raise using value of ans + if ans._isinfinity(): + context._raise_error(Overflow, + 'Infinite result from next_toward', + ans._sign) + context._raise_error(Inexact) + context._raise_error(Rounded) + elif ans.adjusted() < context.Emin: + context._raise_error(Underflow) + context._raise_error(Subnormal) + context._raise_error(Inexact) + context._raise_error(Rounded) + # if precision == 1 then we don't raise Clamped for a + # result 0E-Etiny. + if not ans: + context._raise_error(Clamped) + + return ans + + def number_class(self, context=None): + """Returns an indication of the class of self. + + The class is one of the following strings: + sNaN + NaN + -Infinity + -Normal + -Subnormal + -Zero + +Zero + +Subnormal + +Normal + +Infinity + """ + if self.is_snan(): + return "sNaN" + if self.is_qnan(): + return "NaN" + inf = self._isinfinity() + if inf == 1: + return "+Infinity" + if inf == -1: + return "-Infinity" + if self.is_zero(): + if self._sign: + return "-Zero" + else: + return "+Zero" + if context is None: + context = getcontext() + if self.is_subnormal(context=context): + if self._sign: + return "-Subnormal" + else: + return "+Subnormal" + # just a normal, regular, boring number, :) + if self._sign: + return "-Normal" + else: + return "+Normal" + + def radix(self): + """Just returns 10, as this is Decimal, :)""" + return Decimal(10) + + def rotate(self, other, context=None): + """Returns a rotated copy of self, value-of-other times.""" + if context is None: + context = getcontext() + + other = _convert_other(other, raiseit=True) + + ans = self._check_nans(other, context) + if ans: + return ans + + if other._exp != 0: + return context._raise_error(InvalidOperation) + if not (-context.prec <= int(other) <= context.prec): + return context._raise_error(InvalidOperation) + + if self._isinfinity(): + return Decimal(self) + + # get values, pad if necessary + torot = int(other) + rotdig = self._int + topad = context.prec - len(rotdig) + if topad > 0: + rotdig = '0'*topad + rotdig + elif topad < 0: + rotdig = rotdig[-topad:] + + # let's rotate! + rotated = rotdig[torot:] + rotdig[:torot] + return _dec_from_triple(self._sign, + rotated.lstrip('0') or '0', self._exp) + + def scaleb(self, other, context=None): + """Returns self operand after adding the second value to its exp.""" + if context is None: + context = getcontext() + + other = _convert_other(other, raiseit=True) + + ans = self._check_nans(other, context) + if ans: + return ans + + if other._exp != 0: + return context._raise_error(InvalidOperation) + liminf = -2 * (context.Emax + context.prec) + limsup = 2 * (context.Emax + context.prec) + if not (liminf <= int(other) <= limsup): + return context._raise_error(InvalidOperation) + + if self._isinfinity(): + return Decimal(self) + + d = _dec_from_triple(self._sign, self._int, self._exp + int(other)) + d = d._fix(context) + return d + + def shift(self, other, context=None): + """Returns a shifted copy of self, value-of-other times.""" + if context is None: + context = getcontext() + + other = _convert_other(other, raiseit=True) + + ans = self._check_nans(other, context) + if ans: + return ans + + if other._exp != 0: + return context._raise_error(InvalidOperation) + if not (-context.prec <= int(other) <= context.prec): + return context._raise_error(InvalidOperation) + + if self._isinfinity(): + return Decimal(self) + + # get values, pad if necessary + torot = int(other) + rotdig = self._int + topad = context.prec - len(rotdig) + if topad > 0: + rotdig = '0'*topad + rotdig + elif topad < 0: + rotdig = rotdig[-topad:] + + # let's shift! + if torot < 0: + shifted = rotdig[:torot] + else: + shifted = rotdig + '0'*torot + shifted = shifted[-context.prec:] + + return _dec_from_triple(self._sign, + shifted.lstrip('0') or '0', self._exp) + + # Support for pickling, copy, and deepcopy + def __reduce__(self): + return (self.__class__, (str(self),)) + + def __copy__(self): + if type(self) is Decimal: + return self # I'm immutable; therefore I am my own clone + return self.__class__(str(self)) + + def __deepcopy__(self, memo): + if type(self) is Decimal: + return self # My components are also immutable + return self.__class__(str(self)) + + # PEP 3101 support. the _localeconv keyword argument should be + # considered private: it's provided for ease of testing only. + def __format__(self, specifier, context=None, _localeconv=None): + """Format a Decimal instance according to the given specifier. + + The specifier should be a standard format specifier, with the + form described in PEP 3101. Formatting types 'e', 'E', 'f', + 'F', 'g', 'G', 'n' and '%' are supported. If the formatting + type is omitted it defaults to 'g' or 'G', depending on the + value of context.capitals. + """ + + # Note: PEP 3101 says that if the type is not present then + # there should be at least one digit after the decimal point. + # We take the liberty of ignoring this requirement for + # Decimal---it's presumably there to make sure that + # format(float, '') behaves similarly to str(float). + if context is None: + context = getcontext() + + spec = _parse_format_specifier(specifier, _localeconv=_localeconv) + + # special values don't care about the type or precision + if self._is_special: + sign = _format_sign(self._sign, spec) + body = str(self.copy_abs()) + if spec['type'] == '%': + body += '%' + return _format_align(sign, body, spec) + + # a type of None defaults to 'g' or 'G', depending on context + if spec['type'] is None: + spec['type'] = ['g', 'G'][context.capitals] + + # if type is '%', adjust exponent of self accordingly + if spec['type'] == '%': + self = _dec_from_triple(self._sign, self._int, self._exp+2) + + # round if necessary, taking rounding mode from the context + rounding = context.rounding + precision = spec['precision'] + if precision is not None: + if spec['type'] in 'eE': + self = self._round(precision+1, rounding) + elif spec['type'] in 'fF%': + self = self._rescale(-precision, rounding) + elif spec['type'] in 'gG' and len(self._int) > precision: + self = self._round(precision, rounding) + # special case: zeros with a positive exponent can't be + # represented in fixed point; rescale them to 0e0. + if not self and self._exp > 0 and spec['type'] in 'fF%': + self = self._rescale(0, rounding) + + # figure out placement of the decimal point + leftdigits = self._exp + len(self._int) + if spec['type'] in 'eE': + if not self and precision is not None: + dotplace = 1 - precision + else: + dotplace = 1 + elif spec['type'] in 'fF%': + dotplace = leftdigits + elif spec['type'] in 'gG': + if self._exp <= 0 and leftdigits > -6: + dotplace = leftdigits + else: + dotplace = 1 + + # find digits before and after decimal point, and get exponent + if dotplace < 0: + intpart = '0' + fracpart = '0'*(-dotplace) + self._int + elif dotplace > len(self._int): + intpart = self._int + '0'*(dotplace-len(self._int)) + fracpart = '' + else: + intpart = self._int[:dotplace] or '0' + fracpart = self._int[dotplace:] + exp = leftdigits-dotplace + + # done with the decimal-specific stuff; hand over the rest + # of the formatting to the _format_number function + return _format_number(self._sign, intpart, fracpart, exp, spec) + +def _dec_from_triple(sign, coefficient, exponent, special=False): + """Create a decimal instance directly, without any validation, + normalization (e.g. removal of leading zeros) or argument + conversion. + + This function is for *internal use only*. + """ + + self = object.__new__(Decimal) + self._sign = sign + self._int = coefficient + self._exp = exponent + self._is_special = special + + return self + +# Register Decimal as a kind of Number (an abstract base class). +# However, do not register it as Real (because Decimals are not +# interoperable with floats). +_numbers.Number.register(Decimal) + + +##### Context class ####################################################### + +class _ContextManager(object): + """Context manager class to support localcontext(). + + Sets a copy of the supplied context in __enter__() and restores + the previous decimal context in __exit__() + """ + def __init__(self, new_context): + self.new_context = new_context.copy() + def __enter__(self): + self.saved_context = getcontext() + setcontext(self.new_context) + return self.new_context + def __exit__(self, t, v, tb): + setcontext(self.saved_context) + +class Context(object): + """Contains the context for a Decimal instance. + + Contains: + prec - precision (for use in rounding, division, square roots..) + rounding - rounding type (how you round) + traps - If traps[exception] = 1, then the exception is + raised when it is caused. Otherwise, a value is + substituted in. + flags - When an exception is caused, flags[exception] is set. + (Whether or not the trap_enabler is set) + Should be reset by user of Decimal instance. + Emin - Minimum exponent + Emax - Maximum exponent + capitals - If 1, 1*10^1 is printed as 1E+1. + If 0, printed as 1e1 + clamp - If 1, change exponents if too high (Default 0) + """ + + def __init__(self, prec=None, rounding=None, Emin=None, Emax=None, + capitals=None, clamp=None, flags=None, traps=None, + _ignored_flags=None): + # Set defaults; for everything except flags and _ignored_flags, + # inherit from DefaultContext. + try: + dc = DefaultContext + except NameError: + pass + + self.prec = prec if prec is not None else dc.prec + self.rounding = rounding if rounding is not None else dc.rounding + self.Emin = Emin if Emin is not None else dc.Emin + self.Emax = Emax if Emax is not None else dc.Emax + self.capitals = capitals if capitals is not None else dc.capitals + self.clamp = clamp if clamp is not None else dc.clamp + + if _ignored_flags is None: + self._ignored_flags = [] + else: + self._ignored_flags = _ignored_flags + + if traps is None: + self.traps = dc.traps.copy() + elif not isinstance(traps, dict): + self.traps = dict((s, int(s in traps)) for s in _signals + traps) + else: + self.traps = traps + + if flags is None: + self.flags = dict.fromkeys(_signals, 0) + elif not isinstance(flags, dict): + self.flags = dict((s, int(s in flags)) for s in _signals + flags) + else: + self.flags = flags + + def _set_integer_check(self, name, value, vmin, vmax): + if not isinstance(value, int): + raise TypeError("%s must be an integer" % name) + if vmin == '-inf': + if value > vmax: + raise ValueError("%s must be in [%s, %d]. got: %s" % (name, vmin, vmax, value)) + elif vmax == 'inf': + if value < vmin: + raise ValueError("%s must be in [%d, %s]. got: %s" % (name, vmin, vmax, value)) + else: + if value < vmin or value > vmax: + raise ValueError("%s must be in [%d, %d]. got %s" % (name, vmin, vmax, value)) + return object.__setattr__(self, name, value) + + def _set_signal_dict(self, name, d): + if not isinstance(d, dict): + raise TypeError("%s must be a signal dict" % d) + for key in d: + if not key in _signals: + raise KeyError("%s is not a valid signal dict" % d) + for key in _signals: + if not key in d: + raise KeyError("%s is not a valid signal dict" % d) + return object.__setattr__(self, name, d) + + def __setattr__(self, name, value): + if name == 'prec': + return self._set_integer_check(name, value, 1, 'inf') + elif name == 'Emin': + return self._set_integer_check(name, value, '-inf', 0) + elif name == 'Emax': + return self._set_integer_check(name, value, 0, 'inf') + elif name == 'capitals': + return self._set_integer_check(name, value, 0, 1) + elif name == 'clamp': + return self._set_integer_check(name, value, 0, 1) + elif name == 'rounding': + if not value in _rounding_modes: + # raise TypeError even for strings to have consistency + # among various implementations. + raise TypeError("%s: invalid rounding mode" % value) + return object.__setattr__(self, name, value) + elif name == 'flags' or name == 'traps': + return self._set_signal_dict(name, value) + elif name == '_ignored_flags': + return object.__setattr__(self, name, value) + else: + raise AttributeError( + "'decimal.Context' object has no attribute '%s'" % name) + + def __delattr__(self, name): + raise AttributeError("%s cannot be deleted" % name) + + # Support for pickling, copy, and deepcopy + def __reduce__(self): + flags = [sig for sig, v in self.flags.items() if v] + traps = [sig for sig, v in self.traps.items() if v] + return (self.__class__, + (self.prec, self.rounding, self.Emin, self.Emax, + self.capitals, self.clamp, flags, traps)) + + def __repr__(self): + """Show the current context.""" + s = [] + s.append('Context(prec=%(prec)d, rounding=%(rounding)s, ' + 'Emin=%(Emin)d, Emax=%(Emax)d, capitals=%(capitals)d, ' + 'clamp=%(clamp)d' + % vars(self)) + names = [f.__name__ for f, v in self.flags.items() if v] + s.append('flags=[' + ', '.join(names) + ']') + names = [t.__name__ for t, v in self.traps.items() if v] + s.append('traps=[' + ', '.join(names) + ']') + return ', '.join(s) + ')' + + def clear_flags(self): + """Reset all flags to zero""" + for flag in self.flags: + self.flags[flag] = 0 + + def clear_traps(self): + """Reset all traps to zero""" + for flag in self.traps: + self.traps[flag] = 0 + + def _shallow_copy(self): + """Returns a shallow copy from self.""" + nc = Context(self.prec, self.rounding, self.Emin, self.Emax, + self.capitals, self.clamp, self.flags, self.traps, + self._ignored_flags) + return nc + + def copy(self): + """Returns a deep copy from self.""" + nc = Context(self.prec, self.rounding, self.Emin, self.Emax, + self.capitals, self.clamp, + self.flags.copy(), self.traps.copy(), + self._ignored_flags) + return nc + __copy__ = copy + + def _raise_error(self, condition, explanation = None, *args): + """Handles an error + + If the flag is in _ignored_flags, returns the default response. + Otherwise, it sets the flag, then, if the corresponding + trap_enabler is set, it reraises the exception. Otherwise, it returns + the default value after setting the flag. + """ + error = _condition_map.get(condition, condition) + if error in self._ignored_flags: + # Don't touch the flag + return error().handle(self, *args) + + self.flags[error] = 1 + if not self.traps[error]: + # The errors define how to handle themselves. + return condition().handle(self, *args) + + # Errors should only be risked on copies of the context + # self._ignored_flags = [] + raise error(explanation) + + def _ignore_all_flags(self): + """Ignore all flags, if they are raised""" + return self._ignore_flags(*_signals) + + def _ignore_flags(self, *flags): + """Ignore the flags, if they are raised""" + # Do not mutate-- This way, copies of a context leave the original + # alone. + self._ignored_flags = (self._ignored_flags + list(flags)) + return list(flags) + + def _regard_flags(self, *flags): + """Stop ignoring the flags, if they are raised""" + if flags and isinstance(flags[0], (tuple,list)): + flags = flags[0] + for flag in flags: + self._ignored_flags.remove(flag) + + # We inherit object.__hash__, so we must deny this explicitly + __hash__ = None + + def Etiny(self): + """Returns Etiny (= Emin - prec + 1)""" + return int(self.Emin - self.prec + 1) + + def Etop(self): + """Returns maximum exponent (= Emax - prec + 1)""" + return int(self.Emax - self.prec + 1) + + def _set_rounding(self, type): + """Sets the rounding type. + + Sets the rounding type, and returns the current (previous) + rounding type. Often used like: + + context = context.copy() + # so you don't change the calling context + # if an error occurs in the middle. + rounding = context._set_rounding(ROUND_UP) + val = self.__sub__(other, context=context) + context._set_rounding(rounding) + + This will make it round up for that operation. + """ + rounding = self.rounding + self.rounding= type + return rounding + + def create_decimal(self, num='0'): + """Creates a new Decimal instance but using self as context. + + This method implements the to-number operation of the + IBM Decimal specification.""" + + if isinstance(num, str) and num != num.strip(): + return self._raise_error(ConversionSyntax, + "no trailing or leading whitespace is " + "permitted.") + + d = Decimal(num, context=self) + if d._isnan() and len(d._int) > self.prec - self.clamp: + return self._raise_error(ConversionSyntax, + "diagnostic info too long in NaN") + return d._fix(self) + + def create_decimal_from_float(self, f): + """Creates a new Decimal instance from a float but rounding using self + as the context. + + >>> context = Context(prec=5, rounding=ROUND_DOWN) + >>> context.create_decimal_from_float(3.1415926535897932) + Decimal('3.1415') + >>> context = Context(prec=5, traps=[Inexact]) + >>> context.create_decimal_from_float(3.1415926535897932) + Traceback (most recent call last): + ... + decimal.Inexact + + """ + d = Decimal.from_float(f) # An exact conversion + return d._fix(self) # Apply the context rounding + + # Methods + def abs(self, a): + """Returns the absolute value of the operand. + + If the operand is negative, the result is the same as using the minus + operation on the operand. Otherwise, the result is the same as using + the plus operation on the operand. + + >>> ExtendedContext.abs(Decimal('2.1')) + Decimal('2.1') + >>> ExtendedContext.abs(Decimal('-100')) + Decimal('100') + >>> ExtendedContext.abs(Decimal('101.5')) + Decimal('101.5') + >>> ExtendedContext.abs(Decimal('-101.5')) + Decimal('101.5') + >>> ExtendedContext.abs(-1) + Decimal('1') + """ + a = _convert_other(a, raiseit=True) + return a.__abs__(context=self) + + def add(self, a, b): + """Return the sum of the two operands. + + >>> ExtendedContext.add(Decimal('12'), Decimal('7.00')) + Decimal('19.00') + >>> ExtendedContext.add(Decimal('1E+2'), Decimal('1.01E+4')) + Decimal('1.02E+4') + >>> ExtendedContext.add(1, Decimal(2)) + Decimal('3') + >>> ExtendedContext.add(Decimal(8), 5) + Decimal('13') + >>> ExtendedContext.add(5, 5) + Decimal('10') + """ + a = _convert_other(a, raiseit=True) + r = a.__add__(b, context=self) + if r is NotImplemented: + raise TypeError("Unable to convert %s to Decimal" % b) + else: + return r + + def _apply(self, a): + return str(a._fix(self)) + + def canonical(self, a): + """Returns the same Decimal object. + + As we do not have different encodings for the same number, the + received object already is in its canonical form. + + >>> ExtendedContext.canonical(Decimal('2.50')) + Decimal('2.50') + """ + if not isinstance(a, Decimal): + raise TypeError("canonical requires a Decimal as an argument.") + return a.canonical() + + def compare(self, a, b): + """Compares values numerically. + + If the signs of the operands differ, a value representing each operand + ('-1' if the operand is less than zero, '0' if the operand is zero or + negative zero, or '1' if the operand is greater than zero) is used in + place of that operand for the comparison instead of the actual + operand. + + The comparison is then effected by subtracting the second operand from + the first and then returning a value according to the result of the + subtraction: '-1' if the result is less than zero, '0' if the result is + zero or negative zero, or '1' if the result is greater than zero. + + >>> ExtendedContext.compare(Decimal('2.1'), Decimal('3')) + Decimal('-1') + >>> ExtendedContext.compare(Decimal('2.1'), Decimal('2.1')) + Decimal('0') + >>> ExtendedContext.compare(Decimal('2.1'), Decimal('2.10')) + Decimal('0') + >>> ExtendedContext.compare(Decimal('3'), Decimal('2.1')) + Decimal('1') + >>> ExtendedContext.compare(Decimal('2.1'), Decimal('-3')) + Decimal('1') + >>> ExtendedContext.compare(Decimal('-3'), Decimal('2.1')) + Decimal('-1') + >>> ExtendedContext.compare(1, 2) + Decimal('-1') + >>> ExtendedContext.compare(Decimal(1), 2) + Decimal('-1') + >>> ExtendedContext.compare(1, Decimal(2)) + Decimal('-1') + """ + a = _convert_other(a, raiseit=True) + return a.compare(b, context=self) + + def compare_signal(self, a, b): + """Compares the values of the two operands numerically. + + It's pretty much like compare(), but all NaNs signal, with signaling + NaNs taking precedence over quiet NaNs. + + >>> c = ExtendedContext + >>> c.compare_signal(Decimal('2.1'), Decimal('3')) + Decimal('-1') + >>> c.compare_signal(Decimal('2.1'), Decimal('2.1')) + Decimal('0') + >>> c.flags[InvalidOperation] = 0 + >>> print(c.flags[InvalidOperation]) + 0 + >>> c.compare_signal(Decimal('NaN'), Decimal('2.1')) + Decimal('NaN') + >>> print(c.flags[InvalidOperation]) + 1 + >>> c.flags[InvalidOperation] = 0 + >>> print(c.flags[InvalidOperation]) + 0 + >>> c.compare_signal(Decimal('sNaN'), Decimal('2.1')) + Decimal('NaN') + >>> print(c.flags[InvalidOperation]) + 1 + >>> c.compare_signal(-1, 2) + Decimal('-1') + >>> c.compare_signal(Decimal(-1), 2) + Decimal('-1') + >>> c.compare_signal(-1, Decimal(2)) + Decimal('-1') + """ + a = _convert_other(a, raiseit=True) + return a.compare_signal(b, context=self) + + def compare_total(self, a, b): + """Compares two operands using their abstract representation. + + This is not like the standard compare, which use their numerical + value. Note that a total ordering is defined for all possible abstract + representations. + + >>> ExtendedContext.compare_total(Decimal('12.73'), Decimal('127.9')) + Decimal('-1') + >>> ExtendedContext.compare_total(Decimal('-127'), Decimal('12')) + Decimal('-1') + >>> ExtendedContext.compare_total(Decimal('12.30'), Decimal('12.3')) + Decimal('-1') + >>> ExtendedContext.compare_total(Decimal('12.30'), Decimal('12.30')) + Decimal('0') + >>> ExtendedContext.compare_total(Decimal('12.3'), Decimal('12.300')) + Decimal('1') + >>> ExtendedContext.compare_total(Decimal('12.3'), Decimal('NaN')) + Decimal('-1') + >>> ExtendedContext.compare_total(1, 2) + Decimal('-1') + >>> ExtendedContext.compare_total(Decimal(1), 2) + Decimal('-1') + >>> ExtendedContext.compare_total(1, Decimal(2)) + Decimal('-1') + """ + a = _convert_other(a, raiseit=True) + return a.compare_total(b) + + def compare_total_mag(self, a, b): + """Compares two operands using their abstract representation ignoring sign. + + Like compare_total, but with operand's sign ignored and assumed to be 0. + """ + a = _convert_other(a, raiseit=True) + return a.compare_total_mag(b) + + def copy_abs(self, a): + """Returns a copy of the operand with the sign set to 0. + + >>> ExtendedContext.copy_abs(Decimal('2.1')) + Decimal('2.1') + >>> ExtendedContext.copy_abs(Decimal('-100')) + Decimal('100') + >>> ExtendedContext.copy_abs(-1) + Decimal('1') + """ + a = _convert_other(a, raiseit=True) + return a.copy_abs() + + def copy_decimal(self, a): + """Returns a copy of the decimal object. + + >>> ExtendedContext.copy_decimal(Decimal('2.1')) + Decimal('2.1') + >>> ExtendedContext.copy_decimal(Decimal('-1.00')) + Decimal('-1.00') + >>> ExtendedContext.copy_decimal(1) + Decimal('1') + """ + a = _convert_other(a, raiseit=True) + return Decimal(a) + + def copy_negate(self, a): + """Returns a copy of the operand with the sign inverted. + + >>> ExtendedContext.copy_negate(Decimal('101.5')) + Decimal('-101.5') + >>> ExtendedContext.copy_negate(Decimal('-101.5')) + Decimal('101.5') + >>> ExtendedContext.copy_negate(1) + Decimal('-1') + """ + a = _convert_other(a, raiseit=True) + return a.copy_negate() + + def copy_sign(self, a, b): + """Copies the second operand's sign to the first one. + + In detail, it returns a copy of the first operand with the sign + equal to the sign of the second operand. + + >>> ExtendedContext.copy_sign(Decimal( '1.50'), Decimal('7.33')) + Decimal('1.50') + >>> ExtendedContext.copy_sign(Decimal('-1.50'), Decimal('7.33')) + Decimal('1.50') + >>> ExtendedContext.copy_sign(Decimal( '1.50'), Decimal('-7.33')) + Decimal('-1.50') + >>> ExtendedContext.copy_sign(Decimal('-1.50'), Decimal('-7.33')) + Decimal('-1.50') + >>> ExtendedContext.copy_sign(1, -2) + Decimal('-1') + >>> ExtendedContext.copy_sign(Decimal(1), -2) + Decimal('-1') + >>> ExtendedContext.copy_sign(1, Decimal(-2)) + Decimal('-1') + """ + a = _convert_other(a, raiseit=True) + return a.copy_sign(b) + + def divide(self, a, b): + """Decimal division in a specified context. + + >>> ExtendedContext.divide(Decimal('1'), Decimal('3')) + Decimal('0.333333333') + >>> ExtendedContext.divide(Decimal('2'), Decimal('3')) + Decimal('0.666666667') + >>> ExtendedContext.divide(Decimal('5'), Decimal('2')) + Decimal('2.5') + >>> ExtendedContext.divide(Decimal('1'), Decimal('10')) + Decimal('0.1') + >>> ExtendedContext.divide(Decimal('12'), Decimal('12')) + Decimal('1') + >>> ExtendedContext.divide(Decimal('8.00'), Decimal('2')) + Decimal('4.00') + >>> ExtendedContext.divide(Decimal('2.400'), Decimal('2.0')) + Decimal('1.20') + >>> ExtendedContext.divide(Decimal('1000'), Decimal('100')) + Decimal('10') + >>> ExtendedContext.divide(Decimal('1000'), Decimal('1')) + Decimal('1000') + >>> ExtendedContext.divide(Decimal('2.40E+6'), Decimal('2')) + Decimal('1.20E+6') + >>> ExtendedContext.divide(5, 5) + Decimal('1') + >>> ExtendedContext.divide(Decimal(5), 5) + Decimal('1') + >>> ExtendedContext.divide(5, Decimal(5)) + Decimal('1') + """ + a = _convert_other(a, raiseit=True) + r = a.__truediv__(b, context=self) + if r is NotImplemented: + raise TypeError("Unable to convert %s to Decimal" % b) + else: + return r + + def divide_int(self, a, b): + """Divides two numbers and returns the integer part of the result. + + >>> ExtendedContext.divide_int(Decimal('2'), Decimal('3')) + Decimal('0') + >>> ExtendedContext.divide_int(Decimal('10'), Decimal('3')) + Decimal('3') + >>> ExtendedContext.divide_int(Decimal('1'), Decimal('0.3')) + Decimal('3') + >>> ExtendedContext.divide_int(10, 3) + Decimal('3') + >>> ExtendedContext.divide_int(Decimal(10), 3) + Decimal('3') + >>> ExtendedContext.divide_int(10, Decimal(3)) + Decimal('3') + """ + a = _convert_other(a, raiseit=True) + r = a.__floordiv__(b, context=self) + if r is NotImplemented: + raise TypeError("Unable to convert %s to Decimal" % b) + else: + return r + + def divmod(self, a, b): + """Return (a // b, a % b). + + >>> ExtendedContext.divmod(Decimal(8), Decimal(3)) + (Decimal('2'), Decimal('2')) + >>> ExtendedContext.divmod(Decimal(8), Decimal(4)) + (Decimal('2'), Decimal('0')) + >>> ExtendedContext.divmod(8, 4) + (Decimal('2'), Decimal('0')) + >>> ExtendedContext.divmod(Decimal(8), 4) + (Decimal('2'), Decimal('0')) + >>> ExtendedContext.divmod(8, Decimal(4)) + (Decimal('2'), Decimal('0')) + """ + a = _convert_other(a, raiseit=True) + r = a.__divmod__(b, context=self) + if r is NotImplemented: + raise TypeError("Unable to convert %s to Decimal" % b) + else: + return r + + def exp(self, a): + """Returns e ** a. + + >>> c = ExtendedContext.copy() + >>> c.Emin = -999 + >>> c.Emax = 999 + >>> c.exp(Decimal('-Infinity')) + Decimal('0') + >>> c.exp(Decimal('-1')) + Decimal('0.367879441') + >>> c.exp(Decimal('0')) + Decimal('1') + >>> c.exp(Decimal('1')) + Decimal('2.71828183') + >>> c.exp(Decimal('0.693147181')) + Decimal('2.00000000') + >>> c.exp(Decimal('+Infinity')) + Decimal('Infinity') + >>> c.exp(10) + Decimal('22026.4658') + """ + a =_convert_other(a, raiseit=True) + return a.exp(context=self) + + def fma(self, a, b, c): + """Returns a multiplied by b, plus c. + + The first two operands are multiplied together, using multiply, + the third operand is then added to the result of that + multiplication, using add, all with only one final rounding. + + >>> ExtendedContext.fma(Decimal('3'), Decimal('5'), Decimal('7')) + Decimal('22') + >>> ExtendedContext.fma(Decimal('3'), Decimal('-5'), Decimal('7')) + Decimal('-8') + >>> ExtendedContext.fma(Decimal('888565290'), Decimal('1557.96930'), Decimal('-86087.7578')) + Decimal('1.38435736E+12') + >>> ExtendedContext.fma(1, 3, 4) + Decimal('7') + >>> ExtendedContext.fma(1, Decimal(3), 4) + Decimal('7') + >>> ExtendedContext.fma(1, 3, Decimal(4)) + Decimal('7') + """ + a = _convert_other(a, raiseit=True) + return a.fma(b, c, context=self) + + def is_canonical(self, a): + """Return True if the operand is canonical; otherwise return False. + + Currently, the encoding of a Decimal instance is always + canonical, so this method returns True for any Decimal. + + >>> ExtendedContext.is_canonical(Decimal('2.50')) + True + """ + if not isinstance(a, Decimal): + raise TypeError("is_canonical requires a Decimal as an argument.") + return a.is_canonical() + + def is_finite(self, a): + """Return True if the operand is finite; otherwise return False. + + A Decimal instance is considered finite if it is neither + infinite nor a NaN. + + >>> ExtendedContext.is_finite(Decimal('2.50')) + True + >>> ExtendedContext.is_finite(Decimal('-0.3')) + True + >>> ExtendedContext.is_finite(Decimal('0')) + True + >>> ExtendedContext.is_finite(Decimal('Inf')) + False + >>> ExtendedContext.is_finite(Decimal('NaN')) + False + >>> ExtendedContext.is_finite(1) + True + """ + a = _convert_other(a, raiseit=True) + return a.is_finite() + + def is_infinite(self, a): + """Return True if the operand is infinite; otherwise return False. + + >>> ExtendedContext.is_infinite(Decimal('2.50')) + False + >>> ExtendedContext.is_infinite(Decimal('-Inf')) + True + >>> ExtendedContext.is_infinite(Decimal('NaN')) + False + >>> ExtendedContext.is_infinite(1) + False + """ + a = _convert_other(a, raiseit=True) + return a.is_infinite() + + def is_nan(self, a): + """Return True if the operand is a qNaN or sNaN; + otherwise return False. + + >>> ExtendedContext.is_nan(Decimal('2.50')) + False + >>> ExtendedContext.is_nan(Decimal('NaN')) + True + >>> ExtendedContext.is_nan(Decimal('-sNaN')) + True + >>> ExtendedContext.is_nan(1) + False + """ + a = _convert_other(a, raiseit=True) + return a.is_nan() + + def is_normal(self, a): + """Return True if the operand is a normal number; + otherwise return False. + + >>> c = ExtendedContext.copy() + >>> c.Emin = -999 + >>> c.Emax = 999 + >>> c.is_normal(Decimal('2.50')) + True + >>> c.is_normal(Decimal('0.1E-999')) + False + >>> c.is_normal(Decimal('0.00')) + False + >>> c.is_normal(Decimal('-Inf')) + False + >>> c.is_normal(Decimal('NaN')) + False + >>> c.is_normal(1) + True + """ + a = _convert_other(a, raiseit=True) + return a.is_normal(context=self) + + def is_qnan(self, a): + """Return True if the operand is a quiet NaN; otherwise return False. + + >>> ExtendedContext.is_qnan(Decimal('2.50')) + False + >>> ExtendedContext.is_qnan(Decimal('NaN')) + True + >>> ExtendedContext.is_qnan(Decimal('sNaN')) + False + >>> ExtendedContext.is_qnan(1) + False + """ + a = _convert_other(a, raiseit=True) + return a.is_qnan() + + def is_signed(self, a): + """Return True if the operand is negative; otherwise return False. + + >>> ExtendedContext.is_signed(Decimal('2.50')) + False + >>> ExtendedContext.is_signed(Decimal('-12')) + True + >>> ExtendedContext.is_signed(Decimal('-0')) + True + >>> ExtendedContext.is_signed(8) + False + >>> ExtendedContext.is_signed(-8) + True + """ + a = _convert_other(a, raiseit=True) + return a.is_signed() + + def is_snan(self, a): + """Return True if the operand is a signaling NaN; + otherwise return False. + + >>> ExtendedContext.is_snan(Decimal('2.50')) + False + >>> ExtendedContext.is_snan(Decimal('NaN')) + False + >>> ExtendedContext.is_snan(Decimal('sNaN')) + True + >>> ExtendedContext.is_snan(1) + False + """ + a = _convert_other(a, raiseit=True) + return a.is_snan() + + def is_subnormal(self, a): + """Return True if the operand is subnormal; otherwise return False. + + >>> c = ExtendedContext.copy() + >>> c.Emin = -999 + >>> c.Emax = 999 + >>> c.is_subnormal(Decimal('2.50')) + False + >>> c.is_subnormal(Decimal('0.1E-999')) + True + >>> c.is_subnormal(Decimal('0.00')) + False + >>> c.is_subnormal(Decimal('-Inf')) + False + >>> c.is_subnormal(Decimal('NaN')) + False + >>> c.is_subnormal(1) + False + """ + a = _convert_other(a, raiseit=True) + return a.is_subnormal(context=self) + + def is_zero(self, a): + """Return True if the operand is a zero; otherwise return False. + + >>> ExtendedContext.is_zero(Decimal('0')) + True + >>> ExtendedContext.is_zero(Decimal('2.50')) + False + >>> ExtendedContext.is_zero(Decimal('-0E+2')) + True + >>> ExtendedContext.is_zero(1) + False + >>> ExtendedContext.is_zero(0) + True + """ + a = _convert_other(a, raiseit=True) + return a.is_zero() + + def ln(self, a): + """Returns the natural (base e) logarithm of the operand. + + >>> c = ExtendedContext.copy() + >>> c.Emin = -999 + >>> c.Emax = 999 + >>> c.ln(Decimal('0')) + Decimal('-Infinity') + >>> c.ln(Decimal('1.000')) + Decimal('0') + >>> c.ln(Decimal('2.71828183')) + Decimal('1.00000000') + >>> c.ln(Decimal('10')) + Decimal('2.30258509') + >>> c.ln(Decimal('+Infinity')) + Decimal('Infinity') + >>> c.ln(1) + Decimal('0') + """ + a = _convert_other(a, raiseit=True) + return a.ln(context=self) + + def log10(self, a): + """Returns the base 10 logarithm of the operand. + + >>> c = ExtendedContext.copy() + >>> c.Emin = -999 + >>> c.Emax = 999 + >>> c.log10(Decimal('0')) + Decimal('-Infinity') + >>> c.log10(Decimal('0.001')) + Decimal('-3') + >>> c.log10(Decimal('1.000')) + Decimal('0') + >>> c.log10(Decimal('2')) + Decimal('0.301029996') + >>> c.log10(Decimal('10')) + Decimal('1') + >>> c.log10(Decimal('70')) + Decimal('1.84509804') + >>> c.log10(Decimal('+Infinity')) + Decimal('Infinity') + >>> c.log10(0) + Decimal('-Infinity') + >>> c.log10(1) + Decimal('0') + """ + a = _convert_other(a, raiseit=True) + return a.log10(context=self) + + def logb(self, a): + """ Returns the exponent of the magnitude of the operand's MSD. + + The result is the integer which is the exponent of the magnitude + of the most significant digit of the operand (as though the + operand were truncated to a single digit while maintaining the + value of that digit and without limiting the resulting exponent). + + >>> ExtendedContext.logb(Decimal('250')) + Decimal('2') + >>> ExtendedContext.logb(Decimal('2.50')) + Decimal('0') + >>> ExtendedContext.logb(Decimal('0.03')) + Decimal('-2') + >>> ExtendedContext.logb(Decimal('0')) + Decimal('-Infinity') + >>> ExtendedContext.logb(1) + Decimal('0') + >>> ExtendedContext.logb(10) + Decimal('1') + >>> ExtendedContext.logb(100) + Decimal('2') + """ + a = _convert_other(a, raiseit=True) + return a.logb(context=self) + + def logical_and(self, a, b): + """Applies the logical operation 'and' between each operand's digits. + + The operands must be both logical numbers. + + >>> ExtendedContext.logical_and(Decimal('0'), Decimal('0')) + Decimal('0') + >>> ExtendedContext.logical_and(Decimal('0'), Decimal('1')) + Decimal('0') + >>> ExtendedContext.logical_and(Decimal('1'), Decimal('0')) + Decimal('0') + >>> ExtendedContext.logical_and(Decimal('1'), Decimal('1')) + Decimal('1') + >>> ExtendedContext.logical_and(Decimal('1100'), Decimal('1010')) + Decimal('1000') + >>> ExtendedContext.logical_and(Decimal('1111'), Decimal('10')) + Decimal('10') + >>> ExtendedContext.logical_and(110, 1101) + Decimal('100') + >>> ExtendedContext.logical_and(Decimal(110), 1101) + Decimal('100') + >>> ExtendedContext.logical_and(110, Decimal(1101)) + Decimal('100') + """ + a = _convert_other(a, raiseit=True) + return a.logical_and(b, context=self) + + def logical_invert(self, a): + """Invert all the digits in the operand. + + The operand must be a logical number. + + >>> ExtendedContext.logical_invert(Decimal('0')) + Decimal('111111111') + >>> ExtendedContext.logical_invert(Decimal('1')) + Decimal('111111110') + >>> ExtendedContext.logical_invert(Decimal('111111111')) + Decimal('0') + >>> ExtendedContext.logical_invert(Decimal('101010101')) + Decimal('10101010') + >>> ExtendedContext.logical_invert(1101) + Decimal('111110010') + """ + a = _convert_other(a, raiseit=True) + return a.logical_invert(context=self) + + def logical_or(self, a, b): + """Applies the logical operation 'or' between each operand's digits. + + The operands must be both logical numbers. + + >>> ExtendedContext.logical_or(Decimal('0'), Decimal('0')) + Decimal('0') + >>> ExtendedContext.logical_or(Decimal('0'), Decimal('1')) + Decimal('1') + >>> ExtendedContext.logical_or(Decimal('1'), Decimal('0')) + Decimal('1') + >>> ExtendedContext.logical_or(Decimal('1'), Decimal('1')) + Decimal('1') + >>> ExtendedContext.logical_or(Decimal('1100'), Decimal('1010')) + Decimal('1110') + >>> ExtendedContext.logical_or(Decimal('1110'), Decimal('10')) + Decimal('1110') + >>> ExtendedContext.logical_or(110, 1101) + Decimal('1111') + >>> ExtendedContext.logical_or(Decimal(110), 1101) + Decimal('1111') + >>> ExtendedContext.logical_or(110, Decimal(1101)) + Decimal('1111') + """ + a = _convert_other(a, raiseit=True) + return a.logical_or(b, context=self) + + def logical_xor(self, a, b): + """Applies the logical operation 'xor' between each operand's digits. + + The operands must be both logical numbers. + + >>> ExtendedContext.logical_xor(Decimal('0'), Decimal('0')) + Decimal('0') + >>> ExtendedContext.logical_xor(Decimal('0'), Decimal('1')) + Decimal('1') + >>> ExtendedContext.logical_xor(Decimal('1'), Decimal('0')) + Decimal('1') + >>> ExtendedContext.logical_xor(Decimal('1'), Decimal('1')) + Decimal('0') + >>> ExtendedContext.logical_xor(Decimal('1100'), Decimal('1010')) + Decimal('110') + >>> ExtendedContext.logical_xor(Decimal('1111'), Decimal('10')) + Decimal('1101') + >>> ExtendedContext.logical_xor(110, 1101) + Decimal('1011') + >>> ExtendedContext.logical_xor(Decimal(110), 1101) + Decimal('1011') + >>> ExtendedContext.logical_xor(110, Decimal(1101)) + Decimal('1011') + """ + a = _convert_other(a, raiseit=True) + return a.logical_xor(b, context=self) + + def max(self, a, b): + """max compares two values numerically and returns the maximum. + + If either operand is a NaN then the general rules apply. + Otherwise, the operands are compared as though by the compare + operation. If they are numerically equal then the left-hand operand + is chosen as the result. Otherwise the maximum (closer to positive + infinity) of the two operands is chosen as the result. + + >>> ExtendedContext.max(Decimal('3'), Decimal('2')) + Decimal('3') + >>> ExtendedContext.max(Decimal('-10'), Decimal('3')) + Decimal('3') + >>> ExtendedContext.max(Decimal('1.0'), Decimal('1')) + Decimal('1') + >>> ExtendedContext.max(Decimal('7'), Decimal('NaN')) + Decimal('7') + >>> ExtendedContext.max(1, 2) + Decimal('2') + >>> ExtendedContext.max(Decimal(1), 2) + Decimal('2') + >>> ExtendedContext.max(1, Decimal(2)) + Decimal('2') + """ + a = _convert_other(a, raiseit=True) + return a.max(b, context=self) + + def max_mag(self, a, b): + """Compares the values numerically with their sign ignored. + + >>> ExtendedContext.max_mag(Decimal('7'), Decimal('NaN')) + Decimal('7') + >>> ExtendedContext.max_mag(Decimal('7'), Decimal('-10')) + Decimal('-10') + >>> ExtendedContext.max_mag(1, -2) + Decimal('-2') + >>> ExtendedContext.max_mag(Decimal(1), -2) + Decimal('-2') + >>> ExtendedContext.max_mag(1, Decimal(-2)) + Decimal('-2') + """ + a = _convert_other(a, raiseit=True) + return a.max_mag(b, context=self) + + def min(self, a, b): + """min compares two values numerically and returns the minimum. + + If either operand is a NaN then the general rules apply. + Otherwise, the operands are compared as though by the compare + operation. If they are numerically equal then the left-hand operand + is chosen as the result. Otherwise the minimum (closer to negative + infinity) of the two operands is chosen as the result. + + >>> ExtendedContext.min(Decimal('3'), Decimal('2')) + Decimal('2') + >>> ExtendedContext.min(Decimal('-10'), Decimal('3')) + Decimal('-10') + >>> ExtendedContext.min(Decimal('1.0'), Decimal('1')) + Decimal('1.0') + >>> ExtendedContext.min(Decimal('7'), Decimal('NaN')) + Decimal('7') + >>> ExtendedContext.min(1, 2) + Decimal('1') + >>> ExtendedContext.min(Decimal(1), 2) + Decimal('1') + >>> ExtendedContext.min(1, Decimal(29)) + Decimal('1') + """ + a = _convert_other(a, raiseit=True) + return a.min(b, context=self) + + def min_mag(self, a, b): + """Compares the values numerically with their sign ignored. + + >>> ExtendedContext.min_mag(Decimal('3'), Decimal('-2')) + Decimal('-2') + >>> ExtendedContext.min_mag(Decimal('-3'), Decimal('NaN')) + Decimal('-3') + >>> ExtendedContext.min_mag(1, -2) + Decimal('1') + >>> ExtendedContext.min_mag(Decimal(1), -2) + Decimal('1') + >>> ExtendedContext.min_mag(1, Decimal(-2)) + Decimal('1') + """ + a = _convert_other(a, raiseit=True) + return a.min_mag(b, context=self) + + def minus(self, a): + """Minus corresponds to unary prefix minus in Python. + + The operation is evaluated using the same rules as subtract; the + operation minus(a) is calculated as subtract('0', a) where the '0' + has the same exponent as the operand. + + >>> ExtendedContext.minus(Decimal('1.3')) + Decimal('-1.3') + >>> ExtendedContext.minus(Decimal('-1.3')) + Decimal('1.3') + >>> ExtendedContext.minus(1) + Decimal('-1') + """ + a = _convert_other(a, raiseit=True) + return a.__neg__(context=self) + + def multiply(self, a, b): + """multiply multiplies two operands. + + If either operand is a special value then the general rules apply. + Otherwise, the operands are multiplied together + ('long multiplication'), resulting in a number which may be as long as + the sum of the lengths of the two operands. + + >>> ExtendedContext.multiply(Decimal('1.20'), Decimal('3')) + Decimal('3.60') + >>> ExtendedContext.multiply(Decimal('7'), Decimal('3')) + Decimal('21') + >>> ExtendedContext.multiply(Decimal('0.9'), Decimal('0.8')) + Decimal('0.72') + >>> ExtendedContext.multiply(Decimal('0.9'), Decimal('-0')) + Decimal('-0.0') + >>> ExtendedContext.multiply(Decimal('654321'), Decimal('654321')) + Decimal('4.28135971E+11') + >>> ExtendedContext.multiply(7, 7) + Decimal('49') + >>> ExtendedContext.multiply(Decimal(7), 7) + Decimal('49') + >>> ExtendedContext.multiply(7, Decimal(7)) + Decimal('49') + """ + a = _convert_other(a, raiseit=True) + r = a.__mul__(b, context=self) + if r is NotImplemented: + raise TypeError("Unable to convert %s to Decimal" % b) + else: + return r + + def next_minus(self, a): + """Returns the largest representable number smaller than a. + + >>> c = ExtendedContext.copy() + >>> c.Emin = -999 + >>> c.Emax = 999 + >>> ExtendedContext.next_minus(Decimal('1')) + Decimal('0.999999999') + >>> c.next_minus(Decimal('1E-1007')) + Decimal('0E-1007') + >>> ExtendedContext.next_minus(Decimal('-1.00000003')) + Decimal('-1.00000004') + >>> c.next_minus(Decimal('Infinity')) + Decimal('9.99999999E+999') + >>> c.next_minus(1) + Decimal('0.999999999') + """ + a = _convert_other(a, raiseit=True) + return a.next_minus(context=self) + + def next_plus(self, a): + """Returns the smallest representable number larger than a. + + >>> c = ExtendedContext.copy() + >>> c.Emin = -999 + >>> c.Emax = 999 + >>> ExtendedContext.next_plus(Decimal('1')) + Decimal('1.00000001') + >>> c.next_plus(Decimal('-1E-1007')) + Decimal('-0E-1007') + >>> ExtendedContext.next_plus(Decimal('-1.00000003')) + Decimal('-1.00000002') + >>> c.next_plus(Decimal('-Infinity')) + Decimal('-9.99999999E+999') + >>> c.next_plus(1) + Decimal('1.00000001') + """ + a = _convert_other(a, raiseit=True) + return a.next_plus(context=self) + + def next_toward(self, a, b): + """Returns the number closest to a, in direction towards b. + + The result is the closest representable number from the first + operand (but not the first operand) that is in the direction + towards the second operand, unless the operands have the same + value. + + >>> c = ExtendedContext.copy() + >>> c.Emin = -999 + >>> c.Emax = 999 + >>> c.next_toward(Decimal('1'), Decimal('2')) + Decimal('1.00000001') + >>> c.next_toward(Decimal('-1E-1007'), Decimal('1')) + Decimal('-0E-1007') + >>> c.next_toward(Decimal('-1.00000003'), Decimal('0')) + Decimal('-1.00000002') + >>> c.next_toward(Decimal('1'), Decimal('0')) + Decimal('0.999999999') + >>> c.next_toward(Decimal('1E-1007'), Decimal('-100')) + Decimal('0E-1007') + >>> c.next_toward(Decimal('-1.00000003'), Decimal('-10')) + Decimal('-1.00000004') + >>> c.next_toward(Decimal('0.00'), Decimal('-0.0000')) + Decimal('-0.00') + >>> c.next_toward(0, 1) + Decimal('1E-1007') + >>> c.next_toward(Decimal(0), 1) + Decimal('1E-1007') + >>> c.next_toward(0, Decimal(1)) + Decimal('1E-1007') + """ + a = _convert_other(a, raiseit=True) + return a.next_toward(b, context=self) + + def normalize(self, a): + """normalize reduces an operand to its simplest form. + + Essentially a plus operation with all trailing zeros removed from the + result. + + >>> ExtendedContext.normalize(Decimal('2.1')) + Decimal('2.1') + >>> ExtendedContext.normalize(Decimal('-2.0')) + Decimal('-2') + >>> ExtendedContext.normalize(Decimal('1.200')) + Decimal('1.2') + >>> ExtendedContext.normalize(Decimal('-120')) + Decimal('-1.2E+2') + >>> ExtendedContext.normalize(Decimal('120.00')) + Decimal('1.2E+2') + >>> ExtendedContext.normalize(Decimal('0.00')) + Decimal('0') + >>> ExtendedContext.normalize(6) + Decimal('6') + """ + a = _convert_other(a, raiseit=True) + return a.normalize(context=self) + + def number_class(self, a): + """Returns an indication of the class of the operand. + + The class is one of the following strings: + -sNaN + -NaN + -Infinity + -Normal + -Subnormal + -Zero + +Zero + +Subnormal + +Normal + +Infinity + + >>> c = ExtendedContext.copy() + >>> c.Emin = -999 + >>> c.Emax = 999 + >>> c.number_class(Decimal('Infinity')) + '+Infinity' + >>> c.number_class(Decimal('1E-10')) + '+Normal' + >>> c.number_class(Decimal('2.50')) + '+Normal' + >>> c.number_class(Decimal('0.1E-999')) + '+Subnormal' + >>> c.number_class(Decimal('0')) + '+Zero' + >>> c.number_class(Decimal('-0')) + '-Zero' + >>> c.number_class(Decimal('-0.1E-999')) + '-Subnormal' + >>> c.number_class(Decimal('-1E-10')) + '-Normal' + >>> c.number_class(Decimal('-2.50')) + '-Normal' + >>> c.number_class(Decimal('-Infinity')) + '-Infinity' + >>> c.number_class(Decimal('NaN')) + 'NaN' + >>> c.number_class(Decimal('-NaN')) + 'NaN' + >>> c.number_class(Decimal('sNaN')) + 'sNaN' + >>> c.number_class(123) + '+Normal' + """ + a = _convert_other(a, raiseit=True) + return a.number_class(context=self) + + def plus(self, a): + """Plus corresponds to unary prefix plus in Python. + + The operation is evaluated using the same rules as add; the + operation plus(a) is calculated as add('0', a) where the '0' + has the same exponent as the operand. + + >>> ExtendedContext.plus(Decimal('1.3')) + Decimal('1.3') + >>> ExtendedContext.plus(Decimal('-1.3')) + Decimal('-1.3') + >>> ExtendedContext.plus(-1) + Decimal('-1') + """ + a = _convert_other(a, raiseit=True) + return a.__pos__(context=self) + + def power(self, a, b, modulo=None): + """Raises a to the power of b, to modulo if given. + + With two arguments, compute a**b. If a is negative then b + must be integral. The result will be inexact unless b is + integral and the result is finite and can be expressed exactly + in 'precision' digits. + + With three arguments, compute (a**b) % modulo. For the + three argument form, the following restrictions on the + arguments hold: + + - all three arguments must be integral + - b must be nonnegative + - at least one of a or b must be nonzero + - modulo must be nonzero and have at most 'precision' digits + + The result of pow(a, b, modulo) is identical to the result + that would be obtained by computing (a**b) % modulo with + unbounded precision, but is computed more efficiently. It is + always exact. + + >>> c = ExtendedContext.copy() + >>> c.Emin = -999 + >>> c.Emax = 999 + >>> c.power(Decimal('2'), Decimal('3')) + Decimal('8') + >>> c.power(Decimal('-2'), Decimal('3')) + Decimal('-8') + >>> c.power(Decimal('2'), Decimal('-3')) + Decimal('0.125') + >>> c.power(Decimal('1.7'), Decimal('8')) + Decimal('69.7575744') + >>> c.power(Decimal('10'), Decimal('0.301029996')) + Decimal('2.00000000') + >>> c.power(Decimal('Infinity'), Decimal('-1')) + Decimal('0') + >>> c.power(Decimal('Infinity'), Decimal('0')) + Decimal('1') + >>> c.power(Decimal('Infinity'), Decimal('1')) + Decimal('Infinity') + >>> c.power(Decimal('-Infinity'), Decimal('-1')) + Decimal('-0') + >>> c.power(Decimal('-Infinity'), Decimal('0')) + Decimal('1') + >>> c.power(Decimal('-Infinity'), Decimal('1')) + Decimal('-Infinity') + >>> c.power(Decimal('-Infinity'), Decimal('2')) + Decimal('Infinity') + >>> c.power(Decimal('0'), Decimal('0')) + Decimal('NaN') + + >>> c.power(Decimal('3'), Decimal('7'), Decimal('16')) + Decimal('11') + >>> c.power(Decimal('-3'), Decimal('7'), Decimal('16')) + Decimal('-11') + >>> c.power(Decimal('-3'), Decimal('8'), Decimal('16')) + Decimal('1') + >>> c.power(Decimal('3'), Decimal('7'), Decimal('-16')) + Decimal('11') + >>> c.power(Decimal('23E12345'), Decimal('67E189'), Decimal('123456789')) + Decimal('11729830') + >>> c.power(Decimal('-0'), Decimal('17'), Decimal('1729')) + Decimal('-0') + >>> c.power(Decimal('-23'), Decimal('0'), Decimal('65537')) + Decimal('1') + >>> ExtendedContext.power(7, 7) + Decimal('823543') + >>> ExtendedContext.power(Decimal(7), 7) + Decimal('823543') + >>> ExtendedContext.power(7, Decimal(7), 2) + Decimal('1') + """ + a = _convert_other(a, raiseit=True) + r = a.__pow__(b, modulo, context=self) + if r is NotImplemented: + raise TypeError("Unable to convert %s to Decimal" % b) + else: + return r + + def quantize(self, a, b): + """Returns a value equal to 'a' (rounded), having the exponent of 'b'. + + The coefficient of the result is derived from that of the left-hand + operand. It may be rounded using the current rounding setting (if the + exponent is being increased), multiplied by a positive power of ten (if + the exponent is being decreased), or is unchanged (if the exponent is + already equal to that of the right-hand operand). + + Unlike other operations, if the length of the coefficient after the + quantize operation would be greater than precision then an Invalid + operation condition is raised. This guarantees that, unless there is + an error condition, the exponent of the result of a quantize is always + equal to that of the right-hand operand. + + Also unlike other operations, quantize will never raise Underflow, even + if the result is subnormal and inexact. + + >>> ExtendedContext.quantize(Decimal('2.17'), Decimal('0.001')) + Decimal('2.170') + >>> ExtendedContext.quantize(Decimal('2.17'), Decimal('0.01')) + Decimal('2.17') + >>> ExtendedContext.quantize(Decimal('2.17'), Decimal('0.1')) + Decimal('2.2') + >>> ExtendedContext.quantize(Decimal('2.17'), Decimal('1e+0')) + Decimal('2') + >>> ExtendedContext.quantize(Decimal('2.17'), Decimal('1e+1')) + Decimal('0E+1') + >>> ExtendedContext.quantize(Decimal('-Inf'), Decimal('Infinity')) + Decimal('-Infinity') + >>> ExtendedContext.quantize(Decimal('2'), Decimal('Infinity')) + Decimal('NaN') + >>> ExtendedContext.quantize(Decimal('-0.1'), Decimal('1')) + Decimal('-0') + >>> ExtendedContext.quantize(Decimal('-0'), Decimal('1e+5')) + Decimal('-0E+5') + >>> ExtendedContext.quantize(Decimal('+35236450.6'), Decimal('1e-2')) + Decimal('NaN') + >>> ExtendedContext.quantize(Decimal('-35236450.6'), Decimal('1e-2')) + Decimal('NaN') + >>> ExtendedContext.quantize(Decimal('217'), Decimal('1e-1')) + Decimal('217.0') + >>> ExtendedContext.quantize(Decimal('217'), Decimal('1e-0')) + Decimal('217') + >>> ExtendedContext.quantize(Decimal('217'), Decimal('1e+1')) + Decimal('2.2E+2') + >>> ExtendedContext.quantize(Decimal('217'), Decimal('1e+2')) + Decimal('2E+2') + >>> ExtendedContext.quantize(1, 2) + Decimal('1') + >>> ExtendedContext.quantize(Decimal(1), 2) + Decimal('1') + >>> ExtendedContext.quantize(1, Decimal(2)) + Decimal('1') + """ + a = _convert_other(a, raiseit=True) + return a.quantize(b, context=self) + + def radix(self): + """Just returns 10, as this is Decimal, :) + + >>> ExtendedContext.radix() + Decimal('10') + """ + return Decimal(10) + + def remainder(self, a, b): + """Returns the remainder from integer division. + + The result is the residue of the dividend after the operation of + calculating integer division as described for divide-integer, rounded + to precision digits if necessary. The sign of the result, if + non-zero, is the same as that of the original dividend. + + This operation will fail under the same conditions as integer division + (that is, if integer division on the same two operands would fail, the + remainder cannot be calculated). + + >>> ExtendedContext.remainder(Decimal('2.1'), Decimal('3')) + Decimal('2.1') + >>> ExtendedContext.remainder(Decimal('10'), Decimal('3')) + Decimal('1') + >>> ExtendedContext.remainder(Decimal('-10'), Decimal('3')) + Decimal('-1') + >>> ExtendedContext.remainder(Decimal('10.2'), Decimal('1')) + Decimal('0.2') + >>> ExtendedContext.remainder(Decimal('10'), Decimal('0.3')) + Decimal('0.1') + >>> ExtendedContext.remainder(Decimal('3.6'), Decimal('1.3')) + Decimal('1.0') + >>> ExtendedContext.remainder(22, 6) + Decimal('4') + >>> ExtendedContext.remainder(Decimal(22), 6) + Decimal('4') + >>> ExtendedContext.remainder(22, Decimal(6)) + Decimal('4') + """ + a = _convert_other(a, raiseit=True) + r = a.__mod__(b, context=self) + if r is NotImplemented: + raise TypeError("Unable to convert %s to Decimal" % b) + else: + return r + + def remainder_near(self, a, b): + """Returns to be "a - b * n", where n is the integer nearest the exact + value of "x / b" (if two integers are equally near then the even one + is chosen). If the result is equal to 0 then its sign will be the + sign of a. + + This operation will fail under the same conditions as integer division + (that is, if integer division on the same two operands would fail, the + remainder cannot be calculated). + + >>> ExtendedContext.remainder_near(Decimal('2.1'), Decimal('3')) + Decimal('-0.9') + >>> ExtendedContext.remainder_near(Decimal('10'), Decimal('6')) + Decimal('-2') + >>> ExtendedContext.remainder_near(Decimal('10'), Decimal('3')) + Decimal('1') + >>> ExtendedContext.remainder_near(Decimal('-10'), Decimal('3')) + Decimal('-1') + >>> ExtendedContext.remainder_near(Decimal('10.2'), Decimal('1')) + Decimal('0.2') + >>> ExtendedContext.remainder_near(Decimal('10'), Decimal('0.3')) + Decimal('0.1') + >>> ExtendedContext.remainder_near(Decimal('3.6'), Decimal('1.3')) + Decimal('-0.3') + >>> ExtendedContext.remainder_near(3, 11) + Decimal('3') + >>> ExtendedContext.remainder_near(Decimal(3), 11) + Decimal('3') + >>> ExtendedContext.remainder_near(3, Decimal(11)) + Decimal('3') + """ + a = _convert_other(a, raiseit=True) + return a.remainder_near(b, context=self) + + def rotate(self, a, b): + """Returns a rotated copy of a, b times. + + The coefficient of the result is a rotated copy of the digits in + the coefficient of the first operand. The number of places of + rotation is taken from the absolute value of the second operand, + with the rotation being to the left if the second operand is + positive or to the right otherwise. + + >>> ExtendedContext.rotate(Decimal('34'), Decimal('8')) + Decimal('400000003') + >>> ExtendedContext.rotate(Decimal('12'), Decimal('9')) + Decimal('12') + >>> ExtendedContext.rotate(Decimal('123456789'), Decimal('-2')) + Decimal('891234567') + >>> ExtendedContext.rotate(Decimal('123456789'), Decimal('0')) + Decimal('123456789') + >>> ExtendedContext.rotate(Decimal('123456789'), Decimal('+2')) + Decimal('345678912') + >>> ExtendedContext.rotate(1333333, 1) + Decimal('13333330') + >>> ExtendedContext.rotate(Decimal(1333333), 1) + Decimal('13333330') + >>> ExtendedContext.rotate(1333333, Decimal(1)) + Decimal('13333330') + """ + a = _convert_other(a, raiseit=True) + return a.rotate(b, context=self) + + def same_quantum(self, a, b): + """Returns True if the two operands have the same exponent. + + The result is never affected by either the sign or the coefficient of + either operand. + + >>> ExtendedContext.same_quantum(Decimal('2.17'), Decimal('0.001')) + False + >>> ExtendedContext.same_quantum(Decimal('2.17'), Decimal('0.01')) + True + >>> ExtendedContext.same_quantum(Decimal('2.17'), Decimal('1')) + False + >>> ExtendedContext.same_quantum(Decimal('Inf'), Decimal('-Inf')) + True + >>> ExtendedContext.same_quantum(10000, -1) + True + >>> ExtendedContext.same_quantum(Decimal(10000), -1) + True + >>> ExtendedContext.same_quantum(10000, Decimal(-1)) + True + """ + a = _convert_other(a, raiseit=True) + return a.same_quantum(b) + + def scaleb (self, a, b): + """Returns the first operand after adding the second value its exp. + + >>> ExtendedContext.scaleb(Decimal('7.50'), Decimal('-2')) + Decimal('0.0750') + >>> ExtendedContext.scaleb(Decimal('7.50'), Decimal('0')) + Decimal('7.50') + >>> ExtendedContext.scaleb(Decimal('7.50'), Decimal('3')) + Decimal('7.50E+3') + >>> ExtendedContext.scaleb(1, 4) + Decimal('1E+4') + >>> ExtendedContext.scaleb(Decimal(1), 4) + Decimal('1E+4') + >>> ExtendedContext.scaleb(1, Decimal(4)) + Decimal('1E+4') + """ + a = _convert_other(a, raiseit=True) + return a.scaleb(b, context=self) + + def shift(self, a, b): + """Returns a shifted copy of a, b times. + + The coefficient of the result is a shifted copy of the digits + in the coefficient of the first operand. The number of places + to shift is taken from the absolute value of the second operand, + with the shift being to the left if the second operand is + positive or to the right otherwise. Digits shifted into the + coefficient are zeros. + + >>> ExtendedContext.shift(Decimal('34'), Decimal('8')) + Decimal('400000000') + >>> ExtendedContext.shift(Decimal('12'), Decimal('9')) + Decimal('0') + >>> ExtendedContext.shift(Decimal('123456789'), Decimal('-2')) + Decimal('1234567') + >>> ExtendedContext.shift(Decimal('123456789'), Decimal('0')) + Decimal('123456789') + >>> ExtendedContext.shift(Decimal('123456789'), Decimal('+2')) + Decimal('345678900') + >>> ExtendedContext.shift(88888888, 2) + Decimal('888888800') + >>> ExtendedContext.shift(Decimal(88888888), 2) + Decimal('888888800') + >>> ExtendedContext.shift(88888888, Decimal(2)) + Decimal('888888800') + """ + a = _convert_other(a, raiseit=True) + return a.shift(b, context=self) + + def sqrt(self, a): + """Square root of a non-negative number to context precision. + + If the result must be inexact, it is rounded using the round-half-even + algorithm. + + >>> ExtendedContext.sqrt(Decimal('0')) + Decimal('0') + >>> ExtendedContext.sqrt(Decimal('-0')) + Decimal('-0') + >>> ExtendedContext.sqrt(Decimal('0.39')) + Decimal('0.624499800') + >>> ExtendedContext.sqrt(Decimal('100')) + Decimal('10') + >>> ExtendedContext.sqrt(Decimal('1')) + Decimal('1') + >>> ExtendedContext.sqrt(Decimal('1.0')) + Decimal('1.0') + >>> ExtendedContext.sqrt(Decimal('1.00')) + Decimal('1.0') + >>> ExtendedContext.sqrt(Decimal('7')) + Decimal('2.64575131') + >>> ExtendedContext.sqrt(Decimal('10')) + Decimal('3.16227766') + >>> ExtendedContext.sqrt(2) + Decimal('1.41421356') + >>> ExtendedContext.prec + 9 + """ + a = _convert_other(a, raiseit=True) + return a.sqrt(context=self) + + def subtract(self, a, b): + """Return the difference between the two operands. + + >>> ExtendedContext.subtract(Decimal('1.3'), Decimal('1.07')) + Decimal('0.23') + >>> ExtendedContext.subtract(Decimal('1.3'), Decimal('1.30')) + Decimal('0.00') + >>> ExtendedContext.subtract(Decimal('1.3'), Decimal('2.07')) + Decimal('-0.77') + >>> ExtendedContext.subtract(8, 5) + Decimal('3') + >>> ExtendedContext.subtract(Decimal(8), 5) + Decimal('3') + >>> ExtendedContext.subtract(8, Decimal(5)) + Decimal('3') + """ + a = _convert_other(a, raiseit=True) + r = a.__sub__(b, context=self) + if r is NotImplemented: + raise TypeError("Unable to convert %s to Decimal" % b) + else: + return r + + def to_eng_string(self, a): + """Converts a number to a string, using scientific notation. + + The operation is not affected by the context. + """ + a = _convert_other(a, raiseit=True) + return a.to_eng_string(context=self) + + def to_sci_string(self, a): + """Converts a number to a string, using scientific notation. + + The operation is not affected by the context. + """ + a = _convert_other(a, raiseit=True) + return a.__str__(context=self) + + def to_integral_exact(self, a): + """Rounds to an integer. + + When the operand has a negative exponent, the result is the same + as using the quantize() operation using the given operand as the + left-hand-operand, 1E+0 as the right-hand-operand, and the precision + of the operand as the precision setting; Inexact and Rounded flags + are allowed in this operation. The rounding mode is taken from the + context. + + >>> ExtendedContext.to_integral_exact(Decimal('2.1')) + Decimal('2') + >>> ExtendedContext.to_integral_exact(Decimal('100')) + Decimal('100') + >>> ExtendedContext.to_integral_exact(Decimal('100.0')) + Decimal('100') + >>> ExtendedContext.to_integral_exact(Decimal('101.5')) + Decimal('102') + >>> ExtendedContext.to_integral_exact(Decimal('-101.5')) + Decimal('-102') + >>> ExtendedContext.to_integral_exact(Decimal('10E+5')) + Decimal('1.0E+6') + >>> ExtendedContext.to_integral_exact(Decimal('7.89E+77')) + Decimal('7.89E+77') + >>> ExtendedContext.to_integral_exact(Decimal('-Inf')) + Decimal('-Infinity') + """ + a = _convert_other(a, raiseit=True) + return a.to_integral_exact(context=self) + + def to_integral_value(self, a): + """Rounds to an integer. + + When the operand has a negative exponent, the result is the same + as using the quantize() operation using the given operand as the + left-hand-operand, 1E+0 as the right-hand-operand, and the precision + of the operand as the precision setting, except that no flags will + be set. The rounding mode is taken from the context. + + >>> ExtendedContext.to_integral_value(Decimal('2.1')) + Decimal('2') + >>> ExtendedContext.to_integral_value(Decimal('100')) + Decimal('100') + >>> ExtendedContext.to_integral_value(Decimal('100.0')) + Decimal('100') + >>> ExtendedContext.to_integral_value(Decimal('101.5')) + Decimal('102') + >>> ExtendedContext.to_integral_value(Decimal('-101.5')) + Decimal('-102') + >>> ExtendedContext.to_integral_value(Decimal('10E+5')) + Decimal('1.0E+6') + >>> ExtendedContext.to_integral_value(Decimal('7.89E+77')) + Decimal('7.89E+77') + >>> ExtendedContext.to_integral_value(Decimal('-Inf')) + Decimal('-Infinity') + """ + a = _convert_other(a, raiseit=True) + return a.to_integral_value(context=self) + + # the method name changed, but we provide also the old one, for compatibility + to_integral = to_integral_value + +class _WorkRep(object): + __slots__ = ('sign','int','exp') + # sign: 0 or 1 + # int: int + # exp: None, int, or string + + def __init__(self, value=None): + if value is None: + self.sign = None + self.int = 0 + self.exp = None + elif isinstance(value, Decimal): + self.sign = value._sign + self.int = int(value._int) + self.exp = value._exp + else: + # assert isinstance(value, tuple) + self.sign = value[0] + self.int = value[1] + self.exp = value[2] + + def __repr__(self): + return "(%r, %r, %r)" % (self.sign, self.int, self.exp) + + __str__ = __repr__ + + + +def _normalize(op1, op2, prec = 0): + """Normalizes op1, op2 to have the same exp and length of coefficient. + + Done during addition. + """ + if op1.exp < op2.exp: + tmp = op2 + other = op1 + else: + tmp = op1 + other = op2 + + # Let exp = min(tmp.exp - 1, tmp.adjusted() - precision - 1). + # Then adding 10**exp to tmp has the same effect (after rounding) + # as adding any positive quantity smaller than 10**exp; similarly + # for subtraction. So if other is smaller than 10**exp we replace + # it with 10**exp. This avoids tmp.exp - other.exp getting too large. + tmp_len = len(str(tmp.int)) + other_len = len(str(other.int)) + exp = tmp.exp + min(-1, tmp_len - prec - 2) + if other_len + other.exp - 1 < exp: + other.int = 1 + other.exp = exp + + tmp.int *= 10 ** (tmp.exp - other.exp) + tmp.exp = other.exp + return op1, op2 + +##### Integer arithmetic functions used by ln, log10, exp and __pow__ ##### + +_nbits = int.bit_length + +def _decimal_lshift_exact(n, e): + """ Given integers n and e, return n * 10**e if it's an integer, else None. + + The computation is designed to avoid computing large powers of 10 + unnecessarily. + + >>> _decimal_lshift_exact(3, 4) + 30000 + >>> _decimal_lshift_exact(300, -999999999) # returns None + + """ + if n == 0: + return 0 + elif e >= 0: + return n * 10**e + else: + # val_n = largest power of 10 dividing n. + str_n = str(abs(n)) + val_n = len(str_n) - len(str_n.rstrip('0')) + return None if val_n < -e else n // 10**-e + +def _sqrt_nearest(n, a): + """Closest integer to the square root of the positive integer n. a is + an initial approximation to the square root. Any positive integer + will do for a, but the closer a is to the square root of n the + faster convergence will be. + + """ + if n <= 0 or a <= 0: + raise ValueError("Both arguments to _sqrt_nearest should be positive.") + + b=0 + while a != b: + b, a = a, a--n//a>>1 + return a + +def _rshift_nearest(x, shift): + """Given an integer x and a nonnegative integer shift, return closest + integer to x / 2**shift; use round-to-even in case of a tie. + + """ + b, q = 1 << shift, x >> shift + return q + (2*(x & (b-1)) + (q&1) > b) + +def _div_nearest(a, b): + """Closest integer to a/b, a and b positive integers; rounds to even + in the case of a tie. + + """ + q, r = divmod(a, b) + return q + (2*r + (q&1) > b) + +def _ilog(x, M, L = 8): + """Integer approximation to M*log(x/M), with absolute error boundable + in terms only of x/M. + + Given positive integers x and M, return an integer approximation to + M * log(x/M). For L = 8 and 0.1 <= x/M <= 10 the difference + between the approximation and the exact result is at most 22. For + L = 8 and 1.0 <= x/M <= 10.0 the difference is at most 15. In + both cases these are upper bounds on the error; it will usually be + much smaller.""" + + # The basic algorithm is the following: let log1p be the function + # log1p(x) = log(1+x). Then log(x/M) = log1p((x-M)/M). We use + # the reduction + # + # log1p(y) = 2*log1p(y/(1+sqrt(1+y))) + # + # repeatedly until the argument to log1p is small (< 2**-L in + # absolute value). For small y we can use the Taylor series + # expansion + # + # log1p(y) ~ y - y**2/2 + y**3/3 - ... - (-y)**T/T + # + # truncating at T such that y**T is small enough. The whole + # computation is carried out in a form of fixed-point arithmetic, + # with a real number z being represented by an integer + # approximation to z*M. To avoid loss of precision, the y below + # is actually an integer approximation to 2**R*y*M, where R is the + # number of reductions performed so far. + + y = x-M + # argument reduction; R = number of reductions performed + R = 0 + while (R <= L and abs(y) << L-R >= M or + R > L and abs(y) >> R-L >= M): + y = _div_nearest((M*y) << 1, + M + _sqrt_nearest(M*(M+_rshift_nearest(y, R)), M)) + R += 1 + + # Taylor series with T terms + T = -int(-10*len(str(M))//(3*L)) + yshift = _rshift_nearest(y, R) + w = _div_nearest(M, T) + for k in range(T-1, 0, -1): + w = _div_nearest(M, k) - _div_nearest(yshift*w, M) + + return _div_nearest(w*y, M) + +def _dlog10(c, e, p): + """Given integers c, e and p with c > 0, p >= 0, compute an integer + approximation to 10**p * log10(c*10**e), with an absolute error of + at most 1. Assumes that c*10**e is not exactly 1.""" + + # increase precision by 2; compensate for this by dividing + # final result by 100 + p += 2 + + # write c*10**e as d*10**f with either: + # f >= 0 and 1 <= d <= 10, or + # f <= 0 and 0.1 <= d <= 1. + # Thus for c*10**e close to 1, f = 0 + l = len(str(c)) + f = e+l - (e+l >= 1) + + if p > 0: + M = 10**p + k = e+p-f + if k >= 0: + c *= 10**k + else: + c = _div_nearest(c, 10**-k) + + log_d = _ilog(c, M) # error < 5 + 22 = 27 + log_10 = _log10_digits(p) # error < 1 + log_d = _div_nearest(log_d*M, log_10) + log_tenpower = f*M # exact + else: + log_d = 0 # error < 2.31 + log_tenpower = _div_nearest(f, 10**-p) # error < 0.5 + + return _div_nearest(log_tenpower+log_d, 100) + +def _dlog(c, e, p): + """Given integers c, e and p with c > 0, compute an integer + approximation to 10**p * log(c*10**e), with an absolute error of + at most 1. Assumes that c*10**e is not exactly 1.""" + + # Increase precision by 2. The precision increase is compensated + # for at the end with a division by 100. + p += 2 + + # rewrite c*10**e as d*10**f with either f >= 0 and 1 <= d <= 10, + # or f <= 0 and 0.1 <= d <= 1. Then we can compute 10**p * log(c*10**e) + # as 10**p * log(d) + 10**p*f * log(10). + l = len(str(c)) + f = e+l - (e+l >= 1) + + # compute approximation to 10**p*log(d), with error < 27 + if p > 0: + k = e+p-f + if k >= 0: + c *= 10**k + else: + c = _div_nearest(c, 10**-k) # error of <= 0.5 in c + + # _ilog magnifies existing error in c by a factor of at most 10 + log_d = _ilog(c, 10**p) # error < 5 + 22 = 27 + else: + # p <= 0: just approximate the whole thing by 0; error < 2.31 + log_d = 0 + + # compute approximation to f*10**p*log(10), with error < 11. + if f: + extra = len(str(abs(f)))-1 + if p + extra >= 0: + # error in f * _log10_digits(p+extra) < |f| * 1 = |f| + # after division, error < |f|/10**extra + 0.5 < 10 + 0.5 < 11 + f_log_ten = _div_nearest(f*_log10_digits(p+extra), 10**extra) + else: + f_log_ten = 0 + else: + f_log_ten = 0 + + # error in sum < 11+27 = 38; error after division < 0.38 + 0.5 < 1 + return _div_nearest(f_log_ten + log_d, 100) + +class _Log10Memoize(object): + """Class to compute, store, and allow retrieval of, digits of the + constant log(10) = 2.302585.... This constant is needed by + Decimal.ln, Decimal.log10, Decimal.exp and Decimal.__pow__.""" + def __init__(self): + self.digits = "23025850929940456840179914546843642076011014886" + + def getdigits(self, p): + """Given an integer p >= 0, return floor(10**p)*log(10). + + For example, self.getdigits(3) returns 2302. + """ + # digits are stored as a string, for quick conversion to + # integer in the case that we've already computed enough + # digits; the stored digits should always be correct + # (truncated, not rounded to nearest). + if p < 0: + raise ValueError("p should be nonnegative") + + if p >= len(self.digits): + # compute p+3, p+6, p+9, ... digits; continue until at + # least one of the extra digits is nonzero + extra = 3 + while True: + # compute p+extra digits, correct to within 1ulp + M = 10**(p+extra+2) + digits = str(_div_nearest(_ilog(10*M, M), 100)) + if digits[-extra:] != '0'*extra: + break + extra += 3 + # keep all reliable digits so far; remove trailing zeros + # and next nonzero digit + self.digits = digits.rstrip('0')[:-1] + return int(self.digits[:p+1]) + +_log10_digits = _Log10Memoize().getdigits + +def _iexp(x, M, L=8): + """Given integers x and M, M > 0, such that x/M is small in absolute + value, compute an integer approximation to M*exp(x/M). For 0 <= + x/M <= 2.4, the absolute error in the result is bounded by 60 (and + is usually much smaller).""" + + # Algorithm: to compute exp(z) for a real number z, first divide z + # by a suitable power R of 2 so that |z/2**R| < 2**-L. Then + # compute expm1(z/2**R) = exp(z/2**R) - 1 using the usual Taylor + # series + # + # expm1(x) = x + x**2/2! + x**3/3! + ... + # + # Now use the identity + # + # expm1(2x) = expm1(x)*(expm1(x)+2) + # + # R times to compute the sequence expm1(z/2**R), + # expm1(z/2**(R-1)), ... , exp(z/2), exp(z). + + # Find R such that x/2**R/M <= 2**-L + R = _nbits((x<<L)//M) + + # Taylor series. (2**L)**T > M + T = -int(-10*len(str(M))//(3*L)) + y = _div_nearest(x, T) + Mshift = M<<R + for i in range(T-1, 0, -1): + y = _div_nearest(x*(Mshift + y), Mshift * i) + + # Expansion + for k in range(R-1, -1, -1): + Mshift = M<<(k+2) + y = _div_nearest(y*(y+Mshift), Mshift) + + return M+y + +def _dexp(c, e, p): + """Compute an approximation to exp(c*10**e), with p decimal places of + precision. + + Returns integers d, f such that: + + 10**(p-1) <= d <= 10**p, and + (d-1)*10**f < exp(c*10**e) < (d+1)*10**f + + In other words, d*10**f is an approximation to exp(c*10**e) with p + digits of precision, and with an error in d of at most 1. This is + almost, but not quite, the same as the error being < 1ulp: when d + = 10**(p-1) the error could be up to 10 ulp.""" + + # we'll call iexp with M = 10**(p+2), giving p+3 digits of precision + p += 2 + + # compute log(10) with extra precision = adjusted exponent of c*10**e + extra = max(0, e + len(str(c)) - 1) + q = p + extra + + # compute quotient c*10**e/(log(10)) = c*10**(e+q)/(log(10)*10**q), + # rounding down + shift = e+q + if shift >= 0: + cshift = c*10**shift + else: + cshift = c//10**-shift + quot, rem = divmod(cshift, _log10_digits(q)) + + # reduce remainder back to original precision + rem = _div_nearest(rem, 10**extra) + + # error in result of _iexp < 120; error after division < 0.62 + return _div_nearest(_iexp(rem, 10**p), 1000), quot - p + 3 + +def _dpower(xc, xe, yc, ye, p): + """Given integers xc, xe, yc and ye representing Decimals x = xc*10**xe and + y = yc*10**ye, compute x**y. Returns a pair of integers (c, e) such that: + + 10**(p-1) <= c <= 10**p, and + (c-1)*10**e < x**y < (c+1)*10**e + + in other words, c*10**e is an approximation to x**y with p digits + of precision, and with an error in c of at most 1. (This is + almost, but not quite, the same as the error being < 1ulp: when c + == 10**(p-1) we can only guarantee error < 10ulp.) + + We assume that: x is positive and not equal to 1, and y is nonzero. + """ + + # Find b such that 10**(b-1) <= |y| <= 10**b + b = len(str(abs(yc))) + ye + + # log(x) = lxc*10**(-p-b-1), to p+b+1 places after the decimal point + lxc = _dlog(xc, xe, p+b+1) + + # compute product y*log(x) = yc*lxc*10**(-p-b-1+ye) = pc*10**(-p-1) + shift = ye-b + if shift >= 0: + pc = lxc*yc*10**shift + else: + pc = _div_nearest(lxc*yc, 10**-shift) + + if pc == 0: + # we prefer a result that isn't exactly 1; this makes it + # easier to compute a correctly rounded result in __pow__ + if ((len(str(xc)) + xe >= 1) == (yc > 0)): # if x**y > 1: + coeff, exp = 10**(p-1)+1, 1-p + else: + coeff, exp = 10**p-1, -p + else: + coeff, exp = _dexp(pc, -(p+1), p+1) + coeff = _div_nearest(coeff, 10) + exp += 1 + + return coeff, exp + +def _log10_lb(c, correction = { + '1': 100, '2': 70, '3': 53, '4': 40, '5': 31, + '6': 23, '7': 16, '8': 10, '9': 5}): + """Compute a lower bound for 100*log10(c) for a positive integer c.""" + if c <= 0: + raise ValueError("The argument to _log10_lb should be nonnegative.") + str_c = str(c) + return 100*len(str_c) - correction[str_c[0]] + +##### Helper Functions #################################################### + +def _convert_other(other, raiseit=False, allow_float=False): + """Convert other to Decimal. + + Verifies that it's ok to use in an implicit construction. + If allow_float is true, allow conversion from float; this + is used in the comparison methods (__eq__ and friends). + + """ + if isinstance(other, Decimal): + return other + if isinstance(other, int): + return Decimal(other) + if allow_float and isinstance(other, float): + return Decimal.from_float(other) + + if raiseit: + raise TypeError("Unable to convert %s to Decimal" % other) + return NotImplemented + +def _convert_for_comparison(self, other, equality_op=False): + """Given a Decimal instance self and a Python object other, return + a pair (s, o) of Decimal instances such that "s op o" is + equivalent to "self op other" for any of the 6 comparison + operators "op". + + """ + if isinstance(other, Decimal): + return self, other + + # Comparison with a Rational instance (also includes integers): + # self op n/d <=> self*d op n (for n and d integers, d positive). + # A NaN or infinity can be left unchanged without affecting the + # comparison result. + if isinstance(other, _numbers.Rational): + if not self._is_special: + self = _dec_from_triple(self._sign, + str(int(self._int) * other.denominator), + self._exp) + return self, Decimal(other.numerator) + + # Comparisons with float and complex types. == and != comparisons + # with complex numbers should succeed, returning either True or False + # as appropriate. Other comparisons return NotImplemented. + if equality_op and isinstance(other, _numbers.Complex) and other.imag == 0: + other = other.real + if isinstance(other, float): + context = getcontext() + if equality_op: + context.flags[FloatOperation] = 1 + else: + context._raise_error(FloatOperation, + "strict semantics for mixing floats and Decimals are enabled") + return self, Decimal.from_float(other) + return NotImplemented, NotImplemented + + +##### Setup Specific Contexts ############################################ + +# The default context prototype used by Context() +# Is mutable, so that new contexts can have different default values + +DefaultContext = Context( + prec=28, rounding=ROUND_HALF_EVEN, + traps=[DivisionByZero, Overflow, InvalidOperation], + flags=[], + Emax=999999, + Emin=-999999, + capitals=1, + clamp=0 +) + +# Pre-made alternate contexts offered by the specification +# Don't change these; the user should be able to select these +# contexts and be able to reproduce results from other implementations +# of the spec. + +BasicContext = Context( + prec=9, rounding=ROUND_HALF_UP, + traps=[DivisionByZero, Overflow, InvalidOperation, Clamped, Underflow], + flags=[], +) + +ExtendedContext = Context( + prec=9, rounding=ROUND_HALF_EVEN, + traps=[], + flags=[], +) + + +##### crud for parsing strings ############################################# +# +# Regular expression used for parsing numeric strings. Additional +# comments: +# +# 1. Uncomment the two '\s*' lines to allow leading and/or trailing +# whitespace. But note that the specification disallows whitespace in +# a numeric string. +# +# 2. For finite numbers (not infinities and NaNs) the body of the +# number between the optional sign and the optional exponent must have +# at least one decimal digit, possibly after the decimal point. The +# lookahead expression '(?=\d|\.\d)' checks this. + +import re +_parser = re.compile(r""" # A numeric string consists of: +# \s* + (?P<sign>[-+])? # an optional sign, followed by either... + ( + (?=\d|\.\d) # ...a number (with at least one digit) + (?P<int>\d*) # having a (possibly empty) integer part + (\.(?P<frac>\d*))? # followed by an optional fractional part + (E(?P<exp>[-+]?\d+))? # followed by an optional exponent, or... + | + Inf(inity)? # ...an infinity, or... + | + (?P<signal>s)? # ...an (optionally signaling) + NaN # NaN + (?P<diag>\d*) # with (possibly empty) diagnostic info. + ) +# \s* + \Z +""", re.VERBOSE | re.IGNORECASE).match + +_all_zeros = re.compile('0*$').match +_exact_half = re.compile('50*$').match + +##### PEP3101 support functions ############################################## +# The functions in this section have little to do with the Decimal +# class, and could potentially be reused or adapted for other pure +# Python numeric classes that want to implement __format__ +# +# A format specifier for Decimal looks like: +# +# [[fill]align][sign][#][0][minimumwidth][,][.precision][type] + +_parse_format_specifier_regex = re.compile(r"""\A +(?: + (?P<fill>.)? + (?P<align>[<>=^]) +)? +(?P<sign>[-+ ])? +(?P<alt>\#)? +(?P<zeropad>0)? +(?P<minimumwidth>(?!0)\d+)? +(?P<thousands_sep>,)? +(?:\.(?P<precision>0|(?!0)\d+))? +(?P<type>[eEfFgGn%])? +\Z +""", re.VERBOSE|re.DOTALL) + +del re + +# The locale module is only needed for the 'n' format specifier. The +# rest of the PEP 3101 code functions quite happily without it, so we +# don't care too much if locale isn't present. +try: + import locale as _locale +except ImportError: + pass + +def _parse_format_specifier(format_spec, _localeconv=None): + """Parse and validate a format specifier. + + Turns a standard numeric format specifier into a dict, with the + following entries: + + fill: fill character to pad field to minimum width + align: alignment type, either '<', '>', '=' or '^' + sign: either '+', '-' or ' ' + minimumwidth: nonnegative integer giving minimum width + zeropad: boolean, indicating whether to pad with zeros + thousands_sep: string to use as thousands separator, or '' + grouping: grouping for thousands separators, in format + used by localeconv + decimal_point: string to use for decimal point + precision: nonnegative integer giving precision, or None + type: one of the characters 'eEfFgG%', or None + + """ + m = _parse_format_specifier_regex.match(format_spec) + if m is None: + raise ValueError("Invalid format specifier: " + format_spec) + + # get the dictionary + format_dict = m.groupdict() + + # zeropad; defaults for fill and alignment. If zero padding + # is requested, the fill and align fields should be absent. + fill = format_dict['fill'] + align = format_dict['align'] + format_dict['zeropad'] = (format_dict['zeropad'] is not None) + if format_dict['zeropad']: + if fill is not None: + raise ValueError("Fill character conflicts with '0'" + " in format specifier: " + format_spec) + if align is not None: + raise ValueError("Alignment conflicts with '0' in " + "format specifier: " + format_spec) + format_dict['fill'] = fill or ' ' + # PEP 3101 originally specified that the default alignment should + # be left; it was later agreed that right-aligned makes more sense + # for numeric types. See http://bugs.python.org/issue6857. + format_dict['align'] = align or '>' + + # default sign handling: '-' for negative, '' for positive + if format_dict['sign'] is None: + format_dict['sign'] = '-' + + # minimumwidth defaults to 0; precision remains None if not given + format_dict['minimumwidth'] = int(format_dict['minimumwidth'] or '0') + if format_dict['precision'] is not None: + format_dict['precision'] = int(format_dict['precision']) + + # if format type is 'g' or 'G' then a precision of 0 makes little + # sense; convert it to 1. Same if format type is unspecified. + if format_dict['precision'] == 0: + if format_dict['type'] is None or format_dict['type'] in 'gGn': + format_dict['precision'] = 1 + + # determine thousands separator, grouping, and decimal separator, and + # add appropriate entries to format_dict + if format_dict['type'] == 'n': + # apart from separators, 'n' behaves just like 'g' + format_dict['type'] = 'g' + if _localeconv is None: + _localeconv = _locale.localeconv() + if format_dict['thousands_sep'] is not None: + raise ValueError("Explicit thousands separator conflicts with " + "'n' type in format specifier: " + format_spec) + format_dict['thousands_sep'] = _localeconv['thousands_sep'] + format_dict['grouping'] = _localeconv['grouping'] + format_dict['decimal_point'] = _localeconv['decimal_point'] + else: + if format_dict['thousands_sep'] is None: + format_dict['thousands_sep'] = '' + format_dict['grouping'] = [3, 0] + format_dict['decimal_point'] = '.' + + return format_dict + +def _format_align(sign, body, spec): + """Given an unpadded, non-aligned numeric string 'body' and sign + string 'sign', add padding and alignment conforming to the given + format specifier dictionary 'spec' (as produced by + parse_format_specifier). + + """ + # how much extra space do we have to play with? + minimumwidth = spec['minimumwidth'] + fill = spec['fill'] + padding = fill*(minimumwidth - len(sign) - len(body)) + + align = spec['align'] + if align == '<': + result = sign + body + padding + elif align == '>': + result = padding + sign + body + elif align == '=': + result = sign + padding + body + elif align == '^': + half = len(padding)//2 + result = padding[:half] + sign + body + padding[half:] + else: + raise ValueError('Unrecognised alignment field') + + return result + +def _group_lengths(grouping): + """Convert a localeconv-style grouping into a (possibly infinite) + iterable of integers representing group lengths. + + """ + # The result from localeconv()['grouping'], and the input to this + # function, should be a list of integers in one of the + # following three forms: + # + # (1) an empty list, or + # (2) nonempty list of positive integers + [0] + # (3) list of positive integers + [locale.CHAR_MAX], or + + from itertools import chain, repeat + if not grouping: + return [] + elif grouping[-1] == 0 and len(grouping) >= 2: + return chain(grouping[:-1], repeat(grouping[-2])) + elif grouping[-1] == _locale.CHAR_MAX: + return grouping[:-1] + else: + raise ValueError('unrecognised format for grouping') + +def _insert_thousands_sep(digits, spec, min_width=1): + """Insert thousands separators into a digit string. + + spec is a dictionary whose keys should include 'thousands_sep' and + 'grouping'; typically it's the result of parsing the format + specifier using _parse_format_specifier. + + The min_width keyword argument gives the minimum length of the + result, which will be padded on the left with zeros if necessary. + + If necessary, the zero padding adds an extra '0' on the left to + avoid a leading thousands separator. For example, inserting + commas every three digits in '123456', with min_width=8, gives + '0,123,456', even though that has length 9. + + """ + + sep = spec['thousands_sep'] + grouping = spec['grouping'] + + groups = [] + for l in _group_lengths(grouping): + if l <= 0: + raise ValueError("group length should be positive") + # max(..., 1) forces at least 1 digit to the left of a separator + l = min(max(len(digits), min_width, 1), l) + groups.append('0'*(l - len(digits)) + digits[-l:]) + digits = digits[:-l] + min_width -= l + if not digits and min_width <= 0: + break + min_width -= len(sep) + else: + l = max(len(digits), min_width, 1) + groups.append('0'*(l - len(digits)) + digits[-l:]) + return sep.join(reversed(groups)) + +def _format_sign(is_negative, spec): + """Determine sign character.""" + + if is_negative: + return '-' + elif spec['sign'] in ' +': + return spec['sign'] + else: + return '' + +def _format_number(is_negative, intpart, fracpart, exp, spec): + """Format a number, given the following data: + + is_negative: true if the number is negative, else false + intpart: string of digits that must appear before the decimal point + fracpart: string of digits that must come after the point + exp: exponent, as an integer + spec: dictionary resulting from parsing the format specifier + + This function uses the information in spec to: + insert separators (decimal separator and thousands separators) + format the sign + format the exponent + add trailing '%' for the '%' type + zero-pad if necessary + fill and align if necessary + """ + + sign = _format_sign(is_negative, spec) + + if fracpart or spec['alt']: + fracpart = spec['decimal_point'] + fracpart + + if exp != 0 or spec['type'] in 'eE': + echar = {'E': 'E', 'e': 'e', 'G': 'E', 'g': 'e'}[spec['type']] + fracpart += "{0}{1:+}".format(echar, exp) + if spec['type'] == '%': + fracpart += '%' + + if spec['zeropad']: + min_width = spec['minimumwidth'] - len(fracpart) - len(sign) + else: + min_width = 0 + intpart = _insert_thousands_sep(intpart, spec, min_width) + + return _format_align(sign, intpart+fracpart, spec) + + +##### Useful Constants (internal use only) ################################ + +# Reusable defaults +_Infinity = Decimal('Inf') +_NegativeInfinity = Decimal('-Inf') +_NaN = Decimal('NaN') +_Zero = Decimal(0) +_One = Decimal(1) +_NegativeOne = Decimal(-1) + +# _SignedInfinity[sign] is infinity w/ that sign +_SignedInfinity = (_Infinity, _NegativeInfinity) + +# Constants related to the hash implementation; hash(x) is based +# on the reduction of x modulo _PyHASH_MODULUS +_PyHASH_MODULUS = sys.hash_info.modulus +# hash values to use for positive and negative infinities, and nans +_PyHASH_INF = sys.hash_info.inf +_PyHASH_NAN = sys.hash_info.nan + +# _PyHASH_10INV is the inverse of 10 modulo the prime _PyHASH_MODULUS +_PyHASH_10INV = pow(10, _PyHASH_MODULUS - 2, _PyHASH_MODULUS) +del sys diff --git a/Lib/_pyio.py b/Lib/_pyio.py index 577b600..b0f0114 100644 --- a/Lib/_pyio.py +++ b/Lib/_pyio.py @@ -6,6 +6,7 @@ import os import abc import codecs import errno +import array # Import _thread instead of threading to reduce startup cost try: from _thread import allocate_lock as Lock @@ -256,7 +257,7 @@ class OpenWrapper: Trick so that open won't become a bound method when stored as a class variable (as dbm.dumb does). - See initstdio() in Python/pythonrun.c. + See initstdio() in Python/pylifecycle.c. """ __doc__ = DocDescriptor() @@ -662,16 +663,33 @@ class BufferedIOBase(IOBase): Raises BlockingIOError if the underlying raw stream has no data at the moment. """ - # XXX This ought to work with anything that supports the buffer API - data = self.read(len(b)) + + return self._readinto(b, read1=False) + + def readinto1(self, b): + """Read up to len(b) bytes into *b*, using at most one system call + + Returns an int representing the number of bytes read (0 for EOF). + + Raises BlockingIOError if the underlying raw stream has no + data at the moment. + """ + + return self._readinto(b, read1=True) + + def _readinto(self, b, read1): + if not isinstance(b, memoryview): + b = memoryview(b) + b = b.cast('B') + + if read1: + data = self.read1(len(b)) + else: + data = self.read(len(b)) n = len(data) - try: - b[:n] = data - except TypeError as err: - import array - if not isinstance(b, array.array): - raise err - b[:n] = array.array('b', data) + + b[:n] = data + return n def write(self, b): @@ -790,13 +808,14 @@ class _BufferedIOMixin(BufferedIOBase): .format(self.__class__.__name__)) def __repr__(self): - clsname = self.__class__.__name__ + modname = self.__class__.__module__ + clsname = self.__class__.__qualname__ try: name = self.name except Exception: - return "<_pyio.{0}>".format(clsname) + return "<{}.{}>".format(modname, clsname) else: - return "<_pyio.{0} name={1!r}>".format(clsname, name) + return "<{}.{} name={!r}>".format(modname, clsname, name) ### Lower-level APIs ### @@ -993,10 +1012,7 @@ class BufferedReader(_BufferedIOMixin): current_size = 0 while True: # Read until EOF or until read() would block. - try: - chunk = self.raw.read() - except InterruptedError: - continue + chunk = self.raw.read() if chunk in empty_values: nodata_val = chunk break @@ -1015,10 +1031,7 @@ class BufferedReader(_BufferedIOMixin): chunks = [buf[pos:]] wanted = max(self.buffer_size, n) while avail < n: - try: - chunk = self.raw.read(wanted) - except InterruptedError: - continue + chunk = self.raw.read(wanted) if chunk in empty_values: nodata_val = chunk break @@ -1047,12 +1060,7 @@ class BufferedReader(_BufferedIOMixin): have = len(self._read_buf) - self._read_pos if have < want or have <= 0: to_read = self.buffer_size - have - while True: - try: - current = self.raw.read(to_read) - except InterruptedError: - continue - break + current = self.raw.read(to_read) if current: self._read_buf = self._read_buf[self._read_pos:] + current self._read_pos = 0 @@ -1071,6 +1079,58 @@ class BufferedReader(_BufferedIOMixin): return self._read_unlocked( min(size, len(self._read_buf) - self._read_pos)) + # Implementing readinto() and readinto1() is not strictly necessary (we + # could rely on the base class that provides an implementation in terms of + # read() and read1()). We do it anyway to keep the _pyio implementation + # similar to the io implementation (which implements the methods for + # performance reasons). + def _readinto(self, buf, read1): + """Read data into *buf* with at most one system call.""" + + if len(buf) == 0: + return 0 + + # Need to create a memoryview object of type 'b', otherwise + # we may not be able to assign bytes to it, and slicing it + # would create a new object. + if not isinstance(buf, memoryview): + buf = memoryview(buf) + buf = buf.cast('B') + + written = 0 + with self._read_lock: + while written < len(buf): + + # First try to read from internal buffer + avail = min(len(self._read_buf) - self._read_pos, len(buf)) + if avail: + buf[written:written+avail] = \ + self._read_buf[self._read_pos:self._read_pos+avail] + self._read_pos += avail + written += avail + if written == len(buf): + break + + # If remaining space in callers buffer is larger than + # internal buffer, read directly into callers buffer + if len(buf) - written > self.buffer_size: + n = self.raw.readinto(buf[written:]) + if not n: + break # eof + written += n + + # Otherwise refill internal buffer - unless we're + # in read1 mode and already got some data + elif not (read1 and written): + if not self._peek_unlocked(1): + break # eof + + # In readinto1 mode, return as soon as we have some data + if read1 and written: + break + + return written + def tell(self): return _BufferedIOMixin.tell(self) - len(self._read_buf) + self._read_pos @@ -1149,8 +1209,6 @@ class BufferedWriter(_BufferedIOMixin): while self._write_buf: try: n = self.raw.write(self._write_buf) - except InterruptedError: - continue except BlockingIOError: raise RuntimeError("self.raw should implement RawIOBase: it " "should not raise BlockingIOError") @@ -1220,6 +1278,9 @@ class BufferedRWPair(BufferedIOBase): def read1(self, size): return self.reader.read1(size) + def readinto1(self, b): + return self.reader.readinto1(b) + def readable(self): return self.reader.readable() @@ -1302,6 +1363,10 @@ class BufferedRandom(BufferedWriter, BufferedReader): self.flush() return BufferedReader.read1(self, size) + def readinto1(self, b): + self.flush() + return BufferedReader.readinto1(self, b) + def write(self, b): if self._read_buf: # Undo readahead @@ -1564,7 +1629,8 @@ class TextIOWrapper(TextIOBase): # - "chars_..." for integer variables that count decoded characters def __repr__(self): - result = "<_pyio.TextIOWrapper" + result = "<{}.{}".format(self.__class__.__module__, + self.__class__.__qualname__) try: name = self.name except Exception: diff --git a/Lib/_strptime.py b/Lib/_strptime.py index 53bd34b..42f23d3 100644 --- a/Lib/_strptime.py +++ b/Lib/_strptime.py @@ -167,9 +167,9 @@ class LocaleTime(object): time.tzset() except AttributeError: pass - no_saving = frozenset(["utc", "gmt", time.tzname[0].lower()]) + no_saving = frozenset({"utc", "gmt", time.tzname[0].lower()}) if time.daylight: - has_saving = frozenset([time.tzname[1].lower()]) + has_saving = frozenset({time.tzname[1].lower()}) else: has_saving = frozenset() self.timezone = (no_saving, has_saving) @@ -168,7 +168,7 @@ class ABCMeta(type): def _dump_registry(cls, file=None): """Debug helper to print the ABC registry.""" - print("Class: %s.%s" % (cls.__module__, cls.__name__), file=file) + print("Class: %s.%s" % (cls.__module__, cls.__qualname__), file=file) print("Inv.counter: %s" % ABCMeta._abc_invalidation_counter, file=file) for name in sorted(cls.__dict__.keys()): if name.startswith("_abc_"): diff --git a/Lib/argparse.py b/Lib/argparse.py index be276bb..9a06719 100644 --- a/Lib/argparse.py +++ b/Lib/argparse.py @@ -1209,11 +1209,6 @@ class Namespace(_AttributeHolder): return NotImplemented return vars(self) == vars(other) - def __ne__(self, other): - if not isinstance(other, Namespace): - return NotImplemented - return not (self == other) - def __contains__(self, key): return key in self.__dict__ @@ -1595,6 +1590,7 @@ class ArgumentParser(_AttributeHolder, _ActionsContainer): - argument_default -- The default value for all arguments - conflict_handler -- String indicating how to handle conflicts - add_help -- Add a -h/-help option + - allow_abbrev -- Allow long options to be abbreviated unambiguously """ def __init__(self, @@ -1608,7 +1604,8 @@ class ArgumentParser(_AttributeHolder, _ActionsContainer): fromfile_prefix_chars=None, argument_default=None, conflict_handler='error', - add_help=True): + add_help=True, + allow_abbrev=True): superinit = super(ArgumentParser, self).__init__ superinit(description=description, @@ -1626,6 +1623,7 @@ class ArgumentParser(_AttributeHolder, _ActionsContainer): self.formatter_class = formatter_class self.fromfile_prefix_chars = fromfile_prefix_chars self.add_help = add_help + self.allow_abbrev = allow_abbrev add_group = self.add_argument_group self._positionals = add_group(_('positional arguments')) @@ -2103,23 +2101,24 @@ class ArgumentParser(_AttributeHolder, _ActionsContainer): action = self._option_string_actions[option_string] return action, option_string, explicit_arg - # search through all possible prefixes of the option string - # and all actions in the parser for possible interpretations - option_tuples = self._get_option_tuples(arg_string) - - # if multiple actions match, the option string was ambiguous - if len(option_tuples) > 1: - options = ', '.join([option_string - for action, option_string, explicit_arg in option_tuples]) - args = {'option': arg_string, 'matches': options} - msg = _('ambiguous option: %(option)s could match %(matches)s') - self.error(msg % args) - - # if exactly one action matched, this segmentation is good, - # so return the parsed action - elif len(option_tuples) == 1: - option_tuple, = option_tuples - return option_tuple + if self.allow_abbrev: + # search through all possible prefixes of the option string + # and all actions in the parser for possible interpretations + option_tuples = self._get_option_tuples(arg_string) + + # if multiple actions match, the option string was ambiguous + if len(option_tuples) > 1: + options = ', '.join([option_string + for action, option_string, explicit_arg in option_tuples]) + args = {'option': arg_string, 'matches': options} + msg = _('ambiguous option: %(option)s could match %(matches)s') + self.error(msg % args) + + # if exactly one action matched, this segmentation is good, + # so return the parsed action + elif len(option_tuples) == 1: + option_tuple, = option_tuples + return option_tuple # if it was not found as an option, but it looks like a negative # number, it was meant to be positional diff --git a/Lib/asynchat.py b/Lib/asynchat.py index 14c152f..f728d1b 100644 --- a/Lib/asynchat.py +++ b/Lib/asynchat.py @@ -287,6 +287,9 @@ class simple_producer: class fifo: def __init__(self, list=None): + import warnings + warnings.warn('fifo class will be removed in Python 3.6', + DeprecationWarning, stacklevel=2) if not list: self.list = deque() else: diff --git a/Lib/asyncio/events.py b/Lib/asyncio/events.py index 8a7bb81..01320cd 100644 --- a/Lib/asyncio/events.py +++ b/Lib/asyncio/events.py @@ -178,10 +178,6 @@ class TimerHandle(Handle): self._cancelled == other._cancelled) return NotImplemented - def __ne__(self, other): - equal = self.__eq__(other) - return NotImplemented if equal is NotImplemented else not equal - def cancel(self): if not self._cancelled: self._loop._timer_handle_cancelled(self) diff --git a/Lib/asyncore.py b/Lib/asyncore.py index 00a6396..68efd45 100644 --- a/Lib/asyncore.py +++ b/Lib/asyncore.py @@ -57,8 +57,8 @@ from errno import EALREADY, EINPROGRESS, EWOULDBLOCK, ECONNRESET, EINVAL, \ ENOTCONN, ESHUTDOWN, EISCONN, EBADF, ECONNABORTED, EPIPE, EAGAIN, \ errorcode -_DISCONNECTED = frozenset((ECONNRESET, ENOTCONN, ESHUTDOWN, ECONNABORTED, EPIPE, - EBADF)) +_DISCONNECTED = frozenset({ECONNRESET, ENOTCONN, ESHUTDOWN, ECONNABORTED, EPIPE, + EBADF}) try: socket_map @@ -220,7 +220,7 @@ class dispatcher: connecting = False closing = False addr = None - ignore_log_types = frozenset(['warning']) + ignore_log_types = frozenset({'warning'}) def __init__(self, sock=None, map=None): if map is None: @@ -255,7 +255,7 @@ class dispatcher: self.socket = None def __repr__(self): - status = [self.__class__.__module__+"."+self.__class__.__name__] + status = [self.__class__.__module__+"."+self.__class__.__qualname__] if self.accepting and self.addr: status.append('listening') elif self.connected: @@ -404,20 +404,6 @@ class dispatcher: if why.args[0] not in (ENOTCONN, EBADF): raise - # cheap inheritance, used to pass all other attribute - # references to the underlying socket object. - def __getattr__(self, attr): - try: - retattr = getattr(self.socket, attr) - except AttributeError: - raise AttributeError("%s instance has no attribute '%s'" - %(self.__class__.__name__, attr)) - else: - msg = "%(me)s.%(attr)s is deprecated; use %(me)s.socket.%(attr)s " \ - "instead" % {'me' : self.__class__.__name__, 'attr' : attr} - warnings.warn(msg, DeprecationWarning, stacklevel=2) - return retattr - # log and log_info may be overridden to provide more sophisticated # logging and warning methods. In general, log is for 'hit' logging # and 'log_info' is for informational, warning and error logging. @@ -604,8 +590,6 @@ def close_all(map=None, ignore_all=False): # Regardless, this is useful for pipes, and stdin/stdout... if os.name == 'posix': - import fcntl - class file_wrapper: # Here we override just enough to make a file # look like a socket for the purposes of asyncore. @@ -656,9 +640,7 @@ if os.name == 'posix': pass self.set_file(fd) # set it to non-blocking mode - flags = fcntl.fcntl(fd, fcntl.F_GETFL, 0) - flags = flags | os.O_NONBLOCK - fcntl.fcntl(fd, fcntl.F_SETFL, flags) + os.set_blocking(fd, False) def set_file(self, fd): self.socket = file_wrapper(fd) @@ -566,6 +566,12 @@ class FieldStorage: except AttributeError: pass + def __enter__(self): + return self + + def __exit__(self, *args): + self.file.close() + def __repr__(self): """Return a printable representation.""" return "FieldStorage(%r, %r, %r)" % ( diff --git a/Lib/code.py b/Lib/code.py index f8184b6..53244e3 100644 --- a/Lib/code.py +++ b/Lib/code.py @@ -7,6 +7,7 @@ import sys import traceback +import argparse from codeop import CommandCompiler, compile_command __all__ = ["InteractiveInterpreter", "InteractiveConsole", "interact", @@ -136,25 +137,18 @@ class InteractiveInterpreter: The output is written by self.write(), below. """ + sys.last_type, sys.last_value, last_tb = ei = sys.exc_info() + sys.last_traceback = last_tb try: - type, value, tb = sys.exc_info() - sys.last_type = type - sys.last_value = value - sys.last_traceback = tb - tblist = traceback.extract_tb(tb) - del tblist[:1] - lines = traceback.format_list(tblist) - if lines: - lines.insert(0, "Traceback (most recent call last):\n") - lines.extend(traceback.format_exception_only(type, value)) + lines = traceback.format_exception(ei[0], ei[1], last_tb.tb_next) + if sys.excepthook is sys.__excepthook__: + self.write(''.join(lines)) + else: + # If someone has set sys.excepthook, we let that take precedence + # over self.write + sys.excepthook(ei[0], ei[1], last_tb) finally: - tblist = tb = None - if sys.excepthook is sys.__excepthook__: - self.write(''.join(lines)) - else: - # If someone has set sys.excepthook, we let that take precedence - # over self.write - sys.excepthook(type, value, tb) + last_tb = ei = None def write(self, data): """Write a string. @@ -299,4 +293,12 @@ def interact(banner=None, readfunc=None, local=None): if __name__ == "__main__": - interact() + parser = argparse.ArgumentParser() + parser.add_argument('-q', action='store_true', + help="don't print version and copyright messages") + args = parser.parse_args() + if args.q or sys.flags.quiet: + banner = '' + else: + banner = None + interact(banner) diff --git a/Lib/codecs.py b/Lib/codecs.py index 145bf12..c2b5d6c 100644 --- a/Lib/codecs.py +++ b/Lib/codecs.py @@ -27,7 +27,8 @@ __all__ = ["register", "lookup", "open", "EncodedFile", "BOM", "BOM_BE", "getincrementaldecoder", "getreader", "getwriter", "encode", "decode", "iterencode", "iterdecode", "strict_errors", "ignore_errors", "replace_errors", - "xmlcharrefreplace_errors", "backslashreplace_errors", + "xmlcharrefreplace_errors", + "backslashreplace_errors", "namereplace_errors", "register_error", "lookup_error"] ### Constants @@ -105,8 +106,8 @@ class CodecInfo(tuple): return self def __repr__(self): - return "<%s.%s object for encoding %s at 0x%x>" % \ - (self.__class__.__module__, self.__class__.__name__, + return "<%s.%s object for encoding %s at %#x>" % \ + (self.__class__.__module__, self.__class__.__qualname__, self.name, id(self)) class Codec: @@ -126,7 +127,8 @@ class Codec: 'surrogateescape' - replace with private code points U+DCnn. 'xmlcharrefreplace' - Replace with the appropriate XML character reference (only for encoding). - 'backslashreplace' - Replace with backslashed escape sequences + 'backslashreplace' - Replace with backslashed escape sequences. + 'namereplace' - Replace with \\N{...} escape sequences (only for encoding). The set of allowed values can be extended via register_error. @@ -358,7 +360,8 @@ class StreamWriter(Codec): 'xmlcharrefreplace' - Replace with the appropriate XML character reference. 'backslashreplace' - Replace with backslashed escape - sequences (only for encoding). + sequences. + 'namereplace' - Replace with \\N{...} escape sequences. The set of allowed parameter values can be extended via register_error. @@ -428,7 +431,8 @@ class StreamReader(Codec): 'strict' - raise a ValueError (or a subclass) 'ignore' - ignore the character and continue with the next - 'replace'- replace with a suitable replacement character; + 'replace'- replace with a suitable replacement character + 'backslashreplace' - Replace with backslashed escape sequences; The set of allowed parameter values can be extended via register_error. @@ -1080,6 +1084,7 @@ try: replace_errors = lookup_error("replace") xmlcharrefreplace_errors = lookup_error("xmlcharrefreplace") backslashreplace_errors = lookup_error("backslashreplace") + namereplace_errors = lookup_error("namereplace") except LookupError: # In --disable-unicode builds, these error handler are missing strict_errors = None @@ -1087,6 +1092,7 @@ except LookupError: replace_errors = None xmlcharrefreplace_errors = None backslashreplace_errors = None + namereplace_errors = None # Tell modulefinder that using codecs probably needs the encodings # package diff --git a/Lib/collections/__init__.py b/Lib/collections/__init__.py index 565ae86..ce67f0b 100644 --- a/Lib/collections/__init__.py +++ b/Lib/collections/__init__.py @@ -20,6 +20,23 @@ from reprlib import recursive_repr as _recursive_repr ### OrderedDict ################################################################################ +class _OrderedDictKeysView(KeysView): + + def __reversed__(self): + yield from reversed(self._mapping) + +class _OrderedDictItemsView(ItemsView): + + def __reversed__(self): + for key in reversed(self._mapping): + yield (key, self._mapping[key]) + +class _OrderedDictValuesView(ValuesView): + + def __reversed__(self): + for key in reversed(self._mapping): + yield self._mapping[key] + class _Link(object): __slots__ = 'prev', 'next', 'key', '__weakref__' @@ -83,6 +100,8 @@ class OrderedDict(dict): link_next = link.next link_prev.next = link_next link_next.prev = link_prev + link.prev = None + link.next = None def __iter__(self): 'od.__iter__() <==> iter(od)' @@ -166,9 +185,19 @@ class OrderedDict(dict): return size update = __update = MutableMapping.update - keys = MutableMapping.keys - values = MutableMapping.values - items = MutableMapping.items + + def keys(self): + "D.keys() -> a set-like object providing a view on D's keys" + return _OrderedDictKeysView(self) + + def items(self): + "D.items() -> a set-like object providing a view on D's items" + return _OrderedDictItemsView(self) + + def values(self): + "D.values() -> an object providing a view on D's values" + return _OrderedDictValuesView(self) + __ne__ = MutableMapping.__ne__ __marker = object() @@ -958,7 +987,6 @@ class UserList(MutableSequence): def __lt__(self, other): return self.data < self.__cast(other) def __le__(self, other): return self.data <= self.__cast(other) def __eq__(self, other): return self.data == self.__cast(other) - def __ne__(self, other): return self.data != self.__cast(other) def __gt__(self, other): return self.data > self.__cast(other) def __ge__(self, other): return self.data >= self.__cast(other) def __cast(self, other): @@ -1035,10 +1063,6 @@ class UserString(Sequence): if isinstance(string, UserString): return self.data == string.data return self.data == string - def __ne__(self, string): - if isinstance(string, UserString): - return self.data != string.data - return self.data != string def __lt__(self, string): if isinstance(string, UserString): return self.data < string.data diff --git a/Lib/compileall.py b/Lib/compileall.py index d957ee5..4f46920 100644 --- a/Lib/compileall.py +++ b/Lib/compileall.py @@ -16,32 +16,24 @@ import importlib.util import py_compile import struct -__all__ = ["compile_dir","compile_file","compile_path"] - -def compile_dir(dir, maxlevels=10, ddir=None, force=False, rx=None, - quiet=False, legacy=False, optimize=-1): - """Byte-compile all modules in the given directory tree. +try: + from concurrent.futures import ProcessPoolExecutor +except ImportError: + ProcessPoolExecutor = None +from functools import partial - Arguments (only dir is required): +__all__ = ["compile_dir","compile_file","compile_path"] - dir: the directory to byte-compile - maxlevels: maximum recursion level (default 10) - ddir: the directory that will be prepended to the path to the - file as it is compiled into each byte-code file. - force: if True, force compilation, even if timestamps are up-to-date - quiet: if True, be quiet during compilation - legacy: if True, produce legacy pyc paths instead of PEP 3147 paths - optimize: optimization level or -1 for level of the interpreter - """ +def _walk_dir(dir, ddir=None, maxlevels=10, quiet=0): if not quiet: print('Listing {!r}...'.format(dir)) try: names = os.listdir(dir) except OSError: - print("Can't list {!r}".format(dir)) + if quiet < 2: + print("Can't list {!r}".format(dir)) names = [] names.sort() - success = 1 for name in names: if name == '__pycache__': continue @@ -51,17 +43,55 @@ def compile_dir(dir, maxlevels=10, ddir=None, force=False, rx=None, else: dfile = None if not os.path.isdir(fullname): - if not compile_file(fullname, ddir, force, rx, quiet, - legacy, optimize): - success = 0 + yield fullname elif (maxlevels > 0 and name != os.curdir and name != os.pardir and os.path.isdir(fullname) and not os.path.islink(fullname)): - if not compile_dir(fullname, maxlevels - 1, dfile, force, rx, - quiet, legacy, optimize): + yield from _walk_dir(fullname, ddir=dfile, + maxlevels=maxlevels - 1, quiet=quiet) + +def compile_dir(dir, maxlevels=10, ddir=None, force=False, rx=None, + quiet=0, legacy=False, optimize=-1, workers=1): + """Byte-compile all modules in the given directory tree. + + Arguments (only dir is required): + + dir: the directory to byte-compile + maxlevels: maximum recursion level (default 10) + ddir: the directory that will be prepended to the path to the + file as it is compiled into each byte-code file. + force: if True, force compilation, even if timestamps are up-to-date + quiet: full output with False or 0, errors only with 1, + no output with 2 + legacy: if True, produce legacy pyc paths instead of PEP 3147 paths + optimize: optimization level or -1 for level of the interpreter + workers: maximum number of parallel workers + """ + files = _walk_dir(dir, quiet=quiet, maxlevels=maxlevels, + ddir=ddir) + success = 1 + if workers is not None and workers != 1: + if workers < 0: + raise ValueError('workers must be greater or equal to 0') + if ProcessPoolExecutor is None: + raise NotImplementedError('multiprocessing support not available') + + workers = workers or None + with ProcessPoolExecutor(max_workers=workers) as executor: + results = executor.map(partial(compile_file, + ddir=ddir, force=force, + rx=rx, quiet=quiet, + legacy=legacy, + optimize=optimize), + files) + success = min(results, default=1) + else: + for file in files: + if not compile_file(file, ddir, force, rx, quiet, + legacy, optimize): success = 0 return success -def compile_file(fullname, ddir=None, force=False, rx=None, quiet=False, +def compile_file(fullname, ddir=None, force=False, rx=None, quiet=0, legacy=False, optimize=-1): """Byte-compile one file. @@ -71,7 +101,8 @@ def compile_file(fullname, ddir=None, force=False, rx=None, quiet=False, ddir: if given, the directory name compiled in to the byte-code file. force: if True, force compilation, even if timestamps are up-to-date - quiet: if True, be quiet during compilation + quiet: full output with False or 0, errors only with 1, + no output with 2 legacy: if True, produce legacy pyc paths instead of PEP 3147 paths optimize: optimization level or -1 for level of the interpreter """ @@ -114,7 +145,10 @@ def compile_file(fullname, ddir=None, force=False, rx=None, quiet=False, ok = py_compile.compile(fullname, cfile, dfile, True, optimize=optimize) except py_compile.PyCompileError as err: - if quiet: + success = 0 + if quiet >= 2: + return success + elif quiet: print('*** Error compiling {!r}...'.format(fullname)) else: print('*** ', end='') @@ -123,20 +157,21 @@ def compile_file(fullname, ddir=None, force=False, rx=None, quiet=False, errors='backslashreplace') msg = msg.decode(sys.stdout.encoding) print(msg) - success = 0 except (SyntaxError, UnicodeError, OSError) as e: - if quiet: + success = 0 + if quiet >= 2: + return success + elif quiet: print('*** Error compiling {!r}...'.format(fullname)) else: print('*** ', end='') print(e.__class__.__name__ + ':', e) - success = 0 else: if ok == 0: success = 0 return success -def compile_path(skip_curdir=1, maxlevels=0, force=False, quiet=False, +def compile_path(skip_curdir=1, maxlevels=0, force=False, quiet=0, legacy=False, optimize=-1): """Byte-compile all module on sys.path. @@ -145,14 +180,15 @@ def compile_path(skip_curdir=1, maxlevels=0, force=False, quiet=False, skip_curdir: if true, skip current directory (default True) maxlevels: max recursion level (default 0) force: as for compile_dir() (default False) - quiet: as for compile_dir() (default False) + quiet: as for compile_dir() (default 0) legacy: as for compile_dir() (default False) optimize: as for compile_dir() (default -1) """ success = 1 for dir in sys.path: if (not dir or dir == os.curdir) and skip_curdir: - print('Skipping current directory') + if quiet < 2: + print('Skipping current directory') else: success = success and compile_dir(dir, maxlevels, None, force, quiet=quiet, @@ -169,10 +205,15 @@ def main(): parser.add_argument('-l', action='store_const', const=0, default=10, dest='maxlevels', help="don't recurse into subdirectories") + parser.add_argument('-r', type=int, dest='recursion', + help=('control the maximum recursion level. ' + 'if `-l` and `-r` options are specified, ' + 'then `-r` takes precedence.')) parser.add_argument('-f', action='store_true', dest='force', help='force rebuild even if timestamps are up to date') - parser.add_argument('-q', action='store_true', dest='quiet', - help='output only error messages') + parser.add_argument('-q', action='count', dest='quiet', default=0, + help='output only error messages; -qq will suppress ' + 'the error messages as well.') parser.add_argument('-b', action='store_true', dest='legacy', help='use legacy (pre-PEP3147) compiled file locations') parser.add_argument('-d', metavar='DESTDIR', dest='ddir', default=None, @@ -192,8 +233,10 @@ def main(): help=('zero or more file and directory names ' 'to compile; if no arguments given, defaults ' 'to the equivalent of -l sys.path')) - args = parser.parse_args() + parser.add_argument('-j', '--workers', default=1, + type=int, help='Run compileall concurrently') + args = parser.parse_args() compile_dests = args.compile_dest if (args.ddir and (len(compile_dests) != 1 @@ -203,6 +246,12 @@ def main(): import re args.rx = re.compile(args.rx) + + if args.recursion is not None: + maxlevels = args.recursion + else: + maxlevels = args.maxlevels + # if flist is provided then load it if args.flist: try: @@ -210,9 +259,13 @@ def main(): for line in f: compile_dests.append(line.strip()) except OSError: - print("Error reading file list {}".format(args.flist)) + if args.quiet < 2: + print("Error reading file list {}".format(args.flist)) return False + if args.workers is not None: + args.workers = args.workers or None + success = True try: if compile_dests: @@ -222,16 +275,17 @@ def main(): args.quiet, args.legacy): success = False else: - if not compile_dir(dest, args.maxlevels, args.ddir, + if not compile_dir(dest, maxlevels, args.ddir, args.force, args.rx, args.quiet, - args.legacy): + args.legacy, workers=args.workers): success = False return success else: return compile_path(legacy=args.legacy, force=args.force, quiet=args.quiet) except KeyboardInterrupt: - print("\n[interrupted]") + if args.quiet < 2: + print("\n[interrupted]") return False return True diff --git a/Lib/concurrent/futures/_base.py b/Lib/concurrent/futures/_base.py index acd05d0..9e44713 100644 --- a/Lib/concurrent/futures/_base.py +++ b/Lib/concurrent/futures/_base.py @@ -302,17 +302,20 @@ class Future(object): with self._condition: if self._state == FINISHED: if self._exception: - return '<Future at %s state=%s raised %s>' % ( - hex(id(self)), + return '<%s at %#x state=%s raised %s>' % ( + self.__class__.__name__, + id(self), _STATE_TO_DESCRIPTION_MAP[self._state], self._exception.__class__.__name__) else: - return '<Future at %s state=%s returned %s>' % ( - hex(id(self)), + return '<%s at %#x state=%s returned %s>' % ( + self.__class__.__name__, + id(self), _STATE_TO_DESCRIPTION_MAP[self._state], self._result.__class__.__name__) - return '<Future at %s state=%s>' % ( - hex(id(self)), + return '<%s at %#x state=%s>' % ( + self.__class__.__name__, + id(self), _STATE_TO_DESCRIPTION_MAP[self._state]) def cancel(self): @@ -517,7 +520,7 @@ class Executor(object): """ raise NotImplementedError() - def map(self, fn, *iterables, timeout=None): + def map(self, fn, *iterables, timeout=None, chunksize=1): """Returns a iterator equivalent to map(fn, iter). Args: @@ -525,6 +528,10 @@ class Executor(object): passed iterables. timeout: The maximum number of seconds to wait. If None, then there is no limit on the wait time. + chunksize: The size of the chunks the iterable will be broken into + before being passed to a child process. This argument is only + used by ProcessPoolExecutor; it is ignored by + ThreadPoolExecutor. Returns: An iterator equivalent to: map(func, *iterables) but the calls may diff --git a/Lib/concurrent/futures/process.py b/Lib/concurrent/futures/process.py index 07b5225..3dd6da1 100644 --- a/Lib/concurrent/futures/process.py +++ b/Lib/concurrent/futures/process.py @@ -55,6 +55,9 @@ from multiprocessing import SimpleQueue from multiprocessing.connection import wait import threading import weakref +from functools import partial +import itertools +import traceback # Workers are created as daemon threads and processes. This is done to allow the # interpreter to exit when there are still idle processes in a @@ -88,6 +91,27 @@ def _python_exit(): # (Futures in the call queue cannot be cancelled). EXTRA_QUEUED_CALLS = 1 +# Hack to embed stringification of remote traceback in local traceback + +class _RemoteTraceback(Exception): + def __init__(self, tb): + self.tb = tb + def __str__(self): + return self.tb + +class _ExceptionWithTraceback: + def __init__(self, exc, tb): + tb = traceback.format_exception(type(exc), exc, tb) + tb = ''.join(tb) + self.exc = exc + self.tb = '\n"""\n%s"""' % tb + def __reduce__(self): + return _rebuild_exc, (self.exc, self.tb) + +def _rebuild_exc(exc, tb): + exc.__cause__ = _RemoteTraceback(tb) + return exc + class _WorkItem(object): def __init__(self, future, fn, args, kwargs): self.future = future @@ -108,6 +132,26 @@ class _CallItem(object): self.args = args self.kwargs = kwargs +def _get_chunks(*iterables, chunksize): + """ Iterates over zip()ed iterables in chunks. """ + it = zip(*iterables) + while True: + chunk = tuple(itertools.islice(it, chunksize)) + if not chunk: + return + yield chunk + +def _process_chunk(fn, chunk): + """ Processes a chunk of an iterable passed to map. + + Runs the function passed to map() on a chunk of the + iterable passed to map. + + This function is run in a separate process. + + """ + return [fn(*args) for args in chunk] + def _process_worker(call_queue, result_queue): """Evaluates calls from call_queue and places the results in result_queue. @@ -130,8 +174,8 @@ def _process_worker(call_queue, result_queue): try: r = call_item.fn(*call_item.args, **call_item.kwargs) except BaseException as e: - result_queue.put(_ResultItem(call_item.work_id, - exception=e)) + exc = _ExceptionWithTraceback(e, e.__traceback__) + result_queue.put(_ResultItem(call_item.work_id, exception=exc)) else: result_queue.put(_ResultItem(call_item.work_id, result=r)) @@ -334,6 +378,9 @@ class ProcessPoolExecutor(_base.Executor): if max_workers is None: self._max_workers = os.cpu_count() or 1 else: + if max_workers <= 0: + raise ValueError("max_workers must be greater than 0") + self._max_workers = max_workers # Make the call queue slightly larger than the number of processes to @@ -408,6 +455,35 @@ class ProcessPoolExecutor(_base.Executor): return f submit.__doc__ = _base.Executor.submit.__doc__ + def map(self, fn, *iterables, timeout=None, chunksize=1): + """Returns a iterator equivalent to map(fn, iter). + + Args: + fn: A callable that will take as many arguments as there are + passed iterables. + timeout: The maximum number of seconds to wait. If None, then there + is no limit on the wait time. + chunksize: If greater than one, the iterables will be chopped into + chunks of size chunksize and submitted to the process pool. + If set to one, the items in the list will be sent one at a time. + + Returns: + An iterator equivalent to: map(func, *iterables) but the calls may + be evaluated out-of-order. + + Raises: + TimeoutError: If the entire result iterator could not be generated + before the given timeout. + Exception: If fn(*args) raises for any values. + """ + if chunksize < 1: + raise ValueError("chunksize must be >= 1.") + + results = super().map(partial(_process_chunk, fn), + _get_chunks(*iterables, chunksize=chunksize), + timeout=timeout) + return itertools.chain.from_iterable(results) + def shutdown(self, wait=True): with self._shutdown_lock: self._shutdown_thread = True diff --git a/Lib/concurrent/futures/thread.py b/Lib/concurrent/futures/thread.py index f9beb0f..3ae442d 100644 --- a/Lib/concurrent/futures/thread.py +++ b/Lib/concurrent/futures/thread.py @@ -10,6 +10,7 @@ from concurrent.futures import _base import queue import threading import weakref +import os # Workers are created as daemon threads. This is done to allow the interpreter # to exit when there are still idle threads in a ThreadPoolExecutor's thread @@ -80,13 +81,20 @@ def _worker(executor_reference, work_queue): _base.LOGGER.critical('Exception in worker', exc_info=True) class ThreadPoolExecutor(_base.Executor): - def __init__(self, max_workers): + def __init__(self, max_workers=None): """Initializes a new ThreadPoolExecutor instance. Args: max_workers: The maximum number of threads that can be used to execute the given calls. """ + if max_workers is None: + # Use this number because ThreadPoolExecutor is often + # used to overlap I/O instead of CPU work. + max_workers = (os.cpu_count() or 1) * 5 + if max_workers <= 0: + raise ValueError("max_workers must be greater than 0") + self._max_workers = max_workers self._work_queue = queue.Queue() self._threads = set() diff --git a/Lib/configparser.py b/Lib/configparser.py index 4ee8307..ecd0660 100644 --- a/Lib/configparser.py +++ b/Lib/configparser.py @@ -17,7 +17,8 @@ ConfigParser -- responsible for parsing a list of __init__(defaults=None, dict_type=_default_dict, allow_no_value=False, delimiters=('=', ':'), comment_prefixes=('#', ';'), inline_comment_prefixes=None, strict=True, - empty_lines_in_values=True): + empty_lines_in_values=True, default_section='DEFAULT', + interpolation=<unset>, converters=<unset>): Create the parser. When `defaults' is given, it is initialized into the dictionary or intrinsic defaults. The keys must be strings, the values must be appropriate for %()s string interpolation. @@ -47,6 +48,25 @@ ConfigParser -- responsible for parsing a list of When `allow_no_value' is True (default: False), options without values are accepted; the value presented for these is None. + When `default_section' is given, the name of the special section is + named accordingly. By default it is called ``"DEFAULT"`` but this can + be customized to point to any other valid section name. Its current + value can be retrieved using the ``parser_instance.default_section`` + attribute and may be modified at runtime. + + When `interpolation` is given, it should be an Interpolation subclass + instance. It will be used as the handler for option value + pre-processing when using getters. RawConfigParser object s don't do + any sort of interpolation, whereas ConfigParser uses an instance of + BasicInterpolation. The library also provides a ``zc.buildbot`` + inspired ExtendedInterpolation implementation. + + When `converters` is given, it should be a dictionary where each key + represents the name of a type converter and each value is a callable + implementing the conversion from string to the desired datatype. Every + converter gets its corresponding get*() method on the parser object and + section proxies. + sections() Return all the configuration section names, sans DEFAULT. @@ -129,9 +149,11 @@ import warnings __all__ = ["NoSectionError", "DuplicateOptionError", "DuplicateSectionError", "NoOptionError", "InterpolationError", "InterpolationDepthError", - "InterpolationSyntaxError", "ParsingError", - "MissingSectionHeaderError", + "InterpolationMissingOptionError", "InterpolationSyntaxError", + "ParsingError", "MissingSectionHeaderError", "ConfigParser", "SafeConfigParser", "RawConfigParser", + "Interpolation", "BasicInterpolation", "ExtendedInterpolation", + "LegacyInterpolation", "SectionProxy", "ConverterMapping", "DEFAULTSECT", "MAX_INTERPOLATION_DEPTH"] DEFAULTSECT = "DEFAULT" @@ -410,7 +432,7 @@ class BasicInterpolation(Interpolation): v = map[var] except KeyError: raise InterpolationMissingOptionError( - option, section, rest, var) + option, section, rest, var) from None if "%" in v: self._interpolate_some(parser, option, accum, v, section, map, depth + 1) @@ -482,7 +504,7 @@ class ExtendedInterpolation(Interpolation): "More than one ':' found: %r" % (rest,)) except (KeyError, NoSectionError, NoOptionError): raise InterpolationMissingOptionError( - option, section, rest, ":".join(path)) + option, section, rest, ":".join(path)) from None if "$" in v: self._interpolate_some(parser, opt, accum, v, sect, dict(parser.items(sect, raw=True)), @@ -515,7 +537,7 @@ class LegacyInterpolation(Interpolation): value = value % vars except KeyError as e: raise InterpolationMissingOptionError( - option, section, rawval, e.args[0]) + option, section, rawval, e.args[0]) from None else: break if value and "%(" in value: @@ -580,11 +602,12 @@ class RawConfigParser(MutableMapping): comment_prefixes=('#', ';'), inline_comment_prefixes=None, strict=True, empty_lines_in_values=True, default_section=DEFAULTSECT, - interpolation=_UNSET): + interpolation=_UNSET, converters=_UNSET): self._dict = dict_type self._sections = self._dict() self._defaults = self._dict() + self._converters = ConverterMapping(self) self._proxies = self._dict() self._proxies[default_section] = SectionProxy(self, default_section) if defaults: @@ -612,6 +635,8 @@ class RawConfigParser(MutableMapping): self._interpolation = self._DEFAULT_INTERPOLATION if self._interpolation is None: self._interpolation = Interpolation() + if converters is not _UNSET: + self._converters.update(converters) def defaults(self): return self._defaults @@ -647,7 +672,7 @@ class RawConfigParser(MutableMapping): try: opts = self._sections[section].copy() except KeyError: - raise NoSectionError(section) + raise NoSectionError(section) from None opts.update(self._defaults) return list(opts.keys()) @@ -775,36 +800,31 @@ class RawConfigParser(MutableMapping): def _get(self, section, conv, option, **kwargs): return conv(self.get(section, option, **kwargs)) - def getint(self, section, option, *, raw=False, vars=None, - fallback=_UNSET): + def _get_conv(self, section, option, conv, *, raw=False, vars=None, + fallback=_UNSET, **kwargs): try: - return self._get(section, int, option, raw=raw, vars=vars) + return self._get(section, conv, option, raw=raw, vars=vars, + **kwargs) except (NoSectionError, NoOptionError): if fallback is _UNSET: raise - else: - return fallback + return fallback + + # getint, getfloat and getboolean provided directly for backwards compat + def getint(self, section, option, *, raw=False, vars=None, + fallback=_UNSET, **kwargs): + return self._get_conv(section, option, int, raw=raw, vars=vars, + fallback=fallback, **kwargs) def getfloat(self, section, option, *, raw=False, vars=None, - fallback=_UNSET): - try: - return self._get(section, float, option, raw=raw, vars=vars) - except (NoSectionError, NoOptionError): - if fallback is _UNSET: - raise - else: - return fallback + fallback=_UNSET, **kwargs): + return self._get_conv(section, option, float, raw=raw, vars=vars, + fallback=fallback, **kwargs) def getboolean(self, section, option, *, raw=False, vars=None, - fallback=_UNSET): - try: - return self._get(section, self._convert_to_boolean, option, - raw=raw, vars=vars) - except (NoSectionError, NoOptionError): - if fallback is _UNSET: - raise - else: - return fallback + fallback=_UNSET, **kwargs): + return self._get_conv(section, option, self._convert_to_boolean, + raw=raw, vars=vars, fallback=fallback, **kwargs) def items(self, section=_UNSET, raw=False, vars=None): """Return a list of (name, value) tuples for each option in a section. @@ -876,7 +896,7 @@ class RawConfigParser(MutableMapping): try: sectdict = self._sections[section] except KeyError: - raise NoSectionError(section) + raise NoSectionError(section) from None sectdict[self.optionxform(option)] = value def write(self, fp, space_around_delimiters=True): @@ -917,7 +937,7 @@ class RawConfigParser(MutableMapping): try: sectdict = self._sections[section] except KeyError: - raise NoSectionError(section) + raise NoSectionError(section) from None option = self.optionxform(option) existed = option in sectdict if existed: @@ -1154,6 +1174,10 @@ class RawConfigParser(MutableMapping): if not isinstance(value, str): raise TypeError("option values must be strings") + @property + def converters(self): + return self._converters + class ConfigParser(RawConfigParser): """ConfigParser implementing interpolation.""" @@ -1194,6 +1218,10 @@ class SectionProxy(MutableMapping): """Creates a view on a section of the specified `name` in `parser`.""" self._parser = parser self._name = name + for conv in parser.converters: + key = 'get' + conv + getter = functools.partial(self.get, _impl=getattr(parser, key)) + setattr(self, key, getter) def __repr__(self): return '<Section: {}>'.format(self._name) @@ -1227,22 +1255,6 @@ class SectionProxy(MutableMapping): else: return self._parser.defaults() - def get(self, option, fallback=None, *, raw=False, vars=None): - return self._parser.get(self._name, option, raw=raw, vars=vars, - fallback=fallback) - - def getint(self, option, fallback=None, *, raw=False, vars=None): - return self._parser.getint(self._name, option, raw=raw, vars=vars, - fallback=fallback) - - def getfloat(self, option, fallback=None, *, raw=False, vars=None): - return self._parser.getfloat(self._name, option, raw=raw, vars=vars, - fallback=fallback) - - def getboolean(self, option, fallback=None, *, raw=False, vars=None): - return self._parser.getboolean(self._name, option, raw=raw, vars=vars, - fallback=fallback) - @property def parser(self): # The parser object of the proxy is read-only. @@ -1252,3 +1264,77 @@ class SectionProxy(MutableMapping): def name(self): # The name of the section on a proxy is read-only. return self._name + + def get(self, option, fallback=None, *, raw=False, vars=None, + _impl=None, **kwargs): + """Get an option value. + + Unless `fallback` is provided, `None` will be returned if the option + is not found. + + """ + # If `_impl` is provided, it should be a getter method on the parser + # object that provides the desired type conversion. + if not _impl: + _impl = self._parser.get + return _impl(self._name, option, raw=raw, vars=vars, + fallback=fallback, **kwargs) + + +class ConverterMapping(MutableMapping): + """Enables reuse of get*() methods between the parser and section proxies. + + If a parser class implements a getter directly, the value for the given + key will be ``None``. The presence of the converter name here enables + section proxies to find and use the implementation on the parser class. + """ + + GETTERCRE = re.compile(r"^get(?P<name>.+)$") + + def __init__(self, parser): + self._parser = parser + self._data = {} + for getter in dir(self._parser): + m = self.GETTERCRE.match(getter) + if not m or not callable(getattr(self._parser, getter)): + continue + self._data[m.group('name')] = None # See class docstring. + + def __getitem__(self, key): + return self._data[key] + + def __setitem__(self, key, value): + try: + k = 'get' + key + except TypeError: + raise ValueError('Incompatible key: {} (type: {})' + ''.format(key, type(key))) + if k == 'get': + raise ValueError('Incompatible key: cannot use "" as a name') + self._data[key] = value + func = functools.partial(self._parser._get_conv, conv=value) + func.converter = value + setattr(self._parser, k, func) + for proxy in self._parser.values(): + getter = functools.partial(proxy.get, _impl=func) + setattr(proxy, k, getter) + + def __delitem__(self, key): + try: + k = 'get' + (key or None) + except TypeError: + raise KeyError(key) + del self._data[key] + for inst in itertools.chain((self._parser,), self._parser.values()): + try: + delattr(inst, k) + except AttributeError: + # don't raise since the entry was present in _data, silently + # clean up + continue + + def __iter__(self): + return iter(self._data) + + def __len__(self): + return len(self._data) diff --git a/Lib/contextlib.py b/Lib/contextlib.py index 82ee955..2fbc90c 100644 --- a/Lib/contextlib.py +++ b/Lib/contextlib.py @@ -5,7 +5,7 @@ from collections import deque from functools import wraps __all__ = ["contextmanager", "closing", "ContextDecorator", "ExitStack", - "redirect_stdout", "suppress"] + "redirect_stdout", "redirect_stderr", "suppress"] class ContextDecorator(object): @@ -151,8 +151,27 @@ class closing(object): def __exit__(self, *exc_info): self.thing.close() -class redirect_stdout: - """Context manager for temporarily redirecting stdout to another file + +class _RedirectStream: + + _stream = None + + def __init__(self, new_target): + self._new_target = new_target + # We use a list of old targets to make this CM re-entrant + self._old_targets = [] + + def __enter__(self): + self._old_targets.append(getattr(sys, self._stream)) + setattr(sys, self._stream, self._new_target) + return self._new_target + + def __exit__(self, exctype, excinst, exctb): + setattr(sys, self._stream, self._old_targets.pop()) + + +class redirect_stdout(_RedirectStream): + """Context manager for temporarily redirecting stdout to another file. # How to send help() to stderr with redirect_stdout(sys.stderr): @@ -164,18 +183,13 @@ class redirect_stdout: help(pow) """ - def __init__(self, new_target): - self._new_target = new_target - # We use a list of old targets to make this CM re-entrant - self._old_targets = [] + _stream = "stdout" - def __enter__(self): - self._old_targets.append(sys.stdout) - sys.stdout = self._new_target - return self._new_target - def __exit__(self, exctype, excinst, exctb): - sys.stdout = self._old_targets.pop() +class redirect_stderr(_RedirectStream): + """Context manager for temporarily redirecting stderr to another file.""" + + _stream = "stderr" class suppress: diff --git a/Lib/copy.py b/Lib/copy.py index bb8840e..383609b 100644 --- a/Lib/copy.py +++ b/Lib/copy.py @@ -221,17 +221,15 @@ def _deepcopy_list(x, memo): d[list] = _deepcopy_list def _deepcopy_tuple(x, memo): - y = [] - for a in x: - y.append(deepcopy(a, memo)) + y = [deepcopy(a, memo) for a in x] # We're not going to put the tuple in the memo, but it's still important we # check for it, in case the tuple contains recursive mutable structures. try: return memo[id(x)] except KeyError: pass - for i in range(len(x)): - if x[i] is not y[i]: + for k, j in zip(x, y): + if k is not j: y = tuple(y) break else: diff --git a/Lib/ctypes/__init__.py b/Lib/ctypes/__init__.py index 5c803ff..055294c 100644 --- a/Lib/ctypes/__init__.py +++ b/Lib/ctypes/__init__.py @@ -353,7 +353,7 @@ class CDLL(object): self._handle = handle def __repr__(self): - return "<%s '%s', handle %x at %x>" % \ + return "<%s '%s', handle %x at %#x>" % \ (self.__class__.__name__, self._name, (self._handle & (_sys.maxsize*2 + 1)), id(self) & (_sys.maxsize*2 + 1)) diff --git a/Lib/ctypes/_endian.py b/Lib/ctypes/_endian.py index dae65fc..37444bd 100644 --- a/Lib/ctypes/_endian.py +++ b/Lib/ctypes/_endian.py @@ -45,6 +45,7 @@ if sys.byteorder == "little": class BigEndianStructure(Structure, metaclass=_swapped_meta): """Structure with big endian byte order""" + __slots__ = () _swappedbytes_ = None elif sys.byteorder == "big": @@ -53,6 +54,7 @@ elif sys.byteorder == "big": BigEndianStructure = Structure class LittleEndianStructure(Structure, metaclass=_swapped_meta): """Structure with little endian byte order""" + __slots__ = () _swappedbytes_ = None else: diff --git a/Lib/ctypes/test/test_byteswap.py b/Lib/ctypes/test/test_byteswap.py index 427bb8b..01c97e8 100644 --- a/Lib/ctypes/test/test_byteswap.py +++ b/Lib/ctypes/test/test_byteswap.py @@ -22,6 +22,26 @@ class Test(unittest.TestCase): setattr(bits, "i%s" % i, 1) dump(bits) + def test_slots(self): + class BigPoint(BigEndianStructure): + __slots__ = () + _fields_ = [("x", c_int), ("y", c_int)] + + class LowPoint(LittleEndianStructure): + __slots__ = () + _fields_ = [("x", c_int), ("y", c_int)] + + big = BigPoint() + little = LowPoint() + big.x = 4 + big.y = 2 + little.x = 2 + little.y = 4 + with self.assertRaises(AttributeError): + big.z = 42 + with self.assertRaises(AttributeError): + little.z = 24 + def test_endian_short(self): if sys.byteorder == "little": self.assertIs(c_short.__ctype_le__, c_short) diff --git a/Lib/ctypes/test/test_pointers.py b/Lib/ctypes/test/test_pointers.py index 4cd3a7a..78e3357 100644 --- a/Lib/ctypes/test/test_pointers.py +++ b/Lib/ctypes/test/test_pointers.py @@ -24,7 +24,10 @@ class PointersTestCase(unittest.TestCase): def test_pass_pointers(self): dll = CDLL(_ctypes_test.__file__) func = dll._testfunc_p_p - func.restype = c_long + if sizeof(c_longlong) == sizeof(c_void_p): + func.restype = c_longlong + else: + func.restype = c_long i = c_int(12345678) ## func.argtypes = (POINTER(c_int),) diff --git a/Lib/ctypes/test/test_prototypes.py b/Lib/ctypes/test/test_prototypes.py index 818c111..cd0c649 100644 --- a/Lib/ctypes/test/test_prototypes.py +++ b/Lib/ctypes/test/test_prototypes.py @@ -69,7 +69,10 @@ class CharPointersTestCase(unittest.TestCase): def test_int_pointer_arg(self): func = testdll._testfunc_p_p - func.restype = c_long + if sizeof(c_longlong) == sizeof(c_void_p): + func.restype = c_longlong + else: + func.restype = c_long self.assertEqual(0, func(0)) ci = c_int(0) diff --git a/Lib/ctypes/util.py b/Lib/ctypes/util.py index 595113b..9c19899 100644 --- a/Lib/ctypes/util.py +++ b/Lib/ctypes/util.py @@ -19,6 +19,8 @@ if os.name == "nt": i = i + len(prefix) s, rest = sys.version[i:].split(" ", 1) majorVersion = int(s[:-2]) - 6 + if majorVersion >= 13: + majorVersion += 1 minorVersion = int(s[2:3]) / 10.0 # I don't think paths are affected by minor version in version 6 if majorVersion == 6: @@ -36,8 +38,10 @@ if os.name == "nt": return None if version <= 6: clibname = 'msvcrt' - else: + elif version <= 13: clibname = 'msvcr%d' % (version * 10) + else: + clibname = 'appcrt%d' % (version * 10) # If python was built with in debug mode import importlib.machinery diff --git a/Lib/datetime.py b/Lib/datetime.py index 4c442f2..de57472 100644 --- a/Lib/datetime.py +++ b/Lib/datetime.py @@ -12,7 +12,7 @@ def _cmp(x, y): MINYEAR = 1 MAXYEAR = 9999 -_MAXORDINAL = 3652059 # date.max.toordinal() +_MAXORDINAL = 3652059 # date.max.toordinal() # Utility functions, adapted from Python's Demo/classes/Dates.py, which # also assumes the current Gregorian calendar indefinitely extended in @@ -26,7 +26,7 @@ _MAXORDINAL = 3652059 # date.max.toordinal() # -1 is a placeholder for indexing purposes. _DAYS_IN_MONTH = [-1, 31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31] -_DAYS_BEFORE_MONTH = [-1] # -1 is a placeholder for indexing purposes. +_DAYS_BEFORE_MONTH = [-1] # -1 is a placeholder for indexing purposes. dbm = 0 for dim in _DAYS_IN_MONTH[1:]: _DAYS_BEFORE_MONTH.append(dbm) @@ -162,9 +162,9 @@ def _format_time(hh, mm, ss, us): # Correctly substitute for %z and %Z escapes in strftime formats. def _wrap_strftime(object, format, timetuple): # Don't call utcoffset() or tzname() unless actually needed. - freplace = None # the string to use for %f - zreplace = None # the string to use for %z - Zreplace = None # the string to use for %Z + freplace = None # the string to use for %f + zreplace = None # the string to use for %z + Zreplace = None # the string to use for %Z # Scan format for %z and %Z escapes, replacing as needed. newformat = [] @@ -217,11 +217,6 @@ def _wrap_strftime(object, format, timetuple): newformat = "".join(newformat) return _time.strftime(newformat, timetuple) -def _call_tzinfo_method(tzinfo, methname, tzinfoarg): - if tzinfo is None: - return None - return getattr(tzinfo, methname)(tzinfoarg) - # Just raise TypeError if the arg isn't None or a string. def _check_tzname(name): if name is not None and not isinstance(name, str): @@ -245,13 +240,31 @@ def _check_utc_offset(name, offset): raise ValueError("tzinfo.%s() must return a whole number " "of minutes, got %s" % (name, offset)) if not -timedelta(1) < offset < timedelta(1): - raise ValueError("%s()=%s, must be must be strictly between" - " -timedelta(hours=24) and timedelta(hours=24)" - % (name, offset)) + raise ValueError("%s()=%s, must be must be strictly between " + "-timedelta(hours=24) and timedelta(hours=24)" % + (name, offset)) + +def _check_int_field(value): + if isinstance(value, int): + return value + if not isinstance(value, float): + try: + value = value.__int__() + except AttributeError: + pass + else: + if isinstance(value, int): + return value + raise TypeError('__int__ returned non-int (type %s)' % + type(value).__name__) + raise TypeError('an integer is required (got type %s)' % + type(value).__name__) + raise TypeError('integer argument expected, got float') def _check_date_fields(year, month, day): - if not isinstance(year, int): - raise TypeError('int expected') + year = _check_int_field(year) + month = _check_int_field(month) + day = _check_int_field(day) if not MINYEAR <= year <= MAXYEAR: raise ValueError('year must be in %d..%d' % (MINYEAR, MAXYEAR), year) if not 1 <= month <= 12: @@ -259,10 +272,13 @@ def _check_date_fields(year, month, day): dim = _days_in_month(year, month) if not 1 <= day <= dim: raise ValueError('day must be in 1..%d' % dim, day) + return year, month, day def _check_time_fields(hour, minute, second, microsecond): - if not isinstance(hour, int): - raise TypeError('int expected') + hour = _check_int_field(hour) + minute = _check_int_field(minute) + second = _check_int_field(second) + microsecond = _check_int_field(microsecond) if not 0 <= hour <= 23: raise ValueError('hour must be in 0..23', hour) if not 0 <= minute <= 59: @@ -271,6 +287,7 @@ def _check_time_fields(hour, minute, second, microsecond): raise ValueError('second must be in 0..59', second) if not 0 <= microsecond <= 999999: raise ValueError('microsecond must be in 0..999999', microsecond) + return hour, minute, second, microsecond def _check_tzinfo_arg(tz): if tz is not None and not isinstance(tz, tzinfo): @@ -316,7 +333,7 @@ class timedelta: Representation: (days, seconds, microseconds). Why? Because I felt like it. """ - __slots__ = '_days', '_seconds', '_microseconds' + __slots__ = '_days', '_seconds', '_microseconds', '_hashcode' def __new__(cls, days=0, seconds=0, microseconds=0, milliseconds=0, minutes=0, hours=0, weeks=0): @@ -382,38 +399,26 @@ class timedelta: # secondsfrac isn't referenced again if isinstance(microseconds, float): - microseconds += usdouble - microseconds = round(microseconds, 0) - seconds, microseconds = divmod(microseconds, 1e6) - assert microseconds == int(microseconds) - assert seconds == int(seconds) - days, seconds = divmod(seconds, 24.*3600.) - assert days == int(days) - assert seconds == int(seconds) - d += int(days) - s += int(seconds) # can't overflow - assert isinstance(s, int) - assert abs(s) <= 3 * 24 * 3600 + microseconds = round(microseconds + usdouble) + seconds, microseconds = divmod(microseconds, 1000000) + days, seconds = divmod(seconds, 24*3600) + d += days + s += seconds else: + microseconds = int(microseconds) seconds, microseconds = divmod(microseconds, 1000000) days, seconds = divmod(seconds, 24*3600) d += days - s += int(seconds) # can't overflow - assert isinstance(s, int) - assert abs(s) <= 3 * 24 * 3600 - microseconds = float(microseconds) - microseconds += usdouble - microseconds = round(microseconds, 0) + s += seconds + microseconds = round(microseconds + usdouble) + assert isinstance(s, int) + assert isinstance(microseconds, int) assert abs(s) <= 3 * 24 * 3600 assert abs(microseconds) < 3.1e6 # Just a little bit of carrying possible for microseconds and seconds. - assert isinstance(microseconds, float) - assert int(microseconds) == microseconds - us = int(microseconds) - seconds, us = divmod(us, 1000000) - s += seconds # cant't overflow - assert isinstance(s, int) + seconds, us = divmod(microseconds, 1000000) + s += seconds days, s = divmod(s, 24*3600) d += days @@ -421,27 +426,31 @@ class timedelta: assert isinstance(s, int) and 0 <= s < 24*3600 assert isinstance(us, int) and 0 <= us < 1000000 - self = object.__new__(cls) + if abs(d) > 999999999: + raise OverflowError("timedelta # of days is too large: %d" % d) + self = object.__new__(cls) self._days = d self._seconds = s self._microseconds = us - if abs(d) > 999999999: - raise OverflowError("timedelta # of days is too large: %d" % d) - + self._hashcode = -1 return self def __repr__(self): if self._microseconds: - return "%s(%d, %d, %d)" % ('datetime.' + self.__class__.__name__, - self._days, - self._seconds, - self._microseconds) + return "%s.%s(%d, %d, %d)" % (self.__class__.__module__, + self.__class__.__qualname__, + self._days, + self._seconds, + self._microseconds) if self._seconds: - return "%s(%d, %d)" % ('datetime.' + self.__class__.__name__, - self._days, - self._seconds) - return "%s(%d)" % ('datetime.' + self.__class__.__name__, self._days) + return "%s.%s(%d, %d)" % (self.__class__.__module__, + self.__class__.__qualname__, + self._days, + self._seconds) + return "%s.%s(%d)" % (self.__class__.__module__, + self.__class__.__qualname__, + self._days) def __str__(self): mm, ss = divmod(self._seconds, 60) @@ -457,7 +466,7 @@ class timedelta: def total_seconds(self): """Total seconds in the duration.""" - return ((self.days * 86400 + self.seconds)*10**6 + + return ((self.days * 86400 + self.seconds) * 10**6 + self.microseconds) / 10**6 # Read-only field accessors @@ -578,12 +587,6 @@ class timedelta: else: return False - def __ne__(self, other): - if isinstance(other, timedelta): - return self._cmp(other) != 0 - else: - return True - def __le__(self, other): if isinstance(other, timedelta): return self._cmp(other) <= 0 @@ -613,7 +616,9 @@ class timedelta: return _cmp(self._getstate(), other._getstate()) def __hash__(self): - return hash(self._getstate()) + if self._hashcode == -1: + self._hashcode = hash(self._getstate()) + return self._hashcode def __bool__(self): return (self._days != 0 or @@ -661,7 +666,7 @@ class date: Properties (readonly): year, month, day """ - __slots__ = '_year', '_month', '_day' + __slots__ = '_year', '_month', '_day', '_hashcode' def __new__(cls, year, month=None, day=None): """Constructor. @@ -670,17 +675,19 @@ class date: year, month, day (required, base 1) """ - if (isinstance(year, bytes) and len(year) == 4 and - 1 <= year[2] <= 12 and month is None): # Month is sane + if month is None and isinstance(year, bytes) and len(year) == 4 and \ + 1 <= year[2] <= 12: # Pickle support self = object.__new__(cls) self.__setstate(year) + self._hashcode = -1 return self - _check_date_fields(year, month, day) + year, month, day = _check_date_fields(year, month, day) self = object.__new__(cls) self._year = year self._month = month self._day = day + self._hashcode = -1 return self # Additional constructors @@ -720,10 +727,11 @@ class date: >>> repr(dt) 'datetime.datetime(2010, 1, 1, 0, 0, tzinfo=datetime.timezone.utc)' """ - return "%s(%d, %d, %d)" % ('datetime.' + self.__class__.__name__, - self._year, - self._month, - self._day) + return "%s.%s(%d, %d, %d)" % (self.__class__.__module__, + self.__class__.__qualname__, + self._year, + self._month, + self._day) # XXX These shouldn't depend on time.localtime(), because that # clips the usable dates to [1970 .. 2038). At least ctime() is # easily done without using strftime() -- that's better too because @@ -743,6 +751,8 @@ class date: return _wrap_strftime(self, fmt, self.timetuple()) def __format__(self, fmt): + if not isinstance(fmt, str): + raise TypeError("must be str, not %s" % type(fmt).__name__) if len(fmt) != 0: return self.strftime(fmt) return str(self) @@ -799,7 +809,6 @@ class date: month = self._month if day is None: day = self._day - _check_date_fields(year, month, day) return date(year, month, day) # Comparisons of date objects with other. @@ -809,11 +818,6 @@ class date: return self._cmp(other) == 0 return NotImplemented - def __ne__(self, other): - if isinstance(other, date): - return self._cmp(other) != 0 - return NotImplemented - def __le__(self, other): if isinstance(other, date): return self._cmp(other) <= 0 @@ -842,7 +846,9 @@ class date: def __hash__(self): "Hash." - return hash(self._getstate()) + if self._hashcode == -1: + self._hashcode = hash(self._getstate()) + return self._hashcode # Computations @@ -912,8 +918,6 @@ class date: return bytes([yhi, ylo, self._month, self._day]), def __setstate(self, string): - if len(string) != 4 or not (1 <= string[2] <= 12): - raise TypeError("not enough arguments") yhi, ylo, self._month, self._day = string self._year = yhi * 256 + ylo @@ -932,6 +936,7 @@ class tzinfo: Subclasses must override the name(), utcoffset() and dst() methods. """ __slots__ = () + def tzname(self, dt): "datetime -> string name of time zone." raise NotImplementedError("tzinfo subclass must override tzname()") @@ -1018,6 +1023,7 @@ class time: Properties (readonly): hour, minute, second, microsecond, tzinfo """ + __slots__ = '_hour', '_minute', '_second', '_microsecond', '_tzinfo', '_hashcode' def __new__(cls, hour=0, minute=0, second=0, microsecond=0, tzinfo=None): """Constructor. @@ -1028,18 +1034,22 @@ class time: second, microsecond (default to zero) tzinfo (default to None) """ - self = object.__new__(cls) - if isinstance(hour, bytes) and len(hour) == 6: + if isinstance(hour, bytes) and len(hour) == 6 and hour[0] < 24: # Pickle support + self = object.__new__(cls) self.__setstate(hour, minute or None) + self._hashcode = -1 return self + hour, minute, second, microsecond = _check_time_fields( + hour, minute, second, microsecond) _check_tzinfo_arg(tzinfo) - _check_time_fields(hour, minute, second, microsecond) + self = object.__new__(cls) self._hour = hour self._minute = minute self._second = second self._microsecond = microsecond self._tzinfo = tzinfo + self._hashcode = -1 return self # Read-only field accessors @@ -1078,12 +1088,6 @@ class time: else: return False - def __ne__(self, other): - if isinstance(other, time): - return self._cmp(other, allow_mixed=True) != 0 - else: - return True - def __le__(self, other): if isinstance(other, time): return self._cmp(other) <= 0 @@ -1124,8 +1128,8 @@ class time: if base_compare: return _cmp((self._hour, self._minute, self._second, self._microsecond), - (other._hour, other._minute, other._second, - other._microsecond)) + (other._hour, other._minute, other._second, + other._microsecond)) if myoff is None or otoff is None: if allow_mixed: return 2 # arbitrary non-zero value @@ -1138,16 +1142,20 @@ class time: def __hash__(self): """Hash.""" - tzoff = self.utcoffset() - if not tzoff: # zero or None - return hash(self._getstate()[0]) - h, m = divmod(timedelta(hours=self.hour, minutes=self.minute) - tzoff, - timedelta(hours=1)) - assert not m % timedelta(minutes=1), "whole minute" - m //= timedelta(minutes=1) - if 0 <= h < 24: - return hash(time(h, m, self.second, self.microsecond)) - return hash((h, m, self.second, self.microsecond)) + if self._hashcode == -1: + tzoff = self.utcoffset() + if not tzoff: # zero or None + self._hashcode = hash(self._getstate()[0]) + else: + h, m = divmod(timedelta(hours=self.hour, minutes=self.minute) - tzoff, + timedelta(hours=1)) + assert not m % timedelta(minutes=1), "whole minute" + m //= timedelta(minutes=1) + if 0 <= h < 24: + self._hashcode = hash(time(h, m, self.second, self.microsecond)) + else: + self._hashcode = hash((h, m, self.second, self.microsecond)) + return self._hashcode # Conversion to string @@ -1175,8 +1183,9 @@ class time: s = ", %d" % self._second else: s = "" - s= "%s(%d, %d%s)" % ('datetime.' + self.__class__.__name__, - self._hour, self._minute, s) + s= "%s.%s(%d, %d%s)" % (self.__class__.__module__, + self.__class__.__qualname__, + self._hour, self._minute, s) if self._tzinfo is not None: assert s[-1:] == ")" s = s[:-1] + ", tzinfo=%r" % self._tzinfo + ")" @@ -1209,6 +1218,8 @@ class time: return _wrap_strftime(self, fmt, timetuple) def __format__(self, fmt): + if not isinstance(fmt, str): + raise TypeError("must be str, not %s" % type(fmt).__name__) if len(fmt) != 0: return self.strftime(fmt) return str(self) @@ -1265,16 +1276,8 @@ class time: microsecond = self.microsecond if tzinfo is True: tzinfo = self.tzinfo - _check_time_fields(hour, minute, second, microsecond) - _check_tzinfo_arg(tzinfo) return time(hour, minute, second, microsecond, tzinfo) - def __bool__(self): - if self.second or self.microsecond: - return True - offset = self.utcoffset() or timedelta(0) - return timedelta(hours=self.hour, minutes=self.minute) != offset - # Pickle support. def _getstate(self): @@ -1288,15 +1291,11 @@ class time: return (basestate, self._tzinfo) def __setstate(self, string, tzinfo): - if len(string) != 6 or string[0] >= 24: - raise TypeError("an integer is required") - (self._hour, self._minute, self._second, - us1, us2, us3) = string + if tzinfo is not None and not isinstance(tzinfo, _tzinfo_class): + raise TypeError("bad tzinfo state arg") + self._hour, self._minute, self._second, us1, us2, us3 = string self._microsecond = (((us1 << 8) | us2) << 8) | us3 - if tzinfo is None or isinstance(tzinfo, _tzinfo_class): - self._tzinfo = tzinfo - else: - raise TypeError("bad tzinfo state arg %r" % tzinfo) + self._tzinfo = tzinfo def __reduce__(self): return (time, self._getstate()) @@ -1313,25 +1312,30 @@ class datetime(date): The year, month and day arguments are required. tzinfo may be None, or an instance of a tzinfo subclass. The remaining arguments may be ints. """ + __slots__ = date.__slots__ + time.__slots__ - __slots__ = date.__slots__ + ( - '_hour', '_minute', '_second', - '_microsecond', '_tzinfo') def __new__(cls, year, month=None, day=None, hour=0, minute=0, second=0, microsecond=0, tzinfo=None): - if isinstance(year, bytes) and len(year) == 10: + if isinstance(year, bytes) and len(year) == 10 and 1 <= year[2] <= 12: # Pickle support - self = date.__new__(cls, year[:4]) + self = object.__new__(cls) self.__setstate(year, month) + self._hashcode = -1 return self + year, month, day = _check_date_fields(year, month, day) + hour, minute, second, microsecond = _check_time_fields( + hour, minute, second, microsecond) _check_tzinfo_arg(tzinfo) - _check_time_fields(hour, minute, second, microsecond) - self = date.__new__(cls, year, month, day) + self = object.__new__(cls) + self._year = year + self._month = month + self._day = day self._hour = hour self._minute = minute self._second = second self._microsecond = microsecond self._tzinfo = tzinfo + self._hashcode = -1 return self # Read-only field accessors @@ -1366,7 +1370,6 @@ class datetime(date): A timezone info object may be passed in as well. """ - _check_tzinfo_arg(tz) converter = _time.localtime if tz is None else _time.gmtime @@ -1390,7 +1393,7 @@ class datetime(date): @classmethod def utcfromtimestamp(cls, t): - "Construct a UTC datetime from a POSIX timestamp (like time.time())." + """Construct a naive UTC datetime from a POSIX timestamp.""" t, frac = divmod(t, 1.0) us = int(frac * 1e6) @@ -1405,11 +1408,6 @@ class datetime(date): ss = min(ss, 59) # clamp out leap seconds if the platform has them return cls(y, m, d, hh, mm, ss, us) - # XXX This is supposed to do better than we *can* do by using time.time(), - # XXX if the platform supports a more accurate way. The C implementation - # XXX uses gettimeofday on platforms that have it, but that isn't - # XXX available from Python. So now() may return different results - # XXX across the implementations. @classmethod def now(cls, tz=None): "Construct a datetime from time.time() and optional time zone info." @@ -1496,11 +1494,8 @@ class datetime(date): microsecond = self.microsecond if tzinfo is True: tzinfo = self.tzinfo - _check_date_fields(year, month, day) - _check_time_fields(hour, minute, second, microsecond) - _check_tzinfo_arg(tzinfo) - return datetime(year, month, day, hour, minute, second, - microsecond, tzinfo) + return datetime(year, month, day, hour, minute, second, microsecond, + tzinfo) def astimezone(self, tz=None): if tz is None: @@ -1570,10 +1565,9 @@ class datetime(date): Optional argument sep specifies the separator between date and time, default 'T'. """ - s = ("%04d-%02d-%02d%c" % (self._year, self._month, self._day, - sep) + - _format_time(self._hour, self._minute, self._second, - self._microsecond)) + s = ("%04d-%02d-%02d%c" % (self._year, self._month, self._day, sep) + + _format_time(self._hour, self._minute, self._second, + self._microsecond)) off = self.utcoffset() if off is not None: if off.days < 0: @@ -1589,14 +1583,15 @@ class datetime(date): def __repr__(self): """Convert to formal string, for repr().""" - L = [self._year, self._month, self._day, # These are never zero + L = [self._year, self._month, self._day, # These are never zero self._hour, self._minute, self._second, self._microsecond] if L[-1] == 0: del L[-1] if L[-1] == 0: del L[-1] - s = ", ".join(map(str, L)) - s = "%s(%s)" % ('datetime.' + self.__class__.__name__, s) + s = "%s.%s(%s)" % (self.__class__.__module__, + self.__class__.__qualname__, + ", ".join(map(str, L))) if self._tzinfo is not None: assert s[-1:] == ")" s = s[:-1] + ", tzinfo=%r" % self._tzinfo + ")" @@ -1628,7 +1623,9 @@ class datetime(date): it mean anything in particular. For example, "GMT", "UTC", "-500", "-5:00", "EDT", "US/Eastern", "America/New York" are all valid replies. """ - name = _call_tzinfo_method(self._tzinfo, "tzname", self) + if self._tzinfo is None: + return None + name = self._tzinfo.tzname(self) _check_tzname(name) return name @@ -1657,14 +1654,6 @@ class datetime(date): else: return False - def __ne__(self, other): - if isinstance(other, datetime): - return self._cmp(other, allow_mixed=True) != 0 - elif not isinstance(other, date): - return NotImplemented - else: - return True - def __le__(self, other): if isinstance(other, datetime): return self._cmp(other) <= 0 @@ -1714,9 +1703,9 @@ class datetime(date): return _cmp((self._year, self._month, self._day, self._hour, self._minute, self._second, self._microsecond), - (other._year, other._month, other._day, - other._hour, other._minute, other._second, - other._microsecond)) + (other._year, other._month, other._day, + other._hour, other._minute, other._second, + other._microsecond)) if myoff is None or otoff is None: if allow_mixed: return 2 # arbitrary non-zero value @@ -1774,12 +1763,15 @@ class datetime(date): return base + otoff - myoff def __hash__(self): - tzoff = self.utcoffset() - if tzoff is None: - return hash(self._getstate()[0]) - days = _ymd2ord(self.year, self.month, self.day) - seconds = self.hour * 3600 + self.minute * 60 + self.second - return hash(timedelta(days, seconds, self.microsecond) - tzoff) + if self._hashcode == -1: + tzoff = self.utcoffset() + if tzoff is None: + self._hashcode = hash(self._getstate()[0]) + else: + days = _ymd2ord(self.year, self.month, self.day) + seconds = self.hour * 3600 + self.minute * 60 + self.second + self._hashcode = hash(timedelta(days, seconds, self.microsecond) - tzoff) + return self._hashcode # Pickle support. @@ -1796,14 +1788,13 @@ class datetime(date): return (basestate, self._tzinfo) def __setstate(self, string, tzinfo): + if tzinfo is not None and not isinstance(tzinfo, _tzinfo_class): + raise TypeError("bad tzinfo state arg") (yhi, ylo, self._month, self._day, self._hour, self._minute, self._second, us1, us2, us3) = string self._year = yhi * 256 + ylo self._microsecond = (((us1 << 8) | us2) << 8) | us3 - if tzinfo is None or isinstance(tzinfo, _tzinfo_class): - self._tzinfo = tzinfo - else: - raise TypeError("bad tzinfo state arg %r" % tzinfo) + self._tzinfo = tzinfo def __reduce__(self): return (self.__class__, self._getstate()) @@ -1819,7 +1810,7 @@ def _isoweek1monday(year): # XXX This could be done more efficiently THURSDAY = 3 firstday = _ymd2ord(year, 1, 1) - firstweekday = (firstday + 6) % 7 # See weekday() above + firstweekday = (firstday + 6) % 7 # See weekday() above week1monday = firstday - firstweekday if firstweekday > THURSDAY: week1monday += 7 @@ -1840,13 +1831,12 @@ class timezone(tzinfo): elif not isinstance(name, str): raise TypeError("name must be a string") if not cls._minoffset <= offset <= cls._maxoffset: - raise ValueError("offset must be a timedelta" - " strictly between -timedelta(hours=24) and" - " timedelta(hours=24).") - if (offset.microseconds != 0 or - offset.seconds % 60 != 0): - raise ValueError("offset must be a timedelta" - " representing a whole number of minutes") + raise ValueError("offset must be a timedelta " + "strictly between -timedelta(hours=24) and " + "timedelta(hours=24).") + if (offset.microseconds != 0 or offset.seconds % 60 != 0): + raise ValueError("offset must be a timedelta " + "representing a whole number of minutes") return cls._create(offset, name) @classmethod @@ -1883,10 +1873,12 @@ class timezone(tzinfo): if self is self.utc: return 'datetime.timezone.utc' if self._name is None: - return "%s(%r)" % ('datetime.' + self.__class__.__name__, - self._offset) - return "%s(%r, %r)" % ('datetime.' + self.__class__.__name__, - self._offset, self._name) + return "%s.%s(%r)" % (self.__class__.__module__, + self.__class__.__qualname__, + self._offset) + return "%s.%s(%r, %r)" % (self.__class__.__module__, + self.__class__.__qualname__, + self._offset, self._name) def __str__(self): return self.tzname(None) @@ -2141,14 +2133,13 @@ except ImportError: pass else: # Clean up unused names - del (_DAYNAMES, _DAYS_BEFORE_MONTH, _DAYS_IN_MONTH, - _DI100Y, _DI400Y, _DI4Y, _MAXORDINAL, _MONTHNAMES, - _build_struct_time, _call_tzinfo_method, _check_date_fields, - _check_time_fields, _check_tzinfo_arg, _check_tzname, - _check_utc_offset, _cmp, _cmperror, _date_class, _days_before_month, - _days_before_year, _days_in_month, _format_time, _is_leap, - _isoweek1monday, _math, _ord2ymd, _time, _time_class, _tzinfo_class, - _wrap_strftime, _ymd2ord) + del (_DAYNAMES, _DAYS_BEFORE_MONTH, _DAYS_IN_MONTH, _DI100Y, _DI400Y, + _DI4Y, _EPOCH, _MAXORDINAL, _MONTHNAMES, _build_struct_time, + _check_date_fields, _check_int_field, _check_time_fields, + _check_tzinfo_arg, _check_tzname, _check_utc_offset, _cmp, _cmperror, + _date_class, _days_before_month, _days_before_year, _days_in_month, + _format_time, _is_leap, _isoweek1monday, _math, _ord2ymd, + _time, _time_class, _tzinfo_class, _wrap_strftime, _ymd2ord) # XXX Since import * above excludes names that start with _, # docstring does not get overwritten. In the future, it may be # appropriate to maintain a single module level docstring and diff --git a/Lib/dbm/dumb.py b/Lib/dbm/dumb.py index a9ead68..3424096 100644 --- a/Lib/dbm/dumb.py +++ b/Lib/dbm/dumb.py @@ -45,7 +45,7 @@ class _Database(collections.MutableMapping): _os = _os # for _commit() _io = _io # for _commit() - def __init__(self, filebasename, mode): + def __init__(self, filebasename, mode, flag='c'): self._mode = mode # The directory file is a text file. Each line looks like @@ -65,6 +65,17 @@ class _Database(collections.MutableMapping): # The index is an in-memory dict, mirroring the directory file. self._index = None # maps keys to (pos, siz) pairs + # Handle the creation + self._create(flag) + self._update() + + def _create(self, flag): + if flag == 'n': + for filename in (self._datfile, self._bakfile, self._dirfile): + try: + _os.remove(filename) + except OSError: + pass # Mod by Jack: create data file if needed try: f = _io.open(self._datfile, 'r', encoding="Latin-1") @@ -73,7 +84,6 @@ class _Database(collections.MutableMapping): self._chmod(self._datfile) else: f.close() - self._update() # Read directory file into the in-memory index dict. def _update(self): @@ -264,20 +274,20 @@ class _Database(collections.MutableMapping): self.close() -def open(file, flag=None, mode=0o666): +def open(file, flag='c', mode=0o666): """Open the database file, filename, and return corresponding object. The flag argument, used to control how the database is opened in the - other DBM implementations, is ignored in the dbm.dumb module; the - database is always opened for update, and will be created if it does - not exist. + other DBM implementations, supports only the semantics of 'c' and 'n' + values. Other values will default to the semantics of 'c' value: + the database will always opened for update and will be created if it + does not exist. The optional mode argument is the UNIX mode of the file, used only when the database has to be created. It defaults to octal code 0o666 (and will be modified by the prevailing umask). """ - # flag argument is currently ignored # Modify mode depending on the umask try: @@ -288,5 +298,4 @@ def open(file, flag=None, mode=0o666): else: # Turn off any bits that are set in the umask mode = mode & (~um) - - return _Database(file, mode) + return _Database(file, mode, flag=flag) diff --git a/Lib/decimal.py b/Lib/decimal.py index b254f9c..7746ea2 100644 --- a/Lib/decimal.py +++ b/Lib/decimal.py @@ -1,6414 +1,11 @@ -# Copyright (c) 2004 Python Software Foundation. -# All rights reserved. - -# Written by Eric Price <eprice at tjhsst.edu> -# and Facundo Batista <facundo at taniquetil.com.ar> -# and Raymond Hettinger <python at rcn.com> -# and Aahz <aahz at pobox.com> -# and Tim Peters - -# This module should be kept in sync with the latest updates of the -# IBM specification as it evolves. Those updates will be treated -# as bug fixes (deviation from the spec is a compatibility, usability -# bug) and will be backported. At this point the spec is stabilizing -# and the updates are becoming fewer, smaller, and less significant. - -""" -This is an implementation of decimal floating point arithmetic based on -the General Decimal Arithmetic Specification: - - http://speleotrove.com/decimal/decarith.html - -and IEEE standard 854-1987: - - http://en.wikipedia.org/wiki/IEEE_854-1987 - -Decimal floating point has finite precision with arbitrarily large bounds. - -The purpose of this module is to support arithmetic using familiar -"schoolhouse" rules and to avoid some of the tricky representation -issues associated with binary floating point. The package is especially -useful for financial applications or for contexts where users have -expectations that are at odds with binary floating point (for instance, -in binary floating point, 1.00 % 0.1 gives 0.09999999999999995 instead -of 0.0; Decimal('1.00') % Decimal('0.1') returns the expected -Decimal('0.00')). - -Here are some examples of using the decimal module: - ->>> from decimal import * ->>> setcontext(ExtendedContext) ->>> Decimal(0) -Decimal('0') ->>> Decimal('1') -Decimal('1') ->>> Decimal('-.0123') -Decimal('-0.0123') ->>> Decimal(123456) -Decimal('123456') ->>> Decimal('123.45e12345678') -Decimal('1.2345E+12345680') ->>> Decimal('1.33') + Decimal('1.27') -Decimal('2.60') ->>> Decimal('12.34') + Decimal('3.87') - Decimal('18.41') -Decimal('-2.20') ->>> dig = Decimal(1) ->>> print(dig / Decimal(3)) -0.333333333 ->>> getcontext().prec = 18 ->>> print(dig / Decimal(3)) -0.333333333333333333 ->>> print(dig.sqrt()) -1 ->>> print(Decimal(3).sqrt()) -1.73205080756887729 ->>> print(Decimal(3) ** 123) -4.85192780976896427E+58 ->>> inf = Decimal(1) / Decimal(0) ->>> print(inf) -Infinity ->>> neginf = Decimal(-1) / Decimal(0) ->>> print(neginf) --Infinity ->>> print(neginf + inf) -NaN ->>> print(neginf * inf) --Infinity ->>> print(dig / 0) -Infinity ->>> getcontext().traps[DivisionByZero] = 1 ->>> print(dig / 0) -Traceback (most recent call last): - ... - ... - ... -decimal.DivisionByZero: x / 0 ->>> c = Context() ->>> c.traps[InvalidOperation] = 0 ->>> print(c.flags[InvalidOperation]) -0 ->>> c.divide(Decimal(0), Decimal(0)) -Decimal('NaN') ->>> c.traps[InvalidOperation] = 1 ->>> print(c.flags[InvalidOperation]) -1 ->>> c.flags[InvalidOperation] = 0 ->>> print(c.flags[InvalidOperation]) -0 ->>> print(c.divide(Decimal(0), Decimal(0))) -Traceback (most recent call last): - ... - ... - ... -decimal.InvalidOperation: 0 / 0 ->>> print(c.flags[InvalidOperation]) -1 ->>> c.flags[InvalidOperation] = 0 ->>> c.traps[InvalidOperation] = 0 ->>> print(c.divide(Decimal(0), Decimal(0))) -NaN ->>> print(c.flags[InvalidOperation]) -1 ->>> -""" - -__all__ = [ - # Two major classes - 'Decimal', 'Context', - - # Named tuple representation - 'DecimalTuple', - - # Contexts - 'DefaultContext', 'BasicContext', 'ExtendedContext', - - # Exceptions - 'DecimalException', 'Clamped', 'InvalidOperation', 'DivisionByZero', - 'Inexact', 'Rounded', 'Subnormal', 'Overflow', 'Underflow', - 'FloatOperation', - - # Exceptional conditions that trigger InvalidOperation - 'DivisionImpossible', 'InvalidContext', 'ConversionSyntax', 'DivisionUndefined', - - # Constants for use in setting up contexts - 'ROUND_DOWN', 'ROUND_HALF_UP', 'ROUND_HALF_EVEN', 'ROUND_CEILING', - 'ROUND_FLOOR', 'ROUND_UP', 'ROUND_HALF_DOWN', 'ROUND_05UP', - - # Functions for manipulating contexts - 'setcontext', 'getcontext', 'localcontext', - - # Limits for the C version for compatibility - 'MAX_PREC', 'MAX_EMAX', 'MIN_EMIN', 'MIN_ETINY', - - # C version: compile time choice that enables the thread local context - 'HAVE_THREADS' -] - -__version__ = '1.70' # Highest version of the spec this complies with - # See http://speleotrove.com/decimal/ -__libmpdec_version__ = "2.4.1" # compatible libmpdec version - -import math as _math -import numbers as _numbers -import sys - -try: - from collections import namedtuple as _namedtuple - DecimalTuple = _namedtuple('DecimalTuple', 'sign digits exponent') -except ImportError: - DecimalTuple = lambda *args: args - -# Rounding -ROUND_DOWN = 'ROUND_DOWN' -ROUND_HALF_UP = 'ROUND_HALF_UP' -ROUND_HALF_EVEN = 'ROUND_HALF_EVEN' -ROUND_CEILING = 'ROUND_CEILING' -ROUND_FLOOR = 'ROUND_FLOOR' -ROUND_UP = 'ROUND_UP' -ROUND_HALF_DOWN = 'ROUND_HALF_DOWN' -ROUND_05UP = 'ROUND_05UP' - -# Compatibility with the C version -HAVE_THREADS = True -if sys.maxsize == 2**63-1: - MAX_PREC = 999999999999999999 - MAX_EMAX = 999999999999999999 - MIN_EMIN = -999999999999999999 -else: - MAX_PREC = 425000000 - MAX_EMAX = 425000000 - MIN_EMIN = -425000000 - -MIN_ETINY = MIN_EMIN - (MAX_PREC-1) - -# Errors - -class DecimalException(ArithmeticError): - """Base exception class. - - Used exceptions derive from this. - If an exception derives from another exception besides this (such as - Underflow (Inexact, Rounded, Subnormal) that indicates that it is only - called if the others are present. This isn't actually used for - anything, though. - - handle -- Called when context._raise_error is called and the - trap_enabler is not set. First argument is self, second is the - context. More arguments can be given, those being after - the explanation in _raise_error (For example, - context._raise_error(NewError, '(-x)!', self._sign) would - call NewError().handle(context, self._sign).) - - To define a new exception, it should be sufficient to have it derive - from DecimalException. - """ - def handle(self, context, *args): - pass - - -class Clamped(DecimalException): - """Exponent of a 0 changed to fit bounds. - - This occurs and signals clamped if the exponent of a result has been - altered in order to fit the constraints of a specific concrete - representation. This may occur when the exponent of a zero result would - be outside the bounds of a representation, or when a large normal - number would have an encoded exponent that cannot be represented. In - this latter case, the exponent is reduced to fit and the corresponding - number of zero digits are appended to the coefficient ("fold-down"). - """ - -class InvalidOperation(DecimalException): - """An invalid operation was performed. - - Various bad things cause this: - - Something creates a signaling NaN - -INF + INF - 0 * (+-)INF - (+-)INF / (+-)INF - x % 0 - (+-)INF % x - x._rescale( non-integer ) - sqrt(-x) , x > 0 - 0 ** 0 - x ** (non-integer) - x ** (+-)INF - An operand is invalid - - The result of the operation after these is a quiet positive NaN, - except when the cause is a signaling NaN, in which case the result is - also a quiet NaN, but with the original sign, and an optional - diagnostic information. - """ - def handle(self, context, *args): - if args: - ans = _dec_from_triple(args[0]._sign, args[0]._int, 'n', True) - return ans._fix_nan(context) - return _NaN - -class ConversionSyntax(InvalidOperation): - """Trying to convert badly formed string. - - This occurs and signals invalid-operation if an string is being - converted to a number and it does not conform to the numeric string - syntax. The result is [0,qNaN]. - """ - def handle(self, context, *args): - return _NaN - -class DivisionByZero(DecimalException, ZeroDivisionError): - """Division by 0. - - This occurs and signals division-by-zero if division of a finite number - by zero was attempted (during a divide-integer or divide operation, or a - power operation with negative right-hand operand), and the dividend was - not zero. - - The result of the operation is [sign,inf], where sign is the exclusive - or of the signs of the operands for divide, or is 1 for an odd power of - -0, for power. - """ - - def handle(self, context, sign, *args): - return _SignedInfinity[sign] - -class DivisionImpossible(InvalidOperation): - """Cannot perform the division adequately. - - This occurs and signals invalid-operation if the integer result of a - divide-integer or remainder operation had too many digits (would be - longer than precision). The result is [0,qNaN]. - """ - - def handle(self, context, *args): - return _NaN - -class DivisionUndefined(InvalidOperation, ZeroDivisionError): - """Undefined result of division. - - This occurs and signals invalid-operation if division by zero was - attempted (during a divide-integer, divide, or remainder operation), and - the dividend is also zero. The result is [0,qNaN]. - """ - - def handle(self, context, *args): - return _NaN - -class Inexact(DecimalException): - """Had to round, losing information. - - This occurs and signals inexact whenever the result of an operation is - not exact (that is, it needed to be rounded and any discarded digits - were non-zero), or if an overflow or underflow condition occurs. The - result in all cases is unchanged. - - The inexact signal may be tested (or trapped) to determine if a given - operation (or sequence of operations) was inexact. - """ - -class InvalidContext(InvalidOperation): - """Invalid context. Unknown rounding, for example. - - This occurs and signals invalid-operation if an invalid context was - detected during an operation. This can occur if contexts are not checked - on creation and either the precision exceeds the capability of the - underlying concrete representation or an unknown or unsupported rounding - was specified. These aspects of the context need only be checked when - the values are required to be used. The result is [0,qNaN]. - """ - - def handle(self, context, *args): - return _NaN - -class Rounded(DecimalException): - """Number got rounded (not necessarily changed during rounding). - - This occurs and signals rounded whenever the result of an operation is - rounded (that is, some zero or non-zero digits were discarded from the - coefficient), or if an overflow or underflow condition occurs. The - result in all cases is unchanged. - - The rounded signal may be tested (or trapped) to determine if a given - operation (or sequence of operations) caused a loss of precision. - """ - -class Subnormal(DecimalException): - """Exponent < Emin before rounding. - - This occurs and signals subnormal whenever the result of a conversion or - operation is subnormal (that is, its adjusted exponent is less than - Emin, before any rounding). The result in all cases is unchanged. - - The subnormal signal may be tested (or trapped) to determine if a given - or operation (or sequence of operations) yielded a subnormal result. - """ - -class Overflow(Inexact, Rounded): - """Numerical overflow. - - This occurs and signals overflow if the adjusted exponent of a result - (from a conversion or from an operation that is not an attempt to divide - by zero), after rounding, would be greater than the largest value that - can be handled by the implementation (the value Emax). - - The result depends on the rounding mode: - - For round-half-up and round-half-even (and for round-half-down and - round-up, if implemented), the result of the operation is [sign,inf], - where sign is the sign of the intermediate result. For round-down, the - result is the largest finite number that can be represented in the - current precision, with the sign of the intermediate result. For - round-ceiling, the result is the same as for round-down if the sign of - the intermediate result is 1, or is [0,inf] otherwise. For round-floor, - the result is the same as for round-down if the sign of the intermediate - result is 0, or is [1,inf] otherwise. In all cases, Inexact and Rounded - will also be raised. - """ - - def handle(self, context, sign, *args): - if context.rounding in (ROUND_HALF_UP, ROUND_HALF_EVEN, - ROUND_HALF_DOWN, ROUND_UP): - return _SignedInfinity[sign] - if sign == 0: - if context.rounding == ROUND_CEILING: - return _SignedInfinity[sign] - return _dec_from_triple(sign, '9'*context.prec, - context.Emax-context.prec+1) - if sign == 1: - if context.rounding == ROUND_FLOOR: - return _SignedInfinity[sign] - return _dec_from_triple(sign, '9'*context.prec, - context.Emax-context.prec+1) - - -class Underflow(Inexact, Rounded, Subnormal): - """Numerical underflow with result rounded to 0. - - This occurs and signals underflow if a result is inexact and the - adjusted exponent of the result would be smaller (more negative) than - the smallest value that can be handled by the implementation (the value - Emin). That is, the result is both inexact and subnormal. - - The result after an underflow will be a subnormal number rounded, if - necessary, so that its exponent is not less than Etiny. This may result - in 0 with the sign of the intermediate result and an exponent of Etiny. - - In all cases, Inexact, Rounded, and Subnormal will also be raised. - """ - -class FloatOperation(DecimalException, TypeError): - """Enable stricter semantics for mixing floats and Decimals. - - If the signal is not trapped (default), mixing floats and Decimals is - permitted in the Decimal() constructor, context.create_decimal() and - all comparison operators. Both conversion and comparisons are exact. - Any occurrence of a mixed operation is silently recorded by setting - FloatOperation in the context flags. Explicit conversions with - Decimal.from_float() or context.create_decimal_from_float() do not - set the flag. - - Otherwise (the signal is trapped), only equality comparisons and explicit - conversions are silent. All other mixed operations raise FloatOperation. - """ - -# List of public traps and flags -_signals = [Clamped, DivisionByZero, Inexact, Overflow, Rounded, - Underflow, InvalidOperation, Subnormal, FloatOperation] - -# Map conditions (per the spec) to signals -_condition_map = {ConversionSyntax:InvalidOperation, - DivisionImpossible:InvalidOperation, - DivisionUndefined:InvalidOperation, - InvalidContext:InvalidOperation} - -# Valid rounding modes -_rounding_modes = (ROUND_DOWN, ROUND_HALF_UP, ROUND_HALF_EVEN, ROUND_CEILING, - ROUND_FLOOR, ROUND_UP, ROUND_HALF_DOWN, ROUND_05UP) - -##### Context Functions ################################################## - -# The getcontext() and setcontext() function manage access to a thread-local -# current context. Py2.4 offers direct support for thread locals. If that -# is not available, use threading.current_thread() which is slower but will -# work for older Pythons. If threads are not part of the build, create a -# mock threading object with threading.local() returning the module namespace. - -try: - import threading -except ImportError: - # Python was compiled without threads; create a mock object instead - class MockThreading(object): - def local(self, sys=sys): - return sys.modules[__name__] - threading = MockThreading() - del MockThreading - -try: - threading.local - -except AttributeError: - - # To fix reloading, force it to create a new context - # Old contexts have different exceptions in their dicts, making problems. - if hasattr(threading.current_thread(), '__decimal_context__'): - del threading.current_thread().__decimal_context__ - - def setcontext(context): - """Set this thread's context to context.""" - if context in (DefaultContext, BasicContext, ExtendedContext): - context = context.copy() - context.clear_flags() - threading.current_thread().__decimal_context__ = context - - def getcontext(): - """Returns this thread's context. - - If this thread does not yet have a context, returns - a new context and sets this thread's context. - New contexts are copies of DefaultContext. - """ - try: - return threading.current_thread().__decimal_context__ - except AttributeError: - context = Context() - threading.current_thread().__decimal_context__ = context - return context - -else: - - local = threading.local() - if hasattr(local, '__decimal_context__'): - del local.__decimal_context__ - - def getcontext(_local=local): - """Returns this thread's context. - - If this thread does not yet have a context, returns - a new context and sets this thread's context. - New contexts are copies of DefaultContext. - """ - try: - return _local.__decimal_context__ - except AttributeError: - context = Context() - _local.__decimal_context__ = context - return context - - def setcontext(context, _local=local): - """Set this thread's context to context.""" - if context in (DefaultContext, BasicContext, ExtendedContext): - context = context.copy() - context.clear_flags() - _local.__decimal_context__ = context - - del threading, local # Don't contaminate the namespace - -def localcontext(ctx=None): - """Return a context manager for a copy of the supplied context - - Uses a copy of the current context if no context is specified - The returned context manager creates a local decimal context - in a with statement: - def sin(x): - with localcontext() as ctx: - ctx.prec += 2 - # Rest of sin calculation algorithm - # uses a precision 2 greater than normal - return +s # Convert result to normal precision - - def sin(x): - with localcontext(ExtendedContext): - # Rest of sin calculation algorithm - # uses the Extended Context from the - # General Decimal Arithmetic Specification - return +s # Convert result to normal context - - >>> setcontext(DefaultContext) - >>> print(getcontext().prec) - 28 - >>> with localcontext(): - ... ctx = getcontext() - ... ctx.prec += 2 - ... print(ctx.prec) - ... - 30 - >>> with localcontext(ExtendedContext): - ... print(getcontext().prec) - ... - 9 - >>> print(getcontext().prec) - 28 - """ - if ctx is None: ctx = getcontext() - return _ContextManager(ctx) - - -##### Decimal class ####################################################### - -# Do not subclass Decimal from numbers.Real and do not register it as such -# (because Decimals are not interoperable with floats). See the notes in -# numbers.py for more detail. - -class Decimal(object): - """Floating point class for decimal arithmetic.""" - - __slots__ = ('_exp','_int','_sign', '_is_special') - # Generally, the value of the Decimal instance is given by - # (-1)**_sign * _int * 10**_exp - # Special values are signified by _is_special == True - - # We're immutable, so use __new__ not __init__ - def __new__(cls, value="0", context=None): - """Create a decimal point instance. - - >>> Decimal('3.14') # string input - Decimal('3.14') - >>> Decimal((0, (3, 1, 4), -2)) # tuple (sign, digit_tuple, exponent) - Decimal('3.14') - >>> Decimal(314) # int - Decimal('314') - >>> Decimal(Decimal(314)) # another decimal instance - Decimal('314') - >>> Decimal(' 3.14 \\n') # leading and trailing whitespace okay - Decimal('3.14') - """ - - # Note that the coefficient, self._int, is actually stored as - # a string rather than as a tuple of digits. This speeds up - # the "digits to integer" and "integer to digits" conversions - # that are used in almost every arithmetic operation on - # Decimals. This is an internal detail: the as_tuple function - # and the Decimal constructor still deal with tuples of - # digits. - - self = object.__new__(cls) - - # From a string - # REs insist on real strings, so we can too. - if isinstance(value, str): - m = _parser(value.strip()) - if m is None: - if context is None: - context = getcontext() - return context._raise_error(ConversionSyntax, - "Invalid literal for Decimal: %r" % value) - - if m.group('sign') == "-": - self._sign = 1 - else: - self._sign = 0 - intpart = m.group('int') - if intpart is not None: - # finite number - fracpart = m.group('frac') or '' - exp = int(m.group('exp') or '0') - self._int = str(int(intpart+fracpart)) - self._exp = exp - len(fracpart) - self._is_special = False - else: - diag = m.group('diag') - if diag is not None: - # NaN - self._int = str(int(diag or '0')).lstrip('0') - if m.group('signal'): - self._exp = 'N' - else: - self._exp = 'n' - else: - # infinity - self._int = '0' - self._exp = 'F' - self._is_special = True - return self - - # From an integer - if isinstance(value, int): - if value >= 0: - self._sign = 0 - else: - self._sign = 1 - self._exp = 0 - self._int = str(abs(value)) - self._is_special = False - return self - - # From another decimal - if isinstance(value, Decimal): - self._exp = value._exp - self._sign = value._sign - self._int = value._int - self._is_special = value._is_special - return self - - # From an internal working value - if isinstance(value, _WorkRep): - self._sign = value.sign - self._int = str(value.int) - self._exp = int(value.exp) - self._is_special = False - return self - - # tuple/list conversion (possibly from as_tuple()) - if isinstance(value, (list,tuple)): - if len(value) != 3: - raise ValueError('Invalid tuple size in creation of Decimal ' - 'from list or tuple. The list or tuple ' - 'should have exactly three elements.') - # process sign. The isinstance test rejects floats - if not (isinstance(value[0], int) and value[0] in (0,1)): - raise ValueError("Invalid sign. The first value in the tuple " - "should be an integer; either 0 for a " - "positive number or 1 for a negative number.") - self._sign = value[0] - if value[2] == 'F': - # infinity: value[1] is ignored - self._int = '0' - self._exp = value[2] - self._is_special = True - else: - # process and validate the digits in value[1] - digits = [] - for digit in value[1]: - if isinstance(digit, int) and 0 <= digit <= 9: - # skip leading zeros - if digits or digit != 0: - digits.append(digit) - else: - raise ValueError("The second value in the tuple must " - "be composed of integers in the range " - "0 through 9.") - if value[2] in ('n', 'N'): - # NaN: digits form the diagnostic - self._int = ''.join(map(str, digits)) - self._exp = value[2] - self._is_special = True - elif isinstance(value[2], int): - # finite number: digits give the coefficient - self._int = ''.join(map(str, digits or [0])) - self._exp = value[2] - self._is_special = False - else: - raise ValueError("The third value in the tuple must " - "be an integer, or one of the " - "strings 'F', 'n', 'N'.") - return self - - if isinstance(value, float): - if context is None: - context = getcontext() - context._raise_error(FloatOperation, - "strict semantics for mixing floats and Decimals are " - "enabled") - value = Decimal.from_float(value) - self._exp = value._exp - self._sign = value._sign - self._int = value._int - self._is_special = value._is_special - return self - - raise TypeError("Cannot convert %r to Decimal" % value) - - @classmethod - def from_float(cls, f): - """Converts a float to a decimal number, exactly. - - Note that Decimal.from_float(0.1) is not the same as Decimal('0.1'). - Since 0.1 is not exactly representable in binary floating point, the - value is stored as the nearest representable value which is - 0x1.999999999999ap-4. The exact equivalent of the value in decimal - is 0.1000000000000000055511151231257827021181583404541015625. - - >>> Decimal.from_float(0.1) - Decimal('0.1000000000000000055511151231257827021181583404541015625') - >>> Decimal.from_float(float('nan')) - Decimal('NaN') - >>> Decimal.from_float(float('inf')) - Decimal('Infinity') - >>> Decimal.from_float(-float('inf')) - Decimal('-Infinity') - >>> Decimal.from_float(-0.0) - Decimal('-0') - - """ - if isinstance(f, int): # handle integer inputs - return cls(f) - if not isinstance(f, float): - raise TypeError("argument must be int or float.") - if _math.isinf(f) or _math.isnan(f): - return cls(repr(f)) - if _math.copysign(1.0, f) == 1.0: - sign = 0 - else: - sign = 1 - n, d = abs(f).as_integer_ratio() - k = d.bit_length() - 1 - result = _dec_from_triple(sign, str(n*5**k), -k) - if cls is Decimal: - return result - else: - return cls(result) - - def _isnan(self): - """Returns whether the number is not actually one. - - 0 if a number - 1 if NaN - 2 if sNaN - """ - if self._is_special: - exp = self._exp - if exp == 'n': - return 1 - elif exp == 'N': - return 2 - return 0 - - def _isinfinity(self): - """Returns whether the number is infinite - - 0 if finite or not a number - 1 if +INF - -1 if -INF - """ - if self._exp == 'F': - if self._sign: - return -1 - return 1 - return 0 - - def _check_nans(self, other=None, context=None): - """Returns whether the number is not actually one. - - if self, other are sNaN, signal - if self, other are NaN return nan - return 0 - - Done before operations. - """ - - self_is_nan = self._isnan() - if other is None: - other_is_nan = False - else: - other_is_nan = other._isnan() - - if self_is_nan or other_is_nan: - if context is None: - context = getcontext() - - if self_is_nan == 2: - return context._raise_error(InvalidOperation, 'sNaN', - self) - if other_is_nan == 2: - return context._raise_error(InvalidOperation, 'sNaN', - other) - if self_is_nan: - return self._fix_nan(context) - - return other._fix_nan(context) - return 0 - - def _compare_check_nans(self, other, context): - """Version of _check_nans used for the signaling comparisons - compare_signal, __le__, __lt__, __ge__, __gt__. - - Signal InvalidOperation if either self or other is a (quiet - or signaling) NaN. Signaling NaNs take precedence over quiet - NaNs. - - Return 0 if neither operand is a NaN. - - """ - if context is None: - context = getcontext() - - if self._is_special or other._is_special: - if self.is_snan(): - return context._raise_error(InvalidOperation, - 'comparison involving sNaN', - self) - elif other.is_snan(): - return context._raise_error(InvalidOperation, - 'comparison involving sNaN', - other) - elif self.is_qnan(): - return context._raise_error(InvalidOperation, - 'comparison involving NaN', - self) - elif other.is_qnan(): - return context._raise_error(InvalidOperation, - 'comparison involving NaN', - other) - return 0 - - def __bool__(self): - """Return True if self is nonzero; otherwise return False. - - NaNs and infinities are considered nonzero. - """ - return self._is_special or self._int != '0' - - def _cmp(self, other): - """Compare the two non-NaN decimal instances self and other. - - Returns -1 if self < other, 0 if self == other and 1 - if self > other. This routine is for internal use only.""" - - if self._is_special or other._is_special: - self_inf = self._isinfinity() - other_inf = other._isinfinity() - if self_inf == other_inf: - return 0 - elif self_inf < other_inf: - return -1 - else: - return 1 - - # check for zeros; Decimal('0') == Decimal('-0') - if not self: - if not other: - return 0 - else: - return -((-1)**other._sign) - if not other: - return (-1)**self._sign - - # If different signs, neg one is less - if other._sign < self._sign: - return -1 - if self._sign < other._sign: - return 1 - - self_adjusted = self.adjusted() - other_adjusted = other.adjusted() - if self_adjusted == other_adjusted: - self_padded = self._int + '0'*(self._exp - other._exp) - other_padded = other._int + '0'*(other._exp - self._exp) - if self_padded == other_padded: - return 0 - elif self_padded < other_padded: - return -(-1)**self._sign - else: - return (-1)**self._sign - elif self_adjusted > other_adjusted: - return (-1)**self._sign - else: # self_adjusted < other_adjusted - return -((-1)**self._sign) - - # Note: The Decimal standard doesn't cover rich comparisons for - # Decimals. In particular, the specification is silent on the - # subject of what should happen for a comparison involving a NaN. - # We take the following approach: - # - # == comparisons involving a quiet NaN always return False - # != comparisons involving a quiet NaN always return True - # == or != comparisons involving a signaling NaN signal - # InvalidOperation, and return False or True as above if the - # InvalidOperation is not trapped. - # <, >, <= and >= comparisons involving a (quiet or signaling) - # NaN signal InvalidOperation, and return False if the - # InvalidOperation is not trapped. - # - # This behavior is designed to conform as closely as possible to - # that specified by IEEE 754. - - def __eq__(self, other, context=None): - self, other = _convert_for_comparison(self, other, equality_op=True) - if other is NotImplemented: - return other - if self._check_nans(other, context): - return False - return self._cmp(other) == 0 - - def __ne__(self, other, context=None): - self, other = _convert_for_comparison(self, other, equality_op=True) - if other is NotImplemented: - return other - if self._check_nans(other, context): - return True - return self._cmp(other) != 0 - - - def __lt__(self, other, context=None): - self, other = _convert_for_comparison(self, other) - if other is NotImplemented: - return other - ans = self._compare_check_nans(other, context) - if ans: - return False - return self._cmp(other) < 0 - - def __le__(self, other, context=None): - self, other = _convert_for_comparison(self, other) - if other is NotImplemented: - return other - ans = self._compare_check_nans(other, context) - if ans: - return False - return self._cmp(other) <= 0 - - def __gt__(self, other, context=None): - self, other = _convert_for_comparison(self, other) - if other is NotImplemented: - return other - ans = self._compare_check_nans(other, context) - if ans: - return False - return self._cmp(other) > 0 - - def __ge__(self, other, context=None): - self, other = _convert_for_comparison(self, other) - if other is NotImplemented: - return other - ans = self._compare_check_nans(other, context) - if ans: - return False - return self._cmp(other) >= 0 - - def compare(self, other, context=None): - """Compares one to another. - - -1 => a < b - 0 => a = b - 1 => a > b - NaN => one is NaN - Like __cmp__, but returns Decimal instances. - """ - other = _convert_other(other, raiseit=True) - - # Compare(NaN, NaN) = NaN - if (self._is_special or other and other._is_special): - ans = self._check_nans(other, context) - if ans: - return ans - - return Decimal(self._cmp(other)) - - def __hash__(self): - """x.__hash__() <==> hash(x)""" - - # In order to make sure that the hash of a Decimal instance - # agrees with the hash of a numerically equal integer, float - # or Fraction, we follow the rules for numeric hashes outlined - # in the documentation. (See library docs, 'Built-in Types'). - if self._is_special: - if self.is_snan(): - raise TypeError('Cannot hash a signaling NaN value.') - elif self.is_nan(): - return _PyHASH_NAN - else: - if self._sign: - return -_PyHASH_INF - else: - return _PyHASH_INF - - if self._exp >= 0: - exp_hash = pow(10, self._exp, _PyHASH_MODULUS) - else: - exp_hash = pow(_PyHASH_10INV, -self._exp, _PyHASH_MODULUS) - hash_ = int(self._int) * exp_hash % _PyHASH_MODULUS - ans = hash_ if self >= 0 else -hash_ - return -2 if ans == -1 else ans - - def as_tuple(self): - """Represents the number as a triple tuple. - - To show the internals exactly as they are. - """ - return DecimalTuple(self._sign, tuple(map(int, self._int)), self._exp) - - def __repr__(self): - """Represents the number as an instance of Decimal.""" - # Invariant: eval(repr(d)) == d - return "Decimal('%s')" % str(self) - - def __str__(self, eng=False, context=None): - """Return string representation of the number in scientific notation. - - Captures all of the information in the underlying representation. - """ - - sign = ['', '-'][self._sign] - if self._is_special: - if self._exp == 'F': - return sign + 'Infinity' - elif self._exp == 'n': - return sign + 'NaN' + self._int - else: # self._exp == 'N' - return sign + 'sNaN' + self._int - - # number of digits of self._int to left of decimal point - leftdigits = self._exp + len(self._int) - - # dotplace is number of digits of self._int to the left of the - # decimal point in the mantissa of the output string (that is, - # after adjusting the exponent) - if self._exp <= 0 and leftdigits > -6: - # no exponent required - dotplace = leftdigits - elif not eng: - # usual scientific notation: 1 digit on left of the point - dotplace = 1 - elif self._int == '0': - # engineering notation, zero - dotplace = (leftdigits + 1) % 3 - 1 - else: - # engineering notation, nonzero - dotplace = (leftdigits - 1) % 3 + 1 - - if dotplace <= 0: - intpart = '0' - fracpart = '.' + '0'*(-dotplace) + self._int - elif dotplace >= len(self._int): - intpart = self._int+'0'*(dotplace-len(self._int)) - fracpart = '' - else: - intpart = self._int[:dotplace] - fracpart = '.' + self._int[dotplace:] - if leftdigits == dotplace: - exp = '' - else: - if context is None: - context = getcontext() - exp = ['e', 'E'][context.capitals] + "%+d" % (leftdigits-dotplace) - - return sign + intpart + fracpart + exp - - def to_eng_string(self, context=None): - """Convert to engineering-type string. - - Engineering notation has an exponent which is a multiple of 3, so there - are up to 3 digits left of the decimal place. - - Same rules for when in exponential and when as a value as in __str__. - """ - return self.__str__(eng=True, context=context) - - def __neg__(self, context=None): - """Returns a copy with the sign switched. - - Rounds, if it has reason. - """ - if self._is_special: - ans = self._check_nans(context=context) - if ans: - return ans - - if context is None: - context = getcontext() - - if not self and context.rounding != ROUND_FLOOR: - # -Decimal('0') is Decimal('0'), not Decimal('-0'), except - # in ROUND_FLOOR rounding mode. - ans = self.copy_abs() - else: - ans = self.copy_negate() - - return ans._fix(context) - - def __pos__(self, context=None): - """Returns a copy, unless it is a sNaN. - - Rounds the number (if more then precision digits) - """ - if self._is_special: - ans = self._check_nans(context=context) - if ans: - return ans - - if context is None: - context = getcontext() - - if not self and context.rounding != ROUND_FLOOR: - # + (-0) = 0, except in ROUND_FLOOR rounding mode. - ans = self.copy_abs() - else: - ans = Decimal(self) - - return ans._fix(context) - - def __abs__(self, round=True, context=None): - """Returns the absolute value of self. - - If the keyword argument 'round' is false, do not round. The - expression self.__abs__(round=False) is equivalent to - self.copy_abs(). - """ - if not round: - return self.copy_abs() - - if self._is_special: - ans = self._check_nans(context=context) - if ans: - return ans - - if self._sign: - ans = self.__neg__(context=context) - else: - ans = self.__pos__(context=context) - - return ans - - def __add__(self, other, context=None): - """Returns self + other. - - -INF + INF (or the reverse) cause InvalidOperation errors. - """ - other = _convert_other(other) - if other is NotImplemented: - return other - - if context is None: - context = getcontext() - - if self._is_special or other._is_special: - ans = self._check_nans(other, context) - if ans: - return ans - - if self._isinfinity(): - # If both INF, same sign => same as both, opposite => error. - if self._sign != other._sign and other._isinfinity(): - return context._raise_error(InvalidOperation, '-INF + INF') - return Decimal(self) - if other._isinfinity(): - return Decimal(other) # Can't both be infinity here - - exp = min(self._exp, other._exp) - negativezero = 0 - if context.rounding == ROUND_FLOOR and self._sign != other._sign: - # If the answer is 0, the sign should be negative, in this case. - negativezero = 1 - - if not self and not other: - sign = min(self._sign, other._sign) - if negativezero: - sign = 1 - ans = _dec_from_triple(sign, '0', exp) - ans = ans._fix(context) - return ans - if not self: - exp = max(exp, other._exp - context.prec-1) - ans = other._rescale(exp, context.rounding) - ans = ans._fix(context) - return ans - if not other: - exp = max(exp, self._exp - context.prec-1) - ans = self._rescale(exp, context.rounding) - ans = ans._fix(context) - return ans - - op1 = _WorkRep(self) - op2 = _WorkRep(other) - op1, op2 = _normalize(op1, op2, context.prec) - - result = _WorkRep() - if op1.sign != op2.sign: - # Equal and opposite - if op1.int == op2.int: - ans = _dec_from_triple(negativezero, '0', exp) - ans = ans._fix(context) - return ans - if op1.int < op2.int: - op1, op2 = op2, op1 - # OK, now abs(op1) > abs(op2) - if op1.sign == 1: - result.sign = 1 - op1.sign, op2.sign = op2.sign, op1.sign - else: - result.sign = 0 - # So we know the sign, and op1 > 0. - elif op1.sign == 1: - result.sign = 1 - op1.sign, op2.sign = (0, 0) - else: - result.sign = 0 - # Now, op1 > abs(op2) > 0 - - if op2.sign == 0: - result.int = op1.int + op2.int - else: - result.int = op1.int - op2.int - - result.exp = op1.exp - ans = Decimal(result) - ans = ans._fix(context) - return ans - - __radd__ = __add__ - - def __sub__(self, other, context=None): - """Return self - other""" - other = _convert_other(other) - if other is NotImplemented: - return other - - if self._is_special or other._is_special: - ans = self._check_nans(other, context=context) - if ans: - return ans - - # self - other is computed as self + other.copy_negate() - return self.__add__(other.copy_negate(), context=context) - - def __rsub__(self, other, context=None): - """Return other - self""" - other = _convert_other(other) - if other is NotImplemented: - return other - - return other.__sub__(self, context=context) - - def __mul__(self, other, context=None): - """Return self * other. - - (+-) INF * 0 (or its reverse) raise InvalidOperation. - """ - other = _convert_other(other) - if other is NotImplemented: - return other - - if context is None: - context = getcontext() - - resultsign = self._sign ^ other._sign - - if self._is_special or other._is_special: - ans = self._check_nans(other, context) - if ans: - return ans - - if self._isinfinity(): - if not other: - return context._raise_error(InvalidOperation, '(+-)INF * 0') - return _SignedInfinity[resultsign] - - if other._isinfinity(): - if not self: - return context._raise_error(InvalidOperation, '0 * (+-)INF') - return _SignedInfinity[resultsign] - - resultexp = self._exp + other._exp - - # Special case for multiplying by zero - if not self or not other: - ans = _dec_from_triple(resultsign, '0', resultexp) - # Fixing in case the exponent is out of bounds - ans = ans._fix(context) - return ans - - # Special case for multiplying by power of 10 - if self._int == '1': - ans = _dec_from_triple(resultsign, other._int, resultexp) - ans = ans._fix(context) - return ans - if other._int == '1': - ans = _dec_from_triple(resultsign, self._int, resultexp) - ans = ans._fix(context) - return ans - - op1 = _WorkRep(self) - op2 = _WorkRep(other) - - ans = _dec_from_triple(resultsign, str(op1.int * op2.int), resultexp) - ans = ans._fix(context) - - return ans - __rmul__ = __mul__ - - def __truediv__(self, other, context=None): - """Return self / other.""" - other = _convert_other(other) - if other is NotImplemented: - return NotImplemented - - if context is None: - context = getcontext() - - sign = self._sign ^ other._sign - - if self._is_special or other._is_special: - ans = self._check_nans(other, context) - if ans: - return ans - - if self._isinfinity() and other._isinfinity(): - return context._raise_error(InvalidOperation, '(+-)INF/(+-)INF') - - if self._isinfinity(): - return _SignedInfinity[sign] - - if other._isinfinity(): - context._raise_error(Clamped, 'Division by infinity') - return _dec_from_triple(sign, '0', context.Etiny()) - - # Special cases for zeroes - if not other: - if not self: - return context._raise_error(DivisionUndefined, '0 / 0') - return context._raise_error(DivisionByZero, 'x / 0', sign) - - if not self: - exp = self._exp - other._exp - coeff = 0 - else: - # OK, so neither = 0, INF or NaN - shift = len(other._int) - len(self._int) + context.prec + 1 - exp = self._exp - other._exp - shift - op1 = _WorkRep(self) - op2 = _WorkRep(other) - if shift >= 0: - coeff, remainder = divmod(op1.int * 10**shift, op2.int) - else: - coeff, remainder = divmod(op1.int, op2.int * 10**-shift) - if remainder: - # result is not exact; adjust to ensure correct rounding - if coeff % 5 == 0: - coeff += 1 - else: - # result is exact; get as close to ideal exponent as possible - ideal_exp = self._exp - other._exp - while exp < ideal_exp and coeff % 10 == 0: - coeff //= 10 - exp += 1 - - ans = _dec_from_triple(sign, str(coeff), exp) - return ans._fix(context) - - def _divide(self, other, context): - """Return (self // other, self % other), to context.prec precision. - - Assumes that neither self nor other is a NaN, that self is not - infinite and that other is nonzero. - """ - sign = self._sign ^ other._sign - if other._isinfinity(): - ideal_exp = self._exp - else: - ideal_exp = min(self._exp, other._exp) - - expdiff = self.adjusted() - other.adjusted() - if not self or other._isinfinity() or expdiff <= -2: - return (_dec_from_triple(sign, '0', 0), - self._rescale(ideal_exp, context.rounding)) - if expdiff <= context.prec: - op1 = _WorkRep(self) - op2 = _WorkRep(other) - if op1.exp >= op2.exp: - op1.int *= 10**(op1.exp - op2.exp) - else: - op2.int *= 10**(op2.exp - op1.exp) - q, r = divmod(op1.int, op2.int) - if q < 10**context.prec: - return (_dec_from_triple(sign, str(q), 0), - _dec_from_triple(self._sign, str(r), ideal_exp)) - - # Here the quotient is too large to be representable - ans = context._raise_error(DivisionImpossible, - 'quotient too large in //, % or divmod') - return ans, ans - - def __rtruediv__(self, other, context=None): - """Swaps self/other and returns __truediv__.""" - other = _convert_other(other) - if other is NotImplemented: - return other - return other.__truediv__(self, context=context) - - def __divmod__(self, other, context=None): - """ - Return (self // other, self % other) - """ - other = _convert_other(other) - if other is NotImplemented: - return other - - if context is None: - context = getcontext() - - ans = self._check_nans(other, context) - if ans: - return (ans, ans) - - sign = self._sign ^ other._sign - if self._isinfinity(): - if other._isinfinity(): - ans = context._raise_error(InvalidOperation, 'divmod(INF, INF)') - return ans, ans - else: - return (_SignedInfinity[sign], - context._raise_error(InvalidOperation, 'INF % x')) - - if not other: - if not self: - ans = context._raise_error(DivisionUndefined, 'divmod(0, 0)') - return ans, ans - else: - return (context._raise_error(DivisionByZero, 'x // 0', sign), - context._raise_error(InvalidOperation, 'x % 0')) - - quotient, remainder = self._divide(other, context) - remainder = remainder._fix(context) - return quotient, remainder - - def __rdivmod__(self, other, context=None): - """Swaps self/other and returns __divmod__.""" - other = _convert_other(other) - if other is NotImplemented: - return other - return other.__divmod__(self, context=context) - - def __mod__(self, other, context=None): - """ - self % other - """ - other = _convert_other(other) - if other is NotImplemented: - return other - - if context is None: - context = getcontext() - - ans = self._check_nans(other, context) - if ans: - return ans - - if self._isinfinity(): - return context._raise_error(InvalidOperation, 'INF % x') - elif not other: - if self: - return context._raise_error(InvalidOperation, 'x % 0') - else: - return context._raise_error(DivisionUndefined, '0 % 0') - - remainder = self._divide(other, context)[1] - remainder = remainder._fix(context) - return remainder - - def __rmod__(self, other, context=None): - """Swaps self/other and returns __mod__.""" - other = _convert_other(other) - if other is NotImplemented: - return other - return other.__mod__(self, context=context) - - def remainder_near(self, other, context=None): - """ - Remainder nearest to 0- abs(remainder-near) <= other/2 - """ - if context is None: - context = getcontext() - - other = _convert_other(other, raiseit=True) - - ans = self._check_nans(other, context) - if ans: - return ans - - # self == +/-infinity -> InvalidOperation - if self._isinfinity(): - return context._raise_error(InvalidOperation, - 'remainder_near(infinity, x)') - - # other == 0 -> either InvalidOperation or DivisionUndefined - if not other: - if self: - return context._raise_error(InvalidOperation, - 'remainder_near(x, 0)') - else: - return context._raise_error(DivisionUndefined, - 'remainder_near(0, 0)') - - # other = +/-infinity -> remainder = self - if other._isinfinity(): - ans = Decimal(self) - return ans._fix(context) - - # self = 0 -> remainder = self, with ideal exponent - ideal_exponent = min(self._exp, other._exp) - if not self: - ans = _dec_from_triple(self._sign, '0', ideal_exponent) - return ans._fix(context) - - # catch most cases of large or small quotient - expdiff = self.adjusted() - other.adjusted() - if expdiff >= context.prec + 1: - # expdiff >= prec+1 => abs(self/other) > 10**prec - return context._raise_error(DivisionImpossible) - if expdiff <= -2: - # expdiff <= -2 => abs(self/other) < 0.1 - ans = self._rescale(ideal_exponent, context.rounding) - return ans._fix(context) - - # adjust both arguments to have the same exponent, then divide - op1 = _WorkRep(self) - op2 = _WorkRep(other) - if op1.exp >= op2.exp: - op1.int *= 10**(op1.exp - op2.exp) - else: - op2.int *= 10**(op2.exp - op1.exp) - q, r = divmod(op1.int, op2.int) - # remainder is r*10**ideal_exponent; other is +/-op2.int * - # 10**ideal_exponent. Apply correction to ensure that - # abs(remainder) <= abs(other)/2 - if 2*r + (q&1) > op2.int: - r -= op2.int - q += 1 - - if q >= 10**context.prec: - return context._raise_error(DivisionImpossible) - - # result has same sign as self unless r is negative - sign = self._sign - if r < 0: - sign = 1-sign - r = -r - - ans = _dec_from_triple(sign, str(r), ideal_exponent) - return ans._fix(context) - - def __floordiv__(self, other, context=None): - """self // other""" - other = _convert_other(other) - if other is NotImplemented: - return other - - if context is None: - context = getcontext() - - ans = self._check_nans(other, context) - if ans: - return ans - - if self._isinfinity(): - if other._isinfinity(): - return context._raise_error(InvalidOperation, 'INF // INF') - else: - return _SignedInfinity[self._sign ^ other._sign] - - if not other: - if self: - return context._raise_error(DivisionByZero, 'x // 0', - self._sign ^ other._sign) - else: - return context._raise_error(DivisionUndefined, '0 // 0') - - return self._divide(other, context)[0] - - def __rfloordiv__(self, other, context=None): - """Swaps self/other and returns __floordiv__.""" - other = _convert_other(other) - if other is NotImplemented: - return other - return other.__floordiv__(self, context=context) - - def __float__(self): - """Float representation.""" - if self._isnan(): - if self.is_snan(): - raise ValueError("Cannot convert signaling NaN to float") - s = "-nan" if self._sign else "nan" - else: - s = str(self) - return float(s) - - def __int__(self): - """Converts self to an int, truncating if necessary.""" - if self._is_special: - if self._isnan(): - raise ValueError("Cannot convert NaN to integer") - elif self._isinfinity(): - raise OverflowError("Cannot convert infinity to integer") - s = (-1)**self._sign - if self._exp >= 0: - return s*int(self._int)*10**self._exp - else: - return s*int(self._int[:self._exp] or '0') - - __trunc__ = __int__ - - def real(self): - return self - real = property(real) - - def imag(self): - return Decimal(0) - imag = property(imag) - - def conjugate(self): - return self - - def __complex__(self): - return complex(float(self)) - - def _fix_nan(self, context): - """Decapitate the payload of a NaN to fit the context""" - payload = self._int - - # maximum length of payload is precision if clamp=0, - # precision-1 if clamp=1. - max_payload_len = context.prec - context.clamp - if len(payload) > max_payload_len: - payload = payload[len(payload)-max_payload_len:].lstrip('0') - return _dec_from_triple(self._sign, payload, self._exp, True) - return Decimal(self) - - def _fix(self, context): - """Round if it is necessary to keep self within prec precision. - - Rounds and fixes the exponent. Does not raise on a sNaN. - - Arguments: - self - Decimal instance - context - context used. - """ - - if self._is_special: - if self._isnan(): - # decapitate payload if necessary - return self._fix_nan(context) - else: - # self is +/-Infinity; return unaltered - return Decimal(self) - - # if self is zero then exponent should be between Etiny and - # Emax if clamp==0, and between Etiny and Etop if clamp==1. - Etiny = context.Etiny() - Etop = context.Etop() - if not self: - exp_max = [context.Emax, Etop][context.clamp] - new_exp = min(max(self._exp, Etiny), exp_max) - if new_exp != self._exp: - context._raise_error(Clamped) - return _dec_from_triple(self._sign, '0', new_exp) - else: - return Decimal(self) - - # exp_min is the smallest allowable exponent of the result, - # equal to max(self.adjusted()-context.prec+1, Etiny) - exp_min = len(self._int) + self._exp - context.prec - if exp_min > Etop: - # overflow: exp_min > Etop iff self.adjusted() > Emax - ans = context._raise_error(Overflow, 'above Emax', self._sign) - context._raise_error(Inexact) - context._raise_error(Rounded) - return ans - - self_is_subnormal = exp_min < Etiny - if self_is_subnormal: - exp_min = Etiny - - # round if self has too many digits - if self._exp < exp_min: - digits = len(self._int) + self._exp - exp_min - if digits < 0: - self = _dec_from_triple(self._sign, '1', exp_min-1) - digits = 0 - rounding_method = self._pick_rounding_function[context.rounding] - changed = rounding_method(self, digits) - coeff = self._int[:digits] or '0' - if changed > 0: - coeff = str(int(coeff)+1) - if len(coeff) > context.prec: - coeff = coeff[:-1] - exp_min += 1 - - # check whether the rounding pushed the exponent out of range - if exp_min > Etop: - ans = context._raise_error(Overflow, 'above Emax', self._sign) - else: - ans = _dec_from_triple(self._sign, coeff, exp_min) - - # raise the appropriate signals, taking care to respect - # the precedence described in the specification - if changed and self_is_subnormal: - context._raise_error(Underflow) - if self_is_subnormal: - context._raise_error(Subnormal) - if changed: - context._raise_error(Inexact) - context._raise_error(Rounded) - if not ans: - # raise Clamped on underflow to 0 - context._raise_error(Clamped) - return ans - - if self_is_subnormal: - context._raise_error(Subnormal) - - # fold down if clamp == 1 and self has too few digits - if context.clamp == 1 and self._exp > Etop: - context._raise_error(Clamped) - self_padded = self._int + '0'*(self._exp - Etop) - return _dec_from_triple(self._sign, self_padded, Etop) - - # here self was representable to begin with; return unchanged - return Decimal(self) - - # for each of the rounding functions below: - # self is a finite, nonzero Decimal - # prec is an integer satisfying 0 <= prec < len(self._int) - # - # each function returns either -1, 0, or 1, as follows: - # 1 indicates that self should be rounded up (away from zero) - # 0 indicates that self should be truncated, and that all the - # digits to be truncated are zeros (so the value is unchanged) - # -1 indicates that there are nonzero digits to be truncated - - def _round_down(self, prec): - """Also known as round-towards-0, truncate.""" - if _all_zeros(self._int, prec): - return 0 - else: - return -1 - - def _round_up(self, prec): - """Rounds away from 0.""" - return -self._round_down(prec) - - def _round_half_up(self, prec): - """Rounds 5 up (away from 0)""" - if self._int[prec] in '56789': - return 1 - elif _all_zeros(self._int, prec): - return 0 - else: - return -1 - - def _round_half_down(self, prec): - """Round 5 down""" - if _exact_half(self._int, prec): - return -1 - else: - return self._round_half_up(prec) - - def _round_half_even(self, prec): - """Round 5 to even, rest to nearest.""" - if _exact_half(self._int, prec) and \ - (prec == 0 or self._int[prec-1] in '02468'): - return -1 - else: - return self._round_half_up(prec) - - def _round_ceiling(self, prec): - """Rounds up (not away from 0 if negative.)""" - if self._sign: - return self._round_down(prec) - else: - return -self._round_down(prec) - - def _round_floor(self, prec): - """Rounds down (not towards 0 if negative)""" - if not self._sign: - return self._round_down(prec) - else: - return -self._round_down(prec) - - def _round_05up(self, prec): - """Round down unless digit prec-1 is 0 or 5.""" - if prec and self._int[prec-1] not in '05': - return self._round_down(prec) - else: - return -self._round_down(prec) - - _pick_rounding_function = dict( - ROUND_DOWN = _round_down, - ROUND_UP = _round_up, - ROUND_HALF_UP = _round_half_up, - ROUND_HALF_DOWN = _round_half_down, - ROUND_HALF_EVEN = _round_half_even, - ROUND_CEILING = _round_ceiling, - ROUND_FLOOR = _round_floor, - ROUND_05UP = _round_05up, - ) - - def __round__(self, n=None): - """Round self to the nearest integer, or to a given precision. - - If only one argument is supplied, round a finite Decimal - instance self to the nearest integer. If self is infinite or - a NaN then a Python exception is raised. If self is finite - and lies exactly halfway between two integers then it is - rounded to the integer with even last digit. - - >>> round(Decimal('123.456')) - 123 - >>> round(Decimal('-456.789')) - -457 - >>> round(Decimal('-3.0')) - -3 - >>> round(Decimal('2.5')) - 2 - >>> round(Decimal('3.5')) - 4 - >>> round(Decimal('Inf')) - Traceback (most recent call last): - ... - OverflowError: cannot round an infinity - >>> round(Decimal('NaN')) - Traceback (most recent call last): - ... - ValueError: cannot round a NaN - - If a second argument n is supplied, self is rounded to n - decimal places using the rounding mode for the current - context. - - For an integer n, round(self, -n) is exactly equivalent to - self.quantize(Decimal('1En')). - - >>> round(Decimal('123.456'), 0) - Decimal('123') - >>> round(Decimal('123.456'), 2) - Decimal('123.46') - >>> round(Decimal('123.456'), -2) - Decimal('1E+2') - >>> round(Decimal('-Infinity'), 37) - Decimal('NaN') - >>> round(Decimal('sNaN123'), 0) - Decimal('NaN123') - - """ - if n is not None: - # two-argument form: use the equivalent quantize call - if not isinstance(n, int): - raise TypeError('Second argument to round should be integral') - exp = _dec_from_triple(0, '1', -n) - return self.quantize(exp) - - # one-argument form - if self._is_special: - if self.is_nan(): - raise ValueError("cannot round a NaN") - else: - raise OverflowError("cannot round an infinity") - return int(self._rescale(0, ROUND_HALF_EVEN)) - - def __floor__(self): - """Return the floor of self, as an integer. - - For a finite Decimal instance self, return the greatest - integer n such that n <= self. If self is infinite or a NaN - then a Python exception is raised. - - """ - if self._is_special: - if self.is_nan(): - raise ValueError("cannot round a NaN") - else: - raise OverflowError("cannot round an infinity") - return int(self._rescale(0, ROUND_FLOOR)) - - def __ceil__(self): - """Return the ceiling of self, as an integer. - - For a finite Decimal instance self, return the least integer n - such that n >= self. If self is infinite or a NaN then a - Python exception is raised. - - """ - if self._is_special: - if self.is_nan(): - raise ValueError("cannot round a NaN") - else: - raise OverflowError("cannot round an infinity") - return int(self._rescale(0, ROUND_CEILING)) - - def fma(self, other, third, context=None): - """Fused multiply-add. - - Returns self*other+third with no rounding of the intermediate - product self*other. - - self and other are multiplied together, with no rounding of - the result. The third operand is then added to the result, - and a single final rounding is performed. - """ - - other = _convert_other(other, raiseit=True) - third = _convert_other(third, raiseit=True) - - # compute product; raise InvalidOperation if either operand is - # a signaling NaN or if the product is zero times infinity. - if self._is_special or other._is_special: - if context is None: - context = getcontext() - if self._exp == 'N': - return context._raise_error(InvalidOperation, 'sNaN', self) - if other._exp == 'N': - return context._raise_error(InvalidOperation, 'sNaN', other) - if self._exp == 'n': - product = self - elif other._exp == 'n': - product = other - elif self._exp == 'F': - if not other: - return context._raise_error(InvalidOperation, - 'INF * 0 in fma') - product = _SignedInfinity[self._sign ^ other._sign] - elif other._exp == 'F': - if not self: - return context._raise_error(InvalidOperation, - '0 * INF in fma') - product = _SignedInfinity[self._sign ^ other._sign] - else: - product = _dec_from_triple(self._sign ^ other._sign, - str(int(self._int) * int(other._int)), - self._exp + other._exp) - - return product.__add__(third, context) - - def _power_modulo(self, other, modulo, context=None): - """Three argument version of __pow__""" - - other = _convert_other(other) - if other is NotImplemented: - return other - modulo = _convert_other(modulo) - if modulo is NotImplemented: - return modulo - - if context is None: - context = getcontext() - - # deal with NaNs: if there are any sNaNs then first one wins, - # (i.e. behaviour for NaNs is identical to that of fma) - self_is_nan = self._isnan() - other_is_nan = other._isnan() - modulo_is_nan = modulo._isnan() - if self_is_nan or other_is_nan or modulo_is_nan: - if self_is_nan == 2: - return context._raise_error(InvalidOperation, 'sNaN', - self) - if other_is_nan == 2: - return context._raise_error(InvalidOperation, 'sNaN', - other) - if modulo_is_nan == 2: - return context._raise_error(InvalidOperation, 'sNaN', - modulo) - if self_is_nan: - return self._fix_nan(context) - if other_is_nan: - return other._fix_nan(context) - return modulo._fix_nan(context) - - # check inputs: we apply same restrictions as Python's pow() - if not (self._isinteger() and - other._isinteger() and - modulo._isinteger()): - return context._raise_error(InvalidOperation, - 'pow() 3rd argument not allowed ' - 'unless all arguments are integers') - if other < 0: - return context._raise_error(InvalidOperation, - 'pow() 2nd argument cannot be ' - 'negative when 3rd argument specified') - if not modulo: - return context._raise_error(InvalidOperation, - 'pow() 3rd argument cannot be 0') - - # additional restriction for decimal: the modulus must be less - # than 10**prec in absolute value - if modulo.adjusted() >= context.prec: - return context._raise_error(InvalidOperation, - 'insufficient precision: pow() 3rd ' - 'argument must not have more than ' - 'precision digits') - - # define 0**0 == NaN, for consistency with two-argument pow - # (even though it hurts!) - if not other and not self: - return context._raise_error(InvalidOperation, - 'at least one of pow() 1st argument ' - 'and 2nd argument must be nonzero ;' - '0**0 is not defined') - - # compute sign of result - if other._iseven(): - sign = 0 - else: - sign = self._sign - - # convert modulo to a Python integer, and self and other to - # Decimal integers (i.e. force their exponents to be >= 0) - modulo = abs(int(modulo)) - base = _WorkRep(self.to_integral_value()) - exponent = _WorkRep(other.to_integral_value()) - - # compute result using integer pow() - base = (base.int % modulo * pow(10, base.exp, modulo)) % modulo - for i in range(exponent.exp): - base = pow(base, 10, modulo) - base = pow(base, exponent.int, modulo) - - return _dec_from_triple(sign, str(base), 0) - - def _power_exact(self, other, p): - """Attempt to compute self**other exactly. - - Given Decimals self and other and an integer p, attempt to - compute an exact result for the power self**other, with p - digits of precision. Return None if self**other is not - exactly representable in p digits. - - Assumes that elimination of special cases has already been - performed: self and other must both be nonspecial; self must - be positive and not numerically equal to 1; other must be - nonzero. For efficiency, other._exp should not be too large, - so that 10**abs(other._exp) is a feasible calculation.""" - - # In the comments below, we write x for the value of self and y for the - # value of other. Write x = xc*10**xe and abs(y) = yc*10**ye, with xc - # and yc positive integers not divisible by 10. - - # The main purpose of this method is to identify the *failure* - # of x**y to be exactly representable with as little effort as - # possible. So we look for cheap and easy tests that - # eliminate the possibility of x**y being exact. Only if all - # these tests are passed do we go on to actually compute x**y. - - # Here's the main idea. Express y as a rational number m/n, with m and - # n relatively prime and n>0. Then for x**y to be exactly - # representable (at *any* precision), xc must be the nth power of a - # positive integer and xe must be divisible by n. If y is negative - # then additionally xc must be a power of either 2 or 5, hence a power - # of 2**n or 5**n. - # - # There's a limit to how small |y| can be: if y=m/n as above - # then: - # - # (1) if xc != 1 then for the result to be representable we - # need xc**(1/n) >= 2, and hence also xc**|y| >= 2. So - # if |y| <= 1/nbits(xc) then xc < 2**nbits(xc) <= - # 2**(1/|y|), hence xc**|y| < 2 and the result is not - # representable. - # - # (2) if xe != 0, |xe|*(1/n) >= 1, so |xe|*|y| >= 1. Hence if - # |y| < 1/|xe| then the result is not representable. - # - # Note that since x is not equal to 1, at least one of (1) and - # (2) must apply. Now |y| < 1/nbits(xc) iff |yc|*nbits(xc) < - # 10**-ye iff len(str(|yc|*nbits(xc)) <= -ye. - # - # There's also a limit to how large y can be, at least if it's - # positive: the normalized result will have coefficient xc**y, - # so if it's representable then xc**y < 10**p, and y < - # p/log10(xc). Hence if y*log10(xc) >= p then the result is - # not exactly representable. - - # if len(str(abs(yc*xe)) <= -ye then abs(yc*xe) < 10**-ye, - # so |y| < 1/xe and the result is not representable. - # Similarly, len(str(abs(yc)*xc_bits)) <= -ye implies |y| - # < 1/nbits(xc). - - x = _WorkRep(self) - xc, xe = x.int, x.exp - while xc % 10 == 0: - xc //= 10 - xe += 1 - - y = _WorkRep(other) - yc, ye = y.int, y.exp - while yc % 10 == 0: - yc //= 10 - ye += 1 - - # case where xc == 1: result is 10**(xe*y), with xe*y - # required to be an integer - if xc == 1: - xe *= yc - # result is now 10**(xe * 10**ye); xe * 10**ye must be integral - while xe % 10 == 0: - xe //= 10 - ye += 1 - if ye < 0: - return None - exponent = xe * 10**ye - if y.sign == 1: - exponent = -exponent - # if other is a nonnegative integer, use ideal exponent - if other._isinteger() and other._sign == 0: - ideal_exponent = self._exp*int(other) - zeros = min(exponent-ideal_exponent, p-1) - else: - zeros = 0 - return _dec_from_triple(0, '1' + '0'*zeros, exponent-zeros) - - # case where y is negative: xc must be either a power - # of 2 or a power of 5. - if y.sign == 1: - last_digit = xc % 10 - if last_digit in (2,4,6,8): - # quick test for power of 2 - if xc & -xc != xc: - return None - # now xc is a power of 2; e is its exponent - e = _nbits(xc)-1 - - # We now have: - # - # x = 2**e * 10**xe, e > 0, and y < 0. - # - # The exact result is: - # - # x**y = 5**(-e*y) * 10**(e*y + xe*y) - # - # provided that both e*y and xe*y are integers. Note that if - # 5**(-e*y) >= 10**p, then the result can't be expressed - # exactly with p digits of precision. - # - # Using the above, we can guard against large values of ye. - # 93/65 is an upper bound for log(10)/log(5), so if - # - # ye >= len(str(93*p//65)) - # - # then - # - # -e*y >= -y >= 10**ye > 93*p/65 > p*log(10)/log(5), - # - # so 5**(-e*y) >= 10**p, and the coefficient of the result - # can't be expressed in p digits. - - # emax >= largest e such that 5**e < 10**p. - emax = p*93//65 - if ye >= len(str(emax)): - return None - - # Find -e*y and -xe*y; both must be integers - e = _decimal_lshift_exact(e * yc, ye) - xe = _decimal_lshift_exact(xe * yc, ye) - if e is None or xe is None: - return None - - if e > emax: - return None - xc = 5**e - - elif last_digit == 5: - # e >= log_5(xc) if xc is a power of 5; we have - # equality all the way up to xc=5**2658 - e = _nbits(xc)*28//65 - xc, remainder = divmod(5**e, xc) - if remainder: - return None - while xc % 5 == 0: - xc //= 5 - e -= 1 - - # Guard against large values of ye, using the same logic as in - # the 'xc is a power of 2' branch. 10/3 is an upper bound for - # log(10)/log(2). - emax = p*10//3 - if ye >= len(str(emax)): - return None - - e = _decimal_lshift_exact(e * yc, ye) - xe = _decimal_lshift_exact(xe * yc, ye) - if e is None or xe is None: - return None - - if e > emax: - return None - xc = 2**e - else: - return None - - if xc >= 10**p: - return None - xe = -e-xe - return _dec_from_triple(0, str(xc), xe) - - # now y is positive; find m and n such that y = m/n - if ye >= 0: - m, n = yc*10**ye, 1 - else: - if xe != 0 and len(str(abs(yc*xe))) <= -ye: - return None - xc_bits = _nbits(xc) - if xc != 1 and len(str(abs(yc)*xc_bits)) <= -ye: - return None - m, n = yc, 10**(-ye) - while m % 2 == n % 2 == 0: - m //= 2 - n //= 2 - while m % 5 == n % 5 == 0: - m //= 5 - n //= 5 - - # compute nth root of xc*10**xe - if n > 1: - # if 1 < xc < 2**n then xc isn't an nth power - if xc != 1 and xc_bits <= n: - return None - - xe, rem = divmod(xe, n) - if rem != 0: - return None - - # compute nth root of xc using Newton's method - a = 1 << -(-_nbits(xc)//n) # initial estimate - while True: - q, r = divmod(xc, a**(n-1)) - if a <= q: - break - else: - a = (a*(n-1) + q)//n - if not (a == q and r == 0): - return None - xc = a - - # now xc*10**xe is the nth root of the original xc*10**xe - # compute mth power of xc*10**xe - - # if m > p*100//_log10_lb(xc) then m > p/log10(xc), hence xc**m > - # 10**p and the result is not representable. - if xc > 1 and m > p*100//_log10_lb(xc): - return None - xc = xc**m - xe *= m - if xc > 10**p: - return None - - # by this point the result *is* exactly representable - # adjust the exponent to get as close as possible to the ideal - # exponent, if necessary - str_xc = str(xc) - if other._isinteger() and other._sign == 0: - ideal_exponent = self._exp*int(other) - zeros = min(xe-ideal_exponent, p-len(str_xc)) - else: - zeros = 0 - return _dec_from_triple(0, str_xc+'0'*zeros, xe-zeros) - - def __pow__(self, other, modulo=None, context=None): - """Return self ** other [ % modulo]. - - With two arguments, compute self**other. - - With three arguments, compute (self**other) % modulo. For the - three argument form, the following restrictions on the - arguments hold: - - - all three arguments must be integral - - other must be nonnegative - - either self or other (or both) must be nonzero - - modulo must be nonzero and must have at most p digits, - where p is the context precision. - - If any of these restrictions is violated the InvalidOperation - flag is raised. - - The result of pow(self, other, modulo) is identical to the - result that would be obtained by computing (self**other) % - modulo with unbounded precision, but is computed more - efficiently. It is always exact. - """ - - if modulo is not None: - return self._power_modulo(other, modulo, context) - - other = _convert_other(other) - if other is NotImplemented: - return other - - if context is None: - context = getcontext() - - # either argument is a NaN => result is NaN - ans = self._check_nans(other, context) - if ans: - return ans - - # 0**0 = NaN (!), x**0 = 1 for nonzero x (including +/-Infinity) - if not other: - if not self: - return context._raise_error(InvalidOperation, '0 ** 0') - else: - return _One - - # result has sign 1 iff self._sign is 1 and other is an odd integer - result_sign = 0 - if self._sign == 1: - if other._isinteger(): - if not other._iseven(): - result_sign = 1 - else: - # -ve**noninteger = NaN - # (-0)**noninteger = 0**noninteger - if self: - return context._raise_error(InvalidOperation, - 'x ** y with x negative and y not an integer') - # negate self, without doing any unwanted rounding - self = self.copy_negate() - - # 0**(+ve or Inf)= 0; 0**(-ve or -Inf) = Infinity - if not self: - if other._sign == 0: - return _dec_from_triple(result_sign, '0', 0) - else: - return _SignedInfinity[result_sign] - - # Inf**(+ve or Inf) = Inf; Inf**(-ve or -Inf) = 0 - if self._isinfinity(): - if other._sign == 0: - return _SignedInfinity[result_sign] - else: - return _dec_from_triple(result_sign, '0', 0) - - # 1**other = 1, but the choice of exponent and the flags - # depend on the exponent of self, and on whether other is a - # positive integer, a negative integer, or neither - if self == _One: - if other._isinteger(): - # exp = max(self._exp*max(int(other), 0), - # 1-context.prec) but evaluating int(other) directly - # is dangerous until we know other is small (other - # could be 1e999999999) - if other._sign == 1: - multiplier = 0 - elif other > context.prec: - multiplier = context.prec - else: - multiplier = int(other) - - exp = self._exp * multiplier - if exp < 1-context.prec: - exp = 1-context.prec - context._raise_error(Rounded) - else: - context._raise_error(Inexact) - context._raise_error(Rounded) - exp = 1-context.prec - - return _dec_from_triple(result_sign, '1'+'0'*-exp, exp) - - # compute adjusted exponent of self - self_adj = self.adjusted() - - # self ** infinity is infinity if self > 1, 0 if self < 1 - # self ** -infinity is infinity if self < 1, 0 if self > 1 - if other._isinfinity(): - if (other._sign == 0) == (self_adj < 0): - return _dec_from_triple(result_sign, '0', 0) - else: - return _SignedInfinity[result_sign] - - # from here on, the result always goes through the call - # to _fix at the end of this function. - ans = None - exact = False - - # crude test to catch cases of extreme overflow/underflow. If - # log10(self)*other >= 10**bound and bound >= len(str(Emax)) - # then 10**bound >= 10**len(str(Emax)) >= Emax+1 and hence - # self**other >= 10**(Emax+1), so overflow occurs. The test - # for underflow is similar. - bound = self._log10_exp_bound() + other.adjusted() - if (self_adj >= 0) == (other._sign == 0): - # self > 1 and other +ve, or self < 1 and other -ve - # possibility of overflow - if bound >= len(str(context.Emax)): - ans = _dec_from_triple(result_sign, '1', context.Emax+1) - else: - # self > 1 and other -ve, or self < 1 and other +ve - # possibility of underflow to 0 - Etiny = context.Etiny() - if bound >= len(str(-Etiny)): - ans = _dec_from_triple(result_sign, '1', Etiny-1) - - # try for an exact result with precision +1 - if ans is None: - ans = self._power_exact(other, context.prec + 1) - if ans is not None: - if result_sign == 1: - ans = _dec_from_triple(1, ans._int, ans._exp) - exact = True - - # usual case: inexact result, x**y computed directly as exp(y*log(x)) - if ans is None: - p = context.prec - x = _WorkRep(self) - xc, xe = x.int, x.exp - y = _WorkRep(other) - yc, ye = y.int, y.exp - if y.sign == 1: - yc = -yc - - # compute correctly rounded result: start with precision +3, - # then increase precision until result is unambiguously roundable - extra = 3 - while True: - coeff, exp = _dpower(xc, xe, yc, ye, p+extra) - if coeff % (5*10**(len(str(coeff))-p-1)): - break - extra += 3 - - ans = _dec_from_triple(result_sign, str(coeff), exp) - - # unlike exp, ln and log10, the power function respects the - # rounding mode; no need to switch to ROUND_HALF_EVEN here - - # There's a difficulty here when 'other' is not an integer and - # the result is exact. In this case, the specification - # requires that the Inexact flag be raised (in spite of - # exactness), but since the result is exact _fix won't do this - # for us. (Correspondingly, the Underflow signal should also - # be raised for subnormal results.) We can't directly raise - # these signals either before or after calling _fix, since - # that would violate the precedence for signals. So we wrap - # the ._fix call in a temporary context, and reraise - # afterwards. - if exact and not other._isinteger(): - # pad with zeros up to length context.prec+1 if necessary; this - # ensures that the Rounded signal will be raised. - if len(ans._int) <= context.prec: - expdiff = context.prec + 1 - len(ans._int) - ans = _dec_from_triple(ans._sign, ans._int+'0'*expdiff, - ans._exp-expdiff) - - # create a copy of the current context, with cleared flags/traps - newcontext = context.copy() - newcontext.clear_flags() - for exception in _signals: - newcontext.traps[exception] = 0 - - # round in the new context - ans = ans._fix(newcontext) - - # raise Inexact, and if necessary, Underflow - newcontext._raise_error(Inexact) - if newcontext.flags[Subnormal]: - newcontext._raise_error(Underflow) - - # propagate signals to the original context; _fix could - # have raised any of Overflow, Underflow, Subnormal, - # Inexact, Rounded, Clamped. Overflow needs the correct - # arguments. Note that the order of the exceptions is - # important here. - if newcontext.flags[Overflow]: - context._raise_error(Overflow, 'above Emax', ans._sign) - for exception in Underflow, Subnormal, Inexact, Rounded, Clamped: - if newcontext.flags[exception]: - context._raise_error(exception) - - else: - ans = ans._fix(context) - - return ans - - def __rpow__(self, other, context=None): - """Swaps self/other and returns __pow__.""" - other = _convert_other(other) - if other is NotImplemented: - return other - return other.__pow__(self, context=context) - - def normalize(self, context=None): - """Normalize- strip trailing 0s, change anything equal to 0 to 0e0""" - - if context is None: - context = getcontext() - - if self._is_special: - ans = self._check_nans(context=context) - if ans: - return ans - - dup = self._fix(context) - if dup._isinfinity(): - return dup - - if not dup: - return _dec_from_triple(dup._sign, '0', 0) - exp_max = [context.Emax, context.Etop()][context.clamp] - end = len(dup._int) - exp = dup._exp - while dup._int[end-1] == '0' and exp < exp_max: - exp += 1 - end -= 1 - return _dec_from_triple(dup._sign, dup._int[:end], exp) - - def quantize(self, exp, rounding=None, context=None, watchexp=True): - """Quantize self so its exponent is the same as that of exp. - - Similar to self._rescale(exp._exp) but with error checking. - """ - exp = _convert_other(exp, raiseit=True) - - if context is None: - context = getcontext() - if rounding is None: - rounding = context.rounding - - if self._is_special or exp._is_special: - ans = self._check_nans(exp, context) - if ans: - return ans - - if exp._isinfinity() or self._isinfinity(): - if exp._isinfinity() and self._isinfinity(): - return Decimal(self) # if both are inf, it is OK - return context._raise_error(InvalidOperation, - 'quantize with one INF') - - # if we're not watching exponents, do a simple rescale - if not watchexp: - ans = self._rescale(exp._exp, rounding) - # raise Inexact and Rounded where appropriate - if ans._exp > self._exp: - context._raise_error(Rounded) - if ans != self: - context._raise_error(Inexact) - return ans - - # exp._exp should be between Etiny and Emax - if not (context.Etiny() <= exp._exp <= context.Emax): - return context._raise_error(InvalidOperation, - 'target exponent out of bounds in quantize') - - if not self: - ans = _dec_from_triple(self._sign, '0', exp._exp) - return ans._fix(context) - - self_adjusted = self.adjusted() - if self_adjusted > context.Emax: - return context._raise_error(InvalidOperation, - 'exponent of quantize result too large for current context') - if self_adjusted - exp._exp + 1 > context.prec: - return context._raise_error(InvalidOperation, - 'quantize result has too many digits for current context') - - ans = self._rescale(exp._exp, rounding) - if ans.adjusted() > context.Emax: - return context._raise_error(InvalidOperation, - 'exponent of quantize result too large for current context') - if len(ans._int) > context.prec: - return context._raise_error(InvalidOperation, - 'quantize result has too many digits for current context') - - # raise appropriate flags - if ans and ans.adjusted() < context.Emin: - context._raise_error(Subnormal) - if ans._exp > self._exp: - if ans != self: - context._raise_error(Inexact) - context._raise_error(Rounded) - - # call to fix takes care of any necessary folddown, and - # signals Clamped if necessary - ans = ans._fix(context) - return ans - - def same_quantum(self, other, context=None): - """Return True if self and other have the same exponent; otherwise - return False. - - If either operand is a special value, the following rules are used: - * return True if both operands are infinities - * return True if both operands are NaNs - * otherwise, return False. - """ - other = _convert_other(other, raiseit=True) - if self._is_special or other._is_special: - return (self.is_nan() and other.is_nan() or - self.is_infinite() and other.is_infinite()) - return self._exp == other._exp - - def _rescale(self, exp, rounding): - """Rescale self so that the exponent is exp, either by padding with zeros - or by truncating digits, using the given rounding mode. - - Specials are returned without change. This operation is - quiet: it raises no flags, and uses no information from the - context. - - exp = exp to scale to (an integer) - rounding = rounding mode - """ - if self._is_special: - return Decimal(self) - if not self: - return _dec_from_triple(self._sign, '0', exp) - - if self._exp >= exp: - # pad answer with zeros if necessary - return _dec_from_triple(self._sign, - self._int + '0'*(self._exp - exp), exp) - - # too many digits; round and lose data. If self.adjusted() < - # exp-1, replace self by 10**(exp-1) before rounding - digits = len(self._int) + self._exp - exp - if digits < 0: - self = _dec_from_triple(self._sign, '1', exp-1) - digits = 0 - this_function = self._pick_rounding_function[rounding] - changed = this_function(self, digits) - coeff = self._int[:digits] or '0' - if changed == 1: - coeff = str(int(coeff)+1) - return _dec_from_triple(self._sign, coeff, exp) - - def _round(self, places, rounding): - """Round a nonzero, nonspecial Decimal to a fixed number of - significant figures, using the given rounding mode. - - Infinities, NaNs and zeros are returned unaltered. - - This operation is quiet: it raises no flags, and uses no - information from the context. - - """ - if places <= 0: - raise ValueError("argument should be at least 1 in _round") - if self._is_special or not self: - return Decimal(self) - ans = self._rescale(self.adjusted()+1-places, rounding) - # it can happen that the rescale alters the adjusted exponent; - # for example when rounding 99.97 to 3 significant figures. - # When this happens we end up with an extra 0 at the end of - # the number; a second rescale fixes this. - if ans.adjusted() != self.adjusted(): - ans = ans._rescale(ans.adjusted()+1-places, rounding) - return ans - - def to_integral_exact(self, rounding=None, context=None): - """Rounds to a nearby integer. - - If no rounding mode is specified, take the rounding mode from - the context. This method raises the Rounded and Inexact flags - when appropriate. - - See also: to_integral_value, which does exactly the same as - this method except that it doesn't raise Inexact or Rounded. - """ - if self._is_special: - ans = self._check_nans(context=context) - if ans: - return ans - return Decimal(self) - if self._exp >= 0: - return Decimal(self) - if not self: - return _dec_from_triple(self._sign, '0', 0) - if context is None: - context = getcontext() - if rounding is None: - rounding = context.rounding - ans = self._rescale(0, rounding) - if ans != self: - context._raise_error(Inexact) - context._raise_error(Rounded) - return ans - - def to_integral_value(self, rounding=None, context=None): - """Rounds to the nearest integer, without raising inexact, rounded.""" - if context is None: - context = getcontext() - if rounding is None: - rounding = context.rounding - if self._is_special: - ans = self._check_nans(context=context) - if ans: - return ans - return Decimal(self) - if self._exp >= 0: - return Decimal(self) - else: - return self._rescale(0, rounding) - - # the method name changed, but we provide also the old one, for compatibility - to_integral = to_integral_value - - def sqrt(self, context=None): - """Return the square root of self.""" - if context is None: - context = getcontext() - - if self._is_special: - ans = self._check_nans(context=context) - if ans: - return ans - - if self._isinfinity() and self._sign == 0: - return Decimal(self) - - if not self: - # exponent = self._exp // 2. sqrt(-0) = -0 - ans = _dec_from_triple(self._sign, '0', self._exp // 2) - return ans._fix(context) - - if self._sign == 1: - return context._raise_error(InvalidOperation, 'sqrt(-x), x > 0') - - # At this point self represents a positive number. Let p be - # the desired precision and express self in the form c*100**e - # with c a positive real number and e an integer, c and e - # being chosen so that 100**(p-1) <= c < 100**p. Then the - # (exact) square root of self is sqrt(c)*10**e, and 10**(p-1) - # <= sqrt(c) < 10**p, so the closest representable Decimal at - # precision p is n*10**e where n = round_half_even(sqrt(c)), - # the closest integer to sqrt(c) with the even integer chosen - # in the case of a tie. - # - # To ensure correct rounding in all cases, we use the - # following trick: we compute the square root to an extra - # place (precision p+1 instead of precision p), rounding down. - # Then, if the result is inexact and its last digit is 0 or 5, - # we increase the last digit to 1 or 6 respectively; if it's - # exact we leave the last digit alone. Now the final round to - # p places (or fewer in the case of underflow) will round - # correctly and raise the appropriate flags. - - # use an extra digit of precision - prec = context.prec+1 - - # write argument in the form c*100**e where e = self._exp//2 - # is the 'ideal' exponent, to be used if the square root is - # exactly representable. l is the number of 'digits' of c in - # base 100, so that 100**(l-1) <= c < 100**l. - op = _WorkRep(self) - e = op.exp >> 1 - if op.exp & 1: - c = op.int * 10 - l = (len(self._int) >> 1) + 1 - else: - c = op.int - l = len(self._int)+1 >> 1 - - # rescale so that c has exactly prec base 100 'digits' - shift = prec-l - if shift >= 0: - c *= 100**shift - exact = True - else: - c, remainder = divmod(c, 100**-shift) - exact = not remainder - e -= shift - - # find n = floor(sqrt(c)) using Newton's method - n = 10**prec - while True: - q = c//n - if n <= q: - break - else: - n = n + q >> 1 - exact = exact and n*n == c - - if exact: - # result is exact; rescale to use ideal exponent e - if shift >= 0: - # assert n % 10**shift == 0 - n //= 10**shift - else: - n *= 10**-shift - e += shift - else: - # result is not exact; fix last digit as described above - if n % 5 == 0: - n += 1 - - ans = _dec_from_triple(0, str(n), e) - - # round, and fit to current context - context = context._shallow_copy() - rounding = context._set_rounding(ROUND_HALF_EVEN) - ans = ans._fix(context) - context.rounding = rounding - - return ans - - def max(self, other, context=None): - """Returns the larger value. - - Like max(self, other) except if one is not a number, returns - NaN (and signals if one is sNaN). Also rounds. - """ - other = _convert_other(other, raiseit=True) - - if context is None: - context = getcontext() - - if self._is_special or other._is_special: - # If one operand is a quiet NaN and the other is number, then the - # number is always returned - sn = self._isnan() - on = other._isnan() - if sn or on: - if on == 1 and sn == 0: - return self._fix(context) - if sn == 1 and on == 0: - return other._fix(context) - return self._check_nans(other, context) - - c = self._cmp(other) - if c == 0: - # If both operands are finite and equal in numerical value - # then an ordering is applied: - # - # If the signs differ then max returns the operand with the - # positive sign and min returns the operand with the negative sign - # - # If the signs are the same then the exponent is used to select - # the result. This is exactly the ordering used in compare_total. - c = self.compare_total(other) - - if c == -1: - ans = other - else: - ans = self - - return ans._fix(context) - - def min(self, other, context=None): - """Returns the smaller value. - - Like min(self, other) except if one is not a number, returns - NaN (and signals if one is sNaN). Also rounds. - """ - other = _convert_other(other, raiseit=True) - - if context is None: - context = getcontext() - - if self._is_special or other._is_special: - # If one operand is a quiet NaN and the other is number, then the - # number is always returned - sn = self._isnan() - on = other._isnan() - if sn or on: - if on == 1 and sn == 0: - return self._fix(context) - if sn == 1 and on == 0: - return other._fix(context) - return self._check_nans(other, context) - - c = self._cmp(other) - if c == 0: - c = self.compare_total(other) - - if c == -1: - ans = self - else: - ans = other - - return ans._fix(context) - - def _isinteger(self): - """Returns whether self is an integer""" - if self._is_special: - return False - if self._exp >= 0: - return True - rest = self._int[self._exp:] - return rest == '0'*len(rest) - - def _iseven(self): - """Returns True if self is even. Assumes self is an integer.""" - if not self or self._exp > 0: - return True - return self._int[-1+self._exp] in '02468' - - def adjusted(self): - """Return the adjusted exponent of self""" - try: - return self._exp + len(self._int) - 1 - # If NaN or Infinity, self._exp is string - except TypeError: - return 0 - - def canonical(self): - """Returns the same Decimal object. - - As we do not have different encodings for the same number, the - received object already is in its canonical form. - """ - return self - - def compare_signal(self, other, context=None): - """Compares self to the other operand numerically. - - It's pretty much like compare(), but all NaNs signal, with signaling - NaNs taking precedence over quiet NaNs. - """ - other = _convert_other(other, raiseit = True) - ans = self._compare_check_nans(other, context) - if ans: - return ans - return self.compare(other, context=context) - - def compare_total(self, other, context=None): - """Compares self to other using the abstract representations. - - This is not like the standard compare, which use their numerical - value. Note that a total ordering is defined for all possible abstract - representations. - """ - other = _convert_other(other, raiseit=True) - - # if one is negative and the other is positive, it's easy - if self._sign and not other._sign: - return _NegativeOne - if not self._sign and other._sign: - return _One - sign = self._sign - - # let's handle both NaN types - self_nan = self._isnan() - other_nan = other._isnan() - if self_nan or other_nan: - if self_nan == other_nan: - # compare payloads as though they're integers - self_key = len(self._int), self._int - other_key = len(other._int), other._int - if self_key < other_key: - if sign: - return _One - else: - return _NegativeOne - if self_key > other_key: - if sign: - return _NegativeOne - else: - return _One - return _Zero - - if sign: - if self_nan == 1: - return _NegativeOne - if other_nan == 1: - return _One - if self_nan == 2: - return _NegativeOne - if other_nan == 2: - return _One - else: - if self_nan == 1: - return _One - if other_nan == 1: - return _NegativeOne - if self_nan == 2: - return _One - if other_nan == 2: - return _NegativeOne - - if self < other: - return _NegativeOne - if self > other: - return _One - - if self._exp < other._exp: - if sign: - return _One - else: - return _NegativeOne - if self._exp > other._exp: - if sign: - return _NegativeOne - else: - return _One - return _Zero - - - def compare_total_mag(self, other, context=None): - """Compares self to other using abstract repr., ignoring sign. - - Like compare_total, but with operand's sign ignored and assumed to be 0. - """ - other = _convert_other(other, raiseit=True) - - s = self.copy_abs() - o = other.copy_abs() - return s.compare_total(o) - - def copy_abs(self): - """Returns a copy with the sign set to 0. """ - return _dec_from_triple(0, self._int, self._exp, self._is_special) - - def copy_negate(self): - """Returns a copy with the sign inverted.""" - if self._sign: - return _dec_from_triple(0, self._int, self._exp, self._is_special) - else: - return _dec_from_triple(1, self._int, self._exp, self._is_special) - - def copy_sign(self, other, context=None): - """Returns self with the sign of other.""" - other = _convert_other(other, raiseit=True) - return _dec_from_triple(other._sign, self._int, - self._exp, self._is_special) - - def exp(self, context=None): - """Returns e ** self.""" - - if context is None: - context = getcontext() - - # exp(NaN) = NaN - ans = self._check_nans(context=context) - if ans: - return ans - - # exp(-Infinity) = 0 - if self._isinfinity() == -1: - return _Zero - - # exp(0) = 1 - if not self: - return _One - - # exp(Infinity) = Infinity - if self._isinfinity() == 1: - return Decimal(self) - - # the result is now guaranteed to be inexact (the true - # mathematical result is transcendental). There's no need to - # raise Rounded and Inexact here---they'll always be raised as - # a result of the call to _fix. - p = context.prec - adj = self.adjusted() - - # we only need to do any computation for quite a small range - # of adjusted exponents---for example, -29 <= adj <= 10 for - # the default context. For smaller exponent the result is - # indistinguishable from 1 at the given precision, while for - # larger exponent the result either overflows or underflows. - if self._sign == 0 and adj > len(str((context.Emax+1)*3)): - # overflow - ans = _dec_from_triple(0, '1', context.Emax+1) - elif self._sign == 1 and adj > len(str((-context.Etiny()+1)*3)): - # underflow to 0 - ans = _dec_from_triple(0, '1', context.Etiny()-1) - elif self._sign == 0 and adj < -p: - # p+1 digits; final round will raise correct flags - ans = _dec_from_triple(0, '1' + '0'*(p-1) + '1', -p) - elif self._sign == 1 and adj < -p-1: - # p+1 digits; final round will raise correct flags - ans = _dec_from_triple(0, '9'*(p+1), -p-1) - # general case - else: - op = _WorkRep(self) - c, e = op.int, op.exp - if op.sign == 1: - c = -c - - # compute correctly rounded result: increase precision by - # 3 digits at a time until we get an unambiguously - # roundable result - extra = 3 - while True: - coeff, exp = _dexp(c, e, p+extra) - if coeff % (5*10**(len(str(coeff))-p-1)): - break - extra += 3 - - ans = _dec_from_triple(0, str(coeff), exp) - - # at this stage, ans should round correctly with *any* - # rounding mode, not just with ROUND_HALF_EVEN - context = context._shallow_copy() - rounding = context._set_rounding(ROUND_HALF_EVEN) - ans = ans._fix(context) - context.rounding = rounding - - return ans - - def is_canonical(self): - """Return True if self is canonical; otherwise return False. - - Currently, the encoding of a Decimal instance is always - canonical, so this method returns True for any Decimal. - """ - return True - - def is_finite(self): - """Return True if self is finite; otherwise return False. - - A Decimal instance is considered finite if it is neither - infinite nor a NaN. - """ - return not self._is_special - - def is_infinite(self): - """Return True if self is infinite; otherwise return False.""" - return self._exp == 'F' - - def is_nan(self): - """Return True if self is a qNaN or sNaN; otherwise return False.""" - return self._exp in ('n', 'N') - - def is_normal(self, context=None): - """Return True if self is a normal number; otherwise return False.""" - if self._is_special or not self: - return False - if context is None: - context = getcontext() - return context.Emin <= self.adjusted() - - def is_qnan(self): - """Return True if self is a quiet NaN; otherwise return False.""" - return self._exp == 'n' - - def is_signed(self): - """Return True if self is negative; otherwise return False.""" - return self._sign == 1 - - def is_snan(self): - """Return True if self is a signaling NaN; otherwise return False.""" - return self._exp == 'N' - - def is_subnormal(self, context=None): - """Return True if self is subnormal; otherwise return False.""" - if self._is_special or not self: - return False - if context is None: - context = getcontext() - return self.adjusted() < context.Emin - - def is_zero(self): - """Return True if self is a zero; otherwise return False.""" - return not self._is_special and self._int == '0' - - def _ln_exp_bound(self): - """Compute a lower bound for the adjusted exponent of self.ln(). - In other words, compute r such that self.ln() >= 10**r. Assumes - that self is finite and positive and that self != 1. - """ - - # for 0.1 <= x <= 10 we use the inequalities 1-1/x <= ln(x) <= x-1 - adj = self._exp + len(self._int) - 1 - if adj >= 1: - # argument >= 10; we use 23/10 = 2.3 as a lower bound for ln(10) - return len(str(adj*23//10)) - 1 - if adj <= -2: - # argument <= 0.1 - return len(str((-1-adj)*23//10)) - 1 - op = _WorkRep(self) - c, e = op.int, op.exp - if adj == 0: - # 1 < self < 10 - num = str(c-10**-e) - den = str(c) - return len(num) - len(den) - (num < den) - # adj == -1, 0.1 <= self < 1 - return e + len(str(10**-e - c)) - 1 - - - def ln(self, context=None): - """Returns the natural (base e) logarithm of self.""" - - if context is None: - context = getcontext() - - # ln(NaN) = NaN - ans = self._check_nans(context=context) - if ans: - return ans - - # ln(0.0) == -Infinity - if not self: - return _NegativeInfinity - - # ln(Infinity) = Infinity - if self._isinfinity() == 1: - return _Infinity - - # ln(1.0) == 0.0 - if self == _One: - return _Zero - - # ln(negative) raises InvalidOperation - if self._sign == 1: - return context._raise_error(InvalidOperation, - 'ln of a negative value') - - # result is irrational, so necessarily inexact - op = _WorkRep(self) - c, e = op.int, op.exp - p = context.prec - - # correctly rounded result: repeatedly increase precision by 3 - # until we get an unambiguously roundable result - places = p - self._ln_exp_bound() + 2 # at least p+3 places - while True: - coeff = _dlog(c, e, places) - # assert len(str(abs(coeff)))-p >= 1 - if coeff % (5*10**(len(str(abs(coeff)))-p-1)): - break - places += 3 - ans = _dec_from_triple(int(coeff<0), str(abs(coeff)), -places) - - context = context._shallow_copy() - rounding = context._set_rounding(ROUND_HALF_EVEN) - ans = ans._fix(context) - context.rounding = rounding - return ans - - def _log10_exp_bound(self): - """Compute a lower bound for the adjusted exponent of self.log10(). - In other words, find r such that self.log10() >= 10**r. - Assumes that self is finite and positive and that self != 1. - """ - - # For x >= 10 or x < 0.1 we only need a bound on the integer - # part of log10(self), and this comes directly from the - # exponent of x. For 0.1 <= x <= 10 we use the inequalities - # 1-1/x <= log(x) <= x-1. If x > 1 we have |log10(x)| > - # (1-1/x)/2.31 > 0. If x < 1 then |log10(x)| > (1-x)/2.31 > 0 - - adj = self._exp + len(self._int) - 1 - if adj >= 1: - # self >= 10 - return len(str(adj))-1 - if adj <= -2: - # self < 0.1 - return len(str(-1-adj))-1 - op = _WorkRep(self) - c, e = op.int, op.exp - if adj == 0: - # 1 < self < 10 - num = str(c-10**-e) - den = str(231*c) - return len(num) - len(den) - (num < den) + 2 - # adj == -1, 0.1 <= self < 1 - num = str(10**-e-c) - return len(num) + e - (num < "231") - 1 - - def log10(self, context=None): - """Returns the base 10 logarithm of self.""" - - if context is None: - context = getcontext() - - # log10(NaN) = NaN - ans = self._check_nans(context=context) - if ans: - return ans - - # log10(0.0) == -Infinity - if not self: - return _NegativeInfinity - - # log10(Infinity) = Infinity - if self._isinfinity() == 1: - return _Infinity - - # log10(negative or -Infinity) raises InvalidOperation - if self._sign == 1: - return context._raise_error(InvalidOperation, - 'log10 of a negative value') - - # log10(10**n) = n - if self._int[0] == '1' and self._int[1:] == '0'*(len(self._int) - 1): - # answer may need rounding - ans = Decimal(self._exp + len(self._int) - 1) - else: - # result is irrational, so necessarily inexact - op = _WorkRep(self) - c, e = op.int, op.exp - p = context.prec - - # correctly rounded result: repeatedly increase precision - # until result is unambiguously roundable - places = p-self._log10_exp_bound()+2 - while True: - coeff = _dlog10(c, e, places) - # assert len(str(abs(coeff)))-p >= 1 - if coeff % (5*10**(len(str(abs(coeff)))-p-1)): - break - places += 3 - ans = _dec_from_triple(int(coeff<0), str(abs(coeff)), -places) - - context = context._shallow_copy() - rounding = context._set_rounding(ROUND_HALF_EVEN) - ans = ans._fix(context) - context.rounding = rounding - return ans - - def logb(self, context=None): - """ Returns the exponent of the magnitude of self's MSD. - - The result is the integer which is the exponent of the magnitude - of the most significant digit of self (as though it were truncated - to a single digit while maintaining the value of that digit and - without limiting the resulting exponent). - """ - # logb(NaN) = NaN - ans = self._check_nans(context=context) - if ans: - return ans - - if context is None: - context = getcontext() - - # logb(+/-Inf) = +Inf - if self._isinfinity(): - return _Infinity - - # logb(0) = -Inf, DivisionByZero - if not self: - return context._raise_error(DivisionByZero, 'logb(0)', 1) - - # otherwise, simply return the adjusted exponent of self, as a - # Decimal. Note that no attempt is made to fit the result - # into the current context. - ans = Decimal(self.adjusted()) - return ans._fix(context) - - def _islogical(self): - """Return True if self is a logical operand. - - For being logical, it must be a finite number with a sign of 0, - an exponent of 0, and a coefficient whose digits must all be - either 0 or 1. - """ - if self._sign != 0 or self._exp != 0: - return False - for dig in self._int: - if dig not in '01': - return False - return True - - def _fill_logical(self, context, opa, opb): - dif = context.prec - len(opa) - if dif > 0: - opa = '0'*dif + opa - elif dif < 0: - opa = opa[-context.prec:] - dif = context.prec - len(opb) - if dif > 0: - opb = '0'*dif + opb - elif dif < 0: - opb = opb[-context.prec:] - return opa, opb - - def logical_and(self, other, context=None): - """Applies an 'and' operation between self and other's digits.""" - if context is None: - context = getcontext() - - other = _convert_other(other, raiseit=True) - - if not self._islogical() or not other._islogical(): - return context._raise_error(InvalidOperation) - - # fill to context.prec - (opa, opb) = self._fill_logical(context, self._int, other._int) - - # make the operation, and clean starting zeroes - result = "".join([str(int(a)&int(b)) for a,b in zip(opa,opb)]) - return _dec_from_triple(0, result.lstrip('0') or '0', 0) - - def logical_invert(self, context=None): - """Invert all its digits.""" - if context is None: - context = getcontext() - return self.logical_xor(_dec_from_triple(0,'1'*context.prec,0), - context) - - def logical_or(self, other, context=None): - """Applies an 'or' operation between self and other's digits.""" - if context is None: - context = getcontext() - - other = _convert_other(other, raiseit=True) - - if not self._islogical() or not other._islogical(): - return context._raise_error(InvalidOperation) - - # fill to context.prec - (opa, opb) = self._fill_logical(context, self._int, other._int) - - # make the operation, and clean starting zeroes - result = "".join([str(int(a)|int(b)) for a,b in zip(opa,opb)]) - return _dec_from_triple(0, result.lstrip('0') or '0', 0) - - def logical_xor(self, other, context=None): - """Applies an 'xor' operation between self and other's digits.""" - if context is None: - context = getcontext() - - other = _convert_other(other, raiseit=True) - - if not self._islogical() or not other._islogical(): - return context._raise_error(InvalidOperation) - - # fill to context.prec - (opa, opb) = self._fill_logical(context, self._int, other._int) - - # make the operation, and clean starting zeroes - result = "".join([str(int(a)^int(b)) for a,b in zip(opa,opb)]) - return _dec_from_triple(0, result.lstrip('0') or '0', 0) - - def max_mag(self, other, context=None): - """Compares the values numerically with their sign ignored.""" - other = _convert_other(other, raiseit=True) - - if context is None: - context = getcontext() - - if self._is_special or other._is_special: - # If one operand is a quiet NaN and the other is number, then the - # number is always returned - sn = self._isnan() - on = other._isnan() - if sn or on: - if on == 1 and sn == 0: - return self._fix(context) - if sn == 1 and on == 0: - return other._fix(context) - return self._check_nans(other, context) - - c = self.copy_abs()._cmp(other.copy_abs()) - if c == 0: - c = self.compare_total(other) - - if c == -1: - ans = other - else: - ans = self - - return ans._fix(context) - - def min_mag(self, other, context=None): - """Compares the values numerically with their sign ignored.""" - other = _convert_other(other, raiseit=True) - - if context is None: - context = getcontext() - - if self._is_special or other._is_special: - # If one operand is a quiet NaN and the other is number, then the - # number is always returned - sn = self._isnan() - on = other._isnan() - if sn or on: - if on == 1 and sn == 0: - return self._fix(context) - if sn == 1 and on == 0: - return other._fix(context) - return self._check_nans(other, context) - - c = self.copy_abs()._cmp(other.copy_abs()) - if c == 0: - c = self.compare_total(other) - - if c == -1: - ans = self - else: - ans = other - - return ans._fix(context) - - def next_minus(self, context=None): - """Returns the largest representable number smaller than itself.""" - if context is None: - context = getcontext() - - ans = self._check_nans(context=context) - if ans: - return ans - - if self._isinfinity() == -1: - return _NegativeInfinity - if self._isinfinity() == 1: - return _dec_from_triple(0, '9'*context.prec, context.Etop()) - - context = context.copy() - context._set_rounding(ROUND_FLOOR) - context._ignore_all_flags() - new_self = self._fix(context) - if new_self != self: - return new_self - return self.__sub__(_dec_from_triple(0, '1', context.Etiny()-1), - context) - - def next_plus(self, context=None): - """Returns the smallest representable number larger than itself.""" - if context is None: - context = getcontext() - - ans = self._check_nans(context=context) - if ans: - return ans - - if self._isinfinity() == 1: - return _Infinity - if self._isinfinity() == -1: - return _dec_from_triple(1, '9'*context.prec, context.Etop()) - - context = context.copy() - context._set_rounding(ROUND_CEILING) - context._ignore_all_flags() - new_self = self._fix(context) - if new_self != self: - return new_self - return self.__add__(_dec_from_triple(0, '1', context.Etiny()-1), - context) - - def next_toward(self, other, context=None): - """Returns the number closest to self, in the direction towards other. - - The result is the closest representable number to self - (excluding self) that is in the direction towards other, - unless both have the same value. If the two operands are - numerically equal, then the result is a copy of self with the - sign set to be the same as the sign of other. - """ - other = _convert_other(other, raiseit=True) - - if context is None: - context = getcontext() - - ans = self._check_nans(other, context) - if ans: - return ans - - comparison = self._cmp(other) - if comparison == 0: - return self.copy_sign(other) - - if comparison == -1: - ans = self.next_plus(context) - else: # comparison == 1 - ans = self.next_minus(context) - - # decide which flags to raise using value of ans - if ans._isinfinity(): - context._raise_error(Overflow, - 'Infinite result from next_toward', - ans._sign) - context._raise_error(Inexact) - context._raise_error(Rounded) - elif ans.adjusted() < context.Emin: - context._raise_error(Underflow) - context._raise_error(Subnormal) - context._raise_error(Inexact) - context._raise_error(Rounded) - # if precision == 1 then we don't raise Clamped for a - # result 0E-Etiny. - if not ans: - context._raise_error(Clamped) - - return ans - - def number_class(self, context=None): - """Returns an indication of the class of self. - - The class is one of the following strings: - sNaN - NaN - -Infinity - -Normal - -Subnormal - -Zero - +Zero - +Subnormal - +Normal - +Infinity - """ - if self.is_snan(): - return "sNaN" - if self.is_qnan(): - return "NaN" - inf = self._isinfinity() - if inf == 1: - return "+Infinity" - if inf == -1: - return "-Infinity" - if self.is_zero(): - if self._sign: - return "-Zero" - else: - return "+Zero" - if context is None: - context = getcontext() - if self.is_subnormal(context=context): - if self._sign: - return "-Subnormal" - else: - return "+Subnormal" - # just a normal, regular, boring number, :) - if self._sign: - return "-Normal" - else: - return "+Normal" - - def radix(self): - """Just returns 10, as this is Decimal, :)""" - return Decimal(10) - - def rotate(self, other, context=None): - """Returns a rotated copy of self, value-of-other times.""" - if context is None: - context = getcontext() - - other = _convert_other(other, raiseit=True) - - ans = self._check_nans(other, context) - if ans: - return ans - - if other._exp != 0: - return context._raise_error(InvalidOperation) - if not (-context.prec <= int(other) <= context.prec): - return context._raise_error(InvalidOperation) - - if self._isinfinity(): - return Decimal(self) - - # get values, pad if necessary - torot = int(other) - rotdig = self._int - topad = context.prec - len(rotdig) - if topad > 0: - rotdig = '0'*topad + rotdig - elif topad < 0: - rotdig = rotdig[-topad:] - - # let's rotate! - rotated = rotdig[torot:] + rotdig[:torot] - return _dec_from_triple(self._sign, - rotated.lstrip('0') or '0', self._exp) - - def scaleb(self, other, context=None): - """Returns self operand after adding the second value to its exp.""" - if context is None: - context = getcontext() - - other = _convert_other(other, raiseit=True) - - ans = self._check_nans(other, context) - if ans: - return ans - - if other._exp != 0: - return context._raise_error(InvalidOperation) - liminf = -2 * (context.Emax + context.prec) - limsup = 2 * (context.Emax + context.prec) - if not (liminf <= int(other) <= limsup): - return context._raise_error(InvalidOperation) - - if self._isinfinity(): - return Decimal(self) - - d = _dec_from_triple(self._sign, self._int, self._exp + int(other)) - d = d._fix(context) - return d - - def shift(self, other, context=None): - """Returns a shifted copy of self, value-of-other times.""" - if context is None: - context = getcontext() - - other = _convert_other(other, raiseit=True) - - ans = self._check_nans(other, context) - if ans: - return ans - - if other._exp != 0: - return context._raise_error(InvalidOperation) - if not (-context.prec <= int(other) <= context.prec): - return context._raise_error(InvalidOperation) - - if self._isinfinity(): - return Decimal(self) - - # get values, pad if necessary - torot = int(other) - rotdig = self._int - topad = context.prec - len(rotdig) - if topad > 0: - rotdig = '0'*topad + rotdig - elif topad < 0: - rotdig = rotdig[-topad:] - - # let's shift! - if torot < 0: - shifted = rotdig[:torot] - else: - shifted = rotdig + '0'*torot - shifted = shifted[-context.prec:] - - return _dec_from_triple(self._sign, - shifted.lstrip('0') or '0', self._exp) - - # Support for pickling, copy, and deepcopy - def __reduce__(self): - return (self.__class__, (str(self),)) - - def __copy__(self): - if type(self) is Decimal: - return self # I'm immutable; therefore I am my own clone - return self.__class__(str(self)) - - def __deepcopy__(self, memo): - if type(self) is Decimal: - return self # My components are also immutable - return self.__class__(str(self)) - - # PEP 3101 support. the _localeconv keyword argument should be - # considered private: it's provided for ease of testing only. - def __format__(self, specifier, context=None, _localeconv=None): - """Format a Decimal instance according to the given specifier. - - The specifier should be a standard format specifier, with the - form described in PEP 3101. Formatting types 'e', 'E', 'f', - 'F', 'g', 'G', 'n' and '%' are supported. If the formatting - type is omitted it defaults to 'g' or 'G', depending on the - value of context.capitals. - """ - - # Note: PEP 3101 says that if the type is not present then - # there should be at least one digit after the decimal point. - # We take the liberty of ignoring this requirement for - # Decimal---it's presumably there to make sure that - # format(float, '') behaves similarly to str(float). - if context is None: - context = getcontext() - - spec = _parse_format_specifier(specifier, _localeconv=_localeconv) - - # special values don't care about the type or precision - if self._is_special: - sign = _format_sign(self._sign, spec) - body = str(self.copy_abs()) - if spec['type'] == '%': - body += '%' - return _format_align(sign, body, spec) - - # a type of None defaults to 'g' or 'G', depending on context - if spec['type'] is None: - spec['type'] = ['g', 'G'][context.capitals] - - # if type is '%', adjust exponent of self accordingly - if spec['type'] == '%': - self = _dec_from_triple(self._sign, self._int, self._exp+2) - - # round if necessary, taking rounding mode from the context - rounding = context.rounding - precision = spec['precision'] - if precision is not None: - if spec['type'] in 'eE': - self = self._round(precision+1, rounding) - elif spec['type'] in 'fF%': - self = self._rescale(-precision, rounding) - elif spec['type'] in 'gG' and len(self._int) > precision: - self = self._round(precision, rounding) - # special case: zeros with a positive exponent can't be - # represented in fixed point; rescale them to 0e0. - if not self and self._exp > 0 and spec['type'] in 'fF%': - self = self._rescale(0, rounding) - - # figure out placement of the decimal point - leftdigits = self._exp + len(self._int) - if spec['type'] in 'eE': - if not self and precision is not None: - dotplace = 1 - precision - else: - dotplace = 1 - elif spec['type'] in 'fF%': - dotplace = leftdigits - elif spec['type'] in 'gG': - if self._exp <= 0 and leftdigits > -6: - dotplace = leftdigits - else: - dotplace = 1 - - # find digits before and after decimal point, and get exponent - if dotplace < 0: - intpart = '0' - fracpart = '0'*(-dotplace) + self._int - elif dotplace > len(self._int): - intpart = self._int + '0'*(dotplace-len(self._int)) - fracpart = '' - else: - intpart = self._int[:dotplace] or '0' - fracpart = self._int[dotplace:] - exp = leftdigits-dotplace - - # done with the decimal-specific stuff; hand over the rest - # of the formatting to the _format_number function - return _format_number(self._sign, intpart, fracpart, exp, spec) - -def _dec_from_triple(sign, coefficient, exponent, special=False): - """Create a decimal instance directly, without any validation, - normalization (e.g. removal of leading zeros) or argument - conversion. - - This function is for *internal use only*. - """ - - self = object.__new__(Decimal) - self._sign = sign - self._int = coefficient - self._exp = exponent - self._is_special = special - - return self - -# Register Decimal as a kind of Number (an abstract base class). -# However, do not register it as Real (because Decimals are not -# interoperable with floats). -_numbers.Number.register(Decimal) - - -##### Context class ####################################################### - -class _ContextManager(object): - """Context manager class to support localcontext(). - - Sets a copy of the supplied context in __enter__() and restores - the previous decimal context in __exit__() - """ - def __init__(self, new_context): - self.new_context = new_context.copy() - def __enter__(self): - self.saved_context = getcontext() - setcontext(self.new_context) - return self.new_context - def __exit__(self, t, v, tb): - setcontext(self.saved_context) - -class Context(object): - """Contains the context for a Decimal instance. - - Contains: - prec - precision (for use in rounding, division, square roots..) - rounding - rounding type (how you round) - traps - If traps[exception] = 1, then the exception is - raised when it is caused. Otherwise, a value is - substituted in. - flags - When an exception is caused, flags[exception] is set. - (Whether or not the trap_enabler is set) - Should be reset by user of Decimal instance. - Emin - Minimum exponent - Emax - Maximum exponent - capitals - If 1, 1*10^1 is printed as 1E+1. - If 0, printed as 1e1 - clamp - If 1, change exponents if too high (Default 0) - """ - - def __init__(self, prec=None, rounding=None, Emin=None, Emax=None, - capitals=None, clamp=None, flags=None, traps=None, - _ignored_flags=None): - # Set defaults; for everything except flags and _ignored_flags, - # inherit from DefaultContext. - try: - dc = DefaultContext - except NameError: - pass - - self.prec = prec if prec is not None else dc.prec - self.rounding = rounding if rounding is not None else dc.rounding - self.Emin = Emin if Emin is not None else dc.Emin - self.Emax = Emax if Emax is not None else dc.Emax - self.capitals = capitals if capitals is not None else dc.capitals - self.clamp = clamp if clamp is not None else dc.clamp - - if _ignored_flags is None: - self._ignored_flags = [] - else: - self._ignored_flags = _ignored_flags - - if traps is None: - self.traps = dc.traps.copy() - elif not isinstance(traps, dict): - self.traps = dict((s, int(s in traps)) for s in _signals + traps) - else: - self.traps = traps - - if flags is None: - self.flags = dict.fromkeys(_signals, 0) - elif not isinstance(flags, dict): - self.flags = dict((s, int(s in flags)) for s in _signals + flags) - else: - self.flags = flags - - def _set_integer_check(self, name, value, vmin, vmax): - if not isinstance(value, int): - raise TypeError("%s must be an integer" % name) - if vmin == '-inf': - if value > vmax: - raise ValueError("%s must be in [%s, %d]. got: %s" % (name, vmin, vmax, value)) - elif vmax == 'inf': - if value < vmin: - raise ValueError("%s must be in [%d, %s]. got: %s" % (name, vmin, vmax, value)) - else: - if value < vmin or value > vmax: - raise ValueError("%s must be in [%d, %d]. got %s" % (name, vmin, vmax, value)) - return object.__setattr__(self, name, value) - - def _set_signal_dict(self, name, d): - if not isinstance(d, dict): - raise TypeError("%s must be a signal dict" % d) - for key in d: - if not key in _signals: - raise KeyError("%s is not a valid signal dict" % d) - for key in _signals: - if not key in d: - raise KeyError("%s is not a valid signal dict" % d) - return object.__setattr__(self, name, d) - - def __setattr__(self, name, value): - if name == 'prec': - return self._set_integer_check(name, value, 1, 'inf') - elif name == 'Emin': - return self._set_integer_check(name, value, '-inf', 0) - elif name == 'Emax': - return self._set_integer_check(name, value, 0, 'inf') - elif name == 'capitals': - return self._set_integer_check(name, value, 0, 1) - elif name == 'clamp': - return self._set_integer_check(name, value, 0, 1) - elif name == 'rounding': - if not value in _rounding_modes: - # raise TypeError even for strings to have consistency - # among various implementations. - raise TypeError("%s: invalid rounding mode" % value) - return object.__setattr__(self, name, value) - elif name == 'flags' or name == 'traps': - return self._set_signal_dict(name, value) - elif name == '_ignored_flags': - return object.__setattr__(self, name, value) - else: - raise AttributeError( - "'decimal.Context' object has no attribute '%s'" % name) - - def __delattr__(self, name): - raise AttributeError("%s cannot be deleted" % name) - - # Support for pickling, copy, and deepcopy - def __reduce__(self): - flags = [sig for sig, v in self.flags.items() if v] - traps = [sig for sig, v in self.traps.items() if v] - return (self.__class__, - (self.prec, self.rounding, self.Emin, self.Emax, - self.capitals, self.clamp, flags, traps)) - - def __repr__(self): - """Show the current context.""" - s = [] - s.append('Context(prec=%(prec)d, rounding=%(rounding)s, ' - 'Emin=%(Emin)d, Emax=%(Emax)d, capitals=%(capitals)d, ' - 'clamp=%(clamp)d' - % vars(self)) - names = [f.__name__ for f, v in self.flags.items() if v] - s.append('flags=[' + ', '.join(names) + ']') - names = [t.__name__ for t, v in self.traps.items() if v] - s.append('traps=[' + ', '.join(names) + ']') - return ', '.join(s) + ')' - - def clear_flags(self): - """Reset all flags to zero""" - for flag in self.flags: - self.flags[flag] = 0 - - def clear_traps(self): - """Reset all traps to zero""" - for flag in self.traps: - self.traps[flag] = 0 - - def _shallow_copy(self): - """Returns a shallow copy from self.""" - nc = Context(self.prec, self.rounding, self.Emin, self.Emax, - self.capitals, self.clamp, self.flags, self.traps, - self._ignored_flags) - return nc - - def copy(self): - """Returns a deep copy from self.""" - nc = Context(self.prec, self.rounding, self.Emin, self.Emax, - self.capitals, self.clamp, - self.flags.copy(), self.traps.copy(), - self._ignored_flags) - return nc - __copy__ = copy - - def _raise_error(self, condition, explanation = None, *args): - """Handles an error - - If the flag is in _ignored_flags, returns the default response. - Otherwise, it sets the flag, then, if the corresponding - trap_enabler is set, it reraises the exception. Otherwise, it returns - the default value after setting the flag. - """ - error = _condition_map.get(condition, condition) - if error in self._ignored_flags: - # Don't touch the flag - return error().handle(self, *args) - - self.flags[error] = 1 - if not self.traps[error]: - # The errors define how to handle themselves. - return condition().handle(self, *args) - - # Errors should only be risked on copies of the context - # self._ignored_flags = [] - raise error(explanation) - - def _ignore_all_flags(self): - """Ignore all flags, if they are raised""" - return self._ignore_flags(*_signals) - - def _ignore_flags(self, *flags): - """Ignore the flags, if they are raised""" - # Do not mutate-- This way, copies of a context leave the original - # alone. - self._ignored_flags = (self._ignored_flags + list(flags)) - return list(flags) - - def _regard_flags(self, *flags): - """Stop ignoring the flags, if they are raised""" - if flags and isinstance(flags[0], (tuple,list)): - flags = flags[0] - for flag in flags: - self._ignored_flags.remove(flag) - - # We inherit object.__hash__, so we must deny this explicitly - __hash__ = None - - def Etiny(self): - """Returns Etiny (= Emin - prec + 1)""" - return int(self.Emin - self.prec + 1) - - def Etop(self): - """Returns maximum exponent (= Emax - prec + 1)""" - return int(self.Emax - self.prec + 1) - - def _set_rounding(self, type): - """Sets the rounding type. - - Sets the rounding type, and returns the current (previous) - rounding type. Often used like: - - context = context.copy() - # so you don't change the calling context - # if an error occurs in the middle. - rounding = context._set_rounding(ROUND_UP) - val = self.__sub__(other, context=context) - context._set_rounding(rounding) - - This will make it round up for that operation. - """ - rounding = self.rounding - self.rounding= type - return rounding - - def create_decimal(self, num='0'): - """Creates a new Decimal instance but using self as context. - - This method implements the to-number operation of the - IBM Decimal specification.""" - - if isinstance(num, str) and num != num.strip(): - return self._raise_error(ConversionSyntax, - "no trailing or leading whitespace is " - "permitted.") - - d = Decimal(num, context=self) - if d._isnan() and len(d._int) > self.prec - self.clamp: - return self._raise_error(ConversionSyntax, - "diagnostic info too long in NaN") - return d._fix(self) - - def create_decimal_from_float(self, f): - """Creates a new Decimal instance from a float but rounding using self - as the context. - - >>> context = Context(prec=5, rounding=ROUND_DOWN) - >>> context.create_decimal_from_float(3.1415926535897932) - Decimal('3.1415') - >>> context = Context(prec=5, traps=[Inexact]) - >>> context.create_decimal_from_float(3.1415926535897932) - Traceback (most recent call last): - ... - decimal.Inexact: None - - """ - d = Decimal.from_float(f) # An exact conversion - return d._fix(self) # Apply the context rounding - - # Methods - def abs(self, a): - """Returns the absolute value of the operand. - - If the operand is negative, the result is the same as using the minus - operation on the operand. Otherwise, the result is the same as using - the plus operation on the operand. - - >>> ExtendedContext.abs(Decimal('2.1')) - Decimal('2.1') - >>> ExtendedContext.abs(Decimal('-100')) - Decimal('100') - >>> ExtendedContext.abs(Decimal('101.5')) - Decimal('101.5') - >>> ExtendedContext.abs(Decimal('-101.5')) - Decimal('101.5') - >>> ExtendedContext.abs(-1) - Decimal('1') - """ - a = _convert_other(a, raiseit=True) - return a.__abs__(context=self) - - def add(self, a, b): - """Return the sum of the two operands. - - >>> ExtendedContext.add(Decimal('12'), Decimal('7.00')) - Decimal('19.00') - >>> ExtendedContext.add(Decimal('1E+2'), Decimal('1.01E+4')) - Decimal('1.02E+4') - >>> ExtendedContext.add(1, Decimal(2)) - Decimal('3') - >>> ExtendedContext.add(Decimal(8), 5) - Decimal('13') - >>> ExtendedContext.add(5, 5) - Decimal('10') - """ - a = _convert_other(a, raiseit=True) - r = a.__add__(b, context=self) - if r is NotImplemented: - raise TypeError("Unable to convert %s to Decimal" % b) - else: - return r - - def _apply(self, a): - return str(a._fix(self)) - - def canonical(self, a): - """Returns the same Decimal object. - - As we do not have different encodings for the same number, the - received object already is in its canonical form. - - >>> ExtendedContext.canonical(Decimal('2.50')) - Decimal('2.50') - """ - if not isinstance(a, Decimal): - raise TypeError("canonical requires a Decimal as an argument.") - return a.canonical() - - def compare(self, a, b): - """Compares values numerically. - - If the signs of the operands differ, a value representing each operand - ('-1' if the operand is less than zero, '0' if the operand is zero or - negative zero, or '1' if the operand is greater than zero) is used in - place of that operand for the comparison instead of the actual - operand. - - The comparison is then effected by subtracting the second operand from - the first and then returning a value according to the result of the - subtraction: '-1' if the result is less than zero, '0' if the result is - zero or negative zero, or '1' if the result is greater than zero. - - >>> ExtendedContext.compare(Decimal('2.1'), Decimal('3')) - Decimal('-1') - >>> ExtendedContext.compare(Decimal('2.1'), Decimal('2.1')) - Decimal('0') - >>> ExtendedContext.compare(Decimal('2.1'), Decimal('2.10')) - Decimal('0') - >>> ExtendedContext.compare(Decimal('3'), Decimal('2.1')) - Decimal('1') - >>> ExtendedContext.compare(Decimal('2.1'), Decimal('-3')) - Decimal('1') - >>> ExtendedContext.compare(Decimal('-3'), Decimal('2.1')) - Decimal('-1') - >>> ExtendedContext.compare(1, 2) - Decimal('-1') - >>> ExtendedContext.compare(Decimal(1), 2) - Decimal('-1') - >>> ExtendedContext.compare(1, Decimal(2)) - Decimal('-1') - """ - a = _convert_other(a, raiseit=True) - return a.compare(b, context=self) - - def compare_signal(self, a, b): - """Compares the values of the two operands numerically. - - It's pretty much like compare(), but all NaNs signal, with signaling - NaNs taking precedence over quiet NaNs. - - >>> c = ExtendedContext - >>> c.compare_signal(Decimal('2.1'), Decimal('3')) - Decimal('-1') - >>> c.compare_signal(Decimal('2.1'), Decimal('2.1')) - Decimal('0') - >>> c.flags[InvalidOperation] = 0 - >>> print(c.flags[InvalidOperation]) - 0 - >>> c.compare_signal(Decimal('NaN'), Decimal('2.1')) - Decimal('NaN') - >>> print(c.flags[InvalidOperation]) - 1 - >>> c.flags[InvalidOperation] = 0 - >>> print(c.flags[InvalidOperation]) - 0 - >>> c.compare_signal(Decimal('sNaN'), Decimal('2.1')) - Decimal('NaN') - >>> print(c.flags[InvalidOperation]) - 1 - >>> c.compare_signal(-1, 2) - Decimal('-1') - >>> c.compare_signal(Decimal(-1), 2) - Decimal('-1') - >>> c.compare_signal(-1, Decimal(2)) - Decimal('-1') - """ - a = _convert_other(a, raiseit=True) - return a.compare_signal(b, context=self) - - def compare_total(self, a, b): - """Compares two operands using their abstract representation. - - This is not like the standard compare, which use their numerical - value. Note that a total ordering is defined for all possible abstract - representations. - - >>> ExtendedContext.compare_total(Decimal('12.73'), Decimal('127.9')) - Decimal('-1') - >>> ExtendedContext.compare_total(Decimal('-127'), Decimal('12')) - Decimal('-1') - >>> ExtendedContext.compare_total(Decimal('12.30'), Decimal('12.3')) - Decimal('-1') - >>> ExtendedContext.compare_total(Decimal('12.30'), Decimal('12.30')) - Decimal('0') - >>> ExtendedContext.compare_total(Decimal('12.3'), Decimal('12.300')) - Decimal('1') - >>> ExtendedContext.compare_total(Decimal('12.3'), Decimal('NaN')) - Decimal('-1') - >>> ExtendedContext.compare_total(1, 2) - Decimal('-1') - >>> ExtendedContext.compare_total(Decimal(1), 2) - Decimal('-1') - >>> ExtendedContext.compare_total(1, Decimal(2)) - Decimal('-1') - """ - a = _convert_other(a, raiseit=True) - return a.compare_total(b) - - def compare_total_mag(self, a, b): - """Compares two operands using their abstract representation ignoring sign. - - Like compare_total, but with operand's sign ignored and assumed to be 0. - """ - a = _convert_other(a, raiseit=True) - return a.compare_total_mag(b) - - def copy_abs(self, a): - """Returns a copy of the operand with the sign set to 0. - - >>> ExtendedContext.copy_abs(Decimal('2.1')) - Decimal('2.1') - >>> ExtendedContext.copy_abs(Decimal('-100')) - Decimal('100') - >>> ExtendedContext.copy_abs(-1) - Decimal('1') - """ - a = _convert_other(a, raiseit=True) - return a.copy_abs() - - def copy_decimal(self, a): - """Returns a copy of the decimal object. - - >>> ExtendedContext.copy_decimal(Decimal('2.1')) - Decimal('2.1') - >>> ExtendedContext.copy_decimal(Decimal('-1.00')) - Decimal('-1.00') - >>> ExtendedContext.copy_decimal(1) - Decimal('1') - """ - a = _convert_other(a, raiseit=True) - return Decimal(a) - - def copy_negate(self, a): - """Returns a copy of the operand with the sign inverted. - - >>> ExtendedContext.copy_negate(Decimal('101.5')) - Decimal('-101.5') - >>> ExtendedContext.copy_negate(Decimal('-101.5')) - Decimal('101.5') - >>> ExtendedContext.copy_negate(1) - Decimal('-1') - """ - a = _convert_other(a, raiseit=True) - return a.copy_negate() - - def copy_sign(self, a, b): - """Copies the second operand's sign to the first one. - - In detail, it returns a copy of the first operand with the sign - equal to the sign of the second operand. - - >>> ExtendedContext.copy_sign(Decimal( '1.50'), Decimal('7.33')) - Decimal('1.50') - >>> ExtendedContext.copy_sign(Decimal('-1.50'), Decimal('7.33')) - Decimal('1.50') - >>> ExtendedContext.copy_sign(Decimal( '1.50'), Decimal('-7.33')) - Decimal('-1.50') - >>> ExtendedContext.copy_sign(Decimal('-1.50'), Decimal('-7.33')) - Decimal('-1.50') - >>> ExtendedContext.copy_sign(1, -2) - Decimal('-1') - >>> ExtendedContext.copy_sign(Decimal(1), -2) - Decimal('-1') - >>> ExtendedContext.copy_sign(1, Decimal(-2)) - Decimal('-1') - """ - a = _convert_other(a, raiseit=True) - return a.copy_sign(b) - - def divide(self, a, b): - """Decimal division in a specified context. - - >>> ExtendedContext.divide(Decimal('1'), Decimal('3')) - Decimal('0.333333333') - >>> ExtendedContext.divide(Decimal('2'), Decimal('3')) - Decimal('0.666666667') - >>> ExtendedContext.divide(Decimal('5'), Decimal('2')) - Decimal('2.5') - >>> ExtendedContext.divide(Decimal('1'), Decimal('10')) - Decimal('0.1') - >>> ExtendedContext.divide(Decimal('12'), Decimal('12')) - Decimal('1') - >>> ExtendedContext.divide(Decimal('8.00'), Decimal('2')) - Decimal('4.00') - >>> ExtendedContext.divide(Decimal('2.400'), Decimal('2.0')) - Decimal('1.20') - >>> ExtendedContext.divide(Decimal('1000'), Decimal('100')) - Decimal('10') - >>> ExtendedContext.divide(Decimal('1000'), Decimal('1')) - Decimal('1000') - >>> ExtendedContext.divide(Decimal('2.40E+6'), Decimal('2')) - Decimal('1.20E+6') - >>> ExtendedContext.divide(5, 5) - Decimal('1') - >>> ExtendedContext.divide(Decimal(5), 5) - Decimal('1') - >>> ExtendedContext.divide(5, Decimal(5)) - Decimal('1') - """ - a = _convert_other(a, raiseit=True) - r = a.__truediv__(b, context=self) - if r is NotImplemented: - raise TypeError("Unable to convert %s to Decimal" % b) - else: - return r - - def divide_int(self, a, b): - """Divides two numbers and returns the integer part of the result. - - >>> ExtendedContext.divide_int(Decimal('2'), Decimal('3')) - Decimal('0') - >>> ExtendedContext.divide_int(Decimal('10'), Decimal('3')) - Decimal('3') - >>> ExtendedContext.divide_int(Decimal('1'), Decimal('0.3')) - Decimal('3') - >>> ExtendedContext.divide_int(10, 3) - Decimal('3') - >>> ExtendedContext.divide_int(Decimal(10), 3) - Decimal('3') - >>> ExtendedContext.divide_int(10, Decimal(3)) - Decimal('3') - """ - a = _convert_other(a, raiseit=True) - r = a.__floordiv__(b, context=self) - if r is NotImplemented: - raise TypeError("Unable to convert %s to Decimal" % b) - else: - return r - - def divmod(self, a, b): - """Return (a // b, a % b). - - >>> ExtendedContext.divmod(Decimal(8), Decimal(3)) - (Decimal('2'), Decimal('2')) - >>> ExtendedContext.divmod(Decimal(8), Decimal(4)) - (Decimal('2'), Decimal('0')) - >>> ExtendedContext.divmod(8, 4) - (Decimal('2'), Decimal('0')) - >>> ExtendedContext.divmod(Decimal(8), 4) - (Decimal('2'), Decimal('0')) - >>> ExtendedContext.divmod(8, Decimal(4)) - (Decimal('2'), Decimal('0')) - """ - a = _convert_other(a, raiseit=True) - r = a.__divmod__(b, context=self) - if r is NotImplemented: - raise TypeError("Unable to convert %s to Decimal" % b) - else: - return r - - def exp(self, a): - """Returns e ** a. - - >>> c = ExtendedContext.copy() - >>> c.Emin = -999 - >>> c.Emax = 999 - >>> c.exp(Decimal('-Infinity')) - Decimal('0') - >>> c.exp(Decimal('-1')) - Decimal('0.367879441') - >>> c.exp(Decimal('0')) - Decimal('1') - >>> c.exp(Decimal('1')) - Decimal('2.71828183') - >>> c.exp(Decimal('0.693147181')) - Decimal('2.00000000') - >>> c.exp(Decimal('+Infinity')) - Decimal('Infinity') - >>> c.exp(10) - Decimal('22026.4658') - """ - a =_convert_other(a, raiseit=True) - return a.exp(context=self) - - def fma(self, a, b, c): - """Returns a multiplied by b, plus c. - - The first two operands are multiplied together, using multiply, - the third operand is then added to the result of that - multiplication, using add, all with only one final rounding. - - >>> ExtendedContext.fma(Decimal('3'), Decimal('5'), Decimal('7')) - Decimal('22') - >>> ExtendedContext.fma(Decimal('3'), Decimal('-5'), Decimal('7')) - Decimal('-8') - >>> ExtendedContext.fma(Decimal('888565290'), Decimal('1557.96930'), Decimal('-86087.7578')) - Decimal('1.38435736E+12') - >>> ExtendedContext.fma(1, 3, 4) - Decimal('7') - >>> ExtendedContext.fma(1, Decimal(3), 4) - Decimal('7') - >>> ExtendedContext.fma(1, 3, Decimal(4)) - Decimal('7') - """ - a = _convert_other(a, raiseit=True) - return a.fma(b, c, context=self) - - def is_canonical(self, a): - """Return True if the operand is canonical; otherwise return False. - - Currently, the encoding of a Decimal instance is always - canonical, so this method returns True for any Decimal. - - >>> ExtendedContext.is_canonical(Decimal('2.50')) - True - """ - if not isinstance(a, Decimal): - raise TypeError("is_canonical requires a Decimal as an argument.") - return a.is_canonical() - - def is_finite(self, a): - """Return True if the operand is finite; otherwise return False. - - A Decimal instance is considered finite if it is neither - infinite nor a NaN. - - >>> ExtendedContext.is_finite(Decimal('2.50')) - True - >>> ExtendedContext.is_finite(Decimal('-0.3')) - True - >>> ExtendedContext.is_finite(Decimal('0')) - True - >>> ExtendedContext.is_finite(Decimal('Inf')) - False - >>> ExtendedContext.is_finite(Decimal('NaN')) - False - >>> ExtendedContext.is_finite(1) - True - """ - a = _convert_other(a, raiseit=True) - return a.is_finite() - - def is_infinite(self, a): - """Return True if the operand is infinite; otherwise return False. - - >>> ExtendedContext.is_infinite(Decimal('2.50')) - False - >>> ExtendedContext.is_infinite(Decimal('-Inf')) - True - >>> ExtendedContext.is_infinite(Decimal('NaN')) - False - >>> ExtendedContext.is_infinite(1) - False - """ - a = _convert_other(a, raiseit=True) - return a.is_infinite() - - def is_nan(self, a): - """Return True if the operand is a qNaN or sNaN; - otherwise return False. - - >>> ExtendedContext.is_nan(Decimal('2.50')) - False - >>> ExtendedContext.is_nan(Decimal('NaN')) - True - >>> ExtendedContext.is_nan(Decimal('-sNaN')) - True - >>> ExtendedContext.is_nan(1) - False - """ - a = _convert_other(a, raiseit=True) - return a.is_nan() - - def is_normal(self, a): - """Return True if the operand is a normal number; - otherwise return False. - - >>> c = ExtendedContext.copy() - >>> c.Emin = -999 - >>> c.Emax = 999 - >>> c.is_normal(Decimal('2.50')) - True - >>> c.is_normal(Decimal('0.1E-999')) - False - >>> c.is_normal(Decimal('0.00')) - False - >>> c.is_normal(Decimal('-Inf')) - False - >>> c.is_normal(Decimal('NaN')) - False - >>> c.is_normal(1) - True - """ - a = _convert_other(a, raiseit=True) - return a.is_normal(context=self) - - def is_qnan(self, a): - """Return True if the operand is a quiet NaN; otherwise return False. - - >>> ExtendedContext.is_qnan(Decimal('2.50')) - False - >>> ExtendedContext.is_qnan(Decimal('NaN')) - True - >>> ExtendedContext.is_qnan(Decimal('sNaN')) - False - >>> ExtendedContext.is_qnan(1) - False - """ - a = _convert_other(a, raiseit=True) - return a.is_qnan() - - def is_signed(self, a): - """Return True if the operand is negative; otherwise return False. - - >>> ExtendedContext.is_signed(Decimal('2.50')) - False - >>> ExtendedContext.is_signed(Decimal('-12')) - True - >>> ExtendedContext.is_signed(Decimal('-0')) - True - >>> ExtendedContext.is_signed(8) - False - >>> ExtendedContext.is_signed(-8) - True - """ - a = _convert_other(a, raiseit=True) - return a.is_signed() - - def is_snan(self, a): - """Return True if the operand is a signaling NaN; - otherwise return False. - - >>> ExtendedContext.is_snan(Decimal('2.50')) - False - >>> ExtendedContext.is_snan(Decimal('NaN')) - False - >>> ExtendedContext.is_snan(Decimal('sNaN')) - True - >>> ExtendedContext.is_snan(1) - False - """ - a = _convert_other(a, raiseit=True) - return a.is_snan() - - def is_subnormal(self, a): - """Return True if the operand is subnormal; otherwise return False. - - >>> c = ExtendedContext.copy() - >>> c.Emin = -999 - >>> c.Emax = 999 - >>> c.is_subnormal(Decimal('2.50')) - False - >>> c.is_subnormal(Decimal('0.1E-999')) - True - >>> c.is_subnormal(Decimal('0.00')) - False - >>> c.is_subnormal(Decimal('-Inf')) - False - >>> c.is_subnormal(Decimal('NaN')) - False - >>> c.is_subnormal(1) - False - """ - a = _convert_other(a, raiseit=True) - return a.is_subnormal(context=self) - - def is_zero(self, a): - """Return True if the operand is a zero; otherwise return False. - - >>> ExtendedContext.is_zero(Decimal('0')) - True - >>> ExtendedContext.is_zero(Decimal('2.50')) - False - >>> ExtendedContext.is_zero(Decimal('-0E+2')) - True - >>> ExtendedContext.is_zero(1) - False - >>> ExtendedContext.is_zero(0) - True - """ - a = _convert_other(a, raiseit=True) - return a.is_zero() - - def ln(self, a): - """Returns the natural (base e) logarithm of the operand. - - >>> c = ExtendedContext.copy() - >>> c.Emin = -999 - >>> c.Emax = 999 - >>> c.ln(Decimal('0')) - Decimal('-Infinity') - >>> c.ln(Decimal('1.000')) - Decimal('0') - >>> c.ln(Decimal('2.71828183')) - Decimal('1.00000000') - >>> c.ln(Decimal('10')) - Decimal('2.30258509') - >>> c.ln(Decimal('+Infinity')) - Decimal('Infinity') - >>> c.ln(1) - Decimal('0') - """ - a = _convert_other(a, raiseit=True) - return a.ln(context=self) - - def log10(self, a): - """Returns the base 10 logarithm of the operand. - - >>> c = ExtendedContext.copy() - >>> c.Emin = -999 - >>> c.Emax = 999 - >>> c.log10(Decimal('0')) - Decimal('-Infinity') - >>> c.log10(Decimal('0.001')) - Decimal('-3') - >>> c.log10(Decimal('1.000')) - Decimal('0') - >>> c.log10(Decimal('2')) - Decimal('0.301029996') - >>> c.log10(Decimal('10')) - Decimal('1') - >>> c.log10(Decimal('70')) - Decimal('1.84509804') - >>> c.log10(Decimal('+Infinity')) - Decimal('Infinity') - >>> c.log10(0) - Decimal('-Infinity') - >>> c.log10(1) - Decimal('0') - """ - a = _convert_other(a, raiseit=True) - return a.log10(context=self) - - def logb(self, a): - """ Returns the exponent of the magnitude of the operand's MSD. - - The result is the integer which is the exponent of the magnitude - of the most significant digit of the operand (as though the - operand were truncated to a single digit while maintaining the - value of that digit and without limiting the resulting exponent). - - >>> ExtendedContext.logb(Decimal('250')) - Decimal('2') - >>> ExtendedContext.logb(Decimal('2.50')) - Decimal('0') - >>> ExtendedContext.logb(Decimal('0.03')) - Decimal('-2') - >>> ExtendedContext.logb(Decimal('0')) - Decimal('-Infinity') - >>> ExtendedContext.logb(1) - Decimal('0') - >>> ExtendedContext.logb(10) - Decimal('1') - >>> ExtendedContext.logb(100) - Decimal('2') - """ - a = _convert_other(a, raiseit=True) - return a.logb(context=self) - - def logical_and(self, a, b): - """Applies the logical operation 'and' between each operand's digits. - - The operands must be both logical numbers. - - >>> ExtendedContext.logical_and(Decimal('0'), Decimal('0')) - Decimal('0') - >>> ExtendedContext.logical_and(Decimal('0'), Decimal('1')) - Decimal('0') - >>> ExtendedContext.logical_and(Decimal('1'), Decimal('0')) - Decimal('0') - >>> ExtendedContext.logical_and(Decimal('1'), Decimal('1')) - Decimal('1') - >>> ExtendedContext.logical_and(Decimal('1100'), Decimal('1010')) - Decimal('1000') - >>> ExtendedContext.logical_and(Decimal('1111'), Decimal('10')) - Decimal('10') - >>> ExtendedContext.logical_and(110, 1101) - Decimal('100') - >>> ExtendedContext.logical_and(Decimal(110), 1101) - Decimal('100') - >>> ExtendedContext.logical_and(110, Decimal(1101)) - Decimal('100') - """ - a = _convert_other(a, raiseit=True) - return a.logical_and(b, context=self) - - def logical_invert(self, a): - """Invert all the digits in the operand. - - The operand must be a logical number. - - >>> ExtendedContext.logical_invert(Decimal('0')) - Decimal('111111111') - >>> ExtendedContext.logical_invert(Decimal('1')) - Decimal('111111110') - >>> ExtendedContext.logical_invert(Decimal('111111111')) - Decimal('0') - >>> ExtendedContext.logical_invert(Decimal('101010101')) - Decimal('10101010') - >>> ExtendedContext.logical_invert(1101) - Decimal('111110010') - """ - a = _convert_other(a, raiseit=True) - return a.logical_invert(context=self) - - def logical_or(self, a, b): - """Applies the logical operation 'or' between each operand's digits. - - The operands must be both logical numbers. - - >>> ExtendedContext.logical_or(Decimal('0'), Decimal('0')) - Decimal('0') - >>> ExtendedContext.logical_or(Decimal('0'), Decimal('1')) - Decimal('1') - >>> ExtendedContext.logical_or(Decimal('1'), Decimal('0')) - Decimal('1') - >>> ExtendedContext.logical_or(Decimal('1'), Decimal('1')) - Decimal('1') - >>> ExtendedContext.logical_or(Decimal('1100'), Decimal('1010')) - Decimal('1110') - >>> ExtendedContext.logical_or(Decimal('1110'), Decimal('10')) - Decimal('1110') - >>> ExtendedContext.logical_or(110, 1101) - Decimal('1111') - >>> ExtendedContext.logical_or(Decimal(110), 1101) - Decimal('1111') - >>> ExtendedContext.logical_or(110, Decimal(1101)) - Decimal('1111') - """ - a = _convert_other(a, raiseit=True) - return a.logical_or(b, context=self) - - def logical_xor(self, a, b): - """Applies the logical operation 'xor' between each operand's digits. - - The operands must be both logical numbers. - - >>> ExtendedContext.logical_xor(Decimal('0'), Decimal('0')) - Decimal('0') - >>> ExtendedContext.logical_xor(Decimal('0'), Decimal('1')) - Decimal('1') - >>> ExtendedContext.logical_xor(Decimal('1'), Decimal('0')) - Decimal('1') - >>> ExtendedContext.logical_xor(Decimal('1'), Decimal('1')) - Decimal('0') - >>> ExtendedContext.logical_xor(Decimal('1100'), Decimal('1010')) - Decimal('110') - >>> ExtendedContext.logical_xor(Decimal('1111'), Decimal('10')) - Decimal('1101') - >>> ExtendedContext.logical_xor(110, 1101) - Decimal('1011') - >>> ExtendedContext.logical_xor(Decimal(110), 1101) - Decimal('1011') - >>> ExtendedContext.logical_xor(110, Decimal(1101)) - Decimal('1011') - """ - a = _convert_other(a, raiseit=True) - return a.logical_xor(b, context=self) - - def max(self, a, b): - """max compares two values numerically and returns the maximum. - - If either operand is a NaN then the general rules apply. - Otherwise, the operands are compared as though by the compare - operation. If they are numerically equal then the left-hand operand - is chosen as the result. Otherwise the maximum (closer to positive - infinity) of the two operands is chosen as the result. - - >>> ExtendedContext.max(Decimal('3'), Decimal('2')) - Decimal('3') - >>> ExtendedContext.max(Decimal('-10'), Decimal('3')) - Decimal('3') - >>> ExtendedContext.max(Decimal('1.0'), Decimal('1')) - Decimal('1') - >>> ExtendedContext.max(Decimal('7'), Decimal('NaN')) - Decimal('7') - >>> ExtendedContext.max(1, 2) - Decimal('2') - >>> ExtendedContext.max(Decimal(1), 2) - Decimal('2') - >>> ExtendedContext.max(1, Decimal(2)) - Decimal('2') - """ - a = _convert_other(a, raiseit=True) - return a.max(b, context=self) - - def max_mag(self, a, b): - """Compares the values numerically with their sign ignored. - - >>> ExtendedContext.max_mag(Decimal('7'), Decimal('NaN')) - Decimal('7') - >>> ExtendedContext.max_mag(Decimal('7'), Decimal('-10')) - Decimal('-10') - >>> ExtendedContext.max_mag(1, -2) - Decimal('-2') - >>> ExtendedContext.max_mag(Decimal(1), -2) - Decimal('-2') - >>> ExtendedContext.max_mag(1, Decimal(-2)) - Decimal('-2') - """ - a = _convert_other(a, raiseit=True) - return a.max_mag(b, context=self) - - def min(self, a, b): - """min compares two values numerically and returns the minimum. - - If either operand is a NaN then the general rules apply. - Otherwise, the operands are compared as though by the compare - operation. If they are numerically equal then the left-hand operand - is chosen as the result. Otherwise the minimum (closer to negative - infinity) of the two operands is chosen as the result. - - >>> ExtendedContext.min(Decimal('3'), Decimal('2')) - Decimal('2') - >>> ExtendedContext.min(Decimal('-10'), Decimal('3')) - Decimal('-10') - >>> ExtendedContext.min(Decimal('1.0'), Decimal('1')) - Decimal('1.0') - >>> ExtendedContext.min(Decimal('7'), Decimal('NaN')) - Decimal('7') - >>> ExtendedContext.min(1, 2) - Decimal('1') - >>> ExtendedContext.min(Decimal(1), 2) - Decimal('1') - >>> ExtendedContext.min(1, Decimal(29)) - Decimal('1') - """ - a = _convert_other(a, raiseit=True) - return a.min(b, context=self) - - def min_mag(self, a, b): - """Compares the values numerically with their sign ignored. - - >>> ExtendedContext.min_mag(Decimal('3'), Decimal('-2')) - Decimal('-2') - >>> ExtendedContext.min_mag(Decimal('-3'), Decimal('NaN')) - Decimal('-3') - >>> ExtendedContext.min_mag(1, -2) - Decimal('1') - >>> ExtendedContext.min_mag(Decimal(1), -2) - Decimal('1') - >>> ExtendedContext.min_mag(1, Decimal(-2)) - Decimal('1') - """ - a = _convert_other(a, raiseit=True) - return a.min_mag(b, context=self) - - def minus(self, a): - """Minus corresponds to unary prefix minus in Python. - - The operation is evaluated using the same rules as subtract; the - operation minus(a) is calculated as subtract('0', a) where the '0' - has the same exponent as the operand. - - >>> ExtendedContext.minus(Decimal('1.3')) - Decimal('-1.3') - >>> ExtendedContext.minus(Decimal('-1.3')) - Decimal('1.3') - >>> ExtendedContext.minus(1) - Decimal('-1') - """ - a = _convert_other(a, raiseit=True) - return a.__neg__(context=self) - - def multiply(self, a, b): - """multiply multiplies two operands. - - If either operand is a special value then the general rules apply. - Otherwise, the operands are multiplied together - ('long multiplication'), resulting in a number which may be as long as - the sum of the lengths of the two operands. - - >>> ExtendedContext.multiply(Decimal('1.20'), Decimal('3')) - Decimal('3.60') - >>> ExtendedContext.multiply(Decimal('7'), Decimal('3')) - Decimal('21') - >>> ExtendedContext.multiply(Decimal('0.9'), Decimal('0.8')) - Decimal('0.72') - >>> ExtendedContext.multiply(Decimal('0.9'), Decimal('-0')) - Decimal('-0.0') - >>> ExtendedContext.multiply(Decimal('654321'), Decimal('654321')) - Decimal('4.28135971E+11') - >>> ExtendedContext.multiply(7, 7) - Decimal('49') - >>> ExtendedContext.multiply(Decimal(7), 7) - Decimal('49') - >>> ExtendedContext.multiply(7, Decimal(7)) - Decimal('49') - """ - a = _convert_other(a, raiseit=True) - r = a.__mul__(b, context=self) - if r is NotImplemented: - raise TypeError("Unable to convert %s to Decimal" % b) - else: - return r - - def next_minus(self, a): - """Returns the largest representable number smaller than a. - - >>> c = ExtendedContext.copy() - >>> c.Emin = -999 - >>> c.Emax = 999 - >>> ExtendedContext.next_minus(Decimal('1')) - Decimal('0.999999999') - >>> c.next_minus(Decimal('1E-1007')) - Decimal('0E-1007') - >>> ExtendedContext.next_minus(Decimal('-1.00000003')) - Decimal('-1.00000004') - >>> c.next_minus(Decimal('Infinity')) - Decimal('9.99999999E+999') - >>> c.next_minus(1) - Decimal('0.999999999') - """ - a = _convert_other(a, raiseit=True) - return a.next_minus(context=self) - - def next_plus(self, a): - """Returns the smallest representable number larger than a. - - >>> c = ExtendedContext.copy() - >>> c.Emin = -999 - >>> c.Emax = 999 - >>> ExtendedContext.next_plus(Decimal('1')) - Decimal('1.00000001') - >>> c.next_plus(Decimal('-1E-1007')) - Decimal('-0E-1007') - >>> ExtendedContext.next_plus(Decimal('-1.00000003')) - Decimal('-1.00000002') - >>> c.next_plus(Decimal('-Infinity')) - Decimal('-9.99999999E+999') - >>> c.next_plus(1) - Decimal('1.00000001') - """ - a = _convert_other(a, raiseit=True) - return a.next_plus(context=self) - - def next_toward(self, a, b): - """Returns the number closest to a, in direction towards b. - - The result is the closest representable number from the first - operand (but not the first operand) that is in the direction - towards the second operand, unless the operands have the same - value. - - >>> c = ExtendedContext.copy() - >>> c.Emin = -999 - >>> c.Emax = 999 - >>> c.next_toward(Decimal('1'), Decimal('2')) - Decimal('1.00000001') - >>> c.next_toward(Decimal('-1E-1007'), Decimal('1')) - Decimal('-0E-1007') - >>> c.next_toward(Decimal('-1.00000003'), Decimal('0')) - Decimal('-1.00000002') - >>> c.next_toward(Decimal('1'), Decimal('0')) - Decimal('0.999999999') - >>> c.next_toward(Decimal('1E-1007'), Decimal('-100')) - Decimal('0E-1007') - >>> c.next_toward(Decimal('-1.00000003'), Decimal('-10')) - Decimal('-1.00000004') - >>> c.next_toward(Decimal('0.00'), Decimal('-0.0000')) - Decimal('-0.00') - >>> c.next_toward(0, 1) - Decimal('1E-1007') - >>> c.next_toward(Decimal(0), 1) - Decimal('1E-1007') - >>> c.next_toward(0, Decimal(1)) - Decimal('1E-1007') - """ - a = _convert_other(a, raiseit=True) - return a.next_toward(b, context=self) - - def normalize(self, a): - """normalize reduces an operand to its simplest form. - - Essentially a plus operation with all trailing zeros removed from the - result. - - >>> ExtendedContext.normalize(Decimal('2.1')) - Decimal('2.1') - >>> ExtendedContext.normalize(Decimal('-2.0')) - Decimal('-2') - >>> ExtendedContext.normalize(Decimal('1.200')) - Decimal('1.2') - >>> ExtendedContext.normalize(Decimal('-120')) - Decimal('-1.2E+2') - >>> ExtendedContext.normalize(Decimal('120.00')) - Decimal('1.2E+2') - >>> ExtendedContext.normalize(Decimal('0.00')) - Decimal('0') - >>> ExtendedContext.normalize(6) - Decimal('6') - """ - a = _convert_other(a, raiseit=True) - return a.normalize(context=self) - - def number_class(self, a): - """Returns an indication of the class of the operand. - - The class is one of the following strings: - -sNaN - -NaN - -Infinity - -Normal - -Subnormal - -Zero - +Zero - +Subnormal - +Normal - +Infinity - - >>> c = ExtendedContext.copy() - >>> c.Emin = -999 - >>> c.Emax = 999 - >>> c.number_class(Decimal('Infinity')) - '+Infinity' - >>> c.number_class(Decimal('1E-10')) - '+Normal' - >>> c.number_class(Decimal('2.50')) - '+Normal' - >>> c.number_class(Decimal('0.1E-999')) - '+Subnormal' - >>> c.number_class(Decimal('0')) - '+Zero' - >>> c.number_class(Decimal('-0')) - '-Zero' - >>> c.number_class(Decimal('-0.1E-999')) - '-Subnormal' - >>> c.number_class(Decimal('-1E-10')) - '-Normal' - >>> c.number_class(Decimal('-2.50')) - '-Normal' - >>> c.number_class(Decimal('-Infinity')) - '-Infinity' - >>> c.number_class(Decimal('NaN')) - 'NaN' - >>> c.number_class(Decimal('-NaN')) - 'NaN' - >>> c.number_class(Decimal('sNaN')) - 'sNaN' - >>> c.number_class(123) - '+Normal' - """ - a = _convert_other(a, raiseit=True) - return a.number_class(context=self) - - def plus(self, a): - """Plus corresponds to unary prefix plus in Python. - - The operation is evaluated using the same rules as add; the - operation plus(a) is calculated as add('0', a) where the '0' - has the same exponent as the operand. - - >>> ExtendedContext.plus(Decimal('1.3')) - Decimal('1.3') - >>> ExtendedContext.plus(Decimal('-1.3')) - Decimal('-1.3') - >>> ExtendedContext.plus(-1) - Decimal('-1') - """ - a = _convert_other(a, raiseit=True) - return a.__pos__(context=self) - - def power(self, a, b, modulo=None): - """Raises a to the power of b, to modulo if given. - - With two arguments, compute a**b. If a is negative then b - must be integral. The result will be inexact unless b is - integral and the result is finite and can be expressed exactly - in 'precision' digits. - - With three arguments, compute (a**b) % modulo. For the - three argument form, the following restrictions on the - arguments hold: - - - all three arguments must be integral - - b must be nonnegative - - at least one of a or b must be nonzero - - modulo must be nonzero and have at most 'precision' digits - - The result of pow(a, b, modulo) is identical to the result - that would be obtained by computing (a**b) % modulo with - unbounded precision, but is computed more efficiently. It is - always exact. - - >>> c = ExtendedContext.copy() - >>> c.Emin = -999 - >>> c.Emax = 999 - >>> c.power(Decimal('2'), Decimal('3')) - Decimal('8') - >>> c.power(Decimal('-2'), Decimal('3')) - Decimal('-8') - >>> c.power(Decimal('2'), Decimal('-3')) - Decimal('0.125') - >>> c.power(Decimal('1.7'), Decimal('8')) - Decimal('69.7575744') - >>> c.power(Decimal('10'), Decimal('0.301029996')) - Decimal('2.00000000') - >>> c.power(Decimal('Infinity'), Decimal('-1')) - Decimal('0') - >>> c.power(Decimal('Infinity'), Decimal('0')) - Decimal('1') - >>> c.power(Decimal('Infinity'), Decimal('1')) - Decimal('Infinity') - >>> c.power(Decimal('-Infinity'), Decimal('-1')) - Decimal('-0') - >>> c.power(Decimal('-Infinity'), Decimal('0')) - Decimal('1') - >>> c.power(Decimal('-Infinity'), Decimal('1')) - Decimal('-Infinity') - >>> c.power(Decimal('-Infinity'), Decimal('2')) - Decimal('Infinity') - >>> c.power(Decimal('0'), Decimal('0')) - Decimal('NaN') - - >>> c.power(Decimal('3'), Decimal('7'), Decimal('16')) - Decimal('11') - >>> c.power(Decimal('-3'), Decimal('7'), Decimal('16')) - Decimal('-11') - >>> c.power(Decimal('-3'), Decimal('8'), Decimal('16')) - Decimal('1') - >>> c.power(Decimal('3'), Decimal('7'), Decimal('-16')) - Decimal('11') - >>> c.power(Decimal('23E12345'), Decimal('67E189'), Decimal('123456789')) - Decimal('11729830') - >>> c.power(Decimal('-0'), Decimal('17'), Decimal('1729')) - Decimal('-0') - >>> c.power(Decimal('-23'), Decimal('0'), Decimal('65537')) - Decimal('1') - >>> ExtendedContext.power(7, 7) - Decimal('823543') - >>> ExtendedContext.power(Decimal(7), 7) - Decimal('823543') - >>> ExtendedContext.power(7, Decimal(7), 2) - Decimal('1') - """ - a = _convert_other(a, raiseit=True) - r = a.__pow__(b, modulo, context=self) - if r is NotImplemented: - raise TypeError("Unable to convert %s to Decimal" % b) - else: - return r - - def quantize(self, a, b): - """Returns a value equal to 'a' (rounded), having the exponent of 'b'. - - The coefficient of the result is derived from that of the left-hand - operand. It may be rounded using the current rounding setting (if the - exponent is being increased), multiplied by a positive power of ten (if - the exponent is being decreased), or is unchanged (if the exponent is - already equal to that of the right-hand operand). - - Unlike other operations, if the length of the coefficient after the - quantize operation would be greater than precision then an Invalid - operation condition is raised. This guarantees that, unless there is - an error condition, the exponent of the result of a quantize is always - equal to that of the right-hand operand. - - Also unlike other operations, quantize will never raise Underflow, even - if the result is subnormal and inexact. - - >>> ExtendedContext.quantize(Decimal('2.17'), Decimal('0.001')) - Decimal('2.170') - >>> ExtendedContext.quantize(Decimal('2.17'), Decimal('0.01')) - Decimal('2.17') - >>> ExtendedContext.quantize(Decimal('2.17'), Decimal('0.1')) - Decimal('2.2') - >>> ExtendedContext.quantize(Decimal('2.17'), Decimal('1e+0')) - Decimal('2') - >>> ExtendedContext.quantize(Decimal('2.17'), Decimal('1e+1')) - Decimal('0E+1') - >>> ExtendedContext.quantize(Decimal('-Inf'), Decimal('Infinity')) - Decimal('-Infinity') - >>> ExtendedContext.quantize(Decimal('2'), Decimal('Infinity')) - Decimal('NaN') - >>> ExtendedContext.quantize(Decimal('-0.1'), Decimal('1')) - Decimal('-0') - >>> ExtendedContext.quantize(Decimal('-0'), Decimal('1e+5')) - Decimal('-0E+5') - >>> ExtendedContext.quantize(Decimal('+35236450.6'), Decimal('1e-2')) - Decimal('NaN') - >>> ExtendedContext.quantize(Decimal('-35236450.6'), Decimal('1e-2')) - Decimal('NaN') - >>> ExtendedContext.quantize(Decimal('217'), Decimal('1e-1')) - Decimal('217.0') - >>> ExtendedContext.quantize(Decimal('217'), Decimal('1e-0')) - Decimal('217') - >>> ExtendedContext.quantize(Decimal('217'), Decimal('1e+1')) - Decimal('2.2E+2') - >>> ExtendedContext.quantize(Decimal('217'), Decimal('1e+2')) - Decimal('2E+2') - >>> ExtendedContext.quantize(1, 2) - Decimal('1') - >>> ExtendedContext.quantize(Decimal(1), 2) - Decimal('1') - >>> ExtendedContext.quantize(1, Decimal(2)) - Decimal('1') - """ - a = _convert_other(a, raiseit=True) - return a.quantize(b, context=self) - - def radix(self): - """Just returns 10, as this is Decimal, :) - - >>> ExtendedContext.radix() - Decimal('10') - """ - return Decimal(10) - - def remainder(self, a, b): - """Returns the remainder from integer division. - - The result is the residue of the dividend after the operation of - calculating integer division as described for divide-integer, rounded - to precision digits if necessary. The sign of the result, if - non-zero, is the same as that of the original dividend. - - This operation will fail under the same conditions as integer division - (that is, if integer division on the same two operands would fail, the - remainder cannot be calculated). - - >>> ExtendedContext.remainder(Decimal('2.1'), Decimal('3')) - Decimal('2.1') - >>> ExtendedContext.remainder(Decimal('10'), Decimal('3')) - Decimal('1') - >>> ExtendedContext.remainder(Decimal('-10'), Decimal('3')) - Decimal('-1') - >>> ExtendedContext.remainder(Decimal('10.2'), Decimal('1')) - Decimal('0.2') - >>> ExtendedContext.remainder(Decimal('10'), Decimal('0.3')) - Decimal('0.1') - >>> ExtendedContext.remainder(Decimal('3.6'), Decimal('1.3')) - Decimal('1.0') - >>> ExtendedContext.remainder(22, 6) - Decimal('4') - >>> ExtendedContext.remainder(Decimal(22), 6) - Decimal('4') - >>> ExtendedContext.remainder(22, Decimal(6)) - Decimal('4') - """ - a = _convert_other(a, raiseit=True) - r = a.__mod__(b, context=self) - if r is NotImplemented: - raise TypeError("Unable to convert %s to Decimal" % b) - else: - return r - - def remainder_near(self, a, b): - """Returns to be "a - b * n", where n is the integer nearest the exact - value of "x / b" (if two integers are equally near then the even one - is chosen). If the result is equal to 0 then its sign will be the - sign of a. - - This operation will fail under the same conditions as integer division - (that is, if integer division on the same two operands would fail, the - remainder cannot be calculated). - - >>> ExtendedContext.remainder_near(Decimal('2.1'), Decimal('3')) - Decimal('-0.9') - >>> ExtendedContext.remainder_near(Decimal('10'), Decimal('6')) - Decimal('-2') - >>> ExtendedContext.remainder_near(Decimal('10'), Decimal('3')) - Decimal('1') - >>> ExtendedContext.remainder_near(Decimal('-10'), Decimal('3')) - Decimal('-1') - >>> ExtendedContext.remainder_near(Decimal('10.2'), Decimal('1')) - Decimal('0.2') - >>> ExtendedContext.remainder_near(Decimal('10'), Decimal('0.3')) - Decimal('0.1') - >>> ExtendedContext.remainder_near(Decimal('3.6'), Decimal('1.3')) - Decimal('-0.3') - >>> ExtendedContext.remainder_near(3, 11) - Decimal('3') - >>> ExtendedContext.remainder_near(Decimal(3), 11) - Decimal('3') - >>> ExtendedContext.remainder_near(3, Decimal(11)) - Decimal('3') - """ - a = _convert_other(a, raiseit=True) - return a.remainder_near(b, context=self) - - def rotate(self, a, b): - """Returns a rotated copy of a, b times. - - The coefficient of the result is a rotated copy of the digits in - the coefficient of the first operand. The number of places of - rotation is taken from the absolute value of the second operand, - with the rotation being to the left if the second operand is - positive or to the right otherwise. - - >>> ExtendedContext.rotate(Decimal('34'), Decimal('8')) - Decimal('400000003') - >>> ExtendedContext.rotate(Decimal('12'), Decimal('9')) - Decimal('12') - >>> ExtendedContext.rotate(Decimal('123456789'), Decimal('-2')) - Decimal('891234567') - >>> ExtendedContext.rotate(Decimal('123456789'), Decimal('0')) - Decimal('123456789') - >>> ExtendedContext.rotate(Decimal('123456789'), Decimal('+2')) - Decimal('345678912') - >>> ExtendedContext.rotate(1333333, 1) - Decimal('13333330') - >>> ExtendedContext.rotate(Decimal(1333333), 1) - Decimal('13333330') - >>> ExtendedContext.rotate(1333333, Decimal(1)) - Decimal('13333330') - """ - a = _convert_other(a, raiseit=True) - return a.rotate(b, context=self) - - def same_quantum(self, a, b): - """Returns True if the two operands have the same exponent. - - The result is never affected by either the sign or the coefficient of - either operand. - - >>> ExtendedContext.same_quantum(Decimal('2.17'), Decimal('0.001')) - False - >>> ExtendedContext.same_quantum(Decimal('2.17'), Decimal('0.01')) - True - >>> ExtendedContext.same_quantum(Decimal('2.17'), Decimal('1')) - False - >>> ExtendedContext.same_quantum(Decimal('Inf'), Decimal('-Inf')) - True - >>> ExtendedContext.same_quantum(10000, -1) - True - >>> ExtendedContext.same_quantum(Decimal(10000), -1) - True - >>> ExtendedContext.same_quantum(10000, Decimal(-1)) - True - """ - a = _convert_other(a, raiseit=True) - return a.same_quantum(b) - - def scaleb (self, a, b): - """Returns the first operand after adding the second value its exp. - - >>> ExtendedContext.scaleb(Decimal('7.50'), Decimal('-2')) - Decimal('0.0750') - >>> ExtendedContext.scaleb(Decimal('7.50'), Decimal('0')) - Decimal('7.50') - >>> ExtendedContext.scaleb(Decimal('7.50'), Decimal('3')) - Decimal('7.50E+3') - >>> ExtendedContext.scaleb(1, 4) - Decimal('1E+4') - >>> ExtendedContext.scaleb(Decimal(1), 4) - Decimal('1E+4') - >>> ExtendedContext.scaleb(1, Decimal(4)) - Decimal('1E+4') - """ - a = _convert_other(a, raiseit=True) - return a.scaleb(b, context=self) - - def shift(self, a, b): - """Returns a shifted copy of a, b times. - - The coefficient of the result is a shifted copy of the digits - in the coefficient of the first operand. The number of places - to shift is taken from the absolute value of the second operand, - with the shift being to the left if the second operand is - positive or to the right otherwise. Digits shifted into the - coefficient are zeros. - - >>> ExtendedContext.shift(Decimal('34'), Decimal('8')) - Decimal('400000000') - >>> ExtendedContext.shift(Decimal('12'), Decimal('9')) - Decimal('0') - >>> ExtendedContext.shift(Decimal('123456789'), Decimal('-2')) - Decimal('1234567') - >>> ExtendedContext.shift(Decimal('123456789'), Decimal('0')) - Decimal('123456789') - >>> ExtendedContext.shift(Decimal('123456789'), Decimal('+2')) - Decimal('345678900') - >>> ExtendedContext.shift(88888888, 2) - Decimal('888888800') - >>> ExtendedContext.shift(Decimal(88888888), 2) - Decimal('888888800') - >>> ExtendedContext.shift(88888888, Decimal(2)) - Decimal('888888800') - """ - a = _convert_other(a, raiseit=True) - return a.shift(b, context=self) - - def sqrt(self, a): - """Square root of a non-negative number to context precision. - - If the result must be inexact, it is rounded using the round-half-even - algorithm. - - >>> ExtendedContext.sqrt(Decimal('0')) - Decimal('0') - >>> ExtendedContext.sqrt(Decimal('-0')) - Decimal('-0') - >>> ExtendedContext.sqrt(Decimal('0.39')) - Decimal('0.624499800') - >>> ExtendedContext.sqrt(Decimal('100')) - Decimal('10') - >>> ExtendedContext.sqrt(Decimal('1')) - Decimal('1') - >>> ExtendedContext.sqrt(Decimal('1.0')) - Decimal('1.0') - >>> ExtendedContext.sqrt(Decimal('1.00')) - Decimal('1.0') - >>> ExtendedContext.sqrt(Decimal('7')) - Decimal('2.64575131') - >>> ExtendedContext.sqrt(Decimal('10')) - Decimal('3.16227766') - >>> ExtendedContext.sqrt(2) - Decimal('1.41421356') - >>> ExtendedContext.prec - 9 - """ - a = _convert_other(a, raiseit=True) - return a.sqrt(context=self) - - def subtract(self, a, b): - """Return the difference between the two operands. - - >>> ExtendedContext.subtract(Decimal('1.3'), Decimal('1.07')) - Decimal('0.23') - >>> ExtendedContext.subtract(Decimal('1.3'), Decimal('1.30')) - Decimal('0.00') - >>> ExtendedContext.subtract(Decimal('1.3'), Decimal('2.07')) - Decimal('-0.77') - >>> ExtendedContext.subtract(8, 5) - Decimal('3') - >>> ExtendedContext.subtract(Decimal(8), 5) - Decimal('3') - >>> ExtendedContext.subtract(8, Decimal(5)) - Decimal('3') - """ - a = _convert_other(a, raiseit=True) - r = a.__sub__(b, context=self) - if r is NotImplemented: - raise TypeError("Unable to convert %s to Decimal" % b) - else: - return r - - def to_eng_string(self, a): - """Converts a number to a string, using scientific notation. - - The operation is not affected by the context. - """ - a = _convert_other(a, raiseit=True) - return a.to_eng_string(context=self) - - def to_sci_string(self, a): - """Converts a number to a string, using scientific notation. - - The operation is not affected by the context. - """ - a = _convert_other(a, raiseit=True) - return a.__str__(context=self) - - def to_integral_exact(self, a): - """Rounds to an integer. - - When the operand has a negative exponent, the result is the same - as using the quantize() operation using the given operand as the - left-hand-operand, 1E+0 as the right-hand-operand, and the precision - of the operand as the precision setting; Inexact and Rounded flags - are allowed in this operation. The rounding mode is taken from the - context. - - >>> ExtendedContext.to_integral_exact(Decimal('2.1')) - Decimal('2') - >>> ExtendedContext.to_integral_exact(Decimal('100')) - Decimal('100') - >>> ExtendedContext.to_integral_exact(Decimal('100.0')) - Decimal('100') - >>> ExtendedContext.to_integral_exact(Decimal('101.5')) - Decimal('102') - >>> ExtendedContext.to_integral_exact(Decimal('-101.5')) - Decimal('-102') - >>> ExtendedContext.to_integral_exact(Decimal('10E+5')) - Decimal('1.0E+6') - >>> ExtendedContext.to_integral_exact(Decimal('7.89E+77')) - Decimal('7.89E+77') - >>> ExtendedContext.to_integral_exact(Decimal('-Inf')) - Decimal('-Infinity') - """ - a = _convert_other(a, raiseit=True) - return a.to_integral_exact(context=self) - - def to_integral_value(self, a): - """Rounds to an integer. - - When the operand has a negative exponent, the result is the same - as using the quantize() operation using the given operand as the - left-hand-operand, 1E+0 as the right-hand-operand, and the precision - of the operand as the precision setting, except that no flags will - be set. The rounding mode is taken from the context. - - >>> ExtendedContext.to_integral_value(Decimal('2.1')) - Decimal('2') - >>> ExtendedContext.to_integral_value(Decimal('100')) - Decimal('100') - >>> ExtendedContext.to_integral_value(Decimal('100.0')) - Decimal('100') - >>> ExtendedContext.to_integral_value(Decimal('101.5')) - Decimal('102') - >>> ExtendedContext.to_integral_value(Decimal('-101.5')) - Decimal('-102') - >>> ExtendedContext.to_integral_value(Decimal('10E+5')) - Decimal('1.0E+6') - >>> ExtendedContext.to_integral_value(Decimal('7.89E+77')) - Decimal('7.89E+77') - >>> ExtendedContext.to_integral_value(Decimal('-Inf')) - Decimal('-Infinity') - """ - a = _convert_other(a, raiseit=True) - return a.to_integral_value(context=self) - - # the method name changed, but we provide also the old one, for compatibility - to_integral = to_integral_value - -class _WorkRep(object): - __slots__ = ('sign','int','exp') - # sign: 0 or 1 - # int: int - # exp: None, int, or string - - def __init__(self, value=None): - if value is None: - self.sign = None - self.int = 0 - self.exp = None - elif isinstance(value, Decimal): - self.sign = value._sign - self.int = int(value._int) - self.exp = value._exp - else: - # assert isinstance(value, tuple) - self.sign = value[0] - self.int = value[1] - self.exp = value[2] - - def __repr__(self): - return "(%r, %r, %r)" % (self.sign, self.int, self.exp) - - __str__ = __repr__ - - - -def _normalize(op1, op2, prec = 0): - """Normalizes op1, op2 to have the same exp and length of coefficient. - - Done during addition. - """ - if op1.exp < op2.exp: - tmp = op2 - other = op1 - else: - tmp = op1 - other = op2 - - # Let exp = min(tmp.exp - 1, tmp.adjusted() - precision - 1). - # Then adding 10**exp to tmp has the same effect (after rounding) - # as adding any positive quantity smaller than 10**exp; similarly - # for subtraction. So if other is smaller than 10**exp we replace - # it with 10**exp. This avoids tmp.exp - other.exp getting too large. - tmp_len = len(str(tmp.int)) - other_len = len(str(other.int)) - exp = tmp.exp + min(-1, tmp_len - prec - 2) - if other_len + other.exp - 1 < exp: - other.int = 1 - other.exp = exp - - tmp.int *= 10 ** (tmp.exp - other.exp) - tmp.exp = other.exp - return op1, op2 - -##### Integer arithmetic functions used by ln, log10, exp and __pow__ ##### - -_nbits = int.bit_length - -def _decimal_lshift_exact(n, e): - """ Given integers n and e, return n * 10**e if it's an integer, else None. - - The computation is designed to avoid computing large powers of 10 - unnecessarily. - - >>> _decimal_lshift_exact(3, 4) - 30000 - >>> _decimal_lshift_exact(300, -999999999) # returns None - - """ - if n == 0: - return 0 - elif e >= 0: - return n * 10**e - else: - # val_n = largest power of 10 dividing n. - str_n = str(abs(n)) - val_n = len(str_n) - len(str_n.rstrip('0')) - return None if val_n < -e else n // 10**-e - -def _sqrt_nearest(n, a): - """Closest integer to the square root of the positive integer n. a is - an initial approximation to the square root. Any positive integer - will do for a, but the closer a is to the square root of n the - faster convergence will be. - - """ - if n <= 0 or a <= 0: - raise ValueError("Both arguments to _sqrt_nearest should be positive.") - - b=0 - while a != b: - b, a = a, a--n//a>>1 - return a - -def _rshift_nearest(x, shift): - """Given an integer x and a nonnegative integer shift, return closest - integer to x / 2**shift; use round-to-even in case of a tie. - - """ - b, q = 1 << shift, x >> shift - return q + (2*(x & (b-1)) + (q&1) > b) - -def _div_nearest(a, b): - """Closest integer to a/b, a and b positive integers; rounds to even - in the case of a tie. - - """ - q, r = divmod(a, b) - return q + (2*r + (q&1) > b) - -def _ilog(x, M, L = 8): - """Integer approximation to M*log(x/M), with absolute error boundable - in terms only of x/M. - - Given positive integers x and M, return an integer approximation to - M * log(x/M). For L = 8 and 0.1 <= x/M <= 10 the difference - between the approximation and the exact result is at most 22. For - L = 8 and 1.0 <= x/M <= 10.0 the difference is at most 15. In - both cases these are upper bounds on the error; it will usually be - much smaller.""" - - # The basic algorithm is the following: let log1p be the function - # log1p(x) = log(1+x). Then log(x/M) = log1p((x-M)/M). We use - # the reduction - # - # log1p(y) = 2*log1p(y/(1+sqrt(1+y))) - # - # repeatedly until the argument to log1p is small (< 2**-L in - # absolute value). For small y we can use the Taylor series - # expansion - # - # log1p(y) ~ y - y**2/2 + y**3/3 - ... - (-y)**T/T - # - # truncating at T such that y**T is small enough. The whole - # computation is carried out in a form of fixed-point arithmetic, - # with a real number z being represented by an integer - # approximation to z*M. To avoid loss of precision, the y below - # is actually an integer approximation to 2**R*y*M, where R is the - # number of reductions performed so far. - - y = x-M - # argument reduction; R = number of reductions performed - R = 0 - while (R <= L and abs(y) << L-R >= M or - R > L and abs(y) >> R-L >= M): - y = _div_nearest((M*y) << 1, - M + _sqrt_nearest(M*(M+_rshift_nearest(y, R)), M)) - R += 1 - - # Taylor series with T terms - T = -int(-10*len(str(M))//(3*L)) - yshift = _rshift_nearest(y, R) - w = _div_nearest(M, T) - for k in range(T-1, 0, -1): - w = _div_nearest(M, k) - _div_nearest(yshift*w, M) - - return _div_nearest(w*y, M) - -def _dlog10(c, e, p): - """Given integers c, e and p with c > 0, p >= 0, compute an integer - approximation to 10**p * log10(c*10**e), with an absolute error of - at most 1. Assumes that c*10**e is not exactly 1.""" - - # increase precision by 2; compensate for this by dividing - # final result by 100 - p += 2 - - # write c*10**e as d*10**f with either: - # f >= 0 and 1 <= d <= 10, or - # f <= 0 and 0.1 <= d <= 1. - # Thus for c*10**e close to 1, f = 0 - l = len(str(c)) - f = e+l - (e+l >= 1) - - if p > 0: - M = 10**p - k = e+p-f - if k >= 0: - c *= 10**k - else: - c = _div_nearest(c, 10**-k) - - log_d = _ilog(c, M) # error < 5 + 22 = 27 - log_10 = _log10_digits(p) # error < 1 - log_d = _div_nearest(log_d*M, log_10) - log_tenpower = f*M # exact - else: - log_d = 0 # error < 2.31 - log_tenpower = _div_nearest(f, 10**-p) # error < 0.5 - - return _div_nearest(log_tenpower+log_d, 100) - -def _dlog(c, e, p): - """Given integers c, e and p with c > 0, compute an integer - approximation to 10**p * log(c*10**e), with an absolute error of - at most 1. Assumes that c*10**e is not exactly 1.""" - - # Increase precision by 2. The precision increase is compensated - # for at the end with a division by 100. - p += 2 - - # rewrite c*10**e as d*10**f with either f >= 0 and 1 <= d <= 10, - # or f <= 0 and 0.1 <= d <= 1. Then we can compute 10**p * log(c*10**e) - # as 10**p * log(d) + 10**p*f * log(10). - l = len(str(c)) - f = e+l - (e+l >= 1) - - # compute approximation to 10**p*log(d), with error < 27 - if p > 0: - k = e+p-f - if k >= 0: - c *= 10**k - else: - c = _div_nearest(c, 10**-k) # error of <= 0.5 in c - - # _ilog magnifies existing error in c by a factor of at most 10 - log_d = _ilog(c, 10**p) # error < 5 + 22 = 27 - else: - # p <= 0: just approximate the whole thing by 0; error < 2.31 - log_d = 0 - - # compute approximation to f*10**p*log(10), with error < 11. - if f: - extra = len(str(abs(f)))-1 - if p + extra >= 0: - # error in f * _log10_digits(p+extra) < |f| * 1 = |f| - # after division, error < |f|/10**extra + 0.5 < 10 + 0.5 < 11 - f_log_ten = _div_nearest(f*_log10_digits(p+extra), 10**extra) - else: - f_log_ten = 0 - else: - f_log_ten = 0 - - # error in sum < 11+27 = 38; error after division < 0.38 + 0.5 < 1 - return _div_nearest(f_log_ten + log_d, 100) - -class _Log10Memoize(object): - """Class to compute, store, and allow retrieval of, digits of the - constant log(10) = 2.302585.... This constant is needed by - Decimal.ln, Decimal.log10, Decimal.exp and Decimal.__pow__.""" - def __init__(self): - self.digits = "23025850929940456840179914546843642076011014886" - - def getdigits(self, p): - """Given an integer p >= 0, return floor(10**p)*log(10). - - For example, self.getdigits(3) returns 2302. - """ - # digits are stored as a string, for quick conversion to - # integer in the case that we've already computed enough - # digits; the stored digits should always be correct - # (truncated, not rounded to nearest). - if p < 0: - raise ValueError("p should be nonnegative") - - if p >= len(self.digits): - # compute p+3, p+6, p+9, ... digits; continue until at - # least one of the extra digits is nonzero - extra = 3 - while True: - # compute p+extra digits, correct to within 1ulp - M = 10**(p+extra+2) - digits = str(_div_nearest(_ilog(10*M, M), 100)) - if digits[-extra:] != '0'*extra: - break - extra += 3 - # keep all reliable digits so far; remove trailing zeros - # and next nonzero digit - self.digits = digits.rstrip('0')[:-1] - return int(self.digits[:p+1]) - -_log10_digits = _Log10Memoize().getdigits - -def _iexp(x, M, L=8): - """Given integers x and M, M > 0, such that x/M is small in absolute - value, compute an integer approximation to M*exp(x/M). For 0 <= - x/M <= 2.4, the absolute error in the result is bounded by 60 (and - is usually much smaller).""" - - # Algorithm: to compute exp(z) for a real number z, first divide z - # by a suitable power R of 2 so that |z/2**R| < 2**-L. Then - # compute expm1(z/2**R) = exp(z/2**R) - 1 using the usual Taylor - # series - # - # expm1(x) = x + x**2/2! + x**3/3! + ... - # - # Now use the identity - # - # expm1(2x) = expm1(x)*(expm1(x)+2) - # - # R times to compute the sequence expm1(z/2**R), - # expm1(z/2**(R-1)), ... , exp(z/2), exp(z). - - # Find R such that x/2**R/M <= 2**-L - R = _nbits((x<<L)//M) - - # Taylor series. (2**L)**T > M - T = -int(-10*len(str(M))//(3*L)) - y = _div_nearest(x, T) - Mshift = M<<R - for i in range(T-1, 0, -1): - y = _div_nearest(x*(Mshift + y), Mshift * i) - - # Expansion - for k in range(R-1, -1, -1): - Mshift = M<<(k+2) - y = _div_nearest(y*(y+Mshift), Mshift) - - return M+y - -def _dexp(c, e, p): - """Compute an approximation to exp(c*10**e), with p decimal places of - precision. - - Returns integers d, f such that: - - 10**(p-1) <= d <= 10**p, and - (d-1)*10**f < exp(c*10**e) < (d+1)*10**f - - In other words, d*10**f is an approximation to exp(c*10**e) with p - digits of precision, and with an error in d of at most 1. This is - almost, but not quite, the same as the error being < 1ulp: when d - = 10**(p-1) the error could be up to 10 ulp.""" - - # we'll call iexp with M = 10**(p+2), giving p+3 digits of precision - p += 2 - - # compute log(10) with extra precision = adjusted exponent of c*10**e - extra = max(0, e + len(str(c)) - 1) - q = p + extra - - # compute quotient c*10**e/(log(10)) = c*10**(e+q)/(log(10)*10**q), - # rounding down - shift = e+q - if shift >= 0: - cshift = c*10**shift - else: - cshift = c//10**-shift - quot, rem = divmod(cshift, _log10_digits(q)) - - # reduce remainder back to original precision - rem = _div_nearest(rem, 10**extra) - - # error in result of _iexp < 120; error after division < 0.62 - return _div_nearest(_iexp(rem, 10**p), 1000), quot - p + 3 - -def _dpower(xc, xe, yc, ye, p): - """Given integers xc, xe, yc and ye representing Decimals x = xc*10**xe and - y = yc*10**ye, compute x**y. Returns a pair of integers (c, e) such that: - - 10**(p-1) <= c <= 10**p, and - (c-1)*10**e < x**y < (c+1)*10**e - - in other words, c*10**e is an approximation to x**y with p digits - of precision, and with an error in c of at most 1. (This is - almost, but not quite, the same as the error being < 1ulp: when c - == 10**(p-1) we can only guarantee error < 10ulp.) - - We assume that: x is positive and not equal to 1, and y is nonzero. - """ - - # Find b such that 10**(b-1) <= |y| <= 10**b - b = len(str(abs(yc))) + ye - - # log(x) = lxc*10**(-p-b-1), to p+b+1 places after the decimal point - lxc = _dlog(xc, xe, p+b+1) - - # compute product y*log(x) = yc*lxc*10**(-p-b-1+ye) = pc*10**(-p-1) - shift = ye-b - if shift >= 0: - pc = lxc*yc*10**shift - else: - pc = _div_nearest(lxc*yc, 10**-shift) - - if pc == 0: - # we prefer a result that isn't exactly 1; this makes it - # easier to compute a correctly rounded result in __pow__ - if ((len(str(xc)) + xe >= 1) == (yc > 0)): # if x**y > 1: - coeff, exp = 10**(p-1)+1, 1-p - else: - coeff, exp = 10**p-1, -p - else: - coeff, exp = _dexp(pc, -(p+1), p+1) - coeff = _div_nearest(coeff, 10) - exp += 1 - - return coeff, exp - -def _log10_lb(c, correction = { - '1': 100, '2': 70, '3': 53, '4': 40, '5': 31, - '6': 23, '7': 16, '8': 10, '9': 5}): - """Compute a lower bound for 100*log10(c) for a positive integer c.""" - if c <= 0: - raise ValueError("The argument to _log10_lb should be nonnegative.") - str_c = str(c) - return 100*len(str_c) - correction[str_c[0]] - -##### Helper Functions #################################################### - -def _convert_other(other, raiseit=False, allow_float=False): - """Convert other to Decimal. - - Verifies that it's ok to use in an implicit construction. - If allow_float is true, allow conversion from float; this - is used in the comparison methods (__eq__ and friends). - - """ - if isinstance(other, Decimal): - return other - if isinstance(other, int): - return Decimal(other) - if allow_float and isinstance(other, float): - return Decimal.from_float(other) - - if raiseit: - raise TypeError("Unable to convert %s to Decimal" % other) - return NotImplemented - -def _convert_for_comparison(self, other, equality_op=False): - """Given a Decimal instance self and a Python object other, return - a pair (s, o) of Decimal instances such that "s op o" is - equivalent to "self op other" for any of the 6 comparison - operators "op". - - """ - if isinstance(other, Decimal): - return self, other - - # Comparison with a Rational instance (also includes integers): - # self op n/d <=> self*d op n (for n and d integers, d positive). - # A NaN or infinity can be left unchanged without affecting the - # comparison result. - if isinstance(other, _numbers.Rational): - if not self._is_special: - self = _dec_from_triple(self._sign, - str(int(self._int) * other.denominator), - self._exp) - return self, Decimal(other.numerator) - - # Comparisons with float and complex types. == and != comparisons - # with complex numbers should succeed, returning either True or False - # as appropriate. Other comparisons return NotImplemented. - if equality_op and isinstance(other, _numbers.Complex) and other.imag == 0: - other = other.real - if isinstance(other, float): - context = getcontext() - if equality_op: - context.flags[FloatOperation] = 1 - else: - context._raise_error(FloatOperation, - "strict semantics for mixing floats and Decimals are enabled") - return self, Decimal.from_float(other) - return NotImplemented, NotImplemented - - -##### Setup Specific Contexts ############################################ - -# The default context prototype used by Context() -# Is mutable, so that new contexts can have different default values - -DefaultContext = Context( - prec=28, rounding=ROUND_HALF_EVEN, - traps=[DivisionByZero, Overflow, InvalidOperation], - flags=[], - Emax=999999, - Emin=-999999, - capitals=1, - clamp=0 -) - -# Pre-made alternate contexts offered by the specification -# Don't change these; the user should be able to select these -# contexts and be able to reproduce results from other implementations -# of the spec. - -BasicContext = Context( - prec=9, rounding=ROUND_HALF_UP, - traps=[DivisionByZero, Overflow, InvalidOperation, Clamped, Underflow], - flags=[], -) - -ExtendedContext = Context( - prec=9, rounding=ROUND_HALF_EVEN, - traps=[], - flags=[], -) - - -##### crud for parsing strings ############################################# -# -# Regular expression used for parsing numeric strings. Additional -# comments: -# -# 1. Uncomment the two '\s*' lines to allow leading and/or trailing -# whitespace. But note that the specification disallows whitespace in -# a numeric string. -# -# 2. For finite numbers (not infinities and NaNs) the body of the -# number between the optional sign and the optional exponent must have -# at least one decimal digit, possibly after the decimal point. The -# lookahead expression '(?=\d|\.\d)' checks this. - -import re -_parser = re.compile(r""" # A numeric string consists of: -# \s* - (?P<sign>[-+])? # an optional sign, followed by either... - ( - (?=\d|\.\d) # ...a number (with at least one digit) - (?P<int>\d*) # having a (possibly empty) integer part - (\.(?P<frac>\d*))? # followed by an optional fractional part - (E(?P<exp>[-+]?\d+))? # followed by an optional exponent, or... - | - Inf(inity)? # ...an infinity, or... - | - (?P<signal>s)? # ...an (optionally signaling) - NaN # NaN - (?P<diag>\d*) # with (possibly empty) diagnostic info. - ) -# \s* - \Z -""", re.VERBOSE | re.IGNORECASE).match - -_all_zeros = re.compile('0*$').match -_exact_half = re.compile('50*$').match - -##### PEP3101 support functions ############################################## -# The functions in this section have little to do with the Decimal -# class, and could potentially be reused or adapted for other pure -# Python numeric classes that want to implement __format__ -# -# A format specifier for Decimal looks like: -# -# [[fill]align][sign][#][0][minimumwidth][,][.precision][type] - -_parse_format_specifier_regex = re.compile(r"""\A -(?: - (?P<fill>.)? - (?P<align>[<>=^]) -)? -(?P<sign>[-+ ])? -(?P<alt>\#)? -(?P<zeropad>0)? -(?P<minimumwidth>(?!0)\d+)? -(?P<thousands_sep>,)? -(?:\.(?P<precision>0|(?!0)\d+))? -(?P<type>[eEfFgGn%])? -\Z -""", re.VERBOSE|re.DOTALL) - -del re - -# The locale module is only needed for the 'n' format specifier. The -# rest of the PEP 3101 code functions quite happily without it, so we -# don't care too much if locale isn't present. -try: - import locale as _locale -except ImportError: - pass - -def _parse_format_specifier(format_spec, _localeconv=None): - """Parse and validate a format specifier. - - Turns a standard numeric format specifier into a dict, with the - following entries: - - fill: fill character to pad field to minimum width - align: alignment type, either '<', '>', '=' or '^' - sign: either '+', '-' or ' ' - minimumwidth: nonnegative integer giving minimum width - zeropad: boolean, indicating whether to pad with zeros - thousands_sep: string to use as thousands separator, or '' - grouping: grouping for thousands separators, in format - used by localeconv - decimal_point: string to use for decimal point - precision: nonnegative integer giving precision, or None - type: one of the characters 'eEfFgG%', or None - - """ - m = _parse_format_specifier_regex.match(format_spec) - if m is None: - raise ValueError("Invalid format specifier: " + format_spec) - - # get the dictionary - format_dict = m.groupdict() - - # zeropad; defaults for fill and alignment. If zero padding - # is requested, the fill and align fields should be absent. - fill = format_dict['fill'] - align = format_dict['align'] - format_dict['zeropad'] = (format_dict['zeropad'] is not None) - if format_dict['zeropad']: - if fill is not None: - raise ValueError("Fill character conflicts with '0'" - " in format specifier: " + format_spec) - if align is not None: - raise ValueError("Alignment conflicts with '0' in " - "format specifier: " + format_spec) - format_dict['fill'] = fill or ' ' - # PEP 3101 originally specified that the default alignment should - # be left; it was later agreed that right-aligned makes more sense - # for numeric types. See http://bugs.python.org/issue6857. - format_dict['align'] = align or '>' - - # default sign handling: '-' for negative, '' for positive - if format_dict['sign'] is None: - format_dict['sign'] = '-' - - # minimumwidth defaults to 0; precision remains None if not given - format_dict['minimumwidth'] = int(format_dict['minimumwidth'] or '0') - if format_dict['precision'] is not None: - format_dict['precision'] = int(format_dict['precision']) - - # if format type is 'g' or 'G' then a precision of 0 makes little - # sense; convert it to 1. Same if format type is unspecified. - if format_dict['precision'] == 0: - if format_dict['type'] is None or format_dict['type'] in 'gGn': - format_dict['precision'] = 1 - - # determine thousands separator, grouping, and decimal separator, and - # add appropriate entries to format_dict - if format_dict['type'] == 'n': - # apart from separators, 'n' behaves just like 'g' - format_dict['type'] = 'g' - if _localeconv is None: - _localeconv = _locale.localeconv() - if format_dict['thousands_sep'] is not None: - raise ValueError("Explicit thousands separator conflicts with " - "'n' type in format specifier: " + format_spec) - format_dict['thousands_sep'] = _localeconv['thousands_sep'] - format_dict['grouping'] = _localeconv['grouping'] - format_dict['decimal_point'] = _localeconv['decimal_point'] - else: - if format_dict['thousands_sep'] is None: - format_dict['thousands_sep'] = '' - format_dict['grouping'] = [3, 0] - format_dict['decimal_point'] = '.' - - return format_dict - -def _format_align(sign, body, spec): - """Given an unpadded, non-aligned numeric string 'body' and sign - string 'sign', add padding and alignment conforming to the given - format specifier dictionary 'spec' (as produced by - parse_format_specifier). - - """ - # how much extra space do we have to play with? - minimumwidth = spec['minimumwidth'] - fill = spec['fill'] - padding = fill*(minimumwidth - len(sign) - len(body)) - - align = spec['align'] - if align == '<': - result = sign + body + padding - elif align == '>': - result = padding + sign + body - elif align == '=': - result = sign + padding + body - elif align == '^': - half = len(padding)//2 - result = padding[:half] + sign + body + padding[half:] - else: - raise ValueError('Unrecognised alignment field') - - return result - -def _group_lengths(grouping): - """Convert a localeconv-style grouping into a (possibly infinite) - iterable of integers representing group lengths. - - """ - # The result from localeconv()['grouping'], and the input to this - # function, should be a list of integers in one of the - # following three forms: - # - # (1) an empty list, or - # (2) nonempty list of positive integers + [0] - # (3) list of positive integers + [locale.CHAR_MAX], or - - from itertools import chain, repeat - if not grouping: - return [] - elif grouping[-1] == 0 and len(grouping) >= 2: - return chain(grouping[:-1], repeat(grouping[-2])) - elif grouping[-1] == _locale.CHAR_MAX: - return grouping[:-1] - else: - raise ValueError('unrecognised format for grouping') - -def _insert_thousands_sep(digits, spec, min_width=1): - """Insert thousands separators into a digit string. - - spec is a dictionary whose keys should include 'thousands_sep' and - 'grouping'; typically it's the result of parsing the format - specifier using _parse_format_specifier. - - The min_width keyword argument gives the minimum length of the - result, which will be padded on the left with zeros if necessary. - - If necessary, the zero padding adds an extra '0' on the left to - avoid a leading thousands separator. For example, inserting - commas every three digits in '123456', with min_width=8, gives - '0,123,456', even though that has length 9. - - """ - - sep = spec['thousands_sep'] - grouping = spec['grouping'] - - groups = [] - for l in _group_lengths(grouping): - if l <= 0: - raise ValueError("group length should be positive") - # max(..., 1) forces at least 1 digit to the left of a separator - l = min(max(len(digits), min_width, 1), l) - groups.append('0'*(l - len(digits)) + digits[-l:]) - digits = digits[:-l] - min_width -= l - if not digits and min_width <= 0: - break - min_width -= len(sep) - else: - l = max(len(digits), min_width, 1) - groups.append('0'*(l - len(digits)) + digits[-l:]) - return sep.join(reversed(groups)) - -def _format_sign(is_negative, spec): - """Determine sign character.""" - - if is_negative: - return '-' - elif spec['sign'] in ' +': - return spec['sign'] - else: - return '' - -def _format_number(is_negative, intpart, fracpart, exp, spec): - """Format a number, given the following data: - - is_negative: true if the number is negative, else false - intpart: string of digits that must appear before the decimal point - fracpart: string of digits that must come after the point - exp: exponent, as an integer - spec: dictionary resulting from parsing the format specifier - - This function uses the information in spec to: - insert separators (decimal separator and thousands separators) - format the sign - format the exponent - add trailing '%' for the '%' type - zero-pad if necessary - fill and align if necessary - """ - - sign = _format_sign(is_negative, spec) - - if fracpart or spec['alt']: - fracpart = spec['decimal_point'] + fracpart - - if exp != 0 or spec['type'] in 'eE': - echar = {'E': 'E', 'e': 'e', 'G': 'E', 'g': 'e'}[spec['type']] - fracpart += "{0}{1:+}".format(echar, exp) - if spec['type'] == '%': - fracpart += '%' - - if spec['zeropad']: - min_width = spec['minimumwidth'] - len(fracpart) - len(sign) - else: - min_width = 0 - intpart = _insert_thousands_sep(intpart, spec, min_width) - - return _format_align(sign, intpart+fracpart, spec) - - -##### Useful Constants (internal use only) ################################ - -# Reusable defaults -_Infinity = Decimal('Inf') -_NegativeInfinity = Decimal('-Inf') -_NaN = Decimal('NaN') -_Zero = Decimal(0) -_One = Decimal(1) -_NegativeOne = Decimal(-1) - -# _SignedInfinity[sign] is infinity w/ that sign -_SignedInfinity = (_Infinity, _NegativeInfinity) - -# Constants related to the hash implementation; hash(x) is based -# on the reduction of x modulo _PyHASH_MODULUS -_PyHASH_MODULUS = sys.hash_info.modulus -# hash values to use for positive and negative infinities, and nans -_PyHASH_INF = sys.hash_info.inf -_PyHASH_NAN = sys.hash_info.nan - -# _PyHASH_10INV is the inverse of 10 modulo the prime _PyHASH_MODULUS -_PyHASH_10INV = pow(10, _PyHASH_MODULUS - 2, _PyHASH_MODULUS) -del sys try: - import _decimal -except ImportError: - pass -else: - s1 = set(dir()) - s2 = set(dir(_decimal)) - for name in s1 - s2: - del globals()[name] - del s1, s2, name from _decimal import * - -if __name__ == '__main__': - import doctest, decimal - doctest.testmod(decimal) + from _decimal import __doc__ + from _decimal import __version__ + from _decimal import __libmpdec_version__ +except ImportError: + from _pydecimal import * + from _pydecimal import __doc__ + from _pydecimal import __version__ + from _pydecimal import __libmpdec_version__ diff --git a/Lib/difflib.py b/Lib/difflib.py index 7eb42a9..ae3479d 100644 --- a/Lib/difflib.py +++ b/Lib/difflib.py @@ -30,7 +30,7 @@ __all__ = ['get_close_matches', 'ndiff', 'restore', 'SequenceMatcher', 'Differ','IS_CHARACTER_JUNK', 'IS_LINE_JUNK', 'context_diff', 'unified_diff', 'HtmlDiff', 'Match'] -import heapq +from heapq import nlargest as _nlargest from collections import namedtuple as _namedtuple Match = _namedtuple('Match', 'a b size') @@ -729,7 +729,7 @@ def get_close_matches(word, possibilities, n=3, cutoff=0.6): result.append((s.ratio(), x)) # Move the best scorers to head of list - result = heapq.nlargest(n, result) + result = _nlargest(n, result) # Strip scores for the best n matches return [x for score, x in result] @@ -852,10 +852,9 @@ class Differ: and return true iff the string is junk. The module-level function `IS_LINE_JUNK` may be used to filter out lines without visible characters, except for at most one splat ('#'). It is recommended - to leave linejunk None; as of Python 2.3, the underlying - SequenceMatcher class has grown an adaptive notion of "noise" lines - that's better than any static definition the author has ever been - able to craft. + to leave linejunk None; the underlying SequenceMatcher class has + an adaptive notion of "noise" lines that's better than any static + definition the author has ever been able to craft. - `charjunk`: A function that should accept a string of length 1. The module-level function `IS_CHARACTER_JUNK` may be used to filter out @@ -1298,17 +1297,18 @@ def ndiff(a, b, linejunk=None, charjunk=IS_CHARACTER_JUNK): Compare `a` and `b` (lists of strings); return a `Differ`-style delta. Optional keyword parameters `linejunk` and `charjunk` are for filter - functions (or None): + functions, or can be None: - - linejunk: A function that should accept a single string argument, and + - linejunk: A function that should accept a single string argument and return true iff the string is junk. The default is None, and is - recommended; as of Python 2.3, an adaptive notion of "noise" lines is - used that does a good job on its own. + recommended; the underlying SequenceMatcher class has an adaptive + notion of "noise" lines. - - charjunk: A function that should accept a string of length 1. The - default is module-level function IS_CHARACTER_JUNK, which filters out - whitespace characters (a blank or tab; note: bad idea to include newline - in this!). + - charjunk: A function that accepts a character (string of length + 1), and returns true iff the character is junk. The default is + the module-level function IS_CHARACTER_JUNK, which filters out + whitespace characters (a blank or tab; note: it's a bad idea to + include newline in this!). Tools/scripts/ndiff.py is a command-line front-end to this function. @@ -1410,7 +1410,7 @@ def _mdiff(fromlines, tolines, context=None, linejunk=None, change_re.sub(record_sub_info,markers) # process each tuple inserting our special marks that won't be # noticed by an xml/html escaper. - for key,(begin,end) in sub_info[::-1]: + for key,(begin,end) in reversed(sub_info): text = text[0:begin]+'\0'+key+text[begin:end]+'\1'+text[end:] text = text[2:] # Handle case of add/delete entire line @@ -1448,10 +1448,7 @@ def _mdiff(fromlines, tolines, context=None, linejunk=None, # are a concatenation of the first character of each of the 4 lines # so we can do some very readable comparisons. while len(lines) < 4: - try: - lines.append(next(diff_lines_iterator)) - except StopIteration: - lines.append('X') + lines.append(next(diff_lines_iterator, 'X')) s = ''.join([line[0] for line in lines]) if s.startswith('X'): # When no more lines, pump out any remaining blank lines so the @@ -1514,7 +1511,7 @@ def _mdiff(fromlines, tolines, context=None, linejunk=None, num_blanks_to_yield -= 1 yield ('','\n'),None,True if s.startswith('X'): - raise StopIteration + return else: yield from_line,to_line,True @@ -1679,7 +1676,7 @@ class HtmlDiff(object): tabsize -- tab stop spacing, defaults to 8. wrapcolumn -- column number where lines are broken and wrapped, defaults to None where lines are not wrapped. - linejunk,charjunk -- keyword arguments passed into ndiff() (used to by + linejunk,charjunk -- keyword arguments passed into ndiff() (used by HtmlDiff() to generate the side by side HTML differences). See ndiff() documentation for argument default values and descriptions. """ @@ -29,7 +29,7 @@ def _try_compile(source, name): return c def dis(x=None, *, file=None): - """Disassemble classes, methods, functions, or code. + """Disassemble classes, methods, functions, generators, or code. With no argument, disassemble the last traceback. @@ -41,6 +41,8 @@ def dis(x=None, *, file=None): x = x.__func__ if hasattr(x, '__code__'): # Function x = x.__code__ + if hasattr(x, 'gi_code'): # Generator + x = x.gi_code if hasattr(x, '__dict__'): # Class or module items = sorted(x.__dict__.items()) for name, x1 in items: @@ -99,11 +101,13 @@ def pretty_flags(flags): return ", ".join(names) def _get_code_object(x): - """Helper to handle methods, functions, strings and raw code objects""" + """Helper to handle methods, functions, generators, strings and raw code objects""" if hasattr(x, '__func__'): # Method x = x.__func__ if hasattr(x, '__code__'): # Function x = x.__code__ + if hasattr(x, 'gi_code'): # Generator + x = x.gi_code if isinstance(x, str): # Source code x = _try_compile(x, "<disassembly>") if hasattr(x, 'co_code'): # Code object diff --git a/Lib/distutils/__init__.py b/Lib/distutils/__init__.py index 00a5859..67ec78b 100644 --- a/Lib/distutils/__init__.py +++ b/Lib/distutils/__init__.py @@ -13,5 +13,5 @@ used from a setup script as # Updated automatically by the Python release process. # #--start constants-- -__version__ = "3.4.3" +__version__ = "3.5.0a1" #--end constants-- diff --git a/Lib/distutils/command/build.py b/Lib/distutils/command/build.py index cfc15cf..337dd0b 100644 --- a/Lib/distutils/command/build.py +++ b/Lib/distutils/command/build.py @@ -36,6 +36,8 @@ class build(Command): "(default: %s)" % get_platform()), ('compiler=', 'c', "specify the compiler type"), + ('parallel=', 'j', + "number of parallel build jobs"), ('debug', 'g', "compile extensions and libraries with debugging information"), ('force', 'f', @@ -65,6 +67,7 @@ class build(Command): self.debug = None self.force = 0 self.executable = None + self.parallel = None def finalize_options(self): if self.plat_name is None: @@ -116,6 +119,12 @@ class build(Command): if self.executable is None: self.executable = os.path.normpath(sys.executable) + if isinstance(self.parallel, str): + try: + self.parallel = int(self.parallel) + except ValueError: + raise DistutilsOptionError("parallel should be an integer") + def run(self): # Run all relevant sub-commands. This will be some subset of: # - build_py - pure Python modules diff --git a/Lib/distutils/command/build_ext.py b/Lib/distutils/command/build_ext.py index acbe648..c5a3ce1 100644 --- a/Lib/distutils/command/build_ext.py +++ b/Lib/distutils/command/build_ext.py @@ -4,7 +4,10 @@ Implements the Distutils 'build_ext' command, for building extension modules (currently limited to C extensions, should accommodate C++ extensions ASAP).""" -import sys, os, re +import contextlib +import os +import re +import sys from distutils.core import Command from distutils.errors import * from distutils.sysconfig import customize_compiler, get_python_version @@ -85,6 +88,8 @@ class build_ext(Command): "forcibly build everything (ignore file timestamps)"), ('compiler=', 'c', "specify the compiler type"), + ('parallel=', 'j', + "number of parallel build jobs"), ('swig-cpp', None, "make SWIG create C++ files (default is C)"), ('swig-opts=', None, @@ -124,6 +129,7 @@ class build_ext(Command): self.swig_cpp = None self.swig_opts = None self.user = None + self.parallel = None def finalize_options(self): from distutils import sysconfig @@ -134,6 +140,7 @@ class build_ext(Command): ('compiler', 'compiler'), ('debug', 'debug'), ('force', 'force'), + ('parallel', 'parallel'), ('plat_name', 'plat_name'), ) @@ -202,7 +209,7 @@ class build_ext(Command): if MSVC_VERSION >= 9: # Use the .lib files for the correct architecture if self.plat_name == 'win32': - suffix = '' + suffix = 'win32' else: # win-amd64 or win-ia64 suffix = self.plat_name[4:] @@ -274,6 +281,12 @@ class build_ext(Command): self.library_dirs.append(user_lib) self.rpath.append(user_lib) + if isinstance(self.parallel, str): + try: + self.parallel = int(self.parallel) + except ValueError: + raise DistutilsOptionError("parallel should be an integer") + def run(self): from distutils.ccompiler import new_compiler @@ -442,15 +455,45 @@ class build_ext(Command): def build_extensions(self): # First, sanity-check the 'extensions' list self.check_extensions_list(self.extensions) + if self.parallel: + self._build_extensions_parallel() + else: + self._build_extensions_serial() + + def _build_extensions_parallel(self): + workers = self.parallel + if self.parallel is True: + workers = os.cpu_count() # may return None + try: + from concurrent.futures import ThreadPoolExecutor + except ImportError: + workers = None + + if workers is None: + self._build_extensions_serial() + return + + with ThreadPoolExecutor(max_workers=workers) as executor: + futures = [executor.submit(self.build_extension, ext) + for ext in self.extensions] + for ext, fut in zip(self.extensions, futures): + with self._filter_build_errors(ext): + fut.result() + def _build_extensions_serial(self): for ext in self.extensions: - try: + with self._filter_build_errors(ext): self.build_extension(ext) - except (CCompilerError, DistutilsError, CompileError) as e: - if not ext.optional: - raise - self.warn('building extension "%s" failed: %s' % - (ext.name, e)) + + @contextlib.contextmanager + def _filter_build_errors(self, ext): + try: + yield + except (CCompilerError, DistutilsError, CompileError) as e: + if not ext.optional: + raise + self.warn('building extension "%s" failed: %s' % + (ext.name, e)) def build_extension(self, ext): sources = ext.sources @@ -502,15 +545,8 @@ class build_ext(Command): extra_postargs=extra_args, depends=ext.depends) - # XXX -- this is a Vile HACK! - # - # The setup.py script for Python on Unix needs to be able to - # get this list so it can perform all the clean up needed to - # avoid keeping object files around when cleaning out a failed - # build of an extension module. Since Distutils does not - # track dependencies, we have to get rid of intermediates to - # ensure all the intermediates will be properly re-built. - # + # XXX outdated variable, kept here in case third-part code + # needs it. self._built_objects = objects[:] # Now link the object files together into a "shared object" -- @@ -655,10 +691,7 @@ class build_ext(Command): """ from distutils.sysconfig import get_config_var ext_path = ext_name.split('.') - # extensions in debug_mode are named 'module_d.pyd' under windows ext_suffix = get_config_var('EXT_SUFFIX') - if os.name == 'nt' and self.debug: - return os.path.join(*ext_path) + '_d' + ext_suffix return os.path.join(*ext_path) + ext_suffix def get_export_symbols(self, ext): diff --git a/Lib/distutils/command/install.py b/Lib/distutils/command/install.py index d768dc5..67db007 100644 --- a/Lib/distutils/command/install.py +++ b/Lib/distutils/command/install.py @@ -51,7 +51,7 @@ if HAS_USER_SITE: 'purelib': '$usersite', 'platlib': '$usersite', 'headers': '$userbase/Python$py_version_nodot/Include/$dist_name', - 'scripts': '$userbase/Scripts', + 'scripts': '$userbase/Python$py_version_nodot/Scripts', 'data' : '$userbase', } diff --git a/Lib/distutils/command/upload.py b/Lib/distutils/command/upload.py index 1a96e22..1c4fc48 100644 --- a/Lib/distutils/command/upload.py +++ b/Lib/distutils/command/upload.py @@ -1,11 +1,14 @@ -"""distutils.command.upload +""" +distutils.command.upload -Implements the Distutils 'upload' subcommand (upload package to PyPI).""" +Implements the Distutils 'upload' subcommand (upload package to a package +index). +""" -import sys -import os, io -import socket +import os +import io import platform +import hashlib from base64 import standard_b64encode from urllib.request import urlopen, Request, HTTPError from urllib.parse import urlparse @@ -14,12 +17,6 @@ from distutils.core import PyPIRCCommand from distutils.spawn import spawn from distutils import log -# this keeps compatibility for 2.3 and 2.4 -if sys.version < "2.5": - from md5 import md5 -else: - from hashlib import md5 - class upload(PyPIRCCommand): description = "upload binary package to PyPI" @@ -60,7 +57,8 @@ class upload(PyPIRCCommand): def run(self): if not self.distribution.dist_files: - raise DistutilsOptionError("No dist file created in earlier command") + msg = "No dist file created in earlier command" + raise DistutilsOptionError(msg) for command, pyversion, filename in self.distribution.dist_files: self.upload_file(command, pyversion, filename) @@ -103,10 +101,10 @@ class upload(PyPIRCCommand): 'content': (os.path.basename(filename),content), 'filetype': command, 'pyversion': pyversion, - 'md5_digest': md5(content).hexdigest(), + 'md5_digest': hashlib.md5(content).hexdigest(), # additional meta-data - 'metadata_version' : '1.0', + 'metadata_version': '1.0', 'summary': meta.get_description(), 'home_page': meta.get_url(), 'author': meta.get_contact(), @@ -149,7 +147,7 @@ class upload(PyPIRCCommand): for key, value in data.items(): title = '\r\nContent-Disposition: form-data; name="%s"' % key # handle multiple entries for the same name - if type(value) != type([]): + if not isinstance(value, list): value = [value] for value in value: if type(value) is tuple: @@ -166,13 +164,15 @@ class upload(PyPIRCCommand): body.write(end_boundary) body = body.getvalue() - self.announce("Submitting %s to %s" % (filename, self.repository), log.INFO) + msg = "Submitting %s to %s" % (filename, self.repository) + self.announce(msg, log.INFO) # build the Request - headers = {'Content-type': - 'multipart/form-data; boundary=%s' % boundary, - 'Content-length': str(len(body)), - 'Authorization': auth} + headers = { + 'Content-type': 'multipart/form-data; boundary=%s' % boundary, + 'Content-length': str(len(body)), + 'Authorization': auth, + } request = Request(self.repository, data=body, headers=headers) diff --git a/Lib/distutils/command/wininst-14.0-amd64.exe b/Lib/distutils/command/wininst-14.0-amd64.exe Binary files differnew file mode 100644 index 0000000..43b85b6 --- /dev/null +++ b/Lib/distutils/command/wininst-14.0-amd64.exe diff --git a/Lib/distutils/command/wininst-14.0.exe b/Lib/distutils/command/wininst-14.0.exe Binary files differnew file mode 100644 index 0000000..764524d --- /dev/null +++ b/Lib/distutils/command/wininst-14.0.exe diff --git a/Lib/distutils/dist.py b/Lib/distutils/dist.py index 7eb04bc..ffb33ff6 100644 --- a/Lib/distutils/dist.py +++ b/Lib/distutils/dist.py @@ -4,7 +4,9 @@ Provides the Distribution class, which represents the module distribution being built/installed/distributed. """ -import sys, os, re +import sys +import os +import re from email import message_from_file try: @@ -22,7 +24,7 @@ from distutils.debug import DEBUG # the same as a Python NAME -- I don't allow leading underscores. The fact # that they're very similar is no coincidence; the default naming scheme is # to look for a Python module named after the command. -command_re = re.compile (r'^[a-zA-Z]([a-zA-Z0-9_]*)$') +command_re = re.compile(r'^[a-zA-Z]([a-zA-Z0-9_]*)$') class Distribution: @@ -39,7 +41,6 @@ class Distribution: See the code for 'setup()', in core.py, for details. """ - # 'global_options' describes the command-line options that may be # supplied to the setup script prior to any actual commands. # Eg. "./setup.py -n" or "./setup.py --quiet" both take advantage of @@ -48,12 +49,13 @@ class Distribution: # don't want to pollute the commands with too many options that they # have minimal control over. # The fourth entry for verbose means that it can be repeated. - global_options = [('verbose', 'v', "run verbosely (default)", 1), - ('quiet', 'q', "run quietly (turns verbosity off)"), - ('dry-run', 'n', "don't actually do anything"), - ('help', 'h', "show detailed help message"), - ('no-user-cfg', None, - 'ignore pydistutils.cfg in your home directory'), + global_options = [ + ('verbose', 'v', "run verbosely (default)", 1), + ('quiet', 'q', "run quietly (turns verbosity off)"), + ('dry-run', 'n', "don't actually do anything"), + ('help', 'h', "show detailed help message"), + ('no-user-cfg', None, + 'ignore pydistutils.cfg in your home directory'), ] # 'common_usage' is a short (2-3 line) string describing the common @@ -115,10 +117,9 @@ Common commands: (see '--help-commands' for more) # negative options are options that exclude other options negative_opt = {'quiet': 'verbose'} - # -- Creation/initialization methods ------------------------------- - def __init__ (self, attrs=None): + def __init__(self, attrs=None): """Construct a new Distribution instance: initialize all the attributes of a Distribution, and then use 'attrs' (a dictionary mapping attribute names to values) to assign some of those @@ -532,15 +533,15 @@ Common commands: (see '--help-commands' for more) # to be sure that the basic "command" interface is implemented. if not issubclass(cmd_class, Command): raise DistutilsClassError( - "command class %s must subclass Command" % cmd_class) + "command class %s must subclass Command" % cmd_class) # Also make sure that the command object provides a list of its # known options. if not (hasattr(cmd_class, 'user_options') and isinstance(cmd_class.user_options, list)): - raise DistutilsClassError(("command class %s must provide " + - "'user_options' attribute (a list of tuples)") % \ - cmd_class) + msg = ("command class %s must provide " + "'user_options' attribute (a list of tuples)") + raise DistutilsClassError(msg % cmd_class) # If the command class has a list of negative alias options, # merge it in with the global negative aliases. @@ -552,12 +553,11 @@ Common commands: (see '--help-commands' for more) # Check for help_options in command class. They have a different # format (tuple of four) so we need to preprocess them here. if (hasattr(cmd_class, 'help_options') and - isinstance(cmd_class.help_options, list)): + isinstance(cmd_class.help_options, list)): help_options = fix_help_options(cmd_class.help_options) else: help_options = [] - # All commands support the global options too, just by adding # in 'global_options'. parser.set_option_table(self.global_options + @@ -570,7 +570,7 @@ Common commands: (see '--help-commands' for more) return if (hasattr(cmd_class, 'help_options') and - isinstance(cmd_class.help_options, list)): + isinstance(cmd_class.help_options, list)): help_option_found=0 for (help_option, short, desc, func) in cmd_class.help_options: if hasattr(opts, parser.get_attr_name(help_option)): @@ -647,7 +647,7 @@ Common commands: (see '--help-commands' for more) else: klass = self.get_command_class(command) if (hasattr(klass, 'help_options') and - isinstance(klass.help_options, list)): + isinstance(klass.help_options, list)): parser.set_option_table(klass.user_options + fix_help_options(klass.help_options)) else: @@ -814,7 +814,7 @@ Common commands: (see '--help-commands' for more) klass_name = command try: - __import__ (module_name) + __import__(module_name) module = sys.modules[module_name] except ImportError: continue @@ -823,8 +823,8 @@ Common commands: (see '--help-commands' for more) klass = getattr(module, klass_name) except AttributeError: raise DistutilsModuleError( - "invalid command '%s' (no class '%s' in module '%s')" - % (command, klass_name, module_name)) + "invalid command '%s' (no class '%s' in module '%s')" + % (command, klass_name, module_name)) self.cmdclass[command] = klass return klass @@ -840,7 +840,7 @@ Common commands: (see '--help-commands' for more) cmd_obj = self.command_obj.get(command) if not cmd_obj and create: if DEBUG: - self.announce("Distribution.get_command_obj(): " \ + self.announce("Distribution.get_command_obj(): " "creating '%s' command object" % command) klass = self.get_command_class(command) @@ -897,8 +897,8 @@ Common commands: (see '--help-commands' for more) setattr(command_obj, option, value) else: raise DistutilsOptionError( - "error in %s: command '%s' has no such option '%s'" - % (source, command_name, option)) + "error in %s: command '%s' has no such option '%s'" + % (source, command_name, option)) except ValueError as msg: raise DistutilsOptionError(msg) @@ -974,7 +974,6 @@ Common commands: (see '--help-commands' for more) cmd_obj.run() self.have_run[command] = 1 - # -- Distribution query methods ------------------------------------ def has_pure_modules(self): @@ -1112,17 +1111,17 @@ class DistributionMetadata: """ version = '1.0' if (self.provides or self.requires or self.obsoletes or - self.classifiers or self.download_url): + self.classifiers or self.download_url): version = '1.1' file.write('Metadata-Version: %s\n' % version) - file.write('Name: %s\n' % self.get_name() ) - file.write('Version: %s\n' % self.get_version() ) - file.write('Summary: %s\n' % self.get_description() ) - file.write('Home-page: %s\n' % self.get_url() ) - file.write('Author: %s\n' % self.get_contact() ) - file.write('Author-email: %s\n' % self.get_contact_email() ) - file.write('License: %s\n' % self.get_license() ) + file.write('Name: %s\n' % self.get_name()) + file.write('Version: %s\n' % self.get_version()) + file.write('Summary: %s\n' % self.get_description()) + file.write('Home-page: %s\n' % self.get_url()) + file.write('Author: %s\n' % self.get_contact()) + file.write('Author-email: %s\n' % self.get_contact_email()) + file.write('License: %s\n' % self.get_license()) if self.download_url: file.write('Download-URL: %s\n' % self.download_url) @@ -1131,7 +1130,7 @@ class DistributionMetadata: keywords = ','.join(self.get_keywords()) if keywords: - file.write('Keywords: %s\n' % keywords ) + file.write('Keywords: %s\n' % keywords) self._write_list(file, 'Platform', self.get_platforms()) self._write_list(file, 'Classifier', self.get_classifiers()) diff --git a/Lib/distutils/extension.py b/Lib/distutils/extension.py index a93655a..7efbb74 100644 --- a/Lib/distutils/extension.py +++ b/Lib/distutils/extension.py @@ -131,6 +131,14 @@ class Extension: msg = "Unknown Extension options: %s" % options warnings.warn(msg) + def __repr__(self): + return '<%s.%s(%r) at %#x>' % ( + self.__class__.__module__, + self.__class__.__qualname__, + self.name, + id(self)) + + def read_setup_file(filename): """Reads a Setup file and returns Extension instances.""" from distutils.sysconfig import (parse_makefile, expand_makefile_vars, diff --git a/Lib/distutils/msvc9compiler.py b/Lib/distutils/msvc9compiler.py index 9688f20..d1374ef 100644 --- a/Lib/distutils/msvc9compiler.py +++ b/Lib/distutils/msvc9compiler.py @@ -179,6 +179,9 @@ def get_build_version(): i = i + len(prefix) s, rest = sys.version[i:].split(" ", 1) majorVersion = int(s[:-2]) - 6 + if majorVersion >= 13: + # v13 was skipped and should be v14 + majorVersion += 1 minorVersion = int(s[2:3]) / 10.0 # I don't think paths are affected by minor version in version 6 if majorVersion == 6: diff --git a/Lib/distutils/msvccompiler.py b/Lib/distutils/msvccompiler.py index 8116656..1048cd4 100644 --- a/Lib/distutils/msvccompiler.py +++ b/Lib/distutils/msvccompiler.py @@ -157,6 +157,9 @@ def get_build_version(): i = i + len(prefix) s, rest = sys.version[i:].split(" ", 1) majorVersion = int(s[:-2]) - 6 + if majorVersion >= 13: + # v13 was skipped and should be v14 + majorVersion += 1 minorVersion = int(s[2:3]) / 10.0 # I don't think paths are affected by minor version in version 6 if majorVersion == 6: diff --git a/Lib/distutils/spawn.py b/Lib/distutils/spawn.py index 22e87e8..5dd415a 100644 --- a/Lib/distutils/spawn.py +++ b/Lib/distutils/spawn.py @@ -137,9 +137,6 @@ def _spawn_posix(cmd, search_path=1, verbose=0, dry_run=0): try: pid, status = os.waitpid(pid, 0) except OSError as exc: - import errno - if exc.errno == errno.EINTR: - continue if not DEBUG: cmd = executable raise DistutilsExecError( diff --git a/Lib/distutils/sysconfig.py b/Lib/distutils/sysconfig.py index a1452fe..573724d 100644 --- a/Lib/distutils/sysconfig.py +++ b/Lib/distutils/sysconfig.py @@ -9,6 +9,7 @@ Written by: Fred L. Drake, Jr. Email: <fdrake@acm.org> """ +import _imp import os import re import sys @@ -22,23 +23,15 @@ BASE_PREFIX = os.path.normpath(sys.base_prefix) BASE_EXEC_PREFIX = os.path.normpath(sys.base_exec_prefix) # Path to the base directory of the project. On Windows the binary may -# live in project/PCBuild9. If we're dealing with an x64 Windows build, -# it'll live in project/PCbuild/amd64. +# live in project/PCBuild/win32 or project/PCBuild/amd64. # set for cross builds if "_PYTHON_PROJECT_BASE" in os.environ: project_base = os.path.abspath(os.environ["_PYTHON_PROJECT_BASE"]) else: project_base = os.path.dirname(os.path.abspath(sys.executable)) -if os.name == "nt" and "pcbuild" in project_base[-8:].lower(): - project_base = os.path.abspath(os.path.join(project_base, os.path.pardir)) -# PC/VS7.1 -if os.name == "nt" and "\\pc\\v" in project_base[-10:].lower(): - project_base = os.path.abspath(os.path.join(project_base, os.path.pardir, - os.path.pardir)) -# PC/AMD64 -if os.name == "nt" and "\\pcbuild\\amd64" in project_base[-14:].lower(): - project_base = os.path.abspath(os.path.join(project_base, os.path.pardir, - os.path.pardir)) +if (os.name == 'nt' and + project_base.lower().endswith(('\\pcbuild\\win32', '\\pcbuild\\amd64'))): + project_base = os.path.dirname(os.path.dirname(project_base)) # python_build: (Boolean) if true, we're either building Python or # building an extension with an un-installed Python, so we use @@ -51,11 +44,9 @@ def _is_python_source_dir(d): return True return False _sys_home = getattr(sys, '_home', None) -if _sys_home and os.name == 'nt' and \ - _sys_home.lower().endswith(('pcbuild', 'pcbuild\\amd64')): - _sys_home = os.path.dirname(_sys_home) - if _sys_home.endswith('pcbuild'): # must be amd64 - _sys_home = os.path.dirname(_sys_home) +if (_sys_home and os.name == 'nt' and + _sys_home.lower().endswith(('\\pcbuild\\win32', '\\pcbuild\\amd64'))): + _sys_home = os.path.dirname(os.path.dirname(_sys_home)) def _python_build(): if _sys_home: return _is_python_source_dir(_sys_home) @@ -468,7 +459,7 @@ def _init_nt(): # XXX hmmm.. a normal install puts include files here g['INCLUDEPY'] = get_python_inc(plat_specific=0) - g['EXT_SUFFIX'] = '.pyd' + g['EXT_SUFFIX'] = _imp.extension_suffixes()[0] g['EXE'] = ".exe" g['VERSION'] = get_python_version().replace(".", "") g['BINDIR'] = os.path.dirname(os.path.abspath(sys.executable)) diff --git a/Lib/distutils/tests/test_build_ext.py b/Lib/distutils/tests/test_build_ext.py index b9f407f..366ffbe 100644 --- a/Lib/distutils/tests/test_build_ext.py +++ b/Lib/distutils/tests/test_build_ext.py @@ -37,6 +37,9 @@ class BuildExtTestCase(TempdirManager, from distutils.command import build_ext build_ext.USER_BASE = site.USER_BASE + def build_ext(self, *args, **kwargs): + return build_ext(*args, **kwargs) + def test_build_ext(self): global ALREADY_TESTED copy_xxmodule_c(self.tmp_dir) @@ -44,7 +47,7 @@ class BuildExtTestCase(TempdirManager, xx_ext = Extension('xx', [xx_c]) dist = Distribution({'name': 'xx', 'ext_modules': [xx_ext]}) dist.package_dir = self.tmp_dir - cmd = build_ext(dist) + cmd = self.build_ext(dist) fixup_build_ext(cmd) cmd.build_lib = self.tmp_dir cmd.build_temp = self.tmp_dir @@ -91,7 +94,7 @@ class BuildExtTestCase(TempdirManager, def test_solaris_enable_shared(self): dist = Distribution({'name': 'xx'}) - cmd = build_ext(dist) + cmd = self.build_ext(dist) old = sys.platform sys.platform = 'sunos' # fooling finalize_options @@ -113,7 +116,7 @@ class BuildExtTestCase(TempdirManager, def test_user_site(self): import site dist = Distribution({'name': 'xx'}) - cmd = build_ext(dist) + cmd = self.build_ext(dist) # making sure the user option is there options = [name for name, short, lable in @@ -144,14 +147,14 @@ class BuildExtTestCase(TempdirManager, # with the optional argument. modules = [Extension('foo', ['xxx'], optional=False)] dist = Distribution({'name': 'xx', 'ext_modules': modules}) - cmd = build_ext(dist) + cmd = self.build_ext(dist) cmd.ensure_finalized() self.assertRaises((UnknownFileError, CompileError), cmd.run) # should raise an error modules = [Extension('foo', ['xxx'], optional=True)] dist = Distribution({'name': 'xx', 'ext_modules': modules}) - cmd = build_ext(dist) + cmd = self.build_ext(dist) cmd.ensure_finalized() cmd.run() # should pass @@ -160,7 +163,7 @@ class BuildExtTestCase(TempdirManager, # etc.) are in the include search path. modules = [Extension('foo', ['xxx'], optional=False)] dist = Distribution({'name': 'xx', 'ext_modules': modules}) - cmd = build_ext(dist) + cmd = self.build_ext(dist) cmd.finalize_options() from distutils import sysconfig @@ -172,14 +175,14 @@ class BuildExtTestCase(TempdirManager, # make sure cmd.libraries is turned into a list # if it's a string - cmd = build_ext(dist) + cmd = self.build_ext(dist) cmd.libraries = 'my_lib, other_lib lastlib' cmd.finalize_options() self.assertEqual(cmd.libraries, ['my_lib', 'other_lib', 'lastlib']) # make sure cmd.library_dirs is turned into a list # if it's a string - cmd = build_ext(dist) + cmd = self.build_ext(dist) cmd.library_dirs = 'my_lib_dir%sother_lib_dir' % os.pathsep cmd.finalize_options() self.assertIn('my_lib_dir', cmd.library_dirs) @@ -187,7 +190,7 @@ class BuildExtTestCase(TempdirManager, # make sure rpath is turned into a list # if it's a string - cmd = build_ext(dist) + cmd = self.build_ext(dist) cmd.rpath = 'one%stwo' % os.pathsep cmd.finalize_options() self.assertEqual(cmd.rpath, ['one', 'two']) @@ -196,32 +199,32 @@ class BuildExtTestCase(TempdirManager, # make sure define is turned into 2-tuples # strings if they are ','-separated strings - cmd = build_ext(dist) + cmd = self.build_ext(dist) cmd.define = 'one,two' cmd.finalize_options() self.assertEqual(cmd.define, [('one', '1'), ('two', '1')]) # make sure undef is turned into a list of # strings if they are ','-separated strings - cmd = build_ext(dist) + cmd = self.build_ext(dist) cmd.undef = 'one,two' cmd.finalize_options() self.assertEqual(cmd.undef, ['one', 'two']) # make sure swig_opts is turned into a list - cmd = build_ext(dist) + cmd = self.build_ext(dist) cmd.swig_opts = None cmd.finalize_options() self.assertEqual(cmd.swig_opts, []) - cmd = build_ext(dist) + cmd = self.build_ext(dist) cmd.swig_opts = '1 2' cmd.finalize_options() self.assertEqual(cmd.swig_opts, ['1', '2']) def test_check_extensions_list(self): dist = Distribution() - cmd = build_ext(dist) + cmd = self.build_ext(dist) cmd.finalize_options() #'extensions' option must be a list of Extension instances @@ -270,7 +273,7 @@ class BuildExtTestCase(TempdirManager, def test_get_source_files(self): modules = [Extension('foo', ['xxx'], optional=False)] dist = Distribution({'name': 'xx', 'ext_modules': modules}) - cmd = build_ext(dist) + cmd = self.build_ext(dist) cmd.ensure_finalized() self.assertEqual(cmd.get_source_files(), ['xxx']) @@ -279,7 +282,7 @@ class BuildExtTestCase(TempdirManager, # should not be overriden by a compiler instance # when the command is run dist = Distribution() - cmd = build_ext(dist) + cmd = self.build_ext(dist) cmd.compiler = 'unix' cmd.ensure_finalized() cmd.run() @@ -292,7 +295,7 @@ class BuildExtTestCase(TempdirManager, ext = Extension('foo', [c_file], optional=False) dist = Distribution({'name': 'xx', 'ext_modules': [ext]}) - cmd = build_ext(dist) + cmd = self.build_ext(dist) fixup_build_ext(cmd) cmd.ensure_finalized() self.assertEqual(len(cmd.get_outputs()), 1) @@ -355,7 +358,7 @@ class BuildExtTestCase(TempdirManager, #etree_ext = Extension('lxml.etree', [etree_c]) #dist = Distribution({'name': 'lxml', 'ext_modules': [etree_ext]}) dist = Distribution() - cmd = build_ext(dist) + cmd = self.build_ext(dist) cmd.inplace = 1 cmd.distribution.package_dir = {'': 'src'} cmd.distribution.packages = ['lxml', 'lxml.html'] @@ -462,7 +465,7 @@ class BuildExtTestCase(TempdirManager, 'ext_modules': [deptarget_ext] }) dist.package_dir = self.tmp_dir - cmd = build_ext(dist) + cmd = self.build_ext(dist) cmd.build_lib = self.tmp_dir cmd.build_temp = self.tmp_dir @@ -481,8 +484,19 @@ class BuildExtTestCase(TempdirManager, self.fail("Wrong deployment target during compilation") +class ParallelBuildExtTestCase(BuildExtTestCase): + + def build_ext(self, *args, **kwargs): + build_ext = super().build_ext(*args, **kwargs) + build_ext.parallel = True + return build_ext + + def test_suite(): - return unittest.makeSuite(BuildExtTestCase) + suite = unittest.TestSuite() + suite.addTest(unittest.makeSuite(BuildExtTestCase)) + suite.addTest(unittest.makeSuite(ParallelBuildExtTestCase)) + return suite if __name__ == '__main__': - support.run_unittest(test_suite()) + support.run_unittest(__name__) diff --git a/Lib/distutils/tests/test_install.py b/Lib/distutils/tests/test_install.py index 18e1e57..9313330 100644 --- a/Lib/distutils/tests/test_install.py +++ b/Lib/distutils/tests/test_install.py @@ -20,8 +20,6 @@ from distutils.tests import support def _make_ext_name(modname): - if os.name == 'nt' and sys.executable.endswith('_d.exe'): - modname += '_d' return modname + sysconfig.get_config_var('EXT_SUFFIX') diff --git a/Lib/distutils/version.py b/Lib/distutils/version.py index ebcab84..af14cc1 100644 --- a/Lib/distutils/version.py +++ b/Lib/distutils/version.py @@ -48,12 +48,6 @@ class Version: return c return c == 0 - def __ne__(self, other): - c = self._cmp(other) - if c is NotImplemented: - return c - return c != 0 - def __lt__(self, other): c = self._cmp(other) if c is NotImplemented: diff --git a/Lib/doctest.py b/Lib/doctest.py index 64e6d71..7d5bcf4 100644 --- a/Lib/doctest.py +++ b/Lib/doctest.py @@ -530,8 +530,9 @@ class DocTest: examples = '1 example' else: examples = '%d examples' % len(self.examples) - return ('<DocTest %s from %s:%s (%s)>' % - (self.name, self.filename, self.lineno, examples)) + return ('<%s %s from %s:%s (%s)>' % + (self.__class__.__name__, + self.name, self.filename, self.lineno, examples)) def __eq__(self, other): if type(self) is not type(other): @@ -978,7 +979,8 @@ class DocTestFinder: for valname, val in obj.__dict__.items(): valname = '%s.%s' % (name, valname) # Recurse to functions & classes. - if ((inspect.isroutine(val) or inspect.isclass(val)) and + if ((inspect.isroutine(inspect.unwrap(val)) + or inspect.isclass(val)) and self._from_module(module, val)): self._find(tests, val, valname, module, source_lines, globs, seen) @@ -2367,15 +2369,6 @@ def DocTestSuite(module=None, globs=None, extraglobs=None, test_finder=None, suite = _DocTestSuite() suite.addTest(SkipDocTestCase(module)) return suite - elif not tests: - # Why do we want to do this? Because it reveals a bug that might - # otherwise be hidden. - # It is probably a bug that this exception is not also raised if the - # number of doctest examples in tests is zero (i.e. if no doctest - # examples were found). However, we should probably not be raising - # an exception at all here, though it is too late to make this change - # for a maintenance release. See also issue #14649. - raise ValueError(module, "has no docstrings") tests.sort() suite = _DocTestSuite() diff --git a/Lib/email/__init__.py b/Lib/email/__init__.py index ff16f6a..fae8724 100644 --- a/Lib/email/__init__.py +++ b/Lib/email/__init__.py @@ -4,8 +4,6 @@ """A package for parsing, handling, and generating email messages.""" -__version__ = '5.1.0' - __all__ = [ 'base64mime', 'charset', diff --git a/Lib/email/charset.py b/Lib/email/charset.py index e999472..ee56404 100644 --- a/Lib/email/charset.py +++ b/Lib/email/charset.py @@ -249,9 +249,6 @@ class Charset: def __eq__(self, other): return str(self) == str(other).lower() - def __ne__(self, other): - return not self.__eq__(other) - def get_body_encoding(self): """Return the content-transfer-encoding used for body encoding. diff --git a/Lib/email/header.py b/Lib/email/header.py index 9c89589..6820ea1 100644 --- a/Lib/email/header.py +++ b/Lib/email/header.py @@ -262,9 +262,6 @@ class Header: # args and do another comparison. return other == str(self) - def __ne__(self, other): - return not self == other - def append(self, s, charset=None, errors='strict'): """Append a string to the MIME header. diff --git a/Lib/email/headerregistry.py b/Lib/email/headerregistry.py index 911a2af..468ca9e 100644 --- a/Lib/email/headerregistry.py +++ b/Lib/email/headerregistry.py @@ -81,7 +81,8 @@ class Address: return lp def __repr__(self): - return "Address(display_name={!r}, username={!r}, domain={!r})".format( + return "{}(display_name={!r}, username={!r}, domain={!r})".format( + self.__class__.__name__, self.display_name, self.username, self.domain) def __str__(self): @@ -132,7 +133,8 @@ class Group: return self._addresses def __repr__(self): - return "Group(display_name={!r}, addresses={!r}".format( + return "{}(display_name={!r}, addresses={!r}".format( + self.__class__.__name__, self.display_name, self.addresses) def __str__(self): diff --git a/Lib/email/message.py b/Lib/email/message.py index 2f37dbb..3d3138f 100644 --- a/Lib/email/message.py +++ b/Lib/email/message.py @@ -930,17 +930,6 @@ class Message: # I.e. def walk(self): ... from email.iterators import walk -# XXX Support for temporary deprecation hack for is_attachment property. -class _IsAttachment: - def __init__(self, value): - self.value = value - def __call__(self): - return self.value - def __bool__(self): - warnings.warn("is_attachment will be a method, not a property, in 3.5", - DeprecationWarning, - stacklevel=3) - return self.value class MIMEPart(Message): @@ -950,12 +939,9 @@ class MIMEPart(Message): policy = default Message.__init__(self, policy) - @property def is_attachment(self): c_d = self.get('content-disposition') - result = False if c_d is None else c_d.content_disposition == 'attachment' - # XXX transitional hack to raise deprecation if not called. - return _IsAttachment(result) + return False if c_d is None else c_d.content_disposition == 'attachment' def _find_body(self, part, preferencelist): if part.is_attachment(): diff --git a/Lib/email/mime/text.py b/Lib/email/mime/text.py index ec18b85..479928e 100644 --- a/Lib/email/mime/text.py +++ b/Lib/email/mime/text.py @@ -6,6 +6,7 @@ __all__ = ['MIMEText'] +from email.charset import Charset from email.mime.nonmultipart import MIMENonMultipart @@ -34,6 +35,8 @@ class MIMEText(MIMENonMultipart): _charset = 'us-ascii' except UnicodeEncodeError: _charset = 'utf-8' + if isinstance(_charset, Charset): + _charset = str(_charset) MIMENonMultipart.__init__(self, 'text', _subtype, **{'charset': _charset}) diff --git a/Lib/encodings/cp65001.py b/Lib/encodings/cp65001.py index 287eb87..95cb2ae 100644 --- a/Lib/encodings/cp65001.py +++ b/Lib/encodings/cp65001.py @@ -11,20 +11,23 @@ if not hasattr(codecs, 'code_page_encode'): ### Codec APIs encode = functools.partial(codecs.code_page_encode, 65001) -decode = functools.partial(codecs.code_page_decode, 65001) +_decode = functools.partial(codecs.code_page_decode, 65001) + +def decode(input, errors='strict'): + return codecs.code_page_decode(65001, input, errors, True) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return encode(input, self.errors)[0] class IncrementalDecoder(codecs.BufferedIncrementalDecoder): - _buffer_decode = decode + _buffer_decode = _decode class StreamWriter(codecs.StreamWriter): encode = encode class StreamReader(codecs.StreamReader): - decode = decode + decode = _decode ### encodings module API diff --git a/Lib/enum.py b/Lib/enum.py index 9b19c1d..d744f8f 100644 --- a/Lib/enum.py +++ b/Lib/enum.py @@ -193,7 +193,7 @@ class EnumMeta(type): enum_class.__new__ = Enum.__new__ return enum_class - def __call__(cls, value, names=None, *, module=None, qualname=None, type=None): + def __call__(cls, value, names=None, *, module=None, qualname=None, type=None, start=1): """Either returns an existing member, or creates a new enum class. This method is used both when an enum class is given a value to match @@ -205,7 +205,7 @@ class EnumMeta(type): `value` will be the name of the new class. `names` should be either a string of white-space/comma delimited names - (values will start at 1), or an iterator/mapping of name, value pairs. + (values will start at `start`), or an iterator/mapping of name, value pairs. `module` should be set to the module this class is being created in; if it is not set, an attempt to find that module will be made, but if @@ -221,7 +221,7 @@ class EnumMeta(type): if names is None: # simple value lookup return cls.__new__(cls, value) # otherwise, functional API: we're creating a new Enum type - return cls._create_(value, names, module=module, qualname=qualname, type=type) + return cls._create_(value, names, module=module, qualname=qualname, type=type, start=start) def __contains__(cls, member): return isinstance(member, cls) and member._name_ in cls._member_map_ @@ -292,16 +292,16 @@ class EnumMeta(type): raise AttributeError('Cannot reassign members.') super().__setattr__(name, value) - def _create_(cls, class_name, names=None, *, module=None, qualname=None, type=None): + def _create_(cls, class_name, names=None, *, module=None, qualname=None, type=None, start=1): """Convenience method to create a new Enum class. `names` can be: * A string containing member names, separated either with spaces or - commas. Values are auto-numbered from 1. - * An iterable of member names. Values are auto-numbered from 1. + commas. Values are incremented by 1 from `start`. + * An iterable of member names. Values are incremented by 1 from `start`. * An iterable of (member name, value) pairs. - * A mapping of member name -> value. + * A mapping of member name -> value pairs. """ metacls = cls.__class__ @@ -312,7 +312,7 @@ class EnumMeta(type): if isinstance(names, str): names = names.replace(',', ' ').split() if isinstance(names, (tuple, list)) and isinstance(names[0], str): - names = [(e, i) for (i, e) in enumerate(names, 1)] + names = [(e, i) for (i, e) in enumerate(names, start)] # Here, names is either an iterable of (name, value) or a mapping. for item in names: @@ -470,8 +470,7 @@ class Enum(metaclass=EnumMeta): for m in cls.__dict__ if m[0] != '_' ] - return (['__class__', '__doc__', '__module__', 'name', 'value'] + - added_behavior) + return (['__class__', '__doc__', '__module__'] + added_behavior) def __format__(self, format_spec): # mixed-in Enums should use the mixed-in type's __format__, otherwise diff --git a/Lib/formatter.py b/Lib/formatter.py index 9338261..cc2f4ad 100644 --- a/Lib/formatter.py +++ b/Lib/formatter.py @@ -21,7 +21,7 @@ manage and inserting data into the output. import sys import warnings warnings.warn('the formatter module is deprecated and will be removed in ' - 'Python 3.6', PendingDeprecationWarning) + 'Python 3.6', DeprecationWarning) AS_IS = None diff --git a/Lib/fractions.py b/Lib/fractions.py index 79e83ff..5ddc84c 100644 --- a/Lib/fractions.py +++ b/Lib/fractions.py @@ -70,7 +70,7 @@ class Fraction(numbers.Rational): __slots__ = ('_numerator', '_denominator') # We're immutable, so use __new__ not __init__ - def __new__(cls, numerator=0, denominator=None): + def __new__(cls, numerator=0, denominator=None, _normalize=True): """Constructs a Rational. Takes a string like '3/2' or '1.5', another Rational instance, a @@ -104,7 +104,12 @@ class Fraction(numbers.Rational): self = super(Fraction, cls).__new__(cls) if denominator is None: - if isinstance(numerator, numbers.Rational): + if type(numerator) is int: + self._numerator = numerator + self._denominator = 1 + return self + + elif isinstance(numerator, numbers.Rational): self._numerator = numerator.numerator self._denominator = numerator.denominator return self @@ -153,6 +158,9 @@ class Fraction(numbers.Rational): raise TypeError("argument should be a string " "or a Rational instance") + elif type(numerator) is int is type(denominator): + pass # *very* normal case + elif (isinstance(numerator, numbers.Rational) and isinstance(denominator, numbers.Rational)): numerator, denominator = ( @@ -165,9 +173,12 @@ class Fraction(numbers.Rational): if denominator == 0: raise ZeroDivisionError('Fraction(%s, 0)' % numerator) - g = gcd(numerator, denominator) - self._numerator = numerator // g - self._denominator = denominator // g + if _normalize: + g = gcd(numerator, denominator) + numerator //= g + denominator //= g + self._numerator = numerator + self._denominator = denominator return self @classmethod @@ -277,7 +288,8 @@ class Fraction(numbers.Rational): def __repr__(self): """repr(self)""" - return ('Fraction(%s, %s)' % (self._numerator, self._denominator)) + return '%s(%s, %s)' % (self.__class__.__name__, + self._numerator, self._denominator) def __str__(self): """str(self)""" @@ -395,17 +407,17 @@ class Fraction(numbers.Rational): def _add(a, b): """a + b""" - return Fraction(a.numerator * b.denominator + - b.numerator * a.denominator, - a.denominator * b.denominator) + da, db = a.denominator, b.denominator + return Fraction(a.numerator * db + b.numerator * da, + da * db) __add__, __radd__ = _operator_fallbacks(_add, operator.add) def _sub(a, b): """a - b""" - return Fraction(a.numerator * b.denominator - - b.numerator * a.denominator, - a.denominator * b.denominator) + da, db = a.denominator, b.denominator + return Fraction(a.numerator * db - b.numerator * da, + da * db) __sub__, __rsub__ = _operator_fallbacks(_sub, operator.sub) @@ -453,10 +465,12 @@ class Fraction(numbers.Rational): power = b.numerator if power >= 0: return Fraction(a._numerator ** power, - a._denominator ** power) + a._denominator ** power, + _normalize=False) else: return Fraction(a._denominator ** -power, - a._numerator ** -power) + a._numerator ** -power, + _normalize=False) else: # A fractional power will generally produce an # irrational number. @@ -480,15 +494,15 @@ class Fraction(numbers.Rational): def __pos__(a): """+a: Coerces a subclass instance to Fraction""" - return Fraction(a._numerator, a._denominator) + return Fraction(a._numerator, a._denominator, _normalize=False) def __neg__(a): """-a""" - return Fraction(-a._numerator, a._denominator) + return Fraction(-a._numerator, a._denominator, _normalize=False) def __abs__(a): """abs(a)""" - return Fraction(abs(a._numerator), a._denominator) + return Fraction(abs(a._numerator), a._denominator, _normalize=False) def __trunc__(a): """trunc(a)""" @@ -555,6 +569,8 @@ class Fraction(numbers.Rational): def __eq__(a, b): """a == b""" + if type(b) is int: + return a._numerator == b and a._denominator == 1 if isinstance(b, numbers.Rational): return (a._numerator == b.numerator and a._denominator == b.denominator) diff --git a/Lib/ftplib.py b/Lib/ftplib.py index cd8c1a9..135ec9c 100644 --- a/Lib/ftplib.py +++ b/Lib/ftplib.py @@ -42,7 +42,7 @@ import socket import warnings from socket import _GLOBAL_DEFAULT_TIMEOUT -__all__ = ["FTP", "Netrc"] +__all__ = ["FTP"] # Magic number from <socket.h> MSG_OOB = 0x1 # Process data out of band @@ -918,115 +918,6 @@ def ftpcp(source, sourcename, target, targetname = '', type = 'I'): target.voidresp() -class Netrc: - """Class to parse & provide access to 'netrc' format files. - - See the netrc(4) man page for information on the file format. - - WARNING: This class is obsolete -- use module netrc instead. - - """ - __defuser = None - __defpasswd = None - __defacct = None - - def __init__(self, filename=None): - warnings.warn("This class is deprecated, use the netrc module instead", - DeprecationWarning, 2) - if filename is None: - if "HOME" in os.environ: - filename = os.path.join(os.environ["HOME"], - ".netrc") - else: - raise OSError("specify file to load or set $HOME") - self.__hosts = {} - self.__macros = {} - fp = open(filename, "r") - in_macro = 0 - while 1: - line = fp.readline() - if not line: - break - if in_macro and line.strip(): - macro_lines.append(line) - continue - elif in_macro: - self.__macros[macro_name] = tuple(macro_lines) - in_macro = 0 - words = line.split() - host = user = passwd = acct = None - default = 0 - i = 0 - while i < len(words): - w1 = words[i] - if i+1 < len(words): - w2 = words[i + 1] - else: - w2 = None - if w1 == 'default': - default = 1 - elif w1 == 'machine' and w2: - host = w2.lower() - i = i + 1 - elif w1 == 'login' and w2: - user = w2 - i = i + 1 - elif w1 == 'password' and w2: - passwd = w2 - i = i + 1 - elif w1 == 'account' and w2: - acct = w2 - i = i + 1 - elif w1 == 'macdef' and w2: - macro_name = w2 - macro_lines = [] - in_macro = 1 - break - i = i + 1 - if default: - self.__defuser = user or self.__defuser - self.__defpasswd = passwd or self.__defpasswd - self.__defacct = acct or self.__defacct - if host: - if host in self.__hosts: - ouser, opasswd, oacct = \ - self.__hosts[host] - user = user or ouser - passwd = passwd or opasswd - acct = acct or oacct - self.__hosts[host] = user, passwd, acct - fp.close() - - def get_hosts(self): - """Return a list of hosts mentioned in the .netrc file.""" - return self.__hosts.keys() - - def get_account(self, host): - """Returns login information for the named host. - - The return value is a triple containing userid, - password, and the accounting field. - - """ - host = host.lower() - user = passwd = acct = None - if host in self.__hosts: - user, passwd, acct = self.__hosts[host] - user = user or self.__defuser - passwd = passwd or self.__defpasswd - acct = acct or self.__defacct - return user, passwd, acct - - def get_macros(self): - """Return a list of all defined macro names.""" - return self.__macros.keys() - - def get_macro(self, macro): - """Return a sequence of lines which define a named macro.""" - return self.__macros[macro] - - - def test(): '''Test program. Usage: ftp [-d] [-r[file]] host [-l[dir]] [-d[dir]] [-p] [file] ... @@ -1040,6 +931,8 @@ def test(): print(test.__doc__) sys.exit(0) + import netrc + debugging = 0 rcfile = None while sys.argv[1] == '-d': @@ -1054,14 +947,14 @@ def test(): ftp.set_debuglevel(debugging) userid = passwd = acct = '' try: - netrc = Netrc(rcfile) + netrcobj = netrc.netrc(rcfile) except OSError: if rcfile is not None: sys.stderr.write("Could not open account file" " -- using anonymous login.") else: try: - userid, passwd, acct = netrc.get_account(host) + userid, acct, passwd = netrcobj.authenticators(host) except KeyError: # no account for host sys.stderr.write( diff --git a/Lib/functools.py b/Lib/functools.py index 3e93a3d..91e9685 100644 --- a/Lib/functools.py +++ b/Lib/functools.py @@ -98,7 +98,7 @@ def _gt_from_lt(self, other): 'Return a > b. Computed by @total_ordering from (not a < b) and (a != b).' op_result = self.__lt__(other) if op_result is NotImplemented: - return NotImplemented + return op_result return not op_result and self != other def _le_from_lt(self, other): @@ -110,35 +110,35 @@ def _ge_from_lt(self, other): 'Return a >= b. Computed by @total_ordering from (not a < b).' op_result = self.__lt__(other) if op_result is NotImplemented: - return NotImplemented + return op_result return not op_result def _ge_from_le(self, other): 'Return a >= b. Computed by @total_ordering from (not a <= b) or (a == b).' op_result = self.__le__(other) if op_result is NotImplemented: - return NotImplemented + return op_result return not op_result or self == other def _lt_from_le(self, other): 'Return a < b. Computed by @total_ordering from (a <= b) and (a != b).' op_result = self.__le__(other) if op_result is NotImplemented: - return NotImplemented + return op_result return op_result and self != other def _gt_from_le(self, other): 'Return a > b. Computed by @total_ordering from (not a <= b).' op_result = self.__le__(other) if op_result is NotImplemented: - return NotImplemented + return op_result return not op_result def _lt_from_gt(self, other): 'Return a < b. Computed by @total_ordering from (not a > b) and (a != b).' op_result = self.__gt__(other) if op_result is NotImplemented: - return NotImplemented + return op_result return not op_result and self != other def _ge_from_gt(self, other): @@ -150,52 +150,53 @@ def _le_from_gt(self, other): 'Return a <= b. Computed by @total_ordering from (not a > b).' op_result = self.__gt__(other) if op_result is NotImplemented: - return NotImplemented + return op_result return not op_result def _le_from_ge(self, other): 'Return a <= b. Computed by @total_ordering from (not a >= b) or (a == b).' op_result = self.__ge__(other) if op_result is NotImplemented: - return NotImplemented + return op_result return not op_result or self == other def _gt_from_ge(self, other): 'Return a > b. Computed by @total_ordering from (a >= b) and (a != b).' op_result = self.__ge__(other) if op_result is NotImplemented: - return NotImplemented + return op_result return op_result and self != other def _lt_from_ge(self, other): 'Return a < b. Computed by @total_ordering from (not a >= b).' op_result = self.__ge__(other) if op_result is NotImplemented: - return NotImplemented + return op_result return not op_result +_convert = { + '__lt__': [('__gt__', _gt_from_lt), + ('__le__', _le_from_lt), + ('__ge__', _ge_from_lt)], + '__le__': [('__ge__', _ge_from_le), + ('__lt__', _lt_from_le), + ('__gt__', _gt_from_le)], + '__gt__': [('__lt__', _lt_from_gt), + ('__ge__', _ge_from_gt), + ('__le__', _le_from_gt)], + '__ge__': [('__le__', _le_from_ge), + ('__gt__', _gt_from_ge), + ('__lt__', _lt_from_ge)] +} + def total_ordering(cls): """Class decorator that fills in missing ordering methods""" - convert = { - '__lt__': [('__gt__', _gt_from_lt), - ('__le__', _le_from_lt), - ('__ge__', _ge_from_lt)], - '__le__': [('__ge__', _ge_from_le), - ('__lt__', _lt_from_le), - ('__gt__', _gt_from_le)], - '__gt__': [('__lt__', _lt_from_gt), - ('__ge__', _ge_from_gt), - ('__le__', _le_from_gt)], - '__ge__': [('__le__', _le_from_ge), - ('__gt__', _gt_from_ge), - ('__lt__', _lt_from_ge)] - } # Find user-defined comparisons (not those inherited from object). - roots = [op for op in convert if getattr(cls, op, None) is not getattr(object, op, None)] + roots = [op for op in _convert if getattr(cls, op, None) is not getattr(object, op, None)] if not roots: raise ValueError('must define at least one ordering operation: < > <= >=') root = max(roots) # prefer __lt__ to __le__ to __gt__ to __ge__ - for opname, opfunc in convert[root]: + for opname, opfunc in _convert[root]: if opname not in roots: opfunc.__name__ = opname setattr(cls, opname, opfunc) @@ -222,8 +223,6 @@ def cmp_to_key(mycmp): return mycmp(self.obj, other.obj) <= 0 def __ge__(self, other): return mycmp(self.obj, other.obj) >= 0 - def __ne__(self, other): - return mycmp(self.obj, other.obj) != 0 __hash__ = None return K @@ -242,6 +241,14 @@ def partial(func, *args, **keywords): """New function with partial application of the given arguments and keywords. """ + if hasattr(func, 'func'): + args = func.args + args + tmpkw = func.keywords.copy() + tmpkw.update(keywords) + keywords = tmpkw + del tmpkw + func = func.func + def newfunc(*fargs, **fkeywords): newkeywords = keywords.copy() newkeywords.update(fkeywords) @@ -291,7 +298,7 @@ class partialmethod(object): for k, v in self.keywords.items()) format_string = "{module}.{cls}({func}, {args}, {keywords})" return format_string.format(module=self.__class__.__module__, - cls=self.__class__.__name__, + cls=self.__class__.__qualname__, func=self.func, args=args, keywords=keywords) diff --git a/Lib/genericpath.py b/Lib/genericpath.py index ca4a510..6714061 100644 --- a/Lib/genericpath.py +++ b/Lib/genericpath.py @@ -130,3 +130,16 @@ def _splitext(p, sep, altsep, extsep): filenameIndex += 1 return p, p[:0] + +def _check_arg_types(funcname, *args): + hasstr = hasbytes = False + for s in args: + if isinstance(s, str): + hasstr = True + elif isinstance(s, bytes): + hasbytes = True + else: + raise TypeError('%s() argument must be str or bytes, not %r' % + (funcname, s.__class__.__name__)) from None + if hasstr and hasbytes: + raise TypeError("Can't mix strings and bytes in path components") from None diff --git a/Lib/gettext.py b/Lib/gettext.py index 05d9c1e..15378bc 100644 --- a/Lib/gettext.py +++ b/Lib/gettext.py @@ -225,6 +225,13 @@ class GNUTranslations(NullTranslations): LE_MAGIC = 0x950412de BE_MAGIC = 0xde120495 + # Acceptable .mo versions + VERSIONS = (0, 1) + + def _get_versions(self, version): + """Returns a tuple of major version, minor version""" + return (version >> 16, version & 0xffff) + def _parse(self, fp): """Override this method to support alternative .mo formats.""" unpack = struct.unpack @@ -245,6 +252,12 @@ class GNUTranslations(NullTranslations): ii = '>II' else: raise OSError(0, 'Bad magic number', filename) + + major_version, minor_version = self._get_versions(version) + + if major_version not in self.VERSIONS: + raise OSError(0, 'Bad version number ' + str(major_version), filename) + # Now put all messages from the .mo file buffer into the catalog # dictionary. for i in range(0, msgcount): diff --git a/Lib/glob.py b/Lib/glob.py index d6eca24..56d6704 100644 --- a/Lib/glob.py +++ b/Lib/glob.py @@ -6,7 +6,7 @@ import fnmatch __all__ = ["glob", "iglob"] -def glob(pathname): +def glob(pathname, *, recursive=False): """Return a list of paths matching a pathname pattern. The pattern may contain simple shell-style wildcards a la @@ -14,10 +14,12 @@ def glob(pathname): dot are special cases that are not matched by '*' and '?' patterns. + If recursive is true, the pattern '**' will match any files and + zero or more directories and subdirectories. """ - return list(iglob(pathname)) + return list(iglob(pathname, recursive=recursive)) -def iglob(pathname): +def iglob(pathname, *, recursive=False): """Return an iterator which yields the paths matching a pathname pattern. The pattern may contain simple shell-style wildcards a la @@ -25,6 +27,8 @@ def iglob(pathname): dot are special cases that are not matched by '*' and '?' patterns. + If recursive is true, the pattern '**' will match any files and + zero or more directories and subdirectories. """ dirname, basename = os.path.split(pathname) if not has_magic(pathname): @@ -37,17 +41,23 @@ def iglob(pathname): yield pathname return if not dirname: - yield from glob1(None, basename) + if recursive and _isrecursive(basename): + yield from glob2(dirname, basename) + else: + yield from glob1(dirname, basename) return # `os.path.split()` returns the argument itself as a dirname if it is a # drive or UNC path. Prevent an infinite recursion if a drive or UNC path # contains magic characters (i.e. r'\\?\C:'). if dirname != pathname and has_magic(dirname): - dirs = iglob(dirname) + dirs = iglob(dirname, recursive=recursive) else: dirs = [dirname] if has_magic(basename): - glob_in_dir = glob1 + if recursive and _isrecursive(basename): + glob_in_dir = glob2 + else: + glob_in_dir = glob1 else: glob_in_dir = glob0 for dirname in dirs: @@ -83,6 +93,34 @@ def glob0(dirname, basename): return [basename] return [] +# This helper function recursively yields relative pathnames inside a literal +# directory. + +def glob2(dirname, pattern): + assert _isrecursive(pattern) + if dirname: + yield pattern[:0] + yield from _rlistdir(dirname) + +# Recursively yields relative pathnames inside a literal directory. + +def _rlistdir(dirname): + if not dirname: + if isinstance(dirname, bytes): + dirname = bytes(os.curdir, 'ASCII') + else: + dirname = os.curdir + try: + names = os.listdir(dirname) + except os.error: + return + for x in names: + if not _ishidden(x): + yield x + path = os.path.join(dirname, x) if dirname else x + for y in _rlistdir(path): + yield os.path.join(x, y) + magic_check = re.compile('([*?[])') magic_check_bytes = re.compile(b'([*?[])') @@ -97,6 +135,12 @@ def has_magic(s): def _ishidden(path): return path[0] in ('.', b'.'[0]) +def _isrecursive(pattern): + if isinstance(pattern, bytes): + return pattern == b'**' + else: + return pattern == '**' + def escape(pathname): """Escape all special characters. """ diff --git a/Lib/heapq.py b/Lib/heapq.py index d615239..07af37e 100644 --- a/Lib/heapq.py +++ b/Lib/heapq.py @@ -127,8 +127,6 @@ From all times, sorting has always been a Great Art! :-) __all__ = ['heappush', 'heappop', 'heapify', 'heapreplace', 'merge', 'nlargest', 'nsmallest', 'heappushpop'] -from itertools import islice, count, tee, chain - def heappush(heap, item): """Push item onto heap, maintaining the heap invariant.""" heap.append(item) @@ -141,9 +139,8 @@ def heappop(heap): returnitem = heap[0] heap[0] = lastelt _siftup(heap, 0) - else: - returnitem = lastelt - return returnitem + return returnitem + return lastelt def heapreplace(heap, item): """Pop and return the current smallest value, and add the new item. @@ -179,12 +176,22 @@ def heapify(x): for i in reversed(range(n//2)): _siftup(x, i) -def _heappushpop_max(heap, item): - """Maxheap version of a heappush followed by a heappop.""" - if heap and item < heap[0]: - item, heap[0] = heap[0], item +def _heappop_max(heap): + """Maxheap version of a heappop.""" + lastelt = heap.pop() # raises appropriate IndexError if heap is empty + if heap: + returnitem = heap[0] + heap[0] = lastelt _siftup_max(heap, 0) - return item + return returnitem + return lastelt + +def _heapreplace_max(heap, item): + """Maxheap version of a heappop followed by a heappush.""" + returnitem = heap[0] # raises appropriate IndexError if heap is empty + heap[0] = item + _siftup_max(heap, 0) + return returnitem def _heapify_max(x): """Transform list into a maxheap, in-place, in O(len(x)) time.""" @@ -192,42 +199,6 @@ def _heapify_max(x): for i in reversed(range(n//2)): _siftup_max(x, i) -def nlargest(n, iterable): - """Find the n largest elements in a dataset. - - Equivalent to: sorted(iterable, reverse=True)[:n] - """ - if n < 0: - return [] - it = iter(iterable) - result = list(islice(it, n)) - if not result: - return result - heapify(result) - _heappushpop = heappushpop - for elem in it: - _heappushpop(result, elem) - result.sort(reverse=True) - return result - -def nsmallest(n, iterable): - """Find the n smallest elements in a dataset. - - Equivalent to: sorted(iterable)[:n] - """ - if n < 0: - return [] - it = iter(iterable) - result = list(islice(it, n)) - if not result: - return result - _heapify_max(result) - _heappushpop = _heappushpop_max - for elem in it: - _heappushpop(result, elem) - result.sort() - return result - # 'heap' is a heap at all indices >= startpos, except possibly for pos. pos # is the index of a leaf with a possibly out-of-order value. Restore the # heap invariant. @@ -340,13 +311,7 @@ def _siftup_max(heap, pos): heap[pos] = newitem _siftdown_max(heap, startpos, pos) -# If available, use C implementation -try: - from _heapq import * -except ImportError: - pass - -def merge(*iterables): +def merge(*iterables, key=None, reverse=False): '''Merge multiple sorted inputs into a single sorted output. Similar to sorted(itertools.chain(*iterables)) but returns a generator, @@ -356,51 +321,158 @@ def merge(*iterables): >>> list(merge([1,3,5,7], [0,2,4,8], [5,10,15,20], [], [25])) [0, 1, 2, 3, 4, 5, 5, 7, 8, 10, 15, 20, 25] + If *key* is not None, applies a key function to each element to determine + its sort order. + + >>> list(merge(['dog', 'horse'], ['cat', 'fish', 'kangaroo'], key=len)) + ['dog', 'cat', 'fish', 'horse', 'kangaroo'] + ''' - _heappop, _heapreplace, _StopIteration = heappop, heapreplace, StopIteration - _len = len h = [] h_append = h.append - for itnum, it in enumerate(map(iter, iterables)): + + if reverse: + _heapify = _heapify_max + _heappop = _heappop_max + _heapreplace = _heapreplace_max + direction = -1 + else: + _heapify = heapify + _heappop = heappop + _heapreplace = heapreplace + direction = 1 + + if key is None: + for order, it in enumerate(map(iter, iterables)): + try: + next = it.__next__ + h_append([next(), order * direction, next]) + except StopIteration: + pass + _heapify(h) + while len(h) > 1: + try: + while True: + value, order, next = s = h[0] + yield value + s[0] = next() # raises StopIteration when exhausted + _heapreplace(h, s) # restore heap condition + except StopIteration: + _heappop(h) # remove empty iterator + if h: + # fast case when only a single iterator remains + value, order, next = h[0] + yield value + yield from next.__self__ + return + + for order, it in enumerate(map(iter, iterables)): try: next = it.__next__ - h_append([next(), itnum, next]) - except _StopIteration: + value = next() + h_append([key(value), order * direction, value, next]) + except StopIteration: pass - heapify(h) - - while _len(h) > 1: + _heapify(h) + while len(h) > 1: try: while True: - v, itnum, next = s = h[0] - yield v - s[0] = next() # raises StopIteration when exhausted - _heapreplace(h, s) # restore heap condition - except _StopIteration: - _heappop(h) # remove empty iterator + key_value, order, value, next = s = h[0] + yield value + value = next() + s[0] = key(value) + s[2] = value + _heapreplace(h, s) + except StopIteration: + _heappop(h) if h: - # fast case when only a single iterator remains - v, itnum, next = h[0] - yield v + key_value, order, value, next = h[0] + yield value yield from next.__self__ -# Extend the implementations of nsmallest and nlargest to use a key= argument -_nsmallest = nsmallest + +# Algorithm notes for nlargest() and nsmallest() +# ============================================== +# +# Make a single pass over the data while keeping the k most extreme values +# in a heap. Memory consumption is limited to keeping k values in a list. +# +# Measured performance for random inputs: +# +# number of comparisons +# n inputs k-extreme values (average of 5 trials) % more than min() +# ------------- ---------------- --------------------- ----------------- +# 1,000 100 3,317 231.7% +# 10,000 100 14,046 40.5% +# 100,000 100 105,749 5.7% +# 1,000,000 100 1,007,751 0.8% +# 10,000,000 100 10,009,401 0.1% +# +# Theoretical number of comparisons for k smallest of n random inputs: +# +# Step Comparisons Action +# ---- -------------------------- --------------------------- +# 1 1.66 * k heapify the first k-inputs +# 2 n - k compare remaining elements to top of heap +# 3 k * (1 + lg2(k)) * ln(n/k) replace the topmost value on the heap +# 4 k * lg2(k) - (k/2) final sort of the k most extreme values +# +# Combining and simplifying for a rough estimate gives: +# +# comparisons = n + k * (log(k, 2) * log(n/k) + log(k, 2) + log(n/k)) +# +# Computing the number of comparisons for step 3: +# ----------------------------------------------- +# * For the i-th new value from the iterable, the probability of being in the +# k most extreme values is k/i. For example, the probability of the 101st +# value seen being in the 100 most extreme values is 100/101. +# * If the value is a new extreme value, the cost of inserting it into the +# heap is 1 + log(k, 2). +# * The probability times the cost gives: +# (k/i) * (1 + log(k, 2)) +# * Summing across the remaining n-k elements gives: +# sum((k/i) * (1 + log(k, 2)) for i in range(k+1, n+1)) +# * This reduces to: +# (H(n) - H(k)) * k * (1 + log(k, 2)) +# * Where H(n) is the n-th harmonic number estimated by: +# gamma = 0.5772156649 +# H(n) = log(n, e) + gamma + 1 / (2 * n) +# http://en.wikipedia.org/wiki/Harmonic_series_(mathematics)#Rate_of_divergence +# * Substituting the H(n) formula: +# comparisons = k * (1 + log(k, 2)) * (log(n/k, e) + (1/n - 1/k) / 2) +# +# Worst-case for step 3: +# ---------------------- +# In the worst case, the input data is reversed sorted so that every new element +# must be inserted in the heap: +# +# comparisons = 1.66 * k + log(k, 2) * (n - k) +# +# Alternative Algorithms +# ---------------------- +# Other algorithms were not used because they: +# 1) Took much more auxiliary memory, +# 2) Made multiple passes over the data. +# 3) Made more comparisons in common cases (small k, large n, semi-random input). +# See the more detailed comparison of approach at: +# http://code.activestate.com/recipes/577573-compare-algorithms-for-heapqsmallest + def nsmallest(n, iterable, key=None): """Find the n smallest elements in a dataset. Equivalent to: sorted(iterable, key=key)[:n] """ - # Short-cut for n==1 is to use min() when len(iterable)>0 + + # Short-cut for n==1 is to use min() if n == 1: it = iter(iterable) - head = list(islice(it, 1)) - if not head: - return [] + sentinel = object() if key is None: - return [min(chain(head, it))] - return [min(chain(head, it), key=key)] + result = min(it, default=sentinel) + else: + result = min(it, default=sentinel, key=key) + return [] if result is sentinel else [result] # When n>=size, it's faster to use sorted() try: @@ -413,32 +485,57 @@ def nsmallest(n, iterable, key=None): # When key is none, use simpler decoration if key is None: - it = zip(iterable, count()) # decorate - result = _nsmallest(n, it) - return [r[0] for r in result] # undecorate + it = iter(iterable) + # put the range(n) first so that zip() doesn't + # consume one too many elements from the iterator + result = [(elem, i) for i, elem in zip(range(n), it)] + if not result: + return result + _heapify_max(result) + top = result[0][0] + order = n + _heapreplace = _heapreplace_max + for elem in it: + if elem < top: + _heapreplace(result, (elem, order)) + top = result[0][0] + order += 1 + result.sort() + return [r[0] for r in result] # General case, slowest method - in1, in2 = tee(iterable) - it = zip(map(key, in1), count(), in2) # decorate - result = _nsmallest(n, it) - return [r[2] for r in result] # undecorate + it = iter(iterable) + result = [(key(elem), i, elem) for i, elem in zip(range(n), it)] + if not result: + return result + _heapify_max(result) + top = result[0][0] + order = n + _heapreplace = _heapreplace_max + for elem in it: + k = key(elem) + if k < top: + _heapreplace(result, (k, order, elem)) + top = result[0][0] + order += 1 + result.sort() + return [r[2] for r in result] -_nlargest = nlargest def nlargest(n, iterable, key=None): """Find the n largest elements in a dataset. Equivalent to: sorted(iterable, key=key, reverse=True)[:n] """ - # Short-cut for n==1 is to use max() when len(iterable)>0 + # Short-cut for n==1 is to use max() if n == 1: it = iter(iterable) - head = list(islice(it, 1)) - if not head: - return [] + sentinel = object() if key is None: - return [max(chain(head, it))] - return [max(chain(head, it), key=key)] + result = max(it, default=sentinel) + else: + result = max(it, default=sentinel, key=key) + return [] if result is sentinel else [result] # When n>=size, it's faster to use sorted() try: @@ -451,26 +548,60 @@ def nlargest(n, iterable, key=None): # When key is none, use simpler decoration if key is None: - it = zip(iterable, count(0,-1)) # decorate - result = _nlargest(n, it) - return [r[0] for r in result] # undecorate + it = iter(iterable) + result = [(elem, i) for i, elem in zip(range(0, -n, -1), it)] + if not result: + return result + heapify(result) + top = result[0][0] + order = -n + _heapreplace = heapreplace + for elem in it: + if top < elem: + _heapreplace(result, (elem, order)) + top = result[0][0] + order -= 1 + result.sort(reverse=True) + return [r[0] for r in result] # General case, slowest method - in1, in2 = tee(iterable) - it = zip(map(key, in1), count(0,-1), in2) # decorate - result = _nlargest(n, it) - return [r[2] for r in result] # undecorate + it = iter(iterable) + result = [(key(elem), i, elem) for i, elem in zip(range(0, -n, -1), it)] + if not result: + return result + heapify(result) + top = result[0][0] + order = -n + _heapreplace = heapreplace + for elem in it: + k = key(elem) + if top < k: + _heapreplace(result, (k, order, elem)) + top = result[0][0] + order -= 1 + result.sort(reverse=True) + return [r[2] for r in result] + +# If available, use C implementation +try: + from _heapq import * +except ImportError: + pass +try: + from _heapq import _heapreplace_max +except ImportError: + pass +try: + from _heapq import _heapify_max +except ImportError: + pass +try: + from _heapq import _heappop_max +except ImportError: + pass + if __name__ == "__main__": - # Simple sanity test - heap = [] - data = [1, 3, 5, 7, 9, 2, 4, 6, 8, 0] - for item in data: - heappush(heap, item) - sort = [] - while heap: - sort.append(heappop(heap)) - print(sort) import doctest - doctest.testmod() + print(doctest.testmod()) diff --git a/Lib/html/entities.py b/Lib/html/entities.py index f7deae6..3e1778b 100644 --- a/Lib/html/entities.py +++ b/Lib/html/entities.py @@ -1,5 +1,8 @@ """HTML character entity references.""" +__all__ = ['html5', 'name2codepoint', 'codepoint2name', 'entitydefs'] + + # maps the HTML entity name to the Unicode code point name2codepoint = { 'AElig': 0x00c6, # latin capital letter AE = latin capital ligature AE, U+00C6 ISOlat1 diff --git a/Lib/html/parser.py b/Lib/html/parser.py index a650d5e..390d4cc 100644 --- a/Lib/html/parser.py +++ b/Lib/html/parser.py @@ -29,35 +29,15 @@ starttagopen = re.compile('<[a-zA-Z]') piclose = re.compile('>') commentclose = re.compile(r'--\s*>') # Note: -# 1) the strict attrfind isn't really strict, but we can't make it -# correctly strict without breaking backward compatibility; -# 2) if you change tagfind/attrfind remember to update locatestarttagend too; -# 3) if you change tagfind/attrfind and/or locatestarttagend the parser will +# 1) if you change tagfind/attrfind remember to update locatestarttagend too; +# 2) if you change tagfind/attrfind and/or locatestarttagend the parser will # explode, so don't do it. -tagfind = re.compile('([a-zA-Z][-.a-zA-Z0-9:_]*)(?:\s|/(?!>))*') # see http://www.w3.org/TR/html5/tokenization.html#tag-open-state # and http://www.w3.org/TR/html5/tokenization.html#tag-name-state tagfind_tolerant = re.compile('([a-zA-Z][^\t\n\r\f />\x00]*)(?:\s|/(?!>))*') -attrfind = re.compile( - r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*' - r'(\'[^\']*\'|"[^"]*"|[^\s"\'=<>`]*))?') attrfind_tolerant = re.compile( r'((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*' r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*') -locatestarttagend = re.compile(r""" - <[a-zA-Z][-.a-zA-Z0-9:_]* # tag name - (?:\s+ # whitespace before attribute name - (?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name - (?:\s*=\s* # value indicator - (?:'[^']*' # LITA-enclosed value - |\"[^\"]*\" # LIT-enclosed value - |[^'\">\s]+ # bare value - ) - )? - ) - )* - \s* # trailing whitespace -""", re.VERBOSE) locatestarttagend_tolerant = re.compile(r""" <[a-zA-Z][^\t\n\r\f />\x00]* # tag name (?:[\s/]* # optional whitespace before attribute name @@ -79,25 +59,6 @@ endendtag = re.compile('>') endtagfind = re.compile('</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>') -class HTMLParseError(Exception): - """Exception raised for all parse errors.""" - - def __init__(self, msg, position=(None, None)): - assert msg - self.msg = msg - self.lineno = position[0] - self.offset = position[1] - - def __str__(self): - result = self.msg - if self.lineno is not None: - result = result + ", at line %d" % self.lineno - if self.offset is not None: - result = result + ", column %d" % (self.offset + 1) - return result - - -_default_sentinel = object() class HTMLParser(_markupbase.ParserBase): """Find tags and other markup and call handler functions. @@ -123,27 +84,12 @@ class HTMLParser(_markupbase.ParserBase): CDATA_CONTENT_ELEMENTS = ("script", "style") - def __init__(self, strict=_default_sentinel, *, - convert_charrefs=_default_sentinel): + def __init__(self, *, convert_charrefs=True): """Initialize and reset this instance. - If convert_charrefs is True (default: False), all character references + If convert_charrefs is True (the default), all character references are automatically converted to the corresponding Unicode characters. - If strict is set to False (the default) the parser will parse invalid - markup, otherwise it will raise an error. Note that the strict mode - and argument are deprecated. """ - if strict is not _default_sentinel: - warnings.warn("The strict argument and mode are deprecated.", - DeprecationWarning, stacklevel=2) - else: - strict = False # default - self.strict = strict - if convert_charrefs is _default_sentinel: - convert_charrefs = False # default - warnings.warn("The value of convert_charrefs will become True in " - "3.5. You are encouraged to set the value explicitly.", - DeprecationWarning, stacklevel=2) self.convert_charrefs = convert_charrefs self.reset() @@ -168,11 +114,6 @@ class HTMLParser(_markupbase.ParserBase): """Handle any buffered data.""" self.goahead(1) - def error(self, message): - warnings.warn("The 'error' method is deprecated.", - DeprecationWarning, stacklevel=2) - raise HTMLParseError(message, self.getpos()) - __starttag_text = None def get_starttag_text(self): @@ -227,10 +168,7 @@ class HTMLParser(_markupbase.ParserBase): elif startswith("<?", i): k = self.parse_pi(i) elif startswith("<!", i): - if self.strict: - k = self.parse_declaration(i) - else: - k = self.parse_html_declaration(i) + k = self.parse_html_declaration(i) elif (i + 1) < n: self.handle_data("<") k = i + 1 @@ -239,8 +177,6 @@ class HTMLParser(_markupbase.ParserBase): if k < 0: if not end: break - if self.strict: - self.error("EOF in middle of construct") k = rawdata.find('>', i + 1) if k < 0: k = rawdata.find('<', i + 1) @@ -282,13 +218,10 @@ class HTMLParser(_markupbase.ParserBase): if match: # match.group() will contain at least 2 chars if end and match.group() == rawdata[i:]: - if self.strict: - self.error("EOF in middle of entity or char ref") - else: - k = match.end() - if k <= i: - k = n - i = self.updatepos(i, i + 1) + k = match.end() + if k <= i: + k = n + i = self.updatepos(i, i + 1) # incomplete break elif (i + 1) < n: @@ -367,18 +300,12 @@ class HTMLParser(_markupbase.ParserBase): # Now parse the data between i+1 and j into a tag and attrs attrs = [] - if self.strict: - match = tagfind.match(rawdata, i+1) - else: - match = tagfind_tolerant.match(rawdata, i+1) + match = tagfind_tolerant.match(rawdata, i+1) assert match, 'unexpected call to parse_starttag()' k = match.end() self.lasttag = tag = match.group(1).lower() while k < endpos: - if self.strict: - m = attrfind.match(rawdata, k) - else: - m = attrfind_tolerant.match(rawdata, k) + m = attrfind_tolerant.match(rawdata, k) if not m: break attrname, rest, attrvalue = m.group(1, 2, 3) @@ -401,9 +328,6 @@ class HTMLParser(_markupbase.ParserBase): - self.__starttag_text.rfind("\n") else: offset = offset + len(self.__starttag_text) - if self.strict: - self.error("junk characters in start tag: %r" - % (rawdata[k:endpos][:20],)) self.handle_data(rawdata[i:endpos]) return endpos if end.endswith('/>'): @@ -419,10 +343,7 @@ class HTMLParser(_markupbase.ParserBase): # or -1 if incomplete. def check_for_whole_start_tag(self, i): rawdata = self.rawdata - if self.strict: - m = locatestarttagend.match(rawdata, i) - else: - m = locatestarttagend_tolerant.match(rawdata, i) + m = locatestarttagend_tolerant.match(rawdata, i) if m: j = m.end() next = rawdata[j:j+1] @@ -435,9 +356,6 @@ class HTMLParser(_markupbase.ParserBase): # buffer boundary return -1 # else bogus input - if self.strict: - self.updatepos(i, j + 1) - self.error("malformed empty start tag") if j > i: return j else: @@ -450,9 +368,6 @@ class HTMLParser(_markupbase.ParserBase): # end of input in or before attribute value, or we have the # '/' from a '/>' ending return -1 - if self.strict: - self.updatepos(i, j) - self.error("malformed start tag") if j > i: return j else: @@ -472,8 +387,6 @@ class HTMLParser(_markupbase.ParserBase): if self.cdata_elem is not None: self.handle_data(rawdata[i:gtpos]) return gtpos - if self.strict: - self.error("bad end tag: %r" % (rawdata[i:gtpos],)) # find the name: w3.org/TR/html5/tokenization.html#tag-name-state namematch = tagfind_tolerant.match(rawdata, i+2) if not namematch: @@ -539,8 +452,7 @@ class HTMLParser(_markupbase.ParserBase): pass def unknown_decl(self, data): - if self.strict: - self.error("unknown declaration: %r" % (data,)) + pass # Internal -- helper to remove special character quoting def unescape(self, s): diff --git a/Lib/http/__init__.py b/Lib/http/__init__.py index 196d378..d4334cc 100644 --- a/Lib/http/__init__.py +++ b/Lib/http/__init__.py @@ -1 +1,134 @@ -# This directory is a Python package. +from enum import IntEnum + +__all__ = ['HTTPStatus'] + +class HTTPStatus(IntEnum): + """HTTP status codes and reason phrases + + Status codes from the following RFCs are all observed: + + * RFC 7231: Hypertext Transfer Protocol (HTTP/1.1), obsoletes 2616 + * RFC 6585: Additional HTTP Status Codes + * RFC 3229: Delta encoding in HTTP + * RFC 4918: HTTP Extensions for WebDAV, obsoletes 2518 + * RFC 5842: Binding Extensions to WebDAV + * RFC 7238: Permanent Redirect + * RFC 2295: Transparent Content Negotiation in HTTP + * RFC 2774: An HTTP Extension Framework + """ + def __new__(cls, value, phrase, description=''): + obj = int.__new__(cls, value) + obj._value_ = value + + obj.phrase = phrase + obj.description = description + return obj + + # informational + CONTINUE = 100, 'Continue', 'Request received, please continue' + SWITCHING_PROTOCOLS = (101, 'Switching Protocols', + 'Switching to new protocol; obey Upgrade header') + PROCESSING = 102, 'Processing' + + # success + OK = 200, 'OK', 'Request fulfilled, document follows' + CREATED = 201, 'Created', 'Document created, URL follows' + ACCEPTED = (202, 'Accepted', + 'Request accepted, processing continues off-line') + NON_AUTHORITATIVE_INFORMATION = (203, + 'Non-Authoritative Information', 'Request fulfilled from cache') + NO_CONTENT = 204, 'No Content', 'Request fulfilled, nothing follows' + RESET_CONTENT = 205, 'Reset Content', 'Clear input form for further input' + PARTIAL_CONTENT = 206, 'Partial Content', 'Partial content follows' + MULTI_STATUS = 207, 'Multi-Status' + ALREADY_REPORTED = 208, 'Already Reported' + IM_USED = 226, 'IM Used' + + # redirection + MULTIPLE_CHOICES = (300, 'Multiple Choices', + 'Object has several resources -- see URI list') + MOVED_PERMANENTLY = (301, 'Moved Permanently', + 'Object moved permanently -- see URI list') + FOUND = 302, 'Found', 'Object moved temporarily -- see URI list' + SEE_OTHER = 303, 'See Other', 'Object moved -- see Method and URL list' + NOT_MODIFIED = (304, 'Not Modified', + 'Document has not changed since given time') + USE_PROXY = (305, 'Use Proxy', + 'You must use proxy specified in Location to access this resource') + TEMPORARY_REDIRECT = (307, 'Temporary Redirect', + 'Object moved temporarily -- see URI list') + PERMANENT_REDIRECT = (308, 'Permanent Redirect', + 'Object moved temporarily -- see URI list') + + # client error + BAD_REQUEST = (400, 'Bad Request', + 'Bad request syntax or unsupported method') + UNAUTHORIZED = (401, 'Unauthorized', + 'No permission -- see authorization schemes') + PAYMENT_REQUIRED = (402, 'Payment Required', + 'No payment -- see charging schemes') + FORBIDDEN = (403, 'Forbidden', + 'Request forbidden -- authorization will not help') + NOT_FOUND = (404, 'Not Found', + 'Nothing matches the given URI') + METHOD_NOT_ALLOWED = (405, 'Method Not Allowed', + 'Specified method is invalid for this resource') + NOT_ACCEPTABLE = (406, 'Not Acceptable', + 'URI not available in preferred format') + PROXY_AUTHENTICATION_REQUIRED = (407, + 'Proxy Authentication Required', + 'You must authenticate with this proxy before proceeding') + REQUEST_TIMEOUT = (408, 'Request Timeout', + 'Request timed out; try again later') + CONFLICT = 409, 'Conflict', 'Request conflict' + GONE = (410, 'Gone', + 'URI no longer exists and has been permanently removed') + LENGTH_REQUIRED = (411, 'Length Required', + 'Client must specify Content-Length') + PRECONDITION_FAILED = (412, 'Precondition Failed', + 'Precondition in headers is false') + REQUEST_ENTITY_TOO_LARGE = (413, 'Request Entity Too Large', + 'Entity is too large') + REQUEST_URI_TOO_LONG = (414, 'Request-URI Too Long', + 'URI is too long') + UNSUPPORTED_MEDIA_TYPE = (415, 'Unsupported Media Type', + 'Entity body in unsupported format') + REQUESTED_RANGE_NOT_SATISFIABLE = (416, + 'Requested Range Not Satisfiable', + 'Cannot satisfy request range') + EXPECTATION_FAILED = (417, 'Expectation Failed', + 'Expect condition could not be satisfied') + UNPROCESSABLE_ENTITY = 422, 'Unprocessable Entity' + LOCKED = 423, 'Locked' + FAILED_DEPENDENCY = 424, 'Failed Dependency' + UPGRADE_REQUIRED = 426, 'Upgrade Required' + PRECONDITION_REQUIRED = (428, 'Precondition Required', + 'The origin server requires the request to be conditional') + TOO_MANY_REQUESTS = (429, 'Too Many Requests', + 'The user has sent too many requests in ' + 'a given amount of time ("rate limiting")') + REQUEST_HEADER_FIELDS_TOO_LARGE = (431, + 'Request Header Fields Too Large', + 'The server is unwilling to process the request because its header ' + 'fields are too large') + + # server errors + INTERNAL_SERVER_ERROR = (500, 'Internal Server Error', + 'Server got itself in trouble') + NOT_IMPLEMENTED = (501, 'Not Implemented', + 'Server does not support this operation') + BAD_GATEWAY = (502, 'Bad Gateway', + 'Invalid responses from another server/proxy') + SERVICE_UNAVAILABLE = (503, 'Service Unavailable', + 'The server cannot process the request due to a high load') + GATEWAY_TIMEOUT = (504, 'Gateway Timeout', + 'The gateway server did not receive a timely response') + HTTP_VERSION_NOT_SUPPORTED = (505, 'HTTP Version Not Supported', + 'Cannot fulfill request') + VARIANT_ALSO_NEGOTIATES = 506, 'Variant Also Negotiates' + INSUFFICIENT_STORAGE = 507, 'Insufficient Storage' + LOOP_DETECTED = 508, 'Loop Detected' + NOT_EXTENDED = 510, 'Not Extended' + NETWORK_AUTHENTICATION_REQUIRED = (511, + 'Network Authentication Required', + 'The client needs to authenticate to gain network access') diff --git a/Lib/http/client.py b/Lib/http/client.py index d3d9b30..5e12a85 100644 --- a/Lib/http/client.py +++ b/Lib/http/client.py @@ -68,6 +68,7 @@ Req-sent-unread-response _CS_REQ_SENT <response_class> import email.parser import email.message +import http import io import os import socket @@ -93,122 +94,13 @@ _CS_IDLE = 'Idle' _CS_REQ_STARTED = 'Request-started' _CS_REQ_SENT = 'Request-sent' -# status codes -# informational -CONTINUE = 100 -SWITCHING_PROTOCOLS = 101 -PROCESSING = 102 - -# successful -OK = 200 -CREATED = 201 -ACCEPTED = 202 -NON_AUTHORITATIVE_INFORMATION = 203 -NO_CONTENT = 204 -RESET_CONTENT = 205 -PARTIAL_CONTENT = 206 -MULTI_STATUS = 207 -IM_USED = 226 - -# redirection -MULTIPLE_CHOICES = 300 -MOVED_PERMANENTLY = 301 -FOUND = 302 -SEE_OTHER = 303 -NOT_MODIFIED = 304 -USE_PROXY = 305 -TEMPORARY_REDIRECT = 307 - -# client error -BAD_REQUEST = 400 -UNAUTHORIZED = 401 -PAYMENT_REQUIRED = 402 -FORBIDDEN = 403 -NOT_FOUND = 404 -METHOD_NOT_ALLOWED = 405 -NOT_ACCEPTABLE = 406 -PROXY_AUTHENTICATION_REQUIRED = 407 -REQUEST_TIMEOUT = 408 -CONFLICT = 409 -GONE = 410 -LENGTH_REQUIRED = 411 -PRECONDITION_FAILED = 412 -REQUEST_ENTITY_TOO_LARGE = 413 -REQUEST_URI_TOO_LONG = 414 -UNSUPPORTED_MEDIA_TYPE = 415 -REQUESTED_RANGE_NOT_SATISFIABLE = 416 -EXPECTATION_FAILED = 417 -UNPROCESSABLE_ENTITY = 422 -LOCKED = 423 -FAILED_DEPENDENCY = 424 -UPGRADE_REQUIRED = 426 -PRECONDITION_REQUIRED = 428 -TOO_MANY_REQUESTS = 429 -REQUEST_HEADER_FIELDS_TOO_LARGE = 431 - -# server error -INTERNAL_SERVER_ERROR = 500 -NOT_IMPLEMENTED = 501 -BAD_GATEWAY = 502 -SERVICE_UNAVAILABLE = 503 -GATEWAY_TIMEOUT = 504 -HTTP_VERSION_NOT_SUPPORTED = 505 -INSUFFICIENT_STORAGE = 507 -NOT_EXTENDED = 510 -NETWORK_AUTHENTICATION_REQUIRED = 511 +# hack to maintain backwards compatibility +globals().update(http.HTTPStatus.__members__) + +# another hack to maintain backwards compatibility # Mapping status codes to official W3C names -responses = { - 100: 'Continue', - 101: 'Switching Protocols', - - 200: 'OK', - 201: 'Created', - 202: 'Accepted', - 203: 'Non-Authoritative Information', - 204: 'No Content', - 205: 'Reset Content', - 206: 'Partial Content', - - 300: 'Multiple Choices', - 301: 'Moved Permanently', - 302: 'Found', - 303: 'See Other', - 304: 'Not Modified', - 305: 'Use Proxy', - 306: '(Unused)', - 307: 'Temporary Redirect', - - 400: 'Bad Request', - 401: 'Unauthorized', - 402: 'Payment Required', - 403: 'Forbidden', - 404: 'Not Found', - 405: 'Method Not Allowed', - 406: 'Not Acceptable', - 407: 'Proxy Authentication Required', - 408: 'Request Timeout', - 409: 'Conflict', - 410: 'Gone', - 411: 'Length Required', - 412: 'Precondition Failed', - 413: 'Request Entity Too Large', - 414: 'Request-URI Too Long', - 415: 'Unsupported Media Type', - 416: 'Requested Range Not Satisfiable', - 417: 'Expectation Failed', - 428: 'Precondition Required', - 429: 'Too Many Requests', - 431: 'Request Header Fields Too Large', - - 500: 'Internal Server Error', - 501: 'Not Implemented', - 502: 'Bad Gateway', - 503: 'Service Unavailable', - 504: 'Gateway Timeout', - 505: 'HTTP Version Not Supported', - 511: 'Network Authentication Required', -} +responses = {v: v.phrase for v in http.HTTPStatus.__members__.values()} # maximal amount of data to read at one time in _safe_read MAXAMOUNT = 1048576 @@ -272,7 +164,7 @@ def parse_headers(fp, _class=HTTPMessage): return email.parser.Parser(_class=_class).parsestr(hstring) -class HTTPResponse(io.RawIOBase): +class HTTPResponse(io.BufferedIOBase): # See RFC 2616 sec 19.6 and RFC 1945 sec 6 for details. @@ -497,9 +389,10 @@ class HTTPResponse(io.RawIOBase): return b"" if amt is not None: - # Amount is given, so call base class version - # (which is implemented in terms of self.readinto) - return super(HTTPResponse, self).read(amt) + # Amount is given, implement using readinto + b = bytearray(amt) + n = self.readinto(b) + return memoryview(b)[:n].tobytes() else: # Amount is not given (unbounded read) so we must check self.length # and self.chunked @@ -579,71 +472,67 @@ class HTTPResponse(io.RawIOBase): if line in (b'\r\n', b'\n', b''): break + def _get_chunk_left(self): + # return self.chunk_left, reading a new chunk if necessary. + # chunk_left == 0: at the end of the current chunk, need to close it + # chunk_left == None: No current chunk, should read next. + # This function returns non-zero or None if the last chunk has + # been read. + chunk_left = self.chunk_left + if not chunk_left: # Can be 0 or None + if chunk_left is not None: + # We are at the end of chunk. dicard chunk end + self._safe_read(2) # toss the CRLF at the end of the chunk + try: + chunk_left = self._read_next_chunk_size() + except ValueError: + raise IncompleteRead(b'') + if chunk_left == 0: + # last chunk: 1*("0") [ chunk-extension ] CRLF + self._read_and_discard_trailer() + # we read everything; close the "file" + self._close_conn() + chunk_left = None + self.chunk_left = chunk_left + return chunk_left + def _readall_chunked(self): assert self.chunked != _UNKNOWN - chunk_left = self.chunk_left value = [] - while True: - if chunk_left is None: - try: - chunk_left = self._read_next_chunk_size() - if chunk_left == 0: - break - except ValueError: - raise IncompleteRead(b''.join(value)) - value.append(self._safe_read(chunk_left)) - - # we read the whole chunk, get another - self._safe_read(2) # toss the CRLF at the end of the chunk - chunk_left = None - - self._read_and_discard_trailer() - - # we read everything; close the "file" - self._close_conn() - - return b''.join(value) + try: + while True: + chunk_left = self._get_chunk_left() + if chunk_left is None: + break + value.append(self._safe_read(chunk_left)) + self.chunk_left = 0 + return b''.join(value) + except IncompleteRead: + raise IncompleteRead(b''.join(value)) def _readinto_chunked(self, b): assert self.chunked != _UNKNOWN - chunk_left = self.chunk_left - total_bytes = 0 mvb = memoryview(b) - while True: - if chunk_left is None: - try: - chunk_left = self._read_next_chunk_size() - if chunk_left == 0: - break - except ValueError: - raise IncompleteRead(bytes(b[0:total_bytes])) - - if len(mvb) < chunk_left: - n = self._safe_readinto(mvb) - self.chunk_left = chunk_left - n - return total_bytes + n - elif len(mvb) == chunk_left: - n = self._safe_readinto(mvb) - self._safe_read(2) # toss the CRLF at the end of the chunk - self.chunk_left = None - return total_bytes + n - else: - temp_mvb = mvb[0:chunk_left] + try: + while True: + chunk_left = self._get_chunk_left() + if chunk_left is None: + return total_bytes + + if len(mvb) <= chunk_left: + n = self._safe_readinto(mvb) + self.chunk_left = chunk_left - n + return total_bytes + n + + temp_mvb = mvb[:chunk_left] n = self._safe_readinto(temp_mvb) mvb = mvb[n:] total_bytes += n + self.chunk_left = 0 - # we read the whole chunk, get another - self._safe_read(2) # toss the CRLF at the end of the chunk - chunk_left = None - - self._read_and_discard_trailer() - - # we read everything; close the "file" - self._close_conn() - - return total_bytes + except IncompleteRead: + raise IncompleteRead(bytes(b[0:total_bytes])) def _safe_read(self, amt): """Read the number of bytes requested, compensating for partial reads. @@ -684,6 +573,73 @@ class HTTPResponse(io.RawIOBase): total_bytes += n return total_bytes + def read1(self, n=-1): + """Read with at most one underlying system call. If at least one + byte is buffered, return that instead. + """ + if self.fp is None or self._method == "HEAD": + return b"" + if self.chunked: + return self._read1_chunked(n) + try: + result = self.fp.read1(n) + except ValueError: + if n >= 0: + raise + # some implementations, like BufferedReader, don't support -1 + # Read an arbitrarily selected largeish chunk. + result = self.fp.read1(16*1024) + if not result and n: + self._close_conn() + return result + + def peek(self, n=-1): + # Having this enables IOBase.readline() to read more than one + # byte at a time + if self.fp is None or self._method == "HEAD": + return b"" + if self.chunked: + return self._peek_chunked(n) + return self.fp.peek(n) + + def readline(self, limit=-1): + if self.fp is None or self._method == "HEAD": + return b"" + if self.chunked: + # Fallback to IOBase readline which uses peek() and read() + return super().readline(limit) + result = self.fp.readline(limit) + if not result and limit: + self._close_conn() + return result + + def _read1_chunked(self, n): + # Strictly speaking, _get_chunk_left() may cause more than one read, + # but that is ok, since that is to satisfy the chunked protocol. + chunk_left = self._get_chunk_left() + if chunk_left is None or n == 0: + return b'' + if not (0 <= n <= chunk_left): + n = chunk_left # if n is negative or larger than chunk_left + read = self.fp.read1(n) + self.chunk_left -= len(read) + if not read: + raise IncompleteRead(b"") + return read + + def _peek_chunked(self, n): + # Strictly speaking, _get_chunk_left() may cause more than one read, + # but that is ok, since that is to satisfy the chunked protocol. + try: + chunk_left = self._get_chunk_left() + except IncompleteRead: + return b'' # peek doesn't worry about protocol + if chunk_left is None: + return b'' # eof + # peek is allowed to return more than requested. Just request the + # entire chunk, and truncate what we get. + return self.fp.peek(chunk_left)[:chunk_left] + def fileno(self): return self.fp.fileno() @@ -727,14 +683,6 @@ class HTTPConnection: default_port = HTTP_PORT auto_open = 1 debuglevel = 0 - # TCP Maximum Segment Size (MSS) is determined by the TCP stack on - # a per-connection basis. There is no simple and efficient - # platform independent mechanism for determining the MSS, so - # instead a reasonable estimate is chosen. The getsockopt() - # interface using the TCP_MAXSEG parameter may be a suitable - # approach on some operating systems. A value of 16KiB is chosen - # as a reasonable estimate of the maximum MSS. - mss = 16384 def __init__(self, host, port=None, timeout=socket._GLOBAL_DEFAULT_TIMEOUT, source_address=None): @@ -816,7 +764,7 @@ class HTTPConnection: response = self.response_class(self.sock, method=self._method) (version, code, message) = response._read_status() - if code != 200: + if code != http.HTTPStatus.OK: self.close() raise OSError("Tunnel connection failed: %d %s" % (code, message.strip())) @@ -830,10 +778,14 @@ class HTTPConnection: if line in (b'\r\n', b'\n', b''): break + if self.debuglevel > 0: + print('header:', line.decode()) + def connect(self): """Connect to the host and port specified in __init__.""" - self.sock = self._create_connection((self.host,self.port), - self.timeout, self.source_address) + self.sock = self._create_connection( + (self.host,self.port), self.timeout, self.source_address) + self.sock.setsockopt(socket.IPPROTO_TCP, socket.TCP_NODELAY, 1) if self._tunnel_host: self._tunnel() @@ -912,19 +864,9 @@ class HTTPConnection: self._buffer.extend((b"", b"")) msg = b"\r\n".join(self._buffer) del self._buffer[:] - # If msg and message_body are sent in a single send() call, - # it will avoid performance problems caused by the interaction - # between delayed ack and the Nagle algorithm. However, - # there is no performance gain if the message is larger - # than MSS (and there is a memory penalty for the message - # copy). - if isinstance(message_body, bytes) and len(message_body) < self.mss: - msg += message_body - message_body = None + self.send(msg) if message_body is not None: - # message_body was not a string (i.e. it is a file), and - # we must run the risk of Nagle. self.send(message_body) def putrequest(self, method, url, skip_host=0, skip_accept_encoding=0): @@ -1273,7 +1215,8 @@ class IncompleteRead(HTTPException): e = ', %i more expected' % self.expected else: e = '' - return 'IncompleteRead(%i bytes read%s)' % (len(self.partial), e) + return '%s(%i bytes read%s)' % (self.__class__.__name__, + len(self.partial), e) def __str__(self): return repr(self) diff --git a/Lib/http/cookiejar.py b/Lib/http/cookiejar.py index 7e4982f..22f2833 100644 --- a/Lib/http/cookiejar.py +++ b/Lib/http/cookiejar.py @@ -478,7 +478,7 @@ def parse_ns_headers(ns_headers): if "=" not in param: k, v = param, None else: - k, v = re.split(r"\s*=\s*", param, 1) + k, v = re.split(r"\s*=\s*", param, maxsplit=1) k = k.lstrip() if ii != 0: lc = k.lower() @@ -805,7 +805,7 @@ class Cookie: args.append("%s=%s" % (name, repr(attr))) args.append("rest=%s" % repr(self._rest)) args.append("rfc2109=%s" % repr(self.rfc2109)) - return "Cookie(%s)" % ", ".join(args) + return "%s(%s)" % (self.__class__.__name__, ", ".join(args)) class CookiePolicy: diff --git a/Lib/http/cookies.py b/Lib/http/cookies.py index 3e1abd7..73acbc7 100644 --- a/Lib/http/cookies.py +++ b/Lib/http/cookies.py @@ -533,10 +533,17 @@ class BaseCookie(dict): return def __parse_string(self, str, patt=_CookiePattern): - i = 0 # Our starting point - n = len(str) # Length of string - M = None # current morsel + i = 0 # Our starting point + n = len(str) # Length of string + parsed_items = [] # Parsed (type, key, value) triples + morsel_seen = False # A key=value pair was previously encountered + + TYPE_ATTRIBUTE = 1 + TYPE_KEYVALUE = 2 + # We first parse the whole cookie string and reject it if it's + # syntactically invalid (this helps avoid some classes of injection + # attacks). while 0 <= i < n: # Start looking for a cookie match = patt.match(str, i) @@ -547,22 +554,41 @@ class BaseCookie(dict): key, value = match.group("key"), match.group("val") i = match.end(0) - # Parse the key, value in case it's metainfo if key[0] == "$": - # We ignore attributes which pertain to the cookie - # mechanism as a whole. See RFC 2109. - # (Does anyone care?) - if M: - M[key[1:]] = value + if not morsel_seen: + # We ignore attributes which pertain to the cookie + # mechanism as a whole, such as "$Version". + # See RFC 2965. (Does anyone care?) + continue + parsed_items.append((TYPE_ATTRIBUTE, key[1:], value)) elif key.lower() in Morsel._reserved: - if M: - if value is None: - if key.lower() in Morsel._flags: - M[key] = True + if not morsel_seen: + # Invalid cookie string + return + if value is None: + if key.lower() in Morsel._flags: + parsed_items.append((TYPE_ATTRIBUTE, key, True)) else: - M[key] = _unquote(value) + # Invalid cookie string + return + else: + parsed_items.append((TYPE_ATTRIBUTE, key, _unquote(value))) elif value is not None: - rval, cval = self.value_decode(value) + parsed_items.append((TYPE_KEYVALUE, key, self.value_decode(value))) + morsel_seen = True + else: + # Invalid cookie string + return + + # The cookie string is valid, apply it. + M = None # current morsel + for tp, key, value in parsed_items: + if tp == TYPE_ATTRIBUTE: + assert M is not None + M[key] = value + else: + assert tp == TYPE_KEYVALUE + rval, cval = value self.__set(key, rval, cval) M = self[key] diff --git a/Lib/http/server.py b/Lib/http/server.py index 47655e7..4704d51 100644 --- a/Lib/http/server.py +++ b/Lib/http/server.py @@ -103,6 +103,8 @@ import urllib.parse import copy import argparse +from http import HTTPStatus + # Default error message template DEFAULT_ERROR_MESSAGE = """\ @@ -281,7 +283,9 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler): if len(words) == 3: command, path, version = words if version[:5] != 'HTTP/': - self.send_error(400, "Bad request version (%r)" % version) + self.send_error( + HTTPStatus.BAD_REQUEST, + "Bad request version (%r)" % version) return False try: base_version_number = version.split('/', 1)[1] @@ -296,25 +300,31 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler): raise ValueError version_number = int(version_number[0]), int(version_number[1]) except (ValueError, IndexError): - self.send_error(400, "Bad request version (%r)" % version) + self.send_error( + HTTPStatus.BAD_REQUEST, + "Bad request version (%r)" % version) return False if version_number >= (1, 1) and self.protocol_version >= "HTTP/1.1": self.close_connection = False if version_number >= (2, 0): - self.send_error(505, - "Invalid HTTP Version (%s)" % base_version_number) + self.send_error( + HTTPStatus.HTTP_VERSION_NOT_SUPPORTED, + "Invalid HTTP Version (%s)" % base_version_number) return False elif len(words) == 2: command, path = words self.close_connection = True if command != 'GET': - self.send_error(400, - "Bad HTTP/0.9 request type (%r)" % command) + self.send_error( + HTTPStatus.BAD_REQUEST, + "Bad HTTP/0.9 request type (%r)" % command) return False elif not words: return False else: - self.send_error(400, "Bad request syntax (%r)" % requestline) + self.send_error( + HTTPStatus.BAD_REQUEST, + "Bad request syntax (%r)" % requestline) return False self.command, self.path, self.request_version = command, path, version @@ -323,7 +333,9 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler): self.headers = http.client.parse_headers(self.rfile, _class=self.MessageClass) except http.client.LineTooLong: - self.send_error(400, "Line too long") + self.send_error( + HTTPStatus.BAD_REQUEST, + "Line too long") return False conntype = self.headers.get('Connection', "") @@ -355,7 +367,7 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler): False. """ - self.send_response_only(100) + self.send_response_only(HTTPStatus.CONTINUE) self.end_headers() return True @@ -373,7 +385,7 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler): self.requestline = '' self.request_version = '' self.command = '' - self.send_error(414) + self.send_error(HTTPStatus.REQUEST_URI_TOO_LONG) return if not self.raw_requestline: self.close_connection = True @@ -383,7 +395,9 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler): return mname = 'do_' + self.command if not hasattr(self, mname): - self.send_error(501, "Unsupported method (%r)" % self.command) + self.send_error( + HTTPStatus.NOT_IMPLEMENTED, + "Unsupported method (%r)" % self.command) return method = getattr(self, mname) method() @@ -438,7 +452,11 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler): self.send_header('Connection', 'close') self.send_header('Content-Length', int(len(body))) self.end_headers() - if self.command != 'HEAD' and code >= 200 and code not in (204, 304): + + if (self.command != 'HEAD' and + code >= 200 and + code not in ( + HTTPStatus.NO_CONTENT, HTTPStatus.NOT_MODIFIED)): self.wfile.write(body) def send_response(self, code, message=None): @@ -582,82 +600,11 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler): # MessageClass used to parse headers MessageClass = http.client.HTTPMessage - # Table mapping response codes to messages; entries have the - # form {code: (shortmessage, longmessage)}. - # See RFC 2616 and 6585. + # hack to maintain backwards compatibility responses = { - 100: ('Continue', 'Request received, please continue'), - 101: ('Switching Protocols', - 'Switching to new protocol; obey Upgrade header'), - - 200: ('OK', 'Request fulfilled, document follows'), - 201: ('Created', 'Document created, URL follows'), - 202: ('Accepted', - 'Request accepted, processing continues off-line'), - 203: ('Non-Authoritative Information', 'Request fulfilled from cache'), - 204: ('No Content', 'Request fulfilled, nothing follows'), - 205: ('Reset Content', 'Clear input form for further input.'), - 206: ('Partial Content', 'Partial content follows.'), - - 300: ('Multiple Choices', - 'Object has several resources -- see URI list'), - 301: ('Moved Permanently', 'Object moved permanently -- see URI list'), - 302: ('Found', 'Object moved temporarily -- see URI list'), - 303: ('See Other', 'Object moved -- see Method and URL list'), - 304: ('Not Modified', - 'Document has not changed since given time'), - 305: ('Use Proxy', - 'You must use proxy specified in Location to access this ' - 'resource.'), - 307: ('Temporary Redirect', - 'Object moved temporarily -- see URI list'), - - 400: ('Bad Request', - 'Bad request syntax or unsupported method'), - 401: ('Unauthorized', - 'No permission -- see authorization schemes'), - 402: ('Payment Required', - 'No payment -- see charging schemes'), - 403: ('Forbidden', - 'Request forbidden -- authorization will not help'), - 404: ('Not Found', 'Nothing matches the given URI'), - 405: ('Method Not Allowed', - 'Specified method is invalid for this resource.'), - 406: ('Not Acceptable', 'URI not available in preferred format.'), - 407: ('Proxy Authentication Required', 'You must authenticate with ' - 'this proxy before proceeding.'), - 408: ('Request Timeout', 'Request timed out; try again later.'), - 409: ('Conflict', 'Request conflict.'), - 410: ('Gone', - 'URI no longer exists and has been permanently removed.'), - 411: ('Length Required', 'Client must specify Content-Length.'), - 412: ('Precondition Failed', 'Precondition in headers is false.'), - 413: ('Request Entity Too Large', 'Entity is too large.'), - 414: ('Request-URI Too Long', 'URI is too long.'), - 415: ('Unsupported Media Type', 'Entity body in unsupported format.'), - 416: ('Requested Range Not Satisfiable', - 'Cannot satisfy request range.'), - 417: ('Expectation Failed', - 'Expect condition could not be satisfied.'), - 428: ('Precondition Required', - 'The origin server requires the request to be conditional.'), - 429: ('Too Many Requests', 'The user has sent too many requests ' - 'in a given amount of time ("rate limiting").'), - 431: ('Request Header Fields Too Large', 'The server is unwilling to ' - 'process the request because its header fields are too large.'), - - 500: ('Internal Server Error', 'Server got itself in trouble'), - 501: ('Not Implemented', - 'Server does not support this operation'), - 502: ('Bad Gateway', 'Invalid responses from another server/proxy.'), - 503: ('Service Unavailable', - 'The server cannot process the request due to a high load'), - 504: ('Gateway Timeout', - 'The gateway server did not receive a timely response'), - 505: ('HTTP Version Not Supported', 'Cannot fulfill request.'), - 511: ('Network Authentication Required', - 'The client needs to authenticate to gain network access.'), - } + v: (v.phrase, v.description) + for v in HTTPStatus.__members__.values() + } class SimpleHTTPRequestHandler(BaseHTTPRequestHandler): @@ -707,7 +654,7 @@ class SimpleHTTPRequestHandler(BaseHTTPRequestHandler): parts = urllib.parse.urlsplit(self.path) if not parts.path.endswith('/'): # redirect browser - doing basically what apache does - self.send_response(301) + self.send_response(HTTPStatus.MOVED_PERMANENTLY) new_parts = (parts[0], parts[1], parts[2] + '/', parts[3], parts[4]) new_url = urllib.parse.urlunsplit(new_parts) @@ -725,10 +672,10 @@ class SimpleHTTPRequestHandler(BaseHTTPRequestHandler): try: f = open(path, 'rb') except OSError: - self.send_error(404, "File not found") + self.send_error(HTTPStatus.NOT_FOUND, "File not found") return None try: - self.send_response(200) + self.send_response(HTTPStatus.OK) self.send_header("Content-type", ctype) fs = os.fstat(f.fileno()) self.send_header("Content-Length", str(fs[6])) @@ -750,7 +697,9 @@ class SimpleHTTPRequestHandler(BaseHTTPRequestHandler): try: list = os.listdir(path) except OSError: - self.send_error(404, "No permission to list directory") + self.send_error( + HTTPStatus.NOT_FOUND, + "No permission to list directory") return None list.sort(key=lambda a: a.lower()) r = [] @@ -789,7 +738,7 @@ class SimpleHTTPRequestHandler(BaseHTTPRequestHandler): f = io.BytesIO() f.write(encoded) f.seek(0) - self.send_response(200) + self.send_response(HTTPStatus.OK) self.send_header("Content-type", "text/html; charset=%s" % enc) self.send_header("Content-Length", str(len(encoded))) self.end_headers() @@ -971,7 +920,9 @@ class CGIHTTPRequestHandler(SimpleHTTPRequestHandler): if self.is_cgi(): self.run_cgi() else: - self.send_error(501, "Can only POST to CGI scripts") + self.send_error( + HTTPStatus.NOT_IMPLEMENTED, + "Can only POST to CGI scripts") def send_head(self): """Version of send_head that support CGI scripts""" @@ -1049,17 +1000,21 @@ class CGIHTTPRequestHandler(SimpleHTTPRequestHandler): scriptname = dir + '/' + script scriptfile = self.translate_path(scriptname) if not os.path.exists(scriptfile): - self.send_error(404, "No such CGI script (%r)" % scriptname) + self.send_error( + HTTPStatus.NOT_FOUND, + "No such CGI script (%r)" % scriptname) return if not os.path.isfile(scriptfile): - self.send_error(403, "CGI script is not a plain file (%r)" % - scriptname) + self.send_error( + HTTPStatus.FORBIDDEN, + "CGI script is not a plain file (%r)" % scriptname) return ispy = self.is_python(scriptname) if self.have_fork or not ispy: if not self.is_executable(scriptfile): - self.send_error(403, "CGI script is not executable (%r)" % - scriptname) + self.send_error( + HTTPStatus.FORBIDDEN, + "CGI script is not executable (%r)" % scriptname) return # Reference: http://hoohoo.ncsa.uiuc.edu/cgi/env.html @@ -1127,7 +1082,7 @@ class CGIHTTPRequestHandler(SimpleHTTPRequestHandler): 'HTTP_USER_AGENT', 'HTTP_COOKIE', 'HTTP_REFERER'): env.setdefault(k, "") - self.send_response(200, "Script output follows") + self.send_response(HTTPStatus.OK, "Script output follows") self.flush_headers() decoded_query = query.replace('+', ' ') diff --git a/Lib/idlelib/NEWS.txt b/Lib/idlelib/NEWS.txt index a3a8fbf..828142c 100644 --- a/Lib/idlelib/NEWS.txt +++ b/Lib/idlelib/NEWS.txt @@ -1,4 +1,4 @@ -What's New in Idle 3.4.3? +What's New in IDLE 3.5.0? ========================= - Issue #16893: Update Idle doc chapter to match current Idle and add new @@ -21,10 +21,6 @@ What's New in Idle 3.4.3? - Issue #21986: Code objects are not normally pickled by the pickle module. To match this, they are no longer pickled when running under Idle. - -What's New in IDLE 3.4.2? -========================= - - Issue #17390: Adjust Editor window title; remove 'Python', move version to end. @@ -59,13 +55,8 @@ What's New in IDLE 3.4.2? - Issue #18409: Add unittest for AutoComplete. Patch by Phil Webster. -- Issue #18104: Add idlelib/idle_test/htest.py with a few sample tests to begin - consolidating and improving human-validated tests of Idle. Change other files - as needed to work with htest. Running the module as __main__ runs all tests. - - -What's New in IDLE 3.4.1? -========================= +- Issue #21477: htest.py - Improve framework, complete set of tests. + Patches by Saimadhav Heblikar - Issue #18104: Add idlelib/idle_test/htest.py with a few sample tests to begin consolidating and improving human-validated tests of Idle. Change other files diff --git a/Lib/idlelib/WidgetRedirector.py b/Lib/idlelib/WidgetRedirector.py index b3d7bfa..67d7f61 100644 --- a/Lib/idlelib/WidgetRedirector.py +++ b/Lib/idlelib/WidgetRedirector.py @@ -47,8 +47,9 @@ class WidgetRedirector: tk.createcommand(w, self.dispatch) def __repr__(self): - return "WidgetRedirector(%s<%s>)" % (self.widget.__class__.__name__, - self.widget._w) + return "%s(%s<%s>)" % (self.__class__.__name__, + self.widget.__class__.__name__, + self.widget._w) def close(self): "Unregister operations and revert redirection created by .__init__." @@ -142,7 +143,8 @@ class OriginalCommand: self.orig_and_operation = (redir.orig, operation) def __repr__(self): - return "OriginalCommand(%r, %r)" % (self.redir, self.operation) + return "%s(%r, %r)" % (self.__class__.__name__, + self.redir, self.operation) def __call__(self, *args): return self.tk_call(self.orig_and_operation + args) diff --git a/Lib/idlelib/idle_test/test_searchengine.py b/Lib/idlelib/idle_test/test_searchengine.py index 129a5a3..2c10461 100644 --- a/Lib/idlelib/idle_test/test_searchengine.py +++ b/Lib/idlelib/idle_test/test_searchengine.py @@ -178,7 +178,7 @@ class SearchEngineTest(unittest.TestCase): engine.revar.set(1) Equal(engine.getprog(), None) self.assertEqual(Mbox.showerror.message, - 'Error: nothing to repeat\nPattern: +') + 'Error: nothing to repeat at position 0\nPattern: +') def test_report_error(self): showerror = Mbox.showerror diff --git a/Lib/idlelib/idlever.py b/Lib/idlelib/idlever.py index 6975f5e..1ffbc76 100644 --- a/Lib/idlelib/idlever.py +++ b/Lib/idlelib/idlever.py @@ -1 +1 @@ -IDLE_VERSION = "3.4.3" +IDLE_VERSION = "3.5.0a1" diff --git a/Lib/imaplib.py b/Lib/imaplib.py index 72ab5d7..49ee39d 100644 --- a/Lib/imaplib.py +++ b/Lib/imaplib.py @@ -238,6 +238,14 @@ class IMAP4: return getattr(self, attr.lower()) raise AttributeError("Unknown IMAP4 command: '%s'" % attr) + def __enter__(self): + return self + + def __exit__(self, *args): + try: + self.logout() + except OSError: + pass # Overridable methods diff --git a/Lib/imghdr.py b/Lib/imghdr.py index add2ea8..b267925 100644 --- a/Lib/imghdr.py +++ b/Lib/imghdr.py @@ -110,6 +110,18 @@ def test_bmp(h, f): tests.append(test_bmp) +def test_webp(h, f): + if h.startswith(b'RIFF') and h[8:12] == b'WEBP': + return 'webp' + +tests.append(test_webp) + +def test_exr(h, f): + if h.startswith(b'\x76\x2f\x31\x01'): + return 'exr' + +tests.append(test_exr) + #--------------------# # Small test program # #--------------------# @@ -16,7 +16,7 @@ except ImportError: # Platform doesn't support dynamic loading. load_dynamic = None -from importlib._bootstrap import SourcelessFileLoader, _ERR_MSG, _SpecMethods +from importlib._bootstrap import SourcelessFileLoader, _ERR_MSG, _exec, _load from importlib import machinery from importlib import util @@ -164,11 +164,10 @@ class _LoadSourceCompatibility(_HackedGetData, machinery.SourceFileLoader): def load_source(name, pathname, file=None): loader = _LoadSourceCompatibility(name, pathname, file) spec = util.spec_from_file_location(name, pathname, loader=loader) - methods = _SpecMethods(spec) if name in sys.modules: - module = methods.exec(sys.modules[name]) + module = _exec(spec, sys.modules[name]) else: - module = methods.load() + module = _load(spec) # To allow reloading to potentially work, use a non-hacked loader which # won't rely on a now-closed file object. module.__loader__ = machinery.SourceFileLoader(name, pathname) @@ -185,11 +184,10 @@ def load_compiled(name, pathname, file=None): """**DEPRECATED**""" loader = _LoadCompiledCompatibility(name, pathname, file) spec = util.spec_from_file_location(name, pathname, loader=loader) - methods = _SpecMethods(spec) if name in sys.modules: - module = methods.exec(sys.modules[name]) + module = _exec(spec, sys.modules[name]) else: - module = methods.load() + module = _load(spec) # To allow reloading to potentially work, use a non-hacked loader which # won't rely on a now-closed file object. module.__loader__ = SourcelessFileLoader(name, pathname) @@ -210,11 +208,10 @@ def load_package(name, path): raise ValueError('{!r} is not a package'.format(path)) spec = util.spec_from_file_location(name, path, submodule_search_locations=[]) - methods = _SpecMethods(spec) if name in sys.modules: - return methods.exec(sys.modules[name]) + return _exec(spec, sys.modules[name]) else: - return methods.load() + return _load(spec) def load_module(name, file, filename, details): diff --git a/Lib/importlib/__init__.py b/Lib/importlib/__init__.py index 1bc9947..e99f50e 100644 --- a/Lib/importlib/__init__.py +++ b/Lib/importlib/__init__.py @@ -73,7 +73,7 @@ def find_loader(name, path=None): except KeyError: pass except AttributeError: - raise ValueError('{}.__loader__ is not set'.format(name)) + raise ValueError('{}.__loader__ is not set'.format(name)) from None spec = _bootstrap._find_spec(name, path) # We won't worry about malformed specs (missing attributes). @@ -138,15 +138,15 @@ def reload(module): parent = sys.modules[parent_name] except KeyError: msg = "parent {!r} not in sys.modules" - raise ImportError(msg.format(parent_name), name=parent_name) + raise ImportError(msg.format(parent_name), + name=parent_name) from None else: pkgpath = parent.__path__ else: pkgpath = None target = module spec = module.__spec__ = _bootstrap._find_spec(name, pkgpath, target) - methods = _bootstrap._SpecMethods(spec) - methods.exec(module) + _bootstrap._exec(spec, module) # The module may have replaced itself in sys.modules! return sys.modules[name] finally: diff --git a/Lib/importlib/_bootstrap.py b/Lib/importlib/_bootstrap.py index 5b91c05..0ed7cc6 100644 --- a/Lib/importlib/_bootstrap.py +++ b/Lib/importlib/_bootstrap.py @@ -9,7 +9,7 @@ work. One should use importlib as the public-facing version of this module. # # IMPORTANT: Whenever making changes to this module, be sure to run # a top-level make in order to get the frozen version of the module -# update. Not doing so will result in the Makefile to fail for +# updated. Not doing so will result in the Makefile to fail for # all others who don't have a ./python around to freeze the module # in the early stages of compilation. # @@ -419,12 +419,13 @@ def _call_with_frames_removed(f, *args, **kwds): # Python 3.4a4 3290 (changes to __qualname__ computation) # Python 3.4a4 3300 (more changes to __qualname__ computation) # Python 3.4rc2 3310 (alter __qualname__ computation) +# Python 3.5a0 3320 (matrix multiplication operator) # # MAGIC must change whenever the bytecode emitted by the compiler may no # longer be understood by older implementations of the eval loop (usually # due to the addition of new opcodes). -MAGIC_NUMBER = (3310).to_bytes(2, 'little') + b'\r\n' +MAGIC_NUMBER = (3320).to_bytes(2, 'little') + b'\r\n' _RAW_MAGIC_NUMBER = int.from_bytes(MAGIC_NUMBER, 'little') # For import.c _PYCACHE = '__pycache__' @@ -580,6 +581,7 @@ def _find_module_shim(self, fullname): return loader +# Typically used by loader classes as a method replacement. def _load_module_shim(self, fullname): """Load the specified module into sys.modules and return it. @@ -587,13 +589,12 @@ def _load_module_shim(self, fullname): """ spec = spec_from_loader(fullname, self) - methods = _SpecMethods(spec) if fullname in sys.modules: module = sys.modules[fullname] - methods.exec(module) + _exec(spec, module) return sys.modules[fullname] else: - return methods.load() + return _load(spec) def _validate_bytecode_header(data, source_stats=None, name=None, path=None): @@ -704,7 +705,7 @@ def _module_repr(module): pass else: if spec is not None: - return _SpecMethods(spec).module_repr() + return _module_repr_from_spec(spec) # We could use module.__class__.__name__ instead of 'module' in the # various repr permutations. @@ -990,234 +991,186 @@ def _spec_from_module(module, loader=None, origin=None): return spec -class _SpecMethods: - - """Convenience wrapper around spec objects to provide spec-specific - methods.""" - - # The various spec_from_* functions could be made factory methods here. - - def __init__(self, spec): - self.spec = spec - - def module_repr(self): - """Return the repr to use for the module.""" - # We mostly replicate _module_repr() using the spec attributes. - spec = self.spec - name = '?' if spec.name is None else spec.name - if spec.origin is None: - if spec.loader is None: - return '<module {!r}>'.format(name) - else: - return '<module {!r} ({!r})>'.format(name, spec.loader) - else: - if spec.has_location: - return '<module {!r} from {!r}>'.format(name, spec.origin) - else: - return '<module {!r} ({})>'.format(spec.name, spec.origin) - - def init_module_attrs(self, module, *, _override=False, _force_name=True): - """Set the module's attributes. - - All missing import-related module attributes will be set. Here - is how the spec attributes map onto the module: - - spec.name -> module.__name__ - spec.loader -> module.__loader__ - spec.parent -> module.__package__ - spec -> module.__spec__ - - Optional: - spec.origin -> module.__file__ (if spec.set_fileattr is true) - spec.cached -> module.__cached__ (if __file__ also set) - spec.submodule_search_locations -> module.__path__ (if set) - - """ - spec = self.spec - - # The passed in module may be not support attribute assignment, - # in which case we simply don't set the attributes. - - # __name__ - if (_override or _force_name or - getattr(module, '__name__', None) is None): - try: - module.__name__ = spec.name - except AttributeError: - pass - - # __loader__ - if _override or getattr(module, '__loader__', None) is None: - loader = spec.loader - if loader is None: - # A backward compatibility hack. - if spec.submodule_search_locations is not None: - loader = _NamespaceLoader.__new__(_NamespaceLoader) - loader._path = spec.submodule_search_locations +def _init_module_attrs(spec, module, *, override=False): + # The passed-in module may be not support attribute assignment, + # in which case we simply don't set the attributes. + # __name__ + if (override or getattr(module, '__name__', None) is None): + try: + module.__name__ = spec.name + except AttributeError: + pass + # __loader__ + if override or getattr(module, '__loader__', None) is None: + loader = spec.loader + if loader is None: + # A backward compatibility hack. + if spec.submodule_search_locations is not None: + loader = _NamespaceLoader.__new__(_NamespaceLoader) + loader._path = spec.submodule_search_locations + try: + module.__loader__ = loader + except AttributeError: + pass + # __package__ + if override or getattr(module, '__package__', None) is None: + try: + module.__package__ = spec.parent + except AttributeError: + pass + # __spec__ + try: + module.__spec__ = spec + except AttributeError: + pass + # __path__ + if override or getattr(module, '__path__', None) is None: + if spec.submodule_search_locations is not None: try: - module.__loader__ = loader + module.__path__ = spec.submodule_search_locations except AttributeError: pass - - # __package__ - if _override or getattr(module, '__package__', None) is None: + # __file__/__cached__ + if spec.has_location: + if override or getattr(module, '__file__', None) is None: try: - module.__package__ = spec.parent + module.__file__ = spec.origin except AttributeError: pass - # __spec__ - try: - module.__spec__ = spec - except AttributeError: - pass - - # __path__ - if _override or getattr(module, '__path__', None) is None: - if spec.submodule_search_locations is not None: - try: - module.__path__ = spec.submodule_search_locations - except AttributeError: - pass - - if spec.has_location: - # __file__ - if _override or getattr(module, '__file__', None) is None: + if override or getattr(module, '__cached__', None) is None: + if spec.cached is not None: try: - module.__file__ = spec.origin + module.__cached__ = spec.cached except AttributeError: pass + return module - # __cached__ - if _override or getattr(module, '__cached__', None) is None: - if spec.cached is not None: - try: - module.__cached__ = spec.cached - except AttributeError: - pass - def create(self): - """Return a new module to be loaded. +def module_from_spec(spec): + """Create a module based on the provided spec.""" + # Typically loaders will not implement create_module(). + module = None + if hasattr(spec.loader, 'create_module'): + # If create_module() returns `None` then it means default + # module creation should be used. + module = spec.loader.create_module(spec) + elif hasattr(spec.loader, 'exec_module'): + _warnings.warn('starting in Python 3.6, loaders defining exec_module() ' + 'must also define create_module()', + DeprecationWarning, stacklevel=2) + if module is None: + module = _new_module(spec.name) + _init_module_attrs(spec, module) + return module - The import-related module attributes are also set with the - appropriate values from the spec. - """ - spec = self.spec - # Typically loaders will not implement create_module(). - if hasattr(spec.loader, 'create_module'): - # If create_module() returns `None` it means the default - # module creation should be used. - module = spec.loader.create_module(spec) +def _module_repr_from_spec(spec): + """Return the repr to use for the module.""" + # We mostly replicate _module_repr() using the spec attributes. + name = '?' if spec.name is None else spec.name + if spec.origin is None: + if spec.loader is None: + return '<module {!r}>'.format(name) else: - module = None - if module is None: - # This must be done before open() is ever called as the 'io' - # module implicitly imports 'locale' and would otherwise - # trigger an infinite loop. - module = _new_module(spec.name) - self.init_module_attrs(module) - return module - - def _exec(self, module): - """Do everything necessary to execute the module. - - The namespace of `module` is used as the target of execution. - This method uses the loader's `exec_module()` method. + return '<module {!r} ({!r})>'.format(name, spec.loader) + else: + if spec.has_location: + return '<module {!r} from {!r}>'.format(name, spec.origin) + else: + return '<module {!r} ({})>'.format(spec.name, spec.origin) - """ - self.spec.loader.exec_module(module) - # Used by importlib.reload() and _load_module_shim(). - def exec(self, module): - """Execute the spec in an existing module's namespace.""" - name = self.spec.name - _imp.acquire_lock() - with _ModuleLockManager(name): - if sys.modules.get(name) is not module: - msg = 'module {!r} not in sys.modules'.format(name) - raise ImportError(msg, name=name) - if self.spec.loader is None: - if self.spec.submodule_search_locations is None: - raise ImportError('missing loader', name=self.spec.name) - # namespace package - self.init_module_attrs(module, _override=True) - return module - self.init_module_attrs(module, _override=True) - if not hasattr(self.spec.loader, 'exec_module'): - # (issue19713) Once BuiltinImporter and ExtensionFileLoader - # have exec_module() implemented, we can add a deprecation - # warning here. - self.spec.loader.load_module(name) - else: - self._exec(module) - return sys.modules[name] - - def _load_backward_compatible(self): - # (issue19713) Once BuiltinImporter and ExtensionFileLoader - # have exec_module() implemented, we can add a deprecation - # warning here. - spec = self.spec - spec.loader.load_module(spec.name) - # The module must be in sys.modules at this point! - module = sys.modules[spec.name] - if getattr(module, '__loader__', None) is None: - try: - module.__loader__ = spec.loader - except AttributeError: - pass - if getattr(module, '__package__', None) is None: - try: - # Since module.__path__ may not line up with - # spec.submodule_search_paths, we can't necessarily rely - # on spec.parent here. - module.__package__ = module.__name__ - if not hasattr(module, '__path__'): - module.__package__ = spec.name.rpartition('.')[0] - except AttributeError: - pass - if getattr(module, '__spec__', None) is None: - try: - module.__spec__ = spec - except AttributeError: - pass - return module +# Used by importlib.reload() and _load_module_shim(). +def _exec(spec, module): + """Execute the spec in an existing module's namespace.""" + name = spec.name + _imp.acquire_lock() + with _ModuleLockManager(name): + if sys.modules.get(name) is not module: + msg = 'module {!r} not in sys.modules'.format(name) + raise ImportError(msg, name=name) + if spec.loader is None: + if spec.submodule_search_locations is None: + raise ImportError('missing loader', name=spec.name) + # namespace package + _init_module_attrs(spec, module, override=True) + return module + _init_module_attrs(spec, module, override=True) + if not hasattr(spec.loader, 'exec_module'): + # (issue19713) Once BuiltinImporter and ExtensionFileLoader + # have exec_module() implemented, we can add a deprecation + # warning here. + spec.loader.load_module(name) + else: + spec.loader.exec_module(module) + return sys.modules[name] + + +def _load_backward_compatible(spec): + # (issue19713) Once BuiltinImporter and ExtensionFileLoader + # have exec_module() implemented, we can add a deprecation + # warning here. + spec.loader.load_module(spec.name) + # The module must be in sys.modules at this point! + module = sys.modules[spec.name] + if getattr(module, '__loader__', None) is None: + try: + module.__loader__ = spec.loader + except AttributeError: + pass + if getattr(module, '__package__', None) is None: + try: + # Since module.__path__ may not line up with + # spec.submodule_search_paths, we can't necessarily rely + # on spec.parent here. + module.__package__ = module.__name__ + if not hasattr(module, '__path__'): + module.__package__ = spec.name.rpartition('.')[0] + except AttributeError: + pass + if getattr(module, '__spec__', None) is None: + try: + module.__spec__ = spec + except AttributeError: + pass + return module - def _load_unlocked(self): - # A helper for direct use by the import system. - if self.spec.loader is not None: - # not a namespace package - if not hasattr(self.spec.loader, 'exec_module'): - return self._load_backward_compatible() - - module = self.create() - with _installed_safely(module): - if self.spec.loader is None: - if self.spec.submodule_search_locations is None: - raise ImportError('missing loader', name=self.spec.name) - # A namespace package so do nothing. - else: - self._exec(module) +def _load_unlocked(spec): + # A helper for direct use by the import system. + if spec.loader is not None: + # not a namespace package + if not hasattr(spec.loader, 'exec_module'): + return _load_backward_compatible(spec) + + module = module_from_spec(spec) + with _installed_safely(module): + if spec.loader is None: + if spec.submodule_search_locations is None: + raise ImportError('missing loader', name=spec.name) + # A namespace package so do nothing. + else: + spec.loader.exec_module(module) - # We don't ensure that the import-related module attributes get - # set in the sys.modules replacement case. Such modules are on - # their own. - return sys.modules[self.spec.name] + # We don't ensure that the import-related module attributes get + # set in the sys.modules replacement case. Such modules are on + # their own. + return sys.modules[spec.name] - # A method used during testing of _load_unlocked() and by - # _load_module_shim(). - def load(self): - """Return a new module object, loaded by the spec's loader. +# A method used during testing of _load_unlocked() and by +# _load_module_shim(). +def _load(spec): + """Return a new module object, loaded by the spec's loader. - The module is not added to its parent. + The module is not added to its parent. - If a module is already in sys.modules, that existing module gets - clobbered. + If a module is already in sys.modules, that existing module gets + clobbered. - """ - _imp.acquire_lock() - with _ModuleLockManager(self.spec.name): - return self._load_unlocked() + """ + _imp.acquire_lock() + with _ModuleLockManager(spec.name): + return _load_unlocked(spec) def _fix_up_module(ns, name, pathname, cpathname=None): @@ -1349,6 +1302,10 @@ class FrozenImporter: """ return cls if _imp.is_frozen(fullname) else None + @classmethod + def create_module(cls, spec): + """Use default semantics for module creation.""" + @staticmethod def exec_module(module): name = module.__spec__.name @@ -1462,6 +1419,9 @@ class _LoaderBasics: tail_name = fullname.rpartition('.')[2] return filename_base == '__init__' and tail_name != '__init__' + def create_module(self, spec): + """Use default semantics for module creation.""" + def exec_module(self, module): """Execute the module.""" code = self.get_code(module.__name__) @@ -1799,7 +1759,7 @@ class _NamespacePath: self._path.append(item) -# We use this exclusively in init_module_attrs() for backward-compatibility. +# We use this exclusively in module_from_spec() for backward-compatibility. class _NamespaceLoader: def __init__(self, name, path, path_finder): self._path = _NamespacePath(name, path, path_finder) @@ -1822,6 +1782,9 @@ class _NamespaceLoader: def get_code(self, fullname): return compile('', '<string>', 'exec', dont_inherit=True) + def create_module(self, spec): + """Use default semantics for module creation.""" + def exec_module(self, module): pass @@ -1857,7 +1820,7 @@ class PathFinder: If 'hooks' is false then use sys.path_hooks. """ - if not sys.path_hooks: + if sys.path_hooks is not None and not sys.path_hooks: _warnings.warn('sys.path_hooks is empty', ImportWarning) for hook in sys.path_hooks: try: @@ -1876,7 +1839,12 @@ class PathFinder: """ if path == '': - path = _os.getcwd() + try: + path = _os.getcwd() + except FileNotFoundError: + # Don't cache the failure as the cwd can easily change to + # a valid directory later on. + return None try: finder = sys.path_importer_cache[path] except KeyError: @@ -2146,7 +2114,7 @@ def _find_spec_legacy(finder, name, path): def _find_spec(name, path, target=None): """Find a module's loader.""" - if not sys.meta_path: + if sys.meta_path is not None and not sys.meta_path: _warnings.warn('sys.meta_path is empty', ImportWarning) # We check sys.modules here for the reload case. While a passed-in # target will usually indicate a reload there is no guarantee, whereas @@ -2218,12 +2186,12 @@ def _find_and_load_unlocked(name, import_): path = parent_module.__path__ except AttributeError: msg = (_ERR_MSG + '; {!r} is not a package').format(name, parent) - raise ImportError(msg, name=name) + raise ImportError(msg, name=name) from None spec = _find_spec(name, path) if spec is None: raise ImportError(_ERR_MSG.format(name), name=name) else: - module = _SpecMethods(spec)._load_unlocked() + module = _load_unlocked(spec) if parent: # Set the module as an attribute on its parent. parent_module = sys.modules[parent] @@ -2358,8 +2326,7 @@ def _builtin_from_name(name): spec = BuiltinImporter.find_spec(name) if spec is None: raise ImportError('no built-in module named ' + name) - methods = _SpecMethods(spec) - return methods._load_unlocked() + return _load_unlocked(spec) def _setup(sys_module, _imp_module): @@ -2390,8 +2357,7 @@ def _setup(sys_module, _imp_module): else: continue spec = _spec_from_module(module, loader) - methods = _SpecMethods(spec) - methods.init_module_attrs(module) + _init_module_attrs(spec, module) # Directly load built-in modules needed during bootstrap. self_module = sys.modules[__name__] diff --git a/Lib/importlib/abc.py b/Lib/importlib/abc.py index 558abd3..2878488 100644 --- a/Lib/importlib/abc.py +++ b/Lib/importlib/abc.py @@ -122,11 +122,8 @@ class Loader(metaclass=abc.ABCMeta): This method should raise ImportError if anything prevents it from creating a new module. It may return None to indicate that the spec should create the new module. - - create_module() is optional. - """ - # By default, defer to _SpecMethods.create() for the new module. + # By default, defer to default semantics for the new module. return None # We don't define exec_module() here since that would break @@ -217,7 +214,8 @@ class InspectLoader(Loader): """ raise ImportError - def source_to_code(self, data, path='<string>'): + @staticmethod + def source_to_code(data, path='<string>'): """Compile 'data' into a code object. The 'data' argument can be anything that compile() can handle. The'path' diff --git a/Lib/importlib/util.py b/Lib/importlib/util.py index 6d73b1d..c42ef14 100644 --- a/Lib/importlib/util.py +++ b/Lib/importlib/util.py @@ -1,8 +1,9 @@ """Utility code for constructing importers, etc.""" - +from . import abc from ._bootstrap import MAGIC_NUMBER from ._bootstrap import cache_from_source from ._bootstrap import decode_source +from ._bootstrap import module_from_spec from ._bootstrap import source_from_cache from ._bootstrap import spec_from_loader from ._bootstrap import spec_from_file_location @@ -12,6 +13,7 @@ from ._bootstrap import _find_spec from contextlib import contextmanager import functools import sys +import types import warnings @@ -54,7 +56,7 @@ def _find_spec_from_path(name, path=None): try: spec = module.__spec__ except AttributeError: - raise ValueError('{}.__spec__ is not set'.format(name)) + raise ValueError('{}.__spec__ is not set'.format(name)) from None else: if spec is None: raise ValueError('{}.__spec__ is None'.format(name)) @@ -94,7 +96,7 @@ def find_spec(name, package=None): try: spec = module.__spec__ except AttributeError: - raise ValueError('{}.__spec__ is not set'.format(name)) + raise ValueError('{}.__spec__ is not set'.format(name)) from None else: if spec is None: raise ValueError('{}.__spec__ is None'.format(name)) @@ -200,3 +202,94 @@ def module_for_loader(fxn): return fxn(self, module, *args, **kwargs) return module_for_loader_wrapper + + +class _Module(types.ModuleType): + + """A subclass of the module type to allow __class__ manipulation.""" + + +class _LazyModule(types.ModuleType): + + """A subclass of the module type which triggers loading upon attribute access.""" + + def __getattribute__(self, attr): + """Trigger the load of the module and return the attribute.""" + # All module metadata must be garnered from __spec__ in order to avoid + # using mutated values. + # Stop triggering this method. + self.__class__ = _Module + # Get the original name to make sure no object substitution occurred + # in sys.modules. + original_name = self.__spec__.name + # Figure out exactly what attributes were mutated between the creation + # of the module and now. + attrs_then = self.__spec__.loader_state + attrs_now = self.__dict__ + attrs_updated = {} + for key, value in attrs_now.items(): + # Code that set the attribute may have kept a reference to the + # assigned object, making identity more important than equality. + if key not in attrs_then: + attrs_updated[key] = value + elif id(attrs_now[key]) != id(attrs_then[key]): + attrs_updated[key] = value + self.__spec__.loader.exec_module(self) + # If exec_module() was used directly there is no guarantee the module + # object was put into sys.modules. + if original_name in sys.modules: + if id(self) != id(sys.modules[original_name]): + msg = ('module object for {!r} substituted in sys.modules ' + 'during a lazy load') + raise ValueError(msg.format(original_name)) + # Update after loading since that's what would happen in an eager + # loading situation. + self.__dict__.update(attrs_updated) + return getattr(self, attr) + + def __delattr__(self, attr): + """Trigger the load and then perform the deletion.""" + # To trigger the load and raise an exception if the attribute + # doesn't exist. + self.__getattribute__(attr) + delattr(self, attr) + + +class LazyLoader(abc.Loader): + + """A loader that creates a module which defers loading until attribute access.""" + + @staticmethod + def __check_eager_loader(loader): + if not hasattr(loader, 'exec_module'): + raise TypeError('loader must define exec_module()') + elif hasattr(loader.__class__, 'create_module'): + if abc.Loader.create_module != loader.__class__.create_module: + # Only care if create_module() is overridden in a subclass of + # importlib.abc.Loader. + raise TypeError('loader cannot define create_module()') + + @classmethod + def factory(cls, loader): + """Construct a callable which returns the eager loader made lazy.""" + cls.__check_eager_loader(loader) + return lambda *args, **kwargs: cls(loader(*args, **kwargs)) + + def __init__(self, loader): + self.__check_eager_loader(loader) + self.loader = loader + + def create_module(self, spec): + """Create a module which can have its __class__ manipulated.""" + return _Module(spec.name) + + def exec_module(self, module): + """Make the module load lazily.""" + module.__spec__.loader = self.loader + module.__loader__ = self.loader + # Don't need to worry about deep-copying as trying to set an attribute + # on an object would have triggered the load, + # e.g. ``module.__spec__.loader = None`` would trigger a load from + # trying to access module.__spec__. + module.__spec__.loader_state = module.__dict__.copy() + module.__class__ = _LazyModule diff --git a/Lib/inspect.py b/Lib/inspect.py index 1641824..98d665d 100644 --- a/Lib/inspect.py +++ b/Lib/inspect.py @@ -17,7 +17,7 @@ Here are some of the useful functions provided by this module: getclasstree() - arrange classes so as to represent their hierarchy getargspec(), getargvalues(), getcallargs() - get info about function arguments - getfullargspec() - same, with support for Python-3000 features + getfullargspec() - same, with support for Python 3 features formatargspec(), formatargvalues() - format an argument spec getouterframes(), getinnerframes() - get info about frames currentframe() - get the current stack frame @@ -32,6 +32,7 @@ __author__ = ('Ka-Ping Yee <ping@lfw.org>', 'Yury Selivanov <yselivanov@sprymix.com>') import ast +import enum import importlib.machinery import itertools import linecache @@ -822,6 +823,7 @@ def getsourcelines(object): corresponding to the object and the line number indicates where in the original source file the first line of code was found. An OSError is raised if the source code cannot be retrieved.""" + object = unwrap(object) lines, lnum = findsource(object) if ismodule(object): return lines, 0 @@ -919,13 +921,12 @@ ArgSpec = namedtuple('ArgSpec', 'args varargs keywords defaults') def getargspec(func): """Get the names and default values of a function's arguments. - A tuple of four things is returned: (args, varargs, varkw, defaults). - 'args' is a list of the argument names. - 'args' will include keyword-only argument names. - 'varargs' and 'varkw' are the names of the * and ** arguments or None. + A tuple of four things is returned: (args, varargs, keywords, defaults). + 'args' is a list of the argument names, including keyword-only argument names. + 'varargs' and 'keywords' are the names of the * and ** arguments or None. 'defaults' is an n-tuple of the default values of the last n arguments. - Use the getfullargspec() API for Python-3000 code, as annotations + Use the getfullargspec() API for Python 3 code, as annotations and keyword arguments are supported. getargspec() will raise ValueError if the func has either annotations or keyword arguments. """ @@ -972,9 +973,10 @@ def getfullargspec(func): # getfullargspec() historically ignored __wrapped__ attributes, # so we ensure that remains the case in 3.3+ - sig = _signature_internal(func, - follow_wrapper_chains=False, - skip_bound_arg=False) + sig = _signature_from_callable(func, + follow_wrapper_chains=False, + skip_bound_arg=False, + sigcls=Signature) except Exception as ex: # Most of the times 'signature' will raise ValueError. # But, it can also raise AttributeError, and, maybe something @@ -1043,8 +1045,8 @@ def getargvalues(frame): def formatannotation(annotation, base_module=None): if isinstance(annotation, type): if annotation.__module__ in ('builtins', base_module): - return annotation.__name__ - return annotation.__module__+'.'+annotation.__name__ + return annotation.__qualname__ + return annotation.__module__+'.'+annotation.__qualname__ return repr(annotation) def formatannotationrelativeto(object): @@ -1317,6 +1319,8 @@ def getlineno(frame): # FrameType.f_lineno is now a descriptor that grovels co_lnotab return frame.f_lineno +FrameInfo = namedtuple('FrameInfo', ('frame',) + Traceback._fields) + def getouterframes(frame, context=1): """Get a list of records for a frame and all higher (calling) frames. @@ -1324,7 +1328,8 @@ def getouterframes(frame, context=1): name, a list of lines of context, and index within the context.""" framelist = [] while frame: - framelist.append((frame,) + getframeinfo(frame, context)) + frameinfo = (frame,) + getframeinfo(frame, context) + framelist.append(FrameInfo(*frameinfo)) frame = frame.f_back return framelist @@ -1335,7 +1340,8 @@ def getinnerframes(tb, context=1): name, a list of lines of context, and index within the context.""" framelist = [] while tb: - framelist.append((tb.tb_frame,) + getframeinfo(tb, context)) + frameinfo = (tb.tb_frame,) + getframeinfo(tb, context) + framelist.append(FrameInfo(*frameinfo)) tb = tb.tb_next return framelist @@ -1501,6 +1507,10 @@ _NonUserDefinedCallables = (_WrapperDescriptor, def _signature_get_user_defined_method(cls, method_name): + """Private helper. Checks if ``cls`` has an attribute + named ``method_name`` and returns it only if it is a + pure python function. + """ try: meth = getattr(cls, method_name) except AttributeError: @@ -1513,9 +1523,10 @@ def _signature_get_user_defined_method(cls, method_name): def _signature_get_partial(wrapped_sig, partial, extra_args=()): - # Internal helper to calculate how 'wrapped_sig' signature will - # look like after applying a 'functools.partial' object (or alike) - # on it. + """Private helper to calculate how 'wrapped_sig' signature will + look like after applying a 'functools.partial' object (or alike) + on it. + """ old_params = wrapped_sig.parameters new_params = OrderedDict(old_params.items()) @@ -1588,8 +1599,9 @@ def _signature_get_partial(wrapped_sig, partial, extra_args=()): def _signature_bound_method(sig): - # Internal helper to transform signatures for unbound - # functions to bound methods + """Private helper to transform signatures for unbound + functions to bound methods. + """ params = tuple(sig.parameters.values()) @@ -1613,8 +1625,9 @@ def _signature_bound_method(sig): def _signature_is_builtin(obj): - # Internal helper to test if `obj` is a callable that might - # support Argument Clinic's __text_signature__ protocol. + """Private helper to test if `obj` is a callable that might + support Argument Clinic's __text_signature__ protocol. + """ return (isbuiltin(obj) or ismethoddescriptor(obj) or isinstance(obj, _NonUserDefinedCallables) or @@ -1624,10 +1637,11 @@ def _signature_is_builtin(obj): def _signature_is_functionlike(obj): - # Internal helper to test if `obj` is a duck type of FunctionType. - # A good example of such objects are functions compiled with - # Cython, which have all attributes that a pure Python function - # would have, but have their code statically compiled. + """Private helper to test if `obj` is a duck type of FunctionType. + A good example of such objects are functions compiled with + Cython, which have all attributes that a pure Python function + would have, but have their code statically compiled. + """ if not callable(obj) or isclass(obj): # All function-like objects are obviously callables, @@ -1648,11 +1662,12 @@ def _signature_is_functionlike(obj): def _signature_get_bound_param(spec): - # Internal helper to get first parameter name from a - # __text_signature__ of a builtin method, which should - # be in the following format: '($param1, ...)'. - # Assumptions are that the first argument won't have - # a default value or an annotation. + """ Private helper to get first parameter name from a + __text_signature__ of a builtin method, which should + be in the following format: '($param1, ...)'. + Assumptions are that the first argument won't have + a default value or an annotation. + """ assert spec.startswith('($') @@ -1671,7 +1686,9 @@ def _signature_get_bound_param(spec): def _signature_strip_non_python_syntax(signature): """ - Takes a signature in Argument Clinic's extended signature format. + Private helper function. Takes a signature in Argument Clinic's + extended signature format. + Returns a tuple of three things: * that signature re-rendered in standard Python syntax, * the index of the "self" parameter (generally 0), or None if @@ -1740,8 +1757,10 @@ def _signature_strip_non_python_syntax(signature): def _signature_fromstr(cls, obj, s, skip_bound_arg=True): - # Internal helper to parse content of '__text_signature__' - # and return a Signature based on it + """Private helper to parse content of '__text_signature__' + and return a Signature based on it. + """ + Parameter = cls._parameter_cls clean_signature, self_parameter, last_positional_only = \ @@ -1879,8 +1898,10 @@ def _signature_fromstr(cls, obj, s, skip_bound_arg=True): def _signature_from_builtin(cls, func, skip_bound_arg=True): - # Internal helper function to get signature for - # builtin callables + """Private helper function to get signature for + builtin callables. + """ + if not _signature_is_builtin(func): raise TypeError("{!r} is not a Python builtin " "function".format(func)) @@ -1892,7 +1913,14 @@ def _signature_from_builtin(cls, func, skip_bound_arg=True): return _signature_fromstr(cls, func, s, skip_bound_arg) -def _signature_internal(obj, follow_wrapper_chains=True, skip_bound_arg=True): +def _signature_from_callable(obj, *, + follow_wrapper_chains=True, + skip_bound_arg=True, + sigcls): + + """Private helper function to get signature for arbitrary + callable objects. + """ if not callable(obj): raise TypeError('{!r} is not a callable object'.format(obj)) @@ -1900,9 +1928,12 @@ def _signature_internal(obj, follow_wrapper_chains=True, skip_bound_arg=True): if isinstance(obj, types.MethodType): # In this case we skip the first parameter of the underlying # function (usually `self` or `cls`). - sig = _signature_internal(obj.__func__, - follow_wrapper_chains, - skip_bound_arg) + sig = _signature_from_callable( + obj.__func__, + follow_wrapper_chains=follow_wrapper_chains, + skip_bound_arg=skip_bound_arg, + sigcls=sigcls) + if skip_bound_arg: return _signature_bound_method(sig) else: @@ -1937,9 +1968,12 @@ def _signature_internal(obj, follow_wrapper_chains=True, skip_bound_arg=True): # (usually `self`, or `cls`) will not be passed # automatically (as for boundmethods) - wrapped_sig = _signature_internal(partialmethod.func, - follow_wrapper_chains, - skip_bound_arg) + wrapped_sig = _signature_from_callable( + partialmethod.func, + follow_wrapper_chains=follow_wrapper_chains, + skip_bound_arg=skip_bound_arg, + sigcls=sigcls) + sig = _signature_get_partial(wrapped_sig, partialmethod, (None,)) first_wrapped_param = tuple(wrapped_sig.parameters.values())[0] @@ -1950,16 +1984,18 @@ def _signature_internal(obj, follow_wrapper_chains=True, skip_bound_arg=True): if isfunction(obj) or _signature_is_functionlike(obj): # If it's a pure Python function, or an object that is duck type # of a Python function (Cython functions, for instance), then: - return Signature.from_function(obj) + return sigcls.from_function(obj) if _signature_is_builtin(obj): - return _signature_from_builtin(Signature, obj, + return _signature_from_builtin(sigcls, obj, skip_bound_arg=skip_bound_arg) if isinstance(obj, functools.partial): - wrapped_sig = _signature_internal(obj.func, - follow_wrapper_chains, - skip_bound_arg) + wrapped_sig = _signature_from_callable( + obj.func, + follow_wrapper_chains=follow_wrapper_chains, + skip_bound_arg=skip_bound_arg, + sigcls=sigcls) return _signature_get_partial(wrapped_sig, obj) sig = None @@ -1970,23 +2006,29 @@ def _signature_internal(obj, follow_wrapper_chains=True, skip_bound_arg=True): # in its metaclass call = _signature_get_user_defined_method(type(obj), '__call__') if call is not None: - sig = _signature_internal(call, - follow_wrapper_chains, - skip_bound_arg) + sig = _signature_from_callable( + call, + follow_wrapper_chains=follow_wrapper_chains, + skip_bound_arg=skip_bound_arg, + sigcls=sigcls) else: # Now we check if the 'obj' class has a '__new__' method new = _signature_get_user_defined_method(obj, '__new__') if new is not None: - sig = _signature_internal(new, - follow_wrapper_chains, - skip_bound_arg) + sig = _signature_from_callable( + new, + follow_wrapper_chains=follow_wrapper_chains, + skip_bound_arg=skip_bound_arg, + sigcls=sigcls) else: # Finally, we should have at least __init__ implemented init = _signature_get_user_defined_method(obj, '__init__') if init is not None: - sig = _signature_internal(init, - follow_wrapper_chains, - skip_bound_arg) + sig = _signature_from_callable( + init, + follow_wrapper_chains=follow_wrapper_chains, + skip_bound_arg=skip_bound_arg, + sigcls=sigcls) if sig is None: # At this point we know, that `obj` is a class, with no user- @@ -2008,7 +2050,7 @@ def _signature_internal(obj, follow_wrapper_chains=True, skip_bound_arg=True): if text_sig: # If 'obj' class has a __text_signature__ attribute: # return a signature based on it - return _signature_fromstr(Signature, obj, text_sig) + return _signature_fromstr(sigcls, obj, text_sig) # No '__text_signature__' was found for the 'obj' class. # Last option is to check if its '__init__' is @@ -2028,9 +2070,11 @@ def _signature_internal(obj, follow_wrapper_chains=True, skip_bound_arg=True): call = _signature_get_user_defined_method(type(obj), '__call__') if call is not None: try: - sig = _signature_internal(call, - follow_wrapper_chains, - skip_bound_arg) + sig = _signature_from_callable( + call, + follow_wrapper_chains=follow_wrapper_chains, + skip_bound_arg=skip_bound_arg, + sigcls=sigcls) except ValueError as ex: msg = 'no signature found for {!r}'.format(obj) raise ValueError(msg) from ex @@ -2050,41 +2094,35 @@ def _signature_internal(obj, follow_wrapper_chains=True, skip_bound_arg=True): raise ValueError('callable {!r} is not supported by signature'.format(obj)) -def signature(obj): - '''Get a signature object for the passed callable.''' - return _signature_internal(obj) - class _void: - '''A private marker - used in Parameter & Signature''' + """A private marker - used in Parameter & Signature.""" class _empty: - pass + """Marker object for Signature.empty and Parameter.empty.""" -class _ParameterKind(int): - def __new__(self, *args, name): - obj = int.__new__(self, *args) - obj._name = name - return obj +class _ParameterKind(enum.IntEnum): + POSITIONAL_ONLY = 0 + POSITIONAL_OR_KEYWORD = 1 + VAR_POSITIONAL = 2 + KEYWORD_ONLY = 3 + VAR_KEYWORD = 4 def __str__(self): - return self._name - - def __repr__(self): - return '<_ParameterKind: {!r}>'.format(self._name) + return self._name_ -_POSITIONAL_ONLY = _ParameterKind(0, name='POSITIONAL_ONLY') -_POSITIONAL_OR_KEYWORD = _ParameterKind(1, name='POSITIONAL_OR_KEYWORD') -_VAR_POSITIONAL = _ParameterKind(2, name='VAR_POSITIONAL') -_KEYWORD_ONLY = _ParameterKind(3, name='KEYWORD_ONLY') -_VAR_KEYWORD = _ParameterKind(4, name='VAR_KEYWORD') +_POSITIONAL_ONLY = _ParameterKind.POSITIONAL_ONLY +_POSITIONAL_OR_KEYWORD = _ParameterKind.POSITIONAL_OR_KEYWORD +_VAR_POSITIONAL = _ParameterKind.VAR_POSITIONAL +_KEYWORD_ONLY = _ParameterKind.KEYWORD_ONLY +_VAR_KEYWORD = _ParameterKind.VAR_KEYWORD class Parameter: - '''Represents a parameter in a function signature. + """Represents a parameter in a function signature. Has the following public attributes: @@ -2103,7 +2141,7 @@ class Parameter: Possible values: `Parameter.POSITIONAL_ONLY`, `Parameter.POSITIONAL_OR_KEYWORD`, `Parameter.VAR_POSITIONAL`, `Parameter.KEYWORD_ONLY`, `Parameter.VAR_KEYWORD`. - ''' + """ __slots__ = ('_name', '_kind', '_default', '_annotation') @@ -2140,6 +2178,16 @@ class Parameter: self._name = name + def __reduce__(self): + return (type(self), + (self._name, self._kind), + {'_default': self._default, + '_annotation': self._annotation}) + + def __setstate__(self, state): + self._default = state['_default'] + self._annotation = state['_annotation'] + @property def name(self): return self._name @@ -2158,7 +2206,7 @@ class Parameter: def replace(self, *, name=_void, kind=_void, annotation=_void, default=_void): - '''Creates a customized copy of the Parameter.''' + """Creates a customized copy of the Parameter.""" if name is _void: name = self._name @@ -2194,8 +2242,11 @@ class Parameter: return formatted def __repr__(self): - return '<{} at {:#x} {!r}>'.format(self.__class__.__name__, - id(self), self.name) + return '<{} at {:#x} "{}">'.format(self.__class__.__name__, + id(self), self) + + def __hash__(self): + return hash((self.name, self.kind, self.annotation, self.default)) def __eq__(self, other): return (issubclass(other.__class__, Parameter) and @@ -2204,12 +2255,9 @@ class Parameter: self._default == other._default and self._annotation == other._annotation) - def __ne__(self, other): - return not self.__eq__(other) - class BoundArguments: - '''Result of `Signature.bind` call. Holds the mapping of arguments + """Result of `Signature.bind` call. Holds the mapping of arguments to the function's parameters. Has the following public attributes: @@ -2223,7 +2271,7 @@ class BoundArguments: Tuple of positional arguments values. * kwargs : dict Dict of keyword arguments values. - ''' + """ def __init__(self, signature, arguments): self.arguments = arguments @@ -2291,12 +2339,9 @@ class BoundArguments: self.signature == other.signature and self.arguments == other.arguments) - def __ne__(self, other): - return not self.__eq__(other) - class Signature: - '''A Signature object represents the overall signature of a function. + """A Signature object represents the overall signature of a function. It stores a Parameter object for each parameter accepted by the function, as well as information specific to the function itself. @@ -2316,7 +2361,7 @@ class Signature: * bind_partial(*args, **kwargs) -> BoundArguments Creates a partial mapping from positional and keyword arguments to parameters (simulating 'functools.partial' behavior.) - ''' + """ __slots__ = ('_return_annotation', '_parameters') @@ -2327,9 +2372,9 @@ class Signature: def __init__(self, parameters=None, *, return_annotation=_empty, __validate_parameters__=True): - '''Constructs Signature from the given list of Parameter + """Constructs Signature from the given list of Parameter objects and 'return_annotation'. All arguments are optional. - ''' + """ if parameters is None: params = OrderedDict() @@ -2378,7 +2423,7 @@ class Signature: @classmethod def from_function(cls, func): - '''Constructs Signature for the given python function''' + """Constructs Signature for the given python function.""" is_duck_function = False if not isfunction(func): @@ -2459,8 +2504,14 @@ class Signature: @classmethod def from_builtin(cls, func): + """Constructs Signature for the given builtin function.""" return _signature_from_builtin(cls, func) + @classmethod + def from_callable(cls, obj): + """Constructs Signature for the given callable object.""" + return _signature_from_callable(obj, sigcls=cls) + @property def parameters(self): return self._parameters @@ -2470,10 +2521,10 @@ class Signature: return self._return_annotation def replace(self, *, parameters=_void, return_annotation=_void): - '''Creates a customized copy of the Signature. + """Creates a customized copy of the Signature. Pass 'parameters' and/or 'return_annotation' arguments to override them in the new copy. - ''' + """ if parameters is _void: parameters = self.parameters.values() @@ -2484,41 +2535,26 @@ class Signature: return type(self)(parameters, return_annotation=return_annotation) - def __eq__(self, other): - if (not issubclass(type(other), Signature) or - self.return_annotation != other.return_annotation or - len(self.parameters) != len(other.parameters)): - return False + def _hash_basis(self): + params = tuple(param for param in self.parameters.values() + if param.kind != _KEYWORD_ONLY) - other_positions = {param: idx - for idx, param in enumerate(other.parameters.keys())} + kwo_params = {param.name: param for param in self.parameters.values() + if param.kind == _KEYWORD_ONLY} - for idx, (param_name, param) in enumerate(self.parameters.items()): - if param.kind == _KEYWORD_ONLY: - try: - other_param = other.parameters[param_name] - except KeyError: - return False - else: - if param != other_param: - return False - else: - try: - other_idx = other_positions[param_name] - except KeyError: - return False - else: - if (idx != other_idx or - param != other.parameters[param_name]): - return False + return params, kwo_params, self.return_annotation - return True + def __hash__(self): + params, kwo_params, return_annotation = self._hash_basis() + kwo_params = frozenset(kwo_params.values()) + return hash((params, kwo_params, return_annotation)) - def __ne__(self, other): - return not self.__eq__(other) + def __eq__(self, other): + return (isinstance(other, Signature) and + self._hash_basis() == other._hash_basis()) def _bind(self, args, kwargs, *, partial=False): - '''Private method. Don't use directly.''' + """Private method. Don't use directly.""" arguments = OrderedDict() @@ -2645,19 +2681,31 @@ class Signature: return self._bound_arguments_cls(self, arguments) def bind(*args, **kwargs): - '''Get a BoundArguments object, that maps the passed `args` + """Get a BoundArguments object, that maps the passed `args` and `kwargs` to the function's signature. Raises `TypeError` if the passed arguments can not be bound. - ''' + """ return args[0]._bind(args[1:], kwargs) def bind_partial(*args, **kwargs): - '''Get a BoundArguments object, that partially maps the + """Get a BoundArguments object, that partially maps the passed `args` and `kwargs` to the function's signature. Raises `TypeError` if the passed arguments can not be bound. - ''' + """ return args[0]._bind(args[1:], kwargs, partial=True) + def __reduce__(self): + return (type(self), + (tuple(self._parameters.values()),), + {'_return_annotation': self._return_annotation}) + + def __setstate__(self, state): + self._return_annotation = state['_return_annotation'] + + def __repr__(self): + return '<{} at {:#x} "{}">'.format(self.__class__.__name__, + id(self), self) + def __str__(self): result = [] render_pos_only_separator = False @@ -2703,6 +2751,12 @@ class Signature: return rendered + +def signature(obj): + """Get a signature object for the passed callable.""" + return Signature.from_callable(obj) + + def _main(): """ Logic for inspecting an object given at command line """ import argparse diff --git a/Lib/ipaddress.py b/Lib/ipaddress.py index ac03c36..6c225f3 100644 --- a/Lib/ipaddress.py +++ b/Lib/ipaddress.py @@ -164,22 +164,23 @@ def _split_optional_netmask(address): def _find_address_range(addresses): - """Find a sequence of IPv#Address. + """Find a sequence of sorted deduplicated IPv#Address. Args: addresses: a list of IPv#Address objects. - Returns: + Yields: A tuple containing the first and last IP addresses in the sequence. """ - first = last = addresses[0] - for ip in addresses[1:]: - if ip._ip == last._ip + 1: - last = ip - else: - break - return (first, last) + it = iter(addresses) + first = last = next(it) + for ip in it: + if ip._ip != last._ip + 1: + yield first, last + first = ip + last = ip + yield first, last def _count_righthand_zero_bits(number, bits): @@ -195,11 +196,7 @@ def _count_righthand_zero_bits(number, bits): """ if number == 0: return bits - for i in range(bits): - if (number >> i) & 1: - return i - # All bits of interest were zero, even if there are more in the number - return bits + return min(bits, (~number & (number-1)).bit_length()) def summarize_address_range(first, last): @@ -250,15 +247,14 @@ def summarize_address_range(first, last): while first_int <= last_int: nbits = min(_count_righthand_zero_bits(first_int, ip_bits), (last_int - first_int + 1).bit_length() - 1) - net = ip('%s/%d' % (first, ip_bits - nbits)) + net = ip((first_int, ip_bits - nbits)) yield net first_int += 1 << nbits if first_int - 1 == ip._ALL_ONES: break - first = first.__class__(first_int) -def _collapse_addresses_recursive(addresses): +def _collapse_addresses_internal(addresses): """Loops through the addresses, collapsing concurrent netblocks. Example: @@ -268,7 +264,7 @@ def _collapse_addresses_recursive(addresses): ip3 = IPv4Network('192.0.2.128/26') ip4 = IPv4Network('192.0.2.192/26') - _collapse_addresses_recursive([ip1, ip2, ip3, ip4]) -> + _collapse_addresses_internal([ip1, ip2, ip3, ip4]) -> [IPv4Network('192.0.2.0/24')] This shouldn't be called directly; it is called via @@ -282,28 +278,29 @@ def _collapse_addresses_recursive(addresses): passed. """ - while True: - last_addr = None - ret_array = [] - optimized = False - - for cur_addr in addresses: - if not ret_array: - last_addr = cur_addr - ret_array.append(cur_addr) - elif (cur_addr.network_address >= last_addr.network_address and - cur_addr.broadcast_address <= last_addr.broadcast_address): - optimized = True - elif cur_addr == list(last_addr.supernet().subnets())[1]: - ret_array[-1] = last_addr = last_addr.supernet() - optimized = True - else: - last_addr = cur_addr - ret_array.append(cur_addr) - - addresses = ret_array - if not optimized: - return addresses + # First merge + to_merge = list(addresses) + subnets = {} + while to_merge: + net = to_merge.pop() + supernet = net.supernet() + existing = subnets.get(supernet) + if existing is None: + subnets[supernet] = net + elif existing != net: + # Merge consecutive subnets + del subnets[supernet] + to_merge.append(supernet) + # Then iterate over resulting networks, skipping subsumed subnets + last = None + for net in sorted(subnets.values()): + if last is not None: + # Since they are sorted, last.network_address <= net.network_address + # is a given. + if last.broadcast_address >= net.broadcast_address: + continue + yield net + last = net def collapse_addresses(addresses): @@ -324,7 +321,6 @@ def collapse_addresses(addresses): TypeError: If passed a list of mixed version objects. """ - i = 0 addrs = [] ips = [] nets = [] @@ -352,15 +348,13 @@ def collapse_addresses(addresses): # sort and dedup ips = sorted(set(ips)) - nets = sorted(set(nets)) - while i < len(ips): - (first, last) = _find_address_range(ips[i:]) - i = ips.index(last) + 1 - addrs.extend(summarize_address_range(first, last)) + # find consecutive address ranges in the sorted sequence and summarize them + if ips: + for first, last in _find_address_range(ips): + addrs.extend(summarize_address_range(first, last)) - return iter(_collapse_addresses_recursive(sorted( - addrs + nets, key=_BaseNetwork._get_networks_key))) + return _collapse_addresses_internal(addrs + nets) def get_mixed_type_key(obj): @@ -403,6 +397,17 @@ class _IPAddressBase: return str(self) @property + def reverse_pointer(self): + """The name of the reverse DNS pointer for the IP address, e.g.: + >>> ipaddress.ip_address("127.0.0.1").reverse_pointer + '1.0.0.127.in-addr.arpa' + >>> ipaddress.ip_address("2001:db8::1").reverse_pointer + '1.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.8.b.d.0.1.0.0.2.ip6.arpa' + + """ + return self._reverse_pointer() + + @property def version(self): msg = '%200s has no version specified' % (type(self),) raise NotImplementedError(msg) @@ -423,7 +428,8 @@ class _IPAddressBase: raise AddressValueError(msg % (address, address_len, expected_len, self._version)) - def _ip_int_from_prefix(self, prefixlen): + @classmethod + def _ip_int_from_prefix(cls, prefixlen): """Turn the prefix length into a bitwise netmask Args: @@ -433,9 +439,10 @@ class _IPAddressBase: An integer. """ - return self._ALL_ONES ^ (self._ALL_ONES >> prefixlen) + return cls._ALL_ONES ^ (cls._ALL_ONES >> prefixlen) - def _prefix_from_ip_int(self, ip_int): + @classmethod + def _prefix_from_ip_int(cls, ip_int): """Return prefix length from the bitwise netmask. Args: @@ -448,22 +455,24 @@ class _IPAddressBase: ValueError: If the input intermingles zeroes & ones """ trailing_zeroes = _count_righthand_zero_bits(ip_int, - self._max_prefixlen) - prefixlen = self._max_prefixlen - trailing_zeroes + cls._max_prefixlen) + prefixlen = cls._max_prefixlen - trailing_zeroes leading_ones = ip_int >> trailing_zeroes all_ones = (1 << prefixlen) - 1 if leading_ones != all_ones: - byteslen = self._max_prefixlen // 8 + byteslen = cls._max_prefixlen // 8 details = ip_int.to_bytes(byteslen, 'big') msg = 'Netmask pattern %r mixes zeroes & ones' raise ValueError(msg % details) return prefixlen - def _report_invalid_netmask(self, netmask_str): + @classmethod + def _report_invalid_netmask(cls, netmask_str): msg = '%r is not a valid netmask' % netmask_str raise NetmaskValueError(msg) from None - def _prefix_from_prefix_string(self, prefixlen_str): + @classmethod + def _prefix_from_prefix_string(cls, prefixlen_str): """Return prefix length from a numeric string Args: @@ -478,16 +487,17 @@ class _IPAddressBase: # int allows a leading +/- as well as surrounding whitespace, # so we ensure that isn't the case if not _BaseV4._DECIMAL_DIGITS.issuperset(prefixlen_str): - self._report_invalid_netmask(prefixlen_str) + cls._report_invalid_netmask(prefixlen_str) try: prefixlen = int(prefixlen_str) except ValueError: - self._report_invalid_netmask(prefixlen_str) - if not (0 <= prefixlen <= self._max_prefixlen): - self._report_invalid_netmask(prefixlen_str) + cls._report_invalid_netmask(prefixlen_str) + if not (0 <= prefixlen <= cls._max_prefixlen): + cls._report_invalid_netmask(prefixlen_str) return prefixlen - def _prefix_from_ip_string(self, ip_str): + @classmethod + def _prefix_from_ip_string(cls, ip_str): """Turn a netmask/hostmask string into a prefix length Args: @@ -501,24 +511,27 @@ class _IPAddressBase: """ # Parse the netmask/hostmask like an IP address. try: - ip_int = self._ip_int_from_string(ip_str) + ip_int = cls._ip_int_from_string(ip_str) except AddressValueError: - self._report_invalid_netmask(ip_str) + cls._report_invalid_netmask(ip_str) # Try matching a netmask (this would be /1*0*/ as a bitwise regexp). # Note that the two ambiguous cases (all-ones and all-zeroes) are # treated as netmasks. try: - return self._prefix_from_ip_int(ip_int) + return cls._prefix_from_ip_int(ip_int) except ValueError: pass # Invert the bits, and try matching a /0+1+/ hostmask instead. - ip_int ^= self._ALL_ONES + ip_int ^= cls._ALL_ONES try: - return self._prefix_from_ip_int(ip_int) + return cls._prefix_from_ip_int(ip_int) except ValueError: - self._report_invalid_netmask(ip_str) + cls._report_invalid_netmask(ip_str) + + def __reduce__(self): + return self.__class__, (str(self),) @functools.total_ordering @@ -530,11 +543,6 @@ class _BaseAddress(_IPAddressBase): used by single IP addresses. """ - def __init__(self, address): - if (not isinstance(address, bytes) - and '/' in str(address)): - raise AddressValueError("Unexpected '/' in %r" % address) - def __int__(self): return self._ip @@ -579,6 +587,9 @@ class _BaseAddress(_IPAddressBase): def _get_address_key(self): return (self._version, self) + def __reduce__(self): + return self.__class__, (self._ip,) + @functools.total_ordering class _BaseNetwork(_IPAddressBase): @@ -765,7 +776,7 @@ class _BaseNetwork(_IPAddressBase): other.broadcast_address <= self.broadcast_address): raise ValueError('%s not contained in %s' % (other, self)) if other == self: - raise StopIteration + return # Make sure we're comparing the network of other. other = other.__class__('%s/%s' % (other.network_address, @@ -900,20 +911,11 @@ class _BaseNetwork(_IPAddressBase): 'prefix length diff %d is invalid for netblock %s' % ( new_prefixlen, self)) - first = self.__class__('%s/%s' % - (self.network_address, - self._prefixlen + prefixlen_diff)) - - yield first - current = first - while True: - broadcast = current.broadcast_address - if broadcast == self.broadcast_address: - return - new_addr = self._address_class(int(broadcast) + 1) - current = self.__class__('%s/%s' % (new_addr, - new_prefixlen)) - + start = int(self.network_address) + end = int(self.broadcast_address) + step = (int(self.hostmask) + 1) >> prefixlen_diff + for new_addr in range(start, end, step): + current = self.__class__((new_addr, new_prefixlen)) yield current def supernet(self, prefixlen_diff=1, new_prefix=None): @@ -947,15 +949,15 @@ class _BaseNetwork(_IPAddressBase): raise ValueError('cannot set prefixlen_diff and new_prefix') prefixlen_diff = self._prefixlen - new_prefix - if self.prefixlen - prefixlen_diff < 0: + new_prefixlen = self.prefixlen - prefixlen_diff + if new_prefixlen < 0: raise ValueError( 'current prefixlen is %d, cannot have a prefixlen_diff of %d' % (self.prefixlen, prefixlen_diff)) - # TODO (pmoody): optimize this. - t = self.__class__('%s/%d' % (self.network_address, - self.prefixlen - prefixlen_diff), - strict=False) - return t.__class__('%s/%d' % (t.network_address, t.prefixlen)) + return self.__class__(( + int(self.network_address) & (int(self.netmask) << prefixlen_diff), + new_prefixlen + )) @property def is_multicast(self): @@ -1054,16 +1056,45 @@ class _BaseV4: _DECIMAL_DIGITS = frozenset('0123456789') # the valid octets for host and netmasks. only useful for IPv4. - _valid_mask_octets = frozenset((255, 254, 252, 248, 240, 224, 192, 128, 0)) + _valid_mask_octets = frozenset({255, 254, 252, 248, 240, 224, 192, 128, 0}) + + _max_prefixlen = IPV4LENGTH + # There are only a handful of valid v4 netmasks, so we cache them all + # when constructed (see _make_netmask()). + _netmask_cache = {} def __init__(self, address): self._version = 4 - self._max_prefixlen = IPV4LENGTH def _explode_shorthand_ip_string(self): return str(self) - def _ip_int_from_string(self, ip_str): + @classmethod + def _make_netmask(cls, arg): + """Make a (netmask, prefix_len) tuple from the given argument. + + Argument can be: + - an integer (the prefix length) + - a string representing the prefix length (e.g. "24") + - a string representing the prefix netmask (e.g. "255.255.255.0") + """ + if arg not in cls._netmask_cache: + if isinstance(arg, int): + prefixlen = arg + else: + try: + # Check for a netmask in prefix length form + prefixlen = cls._prefix_from_prefix_string(arg) + except NetmaskValueError: + # Check for a netmask or hostmask in dotted-quad form. + # This may raise NetmaskValueError. + prefixlen = cls._prefix_from_ip_string(arg) + netmask = IPv4Address(cls._ip_int_from_prefix(prefixlen)) + cls._netmask_cache[arg] = netmask, prefixlen + return cls._netmask_cache[arg] + + @classmethod + def _ip_int_from_string(cls, ip_str): """Turn the given IP string into an integer for comparison. Args: @@ -1084,11 +1115,12 @@ class _BaseV4: raise AddressValueError("Expected 4 octets in %r" % ip_str) try: - return int.from_bytes(map(self._parse_octet, octets), 'big') + return int.from_bytes(map(cls._parse_octet, octets), 'big') except ValueError as exc: raise AddressValueError("%s in %r" % (exc, ip_str)) from None - def _parse_octet(self, octet_str): + @classmethod + def _parse_octet(cls, octet_str): """Convert a decimal octet into an integer. Args: @@ -1104,7 +1136,7 @@ class _BaseV4: if not octet_str: raise ValueError("Empty octet not permitted") # Whitelist the characters, since int() allows a lot of bizarre stuff. - if not self._DECIMAL_DIGITS.issuperset(octet_str): + if not cls._DECIMAL_DIGITS.issuperset(octet_str): msg = "Only decimal digits permitted in %r" raise ValueError(msg % octet_str) # We do the length check second, since the invalid character error @@ -1124,7 +1156,8 @@ class _BaseV4: raise ValueError("Octet %d (> 255) not permitted" % octet_int) return octet_int - def _string_from_ip_int(self, ip_int): + @classmethod + def _string_from_ip_int(cls, ip_int): """Turns a 32-bit integer into dotted decimal notation. Args: @@ -1188,6 +1221,15 @@ class _BaseV4: return True return False + def _reverse_pointer(self): + """Return the reverse DNS pointer name for the IPv4 address. + + This implements the method described in RFC1035 3.5. + + """ + reverse_octets = str(self).split('.')[::-1] + return '.'.join(reverse_octets) + '.in-addr.arpa' + @property def max_prefixlen(self): return self._max_prefixlen @@ -1217,7 +1259,6 @@ class IPv4Address(_BaseV4, _BaseAddress): AddressValueError: If ipaddress isn't a valid IPv4 address. """ - _BaseAddress.__init__(self, address) _BaseV4.__init__(self, address) # Efficient constructor from integer. @@ -1235,6 +1276,8 @@ class IPv4Address(_BaseV4, _BaseAddress): # Assume input argument to be string or any object representation # which converts into a formatted IP string. addr_str = str(address) + if '/' in addr_str: + raise AddressValueError("Unexpected '/' in %r" % address) self._ip = self._ip_int_from_string(addr_str) @property @@ -1251,8 +1294,7 @@ class IPv4Address(_BaseV4, _BaseAddress): reserved IPv4 Network range. """ - reserved_network = IPv4Network('240.0.0.0/4') - return self in reserved_network + return self in self._constants._reserved_network @property @functools.lru_cache() @@ -1264,21 +1306,7 @@ class IPv4Address(_BaseV4, _BaseAddress): iana-ipv4-special-registry. """ - return (self in IPv4Network('0.0.0.0/8') or - self in IPv4Network('10.0.0.0/8') or - self in IPv4Network('127.0.0.0/8') or - self in IPv4Network('169.254.0.0/16') or - self in IPv4Network('172.16.0.0/12') or - self in IPv4Network('192.0.0.0/29') or - self in IPv4Network('192.0.0.170/31') or - self in IPv4Network('192.0.2.0/24') or - self in IPv4Network('192.168.0.0/16') or - self in IPv4Network('198.18.0.0/15') or - self in IPv4Network('198.51.100.0/24') or - self in IPv4Network('203.0.113.0/24') or - self in IPv4Network('240.0.0.0/4') or - self in IPv4Network('255.255.255.255/32')) - + return any(self in net for net in self._constants._private_networks) @property def is_multicast(self): @@ -1289,8 +1317,7 @@ class IPv4Address(_BaseV4, _BaseAddress): See RFC 3171 for details. """ - multicast_network = IPv4Network('224.0.0.0/4') - return self in multicast_network + return self in self._constants._multicast_network @property def is_unspecified(self): @@ -1301,8 +1328,7 @@ class IPv4Address(_BaseV4, _BaseAddress): RFC 5735 3. """ - unspecified_address = IPv4Address('0.0.0.0') - return self == unspecified_address + return self == self._constants._unspecified_address @property def is_loopback(self): @@ -1312,8 +1338,7 @@ class IPv4Address(_BaseV4, _BaseAddress): A boolean, True if the address is a loopback per RFC 3330. """ - loopback_network = IPv4Network('127.0.0.0/8') - return self in loopback_network + return self in self._constants._loopback_network @property def is_link_local(self): @@ -1323,8 +1348,7 @@ class IPv4Address(_BaseV4, _BaseAddress): A boolean, True if the address is link-local per RFC 3927. """ - linklocal_network = IPv4Network('169.254.0.0/16') - return self in linklocal_network + return self in self._constants._linklocal_network class IPv4Interface(IPv4Address): @@ -1336,6 +1360,18 @@ class IPv4Interface(IPv4Address): self._prefixlen = self._max_prefixlen return + if isinstance(address, tuple): + IPv4Address.__init__(self, address[0]) + if len(address) > 1: + self._prefixlen = int(address[1]) + else: + self._prefixlen = self._max_prefixlen + + self.network = IPv4Network(address, strict=False) + self.netmask = self.network.netmask + self.hostmask = self.network.hostmask + return + addr = _split_optional_netmask(address) IPv4Address.__init__(self, addr[0]) @@ -1375,6 +1411,8 @@ class IPv4Interface(IPv4Address): def __hash__(self): return self._ip ^ self._prefixlen ^ int(self.network.network_address) + __reduce__ = _IPAddressBase.__reduce__ + @property def ip(self): return IPv4Address(self._ip) @@ -1451,20 +1489,28 @@ class IPv4Network(_BaseV4, _BaseNetwork): _BaseV4.__init__(self, address) _BaseNetwork.__init__(self, address) - # Constructing from a packed address - if isinstance(address, bytes): + # Constructing from a packed address or integer + if isinstance(address, (int, bytes)): self.network_address = IPv4Address(address) - self._prefixlen = self._max_prefixlen - self.netmask = IPv4Address(self._ALL_ONES) - #fixme: address/network test here + self.netmask, self._prefixlen = self._make_netmask(self._max_prefixlen) + #fixme: address/network test here. return - # Efficient constructor from integer. - if isinstance(address, int): - self.network_address = IPv4Address(address) - self._prefixlen = self._max_prefixlen - self.netmask = IPv4Address(self._ALL_ONES) - #fixme: address/network test here. + if isinstance(address, tuple): + if len(address) > 1: + arg = address[1] + else: + # We weren't given an address[1] + arg = self._max_prefixlen + self.network_address = IPv4Address(address[0]) + self.netmask, self._prefixlen = self._make_netmask(arg) + packed = int(self.network_address) + if packed & int(self.netmask) != packed: + if strict: + raise ValueError('%s has host bits set' % self) + else: + self.network_address = IPv4Address(packed & + int(self.netmask)) return # Assume input argument to be string or any object representation @@ -1473,16 +1519,10 @@ class IPv4Network(_BaseV4, _BaseNetwork): self.network_address = IPv4Address(self._ip_int_from_string(addr[0])) if len(addr) == 2: - try: - # Check for a netmask in prefix length form - self._prefixlen = self._prefix_from_prefix_string(addr[1]) - except NetmaskValueError: - # Check for a netmask or hostmask in dotted-quad form. - # This may raise NetmaskValueError. - self._prefixlen = self._prefix_from_ip_string(addr[1]) + arg = addr[1] else: - self._prefixlen = self._max_prefixlen - self.netmask = IPv4Address(self._ip_int_from_prefix(self._prefixlen)) + arg = self._max_prefixlen + self.netmask, self._prefixlen = self._make_netmask(arg) if strict: if (IPv4Address(int(self.network_address) & int(self.netmask)) != @@ -1509,6 +1549,37 @@ class IPv4Network(_BaseV4, _BaseNetwork): not self.is_private) +class _IPv4Constants: + _linklocal_network = IPv4Network('169.254.0.0/16') + + _loopback_network = IPv4Network('127.0.0.0/8') + + _multicast_network = IPv4Network('224.0.0.0/4') + + _private_networks = [ + IPv4Network('0.0.0.0/8'), + IPv4Network('10.0.0.0/8'), + IPv4Network('127.0.0.0/8'), + IPv4Network('169.254.0.0/16'), + IPv4Network('172.16.0.0/12'), + IPv4Network('192.0.0.0/29'), + IPv4Network('192.0.0.170/31'), + IPv4Network('192.0.2.0/24'), + IPv4Network('192.168.0.0/16'), + IPv4Network('198.18.0.0/15'), + IPv4Network('198.51.100.0/24'), + IPv4Network('203.0.113.0/24'), + IPv4Network('240.0.0.0/4'), + IPv4Network('255.255.255.255/32'), + ] + + _reserved_network = IPv4Network('240.0.0.0/4') + + _unspecified_address = IPv4Address('0.0.0.0') + + +IPv4Address._constants = _IPv4Constants + class _BaseV6: @@ -1522,12 +1593,35 @@ class _BaseV6: _ALL_ONES = (2**IPV6LENGTH) - 1 _HEXTET_COUNT = 8 _HEX_DIGITS = frozenset('0123456789ABCDEFabcdef') + _max_prefixlen = IPV6LENGTH + + # There are only a bunch of valid v6 netmasks, so we cache them all + # when constructed (see _make_netmask()). + _netmask_cache = {} def __init__(self, address): self._version = 6 - self._max_prefixlen = IPV6LENGTH - def _ip_int_from_string(self, ip_str): + @classmethod + def _make_netmask(cls, arg): + """Make a (netmask, prefix_len) tuple from the given argument. + + Argument can be: + - an integer (the prefix length) + - a string representing the prefix length (e.g. "24") + - a string representing the prefix netmask (e.g. "255.255.255.0") + """ + if arg not in cls._netmask_cache: + if isinstance(arg, int): + prefixlen = arg + else: + prefixlen = cls._prefix_from_prefix_string(arg) + netmask = IPv6Address(cls._ip_int_from_prefix(prefixlen)) + cls._netmask_cache[arg] = netmask, prefixlen + return cls._netmask_cache[arg] + + @classmethod + def _ip_int_from_string(cls, ip_str): """Turn an IPv6 ip_str into an integer. Args: @@ -1563,7 +1657,7 @@ class _BaseV6: # An IPv6 address can't have more than 8 colons (9 parts). # The extra colon comes from using the "::" notation for a single # leading or trailing zero part. - _max_parts = self._HEXTET_COUNT + 1 + _max_parts = cls._HEXTET_COUNT + 1 if len(parts) > _max_parts: msg = "At most %d colons permitted in %r" % (_max_parts-1, ip_str) raise AddressValueError(msg) @@ -1595,17 +1689,17 @@ class _BaseV6: if parts_lo: msg = "Trailing ':' only permitted as part of '::' in %r" raise AddressValueError(msg % ip_str) # :$ requires ::$ - parts_skipped = self._HEXTET_COUNT - (parts_hi + parts_lo) + parts_skipped = cls._HEXTET_COUNT - (parts_hi + parts_lo) if parts_skipped < 1: msg = "Expected at most %d other parts with '::' in %r" - raise AddressValueError(msg % (self._HEXTET_COUNT-1, ip_str)) + raise AddressValueError(msg % (cls._HEXTET_COUNT-1, ip_str)) else: # Otherwise, allocate the entire address to parts_hi. The # endpoints could still be empty, but _parse_hextet() will check # for that. - if len(parts) != self._HEXTET_COUNT: + if len(parts) != cls._HEXTET_COUNT: msg = "Exactly %d parts expected without '::' in %r" - raise AddressValueError(msg % (self._HEXTET_COUNT, ip_str)) + raise AddressValueError(msg % (cls._HEXTET_COUNT, ip_str)) if not parts[0]: msg = "Leading ':' only permitted as part of '::' in %r" raise AddressValueError(msg % ip_str) # ^: requires ^:: @@ -1621,16 +1715,17 @@ class _BaseV6: ip_int = 0 for i in range(parts_hi): ip_int <<= 16 - ip_int |= self._parse_hextet(parts[i]) + ip_int |= cls._parse_hextet(parts[i]) ip_int <<= 16 * parts_skipped for i in range(-parts_lo, 0): ip_int <<= 16 - ip_int |= self._parse_hextet(parts[i]) + ip_int |= cls._parse_hextet(parts[i]) return ip_int except ValueError as exc: raise AddressValueError("%s in %r" % (exc, ip_str)) from None - def _parse_hextet(self, hextet_str): + @classmethod + def _parse_hextet(cls, hextet_str): """Convert an IPv6 hextet string into an integer. Args: @@ -1645,7 +1740,7 @@ class _BaseV6: """ # Whitelist the characters, since int() allows a lot of bizarre stuff. - if not self._HEX_DIGITS.issuperset(hextet_str): + if not cls._HEX_DIGITS.issuperset(hextet_str): raise ValueError("Only hex digits permitted in %r" % hextet_str) # We do the length check second, since the invalid character error # is likely to be more informative for the user @@ -1655,7 +1750,8 @@ class _BaseV6: # Length check means we can skip checking the integer value return int(hextet_str, 16) - def _compress_hextets(self, hextets): + @classmethod + def _compress_hextets(cls, hextets): """Compresses a list of hextets. Compresses a list of strings, replacing the longest continuous @@ -1702,7 +1798,8 @@ class _BaseV6: return hextets - def _string_from_ip_int(self, ip_int=None): + @classmethod + def _string_from_ip_int(cls, ip_int=None): """Turns a 128-bit integer into hexadecimal notation. Args: @@ -1716,15 +1813,15 @@ class _BaseV6: """ if ip_int is None: - ip_int = int(self._ip) + ip_int = int(cls._ip) - if ip_int > self._ALL_ONES: + if ip_int > cls._ALL_ONES: raise ValueError('IPv6 address is too large') hex_str = '%032x' % ip_int hextets = ['%x' % int(hex_str[x:x+4], 16) for x in range(0, 32, 4)] - hextets = self._compress_hextets(hextets) + hextets = cls._compress_hextets(hextets) return ':'.join(hextets) def _explode_shorthand_ip_string(self): @@ -1751,6 +1848,15 @@ class _BaseV6: return '%s/%d' % (':'.join(parts), self._prefixlen) return ':'.join(parts) + def _reverse_pointer(self): + """Return the reverse DNS pointer name for the IPv6 address. + + This implements the method described in RFC3596 2.5. + + """ + reverse_chars = self.exploded[::-1].replace(':', '') + return '.'.join(reverse_chars) + '.ip6.arpa' + @property def max_prefixlen(self): return self._max_prefixlen @@ -1781,7 +1887,6 @@ class IPv6Address(_BaseV6, _BaseAddress): AddressValueError: If address isn't a valid IPv6 address. """ - _BaseAddress.__init__(self, address) _BaseV6.__init__(self, address) # Efficient constructor from integer. @@ -1799,6 +1904,8 @@ class IPv6Address(_BaseV6, _BaseAddress): # Assume input argument to be string or any object representation # which converts into a formatted IP string. addr_str = str(address) + if '/' in addr_str: + raise AddressValueError("Unexpected '/' in %r" % address) self._ip = self._ip_int_from_string(addr_str) @property @@ -1815,8 +1922,7 @@ class IPv6Address(_BaseV6, _BaseAddress): See RFC 2373 2.7 for details. """ - multicast_network = IPv6Network('ff00::/8') - return self in multicast_network + return self in self._constants._multicast_network @property def is_reserved(self): @@ -1827,16 +1933,7 @@ class IPv6Address(_BaseV6, _BaseAddress): reserved IPv6 Network ranges. """ - reserved_networks = [IPv6Network('::/8'), IPv6Network('100::/8'), - IPv6Network('200::/7'), IPv6Network('400::/6'), - IPv6Network('800::/5'), IPv6Network('1000::/4'), - IPv6Network('4000::/3'), IPv6Network('6000::/3'), - IPv6Network('8000::/3'), IPv6Network('A000::/3'), - IPv6Network('C000::/3'), IPv6Network('E000::/4'), - IPv6Network('F000::/5'), IPv6Network('F800::/6'), - IPv6Network('FE00::/9')] - - return any(self in x for x in reserved_networks) + return any(self in x for x in self._constants._reserved_networks) @property def is_link_local(self): @@ -1846,8 +1943,7 @@ class IPv6Address(_BaseV6, _BaseAddress): A boolean, True if the address is reserved per RFC 4291. """ - linklocal_network = IPv6Network('fe80::/10') - return self in linklocal_network + return self in self._constants._linklocal_network @property def is_site_local(self): @@ -1861,8 +1957,7 @@ class IPv6Address(_BaseV6, _BaseAddress): A boolean, True if the address is reserved per RFC 3513 2.5.6. """ - sitelocal_network = IPv6Network('fec0::/10') - return self in sitelocal_network + return self in self._constants._sitelocal_network @property @functools.lru_cache() @@ -1874,16 +1969,7 @@ class IPv6Address(_BaseV6, _BaseAddress): iana-ipv6-special-registry. """ - return (self in IPv6Network('::1/128') or - self in IPv6Network('::/128') or - self in IPv6Network('::ffff:0:0/96') or - self in IPv6Network('100::/64') or - self in IPv6Network('2001::/23') or - self in IPv6Network('2001:2::/48') or - self in IPv6Network('2001:db8::/32') or - self in IPv6Network('2001:10::/28') or - self in IPv6Network('fc00::/7') or - self in IPv6Network('fe80::/10')) + return any(self in net for net in self._constants._private_networks) @property def is_global(self): @@ -1968,6 +2054,16 @@ class IPv6Interface(IPv6Address): self.network = IPv6Network(self._ip) self._prefixlen = self._max_prefixlen return + if isinstance(address, tuple): + IPv6Address.__init__(self, address[0]) + if len(address) > 1: + self._prefixlen = int(address[1]) + else: + self._prefixlen = self._max_prefixlen + self.network = IPv6Network(address, strict=False) + self.netmask = self.network.netmask + self.hostmask = self.network.hostmask + return addr = _split_optional_netmask(address) IPv6Address.__init__(self, addr[0]) @@ -2006,6 +2102,8 @@ class IPv6Interface(IPv6Address): def __hash__(self): return self._ip ^ self._prefixlen ^ int(self.network.network_address) + __reduce__ = _IPAddressBase.__reduce__ + @property def ip(self): return IPv6Address(self._ip) @@ -2085,18 +2183,26 @@ class IPv6Network(_BaseV6, _BaseNetwork): _BaseV6.__init__(self, address) _BaseNetwork.__init__(self, address) - # Efficient constructor from integer. - if isinstance(address, int): + # Efficient constructor from integer or packed address + if isinstance(address, (bytes, int)): self.network_address = IPv6Address(address) - self._prefixlen = self._max_prefixlen - self.netmask = IPv6Address(self._ALL_ONES) + self.netmask, self._prefixlen = self._make_netmask(self._max_prefixlen) return - # Constructing from a packed address - if isinstance(address, bytes): - self.network_address = IPv6Address(address) - self._prefixlen = self._max_prefixlen - self.netmask = IPv6Address(self._ALL_ONES) + if isinstance(address, tuple): + if len(address) > 1: + arg = address[1] + else: + arg = self._max_prefixlen + self.netmask, self._prefixlen = self._make_netmask(arg) + self.network_address = IPv6Address(address[0]) + packed = int(self.network_address) + if packed & int(self.netmask) != packed: + if strict: + raise ValueError('%s has host bits set' % self) + else: + self.network_address = IPv6Address(packed & + int(self.netmask)) return # Assume input argument to be string or any object representation @@ -2106,12 +2212,11 @@ class IPv6Network(_BaseV6, _BaseNetwork): self.network_address = IPv6Address(self._ip_int_from_string(addr[0])) if len(addr) == 2: - # This may raise NetmaskValueError - self._prefixlen = self._prefix_from_prefix_string(addr[1]) + arg = addr[1] else: - self._prefixlen = self._max_prefixlen + arg = self._max_prefixlen + self.netmask, self._prefixlen = self._make_netmask(arg) - self.netmask = IPv6Address(self._ip_int_from_prefix(self._prefixlen)) if strict: if (IPv6Address(int(self.network_address) & int(self.netmask)) != self.network_address): @@ -2148,3 +2253,39 @@ class IPv6Network(_BaseV6, _BaseNetwork): """ return (self.network_address.is_site_local and self.broadcast_address.is_site_local) + + +class _IPv6Constants: + + _linklocal_network = IPv6Network('fe80::/10') + + _multicast_network = IPv6Network('ff00::/8') + + _private_networks = [ + IPv6Network('::1/128'), + IPv6Network('::/128'), + IPv6Network('::ffff:0:0/96'), + IPv6Network('100::/64'), + IPv6Network('2001::/23'), + IPv6Network('2001:2::/48'), + IPv6Network('2001:db8::/32'), + IPv6Network('2001:10::/28'), + IPv6Network('fc00::/7'), + IPv6Network('fe80::/10'), + ] + + _reserved_networks = [ + IPv6Network('::/8'), IPv6Network('100::/8'), + IPv6Network('200::/7'), IPv6Network('400::/6'), + IPv6Network('800::/5'), IPv6Network('1000::/4'), + IPv6Network('4000::/3'), IPv6Network('6000::/3'), + IPv6Network('8000::/3'), IPv6Network('A000::/3'), + IPv6Network('C000::/3'), IPv6Network('E000::/4'), + IPv6Network('F000::/5'), IPv6Network('F800::/6'), + IPv6Network('FE00::/9'), + ] + + _sitelocal_network = IPv6Network('fec0::/10') + + +IPv6Address._constants = _IPv6Constants diff --git a/Lib/json/__init__.py b/Lib/json/__init__.py index 94f7d8c..6ce9880 100644 --- a/Lib/json/__init__.py +++ b/Lib/json/__init__.py @@ -98,12 +98,12 @@ Using json.tool from the shell to validate and pretty-print:: __version__ = '2.0.9' __all__ = [ 'dump', 'dumps', 'load', 'loads', - 'JSONDecoder', 'JSONEncoder', + 'JSONDecoder', 'JSONDecodeError', 'JSONEncoder', ] __author__ = 'Bob Ippolito <bob@redivi.com>' -from .decoder import JSONDecoder +from .decoder import JSONDecoder, JSONDecodeError from .encoder import JSONEncoder _default_encoder = JSONEncoder( @@ -311,7 +311,8 @@ def loads(s, encoding=None, cls=None, object_hook=None, parse_float=None, raise TypeError('the JSON object must be str, not {!r}'.format( s.__class__.__name__)) if s.startswith(u'\ufeff'): - raise ValueError("Unexpected UTF-8 BOM (decode using utf-8-sig)") + raise JSONDecodeError("Unexpected UTF-8 BOM (decode using utf-8-sig)", + s, 0) if (cls is None and object_hook is None and parse_int is None and parse_float is None and parse_constant is None and object_pairs_hook is None and not kw): diff --git a/Lib/json/decoder.py b/Lib/json/decoder.py index 59e5f41..0f03f20 100644 --- a/Lib/json/decoder.py +++ b/Lib/json/decoder.py @@ -8,7 +8,7 @@ try: except ImportError: c_scanstring = None -__all__ = ['JSONDecoder'] +__all__ = ['JSONDecoder', 'JSONDecodeError'] FLAGS = re.VERBOSE | re.MULTILINE | re.DOTALL @@ -17,32 +17,30 @@ PosInf = float('inf') NegInf = float('-inf') -def linecol(doc, pos): - if isinstance(doc, bytes): - newline = b'\n' - else: - newline = '\n' - lineno = doc.count(newline, 0, pos) + 1 - if lineno == 1: - colno = pos + 1 - else: - colno = pos - doc.rindex(newline, 0, pos) - return lineno, colno - - -def errmsg(msg, doc, pos, end=None): - # Note that this function is called from _json - lineno, colno = linecol(doc, pos) - if end is None: - fmt = '{0}: line {1} column {2} (char {3})' - return fmt.format(msg, lineno, colno, pos) - #fmt = '%s: line %d column %d (char %d)' - #return fmt % (msg, lineno, colno, pos) - endlineno, endcolno = linecol(doc, end) - fmt = '{0}: line {1} column {2} - line {3} column {4} (char {5} - {6})' - return fmt.format(msg, lineno, colno, endlineno, endcolno, pos, end) - #fmt = '%s: line %d column %d - line %d column %d (char %d - %d)' - #return fmt % (msg, lineno, colno, endlineno, endcolno, pos, end) +class JSONDecodeError(ValueError): + """Subclass of ValueError with the following additional properties: + + msg: The unformatted error message + doc: The JSON document being parsed + pos: The start index of doc where parsing failed + lineno: The line corresponding to pos + colno: The column corresponding to pos + + """ + # Note that this exception is used from _json + def __init__(self, msg, doc, pos): + lineno = doc.count('\n', 0, pos) + 1 + colno = pos - doc.rfind('\n', 0, pos) + errmsg = '%s: line %d column %d (char %d)' % (msg, lineno, colno, pos) + ValueError.__init__(self, errmsg) + self.msg = msg + self.doc = doc + self.pos = pos + self.lineno = lineno + self.colno = colno + + def __reduce__(self): + return self.__class__, (self.msg, self.doc, self.pos) _CONSTANTS = { @@ -66,7 +64,7 @@ def _decode_uXXXX(s, pos): except ValueError: pass msg = "Invalid \\uXXXX escape" - raise ValueError(errmsg(msg, s, pos)) + raise JSONDecodeError(msg, s, pos) def py_scanstring(s, end, strict=True, _b=BACKSLASH, _m=STRINGCHUNK.match): @@ -84,8 +82,7 @@ def py_scanstring(s, end, strict=True, while 1: chunk = _m(s, end) if chunk is None: - raise ValueError( - errmsg("Unterminated string starting at", s, begin)) + raise JSONDecodeError("Unterminated string starting at", s, begin) end = chunk.end() content, terminator = chunk.groups() # Content is contains zero or more unescaped string characters @@ -99,22 +96,21 @@ def py_scanstring(s, end, strict=True, if strict: #msg = "Invalid control character %r at" % (terminator,) msg = "Invalid control character {0!r} at".format(terminator) - raise ValueError(errmsg(msg, s, end)) + raise JSONDecodeError(msg, s, end) else: _append(terminator) continue try: esc = s[end] except IndexError: - raise ValueError( - errmsg("Unterminated string starting at", s, begin)) + raise JSONDecodeError("Unterminated string starting at", s, begin) # If not a unicode escape sequence, must be in the lookup table if esc != 'u': try: char = _b[esc] except KeyError: msg = "Invalid \\escape: {0!r}".format(esc) - raise ValueError(errmsg(msg, s, end)) + raise JSONDecodeError(msg, s, end) end += 1 else: uni = _decode_uXXXX(s, end) @@ -163,8 +159,8 @@ def JSONObject(s_and_end, strict, scan_once, object_hook, object_pairs_hook, pairs = object_hook(pairs) return pairs, end + 1 elif nextchar != '"': - raise ValueError(errmsg( - "Expecting property name enclosed in double quotes", s, end)) + raise JSONDecodeError( + "Expecting property name enclosed in double quotes", s, end) end += 1 while True: key, end = scanstring(s, end, strict) @@ -174,7 +170,7 @@ def JSONObject(s_and_end, strict, scan_once, object_hook, object_pairs_hook, if s[end:end + 1] != ':': end = _w(s, end).end() if s[end:end + 1] != ':': - raise ValueError(errmsg("Expecting ':' delimiter", s, end)) + raise JSONDecodeError("Expecting ':' delimiter", s, end) end += 1 try: @@ -188,7 +184,7 @@ def JSONObject(s_and_end, strict, scan_once, object_hook, object_pairs_hook, try: value, end = scan_once(s, end) except StopIteration as err: - raise ValueError(errmsg("Expecting value", s, err.value)) from None + raise JSONDecodeError("Expecting value", s, err.value) from None pairs_append((key, value)) try: nextchar = s[end] @@ -202,13 +198,13 @@ def JSONObject(s_and_end, strict, scan_once, object_hook, object_pairs_hook, if nextchar == '}': break elif nextchar != ',': - raise ValueError(errmsg("Expecting ',' delimiter", s, end - 1)) + raise JSONDecodeError("Expecting ',' delimiter", s, end - 1) end = _w(s, end).end() nextchar = s[end:end + 1] end += 1 if nextchar != '"': - raise ValueError(errmsg( - "Expecting property name enclosed in double quotes", s, end - 1)) + raise JSONDecodeError( + "Expecting property name enclosed in double quotes", s, end - 1) if object_pairs_hook is not None: result = object_pairs_hook(pairs) return result, end @@ -232,7 +228,7 @@ def JSONArray(s_and_end, scan_once, _w=WHITESPACE.match, _ws=WHITESPACE_STR): try: value, end = scan_once(s, end) except StopIteration as err: - raise ValueError(errmsg("Expecting value", s, err.value)) from None + raise JSONDecodeError("Expecting value", s, err.value) from None _append(value) nextchar = s[end:end + 1] if nextchar in _ws: @@ -242,7 +238,7 @@ def JSONArray(s_and_end, scan_once, _w=WHITESPACE.match, _ws=WHITESPACE_STR): if nextchar == ']': break elif nextchar != ',': - raise ValueError(errmsg("Expecting ',' delimiter", s, end - 1)) + raise JSONDecodeError("Expecting ',' delimiter", s, end - 1) try: if s[end] in _ws: end += 1 @@ -343,7 +339,7 @@ class JSONDecoder(object): obj, end = self.raw_decode(s, idx=_w(s, 0).end()) end = _w(s, end).end() if end != len(s): - raise ValueError(errmsg("Extra data", s, end, len(s))) + raise JSONDecodeError("Extra data", s, end) return obj def raw_decode(self, s, idx=0): @@ -358,5 +354,5 @@ class JSONDecoder(object): try: obj, end = self.scan_once(s, idx) except StopIteration as err: - raise ValueError(errmsg("Expecting value", s, err.value)) from None + raise JSONDecodeError("Expecting value", s, err.value) from None return obj, end diff --git a/Lib/json/encoder.py b/Lib/json/encoder.py index 0513838..26e9eb2 100644 --- a/Lib/json/encoder.py +++ b/Lib/json/encoder.py @@ -7,6 +7,10 @@ try: except ImportError: c_encode_basestring_ascii = None try: + from _json import encode_basestring as c_encode_basestring +except ImportError: + c_encode_basestring = None +try: from _json import make_encoder as c_make_encoder except ImportError: c_make_encoder = None @@ -30,7 +34,7 @@ for i in range(0x20): INFINITY = float('inf') FLOAT_REPR = repr -def encode_basestring(s): +def py_encode_basestring(s): """Return a JSON representation of a Python string """ @@ -39,6 +43,9 @@ def encode_basestring(s): return '"' + ESCAPE.sub(replace, s) + '"' +encode_basestring = (c_encode_basestring or py_encode_basestring) + + def py_encode_basestring_ascii(s): """Return an ASCII-only JSON representation of a Python string diff --git a/Lib/json/tool.py b/Lib/json/tool.py index 7db4528..4f3182c 100644 --- a/Lib/json/tool.py +++ b/Lib/json/tool.py @@ -10,28 +10,39 @@ Usage:: Expecting property name enclosed in double quotes: line 1 column 3 (char 2) """ -import sys +import argparse +import collections import json +import sys + def main(): - if len(sys.argv) == 1: - infile = sys.stdin - outfile = sys.stdout - elif len(sys.argv) == 2: - infile = open(sys.argv[1], 'r') - outfile = sys.stdout - elif len(sys.argv) == 3: - infile = open(sys.argv[1], 'r') - outfile = open(sys.argv[2], 'w') - else: - raise SystemExit(sys.argv[0] + " [infile [outfile]]") + prog = 'python -m json.tool' + description = ('A simple command line interface for json module ' + 'to validate and pretty-print JSON objects.') + parser = argparse.ArgumentParser(prog=prog, description=description) + parser.add_argument('infile', nargs='?', type=argparse.FileType(), + help='a JSON file to be validated or pretty-printed') + parser.add_argument('outfile', nargs='?', type=argparse.FileType('w'), + help='write the output of infile to outfile') + parser.add_argument('--sort-keys', action='store_true', default=False, + help='sort the output of dictionaries alphabetically by key') + options = parser.parse_args() + + infile = options.infile or sys.stdin + outfile = options.outfile or sys.stdout + sort_keys = options.sort_keys with infile: try: - obj = json.load(infile) + if sort_keys: + obj = json.load(infile) + else: + obj = json.load(infile, + object_pairs_hook=collections.OrderedDict) except ValueError as e: raise SystemExit(e) with outfile: - json.dump(obj, outfile, sort_keys=True, indent=4) + json.dump(obj, outfile, sort_keys=sort_keys, indent=4) outfile.write('\n') diff --git a/Lib/linecache.py b/Lib/linecache.py index 02a9eb5..33b0af7 100644 --- a/Lib/linecache.py +++ b/Lib/linecache.py @@ -5,6 +5,7 @@ is not found, it will look down the module search path for a file by that name. """ +import functools import sys import os import tokenize @@ -21,7 +22,9 @@ def getline(filename, lineno, module_globals=None): # The cache -cache = {} # The cache +# The cache. Maps filenames to either a thunk which will provide source code, +# or a tuple (size, mtime, lines, fullname) once loaded. +cache = {} def clearcache(): @@ -36,6 +39,9 @@ def getlines(filename, module_globals=None): Update the cache if it doesn't contain an entry for this file already.""" if filename in cache: + entry = cache[filename] + if len(entry) == 1: + return updatecache(filename, module_globals) return cache[filename][2] else: return updatecache(filename, module_globals) @@ -54,7 +60,11 @@ def checkcache(filename=None): return for filename in filenames: - size, mtime, lines, fullname = cache[filename] + entry = cache[filename] + if len(entry) == 1: + # lazy cache entry, leave it lazy. + continue + size, mtime, lines, fullname = entry if mtime is None: continue # no-op for files loaded via a __loader__ try: @@ -72,7 +82,8 @@ def updatecache(filename, module_globals=None): and return an empty list.""" if filename in cache: - del cache[filename] + if len(cache[filename]) != 1: + del cache[filename] if not filename or (filename.startswith('<') and filename.endswith('>')): return [] @@ -82,27 +93,23 @@ def updatecache(filename, module_globals=None): except OSError: basename = filename - # Try for a __loader__, if available - if module_globals and '__loader__' in module_globals: - name = module_globals.get('__name__') - loader = module_globals['__loader__'] - get_source = getattr(loader, 'get_source', None) - - if name and get_source: - try: - data = get_source(name) - except (ImportError, OSError): - pass - else: - if data is None: - # No luck, the PEP302 loader cannot find the source - # for this module. - return [] - cache[filename] = ( - len(data), None, - [line+'\n' for line in data.splitlines()], fullname - ) - return cache[filename][2] + # Realise a lazy loader based lookup if there is one + # otherwise try to lookup right now. + if lazycache(filename, module_globals): + try: + data = cache[filename][0]() + except (ImportError, OSError): + pass + else: + if data is None: + # No luck, the PEP302 loader cannot find the source + # for this module. + return [] + cache[filename] = ( + len(data), None, + [line+'\n' for line in data.splitlines()], fullname + ) + return cache[filename][2] # Try looking through the module search path, which is only useful # when handling a relative filename. @@ -132,3 +139,36 @@ def updatecache(filename, module_globals=None): size, mtime = stat.st_size, stat.st_mtime cache[filename] = size, mtime, lines, fullname return lines + + +def lazycache(filename, module_globals): + """Seed the cache for filename with module_globals. + + The module loader will be asked for the source only when getlines is + called, not immediately. + + If there is an entry in the cache already, it is not altered. + + :return: True if a lazy load is registered in the cache, + otherwise False. To register such a load a module loader with a + get_source method must be found, the filename must be a cachable + filename, and the filename must not be already cached. + """ + if filename in cache: + if len(cache[filename]) == 1: + return True + else: + return False + if not filename or (filename.startswith('<') and filename.endswith('>')): + return False + # Try for a __loader__, if available + if module_globals and '__loader__' in module_globals: + name = module_globals.get('__name__') + loader = module_globals['__loader__'] + get_source = getattr(loader, 'get_source', None) + + if name and get_source: + get_lines = functools.partial(get_source, name) + cache[filename] = (get_lines,) + return True + return False diff --git a/Lib/locale.py b/Lib/locale.py index 7ff4356..6b9eb3a 100644 --- a/Lib/locale.py +++ b/Lib/locale.py @@ -301,8 +301,8 @@ def str(val): """Convert float to integer, taking the locale into account.""" return format("%.12g", val) -def atof(string, func=float): - "Parses a string as a float according to the locale settings." +def delocalize(string): + "Parses a string as a normalized number according to the locale settings." #First, get rid of the grouping ts = localeconv()['thousands_sep'] if ts: @@ -311,12 +311,15 @@ def atof(string, func=float): dd = localeconv()['decimal_point'] if dd: string = string.replace(dd, '.') - #finally, parse the string - return func(string) + return string + +def atof(string, func=float): + "Parses a string as a float according to the locale settings." + return func(delocalize(string)) -def atoi(str): +def atoi(string): "Converts a string to an integer according to the locale settings." - return atof(str, int) + return int(delocalize(string)) def _test(): setlocale(LC_ALL, "") diff --git a/Lib/logging/__init__.py b/Lib/logging/__init__.py index 9a8685b..b1dc319 100644 --- a/Lib/logging/__init__.py +++ b/Lib/logging/__init__.py @@ -1,4 +1,4 @@ -# Copyright 2001-2014 by Vinay Sajip. All Rights Reserved. +# Copyright 2001-2015 by Vinay Sajip. All Rights Reserved. # # Permission to use, copy, modify, and distribute this software and its # documentation for any purpose and without fee is hereby granted, @@ -18,7 +18,7 @@ Logging package for Python. Based on PEP 282 and comments thereto in comp.lang.python. -Copyright (C) 2001-2014 Vinay Sajip. All Rights Reserved. +Copyright (C) 2001-2015 Vinay Sajip. All Rights Reserved. To use, simply 'import logging' and log away! """ @@ -316,6 +316,8 @@ class LogRecord(object): return '<LogRecord: %s, %s, %s, %s, "%s">'%(self.name, self.levelno, self.pathname, self.lineno, self.msg) + __repr__ = __str__ + def getMessage(self): """ Return the message for this LogRecord. @@ -1086,7 +1088,6 @@ class PlaceHolder(object): # # Determine which class to use when instantiating loggers. # -_loggerClass = None def setLoggerClass(klass): """ @@ -1105,7 +1106,6 @@ def getLoggerClass(): """ Return the class to be used when instantiating a logger. """ - return _loggerClass class Manager(object): @@ -1302,12 +1302,11 @@ class Logger(Filterer): if self.isEnabledFor(ERROR): self._log(ERROR, msg, args, **kwargs) - def exception(self, msg, *args, **kwargs): + def exception(self, msg, *args, exc_info=True, **kwargs): """ Convenience method for logging an ERROR with exception information. """ - kwargs['exc_info'] = True - self.error(msg, *args, **kwargs) + self.error(msg, *args, exc_info=exc_info, **kwargs) def critical(self, msg, *args, **kwargs): """ @@ -1402,7 +1401,9 @@ class Logger(Filterer): else: # pragma: no cover fn, lno, func = "(unknown file)", 0, "(unknown function)" if exc_info: - if not isinstance(exc_info, tuple): + if isinstance(exc_info, BaseException): + exc_info = (type(exc_info), exc_info, exc_info.__traceback__) + elif not isinstance(exc_info, tuple): exc_info = sys.exc_info() record = self.makeRecord(self.name, level, fn, lno, msg, args, exc_info, func, extra, sinfo) @@ -1612,12 +1613,11 @@ class LoggerAdapter(object): """ self.log(ERROR, msg, *args, **kwargs) - def exception(self, msg, *args, **kwargs): + def exception(self, msg, *args, exc_info=True, **kwargs): """ Delegate an exception call to the underlying logger. """ - kwargs["exc_info"] = True - self.log(ERROR, msg, *args, **kwargs) + self.log(ERROR, msg, *args, exc_info=exc_info, **kwargs) def critical(self, msg, *args, **kwargs): """ @@ -1799,14 +1799,13 @@ def error(msg, *args, **kwargs): basicConfig() root.error(msg, *args, **kwargs) -def exception(msg, *args, **kwargs): +def exception(msg, *args, exc_info=True, **kwargs): """ Log a message with severity 'ERROR' on the root logger, with exception information. If the logger has no handlers, basicConfig() is called to add a console handler with a pre-defined format. """ - kwargs['exc_info'] = True - error(msg, *args, **kwargs) + error(msg, *args, exc_info=exc_info, **kwargs) def warning(msg, *args, **kwargs): """ diff --git a/Lib/logging/config.py b/Lib/logging/config.py index 895fb26..8a99923 100644 --- a/Lib/logging/config.py +++ b/Lib/logging/config.py @@ -116,11 +116,12 @@ def _create_formatters(cp): sectname = "formatter_%s" % form fs = cp.get(sectname, "format", raw=True, fallback=None) dfs = cp.get(sectname, "datefmt", raw=True, fallback=None) + stl = cp.get(sectname, "style", raw=True, fallback='%') c = logging.Formatter class_name = cp[sectname].get("class") if class_name: c = _resolve(class_name) - f = c(fs, dfs) + f = c(fs, dfs, stl) formatters[form] = f return formatters @@ -660,7 +661,12 @@ class DictConfigurator(BaseConfigurator): fmt = config.get('format', None) dfmt = config.get('datefmt', None) style = config.get('style', '%') - result = logging.Formatter(fmt, dfmt, style) + cname = config.get('class', None) + if not cname: + c = logging.Formatter + else: + c = _resolve(cname) + result = c(fmt, dfmt, style) return result def configure_filter(self, config): diff --git a/Lib/logging/handlers.py b/Lib/logging/handlers.py index c67ac99..d4f8aef 100644 --- a/Lib/logging/handlers.py +++ b/Lib/logging/handlers.py @@ -1,4 +1,4 @@ -# Copyright 2001-2013 by Vinay Sajip. All Rights Reserved. +# Copyright 2001-2015 by Vinay Sajip. All Rights Reserved. # # Permission to use, copy, modify, and distribute this software and its # documentation for any purpose and without fee is hereby granted, @@ -18,7 +18,7 @@ Additional handlers for the logging package for Python. The core package is based on PEP 282 and comments thereto in comp.lang.python. -Copyright (C) 2001-2013 Vinay Sajip. All Rights Reserved. +Copyright (C) 2001-2015 Vinay Sajip. All Rights Reserved. To use, simply 'import logging.handlers' and log away! """ @@ -1350,7 +1350,7 @@ if threading: """ _sentinel = None - def __init__(self, queue, *handlers): + def __init__(self, queue, *handlers, respect_handler_level=False): """ Initialise an instance with the specified queue and handlers. @@ -1359,6 +1359,7 @@ if threading: self.handlers = handlers self._stop = threading.Event() self._thread = None + self.respect_handler_level = respect_handler_level def dequeue(self, block): """ @@ -1399,7 +1400,12 @@ if threading: """ record = self.prepare(record) for handler in self.handlers: - handler.handle(record) + if not self.respect_handler_level: + process = True + else: + process = record.levelno >= handler.level + if process: + handler.handle(record) def _monitor(self): """ diff --git a/Lib/macpath.py b/Lib/macpath.py index 5ca0097..dbcf368 100644 --- a/Lib/macpath.py +++ b/Lib/macpath.py @@ -50,20 +50,24 @@ def isabs(s): def join(s, *p): - colon = _get_colon(s) - path = s - for t in p: - if (not path) or isabs(t): - path = t - continue - if t[:1] == colon: - t = t[1:] - if colon not in path: - path = colon + path - if path[-1:] != colon: - path = path + colon - path = path + t - return path + try: + colon = _get_colon(s) + path = s + for t in p: + if (not path) or isabs(t): + path = t + continue + if t[:1] == colon: + t = t[1:] + if colon not in path: + path = colon + path + if path[-1:] != colon: + path = path + colon + path = path + t + return path + except (TypeError, AttributeError, BytesWarning): + genericpath._check_arg_types('join', s, *p) + raise def split(s): diff --git a/Lib/mailbox.py b/Lib/mailbox.py index 2eee76c..e7f31df 100644 --- a/Lib/mailbox.py +++ b/Lib/mailbox.py @@ -1230,8 +1230,8 @@ class MH(Mailbox): class Babyl(_singlefileMailbox): """An Rmail-style Babyl mailbox.""" - _special_labels = frozenset(('unseen', 'deleted', 'filed', 'answered', - 'forwarded', 'edited', 'resent')) + _special_labels = frozenset({'unseen', 'deleted', 'filed', 'answered', + 'forwarded', 'edited', 'resent'}) def __init__(self, path, factory=None, create=True): """Initialize a Babyl mailbox.""" @@ -1949,7 +1949,7 @@ class _ProxyFile: while True: line = self.readline() if not line: - raise StopIteration + return yield line def tell(self): diff --git a/Lib/multiprocessing/connection.py b/Lib/multiprocessing/connection.py index d2715c2..07d19de 100644 --- a/Lib/multiprocessing/connection.py +++ b/Lib/multiprocessing/connection.py @@ -365,10 +365,7 @@ class Connection(_ConnectionBase): def _send(self, buf, write=_write): remaining = len(buf) while True: - try: - n = write(self._handle, buf) - except InterruptedError: - continue + n = write(self._handle, buf) remaining -= n if remaining == 0: break @@ -379,10 +376,7 @@ class Connection(_ConnectionBase): handle = self._handle remaining = size while remaining > 0: - try: - chunk = read(handle, remaining) - except InterruptedError: - continue + chunk = read(handle, remaining) n = len(chunk) if n == 0: if remaining == size: @@ -400,17 +394,14 @@ class Connection(_ConnectionBase): if n > 16384: # The payload is large so Nagle's algorithm won't be triggered # and we'd better avoid the cost of concatenation. - chunks = [header, buf] - elif n > 0: + self._send(header) + self._send(buf) + else: # Issue # 20540: concatenate before sending, to avoid delays due # to Nagle's algorithm on a TCP socket. - chunks = [header + buf] - else: - # This code path is necessary to avoid "broken pipe" errors - # when sending a 0-length buffer if the other end closed the pipe. - chunks = [header] - for chunk in chunks: - self._send(chunk) + # Also note we want to avoid sending a 0-length buffer separately, + # to avoid "broken pipe" errors if the other end closed the pipe. + self._send(header + buf) def _recv_bytes(self, maxsize=None): buf = self._recv(4) @@ -598,13 +589,7 @@ class SocketListener(object): self._unlink = None def accept(self): - while True: - try: - s, self._last_accepted = self._socket.accept() - except InterruptedError: - pass - else: - break + s, self._last_accepted = self._socket.accept() s.setblocking(True) return Connection(s.detach()) diff --git a/Lib/multiprocessing/dummy/__init__.py b/Lib/multiprocessing/dummy/__init__.py index 135db7f..1abea64 100644 --- a/Lib/multiprocessing/dummy/__init__.py +++ b/Lib/multiprocessing/dummy/__init__.py @@ -86,7 +86,7 @@ class Namespace(object): if not name.startswith('_'): temp.append('%s=%r' % (name, value)) temp.sort() - return 'Namespace(%s)' % str.join(', ', temp) + return '%s(%s)' % (self.__class__.__name__, ', '.join(temp)) dict = dict list = list diff --git a/Lib/multiprocessing/dummy/connection.py b/Lib/multiprocessing/dummy/connection.py index 694ef96..1984375 100644 --- a/Lib/multiprocessing/dummy/connection.py +++ b/Lib/multiprocessing/dummy/connection.py @@ -59,9 +59,8 @@ class Connection(object): return True if timeout <= 0.0: return False - self._in.not_empty.acquire() - self._in.not_empty.wait(timeout) - self._in.not_empty.release() + with self._in.not_empty: + self._in.not_empty.wait(timeout) return self._in.qsize() > 0 def close(self): diff --git a/Lib/multiprocessing/forkserver.py b/Lib/multiprocessing/forkserver.py index 387517e..b27cba5 100644 --- a/Lib/multiprocessing/forkserver.py +++ b/Lib/multiprocessing/forkserver.py @@ -107,7 +107,7 @@ class ForkServer(object): address = connection.arbitrary_address('AF_UNIX') listener.bind(address) os.chmod(address, 0o600) - listener.listen(100) + listener.listen() # all client processes own the write end of the "alive" pipe; # when they all terminate the read end becomes ready. @@ -188,8 +188,6 @@ def main(listener_fd, alive_r, preload, main_path=None, sys_path=None): finally: os._exit(code) - except InterruptedError: - pass except OSError as e: if e.errno != errno.ECONNABORTED: raise @@ -230,13 +228,7 @@ def read_unsigned(fd): data = b'' length = UNSIGNED_STRUCT.size while len(data) < length: - while True: - try: - s = os.read(fd, length - len(data)) - except InterruptedError: - pass - else: - break + s = os.read(fd, length - len(data)) if not s: raise EOFError('unexpected EOF') data += s @@ -245,13 +237,7 @@ def read_unsigned(fd): def write_unsigned(fd, n): msg = UNSIGNED_STRUCT.pack(n) while msg: - while True: - try: - nbytes = os.write(fd, msg) - except InterruptedError: - pass - else: - break + nbytes = os.write(fd, msg) if nbytes == 0: raise RuntimeError('should not get here') msg = msg[nbytes:] diff --git a/Lib/multiprocessing/heap.py b/Lib/multiprocessing/heap.py index 344a45f..333b3ba 100644 --- a/Lib/multiprocessing/heap.py +++ b/Lib/multiprocessing/heap.py @@ -54,7 +54,9 @@ if sys.platform == 'win32': def __setstate__(self, state): self.size, self.name = self._state = state self.buffer = mmap.mmap(-1, self.size, tagname=self.name) - assert _winapi.GetLastError() == _winapi.ERROR_ALREADY_EXISTS + # XXX Temporarily preventing buildbot failures while determining + # XXX the correct long-term fix. See issue 23060 + #assert _winapi.GetLastError() == _winapi.ERROR_ALREADY_EXISTS else: @@ -216,9 +218,8 @@ class Heap(object): assert 0 <= size < sys.maxsize if os.getpid() != self._lastpid: self.__init__() # reinitialize after fork - self._lock.acquire() - self._free_pending_blocks() - try: + with self._lock: + self._free_pending_blocks() size = self._roundup(max(size,1), self._alignment) (arena, start, stop) = self._malloc(size) new_stop = start + size @@ -227,8 +228,6 @@ class Heap(object): block = (arena, start, new_stop) self._allocated_blocks.add(block) return block - finally: - self._lock.release() # # Class representing a chunk of an mmap -- can be inherited by child process diff --git a/Lib/multiprocessing/managers.py b/Lib/multiprocessing/managers.py index 66d46fc..776656e 100644 --- a/Lib/multiprocessing/managers.py +++ b/Lib/multiprocessing/managers.py @@ -65,8 +65,8 @@ class Token(object): (self.typeid, self.address, self.id) = state def __repr__(self): - return 'Token(typeid=%r, address=%r, id=%r)' % \ - (self.typeid, self.address, self.id) + return '%s(typeid=%r, address=%r, id=%r)' % \ + (self.__class__.__name__, self.typeid, self.address, self.id) # # Function for communication with a manager's server process @@ -306,8 +306,7 @@ class Server(object): ''' Return some info --- useful to spot problems with refcounting ''' - self.mutex.acquire() - try: + with self.mutex: result = [] keys = list(self.id_to_obj.keys()) keys.sort() @@ -317,8 +316,6 @@ class Server(object): (ident, self.id_to_refcount[ident], str(self.id_to_obj[ident][0])[:75])) return '\n'.join(result) - finally: - self.mutex.release() def number_of_objects(self, c): ''' @@ -343,8 +340,7 @@ class Server(object): ''' Create a new shared object and return its id ''' - self.mutex.acquire() - try: + with self.mutex: callable, exposed, method_to_typeid, proxytype = \ self.registry[typeid] @@ -374,8 +370,6 @@ class Server(object): # has been created. self.incref(c, ident) return ident, tuple(exposed) - finally: - self.mutex.release() def get_methods(self, c, token): ''' @@ -392,22 +386,16 @@ class Server(object): self.serve_client(c) def incref(self, c, ident): - self.mutex.acquire() - try: + with self.mutex: self.id_to_refcount[ident] += 1 - finally: - self.mutex.release() def decref(self, c, ident): - self.mutex.acquire() - try: + with self.mutex: assert self.id_to_refcount[ident] >= 1 self.id_to_refcount[ident] -= 1 if self.id_to_refcount[ident] == 0: del self.id_to_obj[ident], self.id_to_refcount[ident] util.debug('disposing of obj with id %r', ident) - finally: - self.mutex.release() # # Class to represent state of a manager @@ -671,14 +659,11 @@ class BaseProxy(object): def __init__(self, token, serializer, manager=None, authkey=None, exposed=None, incref=True): - BaseProxy._mutex.acquire() - try: + with BaseProxy._mutex: tls_idset = BaseProxy._address_to_local.get(token.address, None) if tls_idset is None: tls_idset = util.ForkAwareLocal(), ProcessLocalSet() BaseProxy._address_to_local[token.address] = tls_idset - finally: - BaseProxy._mutex.release() # self._tls is used to record the connection used by this # thread to communicate with the manager at token.address @@ -818,8 +803,8 @@ class BaseProxy(object): return self._getvalue() def __repr__(self): - return '<%s object, typeid %r at %s>' % \ - (type(self).__name__, self._token.typeid, '0x%x' % id(self)) + return '<%s object, typeid %r at %#x>' % \ + (type(self).__name__, self._token.typeid, id(self)) def __str__(self): ''' @@ -916,7 +901,7 @@ class Namespace(object): if not name.startswith('_'): temp.append('%s=%r' % (name, value)) temp.sort() - return 'Namespace(%s)' % str.join(', ', temp) + return '%s(%s)' % (self.__class__.__name__, ', '.join(temp)) class Value(object): def __init__(self, typecode, value, lock=True): diff --git a/Lib/multiprocessing/pool.py b/Lib/multiprocessing/pool.py index 8832a5c..75a76a4 100644 --- a/Lib/multiprocessing/pool.py +++ b/Lib/multiprocessing/pool.py @@ -87,7 +87,7 @@ class MaybeEncodingError(Exception): self.exc) def __repr__(self): - return "<MaybeEncodingError: %s>" % str(self) + return "<%s: %s>" % (self.__class__.__name__, self) def worker(inqueue, outqueue, initializer=None, initargs=(), maxtasks=None, @@ -666,8 +666,7 @@ class IMapIterator(object): return self def next(self, timeout=None): - self._cond.acquire() - try: + with self._cond: try: item = self._items.popleft() except IndexError: @@ -680,8 +679,6 @@ class IMapIterator(object): if self._index == self._length: raise StopIteration raise TimeoutError - finally: - self._cond.release() success, value = item if success: @@ -691,8 +688,7 @@ class IMapIterator(object): __next__ = next # XXX def _set(self, i, obj): - self._cond.acquire() - try: + with self._cond: if self._index == i: self._items.append(obj) self._index += 1 @@ -706,18 +702,13 @@ class IMapIterator(object): if self._index == self._length: del self._cache[self._job] - finally: - self._cond.release() def _set_length(self, length): - self._cond.acquire() - try: + with self._cond: self._length = length if self._index == self._length: self._cond.notify() del self._cache[self._job] - finally: - self._cond.release() # # Class whose instances are returned by `Pool.imap_unordered()` @@ -726,15 +717,12 @@ class IMapIterator(object): class IMapUnorderedIterator(IMapIterator): def _set(self, i, obj): - self._cond.acquire() - try: + with self._cond: self._items.append(obj) self._index += 1 self._cond.notify() if self._index == self._length: del self._cache[self._job] - finally: - self._cond.release() # # @@ -760,10 +748,7 @@ class ThreadPool(Pool): @staticmethod def _help_stuff_finish(inqueue, task_handler, size): # put sentinels at head of inqueue to make workers finish - inqueue.not_empty.acquire() - try: + with inqueue.not_empty: inqueue.queue.clear() inqueue.queue.extend([None] * size) inqueue.not_empty.notify_all() - finally: - inqueue.not_empty.release() diff --git a/Lib/multiprocessing/popen_fork.py b/Lib/multiprocessing/popen_fork.py index 367e72e..d2ebd7c 100644 --- a/Lib/multiprocessing/popen_fork.py +++ b/Lib/multiprocessing/popen_fork.py @@ -1,7 +1,6 @@ import os import sys import signal -import errno from . import util @@ -29,8 +28,6 @@ class Popen(object): try: pid, sts = os.waitpid(self.pid, flag) except OSError as e: - if e.errno == errno.EINTR: - continue # Child process not yet created. See #1731717 # e.errno == errno.ECHILD == 10 return None diff --git a/Lib/multiprocessing/queues.py b/Lib/multiprocessing/queues.py index f650771..c07ad40 100644 --- a/Lib/multiprocessing/queues.py +++ b/Lib/multiprocessing/queues.py @@ -81,14 +81,11 @@ class Queue(object): if not self._sem.acquire(block, timeout): raise Full - self._notempty.acquire() - try: + with self._notempty: if self._thread is None: self._start_thread() self._buffer.append(obj) self._notempty.notify() - finally: - self._notempty.release() def get(self, block=True, timeout=None): if block and timeout is None: @@ -201,12 +198,9 @@ class Queue(object): @staticmethod def _finalize_close(buffer, notempty): debug('telling queue thread to quit') - notempty.acquire() - try: + with notempty: buffer.append(_sentinel) notempty.notify() - finally: - notempty.release() @staticmethod def _feed(buffer, notempty, send_bytes, writelock, close, ignore_epipe): @@ -295,35 +289,24 @@ class JoinableQueue(Queue): if not self._sem.acquire(block, timeout): raise Full - self._notempty.acquire() - self._cond.acquire() - try: + with self._notempty, self._cond: if self._thread is None: self._start_thread() self._buffer.append(obj) self._unfinished_tasks.release() self._notempty.notify() - finally: - self._cond.release() - self._notempty.release() def task_done(self): - self._cond.acquire() - try: + with self._cond: if not self._unfinished_tasks.acquire(False): raise ValueError('task_done() called too many times') if self._unfinished_tasks._semlock._is_zero(): self._cond.notify_all() - finally: - self._cond.release() def join(self): - self._cond.acquire() - try: + with self._cond: if not self._unfinished_tasks._semlock._is_zero(): self._cond.wait() - finally: - self._cond.release() # # Simplified Queue type -- really just a locked pipe diff --git a/Lib/multiprocessing/sharedctypes.py b/Lib/multiprocessing/sharedctypes.py index 0c17825..4258f59 100644 --- a/Lib/multiprocessing/sharedctypes.py +++ b/Lib/multiprocessing/sharedctypes.py @@ -188,6 +188,12 @@ class SynchronizedBase(object): self.acquire = self._lock.acquire self.release = self._lock.release + def __enter__(self): + return self._lock.__enter__() + + def __exit__(self, *args): + return self._lock.__exit__(*args) + def __reduce__(self): assert_spawning(self) return synchronized, (self._obj, self._lock) @@ -212,32 +218,20 @@ class SynchronizedArray(SynchronizedBase): return len(self._obj) def __getitem__(self, i): - self.acquire() - try: + with self: return self._obj[i] - finally: - self.release() def __setitem__(self, i, value): - self.acquire() - try: + with self: self._obj[i] = value - finally: - self.release() def __getslice__(self, start, stop): - self.acquire() - try: + with self: return self._obj[start:stop] - finally: - self.release() def __setslice__(self, start, stop, values): - self.acquire() - try: + with self: self._obj[start:stop] = values - finally: - self.release() class SynchronizedString(SynchronizedArray): diff --git a/Lib/multiprocessing/synchronize.py b/Lib/multiprocessing/synchronize.py index dea1cbd..d4bdf0e 100644 --- a/Lib/multiprocessing/synchronize.py +++ b/Lib/multiprocessing/synchronize.py @@ -134,7 +134,7 @@ class Semaphore(SemLock): value = self._semlock._get_value() except Exception: value = 'unknown' - return '<Semaphore(value=%s)>' % value + return '<%s(value=%s)>' % (self.__class__.__name__, value) # # Bounded semaphore @@ -150,8 +150,8 @@ class BoundedSemaphore(Semaphore): value = self._semlock._get_value() except Exception: value = 'unknown' - return '<BoundedSemaphore(value=%s, maxvalue=%s)>' % \ - (value, self._semlock.maxvalue) + return '<%s(value=%s, maxvalue=%s)>' % \ + (self.__class__.__name__, value, self._semlock.maxvalue) # # Non-recursive lock @@ -176,7 +176,7 @@ class Lock(SemLock): name = 'SomeOtherProcess' except Exception: name = 'unknown' - return '<Lock(owner=%s)>' % name + return '<%s(owner=%s)>' % (self.__class__.__name__, name) # # Recursive lock @@ -202,7 +202,7 @@ class RLock(SemLock): name, count = 'SomeOtherProcess', 'nonzero' except Exception: name, count = 'unknown', 'unknown' - return '<RLock(%s, %s)>' % (name, count) + return '<%s(%s, %s)>' % (self.__class__.__name__, name, count) # # Condition variable @@ -243,7 +243,7 @@ class Condition(object): self._woken_count._semlock._get_value()) except Exception: num_waiters = 'unknown' - return '<Condition(%s, %s)>' % (self._lock, num_waiters) + return '<%s(%s, %s)>' % (self.__class__.__name__, self._lock, num_waiters) def wait(self, timeout=None): assert self._lock._semlock._is_mine(), \ @@ -337,34 +337,24 @@ class Event(object): self._flag = ctx.Semaphore(0) def is_set(self): - self._cond.acquire() - try: + with self._cond: if self._flag.acquire(False): self._flag.release() return True return False - finally: - self._cond.release() def set(self): - self._cond.acquire() - try: + with self._cond: self._flag.acquire(False) self._flag.release() self._cond.notify_all() - finally: - self._cond.release() def clear(self): - self._cond.acquire() - try: + with self._cond: self._flag.acquire(False) - finally: - self._cond.release() def wait(self, timeout=None): - self._cond.acquire() - try: + with self._cond: if self._flag.acquire(False): self._flag.release() else: @@ -374,8 +364,6 @@ class Event(object): self._flag.release() return True return False - finally: - self._cond.release() # # Barrier diff --git a/Lib/multiprocessing/util.py b/Lib/multiprocessing/util.py index 0b695e4..ea5443d 100644 --- a/Lib/multiprocessing/util.py +++ b/Lib/multiprocessing/util.py @@ -212,10 +212,11 @@ class Finalize(object): obj = None if obj is None: - return '<Finalize object, dead>' + return '<%s object, dead>' % self.__class__.__name__ - x = '<Finalize object, callback=%s' % \ - getattr(self._callback, '__name__', self._callback) + x = '<%s object, callback=%s' % ( + self.__class__.__name__, + getattr(self._callback, '__name__', self._callback)) if self._args: x += ', args=' + str(self._args) if self._kwargs: @@ -327,6 +328,13 @@ class ForkAwareThreadLock(object): self.acquire = self._lock.acquire self.release = self._lock.release + def __enter__(self): + return self._lock.__enter__() + + def __exit__(self, *args): + return self._lock.__exit__(*args) + + class ForkAwareLocal(threading.local): def __init__(self): register_after_fork(self, lambda obj : obj.__dict__.clear()) diff --git a/Lib/ntpath.py b/Lib/ntpath.py index af3fb87..ee1a215 100644 --- a/Lib/ntpath.py +++ b/Lib/ntpath.py @@ -32,48 +32,12 @@ if 'ce' in sys.builtin_module_names: defpath = '\\Windows' devnull = 'nul' -def _get_empty(path): - if isinstance(path, bytes): - return b'' - else: - return '' - -def _get_sep(path): - if isinstance(path, bytes): - return b'\\' - else: - return '\\' - -def _get_altsep(path): - if isinstance(path, bytes): - return b'/' - else: - return '/' - def _get_bothseps(path): if isinstance(path, bytes): return b'\\/' else: return '\\/' -def _get_dot(path): - if isinstance(path, bytes): - return b'.' - else: - return '.' - -def _get_colon(path): - if isinstance(path, bytes): - return b':' - else: - return ':' - -def _get_special(path): - if isinstance(path, bytes): - return (b'\\\\.\\', b'\\\\?\\') - else: - return ('\\\\.\\', '\\\\?\\') - # Normalize the case of a pathname and map slashes to backslashes. # Other normalizations (such as optimizing '../' away) are not done # (this is done by normpath). @@ -82,10 +46,16 @@ def normcase(s): """Normalize case of pathname. Makes all characters lowercase and all slashes into backslashes.""" - if not isinstance(s, (bytes, str)): - raise TypeError("normcase() argument must be str or bytes, " - "not '{}'".format(s.__class__.__name__)) - return s.replace(_get_altsep(s), _get_sep(s)).lower() + try: + if isinstance(s, bytes): + return s.replace(b'/', b'\\').lower() + else: + return s.replace('/', '\\').lower() + except (TypeError, AttributeError): + if not isinstance(s, (bytes, str)): + raise TypeError("normcase() argument must be str or bytes, " + "not %r" % s.__class__.__name__) from None + raise # Return whether a path is absolute. @@ -97,40 +67,49 @@ def normcase(s): def isabs(s): """Test whether a path is absolute""" s = splitdrive(s)[1] - return len(s) > 0 and s[:1] in _get_bothseps(s) + return len(s) > 0 and s[0] in _get_bothseps(s) # Join two (or more) paths. def join(path, *paths): - sep = _get_sep(path) - seps = _get_bothseps(path) - colon = _get_colon(path) - result_drive, result_path = splitdrive(path) - for p in paths: - p_drive, p_path = splitdrive(p) - if p_path and p_path[0] in seps: - # Second path is absolute - if p_drive or not result_drive: - result_drive = p_drive - result_path = p_path - continue - elif p_drive and p_drive != result_drive: - if p_drive.lower() != result_drive.lower(): - # Different drives => ignore the first path entirely - result_drive = p_drive + if isinstance(path, bytes): + sep = b'\\' + seps = b'\\/' + colon = b':' + else: + sep = '\\' + seps = '\\/' + colon = ':' + try: + result_drive, result_path = splitdrive(path) + for p in paths: + p_drive, p_path = splitdrive(p) + if p_path and p_path[0] in seps: + # Second path is absolute + if p_drive or not result_drive: + result_drive = p_drive result_path = p_path continue - # Same drive in different case - result_drive = p_drive - # Second path is relative to the first - if result_path and result_path[-1] not in seps: - result_path = result_path + sep - result_path = result_path + p_path - ## add separator between UNC and non-absolute path - if (result_path and result_path[0] not in seps and - result_drive and result_drive[-1:] != colon): - return result_drive + sep + result_path - return result_drive + result_path + elif p_drive and p_drive != result_drive: + if p_drive.lower() != result_drive.lower(): + # Different drives => ignore the first path entirely + result_drive = p_drive + result_path = p_path + continue + # Same drive in different case + result_drive = p_drive + # Second path is relative to the first + if result_path and result_path[-1] not in seps: + result_path = result_path + sep + result_path = result_path + p_path + ## add separator between UNC and non-absolute path + if (result_path and result_path[0] not in seps and + result_drive and result_drive[-1:] != colon): + return result_drive + sep + result_path + return result_drive + result_path + except (TypeError, AttributeError, BytesWarning): + genericpath._check_arg_types('join', path, *paths) + raise # Split a path in a drive specification (a drive letter followed by a @@ -155,10 +134,16 @@ def splitdrive(p): Paths cannot contain both a drive letter and a UNC path. """ - empty = _get_empty(p) - if len(p) > 1: - sep = _get_sep(p) - normp = p.replace(_get_altsep(p), sep) + if len(p) >= 2: + if isinstance(p, bytes): + sep = b'\\' + altsep = b'/' + colon = b':' + else: + sep = '\\' + altsep = '/' + colon = ':' + normp = p.replace(altsep, sep) if (normp[0:2] == sep*2) and (normp[2:3] != sep): # is a UNC path: # vvvvvvvvvvvvvvvvvvvv drive letter or UNC path @@ -166,18 +151,18 @@ def splitdrive(p): # directory ^^^^^^^^^^^^^^^ index = normp.find(sep, 2) if index == -1: - return empty, p + return p[:0], p index2 = normp.find(sep, index + 1) # a UNC path can't have two slashes in a row # (after the initial two) if index2 == index + 1: - return empty, p + return p[:0], p if index2 == -1: index2 = len(p) return p[:index2], p[index2:] - if normp[1:2] == _get_colon(p): + if normp[1:2] == colon: return p[:2], p[2:] - return empty, p + return p[:0], p # Parse UNC paths @@ -221,10 +206,7 @@ def split(p): i -= 1 head, tail = p[:i], p[i:] # now tail has no slashes # remove trailing slashes from head, unless it's all slashes - head2 = head - while head2 and head2[-1:] in seps: - head2 = head2[:-1] - head = head2 or head + head = head.rstrip(seps) or head return d + head, tail @@ -234,8 +216,10 @@ def split(p): # It is always true that root + ext == p. def splitext(p): - return genericpath._splitext(p, _get_sep(p), _get_altsep(p), - _get_dot(p)) + if isinstance(p, bytes): + return genericpath._splitext(p, b'\\', b'/', b'.') + else: + return genericpath._splitext(p, '\\', '/', '.') splitext.__doc__ = genericpath._splitext.__doc__ @@ -343,7 +327,7 @@ def expanduser(path): userhome = join(drive, os.environ['HOMEPATH']) if isinstance(path, bytes): - userhome = userhome.encode(sys.getfilesystemencoding()) + userhome = os.fsencode(userhome) if i != 1: #~user userhome = join(dirname(userhome), path[1:i]) @@ -369,13 +353,14 @@ def expandvars(path): Unknown variables are left unchanged.""" if isinstance(path, bytes): - if ord('$') not in path and ord('%') not in path: + if b'$' not in path and b'%' not in path: return path import string varchars = bytes(string.ascii_letters + string.digits + '_-', 'ascii') quote = b'\'' percent = b'%' brace = b'{' + rbrace = b'}' dollar = b'$' environ = getattr(os, 'environb', None) else: @@ -386,6 +371,7 @@ def expandvars(path): quote = '\'' percent = '%' brace = '{' + rbrace = '}' dollar = '$' environ = os.environ res = path[:0] @@ -432,15 +418,9 @@ def expandvars(path): path = path[index+2:] pathlen = len(path) try: - if isinstance(path, bytes): - index = path.index(b'}') - else: - index = path.index('}') + index = path.index(rbrace) except ValueError: - if isinstance(path, bytes): - res += b'${' + path - else: - res += '${' + path + res += dollar + brace + path index = pathlen - 1 else: var = path[:index] @@ -450,10 +430,7 @@ def expandvars(path): else: value = environ[var] except KeyError: - if isinstance(path, bytes): - value = b'${' + var + b'}' - else: - value = '${' + var + '}' + value = dollar + brace + var + rbrace res += value else: var = path[:0] @@ -485,16 +462,25 @@ def expandvars(path): def normpath(path): """Normalize path, eliminating double slashes, etc.""" - sep = _get_sep(path) - dotdot = _get_dot(path) * 2 - special_prefixes = _get_special(path) + if isinstance(path, bytes): + sep = b'\\' + altsep = b'/' + curdir = b'.' + pardir = b'..' + special_prefixes = (b'\\\\.\\', b'\\\\?\\') + else: + sep = '\\' + altsep = '/' + curdir = '.' + pardir = '..' + special_prefixes = ('\\\\.\\', '\\\\?\\') if path.startswith(special_prefixes): # in the case of paths with these prefixes: # \\.\ -> device names # \\?\ -> literal paths # do not do any normalization, but return the path unchanged return path - path = path.replace(_get_altsep(path), sep) + path = path.replace(altsep, sep) prefix, path = splitdrive(path) # collapse initial backslashes @@ -505,13 +491,13 @@ def normpath(path): comps = path.split(sep) i = 0 while i < len(comps): - if not comps[i] or comps[i] == _get_dot(path): + if not comps[i] or comps[i] == curdir: del comps[i] - elif comps[i] == dotdot: - if i > 0 and comps[i-1] != dotdot: + elif comps[i] == pardir: + if i > 0 and comps[i-1] != pardir: del comps[i-1:i+1] i -= 1 - elif i == 0 and prefix.endswith(_get_sep(path)): + elif i == 0 and prefix.endswith(sep): del comps[i] else: i += 1 @@ -519,7 +505,7 @@ def normpath(path): i += 1 # If the path is now empty, substitute '.' if not prefix and not comps: - comps.append(_get_dot(path)) + comps.append(curdir) return prefix + sep.join(comps) @@ -559,42 +545,48 @@ realpath = abspath supports_unicode_filenames = (hasattr(sys, "getwindowsversion") and sys.getwindowsversion()[3] >= 2) -def relpath(path, start=curdir): +def relpath(path, start=None): """Return a relative version of a path""" - sep = _get_sep(path) + if isinstance(path, bytes): + sep = b'\\' + curdir = b'.' + pardir = b'..' + else: + sep = '\\' + curdir = '.' + pardir = '..' - if start is curdir: - start = _get_dot(path) + if start is None: + start = curdir if not path: raise ValueError("no path specified") - start_abs = abspath(normpath(start)) - path_abs = abspath(normpath(path)) - start_drive, start_rest = splitdrive(start_abs) - path_drive, path_rest = splitdrive(path_abs) - if normcase(start_drive) != normcase(path_drive): - error = "path is on mount '{0}', start on mount '{1}'".format( - path_drive, start_drive) - raise ValueError(error) - - start_list = [x for x in start_rest.split(sep) if x] - path_list = [x for x in path_rest.split(sep) if x] - # Work out how much of the filepath is shared by start and path. - i = 0 - for e1, e2 in zip(start_list, path_list): - if normcase(e1) != normcase(e2): - break - i += 1 + try: + start_abs = abspath(normpath(start)) + path_abs = abspath(normpath(path)) + start_drive, start_rest = splitdrive(start_abs) + path_drive, path_rest = splitdrive(path_abs) + if normcase(start_drive) != normcase(path_drive): + raise ValueError("path is on mount %r, start on mount %r" % ( + path_drive, start_drive)) + + start_list = [x for x in start_rest.split(sep) if x] + path_list = [x for x in path_rest.split(sep) if x] + # Work out how much of the filepath is shared by start and path. + i = 0 + for e1, e2 in zip(start_list, path_list): + if normcase(e1) != normcase(e2): + break + i += 1 - if isinstance(path, bytes): - pardir = b'..' - else: - pardir = '..' - rel_list = [pardir] * (len(start_list)-i) + path_list[i:] - if not rel_list: - return _get_dot(path) - return join(*rel_list) + rel_list = [pardir] * (len(start_list)-i) + path_list[i:] + if not rel_list: + return curdir + return join(*rel_list) + except (TypeError, ValueError, AttributeError, BytesWarning, DeprecationWarning): + genericpath._check_arg_types('relpath', path, start) + raise # determine if two files are in fact the same file diff --git a/Lib/opcode.py b/Lib/opcode.py index 0bd1ee6..bfd3c4d 100644 --- a/Lib/opcode.py +++ b/Lib/opcode.py @@ -70,6 +70,9 @@ def_op('UNARY_NOT', 12) def_op('UNARY_INVERT', 15) +def_op('BINARY_MATRIX_MULTIPLY', 16) +def_op('INPLACE_MATRIX_MULTIPLY', 17) + def_op('BINARY_POWER', 19) def_op('BINARY_MULTIPLY', 20) diff --git a/Lib/operator.py b/Lib/operator.py index b60349f..856036d 100644 --- a/Lib/operator.py +++ b/Lib/operator.py @@ -105,6 +105,10 @@ def mul(a, b): "Same as a * b." return a * b +def matmul(a, b): + "Same as a @ b." + return a @ b + def neg(a): "Same as -a." return -a @@ -326,6 +330,11 @@ def imul(a, b): a *= b return a +def imatmul(a, b): + "Same as a @= b." + a @= b + return a + def ior(a, b): "Same as a |= b." a |= b @@ -383,6 +392,7 @@ __invert__ = invert __lshift__ = lshift __mod__ = mod __mul__ = mul +__matmul__ = matmul __neg__ = neg __or__ = or_ __pos__ = pos @@ -403,6 +413,7 @@ __ifloordiv__ = ifloordiv __ilshift__ = ilshift __imod__ = imod __imul__ = imul +__imatmul__ = imatmul __ior__ = ior __ipow__ = ipow __irshift__ = irshift @@ -61,6 +61,10 @@ if 'posix' in _names: except ImportError: pass + import posix + __all__.extend(_get_exports_list(posix)) + del posix + elif 'nt' in _names: name = 'nt' linesep = '\r\n' diff --git a/Lib/pathlib.py b/Lib/pathlib.py index 918ac8d..01e66a0 100644 --- a/Lib/pathlib.py +++ b/Lib/pathlib.py @@ -225,6 +225,36 @@ class _WindowsFlavour(_Flavour): # It's a path on a network drive => 'file://host/share/a/b' return 'file:' + urlquote_from_bytes(path.as_posix().encode('utf-8')) + def gethomedir(self, username): + if 'HOME' in os.environ: + userhome = os.environ['HOME'] + elif 'USERPROFILE' in os.environ: + userhome = os.environ['USERPROFILE'] + elif 'HOMEPATH' in os.environ: + try: + drv = os.environ['HOMEDRIVE'] + except KeyError: + drv = '' + userhome = drv + os.environ['HOMEPATH'] + else: + raise RuntimeError("Can't determine home directory") + + if username: + # Try to guess user home directory. By default all users + # directories are located in the same place and are named by + # corresponding usernames. If current user home directory points + # to nonstandard place, this guess is likely wrong. + if os.environ['USERNAME'] != username: + drv, root, parts = self.parse_parts((userhome,)) + if parts[-1] != os.environ['USERNAME']: + raise RuntimeError("Can't determine home directory " + "for %r" % username) + parts[-1] = username + if drv or root: + userhome = drv + root + self.join(parts[1:]) + else: + userhome = self.join(parts) + return userhome class _PosixFlavour(_Flavour): sep = '/' @@ -308,6 +338,21 @@ class _PosixFlavour(_Flavour): bpath = bytes(path) return 'file://' + urlquote_from_bytes(bpath) + def gethomedir(self, username): + if not username: + try: + return os.environ['HOME'] + except KeyError: + import pwd + return pwd.getpwuid(os.getuid()).pw_dir + else: + import pwd + try: + return pwd.getpwnam(username).pw_dir + except KeyError: + raise RuntimeError("Can't determine home directory " + "for %r" % username) + _windows_flavour = _WindowsFlavour() _posix_flavour = _PosixFlavour() @@ -964,6 +1009,24 @@ class Path(PurePath): """ return cls(os.getcwd()) + @classmethod + def home(cls): + """Return a new path pointing to the user's home directory (as + returned by os.path.expanduser('~')). + """ + return cls(cls()._flavour.gethomedir(None)) + + def samefile(self, other_path): + """Return whether `other_file` is the same or not as this file. + (as returned by os.path.samefile(file, other_file)). + """ + st = self.stat() + try: + other_st = other_path.stat() + except AttributeError: + other_st = os.stat(other_path) + return os.path.samestat(st, other_st) + def iterdir(self): """Iterate over the files in this directory. Does not yield any result for the special paths '.' and '..'. @@ -1072,6 +1135,39 @@ class Path(PurePath): return io.open(str(self), mode, buffering, encoding, errors, newline, opener=self._opener) + def read_bytes(self): + """ + Open the file in bytes mode, read it, and close the file. + """ + with self.open(mode='rb') as f: + return f.read() + + def read_text(self, encoding=None, errors=None): + """ + Open the file in text mode, read it, and close the file. + """ + with self.open(mode='r', encoding=encoding, errors=errors) as f: + return f.read() + + def write_bytes(self, data): + """ + Open the file in bytes mode, write to it, and close the file. + """ + # type-check for the buffer interface before truncating the file + view = memoryview(data) + with self.open(mode='wb') as f: + return f.write(view) + + def write_text(self, data, encoding=None, errors=None): + """ + Open the file in text mode, write to it, and close the file. + """ + if not isinstance(data, str): + raise TypeError('data must be str, not %s' % + data.__class__.__name__) + with self.open(mode='w', encoding=encoding, errors=errors) as f: + return f.write(data) + def touch(self, mode=0o666, exist_ok=True): """ Create this file with the given access mode, if it doesn't exist. @@ -1095,14 +1191,21 @@ class Path(PurePath): fd = self._raw_open(flags, mode) os.close(fd) - def mkdir(self, mode=0o777, parents=False): + def mkdir(self, mode=0o777, parents=False, exist_ok=False): if self._closed: self._raise_closed() if not parents: - self._accessor.mkdir(self, mode) + try: + self._accessor.mkdir(self, mode) + except FileExistsError: + if not exist_ok or not self.is_dir(): + raise else: try: self._accessor.mkdir(self, mode) + except FileExistsError: + if not exist_ok or not self.is_dir(): + raise except OSError as e: if e.errno != ENOENT: raise @@ -1283,6 +1386,17 @@ class Path(PurePath): # (see https://bitbucket.org/pitrou/pathlib/issue/12/) return False + def expanduser(self): + """ Return a new path with expanded ~ and ~user constructs + (as returned by os.path.expanduser) + """ + if (not (self._drv or self._root) and + self._parts and self._parts[0][:1] == '~'): + homedir = self._flavour.gethomedir(self._parts[0][1:]) + return self._from_parts([homedir] + self._parts[1:]) + + return self + class PosixPath(Path, PurePosixPath): __slots__ = () @@ -1316,7 +1316,7 @@ class Pdb(bdb.Bdb, cmd.Cmd): return # Is it a class? if value.__class__ is type: - self.message('Class %s.%s' % (value.__module__, value.__name__)) + self.message('Class %s.%s' % (value.__module__, value.__qualname__)) return # None of the above... self.message(type(value)) diff --git a/Lib/pkgutil.py b/Lib/pkgutil.py index a54e947..fc4a074 100644 --- a/Lib/pkgutil.py +++ b/Lib/pkgutil.py @@ -616,7 +616,7 @@ def get_data(package, resource): return None # XXX needs test mod = (sys.modules.get(package) or - importlib._bootstrap._SpecMethods(spec).load()) + importlib._bootstrap._load(spec)) if mod is None or not hasattr(mod, '__file__'): return None diff --git a/Lib/posixpath.py b/Lib/posixpath.py index 0aa53fe..44ed838 100644 --- a/Lib/posixpath.py +++ b/Lib/posixpath.py @@ -82,11 +82,8 @@ def join(a, *p): path += b else: path += sep + b - except TypeError: - if all(isinstance(s, (str, bytes)) for s in (a,) + p): - # Must have a mixture of text and binary data - raise TypeError("Can't mix strings and bytes in path " - "components") from None + except (TypeError, AttributeError, BytesWarning): + genericpath._check_arg_types('join', a, *p) raise return path @@ -445,13 +442,16 @@ def relpath(path, start=None): if start is None: start = curdir - start_list = [x for x in abspath(start).split(sep) if x] - path_list = [x for x in abspath(path).split(sep) if x] - - # Work out how much of the filepath is shared by start and path. - i = len(commonprefix([start_list, path_list])) - - rel_list = [pardir] * (len(start_list)-i) + path_list[i:] - if not rel_list: - return curdir - return join(*rel_list) + try: + start_list = [x for x in abspath(start).split(sep) if x] + path_list = [x for x in abspath(path).split(sep) if x] + # Work out how much of the filepath is shared by start and path. + i = len(commonprefix([start_list, path_list])) + + rel_list = [pardir] * (len(start_list)-i) + path_list[i:] + if not rel_list: + return curdir + return join(*rel_list) + except (TypeError, AttributeError, BytesWarning, DeprecationWarning): + genericpath._check_arg_types('relpath', path, start) + raise diff --git a/Lib/pprint.py b/Lib/pprint.py index 2cbffed..0091e69 100644 --- a/Lib/pprint.py +++ b/Lib/pprint.py @@ -161,7 +161,7 @@ class PrettyPrinter: return rep = self._repr(object, context, level - 1) typ = type(object) - max_width = self._width - 1 - indent - allowance + max_width = self._width - indent - allowance sepLines = len(rep) > max_width write = stream.write @@ -174,24 +174,14 @@ class PrettyPrinter: length = len(object) if length: context[objid] = 1 - indent = indent + self._indent_per_level if issubclass(typ, _OrderedDict): items = list(object.items()) else: items = sorted(object.items(), key=_safe_tuple) - key, ent = items[0] - rep = self._repr(key, context, level) - write(rep) - write(': ') - self._format(ent, stream, indent + len(rep) + 2, - allowance + 1, context, level) - if length > 1: - for key, ent in items[1:]: - rep = self._repr(key, context, level) - write(',\n%s%s: ' % (' '*indent, rep)) - self._format(ent, stream, indent + len(rep) + 2, - allowance + 1, context, level) - indent = indent - self._indent_per_level + self._format_dict_items(items, stream, + indent + self._indent_per_level, + allowance + 1, + context, level) del context[objid] write('}') return @@ -207,7 +197,10 @@ class PrettyPrinter: endchar = ']' elif issubclass(typ, tuple): write('(') - endchar = ')' + if length == 1: + endchar = ',)' + else: + endchar = ')' else: if not length: write(rep) @@ -227,10 +220,9 @@ class PrettyPrinter: context[objid] = 1 self._format_items(object, stream, indent + self._indent_per_level, - allowance + 1, context, level) + allowance + len(endchar), + context, level) del context[objid] - if issubclass(typ, tuple) and length == 1: - write(',') write(endchar) return @@ -239,19 +231,27 @@ class PrettyPrinter: lines = object.splitlines(True) if level == 1: indent += 1 - max_width -= 2 + allowance += 1 + max_width1 = max_width = self._width - indent for i, line in enumerate(lines): rep = repr(line) - if len(rep) <= max_width: + if i == len(lines) - 1: + max_width1 -= allowance + if len(rep) <= max_width1: chunks.append(rep) else: # A list of alternating (non-space, space) strings - parts = re.split(r'(\s+)', line) + [''] + parts = re.findall(r'\S*\s*', line) + assert parts + assert not parts[-1] + parts.pop() # drop empty last part + max_width2 = max_width current = '' - for i in range(0, len(parts), 2): - part = parts[i] + parts[i+1] + for j, part in enumerate(parts): candidate = current + part - if len(repr(candidate)) > max_width: + if j == len(parts) - 1 and i == len(lines) - 1: + max_width2 -= allowance + if len(repr(candidate)) > max_width2: if current: chunks.append(repr(current)) current = part @@ -273,12 +273,41 @@ class PrettyPrinter: return write(rep) + def _format_dict_items(self, items, stream, indent, allowance, context, + level): + write = stream.write + delimnl = ',\n' + ' ' * indent + last_index = len(items) - 1 + for i, (key, ent) in enumerate(items): + last = i == last_index + rep = self._repr(key, context, level) + write(rep) + write(': ') + self._format(ent, stream, indent + len(rep) + 2, + allowance if last else 1, + context, level) + if not last: + write(delimnl) + def _format_items(self, items, stream, indent, allowance, context, level): write = stream.write delimnl = ',\n' + ' ' * indent delim = '' - width = max_width = self._width - indent - allowance + 2 - for ent in items: + width = max_width = self._width - indent + 1 + it = iter(items) + try: + next_ent = next(it) + except StopIteration: + return + last = False + while not last: + ent = next_ent + try: + next_ent = next(it) + except StopIteration: + last = True + max_width -= allowance + width -= allowance if self._compact: rep = self._repr(ent, context, level) w = len(rep) + 2 @@ -294,7 +323,9 @@ class PrettyPrinter: continue write(delim) delim = delimnl - self._format(ent, stream, indent, allowance, context, level) + self._format(ent, stream, indent, + allowance if last else 1, + context, level) def _repr(self, object, context, level): repr, readable, recursive = self.format(object, context.copy(), diff --git a/Lib/pydoc.py b/Lib/pydoc.py index 8bbebc9..c92b324 100755 --- a/Lib/pydoc.py +++ b/Lib/pydoc.py @@ -264,9 +264,8 @@ def synopsis(filename, cache={}): # XXX We probably don't need to pass in the loader here. spec = importlib.util.spec_from_file_location('__temp__', filename, loader=loader) - _spec = importlib._bootstrap._SpecMethods(spec) try: - module = _spec.load() + module = importlib._bootstrap._load(spec) except: return None del sys.modules['__temp__'] @@ -298,9 +297,8 @@ def importfile(path): loader = importlib._bootstrap.SourceFileLoader(name, path) # XXX We probably don't need to pass in the loader here. spec = importlib.util.spec_from_file_location(name, path, loader=loader) - _spec = importlib._bootstrap._SpecMethods(spec) try: - return _spec.load() + return importlib._bootstrap._load(spec) except: raise ErrorDuringImport(path, sys.exc_info()) @@ -1579,7 +1577,10 @@ def resolve(thing, forceload=0): if isinstance(thing, str): object = locate(thing, forceload) if not object: - raise ImportError('no Python documentation found for %r' % thing) + raise ImportError('''\ +No Python documentation found for %r. +Use help() to get the interactive help utility. +Use help(str) for help on the str class.''' % thing) return object, thing else: name = getattr(thing, '__name__', None) @@ -1823,7 +1824,8 @@ class Helper: if inspect.stack()[1][3] == '?': self() return '' - return '<pydoc.Helper instance>' + return '<%s.%s instance>' % (self.__class__.__module__, + self.__class__.__qualname__) _GoInteractive = object() def __call__(self, request=_GoInteractive): @@ -1849,7 +1851,10 @@ has the same effect as typing a particular string at the help> prompt. break request = replace(request, '"', '', "'", '').strip() if request.lower() in ('q', 'quit'): break - self.help(request) + if request == 'help': + self.intro() + else: + self.help(request) def getline(self, prompt): """Read one line, using input() when appropriate.""" @@ -1863,8 +1868,7 @@ has the same effect as typing a particular string at the help> prompt. def help(self, request): if type(request) is type(''): request = request.strip() - if request == 'help': self.intro() - elif request == 'keywords': self.listkeywords() + if request == 'keywords': self.listkeywords() elif request == 'symbols': self.listsymbols() elif request == 'topics': self.listtopics() elif request == 'modules': self.listmodules() @@ -1877,6 +1881,7 @@ has the same effect as typing a particular string at the help> prompt. elif request in self.keywords: self.showtopic(request) elif request in self.topics: self.showtopic(request) elif request: doc(request, 'Help on %s:', output=self._output) + else: doc(str, 'Help on %s:', output=self._output) elif isinstance(request, Helper): self() else: doc(request, 'Help on %s:', output=self._output) self.output.write('\n') @@ -2072,9 +2077,8 @@ class ModuleScanner: else: path = None else: - _spec = importlib._bootstrap._SpecMethods(spec) try: - module = _spec.load() + module = importlib._bootstrap._load(spec) except ImportError: if onerror: onerror(modname) diff --git a/Lib/pydoc_data/topics.py b/Lib/pydoc_data/topics.py index e54b6dd..489259e 100644 --- a/Lib/pydoc_data/topics.py +++ b/Lib/pydoc_data/topics.py @@ -1,13 +1,13 @@ # -*- coding: utf-8 -*- -# Autogenerated by Sphinx on Sun Feb 22 23:52:05 2015 +# Autogenerated by Sphinx on Sat Feb 7 15:53:56 2015 topics = {'assert': u'\nThe "assert" statement\n**********************\n\nAssert statements are a convenient way to insert debugging assertions\ninto a program:\n\n assert_stmt ::= "assert" expression ["," expression]\n\nThe simple form, "assert expression", is equivalent to\n\n if __debug__:\n if not expression: raise AssertionError\n\nThe extended form, "assert expression1, expression2", is equivalent to\n\n if __debug__:\n if not expression1: raise AssertionError(expression2)\n\nThese equivalences assume that "__debug__" and "AssertionError" refer\nto the built-in variables with those names. In the current\nimplementation, the built-in variable "__debug__" is "True" under\nnormal circumstances, "False" when optimization is requested (command\nline option -O). The current code generator emits no code for an\nassert statement when optimization is requested at compile time. Note\nthat it is unnecessary to include the source code for the expression\nthat failed in the error message; it will be displayed as part of the\nstack trace.\n\nAssignments to "__debug__" are illegal. The value for the built-in\nvariable is determined when the interpreter starts.\n', - 'assignment': u'\nAssignment statements\n*********************\n\nAssignment statements are used to (re)bind names to values and to\nmodify attributes or items of mutable objects:\n\n assignment_stmt ::= (target_list "=")+ (expression_list | yield_expression)\n target_list ::= target ("," target)* [","]\n target ::= identifier\n | "(" target_list ")"\n | "[" target_list "]"\n | attributeref\n | subscription\n | slicing\n | "*" target\n\n(See section *Primaries* for the syntax definitions for\n*attributeref*, *subscription*, and *slicing*.)\n\nAn assignment statement evaluates the expression list (remember that\nthis can be a single expression or a comma-separated list, the latter\nyielding a tuple) and assigns the single resulting object to each of\nthe target lists, from left to right.\n\nAssignment is defined recursively depending on the form of the target\n(list). When a target is part of a mutable object (an attribute\nreference, subscription or slicing), the mutable object must\nultimately perform the assignment and decide about its validity, and\nmay raise an exception if the assignment is unacceptable. The rules\nobserved by various types and the exceptions raised are given with the\ndefinition of the object types (see section *The standard type\nhierarchy*).\n\nAssignment of an object to a target list, optionally enclosed in\nparentheses or square brackets, is recursively defined as follows.\n\n* If the target list is a single target: The object is assigned to\n that target.\n\n* If the target list is a comma-separated list of targets: The\n object must be an iterable with the same number of items as there\n are targets in the target list, and the items are assigned, from\n left to right, to the corresponding targets.\n\n * If the target list contains one target prefixed with an\n asterisk, called a "starred" target: The object must be a sequence\n with at least as many items as there are targets in the target\n list, minus one. The first items of the sequence are assigned,\n from left to right, to the targets before the starred target. The\n final items of the sequence are assigned to the targets after the\n starred target. A list of the remaining items in the sequence is\n then assigned to the starred target (the list can be empty).\n\n * Else: The object must be a sequence with the same number of\n items as there are targets in the target list, and the items are\n assigned, from left to right, to the corresponding targets.\n\nAssignment of an object to a single target is recursively defined as\nfollows.\n\n* If the target is an identifier (name):\n\n * If the name does not occur in a "global" or "nonlocal" statement\n in the current code block: the name is bound to the object in the\n current local namespace.\n\n * Otherwise: the name is bound to the object in the global\n namespace or the outer namespace determined by "nonlocal",\n respectively.\n\n The name is rebound if it was already bound. This may cause the\n reference count for the object previously bound to the name to reach\n zero, causing the object to be deallocated and its destructor (if it\n has one) to be called.\n\n* If the target is a target list enclosed in parentheses or in\n square brackets: The object must be an iterable with the same number\n of items as there are targets in the target list, and its items are\n assigned, from left to right, to the corresponding targets.\n\n* If the target is an attribute reference: The primary expression in\n the reference is evaluated. It should yield an object with\n assignable attributes; if this is not the case, "TypeError" is\n raised. That object is then asked to assign the assigned object to\n the given attribute; if it cannot perform the assignment, it raises\n an exception (usually but not necessarily "AttributeError").\n\n Note: If the object is a class instance and the attribute reference\n occurs on both sides of the assignment operator, the RHS expression,\n "a.x" can access either an instance attribute or (if no instance\n attribute exists) a class attribute. The LHS target "a.x" is always\n set as an instance attribute, creating it if necessary. Thus, the\n two occurrences of "a.x" do not necessarily refer to the same\n attribute: if the RHS expression refers to a class attribute, the\n LHS creates a new instance attribute as the target of the\n assignment:\n\n class Cls:\n x = 3 # class variable\n inst = Cls()\n inst.x = inst.x + 1 # writes inst.x as 4 leaving Cls.x as 3\n\n This description does not necessarily apply to descriptor\n attributes, such as properties created with "property()".\n\n* If the target is a subscription: The primary expression in the\n reference is evaluated. It should yield either a mutable sequence\n object (such as a list) or a mapping object (such as a dictionary).\n Next, the subscript expression is evaluated.\n\n If the primary is a mutable sequence object (such as a list), the\n subscript must yield an integer. If it is negative, the sequence\'s\n length is added to it. The resulting value must be a nonnegative\n integer less than the sequence\'s length, and the sequence is asked\n to assign the assigned object to its item with that index. If the\n index is out of range, "IndexError" is raised (assignment to a\n subscripted sequence cannot add new items to a list).\n\n If the primary is a mapping object (such as a dictionary), the\n subscript must have a type compatible with the mapping\'s key type,\n and the mapping is then asked to create a key/datum pair which maps\n the subscript to the assigned object. This can either replace an\n existing key/value pair with the same key value, or insert a new\n key/value pair (if no key with the same value existed).\n\n For user-defined objects, the "__setitem__()" method is called with\n appropriate arguments.\n\n* If the target is a slicing: The primary expression in the\n reference is evaluated. It should yield a mutable sequence object\n (such as a list). The assigned object should be a sequence object\n of the same type. Next, the lower and upper bound expressions are\n evaluated, insofar they are present; defaults are zero and the\n sequence\'s length. The bounds should evaluate to integers. If\n either bound is negative, the sequence\'s length is added to it. The\n resulting bounds are clipped to lie between zero and the sequence\'s\n length, inclusive. Finally, the sequence object is asked to replace\n the slice with the items of the assigned sequence. The length of\n the slice may be different from the length of the assigned sequence,\n thus changing the length of the target sequence, if the target\n sequence allows it.\n\n**CPython implementation detail:** In the current implementation, the\nsyntax for targets is taken to be the same as for expressions, and\ninvalid syntax is rejected during the code generation phase, causing\nless detailed error messages.\n\nAlthough the definition of assignment implies that overlaps between\nthe left-hand side and the right-hand side are \'simultanenous\' (for\nexample "a, b = b, a" swaps two variables), overlaps *within* the\ncollection of assigned-to variables occur left-to-right, sometimes\nresulting in confusion. For instance, the following program prints\n"[0, 2]":\n\n x = [0, 1]\n i = 0\n i, x[i] = 1, 2 # i is updated, then x[i] is updated\n print(x)\n\nSee also: **PEP 3132** - Extended Iterable Unpacking\n\n The specification for the "*target" feature.\n\n\nAugmented assignment statements\n===============================\n\nAugmented assignment is the combination, in a single statement, of a\nbinary operation and an assignment statement:\n\n augmented_assignment_stmt ::= augtarget augop (expression_list | yield_expression)\n augtarget ::= identifier | attributeref | subscription | slicing\n augop ::= "+=" | "-=" | "*=" | "/=" | "//=" | "%=" | "**="\n | ">>=" | "<<=" | "&=" | "^=" | "|="\n\n(See section *Primaries* for the syntax definitions of the last three\nsymbols.)\n\nAn augmented assignment evaluates the target (which, unlike normal\nassignment statements, cannot be an unpacking) and the expression\nlist, performs the binary operation specific to the type of assignment\non the two operands, and assigns the result to the original target.\nThe target is only evaluated once.\n\nAn augmented assignment expression like "x += 1" can be rewritten as\n"x = x + 1" to achieve a similar, but not exactly equal effect. In the\naugmented version, "x" is only evaluated once. Also, when possible,\nthe actual operation is performed *in-place*, meaning that rather than\ncreating a new object and assigning that to the target, the old object\nis modified instead.\n\nUnlike normal assignments, augmented assignments evaluate the left-\nhand side *before* evaluating the right-hand side. For example, "a[i]\n+= f(x)" first looks-up "a[i]", then it evaluates "f(x)" and performs\nthe addition, and lastly, it writes the result back to "a[i]".\n\nWith the exception of assigning to tuples and multiple targets in a\nsingle statement, the assignment done by augmented assignment\nstatements is handled the same way as normal assignments. Similarly,\nwith the exception of the possible *in-place* behavior, the binary\noperation performed by augmented assignment is the same as the normal\nbinary operations.\n\nFor targets which are attribute references, the same *caveat about\nclass and instance attributes* applies as for regular assignments.\n', + 'assignment': u'\nAssignment statements\n*********************\n\nAssignment statements are used to (re)bind names to values and to\nmodify attributes or items of mutable objects:\n\n assignment_stmt ::= (target_list "=")+ (expression_list | yield_expression)\n target_list ::= target ("," target)* [","]\n target ::= identifier\n | "(" target_list ")"\n | "[" target_list "]"\n | attributeref\n | subscription\n | slicing\n | "*" target\n\n(See section *Primaries* for the syntax definitions for\n*attributeref*, *subscription*, and *slicing*.)\n\nAn assignment statement evaluates the expression list (remember that\nthis can be a single expression or a comma-separated list, the latter\nyielding a tuple) and assigns the single resulting object to each of\nthe target lists, from left to right.\n\nAssignment is defined recursively depending on the form of the target\n(list). When a target is part of a mutable object (an attribute\nreference, subscription or slicing), the mutable object must\nultimately perform the assignment and decide about its validity, and\nmay raise an exception if the assignment is unacceptable. The rules\nobserved by various types and the exceptions raised are given with the\ndefinition of the object types (see section *The standard type\nhierarchy*).\n\nAssignment of an object to a target list, optionally enclosed in\nparentheses or square brackets, is recursively defined as follows.\n\n* If the target list is a single target: The object is assigned to\n that target.\n\n* If the target list is a comma-separated list of targets: The\n object must be an iterable with the same number of items as there\n are targets in the target list, and the items are assigned, from\n left to right, to the corresponding targets.\n\n * If the target list contains one target prefixed with an\n asterisk, called a "starred" target: The object must be a sequence\n with at least as many items as there are targets in the target\n list, minus one. The first items of the sequence are assigned,\n from left to right, to the targets before the starred target. The\n final items of the sequence are assigned to the targets after the\n starred target. A list of the remaining items in the sequence is\n then assigned to the starred target (the list can be empty).\n\n * Else: The object must be a sequence with the same number of\n items as there are targets in the target list, and the items are\n assigned, from left to right, to the corresponding targets.\n\nAssignment of an object to a single target is recursively defined as\nfollows.\n\n* If the target is an identifier (name):\n\n * If the name does not occur in a "global" or "nonlocal" statement\n in the current code block: the name is bound to the object in the\n current local namespace.\n\n * Otherwise: the name is bound to the object in the global\n namespace or the outer namespace determined by "nonlocal",\n respectively.\n\n The name is rebound if it was already bound. This may cause the\n reference count for the object previously bound to the name to reach\n zero, causing the object to be deallocated and its destructor (if it\n has one) to be called.\n\n* If the target is a target list enclosed in parentheses or in\n square brackets: The object must be an iterable with the same number\n of items as there are targets in the target list, and its items are\n assigned, from left to right, to the corresponding targets.\n\n* If the target is an attribute reference: The primary expression in\n the reference is evaluated. It should yield an object with\n assignable attributes; if this is not the case, "TypeError" is\n raised. That object is then asked to assign the assigned object to\n the given attribute; if it cannot perform the assignment, it raises\n an exception (usually but not necessarily "AttributeError").\n\n Note: If the object is a class instance and the attribute reference\n occurs on both sides of the assignment operator, the RHS expression,\n "a.x" can access either an instance attribute or (if no instance\n attribute exists) a class attribute. The LHS target "a.x" is always\n set as an instance attribute, creating it if necessary. Thus, the\n two occurrences of "a.x" do not necessarily refer to the same\n attribute: if the RHS expression refers to a class attribute, the\n LHS creates a new instance attribute as the target of the\n assignment:\n\n class Cls:\n x = 3 # class variable\n inst = Cls()\n inst.x = inst.x + 1 # writes inst.x as 4 leaving Cls.x as 3\n\n This description does not necessarily apply to descriptor\n attributes, such as properties created with "property()".\n\n* If the target is a subscription: The primary expression in the\n reference is evaluated. It should yield either a mutable sequence\n object (such as a list) or a mapping object (such as a dictionary).\n Next, the subscript expression is evaluated.\n\n If the primary is a mutable sequence object (such as a list), the\n subscript must yield an integer. If it is negative, the sequence\'s\n length is added to it. The resulting value must be a nonnegative\n integer less than the sequence\'s length, and the sequence is asked\n to assign the assigned object to its item with that index. If the\n index is out of range, "IndexError" is raised (assignment to a\n subscripted sequence cannot add new items to a list).\n\n If the primary is a mapping object (such as a dictionary), the\n subscript must have a type compatible with the mapping\'s key type,\n and the mapping is then asked to create a key/datum pair which maps\n the subscript to the assigned object. This can either replace an\n existing key/value pair with the same key value, or insert a new\n key/value pair (if no key with the same value existed).\n\n For user-defined objects, the "__setitem__()" method is called with\n appropriate arguments.\n\n* If the target is a slicing: The primary expression in the\n reference is evaluated. It should yield a mutable sequence object\n (such as a list). The assigned object should be a sequence object\n of the same type. Next, the lower and upper bound expressions are\n evaluated, insofar they are present; defaults are zero and the\n sequence\'s length. The bounds should evaluate to integers. If\n either bound is negative, the sequence\'s length is added to it. The\n resulting bounds are clipped to lie between zero and the sequence\'s\n length, inclusive. Finally, the sequence object is asked to replace\n the slice with the items of the assigned sequence. The length of\n the slice may be different from the length of the assigned sequence,\n thus changing the length of the target sequence, if the target\n sequence allows it.\n\n**CPython implementation detail:** In the current implementation, the\nsyntax for targets is taken to be the same as for expressions, and\ninvalid syntax is rejected during the code generation phase, causing\nless detailed error messages.\n\nAlthough the definition of assignment implies that overlaps between\nthe left-hand side and the right-hand side are \'simultanenous\' (for\nexample "a, b = b, a" swaps two variables), overlaps *within* the\ncollection of assigned-to variables occur left-to-right, sometimes\nresulting in confusion. For instance, the following program prints\n"[0, 2]":\n\n x = [0, 1]\n i = 0\n i, x[i] = 1, 2 # i is updated, then x[i] is updated\n print(x)\n\nSee also: **PEP 3132** - Extended Iterable Unpacking\n\n The specification for the "*target" feature.\n\n\nAugmented assignment statements\n===============================\n\nAugmented assignment is the combination, in a single statement, of a\nbinary operation and an assignment statement:\n\n augmented_assignment_stmt ::= augtarget augop (expression_list | yield_expression)\n augtarget ::= identifier | attributeref | subscription | slicing\n augop ::= "+=" | "-=" | "*=" | "@=" | "/=" | "//=" | "%=" | "**="\n | ">>=" | "<<=" | "&=" | "^=" | "|="\n\n(See section *Primaries* for the syntax definitions of the last three\nsymbols.)\n\nAn augmented assignment evaluates the target (which, unlike normal\nassignment statements, cannot be an unpacking) and the expression\nlist, performs the binary operation specific to the type of assignment\non the two operands, and assigns the result to the original target.\nThe target is only evaluated once.\n\nAn augmented assignment expression like "x += 1" can be rewritten as\n"x = x + 1" to achieve a similar, but not exactly equal effect. In the\naugmented version, "x" is only evaluated once. Also, when possible,\nthe actual operation is performed *in-place*, meaning that rather than\ncreating a new object and assigning that to the target, the old object\nis modified instead.\n\nUnlike normal assignments, augmented assignments evaluate the left-\nhand side *before* evaluating the right-hand side. For example, "a[i]\n+= f(x)" first looks-up "a[i]", then it evaluates "f(x)" and performs\nthe addition, and lastly, it writes the result back to "a[i]".\n\nWith the exception of assigning to tuples and multiple targets in a\nsingle statement, the assignment done by augmented assignment\nstatements is handled the same way as normal assignments. Similarly,\nwith the exception of the possible *in-place* behavior, the binary\noperation performed by augmented assignment is the same as the normal\nbinary operations.\n\nFor targets which are attribute references, the same *caveat about\nclass and instance attributes* applies as for regular assignments.\n', 'atom-identifiers': u'\nIdentifiers (Names)\n*******************\n\nAn identifier occurring as an atom is a name. See section\n*Identifiers and keywords* for lexical definition and section *Naming\nand binding* for documentation of naming and binding.\n\nWhen the name is bound to an object, evaluation of the atom yields\nthat object. When a name is not bound, an attempt to evaluate it\nraises a "NameError" exception.\n\n**Private name mangling:** When an identifier that textually occurs in\na class definition begins with two or more underscore characters and\ndoes not end in two or more underscores, it is considered a *private\nname* of that class. Private names are transformed to a longer form\nbefore code is generated for them. The transformation inserts the\nclass name, with leading underscores removed and a single underscore\ninserted, in front of the name. For example, the identifier "__spam"\noccurring in a class named "Ham" will be transformed to "_Ham__spam".\nThis transformation is independent of the syntactical context in which\nthe identifier is used. If the transformed name is extremely long\n(longer than 255 characters), implementation defined truncation may\nhappen. If the class name consists only of underscores, no\ntransformation is done.\n', 'atom-literals': u"\nLiterals\n********\n\nPython supports string and bytes literals and various numeric\nliterals:\n\n literal ::= stringliteral | bytesliteral\n | integer | floatnumber | imagnumber\n\nEvaluation of a literal yields an object of the given type (string,\nbytes, integer, floating point number, complex number) with the given\nvalue. The value may be approximated in the case of floating point\nand imaginary (complex) literals. See section *Literals* for details.\n\nAll literals correspond to immutable data types, and hence the\nobject's identity is less important than its value. Multiple\nevaluations of literals with the same value (either the same\noccurrence in the program text or a different occurrence) may obtain\nthe same object or a different object with the same value.\n", 'attribute-access': u'\nCustomizing attribute access\n****************************\n\nThe following methods can be defined to customize the meaning of\nattribute access (use of, assignment to, or deletion of "x.name") for\nclass instances.\n\nobject.__getattr__(self, name)\n\n Called when an attribute lookup has not found the attribute in the\n usual places (i.e. it is not an instance attribute nor is it found\n in the class tree for "self"). "name" is the attribute name. This\n method should return the (computed) attribute value or raise an\n "AttributeError" exception.\n\n Note that if the attribute is found through the normal mechanism,\n "__getattr__()" is not called. (This is an intentional asymmetry\n between "__getattr__()" and "__setattr__()".) This is done both for\n efficiency reasons and because otherwise "__getattr__()" would have\n no way to access other attributes of the instance. Note that at\n least for instance variables, you can fake total control by not\n inserting any values in the instance attribute dictionary (but\n instead inserting them in another object). See the\n "__getattribute__()" method below for a way to actually get total\n control over attribute access.\n\nobject.__getattribute__(self, name)\n\n Called unconditionally to implement attribute accesses for\n instances of the class. If the class also defines "__getattr__()",\n the latter will not be called unless "__getattribute__()" either\n calls it explicitly or raises an "AttributeError". This method\n should return the (computed) attribute value or raise an\n "AttributeError" exception. In order to avoid infinite recursion in\n this method, its implementation should always call the base class\n method with the same name to access any attributes it needs, for\n example, "object.__getattribute__(self, name)".\n\n Note: This method may still be bypassed when looking up special\n methods as the result of implicit invocation via language syntax\n or built-in functions. See *Special method lookup*.\n\nobject.__setattr__(self, name, value)\n\n Called when an attribute assignment is attempted. This is called\n instead of the normal mechanism (i.e. store the value in the\n instance dictionary). *name* is the attribute name, *value* is the\n value to be assigned to it.\n\n If "__setattr__()" wants to assign to an instance attribute, it\n should call the base class method with the same name, for example,\n "object.__setattr__(self, name, value)".\n\nobject.__delattr__(self, name)\n\n Like "__setattr__()" but for attribute deletion instead of\n assignment. This should only be implemented if "del obj.name" is\n meaningful for the object.\n\nobject.__dir__(self)\n\n Called when "dir()" is called on the object. A sequence must be\n returned. "dir()" converts the returned sequence to a list and\n sorts it.\n\n\nImplementing Descriptors\n========================\n\nThe following methods only apply when an instance of the class\ncontaining the method (a so-called *descriptor* class) appears in an\n*owner* class (the descriptor must be in either the owner\'s class\ndictionary or in the class dictionary for one of its parents). In the\nexamples below, "the attribute" refers to the attribute whose name is\nthe key of the property in the owner class\' "__dict__".\n\nobject.__get__(self, instance, owner)\n\n Called to get the attribute of the owner class (class attribute\n access) or of an instance of that class (instance attribute\n access). *owner* is always the owner class, while *instance* is the\n instance that the attribute was accessed through, or "None" when\n the attribute is accessed through the *owner*. This method should\n return the (computed) attribute value or raise an "AttributeError"\n exception.\n\nobject.__set__(self, instance, value)\n\n Called to set the attribute on an instance *instance* of the owner\n class to a new value, *value*.\n\nobject.__delete__(self, instance)\n\n Called to delete the attribute on an instance *instance* of the\n owner class.\n\nThe attribute "__objclass__" is interpreted by the "inspect" module as\nspecifying the class where this object was defined (setting this\nappropriately can assist in runtime introspection of dynamic class\nattributes). For callables, it may indicate that an instance of the\ngiven type (or a subclass) is expected or required as the first\npositional argument (for example, CPython sets this attribute for\nunbound methods that are implemented in C).\n\n\nInvoking Descriptors\n====================\n\nIn general, a descriptor is an object attribute with "binding\nbehavior", one whose attribute access has been overridden by methods\nin the descriptor protocol: "__get__()", "__set__()", and\n"__delete__()". If any of those methods are defined for an object, it\nis said to be a descriptor.\n\nThe default behavior for attribute access is to get, set, or delete\nthe attribute from an object\'s dictionary. For instance, "a.x" has a\nlookup chain starting with "a.__dict__[\'x\']", then\n"type(a).__dict__[\'x\']", and continuing through the base classes of\n"type(a)" excluding metaclasses.\n\nHowever, if the looked-up value is an object defining one of the\ndescriptor methods, then Python may override the default behavior and\ninvoke the descriptor method instead. Where this occurs in the\nprecedence chain depends on which descriptor methods were defined and\nhow they were called.\n\nThe starting point for descriptor invocation is a binding, "a.x". How\nthe arguments are assembled depends on "a":\n\nDirect Call\n The simplest and least common call is when user code directly\n invokes a descriptor method: "x.__get__(a)".\n\nInstance Binding\n If binding to an object instance, "a.x" is transformed into the\n call: "type(a).__dict__[\'x\'].__get__(a, type(a))".\n\nClass Binding\n If binding to a class, "A.x" is transformed into the call:\n "A.__dict__[\'x\'].__get__(None, A)".\n\nSuper Binding\n If "a" is an instance of "super", then the binding "super(B,\n obj).m()" searches "obj.__class__.__mro__" for the base class "A"\n immediately preceding "B" and then invokes the descriptor with the\n call: "A.__dict__[\'m\'].__get__(obj, obj.__class__)".\n\nFor instance bindings, the precedence of descriptor invocation depends\non the which descriptor methods are defined. A descriptor can define\nany combination of "__get__()", "__set__()" and "__delete__()". If it\ndoes not define "__get__()", then accessing the attribute will return\nthe descriptor object itself unless there is a value in the object\'s\ninstance dictionary. If the descriptor defines "__set__()" and/or\n"__delete__()", it is a data descriptor; if it defines neither, it is\na non-data descriptor. Normally, data descriptors define both\n"__get__()" and "__set__()", while non-data descriptors have just the\n"__get__()" method. Data descriptors with "__set__()" and "__get__()"\ndefined always override a redefinition in an instance dictionary. In\ncontrast, non-data descriptors can be overridden by instances.\n\nPython methods (including "staticmethod()" and "classmethod()") are\nimplemented as non-data descriptors. Accordingly, instances can\nredefine and override methods. This allows individual instances to\nacquire behaviors that differ from other instances of the same class.\n\nThe "property()" function is implemented as a data descriptor.\nAccordingly, instances cannot override the behavior of a property.\n\n\n__slots__\n=========\n\nBy default, instances of classes have a dictionary for attribute\nstorage. This wastes space for objects having very few instance\nvariables. The space consumption can become acute when creating large\nnumbers of instances.\n\nThe default can be overridden by defining *__slots__* in a class\ndefinition. The *__slots__* declaration takes a sequence of instance\nvariables and reserves just enough space in each instance to hold a\nvalue for each variable. Space is saved because *__dict__* is not\ncreated for each instance.\n\nobject.__slots__\n\n This class variable can be assigned a string, iterable, or sequence\n of strings with variable names used by instances. *__slots__*\n reserves space for the declared variables and prevents the\n automatic creation of *__dict__* and *__weakref__* for each\n instance.\n\n\nNotes on using *__slots__*\n--------------------------\n\n* When inheriting from a class without *__slots__*, the *__dict__*\n attribute of that class will always be accessible, so a *__slots__*\n definition in the subclass is meaningless.\n\n* Without a *__dict__* variable, instances cannot be assigned new\n variables not listed in the *__slots__* definition. Attempts to\n assign to an unlisted variable name raises "AttributeError". If\n dynamic assignment of new variables is desired, then add\n "\'__dict__\'" to the sequence of strings in the *__slots__*\n declaration.\n\n* Without a *__weakref__* variable for each instance, classes\n defining *__slots__* do not support weak references to its\n instances. If weak reference support is needed, then add\n "\'__weakref__\'" to the sequence of strings in the *__slots__*\n declaration.\n\n* *__slots__* are implemented at the class level by creating\n descriptors (*Implementing Descriptors*) for each variable name. As\n a result, class attributes cannot be used to set default values for\n instance variables defined by *__slots__*; otherwise, the class\n attribute would overwrite the descriptor assignment.\n\n* The action of a *__slots__* declaration is limited to the class\n where it is defined. As a result, subclasses will have a *__dict__*\n unless they also define *__slots__* (which must only contain names\n of any *additional* slots).\n\n* If a class defines a slot also defined in a base class, the\n instance variable defined by the base class slot is inaccessible\n (except by retrieving its descriptor directly from the base class).\n This renders the meaning of the program undefined. In the future, a\n check may be added to prevent this.\n\n* Nonempty *__slots__* does not work for classes derived from\n "variable-length" built-in types such as "int", "bytes" and "tuple".\n\n* Any non-string iterable may be assigned to *__slots__*. Mappings\n may also be used; however, in the future, special meaning may be\n assigned to the values corresponding to each key.\n\n* *__class__* assignment works only if both classes have the same\n *__slots__*.\n', 'attribute-references': u'\nAttribute references\n********************\n\nAn attribute reference is a primary followed by a period and a name:\n\n attributeref ::= primary "." identifier\n\nThe primary must evaluate to an object of a type that supports\nattribute references, which most objects do. This object is then\nasked to produce the attribute whose name is the identifier. This\nproduction can be customized by overriding the "__getattr__()" method.\nIf this attribute is not available, the exception "AttributeError" is\nraised. Otherwise, the type and value of the object produced is\ndetermined by the object. Multiple evaluations of the same attribute\nreference may yield different objects.\n', - 'augassign': u'\nAugmented assignment statements\n*******************************\n\nAugmented assignment is the combination, in a single statement, of a\nbinary operation and an assignment statement:\n\n augmented_assignment_stmt ::= augtarget augop (expression_list | yield_expression)\n augtarget ::= identifier | attributeref | subscription | slicing\n augop ::= "+=" | "-=" | "*=" | "/=" | "//=" | "%=" | "**="\n | ">>=" | "<<=" | "&=" | "^=" | "|="\n\n(See section *Primaries* for the syntax definitions of the last three\nsymbols.)\n\nAn augmented assignment evaluates the target (which, unlike normal\nassignment statements, cannot be an unpacking) and the expression\nlist, performs the binary operation specific to the type of assignment\non the two operands, and assigns the result to the original target.\nThe target is only evaluated once.\n\nAn augmented assignment expression like "x += 1" can be rewritten as\n"x = x + 1" to achieve a similar, but not exactly equal effect. In the\naugmented version, "x" is only evaluated once. Also, when possible,\nthe actual operation is performed *in-place*, meaning that rather than\ncreating a new object and assigning that to the target, the old object\nis modified instead.\n\nUnlike normal assignments, augmented assignments evaluate the left-\nhand side *before* evaluating the right-hand side. For example, "a[i]\n+= f(x)" first looks-up "a[i]", then it evaluates "f(x)" and performs\nthe addition, and lastly, it writes the result back to "a[i]".\n\nWith the exception of assigning to tuples and multiple targets in a\nsingle statement, the assignment done by augmented assignment\nstatements is handled the same way as normal assignments. Similarly,\nwith the exception of the possible *in-place* behavior, the binary\noperation performed by augmented assignment is the same as the normal\nbinary operations.\n\nFor targets which are attribute references, the same *caveat about\nclass and instance attributes* applies as for regular assignments.\n', - 'binary': u'\nBinary arithmetic operations\n****************************\n\nThe binary arithmetic operations have the conventional priority\nlevels. Note that some of these operations also apply to certain non-\nnumeric types. Apart from the power operator, there are only two\nlevels, one for multiplicative operators and one for additive\noperators:\n\n m_expr ::= u_expr | m_expr "*" u_expr | m_expr "//" u_expr | m_expr "/" u_expr\n | m_expr "%" u_expr\n a_expr ::= m_expr | a_expr "+" m_expr | a_expr "-" m_expr\n\nThe "*" (multiplication) operator yields the product of its arguments.\nThe arguments must either both be numbers, or one argument must be an\ninteger and the other must be a sequence. In the former case, the\nnumbers are converted to a common type and then multiplied together.\nIn the latter case, sequence repetition is performed; a negative\nrepetition factor yields an empty sequence.\n\nThe "/" (division) and "//" (floor division) operators yield the\nquotient of their arguments. The numeric arguments are first\nconverted to a common type. Division of integers yields a float, while\nfloor division of integers results in an integer; the result is that\nof mathematical division with the \'floor\' function applied to the\nresult. Division by zero raises the "ZeroDivisionError" exception.\n\nThe "%" (modulo) operator yields the remainder from the division of\nthe first argument by the second. The numeric arguments are first\nconverted to a common type. A zero right argument raises the\n"ZeroDivisionError" exception. The arguments may be floating point\nnumbers, e.g., "3.14%0.7" equals "0.34" (since "3.14" equals "4*0.7 +\n0.34".) The modulo operator always yields a result with the same sign\nas its second operand (or zero); the absolute value of the result is\nstrictly smaller than the absolute value of the second operand [1].\n\nThe floor division and modulo operators are connected by the following\nidentity: "x == (x//y)*y + (x%y)". Floor division and modulo are also\nconnected with the built-in function "divmod()": "divmod(x, y) ==\n(x//y, x%y)". [2].\n\nIn addition to performing the modulo operation on numbers, the "%"\noperator is also overloaded by string objects to perform old-style\nstring formatting (also known as interpolation). The syntax for\nstring formatting is described in the Python Library Reference,\nsection *printf-style String Formatting*.\n\nThe floor division operator, the modulo operator, and the "divmod()"\nfunction are not defined for complex numbers. Instead, convert to a\nfloating point number using the "abs()" function if appropriate.\n\nThe "+" (addition) operator yields the sum of its arguments. The\narguments must either both be numbers or both be sequences of the same\ntype. In the former case, the numbers are converted to a common type\nand then added together. In the latter case, the sequences are\nconcatenated.\n\nThe "-" (subtraction) operator yields the difference of its arguments.\nThe numeric arguments are first converted to a common type.\n', + 'augassign': u'\nAugmented assignment statements\n*******************************\n\nAugmented assignment is the combination, in a single statement, of a\nbinary operation and an assignment statement:\n\n augmented_assignment_stmt ::= augtarget augop (expression_list | yield_expression)\n augtarget ::= identifier | attributeref | subscription | slicing\n augop ::= "+=" | "-=" | "*=" | "@=" | "/=" | "//=" | "%=" | "**="\n | ">>=" | "<<=" | "&=" | "^=" | "|="\n\n(See section *Primaries* for the syntax definitions of the last three\nsymbols.)\n\nAn augmented assignment evaluates the target (which, unlike normal\nassignment statements, cannot be an unpacking) and the expression\nlist, performs the binary operation specific to the type of assignment\non the two operands, and assigns the result to the original target.\nThe target is only evaluated once.\n\nAn augmented assignment expression like "x += 1" can be rewritten as\n"x = x + 1" to achieve a similar, but not exactly equal effect. In the\naugmented version, "x" is only evaluated once. Also, when possible,\nthe actual operation is performed *in-place*, meaning that rather than\ncreating a new object and assigning that to the target, the old object\nis modified instead.\n\nUnlike normal assignments, augmented assignments evaluate the left-\nhand side *before* evaluating the right-hand side. For example, "a[i]\n+= f(x)" first looks-up "a[i]", then it evaluates "f(x)" and performs\nthe addition, and lastly, it writes the result back to "a[i]".\n\nWith the exception of assigning to tuples and multiple targets in a\nsingle statement, the assignment done by augmented assignment\nstatements is handled the same way as normal assignments. Similarly,\nwith the exception of the possible *in-place* behavior, the binary\noperation performed by augmented assignment is the same as the normal\nbinary operations.\n\nFor targets which are attribute references, the same *caveat about\nclass and instance attributes* applies as for regular assignments.\n', + 'binary': u'\nBinary arithmetic operations\n****************************\n\nThe binary arithmetic operations have the conventional priority\nlevels. Note that some of these operations also apply to certain non-\nnumeric types. Apart from the power operator, there are only two\nlevels, one for multiplicative operators and one for additive\noperators:\n\n m_expr ::= u_expr | m_expr "*" u_expr | m_expr "@" m_expr |\n m_expr "//" u_expr| m_expr "/" u_expr |\n m_expr "%" u_expr\n a_expr ::= m_expr | a_expr "+" m_expr | a_expr "-" m_expr\n\nThe "*" (multiplication) operator yields the product of its arguments.\nThe arguments must either both be numbers, or one argument must be an\ninteger and the other must be a sequence. In the former case, the\nnumbers are converted to a common type and then multiplied together.\nIn the latter case, sequence repetition is performed; a negative\nrepetition factor yields an empty sequence.\n\nThe "@" (at) operator is intended to be used for matrix\nmultiplication. No builtin Python types implement this operator.\n\nNew in version 3.5.\n\nThe "/" (division) and "//" (floor division) operators yield the\nquotient of their arguments. The numeric arguments are first\nconverted to a common type. Division of integers yields a float, while\nfloor division of integers results in an integer; the result is that\nof mathematical division with the \'floor\' function applied to the\nresult. Division by zero raises the "ZeroDivisionError" exception.\n\nThe "%" (modulo) operator yields the remainder from the division of\nthe first argument by the second. The numeric arguments are first\nconverted to a common type. A zero right argument raises the\n"ZeroDivisionError" exception. The arguments may be floating point\nnumbers, e.g., "3.14%0.7" equals "0.34" (since "3.14" equals "4*0.7 +\n0.34".) The modulo operator always yields a result with the same sign\nas its second operand (or zero); the absolute value of the result is\nstrictly smaller than the absolute value of the second operand [1].\n\nThe floor division and modulo operators are connected by the following\nidentity: "x == (x//y)*y + (x%y)". Floor division and modulo are also\nconnected with the built-in function "divmod()": "divmod(x, y) ==\n(x//y, x%y)". [2].\n\nIn addition to performing the modulo operation on numbers, the "%"\noperator is also overloaded by string objects to perform old-style\nstring formatting (also known as interpolation). The syntax for\nstring formatting is described in the Python Library Reference,\nsection *printf-style String Formatting*.\n\nThe floor division operator, the modulo operator, and the "divmod()"\nfunction are not defined for complex numbers. Instead, convert to a\nfloating point number using the "abs()" function if appropriate.\n\nThe "+" (addition) operator yields the sum of its arguments. The\narguments must either both be numbers or both be sequences of the same\ntype. In the former case, the numbers are converted to a common type\nand then added together. In the latter case, the sequences are\nconcatenated.\n\nThe "-" (subtraction) operator yields the difference of its arguments.\nThe numeric arguments are first converted to a common type.\n', 'bitwise': u'\nBinary bitwise operations\n*************************\n\nEach of the three bitwise operations has a different priority level:\n\n and_expr ::= shift_expr | and_expr "&" shift_expr\n xor_expr ::= and_expr | xor_expr "^" and_expr\n or_expr ::= xor_expr | or_expr "|" xor_expr\n\nThe "&" operator yields the bitwise AND of its arguments, which must\nbe integers.\n\nThe "^" operator yields the bitwise XOR (exclusive OR) of its\narguments, which must be integers.\n\nThe "|" operator yields the bitwise (inclusive) OR of its arguments,\nwhich must be integers.\n', 'bltin-code-objects': u'\nCode Objects\n************\n\nCode objects are used by the implementation to represent "pseudo-\ncompiled" executable Python code such as a function body. They differ\nfrom function objects because they don\'t contain a reference to their\nglobal execution environment. Code objects are returned by the built-\nin "compile()" function and can be extracted from function objects\nthrough their "__code__" attribute. See also the "code" module.\n\nA code object can be executed or evaluated by passing it (instead of a\nsource string) to the "exec()" or "eval()" built-in functions.\n\nSee *The standard type hierarchy* for more information.\n', 'bltin-ellipsis-object': u'\nThe Ellipsis Object\n*******************\n\nThis object is commonly used by slicing (see *Slicings*). It supports\nno special operations. There is exactly one ellipsis object, named\n"Ellipsis" (a built-in name). "type(Ellipsis)()" produces the\n"Ellipsis" singleton.\n\nIt is written as "Ellipsis" or "...".\n', @@ -49,9 +49,9 @@ topics = {'assert': u'\nThe "assert" statement\n**********************\n\nAssert 'naming': u'\nNaming and binding\n******************\n\n*Names* refer to objects. Names are introduced by name binding\noperations. Each occurrence of a name in the program text refers to\nthe *binding* of that name established in the innermost function block\ncontaining the use.\n\nA *block* is a piece of Python program text that is executed as a\nunit. The following are blocks: a module, a function body, and a class\ndefinition. Each command typed interactively is a block. A script\nfile (a file given as standard input to the interpreter or specified\nas a command line argument to the interpreter) is a code block. A\nscript command (a command specified on the interpreter command line\nwith the \'**-c**\' option) is a code block. The string argument passed\nto the built-in functions "eval()" and "exec()" is a code block.\n\nA code block is executed in an *execution frame*. A frame contains\nsome administrative information (used for debugging) and determines\nwhere and how execution continues after the code block\'s execution has\ncompleted.\n\nA *scope* defines the visibility of a name within a block. If a local\nvariable is defined in a block, its scope includes that block. If the\ndefinition occurs in a function block, the scope extends to any blocks\ncontained within the defining one, unless a contained block introduces\na different binding for the name. The scope of names defined in a\nclass block is limited to the class block; it does not extend to the\ncode blocks of methods -- this includes comprehensions and generator\nexpressions since they are implemented using a function scope. This\nmeans that the following will fail:\n\n class A:\n a = 42\n b = list(a + i for i in range(10))\n\nWhen a name is used in a code block, it is resolved using the nearest\nenclosing scope. The set of all such scopes visible to a code block\nis called the block\'s *environment*.\n\nIf a name is bound in a block, it is a local variable of that block,\nunless declared as "nonlocal". If a name is bound at the module\nlevel, it is a global variable. (The variables of the module code\nblock are local and global.) If a variable is used in a code block\nbut not defined there, it is a *free variable*.\n\nWhen a name is not found at all, a "NameError" exception is raised.\nIf the name refers to a local variable that has not been bound, an\n"UnboundLocalError" exception is raised. "UnboundLocalError" is a\nsubclass of "NameError".\n\nThe following constructs bind names: formal parameters to functions,\n"import" statements, class and function definitions (these bind the\nclass or function name in the defining block), and targets that are\nidentifiers if occurring in an assignment, "for" loop header, or after\n"as" in a "with" statement or "except" clause. The "import" statement\nof the form "from ... import *" binds all names defined in the\nimported module, except those beginning with an underscore. This form\nmay only be used at the module level.\n\nA target occurring in a "del" statement is also considered bound for\nthis purpose (though the actual semantics are to unbind the name).\n\nEach assignment or import statement occurs within a block defined by a\nclass or function definition or at the module level (the top-level\ncode block).\n\nIf a name binding operation occurs anywhere within a code block, all\nuses of the name within the block are treated as references to the\ncurrent block. This can lead to errors when a name is used within a\nblock before it is bound. This rule is subtle. Python lacks\ndeclarations and allows name binding operations to occur anywhere\nwithin a code block. The local variables of a code block can be\ndetermined by scanning the entire text of the block for name binding\noperations.\n\nIf the "global" statement occurs within a block, all uses of the name\nspecified in the statement refer to the binding of that name in the\ntop-level namespace. Names are resolved in the top-level namespace by\nsearching the global namespace, i.e. the namespace of the module\ncontaining the code block, and the builtins namespace, the namespace\nof the module "builtins". The global namespace is searched first. If\nthe name is not found there, the builtins namespace is searched. The\n"global" statement must precede all uses of the name.\n\nThe builtins namespace associated with the execution of a code block\nis actually found by looking up the name "__builtins__" in its global\nnamespace; this should be a dictionary or a module (in the latter case\nthe module\'s dictionary is used). By default, when in the "__main__"\nmodule, "__builtins__" is the built-in module "builtins"; when in any\nother module, "__builtins__" is an alias for the dictionary of the\n"builtins" module itself. "__builtins__" can be set to a user-created\ndictionary to create a weak form of restricted execution.\n\n**CPython implementation detail:** Users should not touch\n"__builtins__"; it is strictly an implementation detail. Users\nwanting to override values in the builtins namespace should "import"\nthe "builtins" module and modify its attributes appropriately.\n\nThe namespace for a module is automatically created the first time a\nmodule is imported. The main module for a script is always called\n"__main__".\n\nThe "global" statement has the same scope as a name binding operation\nin the same block. If the nearest enclosing scope for a free variable\ncontains a global statement, the free variable is treated as a global.\n\nA class definition is an executable statement that may use and define\nnames. These references follow the normal rules for name resolution.\nThe namespace of the class definition becomes the attribute dictionary\nof the class. Names defined at the class scope are not visible in\nmethods.\n\n\nInteraction with dynamic features\n=================================\n\nThere are several cases where Python statements are illegal when used\nin conjunction with nested scopes that contain free variables.\n\nIf a variable is referenced in an enclosing scope, it is illegal to\ndelete the name. An error will be reported at compile time.\n\nIf the wild card form of import --- "import *" --- is used in a\nfunction and the function contains or is a nested block with free\nvariables, the compiler will raise a "SyntaxError".\n\nThe "eval()" and "exec()" functions do not have access to the full\nenvironment for resolving names. Names may be resolved in the local\nand global namespaces of the caller. Free variables are not resolved\nin the nearest enclosing namespace, but in the global namespace. [1]\nThe "exec()" and "eval()" functions have optional arguments to\noverride the global and local namespace. If only one namespace is\nspecified, it is used for both.\n', 'nonlocal': u'\nThe "nonlocal" statement\n************************\n\n nonlocal_stmt ::= "nonlocal" identifier ("," identifier)*\n\nThe "nonlocal" statement causes the listed identifiers to refer to\npreviously bound variables in the nearest enclosing scope excluding\nglobals. This is important because the default behavior for binding is\nto search the local namespace first. The statement allows\nencapsulated code to rebind variables outside of the local scope\nbesides the global (module) scope.\n\nNames listed in a "nonlocal" statement, unlike those listed in a\n"global" statement, must refer to pre-existing bindings in an\nenclosing scope (the scope in which a new binding should be created\ncannot be determined unambiguously).\n\nNames listed in a "nonlocal" statement must not collide with pre-\nexisting bindings in the local scope.\n\nSee also: **PEP 3104** - Access to Names in Outer Scopes\n\n The specification for the "nonlocal" statement.\n', 'numbers': u'\nNumeric literals\n****************\n\nThere are three types of numeric literals: integers, floating point\nnumbers, and imaginary numbers. There are no complex literals\n(complex numbers can be formed by adding a real number and an\nimaginary number).\n\nNote that numeric literals do not include a sign; a phrase like "-1"\nis actually an expression composed of the unary operator \'"-"\' and the\nliteral "1".\n', - 'numeric-types': u'\nEmulating numeric types\n***********************\n\nThe following methods can be defined to emulate numeric objects.\nMethods corresponding to operations that are not supported by the\nparticular kind of number implemented (e.g., bitwise operations for\nnon-integral numbers) should be left undefined.\n\nobject.__add__(self, other)\nobject.__sub__(self, other)\nobject.__mul__(self, other)\nobject.__truediv__(self, other)\nobject.__floordiv__(self, other)\nobject.__mod__(self, other)\nobject.__divmod__(self, other)\nobject.__pow__(self, other[, modulo])\nobject.__lshift__(self, other)\nobject.__rshift__(self, other)\nobject.__and__(self, other)\nobject.__xor__(self, other)\nobject.__or__(self, other)\n\n These methods are called to implement the binary arithmetic\n operations ("+", "-", "*", "/", "//", "%", "divmod()", "pow()",\n "**", "<<", ">>", "&", "^", "|"). For instance, to evaluate the\n expression "x + y", where *x* is an instance of a class that has an\n "__add__()" method, "x.__add__(y)" is called. The "__divmod__()"\n method should be the equivalent to using "__floordiv__()" and\n "__mod__()"; it should not be related to "__truediv__()". Note\n that "__pow__()" should be defined to accept an optional third\n argument if the ternary version of the built-in "pow()" function is\n to be supported.\n\n If one of those methods does not support the operation with the\n supplied arguments, it should return "NotImplemented".\n\nobject.__radd__(self, other)\nobject.__rsub__(self, other)\nobject.__rmul__(self, other)\nobject.__rtruediv__(self, other)\nobject.__rfloordiv__(self, other)\nobject.__rmod__(self, other)\nobject.__rdivmod__(self, other)\nobject.__rpow__(self, other)\nobject.__rlshift__(self, other)\nobject.__rrshift__(self, other)\nobject.__rand__(self, other)\nobject.__rxor__(self, other)\nobject.__ror__(self, other)\n\n These methods are called to implement the binary arithmetic\n operations ("+", "-", "*", "/", "//", "%", "divmod()", "pow()",\n "**", "<<", ">>", "&", "^", "|") with reflected (swapped) operands.\n These functions are only called if the left operand does not\n support the corresponding operation and the operands are of\n different types. [2] For instance, to evaluate the expression "x -\n y", where *y* is an instance of a class that has an "__rsub__()"\n method, "y.__rsub__(x)" is called if "x.__sub__(y)" returns\n *NotImplemented*.\n\n Note that ternary "pow()" will not try calling "__rpow__()" (the\n coercion rules would become too complicated).\n\n Note: If the right operand\'s type is a subclass of the left\n operand\'s type and that subclass provides the reflected method\n for the operation, this method will be called before the left\n operand\'s non-reflected method. This behavior allows subclasses\n to override their ancestors\' operations.\n\nobject.__iadd__(self, other)\nobject.__isub__(self, other)\nobject.__imul__(self, other)\nobject.__itruediv__(self, other)\nobject.__ifloordiv__(self, other)\nobject.__imod__(self, other)\nobject.__ipow__(self, other[, modulo])\nobject.__ilshift__(self, other)\nobject.__irshift__(self, other)\nobject.__iand__(self, other)\nobject.__ixor__(self, other)\nobject.__ior__(self, other)\n\n These methods are called to implement the augmented arithmetic\n assignments ("+=", "-=", "*=", "/=", "//=", "%=", "**=", "<<=",\n ">>=", "&=", "^=", "|="). These methods should attempt to do the\n operation in-place (modifying *self*) and return the result (which\n could be, but does not have to be, *self*). If a specific method\n is not defined, the augmented assignment falls back to the normal\n methods. For instance, if *x* is an instance of a class with an\n "__iadd__()" method, "x += y" is equivalent to "x = x.__iadd__(y)"\n . Otherwise, "x.__add__(y)" and "y.__radd__(x)" are considered, as\n with the evaluation of "x + y". In certain situations, augmented\n assignment can result in unexpected errors (see *Why does\n a_tuple[i] += [\'item\'] raise an exception when the addition\n works?*), but this behavior is in fact part of the data model.\n\nobject.__neg__(self)\nobject.__pos__(self)\nobject.__abs__(self)\nobject.__invert__(self)\n\n Called to implement the unary arithmetic operations ("-", "+",\n "abs()" and "~").\n\nobject.__complex__(self)\nobject.__int__(self)\nobject.__float__(self)\nobject.__round__(self[, n])\n\n Called to implement the built-in functions "complex()", "int()",\n "float()" and "round()". Should return a value of the appropriate\n type.\n\nobject.__index__(self)\n\n Called to implement "operator.index()", and whenever Python needs\n to losslessly convert the numeric object to an integer object (such\n as in slicing, or in the built-in "bin()", "hex()" and "oct()"\n functions). Presence of this method indicates that the numeric\n object is an integer type. Must return an integer.\n\n Note: In order to have a coherent integer type class, when\n "__index__()" is defined "__int__()" should also be defined, and\n both should return the same value.\n', + 'numeric-types': u'\nEmulating numeric types\n***********************\n\nThe following methods can be defined to emulate numeric objects.\nMethods corresponding to operations that are not supported by the\nparticular kind of number implemented (e.g., bitwise operations for\nnon-integral numbers) should be left undefined.\n\nobject.__add__(self, other)\nobject.__sub__(self, other)\nobject.__mul__(self, other)\nobject.__matmul__(self, other)\nobject.__truediv__(self, other)\nobject.__floordiv__(self, other)\nobject.__mod__(self, other)\nobject.__divmod__(self, other)\nobject.__pow__(self, other[, modulo])\nobject.__lshift__(self, other)\nobject.__rshift__(self, other)\nobject.__and__(self, other)\nobject.__xor__(self, other)\nobject.__or__(self, other)\n\n These methods are called to implement the binary arithmetic\n operations ("+", "-", "*", "@", "/", "//", "%", "divmod()",\n "pow()", "**", "<<", ">>", "&", "^", "|"). For instance, to\n evaluate the expression "x + y", where *x* is an instance of a\n class that has an "__add__()" method, "x.__add__(y)" is called.\n The "__divmod__()" method should be the equivalent to using\n "__floordiv__()" and "__mod__()"; it should not be related to\n "__truediv__()". Note that "__pow__()" should be defined to accept\n an optional third argument if the ternary version of the built-in\n "pow()" function is to be supported.\n\n If one of those methods does not support the operation with the\n supplied arguments, it should return "NotImplemented".\n\nobject.__radd__(self, other)\nobject.__rsub__(self, other)\nobject.__rmul__(self, other)\nobject.__rmatmul__(self, other)\nobject.__rtruediv__(self, other)\nobject.__rfloordiv__(self, other)\nobject.__rmod__(self, other)\nobject.__rdivmod__(self, other)\nobject.__rpow__(self, other)\nobject.__rlshift__(self, other)\nobject.__rrshift__(self, other)\nobject.__rand__(self, other)\nobject.__rxor__(self, other)\nobject.__ror__(self, other)\n\n These methods are called to implement the binary arithmetic\n operations ("+", "-", "*", "@", "/", "//", "%", "divmod()",\n "pow()", "**", "<<", ">>", "&", "^", "|") with reflected (swapped)\n operands. These functions are only called if the left operand does\n not support the corresponding operation and the operands are of\n different types. [2] For instance, to evaluate the expression "x -\n y", where *y* is an instance of a class that has an "__rsub__()"\n method, "y.__rsub__(x)" is called if "x.__sub__(y)" returns\n *NotImplemented*.\n\n Note that ternary "pow()" will not try calling "__rpow__()" (the\n coercion rules would become too complicated).\n\n Note: If the right operand\'s type is a subclass of the left\n operand\'s type and that subclass provides the reflected method\n for the operation, this method will be called before the left\n operand\'s non-reflected method. This behavior allows subclasses\n to override their ancestors\' operations.\n\nobject.__iadd__(self, other)\nobject.__isub__(self, other)\nobject.__imul__(self, other)\nobject.__imatmul__(self, other)\nobject.__itruediv__(self, other)\nobject.__ifloordiv__(self, other)\nobject.__imod__(self, other)\nobject.__ipow__(self, other[, modulo])\nobject.__ilshift__(self, other)\nobject.__irshift__(self, other)\nobject.__iand__(self, other)\nobject.__ixor__(self, other)\nobject.__ior__(self, other)\n\n These methods are called to implement the augmented arithmetic\n assignments ("+=", "-=", "*=", "@=", "/=", "//=", "%=", "**=",\n "<<=", ">>=", "&=", "^=", "|="). These methods should attempt to\n do the operation in-place (modifying *self*) and return the result\n (which could be, but does not have to be, *self*). If a specific\n method is not defined, the augmented assignment falls back to the\n normal methods. For instance, if *x* is an instance of a class\n with an "__iadd__()" method, "x += y" is equivalent to "x =\n x.__iadd__(y)" . Otherwise, "x.__add__(y)" and "y.__radd__(x)" are\n considered, as with the evaluation of "x + y". In certain\n situations, augmented assignment can result in unexpected errors\n (see *Why does a_tuple[i] += [\'item\'] raise an exception when the\n addition works?*), but this behavior is in fact part of the data\n model.\n\nobject.__neg__(self)\nobject.__pos__(self)\nobject.__abs__(self)\nobject.__invert__(self)\n\n Called to implement the unary arithmetic operations ("-", "+",\n "abs()" and "~").\n\nobject.__complex__(self)\nobject.__int__(self)\nobject.__float__(self)\nobject.__round__(self[, n])\n\n Called to implement the built-in functions "complex()", "int()",\n "float()" and "round()". Should return a value of the appropriate\n type.\n\nobject.__index__(self)\n\n Called to implement "operator.index()", and whenever Python needs\n to losslessly convert the numeric object to an integer object (such\n as in slicing, or in the built-in "bin()", "hex()" and "oct()"\n functions). Presence of this method indicates that the numeric\n object is an integer type. Must return an integer.\n\n Note: In order to have a coherent integer type class, when\n "__index__()" is defined "__int__()" should also be defined, and\n both should return the same value.\n', 'objects': u'\nObjects, values and types\n*************************\n\n*Objects* are Python\'s abstraction for data. All data in a Python\nprogram is represented by objects or by relations between objects. (In\na sense, and in conformance to Von Neumann\'s model of a "stored\nprogram computer," code is also represented by objects.)\n\nEvery object has an identity, a type and a value. An object\'s\n*identity* never changes once it has been created; you may think of it\nas the object\'s address in memory. The \'"is"\' operator compares the\nidentity of two objects; the "id()" function returns an integer\nrepresenting its identity.\n\n**CPython implementation detail:** For CPython, "id(x)" is the memory\naddress where "x" is stored.\n\nAn object\'s type determines the operations that the object supports\n(e.g., "does it have a length?") and also defines the possible values\nfor objects of that type. The "type()" function returns an object\'s\ntype (which is an object itself). Like its identity, an object\'s\n*type* is also unchangeable. [1]\n\nThe *value* of some objects can change. Objects whose value can\nchange are said to be *mutable*; objects whose value is unchangeable\nonce they are created are called *immutable*. (The value of an\nimmutable container object that contains a reference to a mutable\nobject can change when the latter\'s value is changed; however the\ncontainer is still considered immutable, because the collection of\nobjects it contains cannot be changed. So, immutability is not\nstrictly the same as having an unchangeable value, it is more subtle.)\nAn object\'s mutability is determined by its type; for instance,\nnumbers, strings and tuples are immutable, while dictionaries and\nlists are mutable.\n\nObjects are never explicitly destroyed; however, when they become\nunreachable they may be garbage-collected. An implementation is\nallowed to postpone garbage collection or omit it altogether --- it is\na matter of implementation quality how garbage collection is\nimplemented, as long as no objects are collected that are still\nreachable.\n\n**CPython implementation detail:** CPython currently uses a reference-\ncounting scheme with (optional) delayed detection of cyclically linked\ngarbage, which collects most objects as soon as they become\nunreachable, but is not guaranteed to collect garbage containing\ncircular references. See the documentation of the "gc" module for\ninformation on controlling the collection of cyclic garbage. Other\nimplementations act differently and CPython may change. Do not depend\non immediate finalization of objects when they become unreachable (so\nyou should always close files explicitly).\n\nNote that the use of the implementation\'s tracing or debugging\nfacilities may keep objects alive that would normally be collectable.\nAlso note that catching an exception with a \'"try"..."except"\'\nstatement may keep objects alive.\n\nSome objects contain references to "external" resources such as open\nfiles or windows. It is understood that these resources are freed\nwhen the object is garbage-collected, but since garbage collection is\nnot guaranteed to happen, such objects also provide an explicit way to\nrelease the external resource, usually a "close()" method. Programs\nare strongly recommended to explicitly close such objects. The\n\'"try"..."finally"\' statement and the \'"with"\' statement provide\nconvenient ways to do this.\n\nSome objects contain references to other objects; these are called\n*containers*. Examples of containers are tuples, lists and\ndictionaries. The references are part of a container\'s value. In\nmost cases, when we talk about the value of a container, we imply the\nvalues, not the identities of the contained objects; however, when we\ntalk about the mutability of a container, only the identities of the\nimmediately contained objects are implied. So, if an immutable\ncontainer (like a tuple) contains a reference to a mutable object, its\nvalue changes if that mutable object is changed.\n\nTypes affect almost all aspects of object behavior. Even the\nimportance of object identity is affected in some sense: for immutable\ntypes, operations that compute new values may actually return a\nreference to any existing object with the same type and value, while\nfor mutable objects this is not allowed. E.g., after "a = 1; b = 1",\n"a" and "b" may or may not refer to the same object with the value\none, depending on the implementation, but after "c = []; d = []", "c"\nand "d" are guaranteed to refer to two different, unique, newly\ncreated empty lists. (Note that "c = d = []" assigns the same object\nto both "c" and "d".)\n', - 'operator-summary': u'\nOperator precedence\n*******************\n\nThe following table summarizes the operator precedence in Python, from\nlowest precedence (least binding) to highest precedence (most\nbinding). Operators in the same box have the same precedence. Unless\nthe syntax is explicitly given, operators are binary. Operators in\nthe same box group left to right (except for exponentiation, which\ngroups from right to left).\n\nNote that comparisons, membership tests, and identity tests, all have\nthe same precedence and have a left-to-right chaining feature as\ndescribed in the *Comparisons* section.\n\n+-------------------------------------------------+---------------------------------------+\n| Operator | Description |\n+=================================================+=======================================+\n| "lambda" | Lambda expression |\n+-------------------------------------------------+---------------------------------------+\n| "if" -- "else" | Conditional expression |\n+-------------------------------------------------+---------------------------------------+\n| "or" | Boolean OR |\n+-------------------------------------------------+---------------------------------------+\n| "and" | Boolean AND |\n+-------------------------------------------------+---------------------------------------+\n| "not" "x" | Boolean NOT |\n+-------------------------------------------------+---------------------------------------+\n| "in", "not in", "is", "is not", "<", "<=", ">", | Comparisons, including membership |\n| ">=", "!=", "==" | tests and identity tests |\n+-------------------------------------------------+---------------------------------------+\n| "|" | Bitwise OR |\n+-------------------------------------------------+---------------------------------------+\n| "^" | Bitwise XOR |\n+-------------------------------------------------+---------------------------------------+\n| "&" | Bitwise AND |\n+-------------------------------------------------+---------------------------------------+\n| "<<", ">>" | Shifts |\n+-------------------------------------------------+---------------------------------------+\n| "+", "-" | Addition and subtraction |\n+-------------------------------------------------+---------------------------------------+\n| "*", "/", "//", "%" | Multiplication, division, remainder |\n| | [5] |\n+-------------------------------------------------+---------------------------------------+\n| "+x", "-x", "~x" | Positive, negative, bitwise NOT |\n+-------------------------------------------------+---------------------------------------+\n| "**" | Exponentiation [6] |\n+-------------------------------------------------+---------------------------------------+\n| "x[index]", "x[index:index]", | Subscription, slicing, call, |\n| "x(arguments...)", "x.attribute" | attribute reference |\n+-------------------------------------------------+---------------------------------------+\n| "(expressions...)", "[expressions...]", "{key: | Binding or tuple display, list |\n| value...}", "{expressions...}" | display, dictionary display, set |\n| | display |\n+-------------------------------------------------+---------------------------------------+\n\n-[ Footnotes ]-\n\n[1] While "abs(x%y) < abs(y)" is true mathematically, for floats\n it may not be true numerically due to roundoff. For example, and\n assuming a platform on which a Python float is an IEEE 754 double-\n precision number, in order that "-1e-100 % 1e100" have the same\n sign as "1e100", the computed result is "-1e-100 + 1e100", which\n is numerically exactly equal to "1e100". The function\n "math.fmod()" returns a result whose sign matches the sign of the\n first argument instead, and so returns "-1e-100" in this case.\n Which approach is more appropriate depends on the application.\n\n[2] If x is very close to an exact integer multiple of y, it\'s\n possible for "x//y" to be one larger than "(x-x%y)//y" due to\n rounding. In such cases, Python returns the latter result, in\n order to preserve that "divmod(x,y)[0] * y + x % y" be very close\n to "x".\n\n[3] While comparisons between strings make sense at the byte\n level, they may be counter-intuitive to users. For example, the\n strings ""\\u00C7"" and ""\\u0327\\u0043"" compare differently, even\n though they both represent the same unicode character (LATIN\n CAPITAL LETTER C WITH CEDILLA). To compare strings in a human\n recognizable way, compare using "unicodedata.normalize()".\n\n[4] Due to automatic garbage-collection, free lists, and the\n dynamic nature of descriptors, you may notice seemingly unusual\n behaviour in certain uses of the "is" operator, like those\n involving comparisons between instance methods, or constants.\n Check their documentation for more info.\n\n[5] The "%" operator is also used for string formatting; the same\n precedence applies.\n\n[6] The power operator "**" binds less tightly than an arithmetic\n or bitwise unary operator on its right, that is, "2**-1" is "0.5".\n', + 'operator-summary': u'\nOperator precedence\n*******************\n\nThe following table summarizes the operator precedence in Python, from\nlowest precedence (least binding) to highest precedence (most\nbinding). Operators in the same box have the same precedence. Unless\nthe syntax is explicitly given, operators are binary. Operators in\nthe same box group left to right (except for exponentiation, which\ngroups from right to left).\n\nNote that comparisons, membership tests, and identity tests, all have\nthe same precedence and have a left-to-right chaining feature as\ndescribed in the *Comparisons* section.\n\n+-------------------------------------------------+---------------------------------------+\n| Operator | Description |\n+=================================================+=======================================+\n| "lambda" | Lambda expression |\n+-------------------------------------------------+---------------------------------------+\n| "if" -- "else" | Conditional expression |\n+-------------------------------------------------+---------------------------------------+\n| "or" | Boolean OR |\n+-------------------------------------------------+---------------------------------------+\n| "and" | Boolean AND |\n+-------------------------------------------------+---------------------------------------+\n| "not" "x" | Boolean NOT |\n+-------------------------------------------------+---------------------------------------+\n| "in", "not in", "is", "is not", "<", "<=", ">", | Comparisons, including membership |\n| ">=", "!=", "==" | tests and identity tests |\n+-------------------------------------------------+---------------------------------------+\n| "|" | Bitwise OR |\n+-------------------------------------------------+---------------------------------------+\n| "^" | Bitwise XOR |\n+-------------------------------------------------+---------------------------------------+\n| "&" | Bitwise AND |\n+-------------------------------------------------+---------------------------------------+\n| "<<", ">>" | Shifts |\n+-------------------------------------------------+---------------------------------------+\n| "+", "-" | Addition and subtraction |\n+-------------------------------------------------+---------------------------------------+\n| "*", "@", "/", "//", "%" | Multiplication, matrix multiplication |\n| | division, remainder [5] |\n+-------------------------------------------------+---------------------------------------+\n| "+x", "-x", "~x" | Positive, negative, bitwise NOT |\n+-------------------------------------------------+---------------------------------------+\n| "**" | Exponentiation [6] |\n+-------------------------------------------------+---------------------------------------+\n| "x[index]", "x[index:index]", | Subscription, slicing, call, |\n| "x(arguments...)", "x.attribute" | attribute reference |\n+-------------------------------------------------+---------------------------------------+\n| "(expressions...)", "[expressions...]", "{key: | Binding or tuple display, list |\n| value...}", "{expressions...}" | display, dictionary display, set |\n| | display |\n+-------------------------------------------------+---------------------------------------+\n\n-[ Footnotes ]-\n\n[1] While "abs(x%y) < abs(y)" is true mathematically, for floats\n it may not be true numerically due to roundoff. For example, and\n assuming a platform on which a Python float is an IEEE 754 double-\n precision number, in order that "-1e-100 % 1e100" have the same\n sign as "1e100", the computed result is "-1e-100 + 1e100", which\n is numerically exactly equal to "1e100". The function\n "math.fmod()" returns a result whose sign matches the sign of the\n first argument instead, and so returns "-1e-100" in this case.\n Which approach is more appropriate depends on the application.\n\n[2] If x is very close to an exact integer multiple of y, it\'s\n possible for "x//y" to be one larger than "(x-x%y)//y" due to\n rounding. In such cases, Python returns the latter result, in\n order to preserve that "divmod(x,y)[0] * y + x % y" be very close\n to "x".\n\n[3] While comparisons between strings make sense at the byte\n level, they may be counter-intuitive to users. For example, the\n strings ""\\u00C7"" and ""\\u0327\\u0043"" compare differently, even\n though they both represent the same unicode character (LATIN\n CAPITAL LETTER C WITH CEDILLA). To compare strings in a human\n recognizable way, compare using "unicodedata.normalize()".\n\n[4] Due to automatic garbage-collection, free lists, and the\n dynamic nature of descriptors, you may notice seemingly unusual\n behaviour in certain uses of the "is" operator, like those\n involving comparisons between instance methods, or constants.\n Check their documentation for more info.\n\n[5] The "%" operator is also used for string formatting; the same\n precedence applies.\n\n[6] The power operator "**" binds less tightly than an arithmetic\n or bitwise unary operator on its right, that is, "2**-1" is "0.5".\n', 'pass': u'\nThe "pass" statement\n********************\n\n pass_stmt ::= "pass"\n\n"pass" is a null operation --- when it is executed, nothing happens.\nIt is useful as a placeholder when a statement is required\nsyntactically, but no code needs to be executed, for example:\n\n def f(arg): pass # a function that does nothing (yet)\n\n class C: pass # a class with no methods (yet)\n', 'power': u'\nThe power operator\n******************\n\nThe power operator binds more tightly than unary operators on its\nleft; it binds less tightly than unary operators on its right. The\nsyntax is:\n\n power ::= primary ["**" u_expr]\n\nThus, in an unparenthesized sequence of power and unary operators, the\noperators are evaluated from right to left (this does not constrain\nthe evaluation order for the operands): "-1**2" results in "-1".\n\nThe power operator has the same semantics as the built-in "pow()"\nfunction, when called with two arguments: it yields its left argument\nraised to the power of its right argument. The numeric arguments are\nfirst converted to a common type, and the result is of that type.\n\nFor int operands, the result has the same type as the operands unless\nthe second argument is negative; in that case, all arguments are\nconverted to float and a float result is delivered. For example,\n"10**2" returns "100", but "10**-2" returns "0.01".\n\nRaising "0.0" to a negative power results in a "ZeroDivisionError".\nRaising a negative number to a fractional power results in a "complex"\nnumber. (In earlier versions it raised a "ValueError".)\n', 'raise': u'\nThe "raise" statement\n*********************\n\n raise_stmt ::= "raise" [expression ["from" expression]]\n\nIf no expressions are present, "raise" re-raises the last exception\nthat was active in the current scope. If no exception is active in\nthe current scope, a "RuntimeError" exception is raised indicating\nthat this is an error.\n\nOtherwise, "raise" evaluates the first expression as the exception\nobject. It must be either a subclass or an instance of\n"BaseException". If it is a class, the exception instance will be\nobtained when needed by instantiating the class with no arguments.\n\nThe *type* of the exception is the exception instance\'s class, the\n*value* is the instance itself.\n\nA traceback object is normally created automatically when an exception\nis raised and attached to it as the "__traceback__" attribute, which\nis writable. You can create an exception and set your own traceback in\none step using the "with_traceback()" exception method (which returns\nthe same exception instance, with its traceback set to its argument),\nlike so:\n\n raise Exception("foo occurred").with_traceback(tracebackobj)\n\nThe "from" clause is used for exception chaining: if given, the second\n*expression* must be another exception class or instance, which will\nthen be attached to the raised exception as the "__cause__" attribute\n(which is writable). If the raised exception is not handled, both\nexceptions will be printed:\n\n >>> try:\n ... print(1 / 0)\n ... except Exception as exc:\n ... raise RuntimeError("Something bad happened") from exc\n ...\n Traceback (most recent call last):\n File "<stdin>", line 2, in <module>\n ZeroDivisionError: int division or modulo by zero\n\n The above exception was the direct cause of the following exception:\n\n Traceback (most recent call last):\n File "<stdin>", line 4, in <module>\n RuntimeError: Something bad happened\n\nA similar mechanism works implicitly if an exception is raised inside\nan exception handler or a "finally" clause: the previous exception is\nthen attached as the new exception\'s "__context__" attribute:\n\n >>> try:\n ... print(1 / 0)\n ... except:\n ... raise RuntimeError("Something bad happened")\n ...\n Traceback (most recent call last):\n File "<stdin>", line 2, in <module>\n ZeroDivisionError: int division or modulo by zero\n\n During handling of the above exception, another exception occurred:\n\n Traceback (most recent call last):\n File "<stdin>", line 4, in <module>\n RuntimeError: Something bad happened\n\nAdditional information on exceptions can be found in section\n*Exceptions*, and information about handling exceptions is in section\n*The try statement*.\n', @@ -60,7 +60,7 @@ topics = {'assert': u'\nThe "assert" statement\n**********************\n\nAssert 'shifting': u'\nShifting operations\n*******************\n\nThe shifting operations have lower priority than the arithmetic\noperations:\n\n shift_expr ::= a_expr | shift_expr ( "<<" | ">>" ) a_expr\n\nThese operators accept integers as arguments. They shift the first\nargument to the left or right by the number of bits given by the\nsecond argument.\n\nA right shift by *n* bits is defined as floor division by "pow(2,n)".\nA left shift by *n* bits is defined as multiplication with "pow(2,n)".\n\nNote: In the current implementation, the right-hand operand is\n required to be at most "sys.maxsize". If the right-hand operand is\n larger than "sys.maxsize" an "OverflowError" exception is raised.\n', 'slicings': u'\nSlicings\n********\n\nA slicing selects a range of items in a sequence object (e.g., a\nstring, tuple or list). Slicings may be used as expressions or as\ntargets in assignment or "del" statements. The syntax for a slicing:\n\n slicing ::= primary "[" slice_list "]"\n slice_list ::= slice_item ("," slice_item)* [","]\n slice_item ::= expression | proper_slice\n proper_slice ::= [lower_bound] ":" [upper_bound] [ ":" [stride] ]\n lower_bound ::= expression\n upper_bound ::= expression\n stride ::= expression\n\nThere is ambiguity in the formal syntax here: anything that looks like\nan expression list also looks like a slice list, so any subscription\ncan be interpreted as a slicing. Rather than further complicating the\nsyntax, this is disambiguated by defining that in this case the\ninterpretation as a subscription takes priority over the\ninterpretation as a slicing (this is the case if the slice list\ncontains no proper slice).\n\nThe semantics for a slicing are as follows. The primary is indexed\n(using the same "__getitem__()" method as normal subscription) with a\nkey that is constructed from the slice list, as follows. If the slice\nlist contains at least one comma, the key is a tuple containing the\nconversion of the slice items; otherwise, the conversion of the lone\nslice item is the key. The conversion of a slice item that is an\nexpression is that expression. The conversion of a proper slice is a\nslice object (see section *The standard type hierarchy*) whose\n"start", "stop" and "step" attributes are the values of the\nexpressions given as lower bound, upper bound and stride,\nrespectively, substituting "None" for missing expressions.\n', 'specialattrs': u'\nSpecial Attributes\n******************\n\nThe implementation adds a few special read-only attributes to several\nobject types, where they are relevant. Some of these are not reported\nby the "dir()" built-in function.\n\nobject.__dict__\n\n A dictionary or other mapping object used to store an object\'s\n (writable) attributes.\n\ninstance.__class__\n\n The class to which a class instance belongs.\n\nclass.__bases__\n\n The tuple of base classes of a class object.\n\nclass.__name__\n\n The name of the class or type.\n\nclass.__qualname__\n\n The *qualified name* of the class or type.\n\n New in version 3.3.\n\nclass.__mro__\n\n This attribute is a tuple of classes that are considered when\n looking for base classes during method resolution.\n\nclass.mro()\n\n This method can be overridden by a metaclass to customize the\n method resolution order for its instances. It is called at class\n instantiation, and its result is stored in "__mro__".\n\nclass.__subclasses__()\n\n Each class keeps a list of weak references to its immediate\n subclasses. This method returns a list of all those references\n still alive. Example:\n\n >>> int.__subclasses__()\n [<class \'bool\'>]\n\n-[ Footnotes ]-\n\n[1] Additional information on these special methods may be found\n in the Python Reference Manual (*Basic customization*).\n\n[2] As a consequence, the list "[1, 2]" is considered equal to\n "[1.0, 2.0]", and similarly for tuples.\n\n[3] They must have since the parser can\'t tell the type of the\n operands.\n\n[4] Cased characters are those with general category property\n being one of "Lu" (Letter, uppercase), "Ll" (Letter, lowercase),\n or "Lt" (Letter, titlecase).\n\n[5] To format only a tuple you should therefore provide a\n singleton tuple whose only element is the tuple to be formatted.\n', - 'specialnames': u'\nSpecial method names\n********************\n\nA class can implement certain operations that are invoked by special\nsyntax (such as arithmetic operations or subscripting and slicing) by\ndefining methods with special names. This is Python\'s approach to\n*operator overloading*, allowing classes to define their own behavior\nwith respect to language operators. For instance, if a class defines\na method named "__getitem__()", and "x" is an instance of this class,\nthen "x[i]" is roughly equivalent to "type(x).__getitem__(x, i)".\nExcept where mentioned, attempts to execute an operation raise an\nexception when no appropriate method is defined (typically\n"AttributeError" or "TypeError").\n\nWhen implementing a class that emulates any built-in type, it is\nimportant that the emulation only be implemented to the degree that it\nmakes sense for the object being modelled. For example, some\nsequences may work well with retrieval of individual elements, but\nextracting a slice may not make sense. (One example of this is the\n"NodeList" interface in the W3C\'s Document Object Model.)\n\n\nBasic customization\n===================\n\nobject.__new__(cls[, ...])\n\n Called to create a new instance of class *cls*. "__new__()" is a\n static method (special-cased so you need not declare it as such)\n that takes the class of which an instance was requested as its\n first argument. The remaining arguments are those passed to the\n object constructor expression (the call to the class). The return\n value of "__new__()" should be the new object instance (usually an\n instance of *cls*).\n\n Typical implementations create a new instance of the class by\n invoking the superclass\'s "__new__()" method using\n "super(currentclass, cls).__new__(cls[, ...])" with appropriate\n arguments and then modifying the newly-created instance as\n necessary before returning it.\n\n If "__new__()" returns an instance of *cls*, then the new\n instance\'s "__init__()" method will be invoked like\n "__init__(self[, ...])", where *self* is the new instance and the\n remaining arguments are the same as were passed to "__new__()".\n\n If "__new__()" does not return an instance of *cls*, then the new\n instance\'s "__init__()" method will not be invoked.\n\n "__new__()" is intended mainly to allow subclasses of immutable\n types (like int, str, or tuple) to customize instance creation. It\n is also commonly overridden in custom metaclasses in order to\n customize class creation.\n\nobject.__init__(self[, ...])\n\n Called after the instance has been created (by "__new__()"), but\n before it is returned to the caller. The arguments are those\n passed to the class constructor expression. If a base class has an\n "__init__()" method, the derived class\'s "__init__()" method, if\n any, must explicitly call it to ensure proper initialization of the\n base class part of the instance; for example:\n "BaseClass.__init__(self, [args...])".\n\n Because "__new__()" and "__init__()" work together in constructing\n objects ("__new__()" to create it, and "__init__()" to customise\n it), no non-"None" value may be returned by "__init__()"; doing so\n will cause a "TypeError" to be raised at runtime.\n\nobject.__del__(self)\n\n Called when the instance is about to be destroyed. This is also\n called a destructor. If a base class has a "__del__()" method, the\n derived class\'s "__del__()" method, if any, must explicitly call it\n to ensure proper deletion of the base class part of the instance.\n Note that it is possible (though not recommended!) for the\n "__del__()" method to postpone destruction of the instance by\n creating a new reference to it. It may then be called at a later\n time when this new reference is deleted. It is not guaranteed that\n "__del__()" methods are called for objects that still exist when\n the interpreter exits.\n\n Note: "del x" doesn\'t directly call "x.__del__()" --- the former\n decrements the reference count for "x" by one, and the latter is\n only called when "x"\'s reference count reaches zero. Some common\n situations that may prevent the reference count of an object from\n going to zero include: circular references between objects (e.g.,\n a doubly-linked list or a tree data structure with parent and\n child pointers); a reference to the object on the stack frame of\n a function that caught an exception (the traceback stored in\n "sys.exc_info()[2]" keeps the stack frame alive); or a reference\n to the object on the stack frame that raised an unhandled\n exception in interactive mode (the traceback stored in\n "sys.last_traceback" keeps the stack frame alive). The first\n situation can only be remedied by explicitly breaking the cycles;\n the second can be resolved by freeing the reference to the\n traceback object when it is no longer useful, and the third can\n be resolved by storing "None" in "sys.last_traceback". Circular\n references which are garbage are detected and cleaned up when the\n cyclic garbage collector is enabled (it\'s on by default). Refer\n to the documentation for the "gc" module for more information\n about this topic.\n\n Warning: Due to the precarious circumstances under which\n "__del__()" methods are invoked, exceptions that occur during\n their execution are ignored, and a warning is printed to\n "sys.stderr" instead. Also, when "__del__()" is invoked in\n response to a module being deleted (e.g., when execution of the\n program is done), other globals referenced by the "__del__()"\n method may already have been deleted or in the process of being\n torn down (e.g. the import machinery shutting down). For this\n reason, "__del__()" methods should do the absolute minimum needed\n to maintain external invariants. Starting with version 1.5,\n Python guarantees that globals whose name begins with a single\n underscore are deleted from their module before other globals are\n deleted; if no other references to such globals exist, this may\n help in assuring that imported modules are still available at the\n time when the "__del__()" method is called.\n\nobject.__repr__(self)\n\n Called by the "repr()" built-in function to compute the "official"\n string representation of an object. If at all possible, this\n should look like a valid Python expression that could be used to\n recreate an object with the same value (given an appropriate\n environment). If this is not possible, a string of the form\n "<...some useful description...>" should be returned. The return\n value must be a string object. If a class defines "__repr__()" but\n not "__str__()", then "__repr__()" is also used when an "informal"\n string representation of instances of that class is required.\n\n This is typically used for debugging, so it is important that the\n representation is information-rich and unambiguous.\n\nobject.__str__(self)\n\n Called by "str(object)" and the built-in functions "format()" and\n "print()" to compute the "informal" or nicely printable string\n representation of an object. The return value must be a *string*\n object.\n\n This method differs from "object.__repr__()" in that there is no\n expectation that "__str__()" return a valid Python expression: a\n more convenient or concise representation can be used.\n\n The default implementation defined by the built-in type "object"\n calls "object.__repr__()".\n\nobject.__bytes__(self)\n\n Called by "bytes()" to compute a byte-string representation of an\n object. This should return a "bytes" object.\n\nobject.__format__(self, format_spec)\n\n Called by the "format()" built-in function (and by extension, the\n "str.format()" method of class "str") to produce a "formatted"\n string representation of an object. The "format_spec" argument is a\n string that contains a description of the formatting options\n desired. The interpretation of the "format_spec" argument is up to\n the type implementing "__format__()", however most classes will\n either delegate formatting to one of the built-in types, or use a\n similar formatting option syntax.\n\n See *Format Specification Mini-Language* for a description of the\n standard formatting syntax.\n\n The return value must be a string object.\n\n Changed in version 3.4: The __format__ method of "object" itself\n raises a "TypeError" if passed any non-empty string.\n\nobject.__lt__(self, other)\nobject.__le__(self, other)\nobject.__eq__(self, other)\nobject.__ne__(self, other)\nobject.__gt__(self, other)\nobject.__ge__(self, other)\n\n These are the so-called "rich comparison" methods. The\n correspondence between operator symbols and method names is as\n follows: "x<y" calls "x.__lt__(y)", "x<=y" calls "x.__le__(y)",\n "x==y" calls "x.__eq__(y)", "x!=y" calls "x.__ne__(y)", "x>y" calls\n "x.__gt__(y)", and "x>=y" calls "x.__ge__(y)".\n\n A rich comparison method may return the singleton "NotImplemented"\n if it does not implement the operation for a given pair of\n arguments. By convention, "False" and "True" are returned for a\n successful comparison. However, these methods can return any value,\n so if the comparison operator is used in a Boolean context (e.g.,\n in the condition of an "if" statement), Python will call "bool()"\n on the value to determine if the result is true or false.\n\n There are no implied relationships among the comparison operators.\n The truth of "x==y" does not imply that "x!=y" is false.\n Accordingly, when defining "__eq__()", one should also define\n "__ne__()" so that the operators will behave as expected. See the\n paragraph on "__hash__()" for some important notes on creating\n *hashable* objects which support custom comparison operations and\n are usable as dictionary keys.\n\n There are no swapped-argument versions of these methods (to be used\n when the left argument does not support the operation but the right\n argument does); rather, "__lt__()" and "__gt__()" are each other\'s\n reflection, "__le__()" and "__ge__()" are each other\'s reflection,\n and "__eq__()" and "__ne__()" are their own reflection.\n\n Arguments to rich comparison methods are never coerced.\n\n To automatically generate ordering operations from a single root\n operation, see "functools.total_ordering()".\n\nobject.__hash__(self)\n\n Called by built-in function "hash()" and for operations on members\n of hashed collections including "set", "frozenset", and "dict".\n "__hash__()" should return an integer. The only required property\n is that objects which compare equal have the same hash value; it is\n advised to somehow mix together (e.g. using exclusive or) the hash\n values for the components of the object that also play a part in\n comparison of objects.\n\n Note: "hash()" truncates the value returned from an object\'s\n custom "__hash__()" method to the size of a "Py_ssize_t". This\n is typically 8 bytes on 64-bit builds and 4 bytes on 32-bit\n builds. If an object\'s "__hash__()" must interoperate on builds\n of different bit sizes, be sure to check the width on all\n supported builds. An easy way to do this is with "python -c\n "import sys; print(sys.hash_info.width)""\n\n If a class does not define an "__eq__()" method it should not\n define a "__hash__()" operation either; if it defines "__eq__()"\n but not "__hash__()", its instances will not be usable as items in\n hashable collections. If a class defines mutable objects and\n implements an "__eq__()" method, it should not implement\n "__hash__()", since the implementation of hashable collections\n requires that a key\'s hash value is immutable (if the object\'s hash\n value changes, it will be in the wrong hash bucket).\n\n User-defined classes have "__eq__()" and "__hash__()" methods by\n default; with them, all objects compare unequal (except with\n themselves) and "x.__hash__()" returns an appropriate value such\n that "x == y" implies both that "x is y" and "hash(x) == hash(y)".\n\n A class that overrides "__eq__()" and does not define "__hash__()"\n will have its "__hash__()" implicitly set to "None". When the\n "__hash__()" method of a class is "None", instances of the class\n will raise an appropriate "TypeError" when a program attempts to\n retrieve their hash value, and will also be correctly identified as\n unhashable when checking "isinstance(obj, collections.Hashable").\n\n If a class that overrides "__eq__()" needs to retain the\n implementation of "__hash__()" from a parent class, the interpreter\n must be told this explicitly by setting "__hash__ =\n <ParentClass>.__hash__".\n\n If a class that does not override "__eq__()" wishes to suppress\n hash support, it should include "__hash__ = None" in the class\n definition. A class which defines its own "__hash__()" that\n explicitly raises a "TypeError" would be incorrectly identified as\n hashable by an "isinstance(obj, collections.Hashable)" call.\n\n Note: By default, the "__hash__()" values of str, bytes and\n datetime objects are "salted" with an unpredictable random value.\n Although they remain constant within an individual Python\n process, they are not predictable between repeated invocations of\n Python.This is intended to provide protection against a denial-\n of-service caused by carefully-chosen inputs that exploit the\n worst case performance of a dict insertion, O(n^2) complexity.\n See http://www.ocert.org/advisories/ocert-2011-003.html for\n details.Changing hash values affects the iteration order of\n dicts, sets and other mappings. Python has never made guarantees\n about this ordering (and it typically varies between 32-bit and\n 64-bit builds).See also "PYTHONHASHSEED".\n\n Changed in version 3.3: Hash randomization is enabled by default.\n\nobject.__bool__(self)\n\n Called to implement truth value testing and the built-in operation\n "bool()"; should return "False" or "True". When this method is not\n defined, "__len__()" is called, if it is defined, and the object is\n considered true if its result is nonzero. If a class defines\n neither "__len__()" nor "__bool__()", all its instances are\n considered true.\n\n\nCustomizing attribute access\n============================\n\nThe following methods can be defined to customize the meaning of\nattribute access (use of, assignment to, or deletion of "x.name") for\nclass instances.\n\nobject.__getattr__(self, name)\n\n Called when an attribute lookup has not found the attribute in the\n usual places (i.e. it is not an instance attribute nor is it found\n in the class tree for "self"). "name" is the attribute name. This\n method should return the (computed) attribute value or raise an\n "AttributeError" exception.\n\n Note that if the attribute is found through the normal mechanism,\n "__getattr__()" is not called. (This is an intentional asymmetry\n between "__getattr__()" and "__setattr__()".) This is done both for\n efficiency reasons and because otherwise "__getattr__()" would have\n no way to access other attributes of the instance. Note that at\n least for instance variables, you can fake total control by not\n inserting any values in the instance attribute dictionary (but\n instead inserting them in another object). See the\n "__getattribute__()" method below for a way to actually get total\n control over attribute access.\n\nobject.__getattribute__(self, name)\n\n Called unconditionally to implement attribute accesses for\n instances of the class. If the class also defines "__getattr__()",\n the latter will not be called unless "__getattribute__()" either\n calls it explicitly or raises an "AttributeError". This method\n should return the (computed) attribute value or raise an\n "AttributeError" exception. In order to avoid infinite recursion in\n this method, its implementation should always call the base class\n method with the same name to access any attributes it needs, for\n example, "object.__getattribute__(self, name)".\n\n Note: This method may still be bypassed when looking up special\n methods as the result of implicit invocation via language syntax\n or built-in functions. See *Special method lookup*.\n\nobject.__setattr__(self, name, value)\n\n Called when an attribute assignment is attempted. This is called\n instead of the normal mechanism (i.e. store the value in the\n instance dictionary). *name* is the attribute name, *value* is the\n value to be assigned to it.\n\n If "__setattr__()" wants to assign to an instance attribute, it\n should call the base class method with the same name, for example,\n "object.__setattr__(self, name, value)".\n\nobject.__delattr__(self, name)\n\n Like "__setattr__()" but for attribute deletion instead of\n assignment. This should only be implemented if "del obj.name" is\n meaningful for the object.\n\nobject.__dir__(self)\n\n Called when "dir()" is called on the object. A sequence must be\n returned. "dir()" converts the returned sequence to a list and\n sorts it.\n\n\nImplementing Descriptors\n------------------------\n\nThe following methods only apply when an instance of the class\ncontaining the method (a so-called *descriptor* class) appears in an\n*owner* class (the descriptor must be in either the owner\'s class\ndictionary or in the class dictionary for one of its parents). In the\nexamples below, "the attribute" refers to the attribute whose name is\nthe key of the property in the owner class\' "__dict__".\n\nobject.__get__(self, instance, owner)\n\n Called to get the attribute of the owner class (class attribute\n access) or of an instance of that class (instance attribute\n access). *owner* is always the owner class, while *instance* is the\n instance that the attribute was accessed through, or "None" when\n the attribute is accessed through the *owner*. This method should\n return the (computed) attribute value or raise an "AttributeError"\n exception.\n\nobject.__set__(self, instance, value)\n\n Called to set the attribute on an instance *instance* of the owner\n class to a new value, *value*.\n\nobject.__delete__(self, instance)\n\n Called to delete the attribute on an instance *instance* of the\n owner class.\n\nThe attribute "__objclass__" is interpreted by the "inspect" module as\nspecifying the class where this object was defined (setting this\nappropriately can assist in runtime introspection of dynamic class\nattributes). For callables, it may indicate that an instance of the\ngiven type (or a subclass) is expected or required as the first\npositional argument (for example, CPython sets this attribute for\nunbound methods that are implemented in C).\n\n\nInvoking Descriptors\n--------------------\n\nIn general, a descriptor is an object attribute with "binding\nbehavior", one whose attribute access has been overridden by methods\nin the descriptor protocol: "__get__()", "__set__()", and\n"__delete__()". If any of those methods are defined for an object, it\nis said to be a descriptor.\n\nThe default behavior for attribute access is to get, set, or delete\nthe attribute from an object\'s dictionary. For instance, "a.x" has a\nlookup chain starting with "a.__dict__[\'x\']", then\n"type(a).__dict__[\'x\']", and continuing through the base classes of\n"type(a)" excluding metaclasses.\n\nHowever, if the looked-up value is an object defining one of the\ndescriptor methods, then Python may override the default behavior and\ninvoke the descriptor method instead. Where this occurs in the\nprecedence chain depends on which descriptor methods were defined and\nhow they were called.\n\nThe starting point for descriptor invocation is a binding, "a.x". How\nthe arguments are assembled depends on "a":\n\nDirect Call\n The simplest and least common call is when user code directly\n invokes a descriptor method: "x.__get__(a)".\n\nInstance Binding\n If binding to an object instance, "a.x" is transformed into the\n call: "type(a).__dict__[\'x\'].__get__(a, type(a))".\n\nClass Binding\n If binding to a class, "A.x" is transformed into the call:\n "A.__dict__[\'x\'].__get__(None, A)".\n\nSuper Binding\n If "a" is an instance of "super", then the binding "super(B,\n obj).m()" searches "obj.__class__.__mro__" for the base class "A"\n immediately preceding "B" and then invokes the descriptor with the\n call: "A.__dict__[\'m\'].__get__(obj, obj.__class__)".\n\nFor instance bindings, the precedence of descriptor invocation depends\non the which descriptor methods are defined. A descriptor can define\nany combination of "__get__()", "__set__()" and "__delete__()". If it\ndoes not define "__get__()", then accessing the attribute will return\nthe descriptor object itself unless there is a value in the object\'s\ninstance dictionary. If the descriptor defines "__set__()" and/or\n"__delete__()", it is a data descriptor; if it defines neither, it is\na non-data descriptor. Normally, data descriptors define both\n"__get__()" and "__set__()", while non-data descriptors have just the\n"__get__()" method. Data descriptors with "__set__()" and "__get__()"\ndefined always override a redefinition in an instance dictionary. In\ncontrast, non-data descriptors can be overridden by instances.\n\nPython methods (including "staticmethod()" and "classmethod()") are\nimplemented as non-data descriptors. Accordingly, instances can\nredefine and override methods. This allows individual instances to\nacquire behaviors that differ from other instances of the same class.\n\nThe "property()" function is implemented as a data descriptor.\nAccordingly, instances cannot override the behavior of a property.\n\n\n__slots__\n---------\n\nBy default, instances of classes have a dictionary for attribute\nstorage. This wastes space for objects having very few instance\nvariables. The space consumption can become acute when creating large\nnumbers of instances.\n\nThe default can be overridden by defining *__slots__* in a class\ndefinition. The *__slots__* declaration takes a sequence of instance\nvariables and reserves just enough space in each instance to hold a\nvalue for each variable. Space is saved because *__dict__* is not\ncreated for each instance.\n\nobject.__slots__\n\n This class variable can be assigned a string, iterable, or sequence\n of strings with variable names used by instances. *__slots__*\n reserves space for the declared variables and prevents the\n automatic creation of *__dict__* and *__weakref__* for each\n instance.\n\n\nNotes on using *__slots__*\n~~~~~~~~~~~~~~~~~~~~~~~~~~\n\n* When inheriting from a class without *__slots__*, the *__dict__*\n attribute of that class will always be accessible, so a *__slots__*\n definition in the subclass is meaningless.\n\n* Without a *__dict__* variable, instances cannot be assigned new\n variables not listed in the *__slots__* definition. Attempts to\n assign to an unlisted variable name raises "AttributeError". If\n dynamic assignment of new variables is desired, then add\n "\'__dict__\'" to the sequence of strings in the *__slots__*\n declaration.\n\n* Without a *__weakref__* variable for each instance, classes\n defining *__slots__* do not support weak references to its\n instances. If weak reference support is needed, then add\n "\'__weakref__\'" to the sequence of strings in the *__slots__*\n declaration.\n\n* *__slots__* are implemented at the class level by creating\n descriptors (*Implementing Descriptors*) for each variable name. As\n a result, class attributes cannot be used to set default values for\n instance variables defined by *__slots__*; otherwise, the class\n attribute would overwrite the descriptor assignment.\n\n* The action of a *__slots__* declaration is limited to the class\n where it is defined. As a result, subclasses will have a *__dict__*\n unless they also define *__slots__* (which must only contain names\n of any *additional* slots).\n\n* If a class defines a slot also defined in a base class, the\n instance variable defined by the base class slot is inaccessible\n (except by retrieving its descriptor directly from the base class).\n This renders the meaning of the program undefined. In the future, a\n check may be added to prevent this.\n\n* Nonempty *__slots__* does not work for classes derived from\n "variable-length" built-in types such as "int", "bytes" and "tuple".\n\n* Any non-string iterable may be assigned to *__slots__*. Mappings\n may also be used; however, in the future, special meaning may be\n assigned to the values corresponding to each key.\n\n* *__class__* assignment works only if both classes have the same\n *__slots__*.\n\n\nCustomizing class creation\n==========================\n\nBy default, classes are constructed using "type()". The class body is\nexecuted in a new namespace and the class name is bound locally to the\nresult of "type(name, bases, namespace)".\n\nThe class creation process can be customised by passing the\n"metaclass" keyword argument in the class definition line, or by\ninheriting from an existing class that included such an argument. In\nthe following example, both "MyClass" and "MySubclass" are instances\nof "Meta":\n\n class Meta(type):\n pass\n\n class MyClass(metaclass=Meta):\n pass\n\n class MySubclass(MyClass):\n pass\n\nAny other keyword arguments that are specified in the class definition\nare passed through to all metaclass operations described below.\n\nWhen a class definition is executed, the following steps occur:\n\n* the appropriate metaclass is determined\n\n* the class namespace is prepared\n\n* the class body is executed\n\n* the class object is created\n\n\nDetermining the appropriate metaclass\n-------------------------------------\n\nThe appropriate metaclass for a class definition is determined as\nfollows:\n\n* if no bases and no explicit metaclass are given, then "type()" is\n used\n\n* if an explicit metaclass is given and it is *not* an instance of\n "type()", then it is used directly as the metaclass\n\n* if an instance of "type()" is given as the explicit metaclass, or\n bases are defined, then the most derived metaclass is used\n\nThe most derived metaclass is selected from the explicitly specified\nmetaclass (if any) and the metaclasses (i.e. "type(cls)") of all\nspecified base classes. The most derived metaclass is one which is a\nsubtype of *all* of these candidate metaclasses. If none of the\ncandidate metaclasses meets that criterion, then the class definition\nwill fail with "TypeError".\n\n\nPreparing the class namespace\n-----------------------------\n\nOnce the appropriate metaclass has been identified, then the class\nnamespace is prepared. If the metaclass has a "__prepare__" attribute,\nit is called as "namespace = metaclass.__prepare__(name, bases,\n**kwds)" (where the additional keyword arguments, if any, come from\nthe class definition).\n\nIf the metaclass has no "__prepare__" attribute, then the class\nnamespace is initialised as an empty "dict()" instance.\n\nSee also: **PEP 3115** - Metaclasses in Python 3000\n\n Introduced the "__prepare__" namespace hook\n\n\nExecuting the class body\n------------------------\n\nThe class body is executed (approximately) as "exec(body, globals(),\nnamespace)". The key difference from a normal call to "exec()" is that\nlexical scoping allows the class body (including any methods) to\nreference names from the current and outer scopes when the class\ndefinition occurs inside a function.\n\nHowever, even when the class definition occurs inside the function,\nmethods defined inside the class still cannot see names defined at the\nclass scope. Class variables must be accessed through the first\nparameter of instance or class methods, and cannot be accessed at all\nfrom static methods.\n\n\nCreating the class object\n-------------------------\n\nOnce the class namespace has been populated by executing the class\nbody, the class object is created by calling "metaclass(name, bases,\nnamespace, **kwds)" (the additional keywords passed here are the same\nas those passed to "__prepare__").\n\nThis class object is the one that will be referenced by the zero-\nargument form of "super()". "__class__" is an implicit closure\nreference created by the compiler if any methods in a class body refer\nto either "__class__" or "super". This allows the zero argument form\nof "super()" to correctly identify the class being defined based on\nlexical scoping, while the class or instance that was used to make the\ncurrent call is identified based on the first argument passed to the\nmethod.\n\nAfter the class object is created, it is passed to the class\ndecorators included in the class definition (if any) and the resulting\nobject is bound in the local namespace as the defined class.\n\nSee also: **PEP 3135** - New super\n\n Describes the implicit "__class__" closure reference\n\n\nMetaclass example\n-----------------\n\nThe potential uses for metaclasses are boundless. Some ideas that have\nbeen explored include logging, interface checking, automatic\ndelegation, automatic property creation, proxies, frameworks, and\nautomatic resource locking/synchronization.\n\nHere is an example of a metaclass that uses an\n"collections.OrderedDict" to remember the order that class variables\nare defined:\n\n class OrderedClass(type):\n\n @classmethod\n def __prepare__(metacls, name, bases, **kwds):\n return collections.OrderedDict()\n\n def __new__(cls, name, bases, namespace, **kwds):\n result = type.__new__(cls, name, bases, dict(namespace))\n result.members = tuple(namespace)\n return result\n\n class A(metaclass=OrderedClass):\n def one(self): pass\n def two(self): pass\n def three(self): pass\n def four(self): pass\n\n >>> A.members\n (\'__module__\', \'one\', \'two\', \'three\', \'four\')\n\nWhen the class definition for *A* gets executed, the process begins\nwith calling the metaclass\'s "__prepare__()" method which returns an\nempty "collections.OrderedDict". That mapping records the methods and\nattributes of *A* as they are defined within the body of the class\nstatement. Once those definitions are executed, the ordered dictionary\nis fully populated and the metaclass\'s "__new__()" method gets\ninvoked. That method builds the new type and it saves the ordered\ndictionary keys in an attribute called "members".\n\n\nCustomizing instance and subclass checks\n========================================\n\nThe following methods are used to override the default behavior of the\n"isinstance()" and "issubclass()" built-in functions.\n\nIn particular, the metaclass "abc.ABCMeta" implements these methods in\norder to allow the addition of Abstract Base Classes (ABCs) as\n"virtual base classes" to any class or type (including built-in\ntypes), including other ABCs.\n\nclass.__instancecheck__(self, instance)\n\n Return true if *instance* should be considered a (direct or\n indirect) instance of *class*. If defined, called to implement\n "isinstance(instance, class)".\n\nclass.__subclasscheck__(self, subclass)\n\n Return true if *subclass* should be considered a (direct or\n indirect) subclass of *class*. If defined, called to implement\n "issubclass(subclass, class)".\n\nNote that these methods are looked up on the type (metaclass) of a\nclass. They cannot be defined as class methods in the actual class.\nThis is consistent with the lookup of special methods that are called\non instances, only in this case the instance is itself a class.\n\nSee also: **PEP 3119** - Introducing Abstract Base Classes\n\n Includes the specification for customizing "isinstance()" and\n "issubclass()" behavior through "__instancecheck__()" and\n "__subclasscheck__()", with motivation for this functionality in\n the context of adding Abstract Base Classes (see the "abc"\n module) to the language.\n\n\nEmulating callable objects\n==========================\n\nobject.__call__(self[, args...])\n\n Called when the instance is "called" as a function; if this method\n is defined, "x(arg1, arg2, ...)" is a shorthand for\n "x.__call__(arg1, arg2, ...)".\n\n\nEmulating container types\n=========================\n\nThe following methods can be defined to implement container objects.\nContainers usually are sequences (such as lists or tuples) or mappings\n(like dictionaries), but can represent other containers as well. The\nfirst set of methods is used either to emulate a sequence or to\nemulate a mapping; the difference is that for a sequence, the\nallowable keys should be the integers *k* for which "0 <= k < N" where\n*N* is the length of the sequence, or slice objects, which define a\nrange of items. It is also recommended that mappings provide the\nmethods "keys()", "values()", "items()", "get()", "clear()",\n"setdefault()", "pop()", "popitem()", "copy()", and "update()"\nbehaving similar to those for Python\'s standard dictionary objects.\nThe "collections" module provides a "MutableMapping" abstract base\nclass to help create those methods from a base set of "__getitem__()",\n"__setitem__()", "__delitem__()", and "keys()". Mutable sequences\nshould provide methods "append()", "count()", "index()", "extend()",\n"insert()", "pop()", "remove()", "reverse()" and "sort()", like Python\nstandard list objects. Finally, sequence types should implement\naddition (meaning concatenation) and multiplication (meaning\nrepetition) by defining the methods "__add__()", "__radd__()",\n"__iadd__()", "__mul__()", "__rmul__()" and "__imul__()" described\nbelow; they should not define other numerical operators. It is\nrecommended that both mappings and sequences implement the\n"__contains__()" method to allow efficient use of the "in" operator;\nfor mappings, "in" should search the mapping\'s keys; for sequences, it\nshould search through the values. It is further recommended that both\nmappings and sequences implement the "__iter__()" method to allow\nefficient iteration through the container; for mappings, "__iter__()"\nshould be the same as "keys()"; for sequences, it should iterate\nthrough the values.\n\nobject.__len__(self)\n\n Called to implement the built-in function "len()". Should return\n the length of the object, an integer ">=" 0. Also, an object that\n doesn\'t define a "__bool__()" method and whose "__len__()" method\n returns zero is considered to be false in a Boolean context.\n\nobject.__length_hint__(self)\n\n Called to implement "operator.length_hint()". Should return an\n estimated length for the object (which may be greater or less than\n the actual length). The length must be an integer ">=" 0. This\n method is purely an optimization and is never required for\n correctness.\n\n New in version 3.4.\n\nNote: Slicing is done exclusively with the following three methods.\n A call like\n\n a[1:2] = b\n\n is translated to\n\n a[slice(1, 2, None)] = b\n\n and so forth. Missing slice items are always filled in with "None".\n\nobject.__getitem__(self, key)\n\n Called to implement evaluation of "self[key]". For sequence types,\n the accepted keys should be integers and slice objects. Note that\n the special interpretation of negative indexes (if the class wishes\n to emulate a sequence type) is up to the "__getitem__()" method. If\n *key* is of an inappropriate type, "TypeError" may be raised; if of\n a value outside the set of indexes for the sequence (after any\n special interpretation of negative values), "IndexError" should be\n raised. For mapping types, if *key* is missing (not in the\n container), "KeyError" should be raised.\n\n Note: "for" loops expect that an "IndexError" will be raised for\n illegal indexes to allow proper detection of the end of the\n sequence.\n\nobject.__missing__(self, key)\n\n Called by "dict"."__getitem__()" to implement "self[key]" for dict\n subclasses when key is not in the dictionary.\n\nobject.__setitem__(self, key, value)\n\n Called to implement assignment to "self[key]". Same note as for\n "__getitem__()". This should only be implemented for mappings if\n the objects support changes to the values for keys, or if new keys\n can be added, or for sequences if elements can be replaced. The\n same exceptions should be raised for improper *key* values as for\n the "__getitem__()" method.\n\nobject.__delitem__(self, key)\n\n Called to implement deletion of "self[key]". Same note as for\n "__getitem__()". This should only be implemented for mappings if\n the objects support removal of keys, or for sequences if elements\n can be removed from the sequence. The same exceptions should be\n raised for improper *key* values as for the "__getitem__()" method.\n\nobject.__iter__(self)\n\n This method is called when an iterator is required for a container.\n This method should return a new iterator object that can iterate\n over all the objects in the container. For mappings, it should\n iterate over the keys of the container.\n\n Iterator objects also need to implement this method; they are\n required to return themselves. For more information on iterator\n objects, see *Iterator Types*.\n\nobject.__reversed__(self)\n\n Called (if present) by the "reversed()" built-in to implement\n reverse iteration. It should return a new iterator object that\n iterates over all the objects in the container in reverse order.\n\n If the "__reversed__()" method is not provided, the "reversed()"\n built-in will fall back to using the sequence protocol ("__len__()"\n and "__getitem__()"). Objects that support the sequence protocol\n should only provide "__reversed__()" if they can provide an\n implementation that is more efficient than the one provided by\n "reversed()".\n\nThe membership test operators ("in" and "not in") are normally\nimplemented as an iteration through a sequence. However, container\nobjects can supply the following special method with a more efficient\nimplementation, which also does not require the object be a sequence.\n\nobject.__contains__(self, item)\n\n Called to implement membership test operators. Should return true\n if *item* is in *self*, false otherwise. For mapping objects, this\n should consider the keys of the mapping rather than the values or\n the key-item pairs.\n\n For objects that don\'t define "__contains__()", the membership test\n first tries iteration via "__iter__()", then the old sequence\n iteration protocol via "__getitem__()", see *this section in the\n language reference*.\n\n\nEmulating numeric types\n=======================\n\nThe following methods can be defined to emulate numeric objects.\nMethods corresponding to operations that are not supported by the\nparticular kind of number implemented (e.g., bitwise operations for\nnon-integral numbers) should be left undefined.\n\nobject.__add__(self, other)\nobject.__sub__(self, other)\nobject.__mul__(self, other)\nobject.__truediv__(self, other)\nobject.__floordiv__(self, other)\nobject.__mod__(self, other)\nobject.__divmod__(self, other)\nobject.__pow__(self, other[, modulo])\nobject.__lshift__(self, other)\nobject.__rshift__(self, other)\nobject.__and__(self, other)\nobject.__xor__(self, other)\nobject.__or__(self, other)\n\n These methods are called to implement the binary arithmetic\n operations ("+", "-", "*", "/", "//", "%", "divmod()", "pow()",\n "**", "<<", ">>", "&", "^", "|"). For instance, to evaluate the\n expression "x + y", where *x* is an instance of a class that has an\n "__add__()" method, "x.__add__(y)" is called. The "__divmod__()"\n method should be the equivalent to using "__floordiv__()" and\n "__mod__()"; it should not be related to "__truediv__()". Note\n that "__pow__()" should be defined to accept an optional third\n argument if the ternary version of the built-in "pow()" function is\n to be supported.\n\n If one of those methods does not support the operation with the\n supplied arguments, it should return "NotImplemented".\n\nobject.__radd__(self, other)\nobject.__rsub__(self, other)\nobject.__rmul__(self, other)\nobject.__rtruediv__(self, other)\nobject.__rfloordiv__(self, other)\nobject.__rmod__(self, other)\nobject.__rdivmod__(self, other)\nobject.__rpow__(self, other)\nobject.__rlshift__(self, other)\nobject.__rrshift__(self, other)\nobject.__rand__(self, other)\nobject.__rxor__(self, other)\nobject.__ror__(self, other)\n\n These methods are called to implement the binary arithmetic\n operations ("+", "-", "*", "/", "//", "%", "divmod()", "pow()",\n "**", "<<", ">>", "&", "^", "|") with reflected (swapped) operands.\n These functions are only called if the left operand does not\n support the corresponding operation and the operands are of\n different types. [2] For instance, to evaluate the expression "x -\n y", where *y* is an instance of a class that has an "__rsub__()"\n method, "y.__rsub__(x)" is called if "x.__sub__(y)" returns\n *NotImplemented*.\n\n Note that ternary "pow()" will not try calling "__rpow__()" (the\n coercion rules would become too complicated).\n\n Note: If the right operand\'s type is a subclass of the left\n operand\'s type and that subclass provides the reflected method\n for the operation, this method will be called before the left\n operand\'s non-reflected method. This behavior allows subclasses\n to override their ancestors\' operations.\n\nobject.__iadd__(self, other)\nobject.__isub__(self, other)\nobject.__imul__(self, other)\nobject.__itruediv__(self, other)\nobject.__ifloordiv__(self, other)\nobject.__imod__(self, other)\nobject.__ipow__(self, other[, modulo])\nobject.__ilshift__(self, other)\nobject.__irshift__(self, other)\nobject.__iand__(self, other)\nobject.__ixor__(self, other)\nobject.__ior__(self, other)\n\n These methods are called to implement the augmented arithmetic\n assignments ("+=", "-=", "*=", "/=", "//=", "%=", "**=", "<<=",\n ">>=", "&=", "^=", "|="). These methods should attempt to do the\n operation in-place (modifying *self*) and return the result (which\n could be, but does not have to be, *self*). If a specific method\n is not defined, the augmented assignment falls back to the normal\n methods. For instance, if *x* is an instance of a class with an\n "__iadd__()" method, "x += y" is equivalent to "x = x.__iadd__(y)"\n . Otherwise, "x.__add__(y)" and "y.__radd__(x)" are considered, as\n with the evaluation of "x + y". In certain situations, augmented\n assignment can result in unexpected errors (see *Why does\n a_tuple[i] += [\'item\'] raise an exception when the addition\n works?*), but this behavior is in fact part of the data model.\n\nobject.__neg__(self)\nobject.__pos__(self)\nobject.__abs__(self)\nobject.__invert__(self)\n\n Called to implement the unary arithmetic operations ("-", "+",\n "abs()" and "~").\n\nobject.__complex__(self)\nobject.__int__(self)\nobject.__float__(self)\nobject.__round__(self[, n])\n\n Called to implement the built-in functions "complex()", "int()",\n "float()" and "round()". Should return a value of the appropriate\n type.\n\nobject.__index__(self)\n\n Called to implement "operator.index()", and whenever Python needs\n to losslessly convert the numeric object to an integer object (such\n as in slicing, or in the built-in "bin()", "hex()" and "oct()"\n functions). Presence of this method indicates that the numeric\n object is an integer type. Must return an integer.\n\n Note: In order to have a coherent integer type class, when\n "__index__()" is defined "__int__()" should also be defined, and\n both should return the same value.\n\n\nWith Statement Context Managers\n===============================\n\nA *context manager* is an object that defines the runtime context to\nbe established when executing a "with" statement. The context manager\nhandles the entry into, and the exit from, the desired runtime context\nfor the execution of the block of code. Context managers are normally\ninvoked using the "with" statement (described in section *The with\nstatement*), but can also be used by directly invoking their methods.\n\nTypical uses of context managers include saving and restoring various\nkinds of global state, locking and unlocking resources, closing opened\nfiles, etc.\n\nFor more information on context managers, see *Context Manager Types*.\n\nobject.__enter__(self)\n\n Enter the runtime context related to this object. The "with"\n statement will bind this method\'s return value to the target(s)\n specified in the "as" clause of the statement, if any.\n\nobject.__exit__(self, exc_type, exc_value, traceback)\n\n Exit the runtime context related to this object. The parameters\n describe the exception that caused the context to be exited. If the\n context was exited without an exception, all three arguments will\n be "None".\n\n If an exception is supplied, and the method wishes to suppress the\n exception (i.e., prevent it from being propagated), it should\n return a true value. Otherwise, the exception will be processed\n normally upon exit from this method.\n\n Note that "__exit__()" methods should not reraise the passed-in\n exception; this is the caller\'s responsibility.\n\nSee also: **PEP 0343** - The "with" statement\n\n The specification, background, and examples for the Python "with"\n statement.\n\n\nSpecial method lookup\n=====================\n\nFor custom classes, implicit invocations of special methods are only\nguaranteed to work correctly if defined on an object\'s type, not in\nthe object\'s instance dictionary. That behaviour is the reason why\nthe following code raises an exception:\n\n >>> class C:\n ... pass\n ...\n >>> c = C()\n >>> c.__len__ = lambda: 5\n >>> len(c)\n Traceback (most recent call last):\n File "<stdin>", line 1, in <module>\n TypeError: object of type \'C\' has no len()\n\nThe rationale behind this behaviour lies with a number of special\nmethods such as "__hash__()" and "__repr__()" that are implemented by\nall objects, including type objects. If the implicit lookup of these\nmethods used the conventional lookup process, they would fail when\ninvoked on the type object itself:\n\n >>> 1 .__hash__() == hash(1)\n True\n >>> int.__hash__() == hash(int)\n Traceback (most recent call last):\n File "<stdin>", line 1, in <module>\n TypeError: descriptor \'__hash__\' of \'int\' object needs an argument\n\nIncorrectly attempting to invoke an unbound method of a class in this\nway is sometimes referred to as \'metaclass confusion\', and is avoided\nby bypassing the instance when looking up special methods:\n\n >>> type(1).__hash__(1) == hash(1)\n True\n >>> type(int).__hash__(int) == hash(int)\n True\n\nIn addition to bypassing any instance attributes in the interest of\ncorrectness, implicit special method lookup generally also bypasses\nthe "__getattribute__()" method even of the object\'s metaclass:\n\n >>> class Meta(type):\n ... def __getattribute__(*args):\n ... print("Metaclass getattribute invoked")\n ... return type.__getattribute__(*args)\n ...\n >>> class C(object, metaclass=Meta):\n ... def __len__(self):\n ... return 10\n ... def __getattribute__(*args):\n ... print("Class getattribute invoked")\n ... return object.__getattribute__(*args)\n ...\n >>> c = C()\n >>> c.__len__() # Explicit lookup via instance\n Class getattribute invoked\n 10\n >>> type(c).__len__(c) # Explicit lookup via type\n Metaclass getattribute invoked\n 10\n >>> len(c) # Implicit lookup\n 10\n\nBypassing the "__getattribute__()" machinery in this fashion provides\nsignificant scope for speed optimisations within the interpreter, at\nthe cost of some flexibility in the handling of special methods (the\nspecial method *must* be set on the class object itself in order to be\nconsistently invoked by the interpreter).\n\n-[ Footnotes ]-\n\n[1] It *is* possible in some cases to change an object\'s type,\n under certain controlled conditions. It generally isn\'t a good\n idea though, since it can lead to some very strange behaviour if\n it is handled incorrectly.\n\n[2] For operands of the same type, it is assumed that if the non-\n reflected method (such as "__add__()") fails the operation is not\n supported, which is why the reflected method is not called.\n', + 'specialnames': u'\nSpecial method names\n********************\n\nA class can implement certain operations that are invoked by special\nsyntax (such as arithmetic operations or subscripting and slicing) by\ndefining methods with special names. This is Python\'s approach to\n*operator overloading*, allowing classes to define their own behavior\nwith respect to language operators. For instance, if a class defines\na method named "__getitem__()", and "x" is an instance of this class,\nthen "x[i]" is roughly equivalent to "type(x).__getitem__(x, i)".\nExcept where mentioned, attempts to execute an operation raise an\nexception when no appropriate method is defined (typically\n"AttributeError" or "TypeError").\n\nWhen implementing a class that emulates any built-in type, it is\nimportant that the emulation only be implemented to the degree that it\nmakes sense for the object being modelled. For example, some\nsequences may work well with retrieval of individual elements, but\nextracting a slice may not make sense. (One example of this is the\n"NodeList" interface in the W3C\'s Document Object Model.)\n\n\nBasic customization\n===================\n\nobject.__new__(cls[, ...])\n\n Called to create a new instance of class *cls*. "__new__()" is a\n static method (special-cased so you need not declare it as such)\n that takes the class of which an instance was requested as its\n first argument. The remaining arguments are those passed to the\n object constructor expression (the call to the class). The return\n value of "__new__()" should be the new object instance (usually an\n instance of *cls*).\n\n Typical implementations create a new instance of the class by\n invoking the superclass\'s "__new__()" method using\n "super(currentclass, cls).__new__(cls[, ...])" with appropriate\n arguments and then modifying the newly-created instance as\n necessary before returning it.\n\n If "__new__()" returns an instance of *cls*, then the new\n instance\'s "__init__()" method will be invoked like\n "__init__(self[, ...])", where *self* is the new instance and the\n remaining arguments are the same as were passed to "__new__()".\n\n If "__new__()" does not return an instance of *cls*, then the new\n instance\'s "__init__()" method will not be invoked.\n\n "__new__()" is intended mainly to allow subclasses of immutable\n types (like int, str, or tuple) to customize instance creation. It\n is also commonly overridden in custom metaclasses in order to\n customize class creation.\n\nobject.__init__(self[, ...])\n\n Called after the instance has been created (by "__new__()"), but\n before it is returned to the caller. The arguments are those\n passed to the class constructor expression. If a base class has an\n "__init__()" method, the derived class\'s "__init__()" method, if\n any, must explicitly call it to ensure proper initialization of the\n base class part of the instance; for example:\n "BaseClass.__init__(self, [args...])".\n\n Because "__new__()" and "__init__()" work together in constructing\n objects ("__new__()" to create it, and "__init__()" to customise\n it), no non-"None" value may be returned by "__init__()"; doing so\n will cause a "TypeError" to be raised at runtime.\n\nobject.__del__(self)\n\n Called when the instance is about to be destroyed. This is also\n called a destructor. If a base class has a "__del__()" method, the\n derived class\'s "__del__()" method, if any, must explicitly call it\n to ensure proper deletion of the base class part of the instance.\n Note that it is possible (though not recommended!) for the\n "__del__()" method to postpone destruction of the instance by\n creating a new reference to it. It may then be called at a later\n time when this new reference is deleted. It is not guaranteed that\n "__del__()" methods are called for objects that still exist when\n the interpreter exits.\n\n Note: "del x" doesn\'t directly call "x.__del__()" --- the former\n decrements the reference count for "x" by one, and the latter is\n only called when "x"\'s reference count reaches zero. Some common\n situations that may prevent the reference count of an object from\n going to zero include: circular references between objects (e.g.,\n a doubly-linked list or a tree data structure with parent and\n child pointers); a reference to the object on the stack frame of\n a function that caught an exception (the traceback stored in\n "sys.exc_info()[2]" keeps the stack frame alive); or a reference\n to the object on the stack frame that raised an unhandled\n exception in interactive mode (the traceback stored in\n "sys.last_traceback" keeps the stack frame alive). The first\n situation can only be remedied by explicitly breaking the cycles;\n the second can be resolved by freeing the reference to the\n traceback object when it is no longer useful, and the third can\n be resolved by storing "None" in "sys.last_traceback". Circular\n references which are garbage are detected and cleaned up when the\n cyclic garbage collector is enabled (it\'s on by default). Refer\n to the documentation for the "gc" module for more information\n about this topic.\n\n Warning: Due to the precarious circumstances under which\n "__del__()" methods are invoked, exceptions that occur during\n their execution are ignored, and a warning is printed to\n "sys.stderr" instead. Also, when "__del__()" is invoked in\n response to a module being deleted (e.g., when execution of the\n program is done), other globals referenced by the "__del__()"\n method may already have been deleted or in the process of being\n torn down (e.g. the import machinery shutting down). For this\n reason, "__del__()" methods should do the absolute minimum needed\n to maintain external invariants. Starting with version 1.5,\n Python guarantees that globals whose name begins with a single\n underscore are deleted from their module before other globals are\n deleted; if no other references to such globals exist, this may\n help in assuring that imported modules are still available at the\n time when the "__del__()" method is called.\n\nobject.__repr__(self)\n\n Called by the "repr()" built-in function to compute the "official"\n string representation of an object. If at all possible, this\n should look like a valid Python expression that could be used to\n recreate an object with the same value (given an appropriate\n environment). If this is not possible, a string of the form\n "<...some useful description...>" should be returned. The return\n value must be a string object. If a class defines "__repr__()" but\n not "__str__()", then "__repr__()" is also used when an "informal"\n string representation of instances of that class is required.\n\n This is typically used for debugging, so it is important that the\n representation is information-rich and unambiguous.\n\nobject.__str__(self)\n\n Called by "str(object)" and the built-in functions "format()" and\n "print()" to compute the "informal" or nicely printable string\n representation of an object. The return value must be a *string*\n object.\n\n This method differs from "object.__repr__()" in that there is no\n expectation that "__str__()" return a valid Python expression: a\n more convenient or concise representation can be used.\n\n The default implementation defined by the built-in type "object"\n calls "object.__repr__()".\n\nobject.__bytes__(self)\n\n Called by "bytes()" to compute a byte-string representation of an\n object. This should return a "bytes" object.\n\nobject.__format__(self, format_spec)\n\n Called by the "format()" built-in function (and by extension, the\n "str.format()" method of class "str") to produce a "formatted"\n string representation of an object. The "format_spec" argument is a\n string that contains a description of the formatting options\n desired. The interpretation of the "format_spec" argument is up to\n the type implementing "__format__()", however most classes will\n either delegate formatting to one of the built-in types, or use a\n similar formatting option syntax.\n\n See *Format Specification Mini-Language* for a description of the\n standard formatting syntax.\n\n The return value must be a string object.\n\n Changed in version 3.4: The __format__ method of "object" itself\n raises a "TypeError" if passed any non-empty string.\n\nobject.__lt__(self, other)\nobject.__le__(self, other)\nobject.__eq__(self, other)\nobject.__ne__(self, other)\nobject.__gt__(self, other)\nobject.__ge__(self, other)\n\n These are the so-called "rich comparison" methods. The\n correspondence between operator symbols and method names is as\n follows: "x<y" calls "x.__lt__(y)", "x<=y" calls "x.__le__(y)",\n "x==y" calls "x.__eq__(y)", "x!=y" calls "x.__ne__(y)", "x>y" calls\n "x.__gt__(y)", and "x>=y" calls "x.__ge__(y)".\n\n A rich comparison method may return the singleton "NotImplemented"\n if it does not implement the operation for a given pair of\n arguments. By convention, "False" and "True" are returned for a\n successful comparison. However, these methods can return any value,\n so if the comparison operator is used in a Boolean context (e.g.,\n in the condition of an "if" statement), Python will call "bool()"\n on the value to determine if the result is true or false.\n\n There are no implied relationships among the comparison operators.\n The truth of "x==y" does not imply that "x!=y" is false.\n Accordingly, when defining "__eq__()", one should also define\n "__ne__()" so that the operators will behave as expected. See the\n paragraph on "__hash__()" for some important notes on creating\n *hashable* objects which support custom comparison operations and\n are usable as dictionary keys.\n\n There are no swapped-argument versions of these methods (to be used\n when the left argument does not support the operation but the right\n argument does); rather, "__lt__()" and "__gt__()" are each other\'s\n reflection, "__le__()" and "__ge__()" are each other\'s reflection,\n and "__eq__()" and "__ne__()" are their own reflection.\n\n Arguments to rich comparison methods are never coerced.\n\n To automatically generate ordering operations from a single root\n operation, see "functools.total_ordering()".\n\nobject.__hash__(self)\n\n Called by built-in function "hash()" and for operations on members\n of hashed collections including "set", "frozenset", and "dict".\n "__hash__()" should return an integer. The only required property\n is that objects which compare equal have the same hash value; it is\n advised to somehow mix together (e.g. using exclusive or) the hash\n values for the components of the object that also play a part in\n comparison of objects.\n\n Note: "hash()" truncates the value returned from an object\'s\n custom "__hash__()" method to the size of a "Py_ssize_t". This\n is typically 8 bytes on 64-bit builds and 4 bytes on 32-bit\n builds. If an object\'s "__hash__()" must interoperate on builds\n of different bit sizes, be sure to check the width on all\n supported builds. An easy way to do this is with "python -c\n "import sys; print(sys.hash_info.width)""\n\n If a class does not define an "__eq__()" method it should not\n define a "__hash__()" operation either; if it defines "__eq__()"\n but not "__hash__()", its instances will not be usable as items in\n hashable collections. If a class defines mutable objects and\n implements an "__eq__()" method, it should not implement\n "__hash__()", since the implementation of hashable collections\n requires that a key\'s hash value is immutable (if the object\'s hash\n value changes, it will be in the wrong hash bucket).\n\n User-defined classes have "__eq__()" and "__hash__()" methods by\n default; with them, all objects compare unequal (except with\n themselves) and "x.__hash__()" returns an appropriate value such\n that "x == y" implies both that "x is y" and "hash(x) == hash(y)".\n\n A class that overrides "__eq__()" and does not define "__hash__()"\n will have its "__hash__()" implicitly set to "None". When the\n "__hash__()" method of a class is "None", instances of the class\n will raise an appropriate "TypeError" when a program attempts to\n retrieve their hash value, and will also be correctly identified as\n unhashable when checking "isinstance(obj, collections.Hashable").\n\n If a class that overrides "__eq__()" needs to retain the\n implementation of "__hash__()" from a parent class, the interpreter\n must be told this explicitly by setting "__hash__ =\n <ParentClass>.__hash__".\n\n If a class that does not override "__eq__()" wishes to suppress\n hash support, it should include "__hash__ = None" in the class\n definition. A class which defines its own "__hash__()" that\n explicitly raises a "TypeError" would be incorrectly identified as\n hashable by an "isinstance(obj, collections.Hashable)" call.\n\n Note: By default, the "__hash__()" values of str, bytes and\n datetime objects are "salted" with an unpredictable random value.\n Although they remain constant within an individual Python\n process, they are not predictable between repeated invocations of\n Python.This is intended to provide protection against a denial-\n of-service caused by carefully-chosen inputs that exploit the\n worst case performance of a dict insertion, O(n^2) complexity.\n See http://www.ocert.org/advisories/ocert-2011-003.html for\n details.Changing hash values affects the iteration order of\n dicts, sets and other mappings. Python has never made guarantees\n about this ordering (and it typically varies between 32-bit and\n 64-bit builds).See also "PYTHONHASHSEED".\n\n Changed in version 3.3: Hash randomization is enabled by default.\n\nobject.__bool__(self)\n\n Called to implement truth value testing and the built-in operation\n "bool()"; should return "False" or "True". When this method is not\n defined, "__len__()" is called, if it is defined, and the object is\n considered true if its result is nonzero. If a class defines\n neither "__len__()" nor "__bool__()", all its instances are\n considered true.\n\n\nCustomizing attribute access\n============================\n\nThe following methods can be defined to customize the meaning of\nattribute access (use of, assignment to, or deletion of "x.name") for\nclass instances.\n\nobject.__getattr__(self, name)\n\n Called when an attribute lookup has not found the attribute in the\n usual places (i.e. it is not an instance attribute nor is it found\n in the class tree for "self"). "name" is the attribute name. This\n method should return the (computed) attribute value or raise an\n "AttributeError" exception.\n\n Note that if the attribute is found through the normal mechanism,\n "__getattr__()" is not called. (This is an intentional asymmetry\n between "__getattr__()" and "__setattr__()".) This is done both for\n efficiency reasons and because otherwise "__getattr__()" would have\n no way to access other attributes of the instance. Note that at\n least for instance variables, you can fake total control by not\n inserting any values in the instance attribute dictionary (but\n instead inserting them in another object). See the\n "__getattribute__()" method below for a way to actually get total\n control over attribute access.\n\nobject.__getattribute__(self, name)\n\n Called unconditionally to implement attribute accesses for\n instances of the class. If the class also defines "__getattr__()",\n the latter will not be called unless "__getattribute__()" either\n calls it explicitly or raises an "AttributeError". This method\n should return the (computed) attribute value or raise an\n "AttributeError" exception. In order to avoid infinite recursion in\n this method, its implementation should always call the base class\n method with the same name to access any attributes it needs, for\n example, "object.__getattribute__(self, name)".\n\n Note: This method may still be bypassed when looking up special\n methods as the result of implicit invocation via language syntax\n or built-in functions. See *Special method lookup*.\n\nobject.__setattr__(self, name, value)\n\n Called when an attribute assignment is attempted. This is called\n instead of the normal mechanism (i.e. store the value in the\n instance dictionary). *name* is the attribute name, *value* is the\n value to be assigned to it.\n\n If "__setattr__()" wants to assign to an instance attribute, it\n should call the base class method with the same name, for example,\n "object.__setattr__(self, name, value)".\n\nobject.__delattr__(self, name)\n\n Like "__setattr__()" but for attribute deletion instead of\n assignment. This should only be implemented if "del obj.name" is\n meaningful for the object.\n\nobject.__dir__(self)\n\n Called when "dir()" is called on the object. A sequence must be\n returned. "dir()" converts the returned sequence to a list and\n sorts it.\n\n\nImplementing Descriptors\n------------------------\n\nThe following methods only apply when an instance of the class\ncontaining the method (a so-called *descriptor* class) appears in an\n*owner* class (the descriptor must be in either the owner\'s class\ndictionary or in the class dictionary for one of its parents). In the\nexamples below, "the attribute" refers to the attribute whose name is\nthe key of the property in the owner class\' "__dict__".\n\nobject.__get__(self, instance, owner)\n\n Called to get the attribute of the owner class (class attribute\n access) or of an instance of that class (instance attribute\n access). *owner* is always the owner class, while *instance* is the\n instance that the attribute was accessed through, or "None" when\n the attribute is accessed through the *owner*. This method should\n return the (computed) attribute value or raise an "AttributeError"\n exception.\n\nobject.__set__(self, instance, value)\n\n Called to set the attribute on an instance *instance* of the owner\n class to a new value, *value*.\n\nobject.__delete__(self, instance)\n\n Called to delete the attribute on an instance *instance* of the\n owner class.\n\nThe attribute "__objclass__" is interpreted by the "inspect" module as\nspecifying the class where this object was defined (setting this\nappropriately can assist in runtime introspection of dynamic class\nattributes). For callables, it may indicate that an instance of the\ngiven type (or a subclass) is expected or required as the first\npositional argument (for example, CPython sets this attribute for\nunbound methods that are implemented in C).\n\n\nInvoking Descriptors\n--------------------\n\nIn general, a descriptor is an object attribute with "binding\nbehavior", one whose attribute access has been overridden by methods\nin the descriptor protocol: "__get__()", "__set__()", and\n"__delete__()". If any of those methods are defined for an object, it\nis said to be a descriptor.\n\nThe default behavior for attribute access is to get, set, or delete\nthe attribute from an object\'s dictionary. For instance, "a.x" has a\nlookup chain starting with "a.__dict__[\'x\']", then\n"type(a).__dict__[\'x\']", and continuing through the base classes of\n"type(a)" excluding metaclasses.\n\nHowever, if the looked-up value is an object defining one of the\ndescriptor methods, then Python may override the default behavior and\ninvoke the descriptor method instead. Where this occurs in the\nprecedence chain depends on which descriptor methods were defined and\nhow they were called.\n\nThe starting point for descriptor invocation is a binding, "a.x". How\nthe arguments are assembled depends on "a":\n\nDirect Call\n The simplest and least common call is when user code directly\n invokes a descriptor method: "x.__get__(a)".\n\nInstance Binding\n If binding to an object instance, "a.x" is transformed into the\n call: "type(a).__dict__[\'x\'].__get__(a, type(a))".\n\nClass Binding\n If binding to a class, "A.x" is transformed into the call:\n "A.__dict__[\'x\'].__get__(None, A)".\n\nSuper Binding\n If "a" is an instance of "super", then the binding "super(B,\n obj).m()" searches "obj.__class__.__mro__" for the base class "A"\n immediately preceding "B" and then invokes the descriptor with the\n call: "A.__dict__[\'m\'].__get__(obj, obj.__class__)".\n\nFor instance bindings, the precedence of descriptor invocation depends\non the which descriptor methods are defined. A descriptor can define\nany combination of "__get__()", "__set__()" and "__delete__()". If it\ndoes not define "__get__()", then accessing the attribute will return\nthe descriptor object itself unless there is a value in the object\'s\ninstance dictionary. If the descriptor defines "__set__()" and/or\n"__delete__()", it is a data descriptor; if it defines neither, it is\na non-data descriptor. Normally, data descriptors define both\n"__get__()" and "__set__()", while non-data descriptors have just the\n"__get__()" method. Data descriptors with "__set__()" and "__get__()"\ndefined always override a redefinition in an instance dictionary. In\ncontrast, non-data descriptors can be overridden by instances.\n\nPython methods (including "staticmethod()" and "classmethod()") are\nimplemented as non-data descriptors. Accordingly, instances can\nredefine and override methods. This allows individual instances to\nacquire behaviors that differ from other instances of the same class.\n\nThe "property()" function is implemented as a data descriptor.\nAccordingly, instances cannot override the behavior of a property.\n\n\n__slots__\n---------\n\nBy default, instances of classes have a dictionary for attribute\nstorage. This wastes space for objects having very few instance\nvariables. The space consumption can become acute when creating large\nnumbers of instances.\n\nThe default can be overridden by defining *__slots__* in a class\ndefinition. The *__slots__* declaration takes a sequence of instance\nvariables and reserves just enough space in each instance to hold a\nvalue for each variable. Space is saved because *__dict__* is not\ncreated for each instance.\n\nobject.__slots__\n\n This class variable can be assigned a string, iterable, or sequence\n of strings with variable names used by instances. *__slots__*\n reserves space for the declared variables and prevents the\n automatic creation of *__dict__* and *__weakref__* for each\n instance.\n\n\nNotes on using *__slots__*\n~~~~~~~~~~~~~~~~~~~~~~~~~~\n\n* When inheriting from a class without *__slots__*, the *__dict__*\n attribute of that class will always be accessible, so a *__slots__*\n definition in the subclass is meaningless.\n\n* Without a *__dict__* variable, instances cannot be assigned new\n variables not listed in the *__slots__* definition. Attempts to\n assign to an unlisted variable name raises "AttributeError". If\n dynamic assignment of new variables is desired, then add\n "\'__dict__\'" to the sequence of strings in the *__slots__*\n declaration.\n\n* Without a *__weakref__* variable for each instance, classes\n defining *__slots__* do not support weak references to its\n instances. If weak reference support is needed, then add\n "\'__weakref__\'" to the sequence of strings in the *__slots__*\n declaration.\n\n* *__slots__* are implemented at the class level by creating\n descriptors (*Implementing Descriptors*) for each variable name. As\n a result, class attributes cannot be used to set default values for\n instance variables defined by *__slots__*; otherwise, the class\n attribute would overwrite the descriptor assignment.\n\n* The action of a *__slots__* declaration is limited to the class\n where it is defined. As a result, subclasses will have a *__dict__*\n unless they also define *__slots__* (which must only contain names\n of any *additional* slots).\n\n* If a class defines a slot also defined in a base class, the\n instance variable defined by the base class slot is inaccessible\n (except by retrieving its descriptor directly from the base class).\n This renders the meaning of the program undefined. In the future, a\n check may be added to prevent this.\n\n* Nonempty *__slots__* does not work for classes derived from\n "variable-length" built-in types such as "int", "bytes" and "tuple".\n\n* Any non-string iterable may be assigned to *__slots__*. Mappings\n may also be used; however, in the future, special meaning may be\n assigned to the values corresponding to each key.\n\n* *__class__* assignment works only if both classes have the same\n *__slots__*.\n\n\nCustomizing class creation\n==========================\n\nBy default, classes are constructed using "type()". The class body is\nexecuted in a new namespace and the class name is bound locally to the\nresult of "type(name, bases, namespace)".\n\nThe class creation process can be customised by passing the\n"metaclass" keyword argument in the class definition line, or by\ninheriting from an existing class that included such an argument. In\nthe following example, both "MyClass" and "MySubclass" are instances\nof "Meta":\n\n class Meta(type):\n pass\n\n class MyClass(metaclass=Meta):\n pass\n\n class MySubclass(MyClass):\n pass\n\nAny other keyword arguments that are specified in the class definition\nare passed through to all metaclass operations described below.\n\nWhen a class definition is executed, the following steps occur:\n\n* the appropriate metaclass is determined\n\n* the class namespace is prepared\n\n* the class body is executed\n\n* the class object is created\n\n\nDetermining the appropriate metaclass\n-------------------------------------\n\nThe appropriate metaclass for a class definition is determined as\nfollows:\n\n* if no bases and no explicit metaclass are given, then "type()" is\n used\n\n* if an explicit metaclass is given and it is *not* an instance of\n "type()", then it is used directly as the metaclass\n\n* if an instance of "type()" is given as the explicit metaclass, or\n bases are defined, then the most derived metaclass is used\n\nThe most derived metaclass is selected from the explicitly specified\nmetaclass (if any) and the metaclasses (i.e. "type(cls)") of all\nspecified base classes. The most derived metaclass is one which is a\nsubtype of *all* of these candidate metaclasses. If none of the\ncandidate metaclasses meets that criterion, then the class definition\nwill fail with "TypeError".\n\n\nPreparing the class namespace\n-----------------------------\n\nOnce the appropriate metaclass has been identified, then the class\nnamespace is prepared. If the metaclass has a "__prepare__" attribute,\nit is called as "namespace = metaclass.__prepare__(name, bases,\n**kwds)" (where the additional keyword arguments, if any, come from\nthe class definition).\n\nIf the metaclass has no "__prepare__" attribute, then the class\nnamespace is initialised as an empty "dict()" instance.\n\nSee also: **PEP 3115** - Metaclasses in Python 3000\n\n Introduced the "__prepare__" namespace hook\n\n\nExecuting the class body\n------------------------\n\nThe class body is executed (approximately) as "exec(body, globals(),\nnamespace)". The key difference from a normal call to "exec()" is that\nlexical scoping allows the class body (including any methods) to\nreference names from the current and outer scopes when the class\ndefinition occurs inside a function.\n\nHowever, even when the class definition occurs inside the function,\nmethods defined inside the class still cannot see names defined at the\nclass scope. Class variables must be accessed through the first\nparameter of instance or class methods, and cannot be accessed at all\nfrom static methods.\n\n\nCreating the class object\n-------------------------\n\nOnce the class namespace has been populated by executing the class\nbody, the class object is created by calling "metaclass(name, bases,\nnamespace, **kwds)" (the additional keywords passed here are the same\nas those passed to "__prepare__").\n\nThis class object is the one that will be referenced by the zero-\nargument form of "super()". "__class__" is an implicit closure\nreference created by the compiler if any methods in a class body refer\nto either "__class__" or "super". This allows the zero argument form\nof "super()" to correctly identify the class being defined based on\nlexical scoping, while the class or instance that was used to make the\ncurrent call is identified based on the first argument passed to the\nmethod.\n\nAfter the class object is created, it is passed to the class\ndecorators included in the class definition (if any) and the resulting\nobject is bound in the local namespace as the defined class.\n\nSee also: **PEP 3135** - New super\n\n Describes the implicit "__class__" closure reference\n\n\nMetaclass example\n-----------------\n\nThe potential uses for metaclasses are boundless. Some ideas that have\nbeen explored include logging, interface checking, automatic\ndelegation, automatic property creation, proxies, frameworks, and\nautomatic resource locking/synchronization.\n\nHere is an example of a metaclass that uses an\n"collections.OrderedDict" to remember the order that class variables\nare defined:\n\n class OrderedClass(type):\n\n @classmethod\n def __prepare__(metacls, name, bases, **kwds):\n return collections.OrderedDict()\n\n def __new__(cls, name, bases, namespace, **kwds):\n result = type.__new__(cls, name, bases, dict(namespace))\n result.members = tuple(namespace)\n return result\n\n class A(metaclass=OrderedClass):\n def one(self): pass\n def two(self): pass\n def three(self): pass\n def four(self): pass\n\n >>> A.members\n (\'__module__\', \'one\', \'two\', \'three\', \'four\')\n\nWhen the class definition for *A* gets executed, the process begins\nwith calling the metaclass\'s "__prepare__()" method which returns an\nempty "collections.OrderedDict". That mapping records the methods and\nattributes of *A* as they are defined within the body of the class\nstatement. Once those definitions are executed, the ordered dictionary\nis fully populated and the metaclass\'s "__new__()" method gets\ninvoked. That method builds the new type and it saves the ordered\ndictionary keys in an attribute called "members".\n\n\nCustomizing instance and subclass checks\n========================================\n\nThe following methods are used to override the default behavior of the\n"isinstance()" and "issubclass()" built-in functions.\n\nIn particular, the metaclass "abc.ABCMeta" implements these methods in\norder to allow the addition of Abstract Base Classes (ABCs) as\n"virtual base classes" to any class or type (including built-in\ntypes), including other ABCs.\n\nclass.__instancecheck__(self, instance)\n\n Return true if *instance* should be considered a (direct or\n indirect) instance of *class*. If defined, called to implement\n "isinstance(instance, class)".\n\nclass.__subclasscheck__(self, subclass)\n\n Return true if *subclass* should be considered a (direct or\n indirect) subclass of *class*. If defined, called to implement\n "issubclass(subclass, class)".\n\nNote that these methods are looked up on the type (metaclass) of a\nclass. They cannot be defined as class methods in the actual class.\nThis is consistent with the lookup of special methods that are called\non instances, only in this case the instance is itself a class.\n\nSee also: **PEP 3119** - Introducing Abstract Base Classes\n\n Includes the specification for customizing "isinstance()" and\n "issubclass()" behavior through "__instancecheck__()" and\n "__subclasscheck__()", with motivation for this functionality in\n the context of adding Abstract Base Classes (see the "abc"\n module) to the language.\n\n\nEmulating callable objects\n==========================\n\nobject.__call__(self[, args...])\n\n Called when the instance is "called" as a function; if this method\n is defined, "x(arg1, arg2, ...)" is a shorthand for\n "x.__call__(arg1, arg2, ...)".\n\n\nEmulating container types\n=========================\n\nThe following methods can be defined to implement container objects.\nContainers usually are sequences (such as lists or tuples) or mappings\n(like dictionaries), but can represent other containers as well. The\nfirst set of methods is used either to emulate a sequence or to\nemulate a mapping; the difference is that for a sequence, the\nallowable keys should be the integers *k* for which "0 <= k < N" where\n*N* is the length of the sequence, or slice objects, which define a\nrange of items. It is also recommended that mappings provide the\nmethods "keys()", "values()", "items()", "get()", "clear()",\n"setdefault()", "pop()", "popitem()", "copy()", and "update()"\nbehaving similar to those for Python\'s standard dictionary objects.\nThe "collections" module provides a "MutableMapping" abstract base\nclass to help create those methods from a base set of "__getitem__()",\n"__setitem__()", "__delitem__()", and "keys()". Mutable sequences\nshould provide methods "append()", "count()", "index()", "extend()",\n"insert()", "pop()", "remove()", "reverse()" and "sort()", like Python\nstandard list objects. Finally, sequence types should implement\naddition (meaning concatenation) and multiplication (meaning\nrepetition) by defining the methods "__add__()", "__radd__()",\n"__iadd__()", "__mul__()", "__rmul__()" and "__imul__()" described\nbelow; they should not define other numerical operators. It is\nrecommended that both mappings and sequences implement the\n"__contains__()" method to allow efficient use of the "in" operator;\nfor mappings, "in" should search the mapping\'s keys; for sequences, it\nshould search through the values. It is further recommended that both\nmappings and sequences implement the "__iter__()" method to allow\nefficient iteration through the container; for mappings, "__iter__()"\nshould be the same as "keys()"; for sequences, it should iterate\nthrough the values.\n\nobject.__len__(self)\n\n Called to implement the built-in function "len()". Should return\n the length of the object, an integer ">=" 0. Also, an object that\n doesn\'t define a "__bool__()" method and whose "__len__()" method\n returns zero is considered to be false in a Boolean context.\n\nobject.__length_hint__(self)\n\n Called to implement "operator.length_hint()". Should return an\n estimated length for the object (which may be greater or less than\n the actual length). The length must be an integer ">=" 0. This\n method is purely an optimization and is never required for\n correctness.\n\n New in version 3.4.\n\nNote: Slicing is done exclusively with the following three methods.\n A call like\n\n a[1:2] = b\n\n is translated to\n\n a[slice(1, 2, None)] = b\n\n and so forth. Missing slice items are always filled in with "None".\n\nobject.__getitem__(self, key)\n\n Called to implement evaluation of "self[key]". For sequence types,\n the accepted keys should be integers and slice objects. Note that\n the special interpretation of negative indexes (if the class wishes\n to emulate a sequence type) is up to the "__getitem__()" method. If\n *key* is of an inappropriate type, "TypeError" may be raised; if of\n a value outside the set of indexes for the sequence (after any\n special interpretation of negative values), "IndexError" should be\n raised. For mapping types, if *key* is missing (not in the\n container), "KeyError" should be raised.\n\n Note: "for" loops expect that an "IndexError" will be raised for\n illegal indexes to allow proper detection of the end of the\n sequence.\n\nobject.__missing__(self, key)\n\n Called by "dict"."__getitem__()" to implement "self[key]" for dict\n subclasses when key is not in the dictionary.\n\nobject.__setitem__(self, key, value)\n\n Called to implement assignment to "self[key]". Same note as for\n "__getitem__()". This should only be implemented for mappings if\n the objects support changes to the values for keys, or if new keys\n can be added, or for sequences if elements can be replaced. The\n same exceptions should be raised for improper *key* values as for\n the "__getitem__()" method.\n\nobject.__delitem__(self, key)\n\n Called to implement deletion of "self[key]". Same note as for\n "__getitem__()". This should only be implemented for mappings if\n the objects support removal of keys, or for sequences if elements\n can be removed from the sequence. The same exceptions should be\n raised for improper *key* values as for the "__getitem__()" method.\n\nobject.__iter__(self)\n\n This method is called when an iterator is required for a container.\n This method should return a new iterator object that can iterate\n over all the objects in the container. For mappings, it should\n iterate over the keys of the container.\n\n Iterator objects also need to implement this method; they are\n required to return themselves. For more information on iterator\n objects, see *Iterator Types*.\n\nobject.__reversed__(self)\n\n Called (if present) by the "reversed()" built-in to implement\n reverse iteration. It should return a new iterator object that\n iterates over all the objects in the container in reverse order.\n\n If the "__reversed__()" method is not provided, the "reversed()"\n built-in will fall back to using the sequence protocol ("__len__()"\n and "__getitem__()"). Objects that support the sequence protocol\n should only provide "__reversed__()" if they can provide an\n implementation that is more efficient than the one provided by\n "reversed()".\n\nThe membership test operators ("in" and "not in") are normally\nimplemented as an iteration through a sequence. However, container\nobjects can supply the following special method with a more efficient\nimplementation, which also does not require the object be a sequence.\n\nobject.__contains__(self, item)\n\n Called to implement membership test operators. Should return true\n if *item* is in *self*, false otherwise. For mapping objects, this\n should consider the keys of the mapping rather than the values or\n the key-item pairs.\n\n For objects that don\'t define "__contains__()", the membership test\n first tries iteration via "__iter__()", then the old sequence\n iteration protocol via "__getitem__()", see *this section in the\n language reference*.\n\n\nEmulating numeric types\n=======================\n\nThe following methods can be defined to emulate numeric objects.\nMethods corresponding to operations that are not supported by the\nparticular kind of number implemented (e.g., bitwise operations for\nnon-integral numbers) should be left undefined.\n\nobject.__add__(self, other)\nobject.__sub__(self, other)\nobject.__mul__(self, other)\nobject.__matmul__(self, other)\nobject.__truediv__(self, other)\nobject.__floordiv__(self, other)\nobject.__mod__(self, other)\nobject.__divmod__(self, other)\nobject.__pow__(self, other[, modulo])\nobject.__lshift__(self, other)\nobject.__rshift__(self, other)\nobject.__and__(self, other)\nobject.__xor__(self, other)\nobject.__or__(self, other)\n\n These methods are called to implement the binary arithmetic\n operations ("+", "-", "*", "@", "/", "//", "%", "divmod()",\n "pow()", "**", "<<", ">>", "&", "^", "|"). For instance, to\n evaluate the expression "x + y", where *x* is an instance of a\n class that has an "__add__()" method, "x.__add__(y)" is called.\n The "__divmod__()" method should be the equivalent to using\n "__floordiv__()" and "__mod__()"; it should not be related to\n "__truediv__()". Note that "__pow__()" should be defined to accept\n an optional third argument if the ternary version of the built-in\n "pow()" function is to be supported.\n\n If one of those methods does not support the operation with the\n supplied arguments, it should return "NotImplemented".\n\nobject.__radd__(self, other)\nobject.__rsub__(self, other)\nobject.__rmul__(self, other)\nobject.__rmatmul__(self, other)\nobject.__rtruediv__(self, other)\nobject.__rfloordiv__(self, other)\nobject.__rmod__(self, other)\nobject.__rdivmod__(self, other)\nobject.__rpow__(self, other)\nobject.__rlshift__(self, other)\nobject.__rrshift__(self, other)\nobject.__rand__(self, other)\nobject.__rxor__(self, other)\nobject.__ror__(self, other)\n\n These methods are called to implement the binary arithmetic\n operations ("+", "-", "*", "@", "/", "//", "%", "divmod()",\n "pow()", "**", "<<", ">>", "&", "^", "|") with reflected (swapped)\n operands. These functions are only called if the left operand does\n not support the corresponding operation and the operands are of\n different types. [2] For instance, to evaluate the expression "x -\n y", where *y* is an instance of a class that has an "__rsub__()"\n method, "y.__rsub__(x)" is called if "x.__sub__(y)" returns\n *NotImplemented*.\n\n Note that ternary "pow()" will not try calling "__rpow__()" (the\n coercion rules would become too complicated).\n\n Note: If the right operand\'s type is a subclass of the left\n operand\'s type and that subclass provides the reflected method\n for the operation, this method will be called before the left\n operand\'s non-reflected method. This behavior allows subclasses\n to override their ancestors\' operations.\n\nobject.__iadd__(self, other)\nobject.__isub__(self, other)\nobject.__imul__(self, other)\nobject.__imatmul__(self, other)\nobject.__itruediv__(self, other)\nobject.__ifloordiv__(self, other)\nobject.__imod__(self, other)\nobject.__ipow__(self, other[, modulo])\nobject.__ilshift__(self, other)\nobject.__irshift__(self, other)\nobject.__iand__(self, other)\nobject.__ixor__(self, other)\nobject.__ior__(self, other)\n\n These methods are called to implement the augmented arithmetic\n assignments ("+=", "-=", "*=", "@=", "/=", "//=", "%=", "**=",\n "<<=", ">>=", "&=", "^=", "|="). These methods should attempt to\n do the operation in-place (modifying *self*) and return the result\n (which could be, but does not have to be, *self*). If a specific\n method is not defined, the augmented assignment falls back to the\n normal methods. For instance, if *x* is an instance of a class\n with an "__iadd__()" method, "x += y" is equivalent to "x =\n x.__iadd__(y)" . Otherwise, "x.__add__(y)" and "y.__radd__(x)" are\n considered, as with the evaluation of "x + y". In certain\n situations, augmented assignment can result in unexpected errors\n (see *Why does a_tuple[i] += [\'item\'] raise an exception when the\n addition works?*), but this behavior is in fact part of the data\n model.\n\nobject.__neg__(self)\nobject.__pos__(self)\nobject.__abs__(self)\nobject.__invert__(self)\n\n Called to implement the unary arithmetic operations ("-", "+",\n "abs()" and "~").\n\nobject.__complex__(self)\nobject.__int__(self)\nobject.__float__(self)\nobject.__round__(self[, n])\n\n Called to implement the built-in functions "complex()", "int()",\n "float()" and "round()". Should return a value of the appropriate\n type.\n\nobject.__index__(self)\n\n Called to implement "operator.index()", and whenever Python needs\n to losslessly convert the numeric object to an integer object (such\n as in slicing, or in the built-in "bin()", "hex()" and "oct()"\n functions). Presence of this method indicates that the numeric\n object is an integer type. Must return an integer.\n\n Note: In order to have a coherent integer type class, when\n "__index__()" is defined "__int__()" should also be defined, and\n both should return the same value.\n\n\nWith Statement Context Managers\n===============================\n\nA *context manager* is an object that defines the runtime context to\nbe established when executing a "with" statement. The context manager\nhandles the entry into, and the exit from, the desired runtime context\nfor the execution of the block of code. Context managers are normally\ninvoked using the "with" statement (described in section *The with\nstatement*), but can also be used by directly invoking their methods.\n\nTypical uses of context managers include saving and restoring various\nkinds of global state, locking and unlocking resources, closing opened\nfiles, etc.\n\nFor more information on context managers, see *Context Manager Types*.\n\nobject.__enter__(self)\n\n Enter the runtime context related to this object. The "with"\n statement will bind this method\'s return value to the target(s)\n specified in the "as" clause of the statement, if any.\n\nobject.__exit__(self, exc_type, exc_value, traceback)\n\n Exit the runtime context related to this object. The parameters\n describe the exception that caused the context to be exited. If the\n context was exited without an exception, all three arguments will\n be "None".\n\n If an exception is supplied, and the method wishes to suppress the\n exception (i.e., prevent it from being propagated), it should\n return a true value. Otherwise, the exception will be processed\n normally upon exit from this method.\n\n Note that "__exit__()" methods should not reraise the passed-in\n exception; this is the caller\'s responsibility.\n\nSee also: **PEP 0343** - The "with" statement\n\n The specification, background, and examples for the Python "with"\n statement.\n\n\nSpecial method lookup\n=====================\n\nFor custom classes, implicit invocations of special methods are only\nguaranteed to work correctly if defined on an object\'s type, not in\nthe object\'s instance dictionary. That behaviour is the reason why\nthe following code raises an exception:\n\n >>> class C:\n ... pass\n ...\n >>> c = C()\n >>> c.__len__ = lambda: 5\n >>> len(c)\n Traceback (most recent call last):\n File "<stdin>", line 1, in <module>\n TypeError: object of type \'C\' has no len()\n\nThe rationale behind this behaviour lies with a number of special\nmethods such as "__hash__()" and "__repr__()" that are implemented by\nall objects, including type objects. If the implicit lookup of these\nmethods used the conventional lookup process, they would fail when\ninvoked on the type object itself:\n\n >>> 1 .__hash__() == hash(1)\n True\n >>> int.__hash__() == hash(int)\n Traceback (most recent call last):\n File "<stdin>", line 1, in <module>\n TypeError: descriptor \'__hash__\' of \'int\' object needs an argument\n\nIncorrectly attempting to invoke an unbound method of a class in this\nway is sometimes referred to as \'metaclass confusion\', and is avoided\nby bypassing the instance when looking up special methods:\n\n >>> type(1).__hash__(1) == hash(1)\n True\n >>> type(int).__hash__(int) == hash(int)\n True\n\nIn addition to bypassing any instance attributes in the interest of\ncorrectness, implicit special method lookup generally also bypasses\nthe "__getattribute__()" method even of the object\'s metaclass:\n\n >>> class Meta(type):\n ... def __getattribute__(*args):\n ... print("Metaclass getattribute invoked")\n ... return type.__getattribute__(*args)\n ...\n >>> class C(object, metaclass=Meta):\n ... def __len__(self):\n ... return 10\n ... def __getattribute__(*args):\n ... print("Class getattribute invoked")\n ... return object.__getattribute__(*args)\n ...\n >>> c = C()\n >>> c.__len__() # Explicit lookup via instance\n Class getattribute invoked\n 10\n >>> type(c).__len__(c) # Explicit lookup via type\n Metaclass getattribute invoked\n 10\n >>> len(c) # Implicit lookup\n 10\n\nBypassing the "__getattribute__()" machinery in this fashion provides\nsignificant scope for speed optimisations within the interpreter, at\nthe cost of some flexibility in the handling of special methods (the\nspecial method *must* be set on the class object itself in order to be\nconsistently invoked by the interpreter).\n\n-[ Footnotes ]-\n\n[1] It *is* possible in some cases to change an object\'s type,\n under certain controlled conditions. It generally isn\'t a good\n idea though, since it can lead to some very strange behaviour if\n it is handled incorrectly.\n\n[2] For operands of the same type, it is assumed that if the non-\n reflected method (such as "__add__()") fails the operation is not\n supported, which is why the reflected method is not called.\n', 'string-methods': u'\nString Methods\n**************\n\nStrings implement all of the *common* sequence operations, along with\nthe additional methods described below.\n\nStrings also support two styles of string formatting, one providing a\nlarge degree of flexibility and customization (see "str.format()",\n*Format String Syntax* and *String Formatting*) and the other based on\nC "printf" style formatting that handles a narrower range of types and\nis slightly harder to use correctly, but is often faster for the cases\nit can handle (*printf-style String Formatting*).\n\nThe *Text Processing Services* section of the standard library covers\na number of other modules that provide various text related utilities\n(including regular expression support in the "re" module).\n\nstr.capitalize()\n\n Return a copy of the string with its first character capitalized\n and the rest lowercased.\n\nstr.casefold()\n\n Return a casefolded copy of the string. Casefolded strings may be\n used for caseless matching.\n\n Casefolding is similar to lowercasing but more aggressive because\n it is intended to remove all case distinctions in a string. For\n example, the German lowercase letter "\'\xdf\'" is equivalent to ""ss"".\n Since it is already lowercase, "lower()" would do nothing to "\'\xdf\'";\n "casefold()" converts it to ""ss"".\n\n The casefolding algorithm is described in section 3.13 of the\n Unicode Standard.\n\n New in version 3.3.\n\nstr.center(width[, fillchar])\n\n Return centered in a string of length *width*. Padding is done\n using the specified *fillchar* (default is an ASCII space). The\n original string is returned if *width* is less than or equal to\n "len(s)".\n\nstr.count(sub[, start[, end]])\n\n Return the number of non-overlapping occurrences of substring *sub*\n in the range [*start*, *end*]. Optional arguments *start* and\n *end* are interpreted as in slice notation.\n\nstr.encode(encoding="utf-8", errors="strict")\n\n Return an encoded version of the string as a bytes object. Default\n encoding is "\'utf-8\'". *errors* may be given to set a different\n error handling scheme. The default for *errors* is "\'strict\'",\n meaning that encoding errors raise a "UnicodeError". Other possible\n values are "\'ignore\'", "\'replace\'", "\'xmlcharrefreplace\'",\n "\'backslashreplace\'" and any other name registered via\n "codecs.register_error()", see section *Error Handlers*. For a list\n of possible encodings, see section *Standard Encodings*.\n\n Changed in version 3.1: Support for keyword arguments added.\n\nstr.endswith(suffix[, start[, end]])\n\n Return "True" if the string ends with the specified *suffix*,\n otherwise return "False". *suffix* can also be a tuple of suffixes\n to look for. With optional *start*, test beginning at that\n position. With optional *end*, stop comparing at that position.\n\nstr.expandtabs(tabsize=8)\n\n Return a copy of the string where all tab characters are replaced\n by one or more spaces, depending on the current column and the\n given tab size. Tab positions occur every *tabsize* characters\n (default is 8, giving tab positions at columns 0, 8, 16 and so on).\n To expand the string, the current column is set to zero and the\n string is examined character by character. If the character is a\n tab ("\\t"), one or more space characters are inserted in the result\n until the current column is equal to the next tab position. (The\n tab character itself is not copied.) If the character is a newline\n ("\\n") or return ("\\r"), it is copied and the current column is\n reset to zero. Any other character is copied unchanged and the\n current column is incremented by one regardless of how the\n character is represented when printed.\n\n >>> \'01\\t012\\t0123\\t01234\'.expandtabs()\n \'01 012 0123 01234\'\n >>> \'01\\t012\\t0123\\t01234\'.expandtabs(4)\n \'01 012 0123 01234\'\n\nstr.find(sub[, start[, end]])\n\n Return the lowest index in the string where substring *sub* is\n found, such that *sub* is contained in the slice "s[start:end]".\n Optional arguments *start* and *end* are interpreted as in slice\n notation. Return "-1" if *sub* is not found.\n\n Note: The "find()" method should be used only if you need to know\n the position of *sub*. To check if *sub* is a substring or not,\n use the "in" operator:\n\n >>> \'Py\' in \'Python\'\n True\n\nstr.format(*args, **kwargs)\n\n Perform a string formatting operation. The string on which this\n method is called can contain literal text or replacement fields\n delimited by braces "{}". Each replacement field contains either\n the numeric index of a positional argument, or the name of a\n keyword argument. Returns a copy of the string where each\n replacement field is replaced with the string value of the\n corresponding argument.\n\n >>> "The sum of 1 + 2 is {0}".format(1+2)\n \'The sum of 1 + 2 is 3\'\n\n See *Format String Syntax* for a description of the various\n formatting options that can be specified in format strings.\n\nstr.format_map(mapping)\n\n Similar to "str.format(**mapping)", except that "mapping" is used\n directly and not copied to a "dict". This is useful if for example\n "mapping" is a dict subclass:\n\n >>> class Default(dict):\n ... def __missing__(self, key):\n ... return key\n ...\n >>> \'{name} was born in {country}\'.format_map(Default(name=\'Guido\'))\n \'Guido was born in country\'\n\n New in version 3.2.\n\nstr.index(sub[, start[, end]])\n\n Like "find()", but raise "ValueError" when the substring is not\n found.\n\nstr.isalnum()\n\n Return true if all characters in the string are alphanumeric and\n there is at least one character, false otherwise. A character "c"\n is alphanumeric if one of the following returns "True":\n "c.isalpha()", "c.isdecimal()", "c.isdigit()", or "c.isnumeric()".\n\nstr.isalpha()\n\n Return true if all characters in the string are alphabetic and\n there is at least one character, false otherwise. Alphabetic\n characters are those characters defined in the Unicode character\n database as "Letter", i.e., those with general category property\n being one of "Lm", "Lt", "Lu", "Ll", or "Lo". Note that this is\n different from the "Alphabetic" property defined in the Unicode\n Standard.\n\nstr.isdecimal()\n\n Return true if all characters in the string are decimal characters\n and there is at least one character, false otherwise. Decimal\n characters are those from general category "Nd". This category\n includes digit characters, and all characters that can be used to\n form decimal-radix numbers, e.g. U+0660, ARABIC-INDIC DIGIT ZERO.\n\nstr.isdigit()\n\n Return true if all characters in the string are digits and there is\n at least one character, false otherwise. Digits include decimal\n characters and digits that need special handling, such as the\n compatibility superscript digits. Formally, a digit is a character\n that has the property value Numeric_Type=Digit or\n Numeric_Type=Decimal.\n\nstr.isidentifier()\n\n Return true if the string is a valid identifier according to the\n language definition, section *Identifiers and keywords*.\n\n Use "keyword.iskeyword()" to test for reserved identifiers such as\n "def" and "class".\n\nstr.islower()\n\n Return true if all cased characters [4] in the string are lowercase\n and there is at least one cased character, false otherwise.\n\nstr.isnumeric()\n\n Return true if all characters in the string are numeric characters,\n and there is at least one character, false otherwise. Numeric\n characters include digit characters, and all characters that have\n the Unicode numeric value property, e.g. U+2155, VULGAR FRACTION\n ONE FIFTH. Formally, numeric characters are those with the\n property value Numeric_Type=Digit, Numeric_Type=Decimal or\n Numeric_Type=Numeric.\n\nstr.isprintable()\n\n Return true if all characters in the string are printable or the\n string is empty, false otherwise. Nonprintable characters are\n those characters defined in the Unicode character database as\n "Other" or "Separator", excepting the ASCII space (0x20) which is\n considered printable. (Note that printable characters in this\n context are those which should not be escaped when "repr()" is\n invoked on a string. It has no bearing on the handling of strings\n written to "sys.stdout" or "sys.stderr".)\n\nstr.isspace()\n\n Return true if there are only whitespace characters in the string\n and there is at least one character, false otherwise. Whitespace\n characters are those characters defined in the Unicode character\n database as "Other" or "Separator" and those with bidirectional\n property being one of "WS", "B", or "S".\n\nstr.istitle()\n\n Return true if the string is a titlecased string and there is at\n least one character, for example uppercase characters may only\n follow uncased characters and lowercase characters only cased ones.\n Return false otherwise.\n\nstr.isupper()\n\n Return true if all cased characters [4] in the string are uppercase\n and there is at least one cased character, false otherwise.\n\nstr.join(iterable)\n\n Return a string which is the concatenation of the strings in the\n *iterable* *iterable*. A "TypeError" will be raised if there are\n any non-string values in *iterable*, including "bytes" objects.\n The separator between elements is the string providing this method.\n\nstr.ljust(width[, fillchar])\n\n Return the string left justified in a string of length *width*.\n Padding is done using the specified *fillchar* (default is an ASCII\n space). The original string is returned if *width* is less than or\n equal to "len(s)".\n\nstr.lower()\n\n Return a copy of the string with all the cased characters [4]\n converted to lowercase.\n\n The lowercasing algorithm used is described in section 3.13 of the\n Unicode Standard.\n\nstr.lstrip([chars])\n\n Return a copy of the string with leading characters removed. The\n *chars* argument is a string specifying the set of characters to be\n removed. If omitted or "None", the *chars* argument defaults to\n removing whitespace. The *chars* argument is not a prefix; rather,\n all combinations of its values are stripped:\n\n >>> \' spacious \'.lstrip()\n \'spacious \'\n >>> \'www.example.com\'.lstrip(\'cmowz.\')\n \'example.com\'\n\nstatic str.maketrans(x[, y[, z]])\n\n This static method returns a translation table usable for\n "str.translate()".\n\n If there is only one argument, it must be a dictionary mapping\n Unicode ordinals (integers) or characters (strings of length 1) to\n Unicode ordinals, strings (of arbitrary lengths) or None.\n Character keys will then be converted to ordinals.\n\n If there are two arguments, they must be strings of equal length,\n and in the resulting dictionary, each character in x will be mapped\n to the character at the same position in y. If there is a third\n argument, it must be a string, whose characters will be mapped to\n None in the result.\n\nstr.partition(sep)\n\n Split the string at the first occurrence of *sep*, and return a\n 3-tuple containing the part before the separator, the separator\n itself, and the part after the separator. If the separator is not\n found, return a 3-tuple containing the string itself, followed by\n two empty strings.\n\nstr.replace(old, new[, count])\n\n Return a copy of the string with all occurrences of substring *old*\n replaced by *new*. If the optional argument *count* is given, only\n the first *count* occurrences are replaced.\n\nstr.rfind(sub[, start[, end]])\n\n Return the highest index in the string where substring *sub* is\n found, such that *sub* is contained within "s[start:end]".\n Optional arguments *start* and *end* are interpreted as in slice\n notation. Return "-1" on failure.\n\nstr.rindex(sub[, start[, end]])\n\n Like "rfind()" but raises "ValueError" when the substring *sub* is\n not found.\n\nstr.rjust(width[, fillchar])\n\n Return the string right justified in a string of length *width*.\n Padding is done using the specified *fillchar* (default is an ASCII\n space). The original string is returned if *width* is less than or\n equal to "len(s)".\n\nstr.rpartition(sep)\n\n Split the string at the last occurrence of *sep*, and return a\n 3-tuple containing the part before the separator, the separator\n itself, and the part after the separator. If the separator is not\n found, return a 3-tuple containing two empty strings, followed by\n the string itself.\n\nstr.rsplit(sep=None, maxsplit=-1)\n\n Return a list of the words in the string, using *sep* as the\n delimiter string. If *maxsplit* is given, at most *maxsplit* splits\n are done, the *rightmost* ones. If *sep* is not specified or\n "None", any whitespace string is a separator. Except for splitting\n from the right, "rsplit()" behaves like "split()" which is\n described in detail below.\n\nstr.rstrip([chars])\n\n Return a copy of the string with trailing characters removed. The\n *chars* argument is a string specifying the set of characters to be\n removed. If omitted or "None", the *chars* argument defaults to\n removing whitespace. The *chars* argument is not a suffix; rather,\n all combinations of its values are stripped:\n\n >>> \' spacious \'.rstrip()\n \' spacious\'\n >>> \'mississippi\'.rstrip(\'ipz\')\n \'mississ\'\n\nstr.split(sep=None, maxsplit=-1)\n\n Return a list of the words in the string, using *sep* as the\n delimiter string. If *maxsplit* is given, at most *maxsplit*\n splits are done (thus, the list will have at most "maxsplit+1"\n elements). If *maxsplit* is not specified or "-1", then there is\n no limit on the number of splits (all possible splits are made).\n\n If *sep* is given, consecutive delimiters are not grouped together\n and are deemed to delimit empty strings (for example,\n "\'1,,2\'.split(\',\')" returns "[\'1\', \'\', \'2\']"). The *sep* argument\n may consist of multiple characters (for example,\n "\'1<>2<>3\'.split(\'<>\')" returns "[\'1\', \'2\', \'3\']"). Splitting an\n empty string with a specified separator returns "[\'\']".\n\n For example:\n\n >>> \'1,2,3\'.split(\',\')\n [\'1\', \'2\', \'3\']\n >>> \'1,2,3\'.split(\',\', maxsplit=1)\n [\'1\', \'2,3\']\n >>> \'1,2,,3,\'.split(\',\')\n [\'1\', \'2\', \'\', \'3\', \'\']\n\n If *sep* is not specified or is "None", a different splitting\n algorithm is applied: runs of consecutive whitespace are regarded\n as a single separator, and the result will contain no empty strings\n at the start or end if the string has leading or trailing\n whitespace. Consequently, splitting an empty string or a string\n consisting of just whitespace with a "None" separator returns "[]".\n\n For example:\n\n >>> \'1 2 3\'.split()\n [\'1\', \'2\', \'3\']\n >>> \'1 2 3\'.split(maxsplit=1)\n [\'1\', \'2 3\']\n >>> \' 1 2 3 \'.split()\n [\'1\', \'2\', \'3\']\n\nstr.splitlines([keepends])\n\n Return a list of the lines in the string, breaking at line\n boundaries. This method uses the *universal newlines* approach to\n splitting lines. Line breaks are not included in the resulting list\n unless *keepends* is given and true.\n\n For example:\n\n >>> \'ab c\\n\\nde fg\\rkl\\r\\n\'.splitlines()\n [\'ab c\', \'\', \'de fg\', \'kl\']\n >>> \'ab c\\n\\nde fg\\rkl\\r\\n\'.splitlines(keepends=True)\n [\'ab c\\n\', \'\\n\', \'de fg\\r\', \'kl\\r\\n\']\n\n Unlike "split()" when a delimiter string *sep* is given, this\n method returns an empty list for the empty string, and a terminal\n line break does not result in an extra line:\n\n >>> "".splitlines()\n []\n >>> "One line\\n".splitlines()\n [\'One line\']\n\n For comparison, "split(\'\\n\')" gives:\n\n >>> \'\'.split(\'\\n\')\n [\'\']\n >>> \'Two lines\\n\'.split(\'\\n\')\n [\'Two lines\', \'\']\n\nstr.startswith(prefix[, start[, end]])\n\n Return "True" if string starts with the *prefix*, otherwise return\n "False". *prefix* can also be a tuple of prefixes to look for.\n With optional *start*, test string beginning at that position.\n With optional *end*, stop comparing string at that position.\n\nstr.strip([chars])\n\n Return a copy of the string with the leading and trailing\n characters removed. The *chars* argument is a string specifying the\n set of characters to be removed. If omitted or "None", the *chars*\n argument defaults to removing whitespace. The *chars* argument is\n not a prefix or suffix; rather, all combinations of its values are\n stripped:\n\n >>> \' spacious \'.strip()\n \'spacious\'\n >>> \'www.example.com\'.strip(\'cmowz.\')\n \'example\'\n\nstr.swapcase()\n\n Return a copy of the string with uppercase characters converted to\n lowercase and vice versa. Note that it is not necessarily true that\n "s.swapcase().swapcase() == s".\n\nstr.title()\n\n Return a titlecased version of the string where words start with an\n uppercase character and the remaining characters are lowercase.\n\n For example:\n\n >>> \'Hello world\'.title()\n \'Hello World\'\n\n The algorithm uses a simple language-independent definition of a\n word as groups of consecutive letters. The definition works in\n many contexts but it means that apostrophes in contractions and\n possessives form word boundaries, which may not be the desired\n result:\n\n >>> "they\'re bill\'s friends from the UK".title()\n "They\'Re Bill\'S Friends From The Uk"\n\n A workaround for apostrophes can be constructed using regular\n expressions:\n\n >>> import re\n >>> def titlecase(s):\n ... return re.sub(r"[A-Za-z]+(\'[A-Za-z]+)?",\n ... lambda mo: mo.group(0)[0].upper() +\n ... mo.group(0)[1:].lower(),\n ... s)\n ...\n >>> titlecase("they\'re bill\'s friends.")\n "They\'re Bill\'s Friends."\n\nstr.translate(map)\n\n Return a copy of the *s* where all characters have been mapped\n through the *map* which must be a dictionary of Unicode ordinals\n (integers) to Unicode ordinals, strings or "None". Unmapped\n characters are left untouched. Characters mapped to "None" are\n deleted.\n\n You can use "str.maketrans()" to create a translation map from\n character-to-character mappings in different formats.\n\n Note: An even more flexible approach is to create a custom\n character mapping codec using the "codecs" module (see\n "encodings.cp1251" for an example).\n\nstr.upper()\n\n Return a copy of the string with all the cased characters [4]\n converted to uppercase. Note that "str.upper().isupper()" might be\n "False" if "s" contains uncased characters or if the Unicode\n category of the resulting character(s) is not "Lu" (Letter,\n uppercase), but e.g. "Lt" (Letter, titlecase).\n\n The uppercasing algorithm used is described in section 3.13 of the\n Unicode Standard.\n\nstr.zfill(width)\n\n Return a copy of the string left filled with ASCII "\'0\'" digits to\n make a string of length *width*. A leading sign prefix ("\'+\'"/"\'-\'"\n is handled by inserting the padding *after* the sign character\n rather than before. The original string is returned if *width* is\n less than or equal to "len(s)".\n\n For example:\n\n >>> "42".zfill(5)\n \'00042\'\n >>> "-42".zfill(5)\n \'-0042\'\n', 'strings': u'\nString and Bytes literals\n*************************\n\nString literals are described by the following lexical definitions:\n\n stringliteral ::= [stringprefix](shortstring | longstring)\n stringprefix ::= "r" | "u" | "R" | "U"\n shortstring ::= "\'" shortstringitem* "\'" | \'"\' shortstringitem* \'"\'\n longstring ::= "\'\'\'" longstringitem* "\'\'\'" | \'"""\' longstringitem* \'"""\'\n shortstringitem ::= shortstringchar | stringescapeseq\n longstringitem ::= longstringchar | stringescapeseq\n shortstringchar ::= <any source character except "\\" or newline or the quote>\n longstringchar ::= <any source character except "\\">\n stringescapeseq ::= "\\" <any source character>\n\n bytesliteral ::= bytesprefix(shortbytes | longbytes)\n bytesprefix ::= "b" | "B" | "br" | "Br" | "bR" | "BR" | "rb" | "rB" | "Rb" | "RB"\n shortbytes ::= "\'" shortbytesitem* "\'" | \'"\' shortbytesitem* \'"\'\n longbytes ::= "\'\'\'" longbytesitem* "\'\'\'" | \'"""\' longbytesitem* \'"""\'\n shortbytesitem ::= shortbyteschar | bytesescapeseq\n longbytesitem ::= longbyteschar | bytesescapeseq\n shortbyteschar ::= <any ASCII character except "\\" or newline or the quote>\n longbyteschar ::= <any ASCII character except "\\">\n bytesescapeseq ::= "\\" <any ASCII character>\n\nOne syntactic restriction not indicated by these productions is that\nwhitespace is not allowed between the "stringprefix" or "bytesprefix"\nand the rest of the literal. The source character set is defined by\nthe encoding declaration; it is UTF-8 if no encoding declaration is\ngiven in the source file; see section *Encoding declarations*.\n\nIn plain English: Both types of literals can be enclosed in matching\nsingle quotes ("\'") or double quotes ("""). They can also be enclosed\nin matching groups of three single or double quotes (these are\ngenerally referred to as *triple-quoted strings*). The backslash\n("\\") character is used to escape characters that otherwise have a\nspecial meaning, such as newline, backslash itself, or the quote\ncharacter.\n\nBytes literals are always prefixed with "\'b\'" or "\'B\'"; they produce\nan instance of the "bytes" type instead of the "str" type. They may\nonly contain ASCII characters; bytes with a numeric value of 128 or\ngreater must be expressed with escapes.\n\nAs of Python 3.3 it is possible again to prefix string literals with a\n"u" prefix to simplify maintenance of dual 2.x and 3.x codebases.\n\nBoth string and bytes literals may optionally be prefixed with a\nletter "\'r\'" or "\'R\'"; such strings are called *raw strings* and treat\nbackslashes as literal characters. As a result, in string literals,\n"\'\\U\'" and "\'\\u\'" escapes in raw strings are not treated specially.\nGiven that Python 2.x\'s raw unicode literals behave differently than\nPython 3.x\'s the "\'ur\'" syntax is not supported.\n\nNew in version 3.3: The "\'rb\'" prefix of raw bytes literals has been\nadded as a synonym of "\'br\'".\n\nNew in version 3.3: Support for the unicode legacy literal\n("u\'value\'") was reintroduced to simplify the maintenance of dual\nPython 2.x and 3.x codebases. See **PEP 414** for more information.\n\nIn triple-quoted literals, unescaped newlines and quotes are allowed\n(and are retained), except that three unescaped quotes in a row\nterminate the literal. (A "quote" is the character used to open the\nliteral, i.e. either "\'" or """.)\n\nUnless an "\'r\'" or "\'R\'" prefix is present, escape sequences in string\nand bytes literals are interpreted according to rules similar to those\nused by Standard C. The recognized escape sequences are:\n\n+-------------------+-----------------------------------+---------+\n| Escape Sequence | Meaning | Notes |\n+===================+===================================+=========+\n| "\\newline" | Backslash and newline ignored | |\n+-------------------+-----------------------------------+---------+\n| "\\\\" | Backslash ("\\") | |\n+-------------------+-----------------------------------+---------+\n| "\\\'" | Single quote ("\'") | |\n+-------------------+-----------------------------------+---------+\n| "\\"" | Double quote (""") | |\n+-------------------+-----------------------------------+---------+\n| "\\a" | ASCII Bell (BEL) | |\n+-------------------+-----------------------------------+---------+\n| "\\b" | ASCII Backspace (BS) | |\n+-------------------+-----------------------------------+---------+\n| "\\f" | ASCII Formfeed (FF) | |\n+-------------------+-----------------------------------+---------+\n| "\\n" | ASCII Linefeed (LF) | |\n+-------------------+-----------------------------------+---------+\n| "\\r" | ASCII Carriage Return (CR) | |\n+-------------------+-----------------------------------+---------+\n| "\\t" | ASCII Horizontal Tab (TAB) | |\n+-------------------+-----------------------------------+---------+\n| "\\v" | ASCII Vertical Tab (VT) | |\n+-------------------+-----------------------------------+---------+\n| "\\ooo" | Character with octal value *ooo* | (1,3) |\n+-------------------+-----------------------------------+---------+\n| "\\xhh" | Character with hex value *hh* | (2,3) |\n+-------------------+-----------------------------------+---------+\n\nEscape sequences only recognized in string literals are:\n\n+-------------------+-----------------------------------+---------+\n| Escape Sequence | Meaning | Notes |\n+===================+===================================+=========+\n| "\\N{name}" | Character named *name* in the | (4) |\n| | Unicode database | |\n+-------------------+-----------------------------------+---------+\n| "\\uxxxx" | Character with 16-bit hex value | (5) |\n| | *xxxx* | |\n+-------------------+-----------------------------------+---------+\n| "\\Uxxxxxxxx" | Character with 32-bit hex value | (6) |\n| | *xxxxxxxx* | |\n+-------------------+-----------------------------------+---------+\n\nNotes:\n\n1. As in Standard C, up to three octal digits are accepted.\n\n2. Unlike in Standard C, exactly two hex digits are required.\n\n3. In a bytes literal, hexadecimal and octal escapes denote the\n byte with the given value. In a string literal, these escapes\n denote a Unicode character with the given value.\n\n4. Changed in version 3.3: Support for name aliases [1] has been\n added.\n\n5. Individual code units which form parts of a surrogate pair can\n be encoded using this escape sequence. Exactly four hex digits are\n required.\n\n6. Any Unicode character can be encoded this way. Exactly eight\n hex digits are required.\n\nUnlike Standard C, all unrecognized escape sequences are left in the\nstring unchanged, i.e., *the backslash is left in the result*. (This\nbehavior is useful when debugging: if an escape sequence is mistyped,\nthe resulting output is more easily recognized as broken.) It is also\nimportant to note that the escape sequences only recognized in string\nliterals fall into the category of unrecognized escapes for bytes\nliterals.\n\nEven in a raw literal, quotes can be escaped with a backslash, but the\nbackslash remains in the result; for example, "r"\\""" is a valid\nstring literal consisting of two characters: a backslash and a double\nquote; "r"\\"" is not a valid string literal (even a raw string cannot\nend in an odd number of backslashes). Specifically, *a raw literal\ncannot end in a single backslash* (since the backslash would escape\nthe following quote character). Note also that a single backslash\nfollowed by a newline is interpreted as those two characters as part\nof the literal, *not* as a line continuation.\n', 'subscriptions': u'\nSubscriptions\n*************\n\nA subscription selects an item of a sequence (string, tuple or list)\nor mapping (dictionary) object:\n\n subscription ::= primary "[" expression_list "]"\n\nThe primary must evaluate to an object that supports subscription\n(lists or dictionaries for example). User-defined objects can support\nsubscription by defining a "__getitem__()" method.\n\nFor built-in objects, there are two types of objects that support\nsubscription:\n\nIf the primary is a mapping, the expression list must evaluate to an\nobject whose value is one of the keys of the mapping, and the\nsubscription selects the value in the mapping that corresponds to that\nkey. (The expression list is a tuple except if it has exactly one\nitem.)\n\nIf the primary is a sequence, the expression (list) must evaluate to\nan integer or a slice (as discussed in the following section).\n\nThe formal syntax makes no special provision for negative indices in\nsequences; however, built-in sequences all provide a "__getitem__()"\nmethod that interprets negative indices by adding the length of the\nsequence to the index (so that "x[-1]" selects the last item of "x").\nThe resulting value must be a nonnegative integer less than the number\nof items in the sequence, and the subscription selects the item whose\nindex is that value (counting from zero). Since the support for\nnegative indices and slicing occurs in the object\'s "__getitem__()"\nmethod, subclasses overriding this method will need to explicitly add\nthat support.\n\nA string\'s items are characters. A character is not a separate data\ntype but a string of exactly one character.\n', diff --git a/Lib/queue.py b/Lib/queue.py index 3cee36b..572425e 100644 --- a/Lib/queue.py +++ b/Lib/queue.py @@ -6,10 +6,7 @@ except ImportError: import dummy_threading as threading from collections import deque from heapq import heappush, heappop -try: - from time import monotonic as time -except ImportError: - from time import time +from time import monotonic as time __all__ = ['Empty', 'Full', 'Queue', 'PriorityQueue', 'LifoQueue'] diff --git a/Lib/random.py b/Lib/random.py index 4642928..1f5be45 100644 --- a/Lib/random.py +++ b/Lib/random.py @@ -687,7 +687,7 @@ def _test_generator(n, func, args): print(round(t1-t0, 3), 'sec,', end=' ') avg = total/n stddev = _sqrt(sqsum/n - avg*avg) - print('avg %g, stddev %g, min %g, max %g' % \ + print('avg %g, stddev %g, min %g, max %g\n' % \ (avg, stddev, smallest, largest)) @@ -128,10 +128,13 @@ except ImportError: _locale = None # public symbols -__all__ = [ "match", "fullmatch", "search", "sub", "subn", "split", "findall", - "compile", "purge", "template", "escape", "A", "I", "L", "M", "S", "X", - "U", "ASCII", "IGNORECASE", "LOCALE", "MULTILINE", "DOTALL", "VERBOSE", - "UNICODE", "error" ] +__all__ = [ + "match", "fullmatch", "search", "sub", "subn", "split", + "findall", "finditer", "compile", "purge", "template", "escape", + "error", "A", "I", "L", "M", "S", "X", "U", + "ASCII", "IGNORECASE", "LOCALE", "MULTILINE", "DOTALL", "VERBOSE", + "UNICODE", +] __version__ = "2.2.1" @@ -209,14 +212,12 @@ def findall(pattern, string, flags=0): Empty matches are included in the result.""" return _compile(pattern, flags).findall(string) -if sys.hexversion >= 0x02020000: - __all__.append("finditer") - def finditer(pattern, string, flags=0): - """Return an iterator over all non-overlapping matches in the - string. For each match, the iterator returns a match object. +def finditer(pattern, string, flags=0): + """Return an iterator over all non-overlapping matches in the + string. For each match, the iterator returns a match object. - Empty matches are included in the result.""" - return _compile(pattern, flags).finditer(string) + Empty matches are included in the result.""" + return _compile(pattern, flags).finditer(string) def compile(pattern, flags=0): "Compile a regular expression pattern, returning a pattern object." @@ -276,14 +277,12 @@ _pattern_type = type(sre_compile.compile("", 0)) _MAXCACHE = 512 def _compile(pattern, flags): # internal: compile pattern - bypass_cache = flags & DEBUG - if not bypass_cache: - try: - p, loc = _cache[type(pattern), pattern, flags] - if loc is None or loc == _locale.setlocale(_locale.LC_CTYPE): - return p - except KeyError: - pass + try: + p, loc = _cache[type(pattern), pattern, flags] + if loc is None or loc == _locale.setlocale(_locale.LC_CTYPE): + return p + except KeyError: + pass if isinstance(pattern, _pattern_type): if flags: raise ValueError( @@ -292,7 +291,7 @@ def _compile(pattern, flags): if not sre_compile.isstring(pattern): raise TypeError("first argument must be string or compiled pattern") p = sre_compile.compile(pattern, flags) - if not bypass_cache: + if not (flags & DEBUG): if len(_cache) >= _MAXCACHE: _cache.clear() if p.flags & LOCALE: @@ -352,10 +351,11 @@ class Scanner: s = sre_parse.Pattern() s.flags = flags for phrase, action in lexicon: + gid = s.opengroup() p.append(sre_parse.SubPattern(s, [ - (SUBPATTERN, (len(p)+1, sre_parse.parse(phrase, flags))), + (SUBPATTERN, (gid, sre_parse.parse(phrase, flags))), ])) - s.groups = len(p)+1 + s.closegroup(gid, p[-1]) p = sre_parse.SubPattern(s, [(BRANCH, (None, p))]) self.scanner = sre_compile.compile(p) def scan(self, string): @@ -363,7 +363,7 @@ class Scanner: append = result.append match = self.scanner.scanner(string).match i = 0 - while 1: + while True: m = match() if not m: break diff --git a/Lib/reprlib.py b/Lib/reprlib.py index f803360..ecbd2cc 100644 --- a/Lib/reprlib.py +++ b/Lib/reprlib.py @@ -83,16 +83,22 @@ class Repr: return self._repr_iterable(x, level, '[', ']', self.maxlist) def repr_array(self, x, level): + if not x: + return "array('%s')" % x.typecode header = "array('%s', [" % x.typecode return self._repr_iterable(x, level, header, '])', self.maxarray) def repr_set(self, x, level): + if not x: + return 'set()' x = _possibly_sorted(x) - return self._repr_iterable(x, level, 'set([', '])', self.maxset) + return self._repr_iterable(x, level, '{', '}', self.maxset) def repr_frozenset(self, x, level): + if not x: + return 'frozenset()' x = _possibly_sorted(x) - return self._repr_iterable(x, level, 'frozenset([', '])', + return self._repr_iterable(x, level, 'frozenset({', '})', self.maxfrozenset) def repr_deque(self, x, level): @@ -136,7 +142,7 @@ class Repr: # Bugs in x.__repr__() can cause arbitrary # exceptions -- then make up something except Exception: - return '<%s instance at %x>' % (x.__class__.__name__, id(x)) + return '<%s instance at %#x>' % (x.__class__.__name__, id(x)) if len(s) > self.maxother: i = max(0, (self.maxother-3)//2) j = max(0, self.maxother-3-i) diff --git a/Lib/runpy.py b/Lib/runpy.py index 0bb57d7..d9c643d 100644 --- a/Lib/runpy.py +++ b/Lib/runpy.py @@ -58,7 +58,7 @@ class _ModifiedArgv0(object): self.value = self._sentinel sys.argv[0] = self._saved_value -# TODO: Replace these helpers with importlib._bootstrap._SpecMethods +# TODO: Replace these helpers with importlib._bootstrap functions def _run_code(code, run_globals, init_globals=None, mod_name=None, mod_spec=None, pkg_name=None, script_name=None): diff --git a/Lib/sched.py b/Lib/sched.py index 2e6b00a..b47648d 100644 --- a/Lib/sched.py +++ b/Lib/sched.py @@ -35,16 +35,12 @@ try: import threading except ImportError: import dummy_threading as threading -try: - from time import monotonic as _time -except ImportError: - from time import time as _time +from time import monotonic as _time __all__ = ["scheduler"] class Event(namedtuple('Event', 'time, priority, action, argument, kwargs')): def __eq__(s, o): return (s.time, s.priority) == (o.time, o.priority) - def __ne__(s, o): return (s.time, s.priority) != (o.time, o.priority) def __lt__(s, o): return (s.time, s.priority) < (o.time, o.priority) def __le__(s, o): return (s.time, s.priority) <= (o.time, o.priority) def __gt__(s, o): return (s.time, s.priority) > (o.time, o.priority) diff --git a/Lib/selectors.py b/Lib/selectors.py index beb7ef7..6d569c3 100644 --- a/Lib/selectors.py +++ b/Lib/selectors.py @@ -174,9 +174,9 @@ class BaseSelector(metaclass=ABCMeta): SelectorKey for this file object """ mapping = self.get_map() + if mapping is None: + raise RuntimeError('Selector is closed') try: - if mapping is None: - raise KeyError return mapping[fileobj] except KeyError: raise KeyError("{!r} is not registered".format(fileobj)) from None @@ -449,6 +449,64 @@ if hasattr(select, 'epoll'): super().close() +if hasattr(select, 'devpoll'): + + class DevpollSelector(_BaseSelectorImpl): + """Solaris /dev/poll selector.""" + + def __init__(self): + super().__init__() + self._devpoll = select.devpoll() + + def fileno(self): + return self._devpoll.fileno() + + def register(self, fileobj, events, data=None): + key = super().register(fileobj, events, data) + poll_events = 0 + if events & EVENT_READ: + poll_events |= select.POLLIN + if events & EVENT_WRITE: + poll_events |= select.POLLOUT + self._devpoll.register(key.fd, poll_events) + return key + + def unregister(self, fileobj): + key = super().unregister(fileobj) + self._devpoll.unregister(key.fd) + return key + + def select(self, timeout=None): + if timeout is None: + timeout = None + elif timeout <= 0: + timeout = 0 + else: + # devpoll() has a resolution of 1 millisecond, round away from + # zero to wait *at least* timeout seconds. + timeout = math.ceil(timeout * 1e3) + ready = [] + try: + fd_event_list = self._devpoll.poll(timeout) + except InterruptedError: + return ready + for fd, event in fd_event_list: + events = 0 + if event & ~select.POLLIN: + events |= EVENT_WRITE + if event & ~select.POLLOUT: + events |= EVENT_READ + + key = self._key_from_fd(fd) + if key: + ready.append((key, events & key.events)) + return ready + + def close(self): + self._devpoll.close() + super().close() + + if hasattr(select, 'kqueue'): class KqueueSelector(_BaseSelectorImpl): @@ -521,12 +579,15 @@ if hasattr(select, 'kqueue'): super().close() -# Choose the best implementation: roughly, epoll|kqueue > poll > select. +# Choose the best implementation, roughly: +# epoll|kqueue|devpoll > poll > select. # select() also can't accept a FD > FD_SETSIZE (usually around 1024) if 'KqueueSelector' in globals(): DefaultSelector = KqueueSelector elif 'EpollSelector' in globals(): DefaultSelector = EpollSelector +elif 'DevpollSelector' in globals(): + DefaultSelector = DevpollSelector elif 'PollSelector' in globals(): DefaultSelector = PollSelector else: diff --git a/Lib/shutil.py b/Lib/shutil.py index ac06ae5..61dc804 100644 --- a/Lib/shutil.py +++ b/Lib/shutil.py @@ -7,7 +7,6 @@ XXX The functions here don't copy the resource fork or other metadata on Mac. import os import sys import stat -from os.path import abspath import fnmatch import collections import errno @@ -21,6 +20,13 @@ except ImportError: _BZ2_SUPPORTED = False try: + import lzma + del lzma + _LZMA_SUPPORTED = True +except ImportError: + _LZMA_SUPPORTED = False + +try: from pwd import getpwnam except ImportError: getpwnam = None @@ -487,7 +493,7 @@ def _basename(path): sep = os.path.sep + (os.path.altsep or '') return os.path.basename(path.rstrip(sep)) -def move(src, dst): +def move(src, dst, copy_function=copy2): """Recursively move a file or directory to another location. This is similar to the Unix "mv" command. Return the file or directory's destination. @@ -504,6 +510,11 @@ def move(src, dst): recreated under the new name if os.rename() fails because of cross filesystem renames. + The optional `copy_function` argument is a callable that will be used + to copy the source or it will be delegated to `copytree`. + By default, copy2() is used, but any function that supports the same + signature (like copy()) can be used. + A lot more could be done here... A look at a mv.c shows a lot of the issues this implementation glosses over. @@ -528,17 +539,19 @@ def move(src, dst): os.unlink(src) elif os.path.isdir(src): if _destinsrc(src, dst): - raise Error("Cannot move a directory '%s' into itself '%s'." % (src, dst)) - copytree(src, real_dst, symlinks=True) + raise Error("Cannot move a directory '%s' into itself" + " '%s'." % (src, dst)) + copytree(src, real_dst, copy_function=copy_function, + symlinks=True) rmtree(src) else: - copy2(src, real_dst) + copy_function(src, real_dst) os.unlink(src) return real_dst def _destinsrc(src, dst): - src = abspath(src) - dst = abspath(dst) + src = os.path.abspath(src) + dst = os.path.abspath(dst) if not src.endswith(os.path.sep): src += os.path.sep if not dst.endswith(os.path.sep): @@ -574,14 +587,14 @@ def _make_tarball(base_name, base_dir, compress="gzip", verbose=0, dry_run=0, """Create a (possibly compressed) tar file from all the files under 'base_dir'. - 'compress' must be "gzip" (the default), "bzip2", or None. + 'compress' must be "gzip" (the default), "bzip2", "xz", or None. 'owner' and 'group' can be used to define an owner and a group for the archive that is being built. If not provided, the current owner and group will be used. The output tar file will be named 'base_name' + ".tar", possibly plus - the appropriate compression extension (".gz", or ".bz2"). + the appropriate compression extension (".gz", ".bz2", or ".xz"). Returns the output filename. """ @@ -592,6 +605,10 @@ def _make_tarball(base_name, base_dir, compress="gzip", verbose=0, dry_run=0, tar_compression['bzip2'] = 'bz2' compress_ext['bzip2'] = '.bz2' + if _LZMA_SUPPORTED: + tar_compression['xz'] = 'xz' + compress_ext['xz'] = '.xz' + # flags for compression program, each element of list will be an argument if compress is not None and compress not in compress_ext: raise ValueError("bad value for 'compress', or compression format not " @@ -631,23 +648,6 @@ def _make_tarball(base_name, base_dir, compress="gzip", verbose=0, dry_run=0, return archive_name -def _call_external_zip(base_dir, zip_filename, verbose=False, dry_run=False): - # XXX see if we want to keep an external call here - if verbose: - zipoptions = "-r" - else: - zipoptions = "-rq" - from distutils.errors import DistutilsExecError - from distutils.spawn import spawn - try: - spawn(["zip", zipoptions, zip_filename, base_dir], dry_run=dry_run) - except DistutilsExecError: - # XXX really should distinguish between "couldn't find - # external 'zip' command" and "zip failed". - raise ExecError("unable to create zip file '%s': " - "could neither import the 'zipfile' module nor " - "find a standalone zip utility") % zip_filename - def _make_zipfile(base_name, base_dir, verbose=0, dry_run=0, logger=None): """Create a zip file from all the files under 'base_dir'. @@ -657,6 +657,8 @@ def _make_zipfile(base_name, base_dir, verbose=0, dry_run=0, logger=None): available, raises ExecError. Returns the name of the output zip file. """ + import zipfile + zip_filename = base_name + ".zip" archive_dir = os.path.dirname(base_name) @@ -666,30 +668,20 @@ def _make_zipfile(base_name, base_dir, verbose=0, dry_run=0, logger=None): if not dry_run: os.makedirs(archive_dir) - # If zipfile module is not available, try spawning an external 'zip' - # command. - try: - import zipfile - except ImportError: - zipfile = None - - if zipfile is None: - _call_external_zip(base_dir, zip_filename, verbose, dry_run) - else: - if logger is not None: - logger.info("creating '%s' and adding '%s' to it", - zip_filename, base_dir) + if logger is not None: + logger.info("creating '%s' and adding '%s' to it", + zip_filename, base_dir) - if not dry_run: - with zipfile.ZipFile(zip_filename, "w", - compression=zipfile.ZIP_DEFLATED) as zf: - for dirpath, dirnames, filenames in os.walk(base_dir): - for name in filenames: - path = os.path.normpath(os.path.join(dirpath, name)) - if os.path.isfile(path): - zf.write(path, path) - if logger is not None: - logger.info("adding '%s'", path) + if not dry_run: + with zipfile.ZipFile(zip_filename, "w", + compression=zipfile.ZIP_DEFLATED) as zf: + for dirpath, dirnames, filenames in os.walk(base_dir): + for name in filenames: + path = os.path.normpath(os.path.join(dirpath, name)) + if os.path.isfile(path): + zf.write(path, path) + if logger is not None: + logger.info("adding '%s'", path) return zip_filename @@ -703,6 +695,10 @@ if _BZ2_SUPPORTED: _ARCHIVE_FORMATS['bztar'] = (_make_tarball, [('compress', 'bzip2')], "bzip2'ed tar-file") +if _LZMA_SUPPORTED: + _ARCHIVE_FORMATS['xztar'] = (_make_tarball, [('compress', 'xz')], + "xz'ed tar-file") + def get_archive_formats(): """Returns a list of supported formats for archiving and unarchiving. @@ -891,7 +887,7 @@ def _unpack_zipfile(filename, extract_dir): zip.close() def _unpack_tarfile(filename, extract_dir): - """Unpack tar/tar.gz/tar.bz2 `filename` to `extract_dir` + """Unpack tar/tar.gz/tar.bz2/tar.xz `filename` to `extract_dir` """ try: tarobj = tarfile.open(filename) @@ -910,9 +906,13 @@ _UNPACK_FORMATS = { } if _BZ2_SUPPORTED: - _UNPACK_FORMATS['bztar'] = (['.bz2'], _unpack_tarfile, [], + _UNPACK_FORMATS['bztar'] = (['.tar.bz2', '.tbz2'], _unpack_tarfile, [], "bzip2'ed tar-file") +if _LZMA_SUPPORTED: + _UNPACK_FORMATS['xztar'] = (['.tar.xz', '.txz'], _unpack_tarfile, [], + "xz'ed tar-file") + def _find_unpack_format(filename): for name, info in _UNPACK_FORMATS.items(): for extension in info[0]: diff --git a/Lib/signal.py b/Lib/signal.py new file mode 100644 index 0000000..0db3df8 --- /dev/null +++ b/Lib/signal.py @@ -0,0 +1,85 @@ +import _signal +from _signal import * +from functools import wraps as _wraps +from enum import IntEnum as _IntEnum + +_globals = globals() + +Signals = _IntEnum( + 'Signals', + {name: value for name, value in _globals.items() + if name.isupper() + and (name.startswith('SIG') and not name.startswith('SIG_')) + or name.startswith('CTRL_')}) + +class Handlers(_IntEnum): + SIG_DFL = _signal.SIG_DFL + SIG_IGN = _signal.SIG_IGN + +_globals.update(Signals.__members__) +_globals.update(Handlers.__members__) + +if 'pthread_sigmask' in _globals: + class Sigmasks(_IntEnum): + SIG_BLOCK = _signal.SIG_BLOCK + SIG_UNBLOCK = _signal.SIG_UNBLOCK + SIG_SETMASK = _signal.SIG_SETMASK + + _globals.update(Sigmasks.__members__) + + +def _int_to_enum(value, enum_klass): + """Convert a numeric value to an IntEnum member. + If it's not a known member, return the numeric value itself. + """ + try: + return enum_klass(value) + except ValueError: + return value + + +def _enum_to_int(value): + """Convert an IntEnum member to a numeric value. + If it's not a IntEnum member return the value itself. + """ + try: + return int(value) + except (ValueError, TypeError): + return value + + +@_wraps(_signal.signal) +def signal(signalnum, handler): + handler = _signal.signal(_enum_to_int(signalnum), _enum_to_int(handler)) + return _int_to_enum(handler, Handlers) + + +@_wraps(_signal.getsignal) +def getsignal(signalnum): + handler = _signal.getsignal(signalnum) + return _int_to_enum(handler, Handlers) + + +if 'pthread_sigmask' in _globals: + @_wraps(_signal.pthread_sigmask) + def pthread_sigmask(how, mask): + sigs_set = _signal.pthread_sigmask(how, mask) + return set(_int_to_enum(x, Signals) for x in sigs_set) + pthread_sigmask.__doc__ = _signal.pthread_sigmask.__doc__ + + +if 'sigpending' in _globals: + @_wraps(_signal.sigpending) + def sigpending(): + sigs = _signal.sigpending() + return set(_int_to_enum(x, Signals) for x in sigs) + + +if 'sigwait' in _globals: + @_wraps(_signal.sigwait) + def sigwait(sigset): + retsig = _signal.sigwait(sigset) + return _int_to_enum(retsig, Signals) + sigwait.__doc__ = _signal.sigwait + +del _globals, _wraps diff --git a/Lib/site.py b/Lib/site.py index ad5d136..4959cfc 100644 --- a/Lib/site.py +++ b/Lib/site.py @@ -7,7 +7,7 @@ This will append site-specific paths to the module search path. On Unix (including Mac OSX), it starts with sys.prefix and sys.exec_prefix (if different) and appends -lib/python<version>/site-packages as well as lib/site-python. +lib/python<version>/site-packages. On other platforms (such as Windows), it tries each of the prefixes directly, as well as with lib/site-packages appended. The resulting directories, if they exist, are appended to sys.path, and @@ -15,7 +15,7 @@ also inspected for path configuration files. If a file named "pyvenv.cfg" exists one directory above sys.executable, sys.prefix and sys.exec_prefix are set to that directory and -it is also checked for site-packages and site-python (sys.base_prefix and +it is also checked for site-packages (sys.base_prefix and sys.base_exec_prefix will always be the "real" prefixes of the Python installation). If "pyvenv.cfg" (a bootstrap configuration file) contains the key "include-system-site-packages" set to anything other than "false" @@ -285,8 +285,7 @@ def addusersitepackages(known_paths): return known_paths def getsitepackages(prefixes=None): - """Returns a list containing all global site-packages directories - (and possibly site-python). + """Returns a list containing all global site-packages directories. For each directory present in ``prefixes`` (or the global ``PREFIXES``), this function will find its `site-packages` subdirectory depending on the @@ -307,7 +306,6 @@ def getsitepackages(prefixes=None): sitepackages.append(os.path.join(prefix, "lib", "python" + sys.version[:3], "site-packages")) - sitepackages.append(os.path.join(prefix, "lib", "site-python")) else: sitepackages.append(prefix) sitepackages.append(os.path.join(prefix, "lib", "site-packages")) @@ -323,14 +321,9 @@ def getsitepackages(prefixes=None): return sitepackages def addsitepackages(known_paths, prefixes=None): - """Add site-packages (and possibly site-python) to sys.path""" + """Add site-packages to sys.path""" for sitedir in getsitepackages(prefixes): if os.path.isdir(sitedir): - if "site-python" in sitedir: - import warnings - warnings.warn('"site-python" directories will not be ' - 'supported in 3.5 anymore', - DeprecationWarning) addsitedir(sitedir, known_paths) return known_paths diff --git a/Lib/smtpd.py b/Lib/smtpd.py index 1fa157a..33653d4 100755 --- a/Lib/smtpd.py +++ b/Lib/smtpd.py @@ -1,5 +1,5 @@ #! /usr/bin/env python3 -"""An RFC 5321 smtp proxy. +"""An RFC 5321 smtp proxy with optional RFC 1870 and RFC 6531 extensions. Usage: %(program)s [options] [localhost:localport [remotehost:remoteport]] @@ -25,6 +25,10 @@ Options: Restrict the total size of the incoming message to "limit" number of bytes via the RFC 1870 SIZE extension. Defaults to 33554432 bytes. + --smtputf8 + -u + Enable the SMTPUTF8 extension and behave as an RFC 6531 smtp proxy. + --debug -d Turn on debugging prints. @@ -98,7 +102,6 @@ class Devnull: DEBUGSTREAM = Devnull() NEWLINE = '\n' -EMPTYSTRING = '' COMMASPACE = ', ' DATA_SIZE_DEFAULT = 33554432 @@ -116,26 +119,48 @@ class SMTPChannel(asynchat.async_chat): command_size_limit = 512 command_size_limits = collections.defaultdict(lambda x=command_size_limit: x) - command_size_limits.update({ - 'MAIL': command_size_limit + 26, - }) - max_command_size_limit = max(command_size_limits.values()) + + @property + def max_command_size_limit(self): + try: + return max(self.command_size_limits.values()) + except ValueError: + return self.command_size_limit def __init__(self, server, conn, addr, data_size_limit=DATA_SIZE_DEFAULT, - map=None): + map=None, enable_SMTPUTF8=False, decode_data=None): asynchat.async_chat.__init__(self, conn, map=map) self.smtp_server = server self.conn = conn self.addr = addr self.data_size_limit = data_size_limit - self.received_lines = [] - self.smtp_state = self.COMMAND + self.enable_SMTPUTF8 = enable_SMTPUTF8 + if enable_SMTPUTF8: + if decode_data: + ValueError("decode_data and enable_SMTPUTF8 cannot be set to" + " True at the same time") + decode_data = False + if decode_data is None: + warn("The decode_data default of True will change to False in 3.6;" + " specify an explicit value for this keyword", + DeprecationWarning, 2) + decode_data = True + self._decode_data = decode_data + if decode_data: + self._emptystring = '' + self._linesep = '\r\n' + self._dotsep = '.' + self._newline = NEWLINE + else: + self._emptystring = b'' + self._linesep = b'\r\n' + self._dotsep = b'.' + self._newline = b'\n' + self._set_rset_state() self.seen_greeting = '' - self.mailfrom = None - self.rcpttos = [] - self.received_data = '' + self.extended_smtp = False + self.command_size_limits.clear() self.fqdn = socket.getfqdn() - self.num_bytes = 0 try: self.peer = conn.getpeername() except OSError as err: @@ -147,8 +172,22 @@ class SMTPChannel(asynchat.async_chat): return print('Peer:', repr(self.peer), file=DEBUGSTREAM) self.push('220 %s %s' % (self.fqdn, __version__)) + + def _set_post_data_state(self): + """Reset state variables to their post-DATA state.""" + self.smtp_state = self.COMMAND + self.mailfrom = None + self.rcpttos = [] + self.require_SMTPUTF8 = False + self.num_bytes = 0 self.set_terminator(b'\r\n') - self.extended_smtp = False + + def _set_rset_state(self): + """Reset all state variables except the greeting.""" + self._set_post_data_state() + self.received_data = '' + self.received_lines = [] + # properties for backwards-compatibility @property @@ -272,9 +311,10 @@ class SMTPChannel(asynchat.async_chat): "set 'addr' instead", DeprecationWarning, 2) self.addr = value - # Overrides base class for convenience + # Overrides base class for convenience. def push(self, msg): - asynchat.async_chat.push(self, bytes(msg + '\r\n', 'ascii')) + asynchat.async_chat.push(self, bytes( + msg + '\r\n', 'utf-8' if self.require_SMTPUTF8 else 'ascii')) # Implementation of base class abstract method def collect_incoming_data(self, data): @@ -287,11 +327,14 @@ class SMTPChannel(asynchat.async_chat): return elif limit: self.num_bytes += len(data) - self.received_lines.append(str(data, "utf-8")) + if self._decode_data: + self.received_lines.append(str(data, 'utf-8')) + else: + self.received_lines.append(data) # Implementation of base class abstract method def found_terminator(self): - line = EMPTYSTRING.join(self.received_lines) + line = self._emptystring.join(self.received_lines) print('Data:', repr(line), file=DEBUGSTREAM) self.received_lines = [] if self.smtp_state == self.COMMAND: @@ -299,7 +342,8 @@ class SMTPChannel(asynchat.async_chat): if not line: self.push('500 Error: bad syntax') return - method = None + if not self._decode_data: + line = str(line, 'utf-8') i = line.find(' ') if i < 0: command = line.upper() @@ -330,21 +374,18 @@ class SMTPChannel(asynchat.async_chat): # Remove extraneous carriage returns and de-transparency according # to RFC 5321, Section 4.5.2. data = [] - for text in line.split('\r\n'): - if text and text[0] == '.': + for text in line.split(self._linesep): + if text and text[0] == self._dotsep: data.append(text[1:]) else: data.append(text) - self.received_data = NEWLINE.join(data) - status = self.smtp_server.process_message(self.peer, - self.mailfrom, - self.rcpttos, - self.received_data) - self.rcpttos = [] - self.mailfrom = None - self.smtp_state = self.COMMAND - self.num_bytes = 0 - self.set_terminator(b'\r\n') + self.received_data = self._newline.join(data) + args = (self.peer, self.mailfrom, self.rcpttos, self.received_data) + if self.require_SMTPUTF8: + status = self.smtp_server.process_smtputf8_message(*args) + else: + status = self.smtp_server.process_message(*args) + self._set_post_data_state() if not status: self.push('250 OK') else: @@ -355,26 +396,34 @@ class SMTPChannel(asynchat.async_chat): if not arg: self.push('501 Syntax: HELO hostname') return + # See issue #21783 for a discussion of this behavior. if self.seen_greeting: self.push('503 Duplicate HELO/EHLO') - else: - self.seen_greeting = arg - self.extended_smtp = False - self.push('250 %s' % self.fqdn) + return + self._set_rset_state() + self.seen_greeting = arg + self.push('250 %s' % self.fqdn) def smtp_EHLO(self, arg): if not arg: self.push('501 Syntax: EHLO hostname') return + # See issue #21783 for a discussion of this behavior. if self.seen_greeting: self.push('503 Duplicate HELO/EHLO') - else: - self.seen_greeting = arg - self.extended_smtp = True - self.push('250-%s' % self.fqdn) - if self.data_size_limit: - self.push('250-SIZE %s' % self.data_size_limit) - self.push('250 HELP') + return + self._set_rset_state() + self.seen_greeting = arg + self.extended_smtp = True + self.push('250-%s' % self.fqdn) + if self.data_size_limit: + self.push('250-SIZE %s' % self.data_size_limit) + self.command_size_limits['MAIL'] += 26 + if self.enable_SMTPUTF8: + self.push('250-8BITMIME') + self.push('250-SMTPUTF8') + self.command_size_limits['MAIL'] += 10 + self.push('250 HELP') def smtp_NOOP(self, arg): if arg: @@ -407,8 +456,8 @@ class SMTPChannel(asynchat.async_chat): def _getparams(self, params): # Return any parameters that appear to be syntactically valid according # to RFC 1869, ignore all others. (Postel rule: accept what we can.) - params = [param.split('=', 1) for param in params.split() - if '=' in param] + params = [param.split('=', 1) if '=' in param else (param, True) + for param in params.split()] return {k: v for k, v in params if k.isalnum()} def smtp_HELP(self, arg): @@ -486,6 +535,14 @@ class SMTPChannel(asynchat.async_chat): if params is None: self.push(syntaxerr) return + body = params.pop('BODY', '7BIT') + if self.enable_SMTPUTF8 and params.pop('SMTPUTF8', False): + if body != '8BITMIME': + self.push('501 Syntax: MAIL FROM: <address>' + ' [BODY=8BITMIME SMTPUTF8]') + return + else: + self.require_SMTPUTF8 = True size = params.pop('SIZE', None) if size: if not size.isdigit(): @@ -546,11 +603,7 @@ class SMTPChannel(asynchat.async_chat): if arg: self.push('501 Syntax: RSET') return - # Resets the sender, recipients, and data, but not the greeting - self.mailfrom = None - self.rcpttos = [] - self.received_data = '' - self.smtp_state = self.COMMAND + self._set_rset_state() self.push('250 OK') def smtp_DATA(self, arg): @@ -577,13 +630,29 @@ class SMTPServer(asyncore.dispatcher): channel_class = SMTPChannel def __init__(self, localaddr, remoteaddr, - data_size_limit=DATA_SIZE_DEFAULT, map=None): + data_size_limit=DATA_SIZE_DEFAULT, map=None, + enable_SMTPUTF8=False, decode_data=None): self._localaddr = localaddr self._remoteaddr = remoteaddr self.data_size_limit = data_size_limit + self.enable_SMTPUTF8 = enable_SMTPUTF8 + if enable_SMTPUTF8: + if decode_data: + raise ValueError("The decode_data and enable_SMTPUTF8" + " parameters cannot be set to True at the" + " same time.") + decode_data = False + if decode_data is None: + warn("The decode_data default of True will change to False in 3.6;" + " specify an explicit value for this keyword", + DeprecationWarning, 2) + decode_data = True + self._decode_data = decode_data asyncore.dispatcher.__init__(self, map=map) try: - self.create_socket(socket.AF_INET, socket.SOCK_STREAM) + gai_results = socket.getaddrinfo(*localaddr, + type=socket.SOCK_STREAM) + self.create_socket(gai_results[0][0], gai_results[0][1]) # try to re-use a server port if possible self.set_reuse_addr() self.bind(localaddr) @@ -598,8 +667,13 @@ class SMTPServer(asyncore.dispatcher): def handle_accepted(self, conn, addr): print('Incoming connection from %s' % repr(addr), file=DEBUGSTREAM) - channel = self.channel_class(self, conn, addr, self.data_size_limit, - self._map) + channel = self.channel_class(self, + conn, + addr, + self.data_size_limit, + self._map, + self.enable_SMTPUTF8, + self._decode_data) # API for "doing something useful with the message" def process_message(self, peer, mailfrom, rcpttos, data): @@ -620,29 +694,63 @@ class SMTPServer(asyncore.dispatcher): containing a `.' followed by other text has had the leading dot removed. - This function should return None, for a normal `250 Ok' response; - otherwise it returns the desired response string in RFC 821 format. + This function should return None for a normal `250 Ok' response; + otherwise, it should return the desired response string in RFC 821 + format. + + """ + raise NotImplementedError + + # API for processing messeges needing Unicode support (RFC 6531, RFC 6532). + def process_smtputf8_message(self, peer, mailfrom, rcpttos, data): + """Same as ``process_message`` but for messages for which the client + has sent the SMTPUTF8 parameter with the MAIL command (see the + enable_SMTPUTF8 parameter of the constructor). + + This function should return None for a normal `250 Ok' response; + otherwise, it should return the desired response string in RFC 6531 + format. """ raise NotImplementedError class DebuggingServer(SMTPServer): - # Do something with the gathered message - def process_message(self, peer, mailfrom, rcpttos, data): + + def _print_message_content(self, peer, data): inheaders = 1 - lines = data.split('\n') - print('---------- MESSAGE FOLLOWS ----------') + lines = data.splitlines() for line in lines: # headers first if inheaders and not line: - print('X-Peer:', peer[0]) + peerheader = 'X-Peer: ' + peer[0] + if not isinstance(data, str): + # decoded_data=false; make header match other binary output + peerheader = repr(peerheader.encode('utf-8')) + print(peerheader) inheaders = 0 + if not isinstance(data, str): + # Avoid spurious 'str on bytes instance' warning. + line = repr(line) print(line) + + def process_message(self, peer, mailfrom, rcpttos, data): + print('---------- MESSAGE FOLLOWS ----------') + self._print_message_content(peer, data) + print('------------ END MESSAGE ------------') + + def process_smtputf8_message(self, peer, mailfrom, rcpttos, data): + print('----- SMTPUTF8 MESSAGE FOLLOWS ------') + self._print_message_content(peer, data) print('------------ END MESSAGE ------------') class PureProxy(SMTPServer): + def __init__(self, *args, **kwargs): + if 'enable_SMTPUTF8' in kwargs and kwargs['enable_SMTPUTF8']: + raise ValueError("PureProxy does not support SMTPUTF8.") + super(PureProxy, self).__init__(*args, **kwargs) + def process_message(self, peer, mailfrom, rcpttos, data): lines = data.split('\n') # Look for the last header @@ -683,6 +791,11 @@ class PureProxy(SMTPServer): class MailmanProxy(PureProxy): + def __init__(self, *args, **kwargs): + if 'enable_SMTPUTF8' in kwargs and kwargs['enable_SMTPUTF8']: + raise ValueError("MailmanProxy does not support SMTPUTF8.") + super(PureProxy, self).__init__(*args, **kwargs) + def process_message(self, peer, mailfrom, rcpttos, data): from io import StringIO from Mailman import Utils @@ -761,17 +874,19 @@ class MailmanProxy(PureProxy): class Options: - setuid = 1 + setuid = True classname = 'PureProxy' size_limit = None + enable_SMTPUTF8 = False def parseargs(): global DEBUGSTREAM try: opts, args = getopt.getopt( - sys.argv[1:], 'nVhc:s:d', - ['class=', 'nosetuid', 'version', 'help', 'size=', 'debug']) + sys.argv[1:], 'nVhc:s:du', + ['class=', 'nosetuid', 'version', 'help', 'size=', 'debug', + 'smtputf8']) except getopt.error as e: usage(1, e) @@ -783,11 +898,13 @@ def parseargs(): print(__version__) sys.exit(0) elif opt in ('-n', '--nosetuid'): - options.setuid = 0 + options.setuid = False elif opt in ('-c', '--class'): options.classname = arg elif opt in ('-d', '--debug'): DEBUGSTREAM = sys.stderr + elif opt in ('-u', '--smtputf8'): + options.enable_SMTPUTF8 = True elif opt in ('-s', '--size'): try: int_size = int(arg) @@ -842,7 +959,7 @@ if __name__ == '__main__': class_ = getattr(mod, classname) proxy = class_((options.localhost, options.localport), (options.remotehost, options.remoteport), - options.size_limit) + options.size_limit, enable_SMTPUTF8=options.enable_SMTPUTF8) if options.setuid: try: import pwd diff --git a/Lib/smtplib.py b/Lib/smtplib.py index fa7f9e6..327a454 100755 --- a/Lib/smtplib.py +++ b/Lib/smtplib.py @@ -571,12 +571,60 @@ class SMTP: if not (200 <= code <= 299): raise SMTPHeloError(code, resp) + def auth(self, mechanism, authobject): + """Authentication command - requires response processing. + + 'mechanism' specifies which authentication mechanism is to + be used - the valid values are those listed in the 'auth' + element of 'esmtp_features'. + + 'authobject' must be a callable object taking a single argument: + + data = authobject(challenge) + + It will be called to process the server's challenge response; the + challenge argument it is passed will be a bytes. It should return + bytes data that will be base64 encoded and sent to the server. + """ + + mechanism = mechanism.upper() + (code, resp) = self.docmd("AUTH", mechanism) + # Server replies with 334 (challenge) or 535 (not supported) + if code == 334: + challenge = base64.decodebytes(resp) + response = encode_base64( + authobject(challenge).encode('ascii'), eol='') + (code, resp) = self.docmd(response) + if code in (235, 503): + return (code, resp) + raise SMTPAuthenticationError(code, resp) + + def auth_cram_md5(self, challenge): + """ Authobject to use with CRAM-MD5 authentication. Requires self.user + and self.password to be set.""" + return self.user + " " + hmac.HMAC( + self.password.encode('ascii'), challenge, 'md5').hexdigest() + + def auth_plain(self, challenge): + """ Authobject to use with PLAIN authentication. Requires self.user and + self.password to be set.""" + return "\0%s\0%s" % (self.user, self.password) + + def auth_login(self, challenge): + """ Authobject to use with LOGIN authentication. Requires self.user and + self.password to be set.""" + (code, resp) = self.docmd( + encode_base64(self.user.encode('ascii'), eol='')) + if code == 334: + return self.password + raise SMTPAuthenticationError(code, resp) + def login(self, user, password): """Log in on an SMTP server that requires authentication. The arguments are: - - user: The user name to authenticate with. - - password: The password for the authentication. + - user: The user name to authenticate with. + - password: The password for the authentication. If there has been no previous EHLO or HELO command this session, this method tries ESMTP EHLO first. @@ -593,63 +641,40 @@ class SMTP: found. """ - def encode_cram_md5(challenge, user, password): - challenge = base64.decodebytes(challenge) - response = user + " " + hmac.HMAC(password.encode('ascii'), - challenge, 'md5').hexdigest() - return encode_base64(response.encode('ascii'), eol='') - - def encode_plain(user, password): - s = "\0%s\0%s" % (user, password) - return encode_base64(s.encode('ascii'), eol='') - - AUTH_PLAIN = "PLAIN" - AUTH_CRAM_MD5 = "CRAM-MD5" - AUTH_LOGIN = "LOGIN" - self.ehlo_or_helo_if_needed() - if not self.has_extn("auth"): raise SMTPException("SMTP AUTH extension not supported by server.") # Authentication methods the server claims to support advertised_authlist = self.esmtp_features["auth"].split() - # List of authentication methods we support: from preferred to - # less preferred methods. Except for the purpose of testing the weaker - # ones, we prefer stronger methods like CRAM-MD5: - preferred_auths = [AUTH_CRAM_MD5, AUTH_PLAIN, AUTH_LOGIN] + # Authentication methods we can handle in our preferred order: + preferred_auths = ['CRAM-MD5', 'PLAIN', 'LOGIN'] - # We try the authentication methods the server advertises, but only the - # ones *we* support. And in our preferred order. - authlist = [auth for auth in preferred_auths if auth in advertised_authlist] + # We try the supported authentications in our preferred order, if + # the server supports them. + authlist = [auth for auth in preferred_auths + if auth in advertised_authlist] if not authlist: raise SMTPException("No suitable authentication method found.") # Some servers advertise authentication methods they don't really # support, so if authentication fails, we continue until we've tried # all methods. + self.user, self.password = user, password for authmethod in authlist: - if authmethod == AUTH_CRAM_MD5: - (code, resp) = self.docmd("AUTH", AUTH_CRAM_MD5) - if code == 334: - (code, resp) = self.docmd(encode_cram_md5(resp, user, password)) - elif authmethod == AUTH_PLAIN: - (code, resp) = self.docmd("AUTH", - AUTH_PLAIN + " " + encode_plain(user, password)) - elif authmethod == AUTH_LOGIN: - (code, resp) = self.docmd("AUTH", - "%s %s" % (AUTH_LOGIN, encode_base64(user.encode('ascii'), eol=''))) - if code == 334: - (code, resp) = self.docmd(encode_base64(password.encode('ascii'), eol='')) - - # 235 == 'Authentication successful' - # 503 == 'Error: already authenticated' - if code in (235, 503): - return (code, resp) - - # We could not login sucessfully. Return result of last attempt. - raise SMTPAuthenticationError(code, resp) + method_name = 'auth_' + authmethod.lower().replace('-', '_') + try: + (code, resp) = self.auth(authmethod, getattr(self, method_name)) + # 235 == 'Authentication successful' + # 503 == 'Error: already authenticated' + if code in (235, 503): + return (code, resp) + except SMTPAuthenticationError as e: + last_exception = e + + # We could not login successfully. Return result of last attempt. + raise last_exception def starttls(self, keyfile=None, certfile=None, context=None): """Puts the connection to the SMTP server into TLS mode. diff --git a/Lib/sndhdr.py b/Lib/sndhdr.py index 240e507..e5901ec 100644 --- a/Lib/sndhdr.py +++ b/Lib/sndhdr.py @@ -32,6 +32,11 @@ explicitly given directories. __all__ = ['what', 'whathdr'] +from collections import namedtuple + +SndHeaders = namedtuple('SndHeaders', + 'filetype framerate nchannels nframes sampwidth') + def what(filename): """Guess the type of a sound file.""" res = whathdr(filename) @@ -45,7 +50,7 @@ def whathdr(filename): for tf in tests: res = tf(h, f) if res: - return res + return SndHeaders(*res) return None diff --git a/Lib/socket.py b/Lib/socket.py index 8efd760..9c39c69 100644 --- a/Lib/socket.py +++ b/Lib/socket.py @@ -49,7 +49,7 @@ the setsockopt() and getsockopt() methods. import _socket from _socket import * -import os, sys, io +import os, sys, io, selectors from enum import IntEnum try: @@ -79,6 +79,11 @@ SocketKind = IntEnum('SocketKind', if name.isupper() and name.startswith('SOCK_')}) globals().update(SocketKind.__members__) + +_LOCALHOST = '127.0.0.1' +_LOCALHOST_V6 = '::1' + + def _intenum_converter(value, enum_klass): """Convert a numeric family value to an IntEnum member. @@ -112,6 +117,9 @@ if sys.platform.lower().startswith("win"): __all__.append("errorTab") +class _GiveupOnSendfile(Exception): pass + + class socket(_socket.socket): """A subclass of _socket.socket adding the makefile() method.""" @@ -141,7 +149,7 @@ class socket(_socket.socket): closed = getattr(self, '_closed', False) s = "<%s.%s%s fd=%i, family=%s, type=%s, proto=%i" \ % (self.__class__.__module__, - self.__class__.__name__, + self.__class__.__qualname__, " [closed]" if closed else "", self.fileno(), self.family, @@ -235,6 +243,149 @@ class socket(_socket.socket): text.mode = mode return text + if hasattr(os, 'sendfile'): + + def _sendfile_use_sendfile(self, file, offset=0, count=None): + self._check_sendfile_params(file, offset, count) + sockno = self.fileno() + try: + fileno = file.fileno() + except (AttributeError, io.UnsupportedOperation) as err: + raise _GiveupOnSendfile(err) # not a regular file + try: + fsize = os.fstat(fileno).st_size + except OSError: + raise _GiveupOnSendfile(err) # not a regular file + if not fsize: + return 0 # empty file + blocksize = fsize if not count else count + + timeout = self.gettimeout() + if timeout == 0: + raise ValueError("non-blocking sockets are not supported") + # poll/select have the advantage of not requiring any + # extra file descriptor, contrarily to epoll/kqueue + # (also, they require a single syscall). + if hasattr(selectors, 'PollSelector'): + selector = selectors.PollSelector() + else: + selector = selectors.SelectSelector() + selector.register(sockno, selectors.EVENT_WRITE) + + total_sent = 0 + # localize variable access to minimize overhead + selector_select = selector.select + os_sendfile = os.sendfile + try: + while True: + if timeout and not selector_select(timeout): + raise _socket.timeout('timed out') + if count: + blocksize = count - total_sent + if blocksize <= 0: + break + try: + sent = os_sendfile(sockno, fileno, offset, blocksize) + except BlockingIOError: + if not timeout: + # Block until the socket is ready to send some + # data; avoids hogging CPU resources. + selector_select() + continue + except OSError as err: + if total_sent == 0: + # We can get here for different reasons, the main + # one being 'file' is not a regular mmap(2)-like + # file, in which case we'll fall back on using + # plain send(). + raise _GiveupOnSendfile(err) + raise err from None + else: + if sent == 0: + break # EOF + offset += sent + total_sent += sent + return total_sent + finally: + if total_sent > 0 and hasattr(file, 'seek'): + file.seek(offset) + else: + def _sendfile_use_sendfile(self, file, offset=0, count=None): + raise _GiveupOnSendfile( + "os.sendfile() not available on this platform") + + def _sendfile_use_send(self, file, offset=0, count=None): + self._check_sendfile_params(file, offset, count) + if self.gettimeout() == 0: + raise ValueError("non-blocking sockets are not supported") + if offset: + file.seek(offset) + blocksize = min(count, 8192) if count else 8192 + total_sent = 0 + # localize variable access to minimize overhead + file_read = file.read + sock_send = self.send + try: + while True: + if count: + blocksize = min(count - total_sent, blocksize) + if blocksize <= 0: + break + data = memoryview(file_read(blocksize)) + if not data: + break # EOF + while True: + try: + sent = sock_send(data) + except BlockingIOError: + continue + else: + total_sent += sent + if sent < len(data): + data = data[sent:] + else: + break + return total_sent + finally: + if total_sent > 0 and hasattr(file, 'seek'): + file.seek(offset + total_sent) + + def _check_sendfile_params(self, file, offset, count): + if 'b' not in getattr(file, 'mode', 'b'): + raise ValueError("file should be opened in binary mode") + if not self.type & SOCK_STREAM: + raise ValueError("only SOCK_STREAM type sockets are supported") + if count is not None: + if not isinstance(count, int): + raise TypeError( + "count must be a positive integer (got {!r})".format(count)) + if count <= 0: + raise ValueError( + "count must be a positive integer (got {!r})".format(count)) + + def sendfile(self, file, offset=0, count=None): + """sendfile(file[, offset[, count]]) -> sent + + Send a file until EOF is reached by using high-performance + os.sendfile() and return the total number of bytes which + were sent. + *file* must be a regular file object opened in binary mode. + If os.sendfile() is not available (e.g. Windows) or file is + not a regular file socket.send() will be used instead. + *offset* tells from where to start reading the file. + If specified, *count* is the total number of bytes to transmit + as opposed to sending the file until EOF is reached. + File position is updated on return or also in case of error in + which case file.tell() can be used to figure out the number of + bytes which were sent. + The socket must be of SOCK_STREAM type. + Non-blocking sockets are not supported. + """ + try: + return self._sendfile_use_sendfile(file, offset, count) + except _GiveupOnSendfile: + return self._sendfile_use_send(file, offset, count) + def _decref_socketios(self): if self._io_refs > 0: self._io_refs -= 1 @@ -325,6 +476,52 @@ if hasattr(_socket, "socketpair"): b = socket(family, type, proto, b.detach()) return a, b +else: + + # Origin: https://gist.github.com/4325783, by Geert Jansen. Public domain. + def socketpair(family=AF_INET, type=SOCK_STREAM, proto=0): + if family == AF_INET: + host = _LOCALHOST + elif family == AF_INET6: + host = _LOCALHOST_V6 + else: + raise ValueError("Only AF_INET and AF_INET6 socket address families " + "are supported") + if type != SOCK_STREAM: + raise ValueError("Only SOCK_STREAM socket type is supported") + if proto != 0: + raise ValueError("Only protocol zero is supported") + + # We create a connected TCP socket. Note the trick with + # setblocking(False) that prevents us from having to create a thread. + lsock = socket(family, type, proto) + try: + lsock.bind((host, 0)) + lsock.listen() + # On IPv6, ignore flow_info and scope_id + addr, port = lsock.getsockname()[:2] + csock = socket(family, type, proto) + try: + csock.setblocking(False) + try: + csock.connect((addr, port)) + except (BlockingIOError, InterruptedError): + pass + csock.setblocking(True) + ssock, _ = lsock.accept() + except: + csock.close() + raise + finally: + lsock.close() + return (ssock, csock) + +socketpair.__doc__ = """socketpair([family[, type[, proto]]]) -> (socket object, socket object) +Create a pair of socket objects from the sockets returned by the platform +socketpair() function. +The arguments are the same as for socket() except the default family is AF_UNIX +if defined on the platform; otherwise, the default is AF_INET. +""" _blocking_errnos = { EAGAIN, EWOULDBLOCK } @@ -375,8 +572,6 @@ class SocketIO(io.RawIOBase): except timeout: self._timeout_occurred = True raise - except InterruptedError: - continue except error as e: if e.args[0] in _blocking_errnos: return None diff --git a/Lib/socketserver.py b/Lib/socketserver.py index 5cb89be..0ce8e81 100644 --- a/Lib/socketserver.py +++ b/Lib/socketserver.py @@ -94,7 +94,7 @@ handle() method. Another approach to handling multiple simultaneous requests in an environment that supports neither threads nor fork (or where these are too expensive or inappropriate for the service) is to maintain an -explicit table of partially finished requests and to use select() to +explicit table of partially finished requests and to use a selector to decide which request to work on next (or whether to handle a new incoming request). This is particularly important for stream services where each client can potentially be connected for a long time (if @@ -104,7 +104,6 @@ Future work: - Standard classes for Sun RPC (which uses either UDP or TCP) - Standard mix-in classes to implement various authentication and encryption schemes -- Standard framework for select-based multiplexing XXX Open problems: - What to do with out-of-band data? @@ -130,13 +129,14 @@ __version__ = "0.4" import socket -import select +import selectors import os import errno try: import threading except ImportError: import dummy_threading as threading +from time import monotonic as time __all__ = ["BaseServer", "TCPServer", "UDPServer", "ForkingUDPServer", "ForkingTCPServer", "ThreadingUDPServer", "ThreadingTCPServer", @@ -147,14 +147,13 @@ if hasattr(socket, "AF_UNIX"): "ThreadingUnixStreamServer", "ThreadingUnixDatagramServer"]) -def _eintr_retry(func, *args): - """restart a system call interrupted by EINTR""" - while True: - try: - return func(*args) - except OSError as e: - if e.errno != errno.EINTR: - raise +# poll/select have the advantage of not requiring any extra file descriptor, +# contrarily to epoll/kqueue (also, they require a single syscall). +if hasattr(selectors, 'PollSelector'): + _ServerSelector = selectors.PollSelector +else: + _ServerSelector = selectors.SelectSelector + class BaseServer: @@ -166,7 +165,7 @@ class BaseServer: - serve_forever(poll_interval=0.5) - shutdown() - handle_request() # if you do not use serve_forever() - - fileno() -> int # for select() + - fileno() -> int # for selector Methods that may be overridden: @@ -227,17 +226,19 @@ class BaseServer: """ self.__is_shut_down.clear() try: - while not self.__shutdown_request: - # XXX: Consider using another file descriptor or - # connecting to the socket to wake this up instead of - # polling. Polling reduces our responsiveness to a - # shutdown request and wastes cpu at all other times. - r, w, e = _eintr_retry(select.select, [self], [], [], - poll_interval) - if self in r: - self._handle_request_noblock() - - self.service_actions() + # XXX: Consider using another file descriptor or connecting to the + # socket to wake this up instead of polling. Polling reduces our + # responsiveness to a shutdown request and wastes cpu at all other + # times. + with _ServerSelector() as selector: + selector.register(self, selectors.EVENT_READ) + + while not self.__shutdown_request: + ready = selector.select(poll_interval) + if ready: + self._handle_request_noblock() + + self.service_actions() finally: self.__shutdown_request = False self.__is_shut_down.set() @@ -260,16 +261,16 @@ class BaseServer: """ pass - # The distinction between handling, getting, processing and - # finishing a request is fairly arbitrary. Remember: + # The distinction between handling, getting, processing and finishing a + # request is fairly arbitrary. Remember: # - # - handle_request() is the top-level call. It calls - # select, get_request(), verify_request() and process_request() + # - handle_request() is the top-level call. It calls selector.select(), + # get_request(), verify_request() and process_request() # - get_request() is different for stream or datagram sockets - # - process_request() is the place that may fork a new process - # or create a new thread to finish the request - # - finish_request() instantiates the request handler class; - # this constructor will handle the request all by itself + # - process_request() is the place that may fork a new process or create a + # new thread to finish the request + # - finish_request() instantiates the request handler class; this + # constructor will handle the request all by itself def handle_request(self): """Handle one request, possibly blocking. @@ -283,18 +284,30 @@ class BaseServer: timeout = self.timeout elif self.timeout is not None: timeout = min(timeout, self.timeout) - fd_sets = _eintr_retry(select.select, [self], [], [], timeout) - if not fd_sets[0]: - self.handle_timeout() - return - self._handle_request_noblock() + if timeout is not None: + deadline = time() + timeout + + # Wait until a request arrives or the timeout expires - the loop is + # necessary to accommodate early wakeups due to EINTR. + with _ServerSelector() as selector: + selector.register(self, selectors.EVENT_READ) + + while True: + ready = selector.select(timeout) + if ready: + return self._handle_request_noblock() + else: + if timeout is not None: + timeout = deadline - time() + if timeout < 0: + return self.handle_timeout() def _handle_request_noblock(self): """Handle one request, without blocking. - I assume that select.select has returned that the socket is - readable before this function was called, so there should be - no risk of blocking in get_request(). + I assume that selector.select() has returned that the socket is + readable before this function was called, so there should be no risk of + blocking in get_request(). """ try: request, client_address = self.get_request() @@ -377,7 +390,7 @@ class TCPServer(BaseServer): - serve_forever(poll_interval=0.5) - shutdown() - handle_request() # if you don't use serve_forever() - - fileno() -> int # for select() + - fileno() -> int # for selector Methods that may be overridden: @@ -463,7 +476,7 @@ class TCPServer(BaseServer): def fileno(self): """Return socket file number. - Interface required by select(). + Interface required by selector. """ return self.socket.fileno() @@ -540,8 +553,6 @@ class ForkingMixIn: try: pid, _ = os.waitpid(-1, 0) self.active_children.discard(pid) - except InterruptedError: - pass except ChildProcessError: # we don't have any children, we're done self.active_children.clear() diff --git a/Lib/sre_compile.py b/Lib/sre_compile.py index 550ea15..30a5fae 100644 --- a/Lib/sre_compile.py +++ b/Lib/sre_compile.py @@ -13,19 +13,13 @@ import _sre import sre_parse from sre_constants import * -from _sre import MAXREPEAT assert _sre.MAGIC == MAGIC, "SRE module mismatch" -if _sre.CODESIZE == 2: - MAXCODE = 65535 -else: - MAXCODE = 0xFFFFFFFF - -_LITERAL_CODES = set([LITERAL, NOT_LITERAL]) -_REPEATING_CODES = set([REPEAT, MIN_REPEAT, MAX_REPEAT]) -_SUCCESS_CODES = set([SUCCESS, FAILURE]) -_ASSERT_CODES = set([ASSERT, ASSERT_NOT]) +_LITERAL_CODES = {LITERAL, NOT_LITERAL} +_REPEATING_CODES = {REPEAT, MIN_REPEAT, MAX_REPEAT} +_SUCCESS_CODES = {SUCCESS, FAILURE} +_ASSERT_CODES = {ASSERT, ASSERT_NOT} # Sets of lowercase characters which have the same uppercase. _equivalences = ( @@ -86,75 +80,75 @@ def _compile(code, pattern, flags): if flags & SRE_FLAG_IGNORECASE: lo = _sre.getlower(av, flags) if fixes and lo in fixes: - emit(OPCODES[IN_IGNORE]) + emit(IN_IGNORE) skip = _len(code); emit(0) if op is NOT_LITERAL: - emit(OPCODES[NEGATE]) + emit(NEGATE) for k in (lo,) + fixes[lo]: - emit(OPCODES[LITERAL]) + emit(LITERAL) emit(k) - emit(OPCODES[FAILURE]) + emit(FAILURE) code[skip] = _len(code) - skip else: - emit(OPCODES[OP_IGNORE[op]]) + emit(OP_IGNORE[op]) emit(lo) else: - emit(OPCODES[op]) + emit(op) emit(av) elif op is IN: if flags & SRE_FLAG_IGNORECASE: - emit(OPCODES[OP_IGNORE[op]]) + emit(OP_IGNORE[op]) def fixup(literal, flags=flags): return _sre.getlower(literal, flags) else: - emit(OPCODES[op]) + emit(op) fixup = None skip = _len(code); emit(0) _compile_charset(av, flags, code, fixup, fixes) code[skip] = _len(code) - skip elif op is ANY: if flags & SRE_FLAG_DOTALL: - emit(OPCODES[ANY_ALL]) + emit(ANY_ALL) else: - emit(OPCODES[ANY]) + emit(ANY) elif op in REPEATING_CODES: if flags & SRE_FLAG_TEMPLATE: raise error("internal: unsupported template operator") elif _simple(av) and op is not REPEAT: if op is MAX_REPEAT: - emit(OPCODES[REPEAT_ONE]) + emit(REPEAT_ONE) else: - emit(OPCODES[MIN_REPEAT_ONE]) + emit(MIN_REPEAT_ONE) skip = _len(code); emit(0) emit(av[0]) emit(av[1]) _compile(code, av[2], flags) - emit(OPCODES[SUCCESS]) + emit(SUCCESS) code[skip] = _len(code) - skip else: - emit(OPCODES[REPEAT]) + emit(REPEAT) skip = _len(code); emit(0) emit(av[0]) emit(av[1]) _compile(code, av[2], flags) code[skip] = _len(code) - skip if op is MAX_REPEAT: - emit(OPCODES[MAX_UNTIL]) + emit(MAX_UNTIL) else: - emit(OPCODES[MIN_UNTIL]) + emit(MIN_UNTIL) elif op is SUBPATTERN: if av[0]: - emit(OPCODES[MARK]) + emit(MARK) emit((av[0]-1)*2) # _compile_info(code, av[1], flags) _compile(code, av[1], flags) if av[0]: - emit(OPCODES[MARK]) + emit(MARK) emit((av[0]-1)*2+1) elif op in SUCCESS_CODES: - emit(OPCODES[op]) + emit(op) elif op in ASSERT_CODES: - emit(OPCODES[op]) + emit(op) skip = _len(code); emit(0) if av[0] >= 0: emit(0) # look ahead @@ -164,57 +158,57 @@ def _compile(code, pattern, flags): raise error("look-behind requires fixed-width pattern") emit(lo) # look behind _compile(code, av[1], flags) - emit(OPCODES[SUCCESS]) + emit(SUCCESS) code[skip] = _len(code) - skip elif op is CALL: - emit(OPCODES[op]) + emit(op) skip = _len(code); emit(0) _compile(code, av, flags) - emit(OPCODES[SUCCESS]) + emit(SUCCESS) code[skip] = _len(code) - skip elif op is AT: - emit(OPCODES[op]) + emit(op) if flags & SRE_FLAG_MULTILINE: av = AT_MULTILINE.get(av, av) if flags & SRE_FLAG_LOCALE: av = AT_LOCALE.get(av, av) elif flags & SRE_FLAG_UNICODE: av = AT_UNICODE.get(av, av) - emit(ATCODES[av]) + emit(av) elif op is BRANCH: - emit(OPCODES[op]) + emit(op) tail = [] tailappend = tail.append for av in av[1]: skip = _len(code); emit(0) # _compile_info(code, av, flags) _compile(code, av, flags) - emit(OPCODES[JUMP]) + emit(JUMP) tailappend(_len(code)); emit(0) code[skip] = _len(code) - skip - emit(0) # end of branch + emit(FAILURE) # end of branch for tail in tail: code[tail] = _len(code) - tail elif op is CATEGORY: - emit(OPCODES[op]) + emit(op) if flags & SRE_FLAG_LOCALE: av = CH_LOCALE[av] elif flags & SRE_FLAG_UNICODE: av = CH_UNICODE[av] - emit(CHCODES[av]) + emit(av) elif op is GROUPREF: if flags & SRE_FLAG_IGNORECASE: - emit(OPCODES[OP_IGNORE[op]]) + emit(OP_IGNORE[op]) else: - emit(OPCODES[op]) + emit(op) emit(av-1) elif op is GROUPREF_EXISTS: - emit(OPCODES[op]) + emit(op) emit(av[0]-1) skipyes = _len(code); emit(0) _compile(code, av[1], flags) if av[2]: - emit(OPCODES[JUMP]) + emit(JUMP) skipno = _len(code); emit(0) code[skipyes] = _len(code) - skipyes + 1 _compile(code, av[2], flags) @@ -227,14 +221,13 @@ def _compile(code, pattern, flags): def _compile_charset(charset, flags, code, fixup=None, fixes=None): # compile charset subprogram emit = code.append - for op, av in _optimize_charset(charset, fixup, fixes, - flags & SRE_FLAG_UNICODE): - emit(OPCODES[op]) + for op, av in _optimize_charset(charset, fixup, fixes): + emit(op) if op is NEGATE: pass elif op is LITERAL: emit(av) - elif op is RANGE: + elif op is RANGE or op is RANGE_IGNORE: emit(av[0]) emit(av[1]) elif op is CHARSET: @@ -243,16 +236,16 @@ def _compile_charset(charset, flags, code, fixup=None, fixes=None): code.extend(av) elif op is CATEGORY: if flags & SRE_FLAG_LOCALE: - emit(CHCODES[CH_LOCALE[av]]) + emit(CH_LOCALE[av]) elif flags & SRE_FLAG_UNICODE: - emit(CHCODES[CH_UNICODE[av]]) + emit(CH_UNICODE[av]) else: - emit(CHCODES[av]) + emit(av) else: raise error("internal: unsupported set operator") - emit(OPCODES[FAILURE]) + emit(FAILURE) -def _optimize_charset(charset, fixup, fixes, isunicode): +def _optimize_charset(charset, fixup, fixes): # internal: optimize character set out = [] tail = [] @@ -262,10 +255,10 @@ def _optimize_charset(charset, fixup, fixes, isunicode): try: if op is LITERAL: if fixup: - i = fixup(av) - charmap[i] = 1 - if fixes and i in fixes: - for k in fixes[i]: + lo = fixup(av) + charmap[lo] = 1 + if fixes and lo in fixes: + for k in fixes[lo]: charmap[k] = 1 else: charmap[av] = 1 @@ -291,21 +284,13 @@ def _optimize_charset(charset, fixup, fixes, isunicode): # character set contains non-UCS1 character codes charmap += b'\0' * 0xff00 continue - # character set contains non-BMP character codes - if fixup and isunicode and op is RANGE: - lo, hi = av - ranges = [av] - # There are only two ranges of cased astral characters: - # 10400-1044F (Deseret) and 118A0-118DF (Warang Citi). - _fixup_range(max(0x10000, lo), min(0x11fff, hi), - ranges, fixup) - for lo, hi in ranges: - if lo == hi: - tail.append((LITERAL, hi)) - else: - tail.append((RANGE, (lo, hi))) - else: - tail.append((op, av)) + # Character set contains non-BMP character codes. + # There are only two ranges of cased non-BMP characters: + # 10400-1044F (Deseret) and 118A0-118DF (Warang Citi), + # and for both ranges RANGE_IGNORE works. + if fixup and op is RANGE: + op = RANGE_IGNORE + tail.append((op, av)) break # compress character map @@ -383,25 +368,8 @@ def _optimize_charset(charset, fixup, fixes, isunicode): out += tail return out -def _fixup_range(lo, hi, ranges, fixup): - for i in map(fixup, range(lo, hi+1)): - for k, (lo, hi) in enumerate(ranges): - if i < lo: - if l == lo - 1: - ranges[k] = (i, hi) - else: - ranges.insert(k, (i, i)) - break - elif i > hi: - if i == hi + 1: - ranges[k] = (lo, i) - break - else: - break - else: - ranges.append((i, i)) - _CODEBITS = _sre.CODESIZE * 8 +MAXCODE = (1 << _CODEBITS) - 1 _BITS_TRANS = b'0' + b'1' * 255 def _mk_bitmap(bits, _CODEBITS=_CODEBITS, _int=int): s = bits.translate(_BITS_TRANS)[::-1] @@ -446,8 +414,11 @@ def _compile_info(code, pattern, flags): # this contains min/max pattern width, and an optional literal # prefix or a character map lo, hi = pattern.getwidth() + if hi > MAXCODE: + hi = MAXCODE if lo == 0: - return # not worth it + code.extend([INFO, 4, 0, lo, hi]) + return # look for a literal prefix prefix = [] prefixappend = prefix.append @@ -505,21 +476,21 @@ def _compile_info(code, pattern, flags): elif op is IN: charset = av ## if prefix: -## print "*** PREFIX", prefix, prefix_skip +## print("*** PREFIX", prefix, prefix_skip) ## if charset: -## print "*** CHARSET", charset +## print("*** CHARSET", charset) # add an info block emit = code.append - emit(OPCODES[INFO]) + emit(INFO) skip = len(code); emit(0) # literal flag mask = 0 if prefix: mask = SRE_INFO_PREFIX if len(prefix) == prefix_skip == len(pattern.data): - mask = mask + SRE_INFO_LITERAL + mask = mask | SRE_INFO_LITERAL elif charset: - mask = mask + SRE_INFO_CHARSET + mask = mask | SRE_INFO_CHARSET emit(mask) # pattern length if lo < MAXCODE: @@ -527,10 +498,7 @@ def _compile_info(code, pattern, flags): else: emit(MAXCODE) prefix = prefix[:MAXCODE] - if hi < MAXCODE: - emit(hi) - else: - emit(0) + emit(min(hi, MAXCODE)) # add literal prefix if prefix: emit(len(prefix)) # length @@ -556,7 +524,7 @@ def _code(p, flags): # compile the pattern _compile(code, p.data, flags) - code.append(OPCODES[SUCCESS]) + code.append(SUCCESS) return code @@ -571,13 +539,7 @@ def compile(p, flags=0): code = _code(p, flags) - # print code - - # XXX: <fl> get rid of this limitation! - if p.pattern.groups > 100: - raise AssertionError( - "sorry, but this version only supports 100 named groups" - ) + # print(code) # map in either direction groupindex = p.pattern.groupdict diff --git a/Lib/sre_constants.py b/Lib/sre_constants.py index 23e3516..8b6bbfa 100644 --- a/Lib/sre_constants.py +++ b/Lib/sre_constants.py @@ -13,153 +13,115 @@ # update when constants are added or removed -MAGIC = 20031017 +MAGIC = 20140917 -from _sre import MAXREPEAT +from _sre import MAXREPEAT, MAXGROUPS # SRE standard exception (access as sre.error) # should this really be here? class error(Exception): - pass + def __init__(self, msg, pattern=None, pos=None): + self.msg = msg + self.pattern = pattern + self.pos = pos + if pattern is not None and pos is not None: + msg = '%s at position %d' % (msg, pos) + if isinstance(pattern, str): + newline = '\n' + else: + newline = b'\n' + self.lineno = pattern.count(newline, 0, pos) + 1 + self.colno = pos - pattern.rfind(newline, 0, pos) + if newline in pattern: + msg = '%s (line %d, column %d)' % (msg, self.lineno, self.colno) + else: + self.lineno = self.colno = None + super().__init__(msg) + + +class _NamedIntConstant(int): + def __new__(cls, value, name): + self = super(_NamedIntConstant, cls).__new__(cls, value) + self.name = name + return self + + def __str__(self): + return self.name + + __repr__ = __str__ + +MAXREPEAT = _NamedIntConstant(MAXREPEAT, 'MAXREPEAT') + +def _makecodes(names): + names = names.strip().split() + items = [_NamedIntConstant(i, name) for i, name in enumerate(names)] + globals().update({item.name: item for item in items}) + return items # operators +# failure=0 success=1 (just because it looks better that way :-) +OPCODES = _makecodes(""" + FAILURE SUCCESS + + ANY ANY_ALL + ASSERT ASSERT_NOT + AT + BRANCH + CALL + CATEGORY + CHARSET BIGCHARSET + GROUPREF GROUPREF_EXISTS GROUPREF_IGNORE + IN IN_IGNORE + INFO + JUMP + LITERAL LITERAL_IGNORE + MARK + MAX_UNTIL + MIN_UNTIL + NOT_LITERAL NOT_LITERAL_IGNORE + NEGATE + RANGE + REPEAT + REPEAT_ONE + SUBPATTERN + MIN_REPEAT_ONE + RANGE_IGNORE -FAILURE = "failure" -SUCCESS = "success" - -ANY = "any" -ANY_ALL = "any_all" -ASSERT = "assert" -ASSERT_NOT = "assert_not" -AT = "at" -BIGCHARSET = "bigcharset" -BRANCH = "branch" -CALL = "call" -CATEGORY = "category" -CHARSET = "charset" -GROUPREF = "groupref" -GROUPREF_IGNORE = "groupref_ignore" -GROUPREF_EXISTS = "groupref_exists" -IN = "in" -IN_IGNORE = "in_ignore" -INFO = "info" -JUMP = "jump" -LITERAL = "literal" -LITERAL_IGNORE = "literal_ignore" -MARK = "mark" -MAX_REPEAT = "max_repeat" -MAX_UNTIL = "max_until" -MIN_REPEAT = "min_repeat" -MIN_UNTIL = "min_until" -NEGATE = "negate" -NOT_LITERAL = "not_literal" -NOT_LITERAL_IGNORE = "not_literal_ignore" -RANGE = "range" -REPEAT = "repeat" -REPEAT_ONE = "repeat_one" -SUBPATTERN = "subpattern" -MIN_REPEAT_ONE = "min_repeat_one" + MIN_REPEAT MAX_REPEAT +""") +del OPCODES[-2:] # remove MIN_REPEAT and MAX_REPEAT # positions -AT_BEGINNING = "at_beginning" -AT_BEGINNING_LINE = "at_beginning_line" -AT_BEGINNING_STRING = "at_beginning_string" -AT_BOUNDARY = "at_boundary" -AT_NON_BOUNDARY = "at_non_boundary" -AT_END = "at_end" -AT_END_LINE = "at_end_line" -AT_END_STRING = "at_end_string" -AT_LOC_BOUNDARY = "at_loc_boundary" -AT_LOC_NON_BOUNDARY = "at_loc_non_boundary" -AT_UNI_BOUNDARY = "at_uni_boundary" -AT_UNI_NON_BOUNDARY = "at_uni_non_boundary" +ATCODES = _makecodes(""" + AT_BEGINNING AT_BEGINNING_LINE AT_BEGINNING_STRING + AT_BOUNDARY AT_NON_BOUNDARY + AT_END AT_END_LINE AT_END_STRING + AT_LOC_BOUNDARY AT_LOC_NON_BOUNDARY + AT_UNI_BOUNDARY AT_UNI_NON_BOUNDARY +""") # categories -CATEGORY_DIGIT = "category_digit" -CATEGORY_NOT_DIGIT = "category_not_digit" -CATEGORY_SPACE = "category_space" -CATEGORY_NOT_SPACE = "category_not_space" -CATEGORY_WORD = "category_word" -CATEGORY_NOT_WORD = "category_not_word" -CATEGORY_LINEBREAK = "category_linebreak" -CATEGORY_NOT_LINEBREAK = "category_not_linebreak" -CATEGORY_LOC_WORD = "category_loc_word" -CATEGORY_LOC_NOT_WORD = "category_loc_not_word" -CATEGORY_UNI_DIGIT = "category_uni_digit" -CATEGORY_UNI_NOT_DIGIT = "category_uni_not_digit" -CATEGORY_UNI_SPACE = "category_uni_space" -CATEGORY_UNI_NOT_SPACE = "category_uni_not_space" -CATEGORY_UNI_WORD = "category_uni_word" -CATEGORY_UNI_NOT_WORD = "category_uni_not_word" -CATEGORY_UNI_LINEBREAK = "category_uni_linebreak" -CATEGORY_UNI_NOT_LINEBREAK = "category_uni_not_linebreak" - -OPCODES = [ - - # failure=0 success=1 (just because it looks better that way :-) - FAILURE, SUCCESS, - - ANY, ANY_ALL, - ASSERT, ASSERT_NOT, - AT, - BRANCH, - CALL, - CATEGORY, - CHARSET, BIGCHARSET, - GROUPREF, GROUPREF_EXISTS, GROUPREF_IGNORE, - IN, IN_IGNORE, - INFO, - JUMP, - LITERAL, LITERAL_IGNORE, - MARK, - MAX_UNTIL, - MIN_UNTIL, - NOT_LITERAL, NOT_LITERAL_IGNORE, - NEGATE, - RANGE, - REPEAT, - REPEAT_ONE, - SUBPATTERN, - MIN_REPEAT_ONE +CHCODES = _makecodes(""" + CATEGORY_DIGIT CATEGORY_NOT_DIGIT + CATEGORY_SPACE CATEGORY_NOT_SPACE + CATEGORY_WORD CATEGORY_NOT_WORD + CATEGORY_LINEBREAK CATEGORY_NOT_LINEBREAK + CATEGORY_LOC_WORD CATEGORY_LOC_NOT_WORD + CATEGORY_UNI_DIGIT CATEGORY_UNI_NOT_DIGIT + CATEGORY_UNI_SPACE CATEGORY_UNI_NOT_SPACE + CATEGORY_UNI_WORD CATEGORY_UNI_NOT_WORD + CATEGORY_UNI_LINEBREAK CATEGORY_UNI_NOT_LINEBREAK +""") -] - -ATCODES = [ - AT_BEGINNING, AT_BEGINNING_LINE, AT_BEGINNING_STRING, AT_BOUNDARY, - AT_NON_BOUNDARY, AT_END, AT_END_LINE, AT_END_STRING, - AT_LOC_BOUNDARY, AT_LOC_NON_BOUNDARY, AT_UNI_BOUNDARY, - AT_UNI_NON_BOUNDARY -] - -CHCODES = [ - CATEGORY_DIGIT, CATEGORY_NOT_DIGIT, CATEGORY_SPACE, - CATEGORY_NOT_SPACE, CATEGORY_WORD, CATEGORY_NOT_WORD, - CATEGORY_LINEBREAK, CATEGORY_NOT_LINEBREAK, CATEGORY_LOC_WORD, - CATEGORY_LOC_NOT_WORD, CATEGORY_UNI_DIGIT, CATEGORY_UNI_NOT_DIGIT, - CATEGORY_UNI_SPACE, CATEGORY_UNI_NOT_SPACE, CATEGORY_UNI_WORD, - CATEGORY_UNI_NOT_WORD, CATEGORY_UNI_LINEBREAK, - CATEGORY_UNI_NOT_LINEBREAK -] - -def makedict(list): - d = {} - i = 0 - for item in list: - d[item] = i - i = i + 1 - return d - -OPCODES = makedict(OPCODES) -ATCODES = makedict(ATCODES) -CHCODES = makedict(CHCODES) # replacement operations for "ignore case" mode OP_IGNORE = { GROUPREF: GROUPREF_IGNORE, IN: IN_IGNORE, LITERAL: LITERAL_IGNORE, - NOT_LITERAL: NOT_LITERAL_IGNORE + NOT_LITERAL: NOT_LITERAL_IGNORE, + RANGE: RANGE_IGNORE, } AT_MULTILINE = { @@ -217,9 +179,9 @@ SRE_INFO_CHARSET = 4 # pattern starts with character from given set if __name__ == "__main__": def dump(f, d, prefix): - items = sorted(d.items(), key=lambda a: a[1]) - for k, v in items: - f.write("#define %s_%s %s\n" % (prefix, k.upper(), v)) + items = sorted(d) + for item in items: + f.write("#define %s_%s %d\n" % (prefix, item, item)) f = open("sre_constants.h", "w") f.write("""\ /* diff --git a/Lib/sre_parse.py b/Lib/sre_parse.py index df1e643..98afd7c 100644 --- a/Lib/sre_parse.py +++ b/Lib/sre_parse.py @@ -13,17 +13,19 @@ # XXX: show string offset and offending character for all errors from sre_constants import * -from _sre import MAXREPEAT SPECIAL_CHARS = ".\\[{()*+?^$|" REPEAT_CHARS = "*+?{" -DIGITS = set("0123456789") +DIGITS = frozenset("0123456789") -OCTDIGITS = set("01234567") -HEXDIGITS = set("0123456789abcdefABCDEF") +OCTDIGITS = frozenset("01234567") +HEXDIGITS = frozenset("0123456789abcdefABCDEF") -WHITESPACE = set(" \t\n\r\v\f") +WHITESPACE = frozenset(" \t\n\r\v\f") + +_REPEATCODES = frozenset({MIN_REPEAT, MAX_REPEAT}) +_UNITCODES = frozenset({ANY, RANGE, IN, LITERAL, NOT_LITERAL, CATEGORY}) ESCAPES = { r"\a": (LITERAL, ord("\a")), @@ -66,26 +68,36 @@ class Pattern: # master pattern object. keeps track of global attributes def __init__(self): self.flags = 0 - self.open = [] - self.groups = 1 self.groupdict = {} - self.lookbehind = 0 - + self.subpatterns = [None] # group 0 + self.lookbehindgroups = None + @property + def groups(self): + return len(self.subpatterns) def opengroup(self, name=None): gid = self.groups - self.groups = gid + 1 + self.subpatterns.append(None) + if self.groups > MAXGROUPS: + raise error("groups number is too large") if name is not None: ogid = self.groupdict.get(name, None) if ogid is not None: - raise error("redefinition of group name %s as group %d; " - "was group %d" % (repr(name), gid, ogid)) + raise error("redefinition of group name %r as group %d; " + "was group %d" % (name, gid, ogid)) self.groupdict[name] = gid - self.open.append(gid) return gid - def closegroup(self, gid): - self.open.remove(gid) + def closegroup(self, gid, p): + self.subpatterns[gid] = p def checkgroup(self, gid): - return gid < self.groups and gid not in self.open + return gid < self.groups and self.subpatterns[gid] is not None + + def checklookbehindgroup(self, gid, source): + if self.lookbehindgroups is not None: + if not self.checkgroup(gid): + raise source.error('cannot refer to an open group') + if gid >= self.lookbehindgroups: + raise source.error('cannot refer to group defined in the same ' + 'lookbehind subpattern') class SubPattern: # a subpattern, in intermediate form @@ -99,24 +111,24 @@ class SubPattern: nl = True seqtypes = (tuple, list) for op, av in self.data: - print(level*" " + op, end='') - if op == IN: + print(level*" " + str(op), end='') + if op is IN: # member sublanguage print() for op, a in av: - print((level+1)*" " + op, a) - elif op == BRANCH: + print((level+1)*" " + str(op), a) + elif op is BRANCH: print() for i, a in enumerate(av[1]): if i: - print(level*" " + "or") + print(level*" " + "OR") a.dump(level+1) - elif op == GROUPREF_EXISTS: + elif op is GROUPREF_EXISTS: condgroup, item_yes, item_no = av print('', condgroup) item_yes.dump(level+1) if item_no: - print(level*" " + "else") + print(level*" " + "ELSE") item_no.dump(level+1) elif isinstance(av, seqtypes): nl = False @@ -153,11 +165,9 @@ class SubPattern: self.data.append(code) def getwidth(self): # determine the width (min, max) for this subpattern - if self.width: + if self.width is not None: return self.width lo = hi = 0 - UNITCODES = (ANY, RANGE, IN, LITERAL, NOT_LITERAL, CATEGORY) - REPEATCODES = (MIN_REPEAT, MAX_REPEAT) for op, av in self.data: if op is BRANCH: i = MAXREPEAT - 1 @@ -176,14 +186,28 @@ class SubPattern: i, j = av[1].getwidth() lo = lo + i hi = hi + j - elif op in REPEATCODES: + elif op in _REPEATCODES: i, j = av[2].getwidth() lo = lo + i * av[0] hi = hi + j * av[1] - elif op in UNITCODES: + elif op in _UNITCODES: lo = lo + 1 hi = hi + 1 - elif op == SUCCESS: + elif op is GROUPREF: + i, j = self.pattern.subpatterns[av].getwidth() + lo = lo + i + hi = hi + j + elif op is GROUPREF_EXISTS: + i, j = av[1].getwidth() + if av[2] is not None: + l, h = av[2].getwidth() + i = min(i, l) + j = max(j, h) + else: + i = 0 + lo = lo + i + hi = hi + j + elif op is SUCCESS: break self.width = min(lo, MAXREPEAT - 1), min(hi, MAXREPEAT) return self.width @@ -192,33 +216,33 @@ class Tokenizer: def __init__(self, string): self.istext = isinstance(string, str) self.string = string + if not self.istext: + string = str(string, 'latin1') + self.decoded_string = string self.index = 0 + self.next = None self.__next() def __next(self): - if self.index >= len(self.string): + index = self.index + try: + char = self.decoded_string[index] + except IndexError: self.next = None return - char = self.string[self.index:self.index+1] - # Special case for the str8, since indexing returns a integer - # XXX This is only needed for test_bug_926075 in test_re.py - if char and not self.istext: - char = chr(char[0]) if char == "\\": + index += 1 try: - c = self.string[self.index + 1] + char += self.decoded_string[index] except IndexError: - raise error("bogus escape (end of line)") - if not self.istext: - c = chr(c) - char = char + c - self.index = self.index + len(char) + raise error("bogus escape (end of line)", + self.string, len(self.string) - 1) from None + self.index = index + 1 self.next = char - def match(self, char, skip=1): + def match(self, char): if char == self.next: - if skip: - self.__next() - return 1 - return 0 + self.__next() + return True + return False def get(self): this = self.next self.__next() @@ -232,10 +256,25 @@ class Tokenizer: result += c self.__next() return result + def getuntil(self, terminator): + result = '' + while True: + c = self.next + self.__next() + if c is None: + raise self.error("unterminated name") + if c == terminator: + break + result += c + return result def tell(self): - return self.index, self.next + return self.index - len(self.next or '') def seek(self, index): - self.index, self.next = index + self.index = index + self.__next() + + def error(self, msg, offset=0): + return error(msg, self.string, self.tell() - offset) # The following three functions are not used in this module anymore, but we keep # them here (with DeprecationWarnings) for backwards compatibility. @@ -270,7 +309,7 @@ def _class_escape(source, escape): if code: return code code = CATEGORIES.get(escape) - if code and code[0] == IN: + if code and code[0] is IN: return code try: c = escape[1:2] @@ -279,7 +318,7 @@ def _class_escape(source, escape): escape += source.getwhile(2, HEXDIGITS) if len(escape) != 4: raise ValueError - return LITERAL, int(escape[2:], 16) & 0xff + return LITERAL, int(escape[2:], 16) elif c == "u" and source.istext: # unicode escape (exactly four digits) escape += source.getwhile(4, HEXDIGITS) @@ -297,14 +336,18 @@ def _class_escape(source, escape): elif c in OCTDIGITS: # octal escape (up to three digits) escape += source.getwhile(2, OCTDIGITS) - return LITERAL, int(escape[1:], 8) & 0xff + c = int(escape[1:], 8) + if c > 0o377: + raise source.error('octal escape value %r outside of ' + 'range 0-0o377' % escape, len(escape)) + return LITERAL, c elif c in DIGITS: raise ValueError if len(escape) == 2: return LITERAL, ord(escape[1]) except ValueError: pass - raise error("bogus escape: %s" % repr(escape)) + raise source.error("bogus escape: %r" % escape, len(escape)) def _escape(source, escape, state): # handle escape code in expression @@ -321,7 +364,7 @@ def _escape(source, escape, state): escape += source.getwhile(2, HEXDIGITS) if len(escape) != 4: raise ValueError - return LITERAL, int(escape[2:], 16) & 0xff + return LITERAL, int(escape[2:], 16) elif c == "u" and source.istext: # unicode escape (exactly four digits) escape += source.getwhile(4, HEXDIGITS) @@ -339,50 +382,48 @@ def _escape(source, escape, state): elif c == "0": # octal escape escape += source.getwhile(2, OCTDIGITS) - return LITERAL, int(escape[1:], 8) & 0xff + return LITERAL, int(escape[1:], 8) elif c in DIGITS: # octal escape *or* decimal group reference (sigh) if source.next in DIGITS: - escape = escape + source.get() + escape += source.get() if (escape[1] in OCTDIGITS and escape[2] in OCTDIGITS and source.next in OCTDIGITS): # got three octal digits; this is an octal escape - escape = escape + source.get() - return LITERAL, int(escape[1:], 8) & 0xff + escape += source.get() + c = int(escape[1:], 8) + if c > 0o377: + raise source.error('octal escape value %r outside of ' + 'range 0-0o377' % escape, + len(escape)) + return LITERAL, c # not an octal escape, so this is a group reference group = int(escape[1:]) if group < state.groups: if not state.checkgroup(group): - raise error("cannot refer to open group") - if state.lookbehind: - import warnings - warnings.warn('group references in lookbehind ' - 'assertions are not supported', - RuntimeWarning) + raise source.error("cannot refer to open group", + len(escape)) + state.checklookbehindgroup(group, source) return GROUPREF, group raise ValueError if len(escape) == 2: return LITERAL, ord(escape[1]) except ValueError: pass - raise error("bogus escape: %s" % repr(escape)) + raise source.error("bogus escape: %r" % escape, len(escape)) -def _parse_sub(source, state, nested=1): +def _parse_sub(source, state, nested=True): # parse an alternation: a|b|c items = [] itemsappend = items.append sourcematch = source.match - while 1: + while True: itemsappend(_parse(source, state)) - if sourcematch("|"): - continue - if not nested: + if not sourcematch("|"): break - if not source.next or sourcematch(")", 0): - break - else: - raise error("pattern not properly closed") + if nested and source.next is not None and source.next != ")": + raise source.error("pattern not properly closed") if len(items) == 1: return items[0] @@ -391,7 +432,7 @@ def _parse_sub(source, state, nested=1): subpatternappend = subpattern.append # check if all items share a common prefix - while 1: + while True: prefix = None for item in items: if not item: @@ -411,16 +452,12 @@ def _parse_sub(source, state, nested=1): # check if the branch can be replaced by a character set for item in items: - if len(item) != 1 or item[0][0] != LITERAL: + if len(item) != 1 or item[0][0] is not LITERAL: break else: # we can store this as a character set instead of a # branch (the compiler may optimize this even more) - set = [] - setappend = set.append - for item in items: - setappend(item[0]) - subpatternappend((IN, set)) + subpatternappend((IN, [item[0] for item in items])) return subpattern subpattern.append((BRANCH, (None, items))) @@ -430,21 +467,16 @@ def _parse_sub_cond(source, state, condgroup): item_yes = _parse(source, state) if source.match("|"): item_no = _parse(source, state) - if source.match("|"): - raise error("conditional backref with more than two branches") + if source.next == "|": + raise source.error("conditional backref with more than two branches") else: item_no = None - if source.next and not source.match(")", 0): - raise error("pattern not properly closed") + if source.next is not None and source.next != ")": + raise source.error("pattern not properly closed") subpattern = SubPattern(state) subpattern.append((GROUPREF_EXISTS, (condgroup, item_yes, item_no))) return subpattern -_PATTERNENDERS = set("|)") -_ASSERTCHARS = set("=!<") -_LOOKBEHINDASSERTCHARS = set("=!") -_REPEATCODES = set([MIN_REPEAT, MAX_REPEAT]) - def _parse(source, state): # parse a simple pattern subpattern = SubPattern(state) @@ -454,32 +486,35 @@ def _parse(source, state): sourceget = source.get sourcematch = source.match _len = len - PATTERNENDERS = _PATTERNENDERS - ASSERTCHARS = _ASSERTCHARS - LOOKBEHINDASSERTCHARS = _LOOKBEHINDASSERTCHARS - REPEATCODES = _REPEATCODES + _ord = ord + verbose = state.flags & SRE_FLAG_VERBOSE - while 1: + while True: - if source.next in PATTERNENDERS: - break # end of subpattern - this = sourceget() + this = source.next if this is None: break # end of pattern + if this in "|)": + break # end of subpattern + sourceget() - if state.flags & SRE_FLAG_VERBOSE: + if verbose: # skip whitespace and comments if this in WHITESPACE: continue if this == "#": - while 1: + while True: this = sourceget() - if this in (None, "\n"): + if this is None or this == "\n": break continue - if this and this[0] not in SPECIAL_CHARS: - subpatternappend((LITERAL, ord(this))) + if this[0] == "\\": + code = _escape(source, this, state) + subpatternappend(code) + + elif this not in SPECIAL_CHARS: + subpatternappend((LITERAL, _ord(this))) elif this == "[": # character set @@ -491,39 +526,38 @@ def _parse(source, state): setappend((NEGATE, None)) # check remaining characters start = set[:] - while 1: + while True: this = sourceget() + if this is None: + raise source.error("unexpected end of regular expression") if this == "]" and set != start: break - elif this and this[0] == "\\": + elif this[0] == "\\": code1 = _class_escape(source, this) - elif this: - code1 = LITERAL, ord(this) else: - raise error("unexpected end of regular expression") + code1 = LITERAL, _ord(this) if sourcematch("-"): # potential range this = sourceget() + if this is None: + raise source.error("unexpected end of regular expression") if this == "]": if code1[0] is IN: code1 = code1[1][0] setappend(code1) - setappend((LITERAL, ord("-"))) + setappend((LITERAL, _ord("-"))) break - elif this: - if this[0] == "\\": - code2 = _class_escape(source, this) - else: - code2 = LITERAL, ord(this) - if code1[0] != LITERAL or code2[0] != LITERAL: - raise error("bad character range") - lo = code1[1] - hi = code2[1] - if hi < lo: - raise error("bad character range") - setappend((RANGE, (lo, hi))) + if this[0] == "\\": + code2 = _class_escape(source, this) else: - raise error("unexpected end of regular expression") + code2 = LITERAL, _ord(this) + if code1[0] != LITERAL or code2[0] != LITERAL: + raise source.error("bad character range", len(this)) + lo = code1[1] + hi = code2[1] + if hi < lo: + raise source.error("bad character range", len(this)) + setappend((RANGE, (lo, hi))) else: if code1[0] is IN: code1 = code1[1][0] @@ -538,8 +572,9 @@ def _parse(source, state): # XXX: <fl> should add charmap optimization here subpatternappend((IN, set)) - elif this and this[0] in REPEAT_CHARS: + elif this in REPEAT_CHARS: # repeat previous item + here = source.tell() if this == "?": min, max = 0, 1 elif this == "*": @@ -549,20 +584,19 @@ def _parse(source, state): min, max = 1, MAXREPEAT elif this == "{": if source.next == "}": - subpatternappend((LITERAL, ord(this))) + subpatternappend((LITERAL, _ord(this))) continue - here = source.tell() min, max = 0, MAXREPEAT lo = hi = "" while source.next in DIGITS: - lo = lo + source.get() + lo += sourceget() if sourcematch(","): while source.next in DIGITS: - hi = hi + sourceget() + hi += sourceget() else: hi = lo if not sourcematch("}"): - subpatternappend((LITERAL, ord(this))) + subpatternappend((LITERAL, _ord(this))) source.seek(here) continue if lo: @@ -574,18 +608,21 @@ def _parse(source, state): if max >= MAXREPEAT: raise OverflowError("the repetition number is too large") if max < min: - raise error("bad repeat interval") + raise source.error("bad repeat interval", + source.tell() - here) else: - raise error("not supported") + raise source.error("not supported", len(this)) # figure out which item to repeat if subpattern: item = subpattern[-1:] else: item = None - if not item or (_len(item) == 1 and item[0][0] == AT): - raise error("nothing to repeat") - if item[0][0] in REPEATCODES: - raise error("multiple repeat") + if not item or (_len(item) == 1 and item[0][0] is AT): + raise source.error("nothing to repeat", + source.tell() - here + len(this)) + if item[0][0] in _REPEATCODES: + raise source.error("multiple repeat", + source.tell() - here + len(this)) if sourcematch("?"): subpattern[-1] = (MIN_REPEAT, (min, max, item)) else: @@ -601,144 +638,137 @@ def _parse(source, state): if sourcematch("?"): group = 0 # options - if sourcematch("P"): + char = sourceget() + if char is None: + raise self.error("unexpected end of pattern") + if char == "P": # python extensions if sourcematch("<"): # named group: skip forward to end of name - name = "" - while 1: - char = sourceget() - if char is None: - raise error("unterminated name") - if char == ">": - break - name = name + char + name = source.getuntil(">") group = 1 if not name: - raise error("missing group name") + raise source.error("missing group name", 1) if not name.isidentifier(): - raise error("bad character in group name %r" % name) + raise source.error("bad character in group name " + "%r" % name, + len(name) + 1) elif sourcematch("="): # named backreference - name = "" - while 1: - char = sourceget() - if char is None: - raise error("unterminated name") - if char == ")": - break - name = name + char + name = source.getuntil(")") if not name: - raise error("missing group name") + raise source.error("missing group name", 1) if not name.isidentifier(): - raise error("bad character in backref group name " - "%r" % name) + raise source.error("bad character in backref " + "group name %r" % name, + len(name) + 1) gid = state.groupdict.get(name) if gid is None: msg = "unknown group name: {0!r}".format(name) - raise error(msg) - if state.lookbehind: - import warnings - warnings.warn('group references in lookbehind ' - 'assertions are not supported', - RuntimeWarning) + raise source.error(msg, len(name) + 1) + state.checklookbehindgroup(gid, source) subpatternappend((GROUPREF, gid)) continue else: char = sourceget() if char is None: - raise error("unexpected end of pattern") - raise error("unknown specifier: ?P%s" % char) - elif sourcematch(":"): + raise source.error("unexpected end of pattern") + raise source.error("unknown specifier: ?P%s" % char, + len(char)) + elif char == ":": # non-capturing group group = 2 - elif sourcematch("#"): + elif char == "#": # comment - while 1: - if source.next is None or source.next == ")": + while True: + if source.next is None: + raise source.error("unbalanced parenthesis") + if sourceget() == ")": break - sourceget() - if not sourcematch(")"): - raise error("unbalanced parenthesis") continue - elif source.next in ASSERTCHARS: + elif char in "=!<": # lookahead assertions - char = sourceget() dir = 1 if char == "<": - if source.next not in LOOKBEHINDASSERTCHARS: - raise error("syntax error") - dir = -1 # lookbehind char = sourceget() - state.lookbehind += 1 + if char is None or char not in "=!": + raise source.error("syntax error") + dir = -1 # lookbehind + lookbehindgroups = state.lookbehindgroups + if lookbehindgroups is None: + state.lookbehindgroups = state.groups p = _parse_sub(source, state) if dir < 0: - state.lookbehind -= 1 + if lookbehindgroups is None: + state.lookbehindgroups = None if not sourcematch(")"): - raise error("unbalanced parenthesis") + raise source.error("unbalanced parenthesis") if char == "=": subpatternappend((ASSERT, (dir, p))) else: subpatternappend((ASSERT_NOT, (dir, p))) continue - elif sourcematch("("): + elif char == "(": # conditional backreference group - condname = "" - while 1: - char = sourceget() - if char is None: - raise error("unterminated name") - if char == ")": - break - condname = condname + char + condname = source.getuntil(")") group = 2 if not condname: - raise error("missing group name") + raise source.error("missing group name", 1) if condname.isidentifier(): condgroup = state.groupdict.get(condname) if condgroup is None: msg = "unknown group name: {0!r}".format(condname) - raise error(msg) + raise source.error(msg, len(condname) + 1) else: try: condgroup = int(condname) + if condgroup < 0: + raise ValueError except ValueError: - raise error("bad character in group name") - if state.lookbehind: - import warnings - warnings.warn('group references in lookbehind ' - 'assertions are not supported', - RuntimeWarning) - else: + raise source.error("bad character in group name", + len(condname) + 1) + if not condgroup: + raise source.error("bad group number", + len(condname) + 1) + if condgroup >= MAXGROUPS: + raise source.error("the group number is too large", + len(condname) + 1) + state.checklookbehindgroup(condgroup, source) + elif char in FLAGS: # flags - if not source.next in FLAGS: - raise error("unexpected end of pattern") + state.flags |= FLAGS[char] while source.next in FLAGS: - state.flags = state.flags | FLAGS[sourceget()] + state.flags |= FLAGS[sourceget()] + verbose = state.flags & SRE_FLAG_VERBOSE + else: + raise source.error("unexpected end of pattern") if group: # parse group contents if group == 2: # anonymous group group = None else: - group = state.opengroup(name) + try: + group = state.opengroup(name) + except error as err: + raise source.error(err.msg, len(name) + 1) if condgroup: p = _parse_sub_cond(source, state, condgroup) else: p = _parse_sub(source, state) if not sourcematch(")"): - raise error("unbalanced parenthesis") + raise source.error("unbalanced parenthesis") if group is not None: - state.closegroup(group) + state.closegroup(group, p) subpatternappend((SUBPATTERN, (group, p))) else: - while 1: + while True: char = sourceget() if char is None: - raise error("unexpected end of pattern") + raise source.error("unexpected end of pattern") if char == ")": break - raise error("unknown extension") + raise source.error("unknown extension", len(char)) elif this == "^": subpatternappend((AT, AT_BEGINNING)) @@ -746,18 +776,19 @@ def _parse(source, state): elif this == "$": subpattern.append((AT, AT_END)) - elif this and this[0] == "\\": - code = _escape(source, this, state) - subpatternappend(code) - else: - raise error("parser error") + raise source.error("parser error", len(this)) return subpattern def fix_flags(src, flags): # Check and fix flags according to the type of pattern (str or bytes) if isinstance(src, str): + if flags & SRE_FLAG_LOCALE: + import warnings + warnings.warn("LOCALE flag with a str pattern is deprecated. " + "Will be an error in 3.6", + DeprecationWarning, stacklevel=6) if not flags & SRE_FLAG_ASCII: flags |= SRE_FLAG_UNICODE elif flags & SRE_FLAG_UNICODE: @@ -765,6 +796,11 @@ def fix_flags(src, flags): else: if flags & SRE_FLAG_UNICODE: raise ValueError("can't use UNICODE flag with a bytes pattern") + if flags & SRE_FLAG_LOCALE and flags & SRE_FLAG_ASCII: + import warnings + warnings.warn("ASCII and LOCALE flags are incompatible. " + "Will be an error in 3.6", + DeprecationWarning, stacklevel=6) return flags def parse(str, flags=0, pattern=None): @@ -780,11 +816,12 @@ def parse(str, flags=0, pattern=None): p = _parse_sub(source, pattern, 0) p.pattern.flags = fix_flags(str, p.pattern.flags) - tail = source.get() - if tail == ")": - raise error("unbalanced parenthesis") - elif tail: - raise error("bogus characters at end of regular expression") + if source.next is not None: + if source.next == ")": + raise source.error("unbalanced parenthesis") + else: + raise source.error("bogus characters at end of regular expression", + len(tail)) if flags & SRE_FLAG_DEBUG: p.dump() @@ -821,22 +858,20 @@ def parse_template(source, pattern): if c == "g": name = "" if s.match("<"): - while True: - char = sget() - if char is None: - raise error("unterminated group name") - if char == ">": - break - name += char + name = s.getuntil(">") if not name: - raise error("missing group name") + raise s.error("missing group name", 1) try: index = int(name) if index < 0: - raise error("negative group number") + raise s.error("negative group number", len(name) + 1) + if index >= MAXGROUPS: + raise s.error("the group number is too large", + len(name) + 1) except ValueError: if not name.isidentifier(): - raise error("bad character in group name") + raise s.error("bad character in group name", + len(name) + 1) try: index = pattern.groupindex[name] except KeyError: @@ -857,7 +892,11 @@ def parse_template(source, pattern): s.next in OCTDIGITS): this += sget() isoctal = True - lappend(chr(int(this[1:], 8) & 0xff)) + c = int(this[1:], 8) + if c > 0o377: + raise s.error('octal escape value %r outside of ' + 'range 0-0o377' % this, len(this)) + lappend(chr(c)) if not isoctal: addgroup(int(this[1:])) else: @@ -878,14 +917,12 @@ def parse_template(source, pattern): def expand_template(template, match): g = match.group - sep = match.string[:0] + empty = match.string[:0] groups, literals = template literals = literals[:] try: for index, group in groups: - literals[index] = s = g(group) - if s is None: - raise error("unmatched group") + literals[index] = g(group) or empty except IndexError: raise error("invalid group reference") - return sep.join(literals) + return empty.join(literals) @@ -87,17 +87,18 @@ ALERT_DESCRIPTION_BAD_CERTIFICATE_HASH_VALUE ALERT_DESCRIPTION_UNKNOWN_PSK_IDENTITY """ +import ipaddress import textwrap import re import sys import os from collections import namedtuple -from enum import Enum as _Enum +from enum import Enum as _Enum, IntEnum as _IntEnum import _ssl # if we can't import it, let the error propagate from _ssl import OPENSSL_VERSION_NUMBER, OPENSSL_VERSION_INFO, OPENSSL_VERSION -from _ssl import _SSLContext +from _ssl import _SSLContext, MemoryBIO from _ssl import ( SSLError, SSLZeroReturnError, SSLWantReadError, SSLWantWriteError, SSLSyscallError, SSLEOFError, @@ -119,30 +120,23 @@ def _import_symbols(prefix): _import_symbols('OP_') _import_symbols('ALERT_DESCRIPTION_') _import_symbols('SSL_ERROR_') -_import_symbols('PROTOCOL_') _import_symbols('VERIFY_') -from _ssl import HAS_SNI, HAS_ECDH, HAS_NPN +from _ssl import HAS_SNI, HAS_ECDH, HAS_NPN, HAS_ALPN from _ssl import _OPENSSL_API_VERSION +_SSLMethod = _IntEnum('_SSLMethod', + {name: value for name, value in vars(_ssl).items() + if name.startswith('PROTOCOL_')}) +globals().update(_SSLMethod.__members__) + +_PROTOCOL_NAMES = {value: name for name, value in _SSLMethod.__members__.items()} -_PROTOCOL_NAMES = {value: name for name, value in globals().items() if name.startswith('PROTOCOL_')} try: - from _ssl import PROTOCOL_SSLv2 _SSLv2_IF_EXISTS = PROTOCOL_SSLv2 -except ImportError: +except NameError: _SSLv2_IF_EXISTS = None -else: - _PROTOCOL_NAMES[PROTOCOL_SSLv2] = "SSLv2" - -try: - from _ssl import PROTOCOL_TLSv1_1, PROTOCOL_TLSv1_2 -except ImportError: - pass -else: - _PROTOCOL_NAMES[PROTOCOL_TLSv1_1] = "TLSv1.1" - _PROTOCOL_NAMES[PROTOCOL_TLSv1_2] = "TLSv1.2" if sys.platform == "win32": from _ssl import enum_certificates, enum_crls @@ -246,6 +240,17 @@ def _dnsname_match(dn, hostname, max_wildcards=1): return pat.match(hostname) +def _ipaddress_match(ipname, host_ip): + """Exact matching of IP addresses. + + RFC 6125 explicitly doesn't define an algorithm for this + (section 1.7.2 - "Out of Scope"). + """ + # OpenSSL may add a trailing newline to a subjectAltName's IP address + ip = ipaddress.ip_address(ipname.rstrip()) + return ip == host_ip + + def match_hostname(cert, hostname): """Verify that *cert* (in decoded format as returned by SSLSocket.getpeercert()) matches the *hostname*. RFC 2818 and RFC 6125 @@ -258,11 +263,20 @@ def match_hostname(cert, hostname): raise ValueError("empty or no certificate, match_hostname needs a " "SSL socket or SSL context with either " "CERT_OPTIONAL or CERT_REQUIRED") + try: + host_ip = ipaddress.ip_address(hostname) + except ValueError: + # Not an IP address (common case) + host_ip = None dnsnames = [] san = cert.get('subjectAltName', ()) for key, value in san: if key == 'DNS': - if _dnsname_match(value, hostname): + if host_ip is None and _dnsname_match(value, hostname): + return + dnsnames.append(value) + elif key == 'IP Address': + if host_ip is not None and _ipaddress_match(value, host_ip): return dnsnames.append(value) if not dnsnames: @@ -361,6 +375,12 @@ class SSLContext(_SSLContext): server_hostname=server_hostname, _context=self) + def wrap_bio(self, incoming, outgoing, server_side=False, + server_hostname=None): + sslobj = self._wrap_bio(incoming, outgoing, server_side=server_side, + server_hostname=server_hostname) + return SSLObject(sslobj) + def set_npn_protocols(self, npn_protocols): protos = bytearray() for protocol in npn_protocols: @@ -372,6 +392,17 @@ class SSLContext(_SSLContext): self._set_npn_protocols(protos) + def set_alpn_protocols(self, alpn_protocols): + protos = bytearray() + for protocol in alpn_protocols: + b = bytes(protocol, 'ascii') + if len(b) == 0 or len(b) > 255: + raise SSLError('ALPN protocols must be 1 to 255 in length') + protos.append(len(b)) + protos.extend(b) + + self._set_alpn_protocols(protos) + def _load_windows_store_certs(self, storename, purpose): certs = bytearray() for cert, encoding, trust in enum_certificates(storename): @@ -488,6 +519,141 @@ _create_default_https_context = create_default_context _create_stdlib_context = _create_unverified_context +class SSLObject: + """This class implements an interface on top of a low-level SSL object as + implemented by OpenSSL. This object captures the state of an SSL connection + but does not provide any network IO itself. IO needs to be performed + through separate "BIO" objects which are OpenSSL's IO abstraction layer. + + This class does not have a public constructor. Instances are returned by + ``SSLContext.wrap_bio``. This class is typically used by framework authors + that want to implement asynchronous IO for SSL through memory buffers. + + When compared to ``SSLSocket``, this object lacks the following features: + + * Any form of network IO incluging methods such as ``recv`` and ``send``. + * The ``do_handshake_on_connect`` and ``suppress_ragged_eofs`` machinery. + """ + + def __init__(self, sslobj, owner=None): + self._sslobj = sslobj + # Note: _sslobj takes a weak reference to owner + self._sslobj.owner = owner or self + + @property + def context(self): + """The SSLContext that is currently in use.""" + return self._sslobj.context + + @context.setter + def context(self, ctx): + self._sslobj.context = ctx + + @property + def server_side(self): + """Whether this is a server-side socket.""" + return self._sslobj.server_side + + @property + def server_hostname(self): + """The currently set server hostname (for SNI), or ``None`` if no + server hostame is set.""" + return self._sslobj.server_hostname + + def read(self, len=0, buffer=None): + """Read up to 'len' bytes from the SSL object and return them. + + If 'buffer' is provided, read into this buffer and return the number of + bytes read. + """ + if buffer is not None: + v = self._sslobj.read(len, buffer) + else: + v = self._sslobj.read(len or 1024) + return v + + def write(self, data): + """Write 'data' to the SSL object and return the number of bytes + written. + + The 'data' argument must support the buffer interface. + """ + return self._sslobj.write(data) + + def getpeercert(self, binary_form=False): + """Returns a formatted version of the data in the certificate provided + by the other end of the SSL channel. + + Return None if no certificate was provided, {} if a certificate was + provided, but not validated. + """ + return self._sslobj.peer_certificate(binary_form) + + def selected_npn_protocol(self): + """Return the currently selected NPN protocol as a string, or ``None`` + if a next protocol was not negotiated or if NPN is not supported by one + of the peers.""" + if _ssl.HAS_NPN: + return self._sslobj.selected_npn_protocol() + + def selected_alpn_protocol(self): + """Return the currently selected ALPN protocol as a string, or ``None`` + if a next protocol was not negotiated or if ALPN is not supported by one + of the peers.""" + if _ssl.HAS_ALPN: + return self._sslobj.selected_alpn_protocol() + + def cipher(self): + """Return the currently selected cipher as a 3-tuple ``(name, + ssl_version, secret_bits)``.""" + return self._sslobj.cipher() + + def shared_ciphers(self): + """Return a list of ciphers shared by the client during the handshake or + None if this is not a valid server connection. + """ + return self._sslobj.shared_ciphers() + + def compression(self): + """Return the current compression algorithm in use, or ``None`` if + compression was not negotiated or not supported by one of the peers.""" + return self._sslobj.compression() + + def pending(self): + """Return the number of bytes that can be read immediately.""" + return self._sslobj.pending() + + def do_handshake(self): + """Start the SSL/TLS handshake.""" + self._sslobj.do_handshake() + if self.context.check_hostname: + if not self.server_hostname: + raise ValueError("check_hostname needs server_hostname " + "argument") + match_hostname(self.getpeercert(), self.server_hostname) + + def unwrap(self): + """Start the SSL shutdown handshake.""" + return self._sslobj.shutdown() + + def get_channel_binding(self, cb_type="tls-unique"): + """Get channel binding data for current connection. Raise ValueError + if the requested `cb_type` is not supported. Return bytes of the data + or None if the data is not available (e.g. before the handshake).""" + if cb_type not in CHANNEL_BINDING_TYPES: + raise ValueError("Unsupported channel binding type") + if cb_type != "tls-unique": + raise NotImplementedError( + "{0} channel binding type not implemented" + .format(cb_type)) + return self._sslobj.tls_unique_cb() + + def version(self): + """Return a string identifying the protocol version used by the + current SSL channel. """ + return self._sslobj.version() + + class SSLSocket(socket): """This class implements a subtype of socket.socket that wraps the underlying OS socket in an SSL context when necessary, and @@ -570,8 +736,9 @@ class SSLSocket(socket): if connected: # create the SSL object try: - self._sslobj = self._context._wrap_socket(self, server_side, - server_hostname) + sslobj = self._context._wrap_socket(self, server_side, + server_hostname) + self._sslobj = SSLObject(sslobj, owner=self) if do_handshake_on_connect: timeout = self.gettimeout() if timeout == 0.0: @@ -616,11 +783,7 @@ class SSLSocket(socket): if not self._sslobj: raise ValueError("Read on closed or unwrapped SSL socket.") try: - if buffer is not None: - v = self._sslobj.read(len, buffer) - else: - v = self._sslobj.read(len or 1024) - return v + return self._sslobj.read(len, buffer) except SSLError as x: if x.args[0] == SSL_ERROR_EOF and self.suppress_ragged_eofs: if buffer is not None: @@ -647,7 +810,7 @@ class SSLSocket(socket): self._checkClosed() self._check_connected() - return self._sslobj.peer_certificate(binary_form) + return self._sslobj.getpeercert(binary_form) def selected_npn_protocol(self): self._checkClosed() @@ -656,6 +819,13 @@ class SSLSocket(socket): else: return self._sslobj.selected_npn_protocol() + def selected_alpn_protocol(self): + self._checkClosed() + if not self._sslobj or not _ssl.HAS_ALPN: + return None + else: + return self._sslobj.selected_alpn_protocol() + def cipher(self): self._checkClosed() if not self._sslobj: @@ -663,6 +833,12 @@ class SSLSocket(socket): else: return self._sslobj.cipher() + def shared_ciphers(self): + self._checkClosed() + if not self._sslobj: + return None + return self._sslobj.shared_ciphers() + def compression(self): self._checkClosed() if not self._sslobj: @@ -677,17 +853,7 @@ class SSLSocket(socket): raise ValueError( "non-zero flags not allowed in calls to send() on %s" % self.__class__) - try: - v = self._sslobj.write(data) - except SSLError as x: - if x.args[0] == SSL_ERROR_WANT_READ: - return 0 - elif x.args[0] == SSL_ERROR_WANT_WRITE: - return 0 - else: - raise - else: - return v + return self._sslobj.write(data) else: return socket.send(self, data, flags) @@ -723,6 +889,16 @@ class SSLSocket(socket): else: return socket.sendall(self, data, flags) + def sendfile(self, file, offset=0, count=None): + """Send a file, possibly by using os.sendfile() if this is a + clear-text socket. Return the total number of bytes sent. + """ + if self._sslobj is None: + # os.sendfile() works with plain sockets only + return super().sendfile(file, offset, count) + else: + return self._sendfile_use_send(file, offset, count) + def recv(self, buflen=1024, flags=0): self._checkClosed() if self._sslobj: @@ -787,7 +963,7 @@ class SSLSocket(socket): def unwrap(self): if self._sslobj: - s = self._sslobj.shutdown() + s = self._sslobj.unwrap() self._sslobj = None return s else: @@ -808,12 +984,6 @@ class SSLSocket(socket): finally: self.settimeout(timeout) - if self.context.check_hostname: - if not self.server_hostname: - raise ValueError("check_hostname needs server_hostname " - "argument") - match_hostname(self.getpeercert(), self.server_hostname) - def _real_connect(self, addr, connect_ex): if self.server_side: raise ValueError("can't connect in server-side mode") @@ -821,7 +991,8 @@ class SSLSocket(socket): # connected at the time of the call. We connect it, then wrap it. if self._connected: raise ValueError("attempt to connect already-connected SSLSocket!") - self._sslobj = self.context._wrap_socket(self, False, self.server_hostname) + sslobj = self.context._wrap_socket(self, False, self.server_hostname) + self._sslobj = SSLObject(sslobj, owner=self) try: if connect_ex: rc = socket.connect_ex(self, addr) @@ -864,15 +1035,18 @@ class SSLSocket(socket): if the requested `cb_type` is not supported. Return bytes of the data or None if the data is not available (e.g. before the handshake). """ - if cb_type not in CHANNEL_BINDING_TYPES: - raise ValueError("Unsupported channel binding type") - if cb_type != "tls-unique": - raise NotImplementedError( - "{0} channel binding type not implemented" - .format(cb_type)) if self._sslobj is None: return None - return self._sslobj.tls_unique_cb() + return self._sslobj.get_channel_binding(cb_type) + + def version(self): + """ + Return a string identifying the protocol version used by the + current SSL channel, or None if there is no established channel. + """ + if self._sslobj is None: + return None + return self._sslobj.version() def wrap_socket(sock, keyfile=None, certfile=None, @@ -892,12 +1066,34 @@ def wrap_socket(sock, keyfile=None, certfile=None, # some utility functions def cert_time_to_seconds(cert_time): - """Takes a date-time string in standard ASN1_print form - ("MON DAY 24HOUR:MINUTE:SEC YEAR TIMEZONE") and return - a Python time value in seconds past the epoch.""" + """Return the time in seconds since the Epoch, given the timestring + representing the "notBefore" or "notAfter" date from a certificate + in ``"%b %d %H:%M:%S %Y %Z"`` strptime format (C locale). + + "notBefore" or "notAfter" dates must use UTC (RFC 5280). - import time - return time.mktime(time.strptime(cert_time, "%b %d %H:%M:%S %Y GMT")) + Month is one of: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec + UTC should be specified as GMT (see ASN1_TIME_print()) + """ + from time import strptime + from calendar import timegm + + months = ( + "Jan","Feb","Mar","Apr","May","Jun", + "Jul","Aug","Sep","Oct","Nov","Dec" + ) + time_format = ' %d %H:%M:%S %Y GMT' # NOTE: no month, fixed GMT + try: + month_number = months.index(cert_time[:3].title()) + 1 + except ValueError: + raise ValueError('time data %r does not match ' + 'format "%%b%s"' % (cert_time, time_format)) + else: + # found valid month + tt = strptime(cert_time[3:], time_format) + # return an integer, the previous mktime()-based implementation + # returned a float (fractional seconds are always zero here). + return timegm((tt[0], month_number) + tt[2:6]) PEM_HEADER = "-----BEGIN CERTIFICATE-----" PEM_FOOTER = "-----END CERTIFICATE-----" diff --git a/Lib/stat.py b/Lib/stat.py index 3eecc3e..46837c0 100644 --- a/Lib/stat.py +++ b/Lib/stat.py @@ -148,6 +148,29 @@ def filemode(mode): perm.append("-") return "".join(perm) + +# Windows FILE_ATTRIBUTE constants for interpreting os.stat()'s +# "st_file_attributes" member + +FILE_ATTRIBUTE_ARCHIVE = 32 +FILE_ATTRIBUTE_COMPRESSED = 2048 +FILE_ATTRIBUTE_DEVICE = 64 +FILE_ATTRIBUTE_DIRECTORY = 16 +FILE_ATTRIBUTE_ENCRYPTED = 16384 +FILE_ATTRIBUTE_HIDDEN = 2 +FILE_ATTRIBUTE_INTEGRITY_STREAM = 32768 +FILE_ATTRIBUTE_NORMAL = 128 +FILE_ATTRIBUTE_NOT_CONTENT_INDEXED = 8192 +FILE_ATTRIBUTE_NO_SCRUB_DATA = 131072 +FILE_ATTRIBUTE_OFFLINE = 4096 +FILE_ATTRIBUTE_READONLY = 1 +FILE_ATTRIBUTE_REPARSE_POINT = 1024 +FILE_ATTRIBUTE_SPARSE_FILE = 512 +FILE_ATTRIBUTE_SYSTEM = 4 +FILE_ATTRIBUTE_TEMPORARY = 256 +FILE_ATTRIBUTE_VIRTUAL = 65536 + + # If available, use C implementation try: from _stat import * diff --git a/Lib/statistics.py b/Lib/statistics.py index 25a26d4..3972ed2 100644 --- a/Lib/statistics.py +++ b/Lib/statistics.py @@ -150,7 +150,7 @@ def _sum(data, start=0): # We fail as soon as we reach a value that is not an int or the type of # the first value which is not an int. E.g. _sum([int, int, float, int]) # is okay, but sum([int, int, float, Fraction]) is not. - allowed_types = set([int, type(start)]) + allowed_types = {int, type(start)} n, d = _exact_ratio(start) partials = {d: n} # map {denominator: sum of numerators} # Micro-optimizations. @@ -168,7 +168,7 @@ def _sum(data, start=0): assert allowed_types.pop() is int T = int else: - T = (allowed_types - set([int])).pop() + T = (allowed_types - {int}).pop() if None in partials: assert issubclass(T, (float, Decimal)) assert not math.isfinite(partials[None]) diff --git a/Lib/subprocess.py b/Lib/subprocess.py index f11e538..6d2c4f5 100644 --- a/Lib/subprocess.py +++ b/Lib/subprocess.py @@ -104,17 +104,21 @@ in the child process prior to executing the command. If env is not None, it defines the environment variables for the new process. -If universal_newlines is false, the file objects stdin, stdout and stderr +If universal_newlines is False, the file objects stdin, stdout and stderr are opened as binary files, and no line ending conversion is done. -If universal_newlines is true, the file objects stdout and stderr are -opened as a text files, but lines may be terminated by any of '\n', +If universal_newlines is True, the file objects stdout and stderr are +opened as a text file, but lines may be terminated by any of '\n', the Unix end-of-line convention, '\r', the old Macintosh convention or '\r\n', the Windows convention. All of these external representations are seen as '\n' by the Python program. Also, the newlines attribute of the file objects stdout, stdin and stderr are not updated by the communicate() method. +In either case, the process being communicated with should start up +expecting to receive bytes on its standard input and decode them with +the same encoding they are sent in. + The startupinfo and creationflags, if given, will be passed to the underlying CreateProcess() function. They can specify things such as appearance of the main window and priority for the new process. @@ -184,6 +188,9 @@ check_output(*popenargs, **kwargs): pass a string to the subprocess's stdin. If you use this argument you may not also use the Popen constructor's "stdin" argument. + If universal_newlines is set to True, the "input" argument must + be a string rather than bytes, and the return value will be a string. + Exceptions ---------- Exceptions raised in the child process, before the new program has @@ -225,9 +232,13 @@ wait() communicate(input=None) Interact with process: Send data to stdin. Read data from stdout and stderr, until end-of-file is reached. Wait for process to - terminate. The optional input argument should be a string to be + terminate. The optional input argument should be data to be sent to the child process, or None, if no data should be sent to - the child. + the child. If the Popen instance was constructed with universal_newlines + set to True, the input argument should be a string and will be encoded + using the preferred system encoding (see locale.getpreferredencoding); + if universal_newlines is False, the input argument should be a + byte string. communicate() returns a tuple (stdout, stderr). @@ -354,10 +365,7 @@ import signal import builtins import warnings import errno -try: - from time import monotonic as _time -except ImportError: - from time import time as _time +from time import monotonic as _time # Exception classes used by this module. class SubprocessError(Exception): pass @@ -453,15 +461,11 @@ if mswindows: raise ValueError("already closed") def __repr__(self): - return "Handle(%d)" % int(self) + return "%s(%d)" % (self.__class__.__name__, int(self)) __del__ = Close __str__ = __repr__ -try: - MAXFD = os.sysconf("SC_OPEN_MAX") -except: - MAXFD = 256 # This lists holds Popen instances for which the underlying process had not # exited at the time its __del__ method got called: those processes are wait()ed @@ -485,14 +489,6 @@ STDOUT = -2 DEVNULL = -3 -def _eintr_retry_call(func, *args): - while True: - try: - return func(*args) - except InterruptedError: - continue - - # XXX This function is only used by multiprocessing and the test suite, # but it's here so that it can be imported when Python is compiled without # threads. @@ -591,8 +587,8 @@ def check_output(*popenargs, timeout=None, **kwargs): ... input=b"when in the course of fooman events\n") b'when in the course of barman events\n' - If universal_newlines=True is passed, the return value will be a - string rather than bytes. + If universal_newlines=True is passed, the "input" argument must be a + string and the return value will be a string rather than bytes. """ if 'stdout' in kwargs: raise ValueError('stdout argument not allowed, it will be overridden.') @@ -918,14 +914,35 @@ class Popen(object): self._devnull = os.open(os.devnull, os.O_RDWR) return self._devnull + def _stdin_write(self, input): + if input: + try: + self.stdin.write(input) + except BrokenPipeError: + # communicate() must ignore broken pipe error + pass + except OSError as e: + if e.errno == errno.EINVAL and self.poll() is not None: + # Issue #19612: On Windows, stdin.write() fails with EINVAL + # if the process already exited before the write + pass + else: + raise + self.stdin.close() + def communicate(self, input=None, timeout=None): """Interact with process: Send data to stdin. Read data from stdout and stderr, until end-of-file is reached. Wait for - process to terminate. The optional input argument should be - bytes to be sent to the child process, or None, if no data - should be sent to the child. + process to terminate. + + The optional "input" argument should be data to be sent to the + child process (if self.universal_newlines is True, this should + be a string; if it is False, "input" should be bytes), or + None, if no data should be sent to the child. - communicate() returns a tuple (stdout, stderr).""" + communicate() returns a tuple (stdout, stderr). These will be + bytes or, if self.universal_newlines was True, a string. + """ if self._communication_started and input: raise ValueError("Cannot send input after starting communication") @@ -938,18 +955,12 @@ class Popen(object): stdout = None stderr = None if self.stdin: - if input: - try: - self.stdin.write(input) - except OSError as e: - if e.errno != errno.EPIPE and e.errno != errno.EINVAL: - raise - self.stdin.close() + self._stdin_write(input) elif self.stdout: - stdout = _eintr_retry_call(self.stdout.read) + stdout = self.stdout.read() self.stdout.close() elif self.stderr: - stderr = _eintr_retry_call(self.stderr.read) + stderr = self.stderr.read() self.stderr.close() self.wait() else: @@ -1193,21 +1204,7 @@ class Popen(object): self.stderr_thread.start() if self.stdin: - if input is not None: - try: - self.stdin.write(input) - except OSError as e: - if e.errno == errno.EPIPE: - # communicate() should ignore pipe full error - pass - elif (e.errno == errno.EINVAL - and self.poll() is not None): - # Issue #19612: stdin.write() fails with EINVAL - # if the process already exited before the write - pass - else: - raise - self.stdin.close() + self._stdin_write(input) # Wait for the reader threads, or time out. If we time out, the # threads remain reading and the fds left open in case the user @@ -1322,16 +1319,6 @@ class Popen(object): errread, errwrite) - def _close_fds(self, fds_to_keep): - start_fd = 3 - for fd in sorted(fds_to_keep): - if fd >= start_fd: - os.closerange(start_fd, fd) - start_fd = fd + 1 - if start_fd <= MAXFD: - os.closerange(start_fd, MAXFD) - - def _execute_child(self, args, executable, preexec_fn, close_fds, pass_fds, cwd, env, startupinfo, creationflags, shell, @@ -1417,7 +1404,7 @@ class Popen(object): # exception (limited in size) errpipe_data = bytearray() while True: - part = _eintr_retry_call(os.read, errpipe_read, 50000) + part = os.read(errpipe_read, 50000) errpipe_data += part if not part or len(errpipe_data) > 50000: break @@ -1427,10 +1414,9 @@ class Popen(object): if errpipe_data: try: - _eintr_retry_call(os.waitpid, self.pid, 0) - except OSError as e: - if e.errno != errno.ECHILD: - raise + os.waitpid(self.pid, 0) + except ChildProcessError: + pass try: exception_name, hex_errno, err_msg = ( errpipe_data.split(b':', 2)) @@ -1513,10 +1499,8 @@ class Popen(object): def _try_wait(self, wait_flags): """All callers to this function MUST hold self._waitpid_lock.""" try: - (pid, sts) = _eintr_retry_call(os.waitpid, self.pid, wait_flags) - except OSError as e: - if e.errno != errno.ECHILD: - raise + (pid, sts) = os.waitpid(self.pid, wait_flags) + except ChildProcessError: # This happens if SIGCLD is set to be ignored or waiting # for child processes has otherwise been disabled for our # process. This child is dead, we can't get the status. @@ -1628,12 +1612,9 @@ class Popen(object): self._input_offset + _PIPE_BUF] try: self._input_offset += os.write(key.fd, chunk) - except OSError as e: - if e.errno == errno.EPIPE: - selector.unregister(key.fileobj) - key.fileobj.close() - else: - raise + except BrokenPipeError: + selector.unregister(key.fileobj) + key.fileobj.close() else: if self._input_offset >= len(self._input): selector.unregister(key.fileobj) diff --git a/Lib/sysconfig.py b/Lib/sysconfig.py index dbf7767..137932e 100644 --- a/Lib/sysconfig.py +++ b/Lib/sysconfig.py @@ -57,7 +57,7 @@ _INSTALL_SCHEMES = { 'purelib': '{userbase}/Python{py_version_nodot}/site-packages', 'platlib': '{userbase}/Python{py_version_nodot}/site-packages', 'include': '{userbase}/Python{py_version_nodot}/Include', - 'scripts': '{userbase}/Scripts', + 'scripts': '{userbase}/Python{py_version_nodot}/Scripts', 'data': '{userbase}', }, 'posix_user': { @@ -109,13 +109,8 @@ else: # unable to retrieve the real program name _PROJECT_BASE = _safe_realpath(os.getcwd()) -if os.name == "nt" and "pcbuild" in _PROJECT_BASE[-8:].lower(): - _PROJECT_BASE = _safe_realpath(os.path.join(_PROJECT_BASE, pardir)) -# PC/VS7.1 -if os.name == "nt" and "\\pc\\v" in _PROJECT_BASE[-10:].lower(): - _PROJECT_BASE = _safe_realpath(os.path.join(_PROJECT_BASE, pardir, pardir)) -# PC/AMD64 -if os.name == "nt" and "\\pcbuild\\amd64" in _PROJECT_BASE[-14:].lower(): +if (os.name == 'nt' and + _PROJECT_BASE.lower().endswith(('\\pcbuild\\win32', '\\pcbuild\\amd64'))): _PROJECT_BASE = _safe_realpath(os.path.join(_PROJECT_BASE, pardir, pardir)) # set for cross builds @@ -129,11 +124,9 @@ def _is_python_source_dir(d): return False _sys_home = getattr(sys, '_home', None) -if _sys_home and os.name == 'nt' and \ - _sys_home.lower().endswith(('pcbuild', 'pcbuild\\amd64')): - _sys_home = os.path.dirname(_sys_home) - if _sys_home.endswith('pcbuild'): # must be amd64 - _sys_home = os.path.dirname(_sys_home) +if (_sys_home and os.name == 'nt' and + _sys_home.lower().endswith(('\\pcbuild\\win32', '\\pcbuild\\amd64'))): + _sys_home = os.path.dirname(os.path.dirname(_sys_home)) def is_python_build(check_home=False): if check_home and _sys_home: return _is_python_source_dir(_sys_home) diff --git a/Lib/tarfile.py b/Lib/tarfile.py index 37e4dcd..ea7a89a 100755 --- a/Lib/tarfile.py +++ b/Lib/tarfile.py @@ -1409,9 +1409,9 @@ class TarFile(object): can be determined, `mode' is overridden by `fileobj's mode. `fileobj' is not closed, when TarFile is closed. """ - modes = {"r": "rb", "a": "r+b", "w": "wb"} + modes = {"r": "rb", "a": "r+b", "w": "wb", "x": "xb"} if mode not in modes: - raise ValueError("mode must be 'r', 'a' or 'w'") + raise ValueError("mode must be 'r', 'a', 'w' or 'x'") self.mode = mode self._mode = modes[mode] @@ -1524,6 +1524,15 @@ class TarFile(object): 'w:bz2' open for writing with bzip2 compression 'w:xz' open for writing with lzma compression + 'x' or 'x:' create a tarfile exclusively without compression, raise + an exception if the file is already created + 'x:gz' create an gzip compressed tarfile, raise an exception + if the file is already created + 'x:bz2' create an bzip2 compressed tarfile, raise an exception + if the file is already created + 'x:xz' create an lzma compressed tarfile, raise an exception + if the file is already created + 'r|*' open a stream of tar blocks with transparent compression 'r|' open an uncompressed stream of tar blocks for reading 'r|gz' open a gzip compressed stream of tar blocks @@ -1582,7 +1591,7 @@ class TarFile(object): t._extfileobj = False return t - elif mode in ("a", "w"): + elif mode in ("a", "w", "x"): return cls.taropen(name, mode, fileobj, **kwargs) raise ValueError("undiscernible mode") @@ -1591,8 +1600,8 @@ class TarFile(object): def taropen(cls, name, mode="r", fileobj=None, **kwargs): """Open uncompressed tar archive name for reading or writing. """ - if mode not in ("r", "a", "w"): - raise ValueError("mode must be 'r', 'a' or 'w'") + if mode not in ("r", "a", "w", "x"): + raise ValueError("mode must be 'r', 'a', 'w' or 'x'") return cls(name, mode, fileobj, **kwargs) @classmethod @@ -1600,8 +1609,8 @@ class TarFile(object): """Open gzip compressed tar archive name for reading or writing. Appending is not allowed. """ - if mode not in ("r", "w"): - raise ValueError("mode must be 'r' or 'w'") + if mode not in ("r", "w", "x"): + raise ValueError("mode must be 'r', 'w' or 'x'") try: import gzip @@ -1634,8 +1643,8 @@ class TarFile(object): """Open bzip2 compressed tar archive name for reading or writing. Appending is not allowed. """ - if mode not in ("r", "w"): - raise ValueError("mode must be 'r' or 'w'.") + if mode not in ("r", "w", "x"): + raise ValueError("mode must be 'r', 'w' or 'x'") try: import bz2 @@ -1663,8 +1672,8 @@ class TarFile(object): """Open lzma compressed tar archive name for reading or writing. Appending is not allowed. """ - if mode not in ("r", "w"): - raise ValueError("mode must be 'r' or 'w'") + if mode not in ("r", "w", "x"): + raise ValueError("mode must be 'r', 'w' or 'x'") try: import lzma @@ -1751,7 +1760,7 @@ class TarFile(object): addfile(). If given, `arcname' specifies an alternative name for the file in the archive. """ - self._check("aw") + self._check("awx") # When fileobj is given, replace name by # fileobj's real name. @@ -1842,14 +1851,17 @@ class TarFile(object): tarinfo.devminor = os.minor(statres.st_rdev) return tarinfo - def list(self, verbose=True): + def list(self, verbose=True, *, members=None): """Print a table of contents to sys.stdout. If `verbose' is False, only the names of the members are printed. If it is True, an `ls -l'-like - output is produced. + output is produced. `members' is optional and must be a subset of the + list returned by getmembers(). """ self._check() - for tarinfo in self: + if members is None: + members = self + for tarinfo in members: if verbose: _safe_print(stat.filemode(tarinfo.mode)) _safe_print("%s/%s" % (tarinfo.uname or tarinfo.uid, @@ -1882,7 +1894,7 @@ class TarFile(object): TarInfo object, if it returns None the TarInfo object will be excluded from the archive. """ - self._check("aw") + self._check("awx") if arcname is None: arcname = name @@ -1939,7 +1951,7 @@ class TarFile(object): On Windows platforms, `fileobj' should always be opened with mode 'rb' to avoid irritation about the file size. """ - self._check("aw") + self._check("awx") tarinfo = copy.copy(tarinfo) diff --git a/Lib/telnetlib.py b/Lib/telnetlib.py index 0cacac8..eebb952 100644 --- a/Lib/telnetlib.py +++ b/Lib/telnetlib.py @@ -36,10 +36,7 @@ To do: import sys import socket import selectors -try: - from time import monotonic as _time -except ImportError: - from time import time as _time +from time import monotonic as _time __all__ = ["Telnet"] diff --git a/Lib/tempfile.py b/Lib/tempfile.py index b6eeca3..0522c79 100644 --- a/Lib/tempfile.py +++ b/Lib/tempfile.py @@ -473,6 +473,11 @@ if _os.name != 'posix' or _os.sys.platform == 'cygwin': TemporaryFile = NamedTemporaryFile else: + # Is the O_TMPFILE flag available and does it work? + # The flag is set to False if os.open(dir, os.O_TMPFILE) raises an + # IsADirectoryError exception + _O_TMPFILE_WORKS = hasattr(_os, 'O_TMPFILE') + def TemporaryFile(mode='w+b', buffering=-1, encoding=None, newline=None, suffix="", prefix=template, dir=None): @@ -488,11 +493,32 @@ else: Returns an object with a file-like interface. The file has no name, and will cease to exist when it is closed. """ + global _O_TMPFILE_WORKS if dir is None: dir = gettempdir() flags = _bin_openflags + if _O_TMPFILE_WORKS: + try: + flags2 = (flags | _os.O_TMPFILE) & ~_os.O_CREAT + fd = _os.open(dir, flags2, 0o600) + except IsADirectoryError: + # Linux kernel older than 3.11 ignores O_TMPFILE flag. + # Set flag to False to not try again. + _O_TMPFILE_WORKS = False + except OSError: + # The filesystem of the directory does not support O_TMPFILE. + # For example, OSError(95, 'Operation not supported'). + pass + else: + try: + return _io.open(fd, mode, buffering=buffering, + newline=newline, encoding=encoding) + except: + _os.close(fd) + raise + # Fallback to _mkstemp_inner(). (fd, name) = _mkstemp_inner(dir, prefix, suffix, flags) try: diff --git a/Lib/test/_test_multiprocessing.py b/Lib/test/_test_multiprocessing.py index 9466d4e..d048f6f 100644 --- a/Lib/test/_test_multiprocessing.py +++ b/Lib/test/_test_multiprocessing.py @@ -2551,7 +2551,7 @@ class _TestPicklingConnections(BaseTestCase): l = socket.socket() l.bind((test.support.HOST, 0)) - l.listen(1) + l.listen() conn.send(l.getsockname()) new_conn, addr = l.accept() conn.send(new_conn) @@ -3198,7 +3198,7 @@ class TestWait(unittest.TestCase): from multiprocessing.connection import wait l = socket.socket() l.bind((test.support.HOST, 0)) - l.listen(4) + l.listen() addr = l.getsockname() readers = [] procs = [] diff --git a/Lib/test/datetimetester.py b/Lib/test/datetimetester.py index 8e48b9f..40ef1ba 100644 --- a/Lib/test/datetimetester.py +++ b/Lib/test/datetimetester.py @@ -3,6 +3,7 @@ See http://www.zope.org/Members/fdrake/DateTimeWiki/TestCases """ +import decimal import sys import pickle import random @@ -50,6 +51,17 @@ class TestModule(unittest.TestCase): self.assertEqual(datetime.MINYEAR, 1) self.assertEqual(datetime.MAXYEAR, 9999) + def test_name_cleanup(self): + if '_Fast' not in str(self): + return + datetime = datetime_module + names = set(name for name in dir(datetime) + if not name.startswith('__') and not name.endswith('__')) + allowed = set(['MAXYEAR', 'MINYEAR', 'date', 'datetime', + 'datetime_CAPI', 'time', 'timedelta', 'timezone', + 'tzinfo']) + self.assertEqual(names - allowed, set([])) + def test_divide_and_round(self): if '_Fast' in str(self): return @@ -650,8 +662,12 @@ class TestTimeDelta(HarmlessMixedComparison, unittest.TestCase): # Single-field rounding. eq(td(milliseconds=0.4/1000), td(0)) # rounds to 0 eq(td(milliseconds=-0.4/1000), td(0)) # rounds to 0 + eq(td(milliseconds=0.5/1000), td(microseconds=0)) + eq(td(milliseconds=-0.5/1000), td(microseconds=0)) eq(td(milliseconds=0.6/1000), td(microseconds=1)) eq(td(milliseconds=-0.6/1000), td(microseconds=-1)) + eq(td(seconds=0.5/10**6), td(microseconds=0)) + eq(td(seconds=-0.5/10**6), td(microseconds=0)) # Rounding due to contributions from more than one field. us_per_hour = 3600e6 @@ -1165,11 +1181,13 @@ class TestDate(HarmlessMixedComparison, unittest.TestCase): #check that this standard extension works t.strftime("%f") - def test_format(self): dt = self.theclass(2007, 9, 10) self.assertEqual(dt.__format__(''), str(dt)) + with self.assertRaisesRegex(TypeError, '^must be str, not int$'): + dt.__format__(123) + # check that a derived class's __str__() gets called class A(self.theclass): def __str__(self): @@ -1321,8 +1339,6 @@ class TestDate(HarmlessMixedComparison, unittest.TestCase): return isinstance(other, LargerThanAnything) def __eq__(self, other): return isinstance(other, LargerThanAnything) - def __ne__(self, other): - return not isinstance(other, LargerThanAnything) def __gt__(self, other): return not isinstance(other, LargerThanAnything) def __ge__(self, other): @@ -1425,9 +1441,10 @@ class TestDate(HarmlessMixedComparison, unittest.TestCase): for month_byte in b'9', b'\0', b'\r', b'\xff': self.assertRaises(TypeError, self.theclass, base[:2] + month_byte + base[3:]) - # Good bytes, but bad tzinfo: - self.assertRaises(TypeError, self.theclass, - bytes([1] * len(base)), 'EST') + if issubclass(self.theclass, datetime): + # Good bytes, but bad tzinfo: + with self.assertRaisesRegex(TypeError, '^bad tzinfo state arg$'): + self.theclass(bytes([1] * len(base)), 'EST') for ord_byte in range(1, 13): # This shouldn't blow up because of the month byte alone. If @@ -1503,6 +1520,9 @@ class TestDateTime(TestDate): dt = self.theclass(2007, 9, 10, 4, 5, 1, 123) self.assertEqual(dt.__format__(''), str(dt)) + with self.assertRaisesRegex(TypeError, '^must be str, not int$'): + dt.__format__(123) + # check that a derived class's __str__() gets called class A(self.theclass): def __str__(self): @@ -1824,6 +1844,7 @@ class TestDateTime(TestDate): tzinfo=timezone(timedelta(hours=-5), 'EST')) self.assertEqual(t.timestamp(), 18000 + 3600 + 2*60 + 3 + 4*1e-6) + def test_microsecond_rounding(self): for fts in [self.theclass.fromtimestamp, self.theclass.utcfromtimestamp]: @@ -1874,6 +1895,7 @@ class TestDateTime(TestDate): for insane in -1e200, 1e200: self.assertRaises(OverflowError, self.theclass.utcfromtimestamp, insane) + @unittest.skipIf(sys.platform == "win32", "Windows doesn't accept negative timestamps") def test_negative_float_fromtimestamp(self): # The result is tz-dependent; at least test that this doesn't @@ -2253,6 +2275,9 @@ class TestTime(HarmlessMixedComparison, unittest.TestCase): t = self.theclass(1, 2, 3, 4) self.assertEqual(t.__format__(''), str(t)) + with self.assertRaisesRegex(TypeError, '^must be str, not int$'): + t.__format__(123) + # check that a derived class's __str__() gets called class A(self.theclass): def __str__(self): @@ -2316,13 +2341,14 @@ class TestTime(HarmlessMixedComparison, unittest.TestCase): self.assertEqual(orig, derived) def test_bool(self): + # time is always True. cls = self.theclass self.assertTrue(cls(1)) self.assertTrue(cls(0, 1)) self.assertTrue(cls(0, 0, 1)) self.assertTrue(cls(0, 0, 0, 1)) - self.assertFalse(cls(0)) - self.assertFalse(cls()) + self.assertTrue(cls(0)) + self.assertTrue(cls()) def test_replace(self): cls = self.theclass @@ -2381,6 +2407,9 @@ class TestTime(HarmlessMixedComparison, unittest.TestCase): for hour_byte in ' ', '9', chr(24), '\xff': self.assertRaises(TypeError, self.theclass, hour_byte + base[1:]) + # Good bytes, but bad tzinfo: + with self.assertRaisesRegex(TypeError, '^bad tzinfo state arg$'): + self.theclass(bytes([1] * len(base)), 'EST') # A mixin for classes with a tzinfo= argument. Subclasses must define # theclass as a class atribute, and theclass(1, 1, 1, tzinfo=whatever) @@ -2640,7 +2669,7 @@ class TestTimeTZ(TestTime, TZInfoBase, unittest.TestCase): self.assertRaises(TypeError, t.strftime, "%Z") # Issue #6697: - if '_Fast' in str(type(self)): + if '_Fast' in str(self): Badtzname.tz = '\ud800' self.assertRaises(ValueError, t.strftime, "%Z") @@ -2675,7 +2704,7 @@ class TestTimeTZ(TestTime, TZInfoBase, unittest.TestCase): self.assertEqual(derived.tzname(), 'cookie') def test_more_bool(self): - # Test cases with non-None tzinfo. + # time is always True. cls = self.theclass t = cls(0, tzinfo=FixedOffset(-300, "")) @@ -2685,23 +2714,11 @@ class TestTimeTZ(TestTime, TZInfoBase, unittest.TestCase): self.assertTrue(t) t = cls(5, tzinfo=FixedOffset(300, "")) - self.assertFalse(t) + self.assertTrue(t) t = cls(23, 59, tzinfo=FixedOffset(23*60 + 59, "")) - self.assertFalse(t) - - # Mostly ensuring this doesn't overflow internally. - t = cls(0, tzinfo=FixedOffset(23*60 + 59, "")) self.assertTrue(t) - # But this should yield a value error -- the utcoffset is bogus. - t = cls(0, tzinfo=FixedOffset(24*60, "")) - self.assertRaises(ValueError, lambda: bool(t)) - - # Likewise. - t = cls(0, tzinfo=FixedOffset(-24*60, "")) - self.assertRaises(ValueError, lambda: bool(t)) - def test_replace(self): cls = self.theclass z100 = FixedOffset(100, "+100") @@ -3814,6 +3831,60 @@ class Oddballs(unittest.TestCase): self.assertEqual(as_datetime, datetime_sc) self.assertEqual(datetime_sc, as_datetime) + def test_extra_attributes(self): + for x in [date.today(), + time(), + datetime.utcnow(), + timedelta(), + tzinfo(), + timezone(timedelta())]: + with self.assertRaises(AttributeError): + x.abc = 1 + + def test_check_arg_types(self): + class Number: + def __init__(self, value): + self.value = value + def __int__(self): + return self.value + + for xx in [decimal.Decimal(10), + decimal.Decimal('10.9'), + Number(10)]: + self.assertEqual(datetime(10, 10, 10, 10, 10, 10, 10), + datetime(xx, xx, xx, xx, xx, xx, xx)) + + with self.assertRaisesRegex(TypeError, '^an integer is required ' + '\(got type str\)$'): + datetime(10, 10, '10') + + f10 = Number(10.9) + with self.assertRaisesRegex(TypeError, '^__int__ returned non-int ' + '\(type float\)$'): + datetime(10, 10, f10) + + class Float(float): + pass + s10 = Float(10.9) + with self.assertRaisesRegex(TypeError, '^integer argument expected, ' + 'got float$'): + datetime(10, 10, s10) + + with self.assertRaises(TypeError): + datetime(10., 10, 10) + with self.assertRaises(TypeError): + datetime(10, 10., 10) + with self.assertRaises(TypeError): + datetime(10, 10, 10.) + with self.assertRaises(TypeError): + datetime(10, 10, 10, 10.) + with self.assertRaises(TypeError): + datetime(10, 10, 10, 10, 10.) + with self.assertRaises(TypeError): + datetime(10, 10, 10, 10, 10, 10.) + with self.assertRaises(TypeError): + datetime(10, 10, 10, 10, 10, 10, 10.) + def test_main(): support.run_unittest(__name__) diff --git a/Lib/test/eintrdata/eintr_tester.py b/Lib/test/eintrdata/eintr_tester.py new file mode 100644 index 0000000..40dca84 --- /dev/null +++ b/Lib/test/eintrdata/eintr_tester.py @@ -0,0 +1,260 @@ +""" +This test suite exercises some system calls subject to interruption with EINTR, +to check that it is actually handled transparently. +It is intended to be run by the main test suite within a child process, to +ensure there is no background thread running (so that signals are delivered to +the correct thread). +Signals are generated in-process using setitimer(ITIMER_REAL), which allows +sub-second periodicity (contrarily to signal()). +""" + +import io +import os +import signal +import socket +import time +import unittest + +from test import support + + +@unittest.skipUnless(hasattr(signal, "setitimer"), "requires setitimer()") +class EINTRBaseTest(unittest.TestCase): + """ Base class for EINTR tests. """ + + # delay for initial signal delivery + signal_delay = 0.1 + # signal delivery periodicity + signal_period = 0.1 + # default sleep time for tests - should obviously have: + # sleep_time > signal_period + sleep_time = 0.2 + + @classmethod + def setUpClass(cls): + cls.orig_handler = signal.signal(signal.SIGALRM, lambda *args: None) + signal.setitimer(signal.ITIMER_REAL, cls.signal_delay, + cls.signal_period) + + @classmethod + def tearDownClass(cls): + signal.setitimer(signal.ITIMER_REAL, 0, 0) + signal.signal(signal.SIGALRM, cls.orig_handler) + + @classmethod + def _sleep(cls): + # default sleep time + time.sleep(cls.sleep_time) + + +@unittest.skipUnless(hasattr(signal, "setitimer"), "requires setitimer()") +class OSEINTRTest(EINTRBaseTest): + """ EINTR tests for the os module. """ + + def _test_wait_multiple(self, wait_func): + num = 3 + for _ in range(num): + pid = os.fork() + if pid == 0: + self._sleep() + os._exit(0) + for _ in range(num): + wait_func() + + def test_wait(self): + self._test_wait_multiple(os.wait) + + @unittest.skipUnless(hasattr(os, 'wait3'), 'requires wait3()') + def test_wait3(self): + self._test_wait_multiple(lambda: os.wait3(0)) + + def _test_wait_single(self, wait_func): + pid = os.fork() + if pid == 0: + self._sleep() + os._exit(0) + else: + wait_func(pid) + + def test_waitpid(self): + self._test_wait_single(lambda pid: os.waitpid(pid, 0)) + + @unittest.skipUnless(hasattr(os, 'wait4'), 'requires wait4()') + def test_wait4(self): + self._test_wait_single(lambda pid: os.wait4(pid, 0)) + + def test_read(self): + rd, wr = os.pipe() + self.addCleanup(os.close, rd) + # wr closed explicitly by parent + + # the payload below are smaller than PIPE_BUF, hence the writes will be + # atomic + datas = [b"hello", b"world", b"spam"] + + pid = os.fork() + if pid == 0: + os.close(rd) + for data in datas: + # let the parent block on read() + self._sleep() + os.write(wr, data) + os._exit(0) + else: + self.addCleanup(os.waitpid, pid, 0) + os.close(wr) + for data in datas: + self.assertEqual(data, os.read(rd, len(data))) + + def test_write(self): + rd, wr = os.pipe() + self.addCleanup(os.close, wr) + # rd closed explicitly by parent + + # we must write enough data for the write() to block + data = b"xyz" * support.PIPE_MAX_SIZE + + pid = os.fork() + if pid == 0: + os.close(wr) + read_data = io.BytesIO() + # let the parent block on write() + self._sleep() + while len(read_data.getvalue()) < len(data): + chunk = os.read(rd, 2 * len(data)) + read_data.write(chunk) + self.assertEqual(read_data.getvalue(), data) + os._exit(0) + else: + os.close(rd) + written = 0 + while written < len(data): + written += os.write(wr, memoryview(data)[written:]) + self.assertEqual(0, os.waitpid(pid, 0)[1]) + + +@unittest.skipUnless(hasattr(signal, "setitimer"), "requires setitimer()") +class SocketEINTRTest(EINTRBaseTest): + """ EINTR tests for the socket module. """ + + @unittest.skipUnless(hasattr(socket, 'socketpair'), 'needs socketpair()') + def _test_recv(self, recv_func): + rd, wr = socket.socketpair() + self.addCleanup(rd.close) + # wr closed explicitly by parent + + # single-byte payload guard us against partial recv + datas = [b"x", b"y", b"z"] + + pid = os.fork() + if pid == 0: + rd.close() + for data in datas: + # let the parent block on recv() + self._sleep() + wr.sendall(data) + os._exit(0) + else: + self.addCleanup(os.waitpid, pid, 0) + wr.close() + for data in datas: + self.assertEqual(data, recv_func(rd, len(data))) + + def test_recv(self): + self._test_recv(socket.socket.recv) + + @unittest.skipUnless(hasattr(socket.socket, 'recvmsg'), 'needs recvmsg()') + def test_recvmsg(self): + self._test_recv(lambda sock, data: sock.recvmsg(data)[0]) + + def _test_send(self, send_func): + rd, wr = socket.socketpair() + self.addCleanup(wr.close) + # rd closed explicitly by parent + + # we must send enough data for the send() to block + data = b"xyz" * (support.SOCK_MAX_SIZE // 3) + + pid = os.fork() + if pid == 0: + wr.close() + # let the parent block on send() + self._sleep() + received_data = bytearray(len(data)) + n = 0 + while n < len(data): + n += rd.recv_into(memoryview(received_data)[n:]) + self.assertEqual(received_data, data) + os._exit(0) + else: + rd.close() + written = 0 + while written < len(data): + sent = send_func(wr, memoryview(data)[written:]) + # sendall() returns None + written += len(data) if sent is None else sent + self.assertEqual(0, os.waitpid(pid, 0)[1]) + + def test_send(self): + self._test_send(socket.socket.send) + + def test_sendall(self): + self._test_send(socket.socket.sendall) + + @unittest.skipUnless(hasattr(socket.socket, 'sendmsg'), 'needs sendmsg()') + def test_sendmsg(self): + self._test_send(lambda sock, data: sock.sendmsg([data])) + + def test_accept(self): + sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM) + self.addCleanup(sock.close) + + sock.bind((support.HOST, 0)) + _, port = sock.getsockname() + sock.listen() + + pid = os.fork() + if pid == 0: + # let parent block on accept() + self._sleep() + with socket.create_connection((support.HOST, port)): + self._sleep() + os._exit(0) + else: + self.addCleanup(os.waitpid, pid, 0) + client_sock, _ = sock.accept() + client_sock.close() + + @unittest.skipUnless(hasattr(os, 'mkfifo'), 'needs mkfifo()') + def _test_open(self, do_open_close_reader, do_open_close_writer): + # Use a fifo: until the child opens it for reading, the parent will + # block when trying to open it for writing. + support.unlink(support.TESTFN) + os.mkfifo(support.TESTFN) + self.addCleanup(support.unlink, support.TESTFN) + + pid = os.fork() + if pid == 0: + # let the parent block + self._sleep() + do_open_close_reader(support.TESTFN) + os._exit(0) + else: + self.addCleanup(os.waitpid, pid, 0) + do_open_close_writer(support.TESTFN) + + def test_open(self): + self._test_open(lambda path: open(path, 'r').close(), + lambda path: open(path, 'w').close()) + + def test_os_open(self): + self._test_open(lambda path: os.close(os.open(path, os.O_RDONLY)), + lambda path: os.close(os.open(path, os.O_WRONLY))) + + +def test_main(): + support.run_unittest(OSEINTRTest, SocketEINTRTest) + + +if __name__ == "__main__": + test_main() diff --git a/Lib/test/fork_wait.py b/Lib/test/fork_wait.py index 19b54ec..713039d 100644 --- a/Lib/test/fork_wait.py +++ b/Lib/test/fork_wait.py @@ -48,7 +48,12 @@ class ForkWait(unittest.TestCase): for i in range(NUM_THREADS): _thread.start_new(self.f, (i,)) - time.sleep(LONGSLEEP) + # busy-loop to wait for threads + deadline = time.monotonic() + 10.0 + while len(self.alive) < NUM_THREADS: + time.sleep(0.1) + if deadline < time.monotonic(): + break a = sorted(self.alive.keys()) self.assertEqual(a, list(range(NUM_THREADS))) diff --git a/Lib/test/imghdrdata/python.exr b/Lib/test/imghdrdata/python.exr Binary files differnew file mode 100644 index 0000000..773c81e --- /dev/null +++ b/Lib/test/imghdrdata/python.exr diff --git a/Lib/test/imghdrdata/python.webp b/Lib/test/imghdrdata/python.webp Binary files differnew file mode 100644 index 0000000..e824ec7 --- /dev/null +++ b/Lib/test/imghdrdata/python.webp diff --git a/Lib/test/inspect_fodder2.py b/Lib/test/inspect_fodder2.py index bd7106f..e452235 100644 --- a/Lib/test/inspect_fodder2.py +++ b/Lib/test/inspect_fodder2.py @@ -109,3 +109,16 @@ def annotated(arg1: list): #line 109 def keyword_only_arg(*, arg): pass + +from functools import wraps + +def decorator(func): + @wraps(func) + def fake(): + return 42 + return fake + +#line 121 +@decorator +def real(): + return 20 diff --git a/Lib/test/list_tests.py b/Lib/test/list_tests.py index 42e118b..9069337 100644 --- a/Lib/test/list_tests.py +++ b/Lib/test/list_tests.py @@ -30,6 +30,12 @@ class CommonTest(seq_tests.CommonTest): self.assertNotEqual(id(a), id(b)) self.assertEqual(a, b) + def test_getitem_error(self): + msg = "list indices must be integers or slices" + with self.assertRaisesRegex(TypeError, msg): + a = [] + a['a'] = "python" + def test_repr(self): l0 = [] l2 = [0, 1, 2] @@ -120,6 +126,10 @@ class CommonTest(seq_tests.CommonTest): a[-1] = 9 self.assertEqual(a, self.type2test([5,6,7,8,9])) + msg = "list indices must be integers or slices" + with self.assertRaisesRegex(TypeError, msg): + a['a'] = "python" + def test_delitem(self): a = self.type2test([0, 1]) del a[1] diff --git a/Lib/test/lock_tests.py b/Lib/test/lock_tests.py index 1cbcea2..136f1c3 100644 --- a/Lib/test/lock_tests.py +++ b/Lib/test/lock_tests.py @@ -82,7 +82,13 @@ class BaseLockTests(BaseTestCase): def test_repr(self): lock = self.locktype() - repr(lock) + self.assertRegex(repr(lock), "<unlocked .* object (.*)?at .*>") + del lock + + def test_locked_repr(self): + lock = self.locktype() + lock.acquire() + self.assertRegex(repr(lock), "<locked .* object (.*)?at .*>") del lock def test_acquire_destroy(self): diff --git a/Lib/test/mock_socket.py b/Lib/test/mock_socket.py index e36724f..b28c473 100644 --- a/Lib/test/mock_socket.py +++ b/Lib/test/mock_socket.py @@ -35,8 +35,9 @@ class MockFile: class MockSocket: """Mock socket object used by smtpd and smtplib tests. """ - def __init__(self): + def __init__(self, family=None): global _reply_data + self.family = family self.output = [] self.lines = [] if _reply_data: @@ -101,15 +102,14 @@ class MockSocket: return len(data) def getpeername(self): - return 'peer' + return ('peer-address', 'peer-port') def close(self): pass def socket(family=None, type=None, proto=None): - return MockSocket() - + return MockSocket(family) def create_connection(address, timeout=socket_module._GLOBAL_DEFAULT_TIMEOUT, source_address=None): @@ -144,13 +144,16 @@ def gethostname(): def gethostbyname(name): return "" +def getaddrinfo(*args, **kw): + return socket_module.getaddrinfo(*args, **kw) gaierror = socket_module.gaierror error = socket_module.error # Constants -AF_INET = None -SOCK_STREAM = None +AF_INET = socket_module.AF_INET +AF_INET6 = socket_module.AF_INET6 +SOCK_STREAM = socket_module.SOCK_STREAM SOL_SOCKET = None SO_REUSEADDR = None diff --git a/Lib/test/pickletester.py b/Lib/test/pickletester.py index 55205d1..f8372e3 100644 --- a/Lib/test/pickletester.py +++ b/Lib/test/pickletester.py @@ -1154,16 +1154,62 @@ class AbstractPickleTests(unittest.TestCase): self.assertGreaterEqual(num_additems, 2) def test_simple_newobj(self): - x = object.__new__(SimpleNewObj) # avoid __init__ + x = SimpleNewObj.__new__(SimpleNewObj, 0xface) # avoid __init__ x.abc = 666 for proto in protocols: - s = self.dumps(x, proto) - self.assertEqual(opcode_in_pickle(pickle.NEWOBJ, s), - 2 <= proto < 4) - self.assertEqual(opcode_in_pickle(pickle.NEWOBJ_EX, s), - proto >= 4) - y = self.loads(s) # will raise TypeError if __init__ called - self.assert_is_copy(x, y) + with self.subTest(proto=proto): + s = self.dumps(x, proto) + if proto < 1: + self.assertIn(b'\nL64206', s) # LONG + else: + self.assertIn(b'M\xce\xfa', s) # BININT2 + self.assertEqual(opcode_in_pickle(pickle.NEWOBJ, s), + 2 <= proto) + self.assertFalse(opcode_in_pickle(pickle.NEWOBJ_EX, s)) + y = self.loads(s) # will raise TypeError if __init__ called + self.assert_is_copy(x, y) + + def test_complex_newobj(self): + x = ComplexNewObj.__new__(ComplexNewObj, 0xface) # avoid __init__ + x.abc = 666 + for proto in protocols: + with self.subTest(proto=proto): + s = self.dumps(x, proto) + if proto < 1: + self.assertIn(b'\nL64206', s) # LONG + elif proto < 2: + self.assertIn(b'M\xce\xfa', s) # BININT2 + elif proto < 4: + self.assertIn(b'X\x04\x00\x00\x00FACE', s) # BINUNICODE + else: + self.assertIn(b'\x8c\x04FACE', s) # SHORT_BINUNICODE + self.assertEqual(opcode_in_pickle(pickle.NEWOBJ, s), + 2 <= proto) + self.assertFalse(opcode_in_pickle(pickle.NEWOBJ_EX, s)) + y = self.loads(s) # will raise TypeError if __init__ called + self.assert_is_copy(x, y) + + def test_complex_newobj_ex(self): + x = ComplexNewObjEx.__new__(ComplexNewObjEx, 0xface) # avoid __init__ + x.abc = 666 + for proto in protocols: + with self.subTest(proto=proto): + if 2 <= proto < 4: + self.assertRaises(ValueError, self.dumps, x, proto) + continue + s = self.dumps(x, proto) + if proto < 1: + self.assertIn(b'\nL64206', s) # LONG + elif proto < 2: + self.assertIn(b'M\xce\xfa', s) # BININT2 + else: + assert proto >= 4 + self.assertIn(b'\x8c\x04FACE', s) # SHORT_BINUNICODE + self.assertFalse(opcode_in_pickle(pickle.NEWOBJ, s)) + self.assertEqual(opcode_in_pickle(pickle.NEWOBJ_EX, s), + 4 <= proto) + y = self.loads(s) # will raise TypeError if __init__ called + self.assert_is_copy(x, y) def test_newobj_list_slots(self): x = SlotList([1, 2, 3]) @@ -1645,6 +1691,27 @@ class AbstractPickleTests(unittest.TestCase): unpickled = self.loads(self.dumps(method, proto)) self.assertEqual(method(*args), unpickled(*args)) + def test_local_lookup_error(self): + # Test that whichmodule() errors out cleanly when looking up + # an assumed globally-reachable object fails. + def f(): + pass + # Since the function is local, lookup will fail + for proto in range(0, pickle.HIGHEST_PROTOCOL + 1): + with self.assertRaises((AttributeError, pickle.PicklingError)): + pickletools.dis(self.dumps(f, proto)) + # Same without a __module__ attribute (exercises a different path + # in _pickle.c). + del f.__module__ + for proto in range(0, pickle.HIGHEST_PROTOCOL + 1): + with self.assertRaises((AttributeError, pickle.PicklingError)): + pickletools.dis(self.dumps(f, proto)) + # Yet a different path. + f.__name__ = f.__qualname__ + for proto in range(0, pickle.HIGHEST_PROTOCOL + 1): + with self.assertRaises((AttributeError, pickle.PicklingError)): + pickletools.dis(self.dumps(f, proto)) + class BigmemPickleTests(unittest.TestCase): @@ -1879,12 +1946,20 @@ myclasses = [MyInt, MyFloat, class SlotList(MyList): __slots__ = ["foo"] -class SimpleNewObj(object): - def __init__(self, a, b, c): +class SimpleNewObj(int): + def __init__(self, *args, **kwargs): # raise an error, to make sure this isn't called raise TypeError("SimpleNewObj.__init__() didn't expect to get called") def __eq__(self, other): - return self.__dict__ == other.__dict__ + return int(self) == int(other) and self.__dict__ == other.__dict__ + +class ComplexNewObj(SimpleNewObj): + def __getnewargs__(self): + return ('%X' % self, 16) + +class ComplexNewObjEx(SimpleNewObj): + def __getnewargs_ex__(self): + return ('%X' % self,), {'base': 16} class BadGetattr: def __getattr__(self, key): diff --git a/Lib/test/pystone.py b/Lib/test/pystone.py index a41f1e5..1f67e66 100755 --- a/Lib/test/pystone.py +++ b/Lib/test/pystone.py @@ -41,7 +41,7 @@ Version History: LOOPS = 50000 -from time import clock +from time import time __version__ = "1.2" @@ -93,10 +93,10 @@ def Proc0(loops=LOOPS): global PtrGlb global PtrGlbNext - starttime = clock() + starttime = time() for i in range(loops): pass - nulltime = clock() - starttime + nulltime = time() - starttime PtrGlbNext = Record() PtrGlb = Record() @@ -108,7 +108,7 @@ def Proc0(loops=LOOPS): String1Loc = "DHRYSTONE PROGRAM, 1'ST STRING" Array2Glob[8][7] = 10 - starttime = clock() + starttime = time() for i in range(loops): Proc5() @@ -134,7 +134,7 @@ def Proc0(loops=LOOPS): IntLoc2 = 7 * (IntLoc3 - IntLoc2) - IntLoc1 IntLoc1 = Proc2(IntLoc1) - benchtime = clock() - starttime - nulltime + benchtime = time() - starttime - nulltime if benchtime == 0.0: loopsPerBenchtime = 0.0 else: diff --git a/Lib/test/regrtest.py b/Lib/test/regrtest.py index b633631..ea1287d 100755 --- a/Lib/test/regrtest.py +++ b/Lib/test/regrtest.py @@ -1276,6 +1276,10 @@ def runtest_inner(test, verbose, quiet, def test_runner(): loader = unittest.TestLoader() tests = loader.loadTestsFromModule(the_module) + for error in loader.errors: + print(error, file=sys.stderr) + if loader.errors: + raise Exception("errors while loading tests") support.run_unittest(tests) test_runner() if huntrleaks: diff --git a/Lib/test/script_helper.py b/Lib/test/script_helper.py index 8c599d1..5531a34 100644 --- a/Lib/test/script_helper.py +++ b/Lib/test/script_helper.py @@ -19,7 +19,7 @@ from test.support import make_legacy_pyc, strip_python_stderr, temp_dir # Cached result of the expensive test performed in the function below. __cached_interp_requires_environment = None -def _interpreter_requires_environment(): +def interpreter_requires_environment(): """ Returns True if our sys.executable interpreter requires environment variables in order to be able to run at all. @@ -52,7 +52,7 @@ def _interpreter_requires_environment(): # Executing the interpreter in a subprocess def _assert_python(expected_success, *args, **env_vars): - env_required = _interpreter_requires_environment() + env_required = interpreter_requires_environment() if '__isolated' in env_vars: isolated = env_vars.pop('__isolated') else: diff --git a/Lib/test/ssl_servers.py b/Lib/test/ssl_servers.py index 759b3f4..f9d30cf 100644 --- a/Lib/test/ssl_servers.py +++ b/Lib/test/ssl_servers.py @@ -150,7 +150,7 @@ class HTTPSServerThread(threading.Thread): def make_https_server(case, *, context=None, certfile=CERTFILE, host=HOST, handler_class=None): if context is None: - context = ssl.SSLContext(ssl.PROTOCOL_SSLv23) + context = ssl.create_default_context(ssl.Purpose.CLIENT_AUTH) # We assume the certfile contains both private key and certificate context.load_cert_chain(certfile) server = HTTPSServerThread(context, host, handler_class) @@ -182,6 +182,8 @@ if __name__ == "__main__": parser.add_argument('--curve-name', dest='curve_name', type=str, action='store', help='curve name for EC-based Diffie-Hellman') + parser.add_argument('--ciphers', dest='ciphers', type=str, + help='allowed cipher list') parser.add_argument('--dh', dest='dh_file', type=str, action='store', help='PEM file containing DH parameters') args = parser.parse_args() @@ -192,12 +194,14 @@ if __name__ == "__main__": else: handler_class = RootedHTTPRequestHandler handler_class.root = os.getcwd() - context = ssl.SSLContext(ssl.PROTOCOL_TLSv1) + context = ssl.create_default_context(ssl.Purpose.CLIENT_AUTH) context.load_cert_chain(CERTFILE) if args.curve_name: context.set_ecdh_curve(args.curve_name) if args.dh_file: context.load_dh_params(args.dh_file) + if args.ciphers: + context.set_ciphers(args.ciphers) server = HTTPSServer(("", args.port), handler_class, context) if args.verbose: diff --git a/Lib/test/string_tests.py b/Lib/test/string_tests.py index 242a931..6e26474 100644 --- a/Lib/test/string_tests.py +++ b/Lib/test/string_tests.py @@ -1176,8 +1176,7 @@ class MixinStrUnicodeUserStringTest: self.checkraises(TypeError, 'abc', '__mod__') self.checkraises(TypeError, '%(foo)s', '__mod__', 42) self.checkraises(TypeError, '%s%s', '__mod__', (42,)) - with self.assertWarns(DeprecationWarning): - self.checkraises(TypeError, '%c', '__mod__', (None,)) + self.checkraises(TypeError, '%c', '__mod__', (None,)) self.checkraises(ValueError, '%(foo', '__mod__', {}) self.checkraises(TypeError, '%(foo)s %(bar)s', '__mod__', ('foo', 42)) self.checkraises(TypeError, '%d', '__mod__', "42") # not numeric diff --git a/Lib/test/support/__init__.py b/Lib/test/support/__init__.py index 32b5687..0ef2e8a 100644 --- a/Lib/test/support/__init__.py +++ b/Lib/test/support/__init__.py @@ -1040,7 +1040,8 @@ def open_urlresource(url, *args, **kw): # Verify the requirement before downloading the file requires('urlfetch') - print('\tfetching %s ...' % url, file=get_original_stdout()) + if verbose: + print('\tfetching %s ...' % url, file=get_original_stdout()) opener = urllib.request.build_opener() if gzip: opener.addheaders.append(('Accept-Encoding', 'gzip')) @@ -2152,6 +2153,7 @@ class SuppressCrashReport: disable the creation of coredump file. """ old_value = None + old_modes = None def __enter__(self): """On Windows, disable Windows Error Reporting dialogs using @@ -2169,6 +2171,26 @@ class SuppressCrashReport: SEM_NOGPFAULTERRORBOX = 0x02 self.old_value = self._k32.SetErrorMode(SEM_NOGPFAULTERRORBOX) self._k32.SetErrorMode(self.old_value | SEM_NOGPFAULTERRORBOX) + + # Suppress assert dialogs in debug builds + # (see http://bugs.python.org/issue23314) + try: + import msvcrt + msvcrt.CrtSetReportMode + except (AttributeError, ImportError): + # no msvcrt or a release build + pass + else: + self.old_modes = {} + for report_type in [msvcrt.CRT_WARN, + msvcrt.CRT_ERROR, + msvcrt.CRT_ASSERT]: + old_mode = msvcrt.CrtSetReportMode(report_type, + msvcrt.CRTDBG_MODE_FILE) + old_file = msvcrt.CrtSetReportFile(report_type, + msvcrt.CRTDBG_FILE_STDERR) + self.old_modes[report_type] = old_mode, old_file + else: if resource is not None: try: @@ -2200,6 +2222,12 @@ class SuppressCrashReport: if sys.platform.startswith('win'): self._k32.SetErrorMode(self.old_value) + + if self.old_modes: + import msvcrt + for report_type, (old_mode, old_file) in self.old_modes.items(): + msvcrt.CrtSetReportMode(report_type, old_mode) + msvcrt.CrtSetReportFile(report_type, old_file) else: if resource is not None: try: diff --git a/Lib/test/test_argparse.py b/Lib/test/test_argparse.py index 1164f3f..d7f90cd 100644 --- a/Lib/test/test_argparse.py +++ b/Lib/test/test_argparse.py @@ -20,15 +20,6 @@ class StdIOBuffer(StringIO): class TestCase(unittest.TestCase): - def assertEqual(self, obj1, obj2): - if obj1 != obj2: - print('') - print(repr(obj1)) - print(repr(obj2)) - print(obj1) - print(obj2) - super(TestCase, self).assertEqual(obj1, obj2) - def setUp(self): # The tests assume that line wrapping occurs at 80 columns, but this # behaviour can be overridden by setting the COLUMNS environment @@ -78,9 +69,6 @@ class NS(object): def __eq__(self, other): return vars(self) == vars(other) - def __ne__(self, other): - return not (self == other) - class ArgumentParserError(Exception): @@ -765,6 +753,39 @@ class TestOptionalsActionCount(ParserTestCase): ] +class TestOptionalsAllowLongAbbreviation(ParserTestCase): + """Allow long options to be abbreviated unambiguously""" + + argument_signatures = [ + Sig('--foo'), + Sig('--foobaz'), + Sig('--fooble', action='store_true'), + ] + failures = ['--foob 5', '--foob'] + successes = [ + ('', NS(foo=None, foobaz=None, fooble=False)), + ('--foo 7', NS(foo='7', foobaz=None, fooble=False)), + ('--fooba a', NS(foo=None, foobaz='a', fooble=False)), + ('--foobl --foo g', NS(foo='g', foobaz=None, fooble=True)), + ] + + +class TestOptionalsDisallowLongAbbreviation(ParserTestCase): + """Do not allow abbreviations of long options at all""" + + parser_signature = Sig(allow_abbrev=False) + argument_signatures = [ + Sig('--foo'), + Sig('--foodle', action='store_true'), + Sig('--foonly'), + ] + failures = ['-foon 3', '--foon 3', '--food', '--food --foo 2'] + successes = [ + ('', NS(foo=None, foodle=False, foonly=None)), + ('--foo 3', NS(foo='3', foodle=False, foonly=None)), + ('--foonly 7 --foodle --foo 2', NS(foo='2', foodle=True, foonly='7')), + ] + # ================ # Positional tests # ================ @@ -1993,14 +2014,9 @@ class TestAddSubparsers(TestCase): ''')) def _test_subparser_help(self, args_str, expected_help): - try: + with self.assertRaises(ArgumentParserError) as cm: self.parser.parse_args(args_str.split()) - except ArgumentParserError: - err = sys.exc_info()[1] - if err.stdout != expected_help: - print(repr(expected_help)) - print(repr(err.stdout)) - self.assertEqual(err.stdout, expected_help) + self.assertEqual(expected_help, cm.exception.stdout) def test_subparser1_help(self): self._test_subparser_help('5.0 1 -h', textwrap.dedent('''\ @@ -2846,15 +2862,15 @@ class TestGetDefault(TestCase): def test_get_default(self): parser = ErrorRaisingArgumentParser() - self.assertEqual(None, parser.get_default("foo")) - self.assertEqual(None, parser.get_default("bar")) + self.assertIsNone(parser.get_default("foo")) + self.assertIsNone(parser.get_default("bar")) parser.add_argument("--foo") - self.assertEqual(None, parser.get_default("foo")) - self.assertEqual(None, parser.get_default("bar")) + self.assertIsNone(parser.get_default("foo")) + self.assertIsNone(parser.get_default("bar")) parser.add_argument("--bar", type=int, default=42) - self.assertEqual(None, parser.get_default("foo")) + self.assertIsNone(parser.get_default("foo")) self.assertEqual(42, parser.get_default("bar")) parser.set_defaults(foo="badger") @@ -2869,18 +2885,16 @@ class TestNamespaceContainsSimple(TestCase): def test_empty(self): ns = argparse.Namespace() - self.assertEqual('' in ns, False) - self.assertEqual('' not in ns, True) - self.assertEqual('x' in ns, False) + self.assertNotIn('', ns) + self.assertNotIn('x', ns) def test_non_empty(self): ns = argparse.Namespace(x=1, y=2) - self.assertEqual('x' in ns, True) - self.assertEqual('x' not in ns, False) - self.assertEqual('y' in ns, True) - self.assertEqual('' in ns, False) - self.assertEqual('xx' in ns, False) - self.assertEqual('z' in ns, False) + self.assertNotIn('', ns) + self.assertIn('x', ns) + self.assertIn('y', ns) + self.assertNotIn('xx', ns) + self.assertNotIn('z', ns) # ===================== # Help formatting tests @@ -2936,13 +2950,6 @@ class TestHelpFormattingMetaclass(type): def _test(self, tester, parser_text): expected_text = getattr(tester, self.func_suffix) expected_text = textwrap.dedent(expected_text) - if expected_text != parser_text: - print(repr(expected_text)) - print(repr(parser_text)) - for char1, char2 in zip(expected_text, parser_text): - if char1 != char2: - print('first diff: %r %r' % (char1, char2)) - break tester.assertEqual(expected_text, parser_text) def test_format(self, tester): @@ -4223,24 +4230,17 @@ class TestInvalidArgumentConstructors(TestCase): self.assertValueError('foo', action='baz') self.assertValueError('--foo', action=('store', 'append')) parser = argparse.ArgumentParser() - try: + with self.assertRaises(ValueError) as cm: parser.add_argument("--foo", action="store-true") - except ValueError: - e = sys.exc_info()[1] - expected = 'unknown action' - msg = 'expected %r, found %r' % (expected, e) - self.assertTrue(expected in str(e), msg) + self.assertIn('unknown action', str(cm.exception)) def test_multiple_dest(self): parser = argparse.ArgumentParser() parser.add_argument(dest='foo') - try: + with self.assertRaises(ValueError) as cm: parser.add_argument('bar', dest='baz') - except ValueError: - e = sys.exc_info()[1] - expected = 'dest supplied twice for positional argument' - msg = 'expected %r, found %r' % (expected, e) - self.assertTrue(expected in str(e), msg) + self.assertIn('dest supplied twice for positional argument', + str(cm.exception)) def test_no_argument_actions(self): for action in ['store_const', 'store_true', 'store_false', @@ -4397,18 +4397,10 @@ class TestConflictHandling(TestCase): class TestOptionalsHelpVersionActions(TestCase): """Test the help and version actions""" - def _get_error(self, func, *args, **kwargs): - try: - func(*args, **kwargs) - except ArgumentParserError: - return sys.exc_info()[1] - else: - self.assertRaises(ArgumentParserError, func, *args, **kwargs) - def assertPrintHelpExit(self, parser, args_str): - self.assertEqual( - parser.format_help(), - self._get_error(parser.parse_args, args_str.split()).stdout) + with self.assertRaises(ArgumentParserError) as cm: + parser.parse_args(args_str.split()) + self.assertEqual(parser.format_help(), cm.exception.stdout) def assertArgumentParserError(self, parser, *args): self.assertRaises(ArgumentParserError, parser.parse_args, args) @@ -4423,8 +4415,9 @@ class TestOptionalsHelpVersionActions(TestCase): def test_version_format(self): parser = ErrorRaisingArgumentParser(prog='PPP') parser.add_argument('-v', '--version', action='version', version='%(prog)s 3.5') - msg = self._get_error(parser.parse_args, ['-v']).stdout - self.assertEqual('PPP 3.5\n', msg) + with self.assertRaises(ArgumentParserError) as cm: + parser.parse_args(['-v']) + self.assertEqual('PPP 3.5\n', cm.exception.stdout) def test_version_no_help(self): parser = ErrorRaisingArgumentParser(add_help=False) @@ -4436,8 +4429,9 @@ class TestOptionalsHelpVersionActions(TestCase): def test_version_action(self): parser = ErrorRaisingArgumentParser(prog='XXX') parser.add_argument('-V', action='version', version='%(prog)s 3.7') - msg = self._get_error(parser.parse_args, ['-V']).stdout - self.assertEqual('XXX 3.7\n', msg) + with self.assertRaises(ArgumentParserError) as cm: + parser.parse_args(['-V']) + self.assertEqual('XXX 3.7\n', cm.exception.stdout) def test_no_help(self): parser = ErrorRaisingArgumentParser(add_help=False) @@ -4607,14 +4601,10 @@ class TestArgumentTypeError(TestCase): parser = ErrorRaisingArgumentParser(prog='PROG', add_help=False) parser.add_argument('x', type=spam) - try: + with self.assertRaises(ArgumentParserError) as cm: parser.parse_args(['XXX']) - except ArgumentParserError: - expected = 'usage: PROG x\nPROG: error: argument x: spam!\n' - msg = sys.exc_info()[1].stderr - self.assertEqual(expected, msg) - else: - self.fail() + self.assertEqual('usage: PROG x\nPROG: error: argument x: spam!\n', + cm.exception.stderr) # ========================= # MessageContentError tests diff --git a/Lib/test/test_array.py b/Lib/test/test_array.py index 07c9bf9..10d9946 100644 --- a/Lib/test/test_array.py +++ b/Lib/test/test_array.py @@ -394,7 +394,9 @@ class BaseTest: self.assertEqual(a, b) def test_tofromstring(self): - nb_warnings = 4 + # Warnings not raised when arguments are incorrect as Argument Clinic + # handles that before the warning can be raised. + nb_warnings = 2 with warnings.catch_warnings(record=True) as r: warnings.filterwarnings("always", message=r"(to|from)string\(\) is deprecated", @@ -1039,6 +1041,11 @@ class BaseTest: a = array.array(self.typecode, "foo") a = array.array(self.typecode, array.array('u', 'foo')) + @support.cpython_only + def test_obsolete_write_lock(self): + from _testcapi import getbuffer_with_null_view + a = array.array('B', b"") + self.assertRaises(BufferError, getbuffer_with_null_view, a) class StringTest(BaseTest): diff --git a/Lib/test/test_asdl_parser.py b/Lib/test/test_asdl_parser.py new file mode 100644 index 0000000..7a6426a --- /dev/null +++ b/Lib/test/test_asdl_parser.py @@ -0,0 +1,122 @@ +"""Tests for the asdl parser in Parser/asdl.py""" + +import importlib.machinery +import os +from os.path import dirname +import sys +import sysconfig +import unittest + + +# This test is only relevant for from-source builds of Python. +if not sysconfig.is_python_build(): + raise unittest.SkipTest('test irrelevant for an installed Python') + +src_base = dirname(dirname(dirname(__file__))) +parser_dir = os.path.join(src_base, 'Parser') + + +class TestAsdlParser(unittest.TestCase): + @classmethod + def setUpClass(cls): + # Loads the asdl module dynamically, since it's not in a real importable + # package. + # Parses Python.asdl into a ast.Module and run the check on it. + # There's no need to do this for each test method, hence setUpClass. + sys.path.insert(0, parser_dir) + loader = importlib.machinery.SourceFileLoader( + 'asdl', os.path.join(parser_dir, 'asdl.py')) + cls.asdl = loader.load_module() + cls.mod = cls.asdl.parse(os.path.join(parser_dir, 'Python.asdl')) + cls.assertTrue(cls.asdl.check(cls.mod), 'Module validation failed') + + @classmethod + def tearDownClass(cls): + del sys.path[0] + + def setUp(self): + # alias stuff from the class, for convenience + self.asdl = TestAsdlParser.asdl + self.mod = TestAsdlParser.mod + self.types = self.mod.types + + def test_module(self): + self.assertEqual(self.mod.name, 'Python') + self.assertIn('stmt', self.types) + self.assertIn('expr', self.types) + self.assertIn('mod', self.types) + + def test_definitions(self): + defs = self.mod.dfns + self.assertIsInstance(defs[0], self.asdl.Type) + self.assertIsInstance(defs[0].value, self.asdl.Sum) + + self.assertIsInstance(self.types['withitem'], self.asdl.Product) + self.assertIsInstance(self.types['alias'], self.asdl.Product) + + def test_product(self): + alias = self.types['alias'] + self.assertEqual( + str(alias), + 'Product([Field(identifier, name), Field(identifier, asname, opt=True)])') + + def test_attributes(self): + stmt = self.types['stmt'] + self.assertEqual(len(stmt.attributes), 2) + self.assertEqual(str(stmt.attributes[0]), 'Field(int, lineno)') + self.assertEqual(str(stmt.attributes[1]), 'Field(int, col_offset)') + + def test_constructor_fields(self): + ehandler = self.types['excepthandler'] + self.assertEqual(len(ehandler.types), 1) + self.assertEqual(len(ehandler.attributes), 2) + + cons = ehandler.types[0] + self.assertIsInstance(cons, self.asdl.Constructor) + self.assertEqual(len(cons.fields), 3) + + f0 = cons.fields[0] + self.assertEqual(f0.type, 'expr') + self.assertEqual(f0.name, 'type') + self.assertTrue(f0.opt) + + f1 = cons.fields[1] + self.assertEqual(f1.type, 'identifier') + self.assertEqual(f1.name, 'name') + self.assertTrue(f1.opt) + + f2 = cons.fields[2] + self.assertEqual(f2.type, 'stmt') + self.assertEqual(f2.name, 'body') + self.assertFalse(f2.opt) + self.assertTrue(f2.seq) + + def test_visitor(self): + class CustomVisitor(self.asdl.VisitorBase): + def __init__(self): + super().__init__() + self.names_with_seq = [] + + def visitModule(self, mod): + for dfn in mod.dfns: + self.visit(dfn) + + def visitType(self, type): + self.visit(type.value) + + def visitSum(self, sum): + for t in sum.types: + self.visit(t) + + def visitConstructor(self, cons): + for f in cons.fields: + if f.seq: + self.names_with_seq.append(cons.name) + + v = CustomVisitor() + v.visit(self.types['mod']) + self.assertEqual(v.names_with_seq, ['Module', 'Interactive', 'Suite']) + + +if __name__ == '__main__': + unittest.main() diff --git a/Lib/test/test_asynchat.py b/Lib/test/test_asynchat.py index 2dc9d0c..3a33fc8 100644 --- a/Lib/test/test_asynchat.py +++ b/Lib/test/test_asynchat.py @@ -12,6 +12,7 @@ import socket import sys import time import unittest +import warnings import unittest.mock try: import threading @@ -38,7 +39,7 @@ if threading: self.start_resend_event = None def run(self): - self.sock.listen(1) + self.sock.listen() self.event.set() conn, client = self.sock.accept() self.buffer = b"" @@ -298,7 +299,10 @@ class TestHelperFunctions(unittest.TestCase): class TestFifo(unittest.TestCase): def test_basic(self): - f = asynchat.fifo() + with self.assertWarns(DeprecationWarning) as cm: + f = asynchat.fifo() + self.assertEqual(str(cm.warning), + "fifo class will be removed in Python 3.6") f.push(7) f.push(b'a') self.assertEqual(len(f), 2) @@ -313,7 +317,10 @@ class TestFifo(unittest.TestCase): self.assertEqual(f.pop(), (0, None)) def test_given_list(self): - f = asynchat.fifo([b'x', 17, 3]) + with self.assertWarns(DeprecationWarning) as cm: + f = asynchat.fifo([b'x', 17, 3]) + self.assertEqual(str(cm.warning), + "fifo class will be removed in Python 3.6") self.assertEqual(len(f), 3) self.assertEqual(f.pop(), (1, b'x')) self.assertEqual(f.pop(), (1, 17)) diff --git a/Lib/test/test_asyncore.py b/Lib/test/test_asyncore.py index d44726d..3857916 100644 --- a/Lib/test/test_asyncore.py +++ b/Lib/test/test_asyncore.py @@ -7,7 +7,6 @@ import sys import time import errno import struct -import warnings from test import support from io import BytesIO @@ -65,7 +64,7 @@ class crashingdummy: # used when testing senders; just collects what it gets until newline is sent def capture_server(evt, buf, serv): try: - serv.listen(5) + serv.listen() conn, addr = serv.accept() except socket.timeout: pass @@ -298,23 +297,6 @@ class DispatcherTests(unittest.TestCase): 'warning: unhandled connect event'] self.assertEqual(lines, expected) - def test_issue_8594(self): - # XXX - this test is supposed to be removed in next major Python - # version - d = asyncore.dispatcher(socket.socket()) - # make sure the error message no longer refers to the socket - # object but the dispatcher instance instead - self.assertRaisesRegex(AttributeError, 'dispatcher instance', - getattr, d, 'foo') - # cheap inheritance with the underlying socket is supposed - # to still work but a DeprecationWarning is expected - with warnings.catch_warnings(record=True) as w: - warnings.simplefilter("always") - family = d.family - self.assertEqual(family, socket.AF_INET) - self.assertEqual(len(w), 1) - self.assertTrue(issubclass(w[0].category, DeprecationWarning)) - def test_strerror(self): # refers to bug #8573 err = asyncore._strerror(errno.EPERM) @@ -331,9 +313,8 @@ class dispatcherwithsend_noread(asyncore.dispatcher_with_send): def handle_connect(self): pass -class DispatcherWithSendTests(unittest.TestCase): - usepoll = False +class DispatcherWithSendTests(unittest.TestCase): def setUp(self): pass @@ -383,10 +364,6 @@ class DispatcherWithSendTests(unittest.TestCase): self.fail("join() timed out") - -class DispatcherWithSendTests_UsePoll(DispatcherWithSendTests): - usepoll = True - @unittest.skipUnless(hasattr(asyncore, 'file_wrapper'), 'asyncore.file_wrapper required') class FileWrapperTest(unittest.TestCase): diff --git a/Lib/test/test_augassign.py b/Lib/test/test_augassign.py index 9a59c58..19b7687 100644 --- a/Lib/test/test_augassign.py +++ b/Lib/test/test_augassign.py @@ -136,6 +136,14 @@ class AugAssignTest(unittest.TestCase): output.append("__imul__ called") return self + def __matmul__(self, val): + output.append("__matmul__ called") + def __rmatmul__(self, val): + output.append("__rmatmul__ called") + def __imatmul__(self, val): + output.append("__imatmul__ called") + return self + def __div__(self, val): output.append("__div__ called") def __rdiv__(self, val): @@ -233,6 +241,10 @@ class AugAssignTest(unittest.TestCase): 1 * x x *= 1 + x @ 1 + 1 @ x + x @= 1 + x / 1 1 / x x /= 1 @@ -279,6 +291,9 @@ __isub__ called __mul__ called __rmul__ called __imul__ called +__matmul__ called +__rmatmul__ called +__imatmul__ called __truediv__ called __rtruediv__ called __itruediv__ called diff --git a/Lib/test/test_buffer.py b/Lib/test/test_buffer.py index 1667847..0976fa9 100644 --- a/Lib/test/test_buffer.py +++ b/Lib/test/test_buffer.py @@ -216,7 +216,7 @@ def iter_format(nitems, testobj='ndarray'): for t in iter_mode(nitems, testobj): yield t if testobj != 'ndarray': - raise StopIteration + return yield struct_items(nitems, testobj) @@ -1007,6 +1007,7 @@ class TestBufferProtocol(unittest.TestCase): # shape, strides, offset structure = ( ([], [], 0), + ([1,3,1], [], 0), ([12], [], 0), ([12], [-1], 11), ([6], [2], 0), @@ -1078,6 +1079,18 @@ class TestBufferProtocol(unittest.TestCase): self.assertRaises(BufferError, ndarray, ex, getbuf=PyBUF_ANY_CONTIGUOUS) nd = ndarray(ex, getbuf=PyBUF_SIMPLE) + # Issue #22445: New precise contiguity definition. + for shape in [1,12,1], [7,0,7]: + for order in 0, ND_FORTRAN: + ex = ndarray(items, shape=shape, flags=order|ND_WRITABLE) + self.assertTrue(is_contiguous(ex, 'F')) + self.assertTrue(is_contiguous(ex, 'C')) + + for flags in requests: + nd = ndarray(ex, getbuf=flags) + self.assertTrue(is_contiguous(nd, 'F')) + self.assertTrue(is_contiguous(nd, 'C')) + def test_ndarray_exceptions(self): nd = ndarray([9], [1]) ndm = ndarray([9], [1], flags=ND_VAREXPORT) diff --git a/Lib/test/test_builtin.py b/Lib/test/test_builtin.py index 14366c6..6166da5 100644 --- a/Lib/test/test_builtin.py +++ b/Lib/test/test_builtin.py @@ -312,11 +312,11 @@ class BuiltinTest(unittest.TestCase): self.assertRaises(TypeError, compile) self.assertRaises(ValueError, compile, 'print(42)\n', '<string>', 'badmode') self.assertRaises(ValueError, compile, 'print(42)\n', '<string>', 'single', 0xff) - self.assertRaises(TypeError, compile, chr(0), 'f', 'exec') + self.assertRaises(ValueError, compile, chr(0), 'f', 'exec') self.assertRaises(TypeError, compile, 'pass', '?', 'exec', mode='eval', source='0', filename='tmp') compile('print("\xe5")\n', '', 'exec') - self.assertRaises(TypeError, compile, chr(0), 'f', 'exec') + self.assertRaises(ValueError, compile, chr(0), 'f', 'exec') self.assertRaises(ValueError, compile, str('a = 1'), 'f', 'bad') # test the optimize argument @@ -1094,7 +1094,7 @@ class BuiltinTest(unittest.TestCase): self.assertAlmostEqual(pow(-1, 0.5), 1j) self.assertAlmostEqual(pow(-1, 1/3), 0.5 + 0.8660254037844386j) - self.assertRaises(TypeError, pow, -1, -2, 3) + self.assertRaises(ValueError, pow, -1, -2, 3) self.assertRaises(ValueError, pow, 1, 2, 0) self.assertRaises(TypeError, pow) diff --git a/Lib/test/test_bytes.py b/Lib/test/test_bytes.py index e15807e..a9f64a0 100644 --- a/Lib/test/test_bytes.py +++ b/Lib/test/test_bytes.py @@ -461,6 +461,28 @@ class BaseBytesTest: self.assertEqual(b.rindex(i, 3, 9), 7) self.assertRaises(ValueError, b.rindex, w, 1, 3) + def test_mod(self): + b = b'hello, %b!' + orig = b + b = b % b'world' + self.assertEqual(b, b'hello, world!') + self.assertEqual(orig, b'hello, %b!') + self.assertFalse(b is orig) + b = b'%s / 100 = %d%%' + a = b % (b'seventy-nine', 79) + self.assertEqual(a, b'seventy-nine / 100 = 79%') + + def test_imod(self): + b = b'hello, %b!' + orig = b + b %= b'world' + self.assertEqual(b, b'hello, world!') + self.assertEqual(orig, b'hello, %b!') + self.assertFalse(b is orig) + b = b'%s / 100 = %d%%' + b %= (b'seventy-nine', 79) + self.assertEqual(b, b'seventy-nine / 100 = 79%') + def test_replace(self): b = self.type2test(b'mississippi') self.assertEqual(b.replace(b'i', b'a'), b'massassappa') @@ -722,6 +744,11 @@ class BaseBytesTest: class BytesTest(BaseBytesTest, unittest.TestCase): type2test = bytes + def test_getitem_error(self): + msg = "byte indices must be integers or slices" + with self.assertRaisesRegex(TypeError, msg): + b'python'['a'] + def test_buffer_is_readonly(self): fd = os.open(__file__, os.O_RDONLY) with open(fd, "rb", buffering=0) as f: @@ -776,6 +803,17 @@ class BytesTest(BaseBytesTest, unittest.TestCase): class ByteArrayTest(BaseBytesTest, unittest.TestCase): type2test = bytearray + def test_getitem_error(self): + msg = "bytearray indices must be integers or slices" + with self.assertRaisesRegex(TypeError, msg): + bytearray(b'python')['a'] + + def test_setitem_error(self): + msg = "bytearray indices must be integers or slices" + with self.assertRaisesRegex(TypeError, msg): + b = bytearray(b'python') + b['a'] = "python" + def test_nohash(self): self.assertRaises(TypeError, hash, bytearray()) @@ -974,6 +1012,28 @@ class ByteArrayTest(BaseBytesTest, unittest.TestCase): b[8:] = b self.assertEqual(b, bytearray(list(range(8)) + list(range(256)))) + def test_mod(self): + b = bytearray(b'hello, %b!') + orig = b + b = b % b'world' + self.assertEqual(b, b'hello, world!') + self.assertEqual(orig, bytearray(b'hello, %b!')) + self.assertFalse(b is orig) + b = bytearray(b'%s / 100 = %d%%') + a = b % (b'seventy-nine', 79) + self.assertEqual(a, bytearray(b'seventy-nine / 100 = 79%')) + + def test_imod(self): + b = bytearray(b'hello, %b!') + orig = b + b %= b'world' + self.assertEqual(b, b'hello, world!') + self.assertEqual(orig, bytearray(b'hello, %b!')) + self.assertFalse(b is orig) + b = bytearray(b'%s / 100 = %d%%') + b %= (b'seventy-nine', 79) + self.assertEqual(b, bytearray(b'seventy-nine / 100 = 79%')) + def test_iconcat(self): b = bytearray(b"abc") b1 = b @@ -1164,6 +1224,10 @@ class ByteArrayTest(BaseBytesTest, unittest.TestCase): self.assertRaises(BufferError, delslice) self.assertEqual(b, orig) + @test.support.cpython_only + def test_obsolete_write_lock(self): + from _testcapi import getbuffer_with_null_view + self.assertRaises(BufferError, getbuffer_with_null_view, bytearray()) class AssortedBytesTest(unittest.TestCase): # diff --git a/Lib/test/test_bz2.py b/Lib/test/test_bz2.py index 1535e8e..2fe3f2a 100644 --- a/Lib/test/test_bz2.py +++ b/Lib/test/test_bz2.py @@ -5,6 +5,7 @@ import unittest from io import BytesIO import os import pickle +import glob import random import subprocess import sys @@ -51,6 +52,19 @@ class BaseTest(unittest.TestCase): EMPTY_DATA = b'BZh9\x17rE8P\x90\x00\x00\x00\x00' BAD_DATA = b'this is not a valid bzip2 file' + # Some tests need more than one block of uncompressed data. Since one block + # is at least 100 kB, we gather some data dynamically and compress it. + # Note that this assumes that compression works correctly, so we cannot + # simply use the bigger test data for all tests. + test_size = 0 + BIG_TEXT = bytearray(128*1024) + for fname in glob.glob(os.path.join(os.path.dirname(__file__), '*.py')): + with open(fname, 'rb') as fh: + test_size += fh.readinto(memoryview(BIG_TEXT)[test_size:]) + if test_size > 128*1024: + break + BIG_DATA = bz2.compress(BIG_TEXT, compresslevel=1) + def setUp(self): self.filename = support.TESTFN @@ -707,6 +721,95 @@ class BZ2DecompressorTest(BaseTest): with self.assertRaises(TypeError): pickle.dumps(BZ2Decompressor(), proto) + def testDecompressorChunksMaxsize(self): + bzd = BZ2Decompressor() + max_length = 100 + out = [] + + # Feed some input + len_ = len(self.BIG_DATA) - 64 + out.append(bzd.decompress(self.BIG_DATA[:len_], + max_length=max_length)) + self.assertFalse(bzd.needs_input) + self.assertEqual(len(out[-1]), max_length) + + # Retrieve more data without providing more input + out.append(bzd.decompress(b'', max_length=max_length)) + self.assertFalse(bzd.needs_input) + self.assertEqual(len(out[-1]), max_length) + + # Retrieve more data while providing more input + out.append(bzd.decompress(self.BIG_DATA[len_:], + max_length=max_length)) + self.assertLessEqual(len(out[-1]), max_length) + + # Retrieve remaining uncompressed data + while not bzd.eof: + out.append(bzd.decompress(b'', max_length=max_length)) + self.assertLessEqual(len(out[-1]), max_length) + + out = b"".join(out) + self.assertEqual(out, self.BIG_TEXT) + self.assertEqual(bzd.unused_data, b"") + + def test_decompressor_inputbuf_1(self): + # Test reusing input buffer after moving existing + # contents to beginning + bzd = BZ2Decompressor() + out = [] + + # Create input buffer and fill it + self.assertEqual(bzd.decompress(self.DATA[:100], + max_length=0), b'') + + # Retrieve some results, freeing capacity at beginning + # of input buffer + out.append(bzd.decompress(b'', 2)) + + # Add more data that fits into input buffer after + # moving existing data to beginning + out.append(bzd.decompress(self.DATA[100:105], 15)) + + # Decompress rest of data + out.append(bzd.decompress(self.DATA[105:])) + self.assertEqual(b''.join(out), self.TEXT) + + def test_decompressor_inputbuf_2(self): + # Test reusing input buffer by appending data at the + # end right away + bzd = BZ2Decompressor() + out = [] + + # Create input buffer and empty it + self.assertEqual(bzd.decompress(self.DATA[:200], + max_length=0), b'') + out.append(bzd.decompress(b'')) + + # Fill buffer with new data + out.append(bzd.decompress(self.DATA[200:280], 2)) + + # Append some more data, not enough to require resize + out.append(bzd.decompress(self.DATA[280:300], 2)) + + # Decompress rest of data + out.append(bzd.decompress(self.DATA[300:])) + self.assertEqual(b''.join(out), self.TEXT) + + def test_decompressor_inputbuf_3(self): + # Test reusing input buffer after extending it + + bzd = BZ2Decompressor() + out = [] + + # Create almost full input buffer + out.append(bzd.decompress(self.DATA[:200], 5)) + + # Add even more data to it, requiring resize + out.append(bzd.decompress(self.DATA[200:300], 5)) + + # Decompress rest of data + out.append(bzd.decompress(self.DATA[300:])) + self.assertEqual(b''.join(out), self.TEXT) class CompressDecompressTest(BaseTest): def testCompress(self): diff --git a/Lib/test/test_capi.py b/Lib/test/test_capi.py index ba7c38d..de8d65a 100644 --- a/Lib/test/test_capi.py +++ b/Lib/test/test_capi.py @@ -150,6 +150,23 @@ class CAPITest(unittest.TestCase): self.assertEqual(_testcapi.docstring_with_signature_and_extra_newlines.__text_signature__, "($module, /, parameter)") + def test_c_type_with_matrix_multiplication(self): + M = _testcapi.matmulType + m1 = M() + m2 = M() + self.assertEqual(m1 @ m2, ("matmul", m1, m2)) + self.assertEqual(m1 @ 42, ("matmul", m1, 42)) + self.assertEqual(42 @ m1, ("matmul", 42, m1)) + o = m1 + o @= m2 + self.assertEqual(o, ("imatmul", m1, m2)) + o = m1 + o @= 42 + self.assertEqual(o, ("imatmul", m1, 42)) + o = 42 + o @= m1 + self.assertEqual(o, ("matmul", 42, m1)) + @unittest.skipUnless(threading, 'Threading required for this test.') class TestPendingCalls(unittest.TestCase): @@ -268,7 +285,7 @@ class EmbeddingTests(unittest.TestCase): exename += ext exepath = os.path.dirname(sys.executable) else: - exepath = os.path.join(basepath, "Modules") + exepath = os.path.join(basepath, "Programs") self.test_exe = exe = os.path.join(exepath, exename) if not os.path.exists(exe): self.skipTest("%r doesn't exist" % exe) @@ -287,12 +304,13 @@ class EmbeddingTests(unittest.TestCase): cmd.extend(args) p = subprocess.Popen(cmd, stdout=subprocess.PIPE, - stderr=subprocess.PIPE) + stderr=subprocess.PIPE, + universal_newlines=True) (out, err) = p.communicate() self.assertEqual(p.returncode, 0, "bad returncode %d, stderr is %r" % (p.returncode, err)) - return out.decode("latin1"), err.decode("latin1") + return out, err def test_subinterps(self): # This is just a "don't crash" test @@ -319,34 +337,38 @@ class EmbeddingTests(unittest.TestCase): print() print(out) print(err) + expected_errors = sys.__stdout__.errors expected_stdin_encoding = sys.__stdin__.encoding expected_pipe_encoding = self._get_default_pipe_encoding() - expected_output = os.linesep.join([ + expected_output = '\n'.join([ "--- Use defaults ---", "Expected encoding: default", "Expected errors: default", - "stdin: {0}:strict", - "stdout: {1}:strict", - "stderr: {1}:backslashreplace", + "stdin: {in_encoding}:{errors}", + "stdout: {out_encoding}:{errors}", + "stderr: {out_encoding}:backslashreplace", "--- Set errors only ---", "Expected encoding: default", - "Expected errors: surrogateescape", - "stdin: {0}:surrogateescape", - "stdout: {1}:surrogateescape", - "stderr: {1}:backslashreplace", + "Expected errors: ignore", + "stdin: {in_encoding}:ignore", + "stdout: {out_encoding}:ignore", + "stderr: {out_encoding}:backslashreplace", "--- Set encoding only ---", "Expected encoding: latin-1", "Expected errors: default", - "stdin: latin-1:strict", - "stdout: latin-1:strict", + "stdin: latin-1:{errors}", + "stdout: latin-1:{errors}", "stderr: latin-1:backslashreplace", "--- Set encoding and errors ---", "Expected encoding: latin-1", - "Expected errors: surrogateescape", - "stdin: latin-1:surrogateescape", - "stdout: latin-1:surrogateescape", - "stderr: latin-1:backslashreplace"]).format(expected_stdin_encoding, - expected_pipe_encoding) + "Expected errors: replace", + "stdin: latin-1:replace", + "stdout: latin-1:replace", + "stderr: latin-1:backslashreplace"]) + expected_output = expected_output.format( + in_encoding=expected_stdin_encoding, + out_encoding=expected_pipe_encoding, + errors=expected_errors) # This is useful if we ever trip over odd platform behaviour self.maxDiff = None self.assertEqual(out.strip(), expected_output) diff --git a/Lib/test/test_cgi.py b/Lib/test/test_cgi.py index 1127dd1..715bd73 100644 --- a/Lib/test/test_cgi.py +++ b/Lib/test/test_cgi.py @@ -1,4 +1,4 @@ -from test.support import run_unittest, check_warnings +from test.support import check_warnings import cgi import os import sys @@ -307,6 +307,17 @@ Content-Type: text/plain got = getattr(files[x], k) self.assertEqual(got, exp) + def test_fieldstorage_as_context_manager(self): + fp = BytesIO(b'x' * 10) + env = {'REQUEST_METHOD': 'PUT'} + with cgi.FieldStorage(fp=fp, environ=env) as fs: + content = fs.file.read() + self.assertFalse(fs.file.closed) + self.assertTrue(fs.file.closed) + self.assertEqual(content, 'x' * 10) + with self.assertRaisesRegex(ValueError, 'I/O operation on closed file'): + fs.file.read() + _qs_result = { 'key1': 'value1', 'key2': ['value2x', 'value2y'], @@ -481,9 +492,5 @@ Content-Transfer-Encoding: binary --AaB03x-- """ - -def test_main(): - run_unittest(CgiTests) - if __name__ == '__main__': - test_main() + unittest.main() diff --git a/Lib/test/test_cmd_line.py b/Lib/test/test_cmd_line.py index 3683a48..ebe557e 100644 --- a/Lib/test/test_cmd_line.py +++ b/Lib/test/test_cmd_line.py @@ -440,7 +440,7 @@ class CmdLineTest(unittest.TestCase): self.assertEqual(err.splitlines().count(b'Unknown option: -a'), 1) self.assertEqual(b'', out) - @unittest.skipIf(script_helper._interpreter_requires_environment(), + @unittest.skipIf(script_helper.interpreter_requires_environment(), 'Cannot run -I tests when PYTHON env vars are required.') def test_isolatedmode(self): self.verify_valid_flag('-I') diff --git a/Lib/test/test_code_module.py b/Lib/test/test_code_module.py index 7a80a80..9b17767 100644 --- a/Lib/test/test_code_module.py +++ b/Lib/test/test_code_module.py @@ -1,6 +1,7 @@ "Test InteractiveConsole and InteractiveInterpreter from code module" import sys import unittest +from textwrap import dedent from contextlib import ExitStack from unittest import mock from test import support @@ -78,6 +79,40 @@ class TestInteractiveConsole(unittest.TestCase): self.console.interact(banner='') self.assertEqual(len(self.stderr.method_calls), 1) + def test_cause_tb(self): + self.infunc.side_effect = ["raise ValueError('') from AttributeError", + EOFError('Finished')] + self.console.interact() + output = ''.join(''.join(call[1]) for call in self.stderr.method_calls) + expected = dedent(""" + AttributeError + + The above exception was the direct cause of the following exception: + + Traceback (most recent call last): + File "<console>", line 1, in <module> + ValueError + """) + self.assertIn(expected, output) + + def test_context_tb(self): + self.infunc.side_effect = ["try: ham\nexcept: eggs\n", + EOFError('Finished')] + self.console.interact() + output = ''.join(''.join(call[1]) for call in self.stderr.method_calls) + expected = dedent(""" + Traceback (most recent call last): + File "<console>", line 1, in <module> + NameError: name 'ham' is not defined + + During handling of the above exception, another exception occurred: + + Traceback (most recent call last): + File "<console>", line 2, in <module> + NameError: name 'eggs' is not defined + """) + self.assertIn(expected, output) + def test_main(): support.run_unittest(TestInteractiveConsole) diff --git a/Lib/test/test_codeccallbacks.py b/Lib/test/test_codeccallbacks.py index 84804bb..e29ac53 100644 --- a/Lib/test/test_codeccallbacks.py +++ b/Lib/test/test_codeccallbacks.py @@ -158,6 +158,22 @@ class CodecCallbackTest(unittest.TestCase): sout = b"a\xac\\u1234\xa4\\u8000\\U0010ffff" self.assertEqual(sin.encode("iso-8859-15", "backslashreplace"), sout) + def test_nameescape(self): + # Does the same as backslashescape, but prefers ``\N{...}`` escape + # sequences. + sin = "a\xac\u1234\u20ac\u8000\U0010ffff" + sout = (b'a\\N{NOT SIGN}\\N{ETHIOPIC SYLLABLE SEE}\\N{EURO SIGN}' + b'\\N{CJK UNIFIED IDEOGRAPH-8000}\\U0010ffff') + self.assertEqual(sin.encode("ascii", "namereplace"), sout) + + sout = (b'a\xac\\N{ETHIOPIC SYLLABLE SEE}\\N{EURO SIGN}' + b'\\N{CJK UNIFIED IDEOGRAPH-8000}\\U0010ffff') + self.assertEqual(sin.encode("latin-1", "namereplace"), sout) + + sout = (b'a\xac\\N{ETHIOPIC SYLLABLE SEE}\xa4' + b'\\N{CJK UNIFIED IDEOGRAPH-8000}\\U0010ffff') + self.assertEqual(sin.encode("iso-8859-15", "namereplace"), sout) + def test_decoding_callbacks(self): # This is a test for a decoding callback handler # that allows the decoding of the invalid sequence @@ -230,6 +246,11 @@ class CodecCallbackTest(unittest.TestCase): "\u0000\ufffd" ) + self.assertEqual( + b"\x00\x00\x00\x00\x00".decode("unicode-internal", "backslashreplace"), + "\u0000\\x00" + ) + codecs.register_error("test.hui", handler_unicodeinternal) self.assertEqual( @@ -297,7 +318,7 @@ class CodecCallbackTest(unittest.TestCase): def test_longstrings(self): # test long strings to check for memory overflow problems errors = [ "strict", "ignore", "replace", "xmlcharrefreplace", - "backslashreplace"] + "backslashreplace", "namereplace"] # register the handlers under different names, # to prevent the codec from recognizing the name for err in errors: @@ -549,17 +570,6 @@ class CodecCallbackTest(unittest.TestCase): codecs.backslashreplace_errors, UnicodeError("ouch") ) - # "backslashreplace" can only be used for encoding - self.assertRaises( - TypeError, - codecs.backslashreplace_errors, - UnicodeDecodeError("ascii", bytearray(b"\xff"), 0, 1, "ouch") - ) - self.assertRaises( - TypeError, - codecs.backslashreplace_errors, - UnicodeTranslateError("\u3042", 0, 1, "ouch") - ) # Use the correct exception self.assertEqual( codecs.backslashreplace_errors( @@ -611,6 +621,91 @@ class CodecCallbackTest(unittest.TestCase): ("\\udfff", 1) ) + def test_badandgoodnamereplaceexceptions(self): + # "namereplace" complains about a non-exception passed in + self.assertRaises( + TypeError, + codecs.namereplace_errors, + 42 + ) + # "namereplace" complains about the wrong exception types + self.assertRaises( + TypeError, + codecs.namereplace_errors, + UnicodeError("ouch") + ) + # "namereplace" can only be used for encoding + self.assertRaises( + TypeError, + codecs.namereplace_errors, + UnicodeDecodeError("ascii", bytearray(b"\xff"), 0, 1, "ouch") + ) + self.assertRaises( + TypeError, + codecs.namereplace_errors, + UnicodeTranslateError("\u3042", 0, 1, "ouch") + ) + # Use the correct exception + self.assertEqual( + codecs.namereplace_errors( + UnicodeEncodeError("ascii", "\u3042", 0, 1, "ouch")), + ("\\N{HIRAGANA LETTER A}", 1) + ) + self.assertEqual( + codecs.namereplace_errors( + UnicodeEncodeError("ascii", "\x00", 0, 1, "ouch")), + ("\\x00", 1) + ) + self.assertEqual( + codecs.namereplace_errors( + UnicodeEncodeError("ascii", "\xff", 0, 1, "ouch")), + ("\\N{LATIN SMALL LETTER Y WITH DIAERESIS}", 1) + ) + self.assertEqual( + codecs.namereplace_errors( + UnicodeEncodeError("ascii", "\u0100", 0, 1, "ouch")), + ("\\N{LATIN CAPITAL LETTER A WITH MACRON}", 1) + ) + self.assertEqual( + codecs.namereplace_errors( + UnicodeEncodeError("ascii", "\uffff", 0, 1, "ouch")), + ("\\uffff", 1) + ) + if SIZEOF_WCHAR_T > 0: + self.assertEqual( + codecs.namereplace_errors( + UnicodeEncodeError("ascii", "\U00010000", + 0, 1, "ouch")), + ("\\N{LINEAR B SYLLABLE B008 A}", 1) + ) + self.assertEqual( + codecs.namereplace_errors( + UnicodeEncodeError("ascii", "\U0010ffff", + 0, 1, "ouch")), + ("\\U0010ffff", 1) + ) + # Lone surrogates (regardless of unicode width) + self.assertEqual( + codecs.namereplace_errors( + UnicodeEncodeError("ascii", "\ud800", 0, 1, "ouch")), + ("\\ud800", 1) + ) + self.assertEqual( + codecs.namereplace_errors( + UnicodeEncodeError("ascii", "\udfff", 0, 1, "ouch")), + ("\\udfff", 1) + ) + self.assertEqual( + codecs.backslashreplace_errors( + UnicodeDecodeError("ascii", bytearray(b"\xff"), 0, 1, "ouch")), + ("\\xff", 1) + ) + self.assertEqual( + codecs.backslashreplace_errors( + UnicodeTranslateError("\u3042", 0, 1, "ouch")), + ("\\u3042", 1) + ) + def test_badhandlerresults(self): results = ( 42, "foo", (1,2,3), ("foo", 1, 3), ("foo", None), ("foo",), ("foo", 1, 3), ("foo", None), ("foo",) ) encs = ("ascii", "latin-1", "iso-8859-1", "iso-8859-15") @@ -651,6 +746,10 @@ class CodecCallbackTest(unittest.TestCase): codecs.backslashreplace_errors, codecs.lookup_error("backslashreplace") ) + self.assertEqual( + codecs.namereplace_errors, + codecs.lookup_error("namereplace") + ) def test_unencodablereplacement(self): def unencrepl(exc): @@ -804,7 +903,8 @@ class CodecCallbackTest(unittest.TestCase): class D(dict): def __getitem__(self, key): raise ValueError - for err in ("strict", "replace", "xmlcharrefreplace", "backslashreplace", "test.posreturn"): + for err in ("strict", "replace", "xmlcharrefreplace", + "backslashreplace", "namereplace", "test.posreturn"): self.assertRaises(UnicodeError, codecs.charmap_encode, "\xff", err, {0xff: None}) self.assertRaises(ValueError, codecs.charmap_encode, "\xff", err, D()) self.assertRaises(TypeError, codecs.charmap_encode, "\xff", err, {0xff: 300}) @@ -819,7 +919,7 @@ class CodecCallbackTest(unittest.TestCase): def __getitem__(self, key): raise ValueError #self.assertRaises(ValueError, "\xff".translate, D()) - self.assertRaises(TypeError, "\xff".translate, {0xff: sys.maxunicode+1}) + self.assertRaises(ValueError, "\xff".translate, {0xff: sys.maxunicode+1}) self.assertRaises(TypeError, "\xff".translate, {0xff: ()}) def test_bug828737(self): diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py index 6629ccd..4d5d7bb 100644 --- a/Lib/test/test_codecs.py +++ b/Lib/test/test_codecs.py @@ -349,6 +349,8 @@ class ReadTest(MixInCheckStateHandling): self.assertRaises(UnicodeEncodeError, "\ud800".encode, self.encoding) self.assertEqual("[\uDC80]".encode(self.encoding, "backslashreplace"), "[\\udc80]".encode(self.encoding)) + self.assertEqual("[\uDC80]".encode(self.encoding, "namereplace"), + "[\\udc80]".encode(self.encoding)) self.assertEqual("[\uDC80]".encode(self.encoding, "xmlcharrefreplace"), "[�]".encode(self.encoding)) self.assertEqual("[\uDC80]".encode(self.encoding, "ignore"), @@ -376,6 +378,10 @@ class ReadTest(MixInCheckStateHandling): before + after) self.assertEqual(test_sequence.decode(self.encoding, "replace"), before + self.ill_formed_sequence_replace + after) + backslashreplace = ''.join('\\x%02x' % b + for b in self.ill_formed_sequence) + self.assertEqual(test_sequence.decode(self.encoding, "backslashreplace"), + before + backslashreplace + after) class UTF32Test(ReadTest, unittest.TestCase): encoding = "utf-32" @@ -808,6 +814,7 @@ class CP65001Test(ReadTest, unittest.TestCase): ('\udc80', 'ignore', b''), ('\udc80', 'replace', b'?'), ('\udc80', 'backslashreplace', b'\\udc80'), + ('\udc80', 'namereplace', b'\\udc80'), ('\udc80', 'surrogatepass', b'\xed\xb2\x80'), )) else: @@ -869,6 +876,8 @@ class CP65001Test(ReadTest, unittest.TestCase): self.assertRaises(UnicodeDecodeError, b"\xed\xa0\x80".decode, "cp65001") self.assertEqual("[\uDC80]".encode("cp65001", "backslashreplace"), b'[\\udc80]') + self.assertEqual("[\uDC80]".encode("cp65001", "namereplace"), + b'[\\udc80]') self.assertEqual("[\uDC80]".encode("cp65001", "xmlcharrefreplace"), b'[�]') self.assertEqual("[\uDC80]".encode("cp65001", "surrogateescape"), @@ -890,10 +899,6 @@ class CP65001Test(ReadTest, unittest.TestCase): "\U00010fff\uD800") self.assertTrue(codecs.lookup_error("surrogatepass")) - def test_readline(self): - self.skipTest("issue #20571: code page 65001 codec does not " - "support partial decoder yet") - class UTF7Test(ReadTest, unittest.TestCase): encoding = "utf-7" @@ -1299,14 +1304,19 @@ class UnicodeInternalTest(unittest.TestCase): "unicode_internal") if sys.byteorder == "little": invalid = b"\x00\x00\x11\x00" + invalid_backslashreplace = r"\x00\x00\x11\x00" else: invalid = b"\x00\x11\x00\x00" + invalid_backslashreplace = r"\x00\x11\x00\x00" with support.check_warnings(): self.assertRaises(UnicodeDecodeError, invalid.decode, "unicode_internal") with support.check_warnings(): self.assertEqual(invalid.decode("unicode_internal", "replace"), '\ufffd') + with support.check_warnings(): + self.assertEqual(invalid.decode("unicode_internal", "backslashreplace"), + invalid_backslashreplace) @unittest.skipUnless(SIZEOF_WCHAR_T == 4, 'specific to 32-bit wchar_t') def test_decode_error_attributes(self): @@ -1612,6 +1622,12 @@ class CodecsModuleTest(unittest.TestCase): self.assertEqual(codecs.decode(b'abc'), 'abc') self.assertRaises(UnicodeDecodeError, codecs.decode, b'\xff', 'ascii') + # test keywords + self.assertEqual(codecs.decode(obj=b'\xe4\xf6\xfc', encoding='latin-1'), + '\xe4\xf6\xfc') + self.assertEqual(codecs.decode(b'[\xff]', 'ascii', errors='ignore'), + '[]') + def test_encode(self): self.assertEqual(codecs.encode('\xe4\xf6\xfc', 'latin-1'), b'\xe4\xf6\xfc') @@ -1620,6 +1636,12 @@ class CodecsModuleTest(unittest.TestCase): self.assertEqual(codecs.encode('abc'), b'abc') self.assertRaises(UnicodeEncodeError, codecs.encode, '\xffff', 'ascii') + # test keywords + self.assertEqual(codecs.encode(obj='\xe4\xf6\xfc', encoding='latin-1'), + b'\xe4\xf6\xfc') + self.assertEqual(codecs.encode('[\xff]', 'ascii', errors='ignore'), + b'[]') + def test_register(self): self.assertRaises(TypeError, codecs.register) self.assertRaises(TypeError, codecs.register, 42) @@ -1668,6 +1690,7 @@ class CodecsModuleTest(unittest.TestCase): "register_error", "lookup_error", "strict_errors", "replace_errors", "ignore_errors", "xmlcharrefreplace_errors", "backslashreplace_errors", + "namereplace_errors", "open", "EncodedFile", "iterencode", "iterdecode", "BOM", "BOM_BE", "BOM_LE", @@ -2029,6 +2052,16 @@ class CharmapTest(unittest.TestCase): ) self.assertEqual( + codecs.charmap_decode(b"\x00\x01\x02", "backslashreplace", "ab"), + ("ab\\x02", 3) + ) + + self.assertEqual( + codecs.charmap_decode(b"\x00\x01\x02", "backslashreplace", "ab\ufffe"), + ("ab\\x02", 3) + ) + + self.assertEqual( codecs.charmap_decode(b"\x00\x01\x02", "ignore", "ab"), ("ab", 3) ) @@ -2105,6 +2138,25 @@ class CharmapTest(unittest.TestCase): ) self.assertEqual( + codecs.charmap_decode(b"\x00\x01\x02", "backslashreplace", + {0: 'a', 1: 'b'}), + ("ab\\x02", 3) + ) + + self.assertEqual( + codecs.charmap_decode(b"\x00\x01\x02", "backslashreplace", + {0: 'a', 1: 'b', 2: None}), + ("ab\\x02", 3) + ) + + # Issue #14850 + self.assertEqual( + codecs.charmap_decode(b"\x00\x01\x02", "backslashreplace", + {0: 'a', 1: 'b', 2: '\ufffe'}), + ("ab\\x02", 3) + ) + + self.assertEqual( codecs.charmap_decode(b"\x00\x01\x02", "ignore", {0: 'a', 1: 'b'}), ("ab", 3) @@ -2181,6 +2233,18 @@ class CharmapTest(unittest.TestCase): ) self.assertEqual( + codecs.charmap_decode(b"\x00\x01\x02", "backslashreplace", + {0: a, 1: b}), + ("ab\\x02", 3) + ) + + self.assertEqual( + codecs.charmap_decode(b"\x00\x01\x02", "backslashreplace", + {0: a, 1: b, 2: 0xFFFE}), + ("ab\\x02", 3) + ) + + self.assertEqual( codecs.charmap_decode(b"\x00\x01\x02", "ignore", {0: a, 1: b}), ("ab", 3) @@ -2239,9 +2303,13 @@ class TypesTest(unittest.TestCase): self.assertRaises(UnicodeDecodeError, codecs.unicode_escape_decode, br"\U00110000") self.assertEqual(codecs.unicode_escape_decode(r"\U00110000", "replace"), ("\ufffd", 10)) + self.assertEqual(codecs.unicode_escape_decode(r"\U00110000", "backslashreplace"), + (r"\x5c\x55\x30\x30\x31\x31\x30\x30\x30\x30", 10)) self.assertRaises(UnicodeDecodeError, codecs.raw_unicode_escape_decode, br"\U00110000") self.assertEqual(codecs.raw_unicode_escape_decode(r"\U00110000", "replace"), ("\ufffd", 10)) + self.assertEqual(codecs.raw_unicode_escape_decode(r"\U00110000", "backslashreplace"), + (r"\x5c\x55\x30\x30\x31\x31\x30\x30\x30\x30", 10)) class UnicodeEscapeTest(unittest.TestCase): @@ -2818,15 +2886,15 @@ class CodePageTest(unittest.TestCase): self.assertRaisesRegex(UnicodeEncodeError, 'cp932', codecs.code_page_encode, 932, '\xff') self.assertRaisesRegex(UnicodeDecodeError, 'cp932', - codecs.code_page_decode, 932, b'\x81\x00') + codecs.code_page_decode, 932, b'\x81\x00', 'strict', True) self.assertRaisesRegex(UnicodeDecodeError, 'CP_UTF8', - codecs.code_page_decode, self.CP_UTF8, b'\xff') + codecs.code_page_decode, self.CP_UTF8, b'\xff', 'strict', True) def check_decode(self, cp, tests): for raw, errors, expected in tests: if expected is not None: try: - decoded = codecs.code_page_decode(cp, raw, errors) + decoded = codecs.code_page_decode(cp, raw, errors, True) except UnicodeDecodeError as err: self.fail('Unable to decode %a from "cp%s" with ' 'errors=%r: %s' % (raw, cp, errors, err)) @@ -2838,7 +2906,7 @@ class CodePageTest(unittest.TestCase): self.assertLessEqual(decoded[1], len(raw)) else: self.assertRaises(UnicodeDecodeError, - codecs.code_page_decode, cp, raw, errors) + codecs.code_page_decode, cp, raw, errors, True) def check_encode(self, cp, tests): for text, errors, expected in tests: @@ -2866,7 +2934,12 @@ class CodePageTest(unittest.TestCase): ('[\xff]', 'replace', b'[y]'), ('[\u20ac]', 'replace', b'[?]'), ('[\xff]', 'backslashreplace', b'[\\xff]'), + ('[\xff]', 'namereplace', + b'[\\N{LATIN SMALL LETTER Y WITH DIAERESIS}]'), ('[\xff]', 'xmlcharrefreplace', b'[ÿ]'), + ('\udcff', 'strict', None), + ('[\udcff]', 'surrogateescape', b'[\xff]'), + ('[\udcff]', 'surrogatepass', None), )) self.check_decode(932, ( (b'abc', 'strict', 'abc'), @@ -2875,10 +2948,13 @@ class CodePageTest(unittest.TestCase): (b'[\xff]', 'strict', None), (b'[\xff]', 'ignore', '[]'), (b'[\xff]', 'replace', '[\ufffd]'), + (b'[\xff]', 'backslashreplace', '[\\xff]'), (b'[\xff]', 'surrogateescape', '[\udcff]'), + (b'[\xff]', 'surrogatepass', None), (b'\x81\x00abc', 'strict', None), (b'\x81\x00abc', 'ignore', '\x00abc'), (b'\x81\x00abc', 'replace', '\ufffd\x00abc'), + (b'\x81\x00abc', 'backslashreplace', '\\x81\x00abc'), )) def test_cp1252(self): @@ -2886,9 +2962,12 @@ class CodePageTest(unittest.TestCase): ('abc', 'strict', b'abc'), ('\xe9\u20ac', 'strict', b'\xe9\x80'), ('\xff', 'strict', b'\xff'), + # test error handlers ('\u0141', 'strict', None), ('\u0141', 'ignore', b''), ('\u0141', 'replace', b'L'), + ('\udc98', 'surrogateescape', b'\x98'), + ('\udc98', 'surrogatepass', None), )) self.check_decode(1252, ( (b'abc', 'strict', 'abc'), diff --git a/Lib/test/test_collections.py b/Lib/test/test_collections.py index df1c63c..a94b5da 100644 --- a/Lib/test/test_collections.py +++ b/Lib/test/test_collections.py @@ -518,7 +518,7 @@ class TestOneTrickPonyABCs(ABCTestCase): class NextOnly: def __next__(self): yield 1 - raise StopIteration + return self.assertNotIsInstance(NextOnly(), Iterator) def test_Sized(self): @@ -647,6 +647,59 @@ class TestCollectionABCs(ABCTestCase): a, b = OneTwoThreeSet(), OneTwoThreeSet() self.assertTrue(hash(a) == hash(b)) + def test_isdisjoint_Set(self): + class MySet(Set): + def __init__(self, itr): + self.contents = itr + def __contains__(self, x): + return x in self.contents + def __iter__(self): + return iter(self.contents) + def __len__(self): + return len([x for x in self.contents]) + s1 = MySet((1, 2, 3)) + s2 = MySet((4, 5, 6)) + s3 = MySet((1, 5, 6)) + self.assertTrue(s1.isdisjoint(s2)) + self.assertFalse(s1.isdisjoint(s3)) + + def test_equality_Set(self): + class MySet(Set): + def __init__(self, itr): + self.contents = itr + def __contains__(self, x): + return x in self.contents + def __iter__(self): + return iter(self.contents) + def __len__(self): + return len([x for x in self.contents]) + s1 = MySet((1,)) + s2 = MySet((1, 2)) + s3 = MySet((3, 4)) + s4 = MySet((3, 4)) + self.assertTrue(s2 > s1) + self.assertTrue(s1 < s2) + self.assertFalse(s2 <= s1) + self.assertFalse(s2 <= s3) + self.assertFalse(s1 >= s2) + self.assertEqual(s3, s4) + self.assertNotEqual(s2, s3) + + def test_arithmetic_Set(self): + class MySet(Set): + def __init__(self, itr): + self.contents = itr + def __contains__(self, x): + return x in self.contents + def __iter__(self): + return iter(self.contents) + def __len__(self): + return len([x for x in self.contents]) + s1 = MySet((1, 2, 3)) + s2 = MySet((3, 4, 5)) + s3 = s1 & s2 + self.assertEqual(s3, MySet((3,))) + def test_MutableSet(self): self.assertIsInstance(set(), MutableSet) self.assertTrue(issubclass(set, MutableSet)) @@ -1378,6 +1431,21 @@ class TestOrderedDict(unittest.TestCase): self.assertEqual(list(od.items()), pairs) self.assertEqual(list(reversed(od)), [t[0] for t in reversed(pairs)]) + self.assertEqual(list(reversed(od.keys())), + [t[0] for t in reversed(pairs)]) + self.assertEqual(list(reversed(od.values())), + [t[1] for t in reversed(pairs)]) + self.assertEqual(list(reversed(od.items())), list(reversed(pairs))) + + def test_detect_deletion_during_iteration(self): + od = OrderedDict.fromkeys('abc') + it = iter(od) + key = next(it) + del od[key] + with self.assertRaises(Exception): + # Note, the exact exception raised is not guaranteed + # The only guarantee that the next() will not succeed + next(it) def test_popitem(self): pairs = [('c', 1), ('b', 2), ('a', 3), ('d', 4), ('e', 5), ('f', 6)] diff --git a/Lib/test/test_compileall.py b/Lib/test/test_compileall.py index 2a42238..7506c70 100644 --- a/Lib/test/test_compileall.py +++ b/Lib/test/test_compileall.py @@ -10,6 +10,13 @@ import time import unittest import io +from unittest import mock, skipUnless +try: + from concurrent.futures import ProcessPoolExecutor + _have_multiprocessing = True +except ImportError: + _have_multiprocessing = False + from test import support, script_helper class CompileallTests(unittest.TestCase): @@ -106,6 +113,33 @@ class CompileallTests(unittest.TestCase): debug_override=not optimize) self.assertTrue(os.path.isfile(cached3)) + @mock.patch('compileall.ProcessPoolExecutor') + def test_compile_pool_called(self, pool_mock): + compileall.compile_dir(self.directory, quiet=True, workers=5) + self.assertTrue(pool_mock.called) + + def test_compile_workers_non_positive(self): + with self.assertRaisesRegex(ValueError, + "workers must be greater or equal to 0"): + compileall.compile_dir(self.directory, workers=-1) + + @mock.patch('compileall.ProcessPoolExecutor') + def test_compile_workers_cpu_count(self, pool_mock): + compileall.compile_dir(self.directory, quiet=True, workers=0) + self.assertEqual(pool_mock.call_args[1]['max_workers'], None) + + @mock.patch('compileall.ProcessPoolExecutor') + @mock.patch('compileall.compile_file') + def test_compile_one_worker(self, compile_file_mock, pool_mock): + compileall.compile_dir(self.directory, quiet=True) + self.assertFalse(pool_mock.called) + self.assertTrue(compile_file_mock.called) + + @mock.patch('compileall.ProcessPoolExecutor', new=None) + def test_compile_missing_multiprocessing(self): + with self.assertRaisesRegex(NotImplementedError, + "multiprocessing support not available"): + compileall.compile_dir(self.directory, quiet=True, workers=5) class EncodingTest(unittest.TestCase): """Issue 6716: compileall should escape source code when printing errors @@ -273,12 +307,53 @@ class CommandLineTests(unittest.TestCase): self.assertCompiled(subinitfn) self.assertCompiled(hamfn) + def test_recursion_limit(self): + subpackage = os.path.join(self.pkgdir, 'spam') + subpackage2 = os.path.join(subpackage, 'ham') + subpackage3 = os.path.join(subpackage2, 'eggs') + for pkg in (subpackage, subpackage2, subpackage3): + script_helper.make_pkg(pkg) + + subinitfn = os.path.join(subpackage, '__init__.py') + hamfn = script_helper.make_script(subpackage, 'ham', '') + spamfn = script_helper.make_script(subpackage2, 'spam', '') + eggfn = script_helper.make_script(subpackage3, 'egg', '') + + self.assertRunOK('-q', '-r 0', self.pkgdir) + self.assertNotCompiled(subinitfn) + self.assertFalse( + os.path.exists(os.path.join(subpackage, '__pycache__'))) + + self.assertRunOK('-q', '-r 1', self.pkgdir) + self.assertCompiled(subinitfn) + self.assertCompiled(hamfn) + self.assertNotCompiled(spamfn) + + self.assertRunOK('-q', '-r 2', self.pkgdir) + self.assertCompiled(subinitfn) + self.assertCompiled(hamfn) + self.assertCompiled(spamfn) + self.assertNotCompiled(eggfn) + + self.assertRunOK('-q', '-r 5', self.pkgdir) + self.assertCompiled(subinitfn) + self.assertCompiled(hamfn) + self.assertCompiled(spamfn) + self.assertCompiled(eggfn) + def test_quiet(self): noisy = self.assertRunOK(self.pkgdir) quiet = self.assertRunOK('-q', self.pkgdir) self.assertNotEqual(b'', noisy) self.assertEqual(b'', quiet) + def test_silent(self): + script_helper.make_script(self.pkgdir, 'crunchyfrog', 'bad(syntax') + _, quiet, _ = self.assertRunNotOK('-q', self.pkgdir) + _, silent, _ = self.assertRunNotOK('-qq', self.pkgdir) + self.assertNotEqual(b'', quiet) + self.assertEqual(b'', silent) + def test_regexp(self): self.assertRunOK('-q', '-x', r'ba[^\\/]*$', self.pkgdir) self.assertNotCompiled(self.barfn) @@ -379,6 +454,29 @@ class CommandLineTests(unittest.TestCase): out = self.assertRunOK('badfilename') self.assertRegex(out, b"Can't list 'badfilename'") + @skipUnless(_have_multiprocessing, "requires multiprocessing") + def test_workers(self): + bar2fn = script_helper.make_script(self.directory, 'bar2', '') + files = [] + for suffix in range(5): + pkgdir = os.path.join(self.directory, 'foo{}'.format(suffix)) + os.mkdir(pkgdir) + fn = script_helper.make_script(pkgdir, '__init__', '') + files.append(script_helper.make_script(pkgdir, 'bar2', '')) + + self.assertRunOK(self.directory, '-j', '0') + self.assertCompiled(bar2fn) + for file in files: + self.assertCompiled(file) + + @mock.patch('compileall.compile_dir') + def test_workers_available_cores(self, compile_dir): + with mock.patch("sys.argv", + new=[sys.executable, self.directory, "-j0"]): + compileall.main() + self.assertTrue(compile_dir.called) + self.assertEqual(compile_dir.call_args[-1]['workers'], None) + if __name__ == "__main__": unittest.main() diff --git a/Lib/test/test_concurrent_futures.py b/Lib/test/test_concurrent_futures.py index c74b2ca..86802c2 100644 --- a/Lib/test/test_concurrent_futures.py +++ b/Lib/test/test_concurrent_futures.py @@ -11,6 +11,7 @@ test.support.import_module('threading') from test.script_helper import assert_python_ok +import os import sys import threading import time @@ -425,6 +426,13 @@ class ExecutorTest: self.assertTrue(collected, "Stale reference not collected within timeout.") + def test_max_workers_negative(self): + for number in (0, -1): + with self.assertRaisesRegex(ValueError, + "max_workers must be greater " + "than 0"): + self.executor_type(max_workers=number) + class ThreadPoolExecutorTest(ThreadPoolMixin, ExecutorTest, unittest.TestCase): def test_map_submits_without_iteration(self): @@ -437,6 +445,11 @@ class ThreadPoolExecutorTest(ThreadPoolMixin, ExecutorTest, unittest.TestCase): self.executor.shutdown(wait=True) self.assertCountEqual(finished, range(10)) + def test_default_workers(self): + executor = self.executor_type() + self.assertEqual(executor._max_workers, + (os.cpu_count() or 1) * 5) + class ProcessPoolExecutorTest(ProcessPoolMixin, ExecutorTest, unittest.TestCase): def test_killed_child(self): @@ -451,6 +464,48 @@ class ProcessPoolExecutorTest(ProcessPoolMixin, ExecutorTest, unittest.TestCase) # Submitting other jobs fails as well. self.assertRaises(BrokenProcessPool, self.executor.submit, pow, 2, 8) + def test_map_chunksize(self): + def bad_map(): + list(self.executor.map(pow, range(40), range(40), chunksize=-1)) + + ref = list(map(pow, range(40), range(40))) + self.assertEqual( + list(self.executor.map(pow, range(40), range(40), chunksize=6)), + ref) + self.assertEqual( + list(self.executor.map(pow, range(40), range(40), chunksize=50)), + ref) + self.assertEqual( + list(self.executor.map(pow, range(40), range(40), chunksize=40)), + ref) + self.assertRaises(ValueError, bad_map) + + @classmethod + def _test_traceback(cls): + raise RuntimeError(123) # some comment + + def test_traceback(self): + # We want ensure that the traceback from the child process is + # contained in the traceback raised in the main process. + future = self.executor.submit(self._test_traceback) + with self.assertRaises(Exception) as cm: + future.result() + + exc = cm.exception + self.assertIs(type(exc), RuntimeError) + self.assertEqual(exc.args, (123,)) + cause = exc.__cause__ + self.assertIs(type(cause), futures.process._RemoteTraceback) + self.assertIn('raise RuntimeError(123) # some comment', cause.tb) + + with test.support.captured_stderr() as f1: + try: + raise exc + except RuntimeError: + sys.excepthook(*sys.exc_info()) + self.assertIn('raise RuntimeError(123) # some comment', + f1.getvalue()) + class FutureTests(unittest.TestCase): def test_done_callback_with_result(self): diff --git a/Lib/test/test_configparser.py b/Lib/test/test_configparser.py index 09c229a..470d2cd 100644 --- a/Lib/test/test_configparser.py +++ b/Lib/test/test_configparser.py @@ -579,7 +579,7 @@ boolean {0[0]} NO return e else: self.fail("expected exception type %s.%s" - % (exc.__module__, exc.__name__)) + % (exc.__module__, exc.__qualname__)) def test_boolean(self): cf = self.fromstring( @@ -1584,6 +1584,34 @@ class CoverageOneHundredTestCase(unittest.TestCase): """) self.assertEqual(repr(parser['section']), '<Section: section>') + def test_inconsistent_converters_state(self): + parser = configparser.ConfigParser() + import decimal + parser.converters['decimal'] = decimal.Decimal + parser.read_string(""" + [s1] + one = 1 + [s2] + two = 2 + """) + self.assertIn('decimal', parser.converters) + self.assertEqual(parser.getdecimal('s1', 'one'), 1) + self.assertEqual(parser.getdecimal('s2', 'two'), 2) + self.assertEqual(parser['s1'].getdecimal('one'), 1) + self.assertEqual(parser['s2'].getdecimal('two'), 2) + del parser.getdecimal + with self.assertRaises(AttributeError): + parser.getdecimal('s1', 'one') + self.assertIn('decimal', parser.converters) + del parser.converters['decimal'] + self.assertNotIn('decimal', parser.converters) + with self.assertRaises(AttributeError): + parser.getdecimal('s1', 'one') + with self.assertRaises(AttributeError): + parser['s1'].getdecimal('one') + with self.assertRaises(AttributeError): + parser['s2'].getdecimal('two') + class ExceptionPicklingTestCase(unittest.TestCase): """Tests for issue #13760: ConfigParser exceptions are not picklable.""" @@ -1776,5 +1804,252 @@ class InlineCommentStrippingTestCase(unittest.TestCase): self.assertEqual(s['k3'], 'v3;#//still v3# and still v3') +class ExceptionContextTestCase(unittest.TestCase): + """ Test that implementation details doesn't leak + through raising exceptions. """ + + def test_get_basic_interpolation(self): + parser = configparser.ConfigParser() + parser.read_string(""" + [Paths] + home_dir: /Users + my_dir: %(home_dir1)s/lumberjack + my_pictures: %(my_dir)s/Pictures + """) + cm = self.assertRaises(configparser.InterpolationMissingOptionError) + with cm: + parser.get('Paths', 'my_dir') + self.assertIs(cm.exception.__suppress_context__, True) + + def test_get_extended_interpolation(self): + parser = configparser.ConfigParser( + interpolation=configparser.ExtendedInterpolation()) + parser.read_string(""" + [Paths] + home_dir: /Users + my_dir: ${home_dir1}/lumberjack + my_pictures: ${my_dir}/Pictures + """) + cm = self.assertRaises(configparser.InterpolationMissingOptionError) + with cm: + parser.get('Paths', 'my_dir') + self.assertIs(cm.exception.__suppress_context__, True) + + def test_missing_options(self): + parser = configparser.ConfigParser() + parser.read_string(""" + [Paths] + home_dir: /Users + """) + with self.assertRaises(configparser.NoSectionError) as cm: + parser.options('test') + self.assertIs(cm.exception.__suppress_context__, True) + + def test_missing_section(self): + config = configparser.ConfigParser() + with self.assertRaises(configparser.NoSectionError) as cm: + config.set('Section1', 'an_int', '15') + self.assertIs(cm.exception.__suppress_context__, True) + + def test_remove_option(self): + config = configparser.ConfigParser() + with self.assertRaises(configparser.NoSectionError) as cm: + config.remove_option('Section1', 'an_int') + self.assertIs(cm.exception.__suppress_context__, True) + + +class ConvertersTestCase(BasicTestCase, unittest.TestCase): + """Introduced in 3.5, issue #18159.""" + + config_class = configparser.ConfigParser + + def newconfig(self, defaults=None): + instance = super().newconfig(defaults=defaults) + instance.converters['list'] = lambda v: [e.strip() for e in v.split() + if e.strip()] + return instance + + def test_converters(self): + cfg = self.newconfig() + self.assertIn('boolean', cfg.converters) + self.assertIn('list', cfg.converters) + self.assertIsNone(cfg.converters['int']) + self.assertIsNone(cfg.converters['float']) + self.assertIsNone(cfg.converters['boolean']) + self.assertIsNotNone(cfg.converters['list']) + self.assertEqual(len(cfg.converters), 4) + with self.assertRaises(ValueError): + cfg.converters[''] = lambda v: v + with self.assertRaises(ValueError): + cfg.converters[None] = lambda v: v + cfg.read_string(""" + [s] + str = string + int = 1 + float = 0.5 + list = a b c d e f g + bool = yes + """) + s = cfg['s'] + self.assertEqual(s['str'], 'string') + self.assertEqual(s['int'], '1') + self.assertEqual(s['float'], '0.5') + self.assertEqual(s['list'], 'a b c d e f g') + self.assertEqual(s['bool'], 'yes') + self.assertEqual(cfg.get('s', 'str'), 'string') + self.assertEqual(cfg.get('s', 'int'), '1') + self.assertEqual(cfg.get('s', 'float'), '0.5') + self.assertEqual(cfg.get('s', 'list'), 'a b c d e f g') + self.assertEqual(cfg.get('s', 'bool'), 'yes') + self.assertEqual(cfg.get('s', 'str'), 'string') + self.assertEqual(cfg.getint('s', 'int'), 1) + self.assertEqual(cfg.getfloat('s', 'float'), 0.5) + self.assertEqual(cfg.getlist('s', 'list'), ['a', 'b', 'c', 'd', + 'e', 'f', 'g']) + self.assertEqual(cfg.getboolean('s', 'bool'), True) + self.assertEqual(s.get('str'), 'string') + self.assertEqual(s.getint('int'), 1) + self.assertEqual(s.getfloat('float'), 0.5) + self.assertEqual(s.getlist('list'), ['a', 'b', 'c', 'd', + 'e', 'f', 'g']) + self.assertEqual(s.getboolean('bool'), True) + with self.assertRaises(AttributeError): + cfg.getdecimal('s', 'float') + with self.assertRaises(AttributeError): + s.getdecimal('float') + import decimal + cfg.converters['decimal'] = decimal.Decimal + self.assertIn('decimal', cfg.converters) + self.assertIsNotNone(cfg.converters['decimal']) + self.assertEqual(len(cfg.converters), 5) + dec0_5 = decimal.Decimal('0.5') + self.assertEqual(cfg.getdecimal('s', 'float'), dec0_5) + self.assertEqual(s.getdecimal('float'), dec0_5) + del cfg.converters['decimal'] + self.assertNotIn('decimal', cfg.converters) + self.assertEqual(len(cfg.converters), 4) + with self.assertRaises(AttributeError): + cfg.getdecimal('s', 'float') + with self.assertRaises(AttributeError): + s.getdecimal('float') + with self.assertRaises(KeyError): + del cfg.converters['decimal'] + with self.assertRaises(KeyError): + del cfg.converters[''] + with self.assertRaises(KeyError): + del cfg.converters[None] + + +class BlatantOverrideConvertersTestCase(unittest.TestCase): + """What if somebody overrode a getboolean()? We want to make sure that in + this case the automatic converters do not kick in.""" + + config = """ + [one] + one = false + two = false + three = long story short + + [two] + one = false + two = false + three = four + """ + + def test_converters_at_init(self): + cfg = configparser.ConfigParser(converters={'len': len}) + cfg.read_string(self.config) + self._test_len(cfg) + self.assertIsNotNone(cfg.converters['len']) + + def test_inheritance(self): + class StrangeConfigParser(configparser.ConfigParser): + gettysburg = 'a historic borough in south central Pennsylvania' + + def getboolean(self, section, option, *, raw=False, vars=None, + fallback=configparser._UNSET): + if section == option: + return True + return super().getboolean(section, option, raw=raw, vars=vars, + fallback=fallback) + def getlen(self, section, option, *, raw=False, vars=None, + fallback=configparser._UNSET): + return self._get_conv(section, option, len, raw=raw, vars=vars, + fallback=fallback) + + cfg = StrangeConfigParser() + cfg.read_string(self.config) + self._test_len(cfg) + self.assertIsNone(cfg.converters['len']) + self.assertTrue(cfg.getboolean('one', 'one')) + self.assertTrue(cfg.getboolean('two', 'two')) + self.assertFalse(cfg.getboolean('one', 'two')) + self.assertFalse(cfg.getboolean('two', 'one')) + cfg.converters['boolean'] = cfg._convert_to_boolean + self.assertFalse(cfg.getboolean('one', 'one')) + self.assertFalse(cfg.getboolean('two', 'two')) + self.assertFalse(cfg.getboolean('one', 'two')) + self.assertFalse(cfg.getboolean('two', 'one')) + + def _test_len(self, cfg): + self.assertEqual(len(cfg.converters), 4) + self.assertIn('boolean', cfg.converters) + self.assertIn('len', cfg.converters) + self.assertNotIn('tysburg', cfg.converters) + self.assertIsNone(cfg.converters['int']) + self.assertIsNone(cfg.converters['float']) + self.assertIsNone(cfg.converters['boolean']) + self.assertEqual(cfg.getlen('one', 'one'), 5) + self.assertEqual(cfg.getlen('one', 'two'), 5) + self.assertEqual(cfg.getlen('one', 'three'), 16) + self.assertEqual(cfg.getlen('two', 'one'), 5) + self.assertEqual(cfg.getlen('two', 'two'), 5) + self.assertEqual(cfg.getlen('two', 'three'), 4) + self.assertEqual(cfg.getlen('two', 'four', fallback=0), 0) + with self.assertRaises(configparser.NoOptionError): + cfg.getlen('two', 'four') + self.assertEqual(cfg['one'].getlen('one'), 5) + self.assertEqual(cfg['one'].getlen('two'), 5) + self.assertEqual(cfg['one'].getlen('three'), 16) + self.assertEqual(cfg['two'].getlen('one'), 5) + self.assertEqual(cfg['two'].getlen('two'), 5) + self.assertEqual(cfg['two'].getlen('three'), 4) + self.assertEqual(cfg['two'].getlen('four', 0), 0) + self.assertEqual(cfg['two'].getlen('four'), None) + + def test_instance_assignment(self): + cfg = configparser.ConfigParser() + cfg.getboolean = lambda section, option: True + cfg.getlen = lambda section, option: len(cfg[section][option]) + cfg.read_string(self.config) + self.assertEqual(len(cfg.converters), 3) + self.assertIn('boolean', cfg.converters) + self.assertNotIn('len', cfg.converters) + self.assertIsNone(cfg.converters['int']) + self.assertIsNone(cfg.converters['float']) + self.assertIsNone(cfg.converters['boolean']) + self.assertTrue(cfg.getboolean('one', 'one')) + self.assertTrue(cfg.getboolean('two', 'two')) + self.assertTrue(cfg.getboolean('one', 'two')) + self.assertTrue(cfg.getboolean('two', 'one')) + cfg.converters['boolean'] = cfg._convert_to_boolean + self.assertFalse(cfg.getboolean('one', 'one')) + self.assertFalse(cfg.getboolean('two', 'two')) + self.assertFalse(cfg.getboolean('one', 'two')) + self.assertFalse(cfg.getboolean('two', 'one')) + self.assertEqual(cfg.getlen('one', 'one'), 5) + self.assertEqual(cfg.getlen('one', 'two'), 5) + self.assertEqual(cfg.getlen('one', 'three'), 16) + self.assertEqual(cfg.getlen('two', 'one'), 5) + self.assertEqual(cfg.getlen('two', 'two'), 5) + self.assertEqual(cfg.getlen('two', 'three'), 4) + # If a getter impl is assigned straight to the instance, it won't + # be available on the section proxies. + with self.assertRaises(AttributeError): + self.assertEqual(cfg['one'].getlen('one'), 5) + with self.assertRaises(AttributeError): + self.assertEqual(cfg['two'].getlen('one'), 5) + + if __name__ == '__main__': unittest.main() diff --git a/Lib/test/test_contextlib.py b/Lib/test/test_contextlib.py index 39cc776..c52066b 100644 --- a/Lib/test/test_contextlib.py +++ b/Lib/test/test_contextlib.py @@ -718,60 +718,76 @@ class TestExitStack(unittest.TestCase): stack.push(cm) self.assertIs(stack._exit_callbacks[-1], cm) -class TestRedirectStdout(unittest.TestCase): + +class TestRedirectStream: + + redirect_stream = None + orig_stream = None @support.requires_docstrings def test_instance_docs(self): # Issue 19330: ensure context manager instances have good docstrings - cm_docstring = redirect_stdout.__doc__ - obj = redirect_stdout(None) + cm_docstring = self.redirect_stream.__doc__ + obj = self.redirect_stream(None) self.assertEqual(obj.__doc__, cm_docstring) def test_no_redirect_in_init(self): - orig_stdout = sys.stdout - redirect_stdout(None) - self.assertIs(sys.stdout, orig_stdout) + orig_stdout = getattr(sys, self.orig_stream) + self.redirect_stream(None) + self.assertIs(getattr(sys, self.orig_stream), orig_stdout) def test_redirect_to_string_io(self): f = io.StringIO() msg = "Consider an API like help(), which prints directly to stdout" - orig_stdout = sys.stdout - with redirect_stdout(f): - print(msg) - self.assertIs(sys.stdout, orig_stdout) + orig_stdout = getattr(sys, self.orig_stream) + with self.redirect_stream(f): + print(msg, file=getattr(sys, self.orig_stream)) + self.assertIs(getattr(sys, self.orig_stream), orig_stdout) s = f.getvalue().strip() self.assertEqual(s, msg) def test_enter_result_is_target(self): f = io.StringIO() - with redirect_stdout(f) as enter_result: + with self.redirect_stream(f) as enter_result: self.assertIs(enter_result, f) def test_cm_is_reusable(self): f = io.StringIO() - write_to_f = redirect_stdout(f) - orig_stdout = sys.stdout + write_to_f = self.redirect_stream(f) + orig_stdout = getattr(sys, self.orig_stream) with write_to_f: - print("Hello", end=" ") + print("Hello", end=" ", file=getattr(sys, self.orig_stream)) with write_to_f: - print("World!") - self.assertIs(sys.stdout, orig_stdout) + print("World!", file=getattr(sys, self.orig_stream)) + self.assertIs(getattr(sys, self.orig_stream), orig_stdout) s = f.getvalue() self.assertEqual(s, "Hello World!\n") def test_cm_is_reentrant(self): f = io.StringIO() - write_to_f = redirect_stdout(f) - orig_stdout = sys.stdout + write_to_f = self.redirect_stream(f) + orig_stdout = getattr(sys, self.orig_stream) with write_to_f: - print("Hello", end=" ") + print("Hello", end=" ", file=getattr(sys, self.orig_stream)) with write_to_f: - print("World!") - self.assertIs(sys.stdout, orig_stdout) + print("World!", file=getattr(sys, self.orig_stream)) + self.assertIs(getattr(sys, self.orig_stream), orig_stdout) s = f.getvalue() self.assertEqual(s, "Hello World!\n") +class TestRedirectStdout(TestRedirectStream, unittest.TestCase): + + redirect_stream = redirect_stdout + orig_stream = "stdout" + + +class TestRedirectStderr(TestRedirectStream, unittest.TestCase): + + redirect_stream = redirect_stderr + orig_stream = "stderr" + + class TestSuppress(unittest.TestCase): @support.requires_docstrings diff --git a/Lib/test/test_cprofile.py b/Lib/test/test_cprofile.py index ce5d27e..f18983f 100644 --- a/Lib/test/test_cprofile.py +++ b/Lib/test/test_cprofile.py @@ -11,7 +11,7 @@ from test.profilee import testfunc class CProfileTest(ProfileTest): profilerclass = cProfile.Profile profilermodule = cProfile - expected_max_output = "{built-in method max}" + expected_max_output = "{built-in method builtins.max}" def get_expected_output(self): return _ProfileOutput @@ -72,9 +72,9 @@ profilee.py:84(helper2_indirect) <- 2 0.000 0.140 profilee.py:88(helper2) <- 6 0.234 0.300 profilee.py:55(helper) 2 0.078 0.100 profilee.py:84(helper2_indirect) profilee.py:98(subhelper) <- 8 0.064 0.080 profilee.py:88(helper2) -{built-in method exc_info} <- 4 0.000 0.000 profilee.py:73(helper1) -{built-in method hasattr} <- 4 0.000 0.004 profilee.py:73(helper1) +{built-in method builtins.hasattr} <- 4 0.000 0.004 profilee.py:73(helper1) 8 0.000 0.008 profilee.py:88(helper2) +{built-in method sys.exc_info} <- 4 0.000 0.000 profilee.py:73(helper1) {method 'append' of 'list' objects} <- 4 0.000 0.000 profilee.py:73(helper1)""" _ProfileOutput['print_callees'] = """\ <string>:1(<module>) -> 1 0.270 1.000 profilee.py:25(testfunc) @@ -87,12 +87,12 @@ profilee.py:48(mul) -> profilee.py:55(helper) -> 4 0.116 0.120 profilee.py:73(helper1) 2 0.000 0.140 profilee.py:84(helper2_indirect) 6 0.234 0.300 profilee.py:88(helper2) -profilee.py:73(helper1) -> 4 0.000 0.000 {built-in method exc_info} +profilee.py:73(helper1) -> 4 0.000 0.004 {built-in method builtins.hasattr} profilee.py:84(helper2_indirect) -> 2 0.006 0.040 profilee.py:35(factorial) 2 0.078 0.100 profilee.py:88(helper2) profilee.py:88(helper2) -> 8 0.064 0.080 profilee.py:98(subhelper) profilee.py:98(subhelper) -> 16 0.016 0.016 profilee.py:110(__getattr__) -{built-in method hasattr} -> 12 0.012 0.012 profilee.py:110(__getattr__)""" +{built-in method builtins.hasattr} -> 12 0.012 0.012 profilee.py:110(__getattr__)""" if __name__ == "__main__": main() diff --git a/Lib/test/test_csv.py b/Lib/test/test_csv.py index 7e2485f..3f3f328 100644 --- a/Lib/test/test_csv.py +++ b/Lib/test/test_csv.py @@ -575,6 +575,16 @@ class TestDictFields(unittest.TestCase): fileobj.readline() # header self.assertEqual(fileobj.read(), "10,,abc\r\n") + def test_write_multiple_dict_rows(self): + fileobj = StringIO() + writer = csv.DictWriter(fileobj, fieldnames=["f1", "f2", "f3"]) + writer.writeheader() + self.assertEqual(fileobj.getvalue(), "f1,f2,f3\r\n") + writer.writerows([{"f1": 1, "f2": "abc", "f3": "f"}, + {"f1": 2, "f2": 5, "f3": "xyz"}]) + self.assertEqual(fileobj.getvalue(), + "f1,f2,f3\r\n1,abc,f\r\n2,5,xyz\r\n") + def test_write_no_fields(self): fileobj = StringIO() self.assertRaises(TypeError, csv.DictWriter, fileobj) @@ -773,7 +783,7 @@ class TestDialectValidity(unittest.TestCase): with self.assertRaises(csv.Error) as cm: mydialect() self.assertEqual(str(cm.exception), - '"quotechar" must be an 1-character string') + '"quotechar" must be a 1-character string') mydialect.quotechar = 4 with self.assertRaises(csv.Error) as cm: @@ -796,13 +806,13 @@ class TestDialectValidity(unittest.TestCase): with self.assertRaises(csv.Error) as cm: mydialect() self.assertEqual(str(cm.exception), - '"delimiter" must be an 1-character string') + '"delimiter" must be a 1-character string') mydialect.delimiter = "" with self.assertRaises(csv.Error) as cm: mydialect() self.assertEqual(str(cm.exception), - '"delimiter" must be an 1-character string') + '"delimiter" must be a 1-character string') mydialect.delimiter = b"," with self.assertRaises(csv.Error) as cm: diff --git a/Lib/test/test_datetime.py b/Lib/test/test_datetime.py index d9ddb32..2d4eb52 100644 --- a/Lib/test/test_datetime.py +++ b/Lib/test/test_datetime.py @@ -1,20 +1,20 @@ import unittest import sys + from test.support import import_fresh_module, run_unittest TESTS = 'test.datetimetester' -# XXX: import_fresh_module() is supposed to leave sys.module cache untouched, -# XXX: but it does not, so we have to save and restore it ourselves. -save_sys_modules = sys.modules.copy() try: pure_tests = import_fresh_module(TESTS, fresh=['datetime', '_strptime'], blocked=['_datetime']) fast_tests = import_fresh_module(TESTS, fresh=['datetime', '_datetime', '_strptime']) finally: - sys.modules.clear() - sys.modules.update(save_sys_modules) + # XXX: import_fresh_module() is supposed to leave sys.module cache untouched, + # XXX: but it does not, so we have to cleanup ourselves. + for modname in ['datetime', '_datetime', '_strptime']: + sys.modules.pop(modname, None) test_modules = [pure_tests, fast_tests] test_suffixes = ["_Pure", "_Fast"] # XXX(gb) First run all the _Pure tests, then all the _Fast tests. You might diff --git a/Lib/test/test_dbm_dumb.py b/Lib/test/test_dbm_dumb.py index dc88ca6..ff63c88 100644 --- a/Lib/test/test_dbm_dumb.py +++ b/Lib/test/test_dbm_dumb.py @@ -217,6 +217,14 @@ class DumbDBMTestCase(unittest.TestCase): self.assertEqual(str(cm.exception), "DBM object has already been closed") + def test_create_new(self): + with dumbdbm.open(_fname, 'n') as f: + for k in self._dict: + f[k] = self._dict[k] + + with dumbdbm.open(_fname, 'n') as f: + self.assertEqual(f.keys(), []) + def test_eval(self): with open(_fname + '.dir', 'w') as stream: stream.write("str(print('Hacked!')), 0\n") diff --git a/Lib/test/test_decimal.py b/Lib/test/test_decimal.py index a178f6f..137aaa5 100644 --- a/Lib/test/test_decimal.py +++ b/Lib/test/test_decimal.py @@ -33,12 +33,13 @@ import unittest import numbers import locale from test.support import (run_unittest, run_doctest, is_resource_enabled, - requires_IEEE_754) + requires_IEEE_754, requires_docstrings) from test.support import (check_warnings, import_fresh_module, TestFailed, run_with_locale, cpython_only) import random import time import warnings +import inspect try: import threading except ImportError: @@ -4174,9 +4175,7 @@ class CheckAttributes(unittest.TestCase): self.assertEqual(C.__version__, P.__version__) self.assertEqual(C.__libmpdec_version__, P.__libmpdec_version__) - x = dir(C) - y = [s for s in dir(P) if '__' in s or not s.startswith('_')] - self.assertEqual(set(x) - set(y), set()) + self.assertEqual(dir(C), dir(P)) def test_context_attributes(self): @@ -4455,18 +4454,6 @@ class PyCoverage(Coverage): class PyFunctionality(unittest.TestCase): """Extra functionality in decimal.py""" - def test_py_quantize_watchexp(self): - # watchexp functionality - Decimal = P.Decimal - localcontext = P.localcontext - - with localcontext() as c: - c.prec = 1 - c.Emax = 1 - c.Emin = -1 - x = Decimal(99999).quantize(Decimal("1e3"), watchexp=False) - self.assertEqual(x, Decimal('1.00E+5')) - def test_py_alternate_formatting(self): # triples giving a format, a Decimal, and the expected result Decimal = P.Decimal @@ -5409,6 +5396,143 @@ class CWhitebox(unittest.TestCase): y = Decimal(10**(9*25)).__sizeof__() self.assertEqual(y, x+4) +@requires_docstrings +@unittest.skipUnless(C, "test requires C version") +class SignatureTest(unittest.TestCase): + """Function signatures""" + + def test_inspect_module(self): + for attr in dir(P): + if attr.startswith('_'): + continue + p_func = getattr(P, attr) + c_func = getattr(C, attr) + if (attr == 'Decimal' or attr == 'Context' or + inspect.isfunction(p_func)): + p_sig = inspect.signature(p_func) + c_sig = inspect.signature(c_func) + + # parameter names: + c_names = list(c_sig.parameters.keys()) + p_names = [x for x in p_sig.parameters.keys() if not + x.startswith('_')] + + self.assertEqual(c_names, p_names, + msg="parameter name mismatch in %s" % p_func) + + c_kind = [x.kind for x in c_sig.parameters.values()] + p_kind = [x[1].kind for x in p_sig.parameters.items() if not + x[0].startswith('_')] + + # parameters: + if attr != 'setcontext': + self.assertEqual(c_kind, p_kind, + msg="parameter kind mismatch in %s" % p_func) + + def test_inspect_types(self): + + POS = inspect._ParameterKind.POSITIONAL_ONLY + POS_KWD = inspect._ParameterKind.POSITIONAL_OR_KEYWORD + + # Type heuristic (type annotations would help!): + pdict = {C: {'other': C.Decimal(1), + 'third': C.Decimal(1), + 'x': C.Decimal(1), + 'y': C.Decimal(1), + 'z': C.Decimal(1), + 'a': C.Decimal(1), + 'b': C.Decimal(1), + 'c': C.Decimal(1), + 'exp': C.Decimal(1), + 'modulo': C.Decimal(1), + 'num': "1", + 'f': 1.0, + 'rounding': C.ROUND_HALF_UP, + 'context': C.getcontext()}, + P: {'other': P.Decimal(1), + 'third': P.Decimal(1), + 'a': P.Decimal(1), + 'b': P.Decimal(1), + 'c': P.Decimal(1), + 'exp': P.Decimal(1), + 'modulo': P.Decimal(1), + 'num': "1", + 'f': 1.0, + 'rounding': P.ROUND_HALF_UP, + 'context': P.getcontext()}} + + def mkargs(module, sig): + args = [] + kwargs = {} + for name, param in sig.parameters.items(): + if name == 'self': continue + if param.kind == POS: + args.append(pdict[module][name]) + elif param.kind == POS_KWD: + kwargs[name] = pdict[module][name] + else: + raise TestFailed("unexpected parameter kind") + return args, kwargs + + def tr(s): + """The C Context docstrings use 'x' in order to prevent confusion + with the article 'a' in the descriptions.""" + if s == 'x': return 'a' + if s == 'y': return 'b' + if s == 'z': return 'c' + return s + + def doit(ty): + p_type = getattr(P, ty) + c_type = getattr(C, ty) + for attr in dir(p_type): + if attr.startswith('_'): + continue + p_func = getattr(p_type, attr) + c_func = getattr(c_type, attr) + if inspect.isfunction(p_func): + p_sig = inspect.signature(p_func) + c_sig = inspect.signature(c_func) + + # parameter names: + p_names = list(p_sig.parameters.keys()) + c_names = [tr(x) for x in c_sig.parameters.keys()] + + self.assertEqual(c_names, p_names, + msg="parameter name mismatch in %s" % p_func) + + p_kind = [x.kind for x in p_sig.parameters.values()] + c_kind = [x.kind for x in c_sig.parameters.values()] + + # 'self' parameter: + self.assertIs(p_kind[0], POS_KWD) + self.assertIs(c_kind[0], POS) + + # remaining parameters: + if ty == 'Decimal': + self.assertEqual(c_kind[1:], p_kind[1:], + msg="parameter kind mismatch in %s" % p_func) + else: # Context methods are positional only in the C version. + self.assertEqual(len(c_kind), len(p_kind), + msg="parameter kind mismatch in %s" % p_func) + + # Run the function: + args, kwds = mkargs(C, c_sig) + try: + getattr(c_type(9), attr)(*args, **kwds) + except Exception as err: + raise TestFailed("invalid signature for %s: %s %s" % (c_func, args, kwds)) + + args, kwds = mkargs(P, p_sig) + try: + getattr(p_type(9), attr)(*args, **kwds) + except Exception as err: + raise TestFailed("invalid signature for %s: %s %s" % (p_func, args, kwds)) + + doit('Decimal') + doit('Context') + + all_tests = [ CExplicitConstructionTest, PyExplicitConstructionTest, CImplicitConstructionTest, PyImplicitConstructionTest, @@ -5434,6 +5558,7 @@ if not C: all_tests = all_tests[1::2] else: all_tests.insert(0, CheckAttributes) + all_tests.insert(1, SignatureTest) def test_main(arith=None, verbose=None, todo_tests=None, debug=None): diff --git a/Lib/test/test_defaultdict.py b/Lib/test/test_defaultdict.py index 532d535..48d1cb5 100644 --- a/Lib/test/test_defaultdict.py +++ b/Lib/test/test_defaultdict.py @@ -157,8 +157,9 @@ class TestDefaultDict(unittest.TestCase): def _factory(self): return [] d = sub() - self.assertTrue(repr(d).startswith( - "defaultdict(<bound method sub._factory of defaultdict(...")) + self.assertRegex(repr(d), + r"defaultdict\(<bound method .*sub\._factory " + r"of defaultdict\(\.\.\., \{\}\)>, \{\}\)") # NOTE: printing a subclass of a builtin type does not call its # tp_print slot. So this part is essentially the same test as above. diff --git a/Lib/test/test_deque.py b/Lib/test/test_deque.py index 5ecbc73..0eebbff 100644 --- a/Lib/test/test_deque.py +++ b/Lib/test/test_deque.py @@ -508,6 +508,11 @@ class TestBasic(unittest.TestCase): for s in ('abcd', range(2000)): self.assertEqual(list(reversed(deque(s))), list(reversed(s))) + def test_reversed_new(self): + klass = type(reversed(deque())) + for s in ('abcd', range(2000)): + self.assertEqual(list(klass(deque(s))), list(reversed(s))) + def test_gc_doesnt_blowup(self): import gc # This used to assert-fail in deque_traverse() under a debug @@ -537,7 +542,7 @@ class TestBasic(unittest.TestCase): @support.cpython_only def test_sizeof(self): - BLOCKLEN = 62 + BLOCKLEN = 64 basesize = support.calcobjsize('2P4nlP') blocksize = struct.calcsize('2P%dP' % BLOCKLEN) self.assertEqual(object.__sizeof__(deque()), basesize) diff --git a/Lib/test/test_descr.py b/Lib/test/test_descr.py index 1de2a99..8d6205a 100644 --- a/Lib/test/test_descr.py +++ b/Lib/test/test_descr.py @@ -1026,6 +1026,22 @@ order (MRO) for bases """ self.assertEqual(x.foo, 1) self.assertEqual(x.__dict__, {'foo': 1}) + def test_object_class_assignment_between_heaptypes_and_nonheaptypes(self): + class SubType(types.ModuleType): + a = 1 + + m = types.ModuleType("m") + self.assertTrue(m.__class__ is types.ModuleType) + self.assertFalse(hasattr(m, "a")) + + m.__class__ = SubType + self.assertTrue(m.__class__ is SubType) + self.assertTrue(hasattr(m, "a")) + + m.__class__ = types.ModuleType + self.assertTrue(m.__class__ is types.ModuleType) + self.assertFalse(hasattr(m, "a")) + def test_slots(self): # Testing __slots__... class C0(object): @@ -4160,6 +4176,7 @@ order (MRO) for bases """ ('__add__', 'x + y', 'x += y'), ('__sub__', 'x - y', 'x -= y'), ('__mul__', 'x * y', 'x *= y'), + ('__matmul__', 'x @ y', 'x @= y'), ('__truediv__', 'operator.truediv(x, y)', None), ('__floordiv__', 'operator.floordiv(x, y)', None), ('__div__', 'x / y', 'x /= y'), @@ -4422,6 +4439,61 @@ order (MRO) for bases """ self.assertIn("__dict__", Base.__dict__) self.assertNotIn("__dict__", Sub.__dict__) + def test_bound_method_repr(self): + class Foo: + def method(self): + pass + self.assertRegex(repr(Foo().method), + r"<bound method .*Foo\.method of <.*Foo object at .*>>") + + + class Base: + def method(self): + pass + class Derived1(Base): + pass + class Derived2(Base): + def method(self): + pass + base = Base() + derived1 = Derived1() + derived2 = Derived2() + super_d2 = super(Derived2, derived2) + self.assertRegex(repr(base.method), + r"<bound method .*Base\.method of <.*Base object at .*>>") + self.assertRegex(repr(derived1.method), + r"<bound method .*Base\.method of <.*Derived1 object at .*>>") + self.assertRegex(repr(derived2.method), + r"<bound method .*Derived2\.method of <.*Derived2 object at .*>>") + self.assertRegex(repr(super_d2.method), + r"<bound method .*Base\.method of <.*Derived2 object at .*>>") + + class Foo: + @classmethod + def method(cls): + pass + foo = Foo() + self.assertRegex(repr(foo.method), # access via instance + r"<bound method .*Foo\.method of <class '.*Foo'>>") + self.assertRegex(repr(Foo.method), # access via the class + r"<bound method .*Foo\.method of <class '.*Foo'>>") + + + class MyCallable: + def __call__(self, arg): + pass + func = MyCallable() # func has no __name__ or __qualname__ attributes + instance = object() + method = types.MethodType(func, instance) + self.assertRegex(repr(method), + r"<bound method \? of <object object at .*>>") + func.__name__ = "name" + self.assertRegex(repr(method), + r"<bound method name of <object object at .*>>") + func.__qualname__ = "qualname" + self.assertRegex(repr(method), + r"<bound method qualname of <object object at .*>>") + class DictProxyTests(unittest.TestCase): def setUp(self): @@ -4536,26 +4608,15 @@ class PicklingTests(unittest.TestCase): def _check_reduce(self, proto, obj, args=(), kwargs={}, state=None, listitems=None, dictitems=None): - if proto >= 4: + if proto >= 2: reduce_value = obj.__reduce_ex__(proto) - self.assertEqual(reduce_value[:3], - (copyreg.__newobj_ex__, - (type(obj), args, kwargs), - state)) - if listitems is not None: - self.assertListEqual(list(reduce_value[3]), listitems) + if kwargs: + self.assertEqual(reduce_value[0], copyreg.__newobj_ex__) + self.assertEqual(reduce_value[1], (type(obj), args, kwargs)) else: - self.assertIsNone(reduce_value[3]) - if dictitems is not None: - self.assertDictEqual(dict(reduce_value[4]), dictitems) - else: - self.assertIsNone(reduce_value[4]) - elif proto >= 2: - reduce_value = obj.__reduce_ex__(proto) - self.assertEqual(reduce_value[:3], - (copyreg.__newobj__, - (type(obj),) + args, - state)) + self.assertEqual(reduce_value[0], copyreg.__newobj__) + self.assertEqual(reduce_value[1], (type(obj),) + args) + self.assertEqual(reduce_value[2], state) if listitems is not None: self.assertListEqual(list(reduce_value[3]), listitems) else: diff --git a/Lib/test/test_dis.py b/Lib/test/test_dis.py index b8daff7..4f30183 100644 --- a/Lib/test/test_dis.py +++ b/Lib/test/test_dis.py @@ -230,6 +230,9 @@ dis_traceback = """\ TRACEBACK_CODE.co_firstlineno + 4, TRACEBACK_CODE.co_firstlineno + 5) +def _g(x): + yield x + class DisTests(unittest.TestCase): def get_disassembly(self, func, lasti=-1, wrapper=True): @@ -315,6 +318,11 @@ class DisTests(unittest.TestCase): method_bytecode = _C(1).__init__.__code__.co_code self.do_disassembly_test(method_bytecode, dis_c_instance_method_bytes) + def test_disassemble_generator(self): + gen_func_disas = self.get_disassembly(_g) # Disassemble generator function + gen_disas = self.get_disassembly(_g(1)) # Disassemble generator itself + self.assertEqual(gen_disas, gen_func_disas) + def test_dis_none(self): try: del sys.last_traceback @@ -561,10 +569,10 @@ expected_jumpy_line = 1 #_instructions = dis.get_instructions(outer, first_line=expected_outer_line) #print('expected_opinfo_outer = [\n ', #',\n '.join(map(str, _instructions)), ',\n]', sep='') -#_instructions = dis.get_instructions(outer(), first_line=expected_outer_line) +#_instructions = dis.get_instructions(outer(), first_line=expected_f_line) #print('expected_opinfo_f = [\n ', #',\n '.join(map(str, _instructions)), ',\n]', sep='') -#_instructions = dis.get_instructions(outer()(), first_line=expected_outer_line) +#_instructions = dis.get_instructions(outer()(), first_line=expected_inner_line) #print('expected_opinfo_inner = [\n ', #',\n '.join(map(str, _instructions)), ',\n]', sep='') #_instructions = dis.get_instructions(jumpy, first_line=expected_jumpy_line) @@ -635,12 +643,12 @@ expected_opinfo_inner = [ ] expected_opinfo_jumpy = [ - Instruction(opname='SETUP_LOOP', opcode=120, arg=74, argval=77, argrepr='to 77', offset=0, starts_line=3, is_jump_target=False), + Instruction(opname='SETUP_LOOP', opcode=120, arg=68, argval=71, argrepr='to 71', offset=0, starts_line=3, is_jump_target=False), Instruction(opname='LOAD_GLOBAL', opcode=116, arg=0, argval='range', argrepr='range', offset=3, starts_line=None, is_jump_target=False), Instruction(opname='LOAD_CONST', opcode=100, arg=1, argval=10, argrepr='10', offset=6, starts_line=None, is_jump_target=False), Instruction(opname='CALL_FUNCTION', opcode=131, arg=1, argval=1, argrepr='1 positional, 0 keyword pair', offset=9, starts_line=None, is_jump_target=False), Instruction(opname='GET_ITER', opcode=68, arg=None, argval=None, argrepr='', offset=12, starts_line=None, is_jump_target=False), - Instruction(opname='FOR_ITER', opcode=93, arg=50, argval=66, argrepr='to 66', offset=13, starts_line=None, is_jump_target=True), + Instruction(opname='FOR_ITER', opcode=93, arg=44, argval=60, argrepr='to 60', offset=13, starts_line=None, is_jump_target=True), Instruction(opname='STORE_FAST', opcode=125, arg=0, argval='i', argrepr='i', offset=16, starts_line=None, is_jump_target=False), Instruction(opname='LOAD_GLOBAL', opcode=116, arg=1, argval='print', argrepr='print', offset=19, starts_line=4, is_jump_target=False), Instruction(opname='LOAD_FAST', opcode=124, arg=0, argval='i', argrepr='i', offset=22, starts_line=None, is_jump_target=False), @@ -649,92 +657,88 @@ expected_opinfo_jumpy = [ Instruction(opname='LOAD_FAST', opcode=124, arg=0, argval='i', argrepr='i', offset=29, starts_line=5, is_jump_target=False), Instruction(opname='LOAD_CONST', opcode=100, arg=2, argval=4, argrepr='4', offset=32, starts_line=None, is_jump_target=False), Instruction(opname='COMPARE_OP', opcode=107, arg=0, argval='<', argrepr='<', offset=35, starts_line=None, is_jump_target=False), - Instruction(opname='POP_JUMP_IF_FALSE', opcode=114, arg=47, argval=47, argrepr='', offset=38, starts_line=None, is_jump_target=False), + Instruction(opname='POP_JUMP_IF_FALSE', opcode=114, arg=44, argval=44, argrepr='', offset=38, starts_line=None, is_jump_target=False), Instruction(opname='JUMP_ABSOLUTE', opcode=113, arg=13, argval=13, argrepr='', offset=41, starts_line=6, is_jump_target=False), - Instruction(opname='JUMP_FORWARD', opcode=110, arg=0, argval=47, argrepr='to 47', offset=44, starts_line=None, is_jump_target=False), - Instruction(opname='LOAD_FAST', opcode=124, arg=0, argval='i', argrepr='i', offset=47, starts_line=7, is_jump_target=True), - Instruction(opname='LOAD_CONST', opcode=100, arg=3, argval=6, argrepr='6', offset=50, starts_line=None, is_jump_target=False), - Instruction(opname='COMPARE_OP', opcode=107, arg=4, argval='>', argrepr='>', offset=53, starts_line=None, is_jump_target=False), - Instruction(opname='POP_JUMP_IF_FALSE', opcode=114, arg=13, argval=13, argrepr='', offset=56, starts_line=None, is_jump_target=False), - Instruction(opname='BREAK_LOOP', opcode=80, arg=None, argval=None, argrepr='', offset=59, starts_line=8, is_jump_target=False), - Instruction(opname='JUMP_ABSOLUTE', opcode=113, arg=13, argval=13, argrepr='', offset=60, starts_line=None, is_jump_target=False), - Instruction(opname='JUMP_ABSOLUTE', opcode=113, arg=13, argval=13, argrepr='', offset=63, starts_line=None, is_jump_target=False), - Instruction(opname='POP_BLOCK', opcode=87, arg=None, argval=None, argrepr='', offset=66, starts_line=None, is_jump_target=True), - Instruction(opname='LOAD_GLOBAL', opcode=116, arg=1, argval='print', argrepr='print', offset=67, starts_line=10, is_jump_target=False), - Instruction(opname='LOAD_CONST', opcode=100, arg=4, argval='I can haz else clause?', argrepr="'I can haz else clause?'", offset=70, starts_line=None, is_jump_target=False), - Instruction(opname='CALL_FUNCTION', opcode=131, arg=1, argval=1, argrepr='1 positional, 0 keyword pair', offset=73, starts_line=None, is_jump_target=False), - Instruction(opname='POP_TOP', opcode=1, arg=None, argval=None, argrepr='', offset=76, starts_line=None, is_jump_target=False), - Instruction(opname='SETUP_LOOP', opcode=120, arg=74, argval=154, argrepr='to 154', offset=77, starts_line=11, is_jump_target=True), - Instruction(opname='LOAD_FAST', opcode=124, arg=0, argval='i', argrepr='i', offset=80, starts_line=None, is_jump_target=True), - Instruction(opname='POP_JUMP_IF_FALSE', opcode=114, arg=143, argval=143, argrepr='', offset=83, starts_line=None, is_jump_target=False), - Instruction(opname='LOAD_GLOBAL', opcode=116, arg=1, argval='print', argrepr='print', offset=86, starts_line=12, is_jump_target=False), - Instruction(opname='LOAD_FAST', opcode=124, arg=0, argval='i', argrepr='i', offset=89, starts_line=None, is_jump_target=False), - Instruction(opname='CALL_FUNCTION', opcode=131, arg=1, argval=1, argrepr='1 positional, 0 keyword pair', offset=92, starts_line=None, is_jump_target=False), - Instruction(opname='POP_TOP', opcode=1, arg=None, argval=None, argrepr='', offset=95, starts_line=None, is_jump_target=False), - Instruction(opname='LOAD_FAST', opcode=124, arg=0, argval='i', argrepr='i', offset=96, starts_line=13, is_jump_target=False), - Instruction(opname='LOAD_CONST', opcode=100, arg=5, argval=1, argrepr='1', offset=99, starts_line=None, is_jump_target=False), - Instruction(opname='INPLACE_SUBTRACT', opcode=56, arg=None, argval=None, argrepr='', offset=102, starts_line=None, is_jump_target=False), - Instruction(opname='STORE_FAST', opcode=125, arg=0, argval='i', argrepr='i', offset=103, starts_line=None, is_jump_target=False), - Instruction(opname='LOAD_FAST', opcode=124, arg=0, argval='i', argrepr='i', offset=106, starts_line=14, is_jump_target=False), - Instruction(opname='LOAD_CONST', opcode=100, arg=3, argval=6, argrepr='6', offset=109, starts_line=None, is_jump_target=False), - Instruction(opname='COMPARE_OP', opcode=107, arg=4, argval='>', argrepr='>', offset=112, starts_line=None, is_jump_target=False), - Instruction(opname='POP_JUMP_IF_FALSE', opcode=114, arg=124, argval=124, argrepr='', offset=115, starts_line=None, is_jump_target=False), - Instruction(opname='JUMP_ABSOLUTE', opcode=113, arg=80, argval=80, argrepr='', offset=118, starts_line=15, is_jump_target=False), - Instruction(opname='JUMP_FORWARD', opcode=110, arg=0, argval=124, argrepr='to 124', offset=121, starts_line=None, is_jump_target=False), - Instruction(opname='LOAD_FAST', opcode=124, arg=0, argval='i', argrepr='i', offset=124, starts_line=16, is_jump_target=True), - Instruction(opname='LOAD_CONST', opcode=100, arg=2, argval=4, argrepr='4', offset=127, starts_line=None, is_jump_target=False), - Instruction(opname='COMPARE_OP', opcode=107, arg=0, argval='<', argrepr='<', offset=130, starts_line=None, is_jump_target=False), - Instruction(opname='POP_JUMP_IF_FALSE', opcode=114, arg=80, argval=80, argrepr='', offset=133, starts_line=None, is_jump_target=False), - Instruction(opname='BREAK_LOOP', opcode=80, arg=None, argval=None, argrepr='', offset=136, starts_line=17, is_jump_target=False), - Instruction(opname='JUMP_ABSOLUTE', opcode=113, arg=80, argval=80, argrepr='', offset=137, starts_line=None, is_jump_target=False), - Instruction(opname='JUMP_ABSOLUTE', opcode=113, arg=80, argval=80, argrepr='', offset=140, starts_line=None, is_jump_target=False), - Instruction(opname='POP_BLOCK', opcode=87, arg=None, argval=None, argrepr='', offset=143, starts_line=None, is_jump_target=True), - Instruction(opname='LOAD_GLOBAL', opcode=116, arg=1, argval='print', argrepr='print', offset=144, starts_line=19, is_jump_target=False), - Instruction(opname='LOAD_CONST', opcode=100, arg=6, argval='Who let lolcatz into this test suite?', argrepr="'Who let lolcatz into this test suite?'", offset=147, starts_line=None, is_jump_target=False), - Instruction(opname='CALL_FUNCTION', opcode=131, arg=1, argval=1, argrepr='1 positional, 0 keyword pair', offset=150, starts_line=None, is_jump_target=False), - Instruction(opname='POP_TOP', opcode=1, arg=None, argval=None, argrepr='', offset=153, starts_line=None, is_jump_target=False), - Instruction(opname='SETUP_FINALLY', opcode=122, arg=72, argval=229, argrepr='to 229', offset=154, starts_line=20, is_jump_target=True), - Instruction(opname='SETUP_EXCEPT', opcode=121, arg=12, argval=172, argrepr='to 172', offset=157, starts_line=None, is_jump_target=False), - Instruction(opname='LOAD_CONST', opcode=100, arg=5, argval=1, argrepr='1', offset=160, starts_line=21, is_jump_target=False), - Instruction(opname='LOAD_CONST', opcode=100, arg=7, argval=0, argrepr='0', offset=163, starts_line=None, is_jump_target=False), - Instruction(opname='BINARY_TRUE_DIVIDE', opcode=27, arg=None, argval=None, argrepr='', offset=166, starts_line=None, is_jump_target=False), - Instruction(opname='POP_TOP', opcode=1, arg=None, argval=None, argrepr='', offset=167, starts_line=None, is_jump_target=False), - Instruction(opname='POP_BLOCK', opcode=87, arg=None, argval=None, argrepr='', offset=168, starts_line=None, is_jump_target=False), - Instruction(opname='JUMP_FORWARD', opcode=110, arg=28, argval=200, argrepr='to 200', offset=169, starts_line=None, is_jump_target=False), - Instruction(opname='DUP_TOP', opcode=4, arg=None, argval=None, argrepr='', offset=172, starts_line=22, is_jump_target=True), - Instruction(opname='LOAD_GLOBAL', opcode=116, arg=2, argval='ZeroDivisionError', argrepr='ZeroDivisionError', offset=173, starts_line=None, is_jump_target=False), - Instruction(opname='COMPARE_OP', opcode=107, arg=10, argval='exception match', argrepr='exception match', offset=176, starts_line=None, is_jump_target=False), - Instruction(opname='POP_JUMP_IF_FALSE', opcode=114, arg=199, argval=199, argrepr='', offset=179, starts_line=None, is_jump_target=False), + Instruction(opname='LOAD_FAST', opcode=124, arg=0, argval='i', argrepr='i', offset=44, starts_line=7, is_jump_target=True), + Instruction(opname='LOAD_CONST', opcode=100, arg=3, argval=6, argrepr='6', offset=47, starts_line=None, is_jump_target=False), + Instruction(opname='COMPARE_OP', opcode=107, arg=4, argval='>', argrepr='>', offset=50, starts_line=None, is_jump_target=False), + Instruction(opname='POP_JUMP_IF_FALSE', opcode=114, arg=13, argval=13, argrepr='', offset=53, starts_line=None, is_jump_target=False), + Instruction(opname='BREAK_LOOP', opcode=80, arg=None, argval=None, argrepr='', offset=56, starts_line=8, is_jump_target=False), + Instruction(opname='JUMP_ABSOLUTE', opcode=113, arg=13, argval=13, argrepr='', offset=57, starts_line=None, is_jump_target=False), + Instruction(opname='POP_BLOCK', opcode=87, arg=None, argval=None, argrepr='', offset=60, starts_line=None, is_jump_target=True), + Instruction(opname='LOAD_GLOBAL', opcode=116, arg=1, argval='print', argrepr='print', offset=61, starts_line=10, is_jump_target=False), + Instruction(opname='LOAD_CONST', opcode=100, arg=4, argval='I can haz else clause?', argrepr="'I can haz else clause?'", offset=64, starts_line=None, is_jump_target=False), + Instruction(opname='CALL_FUNCTION', opcode=131, arg=1, argval=1, argrepr='1 positional, 0 keyword pair', offset=67, starts_line=None, is_jump_target=False), + Instruction(opname='POP_TOP', opcode=1, arg=None, argval=None, argrepr='', offset=70, starts_line=None, is_jump_target=False), + Instruction(opname='SETUP_LOOP', opcode=120, arg=68, argval=142, argrepr='to 142', offset=71, starts_line=11, is_jump_target=True), + Instruction(opname='LOAD_FAST', opcode=124, arg=0, argval='i', argrepr='i', offset=74, starts_line=None, is_jump_target=True), + Instruction(opname='POP_JUMP_IF_FALSE', opcode=114, arg=131, argval=131, argrepr='', offset=77, starts_line=None, is_jump_target=False), + Instruction(opname='LOAD_GLOBAL', opcode=116, arg=1, argval='print', argrepr='print', offset=80, starts_line=12, is_jump_target=False), + Instruction(opname='LOAD_FAST', opcode=124, arg=0, argval='i', argrepr='i', offset=83, starts_line=None, is_jump_target=False), + Instruction(opname='CALL_FUNCTION', opcode=131, arg=1, argval=1, argrepr='1 positional, 0 keyword pair', offset=86, starts_line=None, is_jump_target=False), + Instruction(opname='POP_TOP', opcode=1, arg=None, argval=None, argrepr='', offset=89, starts_line=None, is_jump_target=False), + Instruction(opname='LOAD_FAST', opcode=124, arg=0, argval='i', argrepr='i', offset=90, starts_line=13, is_jump_target=False), + Instruction(opname='LOAD_CONST', opcode=100, arg=5, argval=1, argrepr='1', offset=93, starts_line=None, is_jump_target=False), + Instruction(opname='INPLACE_SUBTRACT', opcode=56, arg=None, argval=None, argrepr='', offset=96, starts_line=None, is_jump_target=False), + Instruction(opname='STORE_FAST', opcode=125, arg=0, argval='i', argrepr='i', offset=97, starts_line=None, is_jump_target=False), + Instruction(opname='LOAD_FAST', opcode=124, arg=0, argval='i', argrepr='i', offset=100, starts_line=14, is_jump_target=False), + Instruction(opname='LOAD_CONST', opcode=100, arg=3, argval=6, argrepr='6', offset=103, starts_line=None, is_jump_target=False), + Instruction(opname='COMPARE_OP', opcode=107, arg=4, argval='>', argrepr='>', offset=106, starts_line=None, is_jump_target=False), + Instruction(opname='POP_JUMP_IF_FALSE', opcode=114, arg=115, argval=115, argrepr='', offset=109, starts_line=None, is_jump_target=False), + Instruction(opname='JUMP_ABSOLUTE', opcode=113, arg=74, argval=74, argrepr='', offset=112, starts_line=15, is_jump_target=False), + Instruction(opname='LOAD_FAST', opcode=124, arg=0, argval='i', argrepr='i', offset=115, starts_line=16, is_jump_target=True), + Instruction(opname='LOAD_CONST', opcode=100, arg=2, argval=4, argrepr='4', offset=118, starts_line=None, is_jump_target=False), + Instruction(opname='COMPARE_OP', opcode=107, arg=0, argval='<', argrepr='<', offset=121, starts_line=None, is_jump_target=False), + Instruction(opname='POP_JUMP_IF_FALSE', opcode=114, arg=74, argval=74, argrepr='', offset=124, starts_line=None, is_jump_target=False), + Instruction(opname='BREAK_LOOP', opcode=80, arg=None, argval=None, argrepr='', offset=127, starts_line=17, is_jump_target=False), + Instruction(opname='JUMP_ABSOLUTE', opcode=113, arg=74, argval=74, argrepr='', offset=128, starts_line=None, is_jump_target=False), + Instruction(opname='POP_BLOCK', opcode=87, arg=None, argval=None, argrepr='', offset=131, starts_line=None, is_jump_target=True), + Instruction(opname='LOAD_GLOBAL', opcode=116, arg=1, argval='print', argrepr='print', offset=132, starts_line=19, is_jump_target=False), + Instruction(opname='LOAD_CONST', opcode=100, arg=6, argval='Who let lolcatz into this test suite?', argrepr="'Who let lolcatz into this test suite?'", offset=135, starts_line=None, is_jump_target=False), + Instruction(opname='CALL_FUNCTION', opcode=131, arg=1, argval=1, argrepr='1 positional, 0 keyword pair', offset=138, starts_line=None, is_jump_target=False), + Instruction(opname='POP_TOP', opcode=1, arg=None, argval=None, argrepr='', offset=141, starts_line=None, is_jump_target=False), + Instruction(opname='SETUP_FINALLY', opcode=122, arg=72, argval=217, argrepr='to 217', offset=142, starts_line=20, is_jump_target=True), + Instruction(opname='SETUP_EXCEPT', opcode=121, arg=12, argval=160, argrepr='to 160', offset=145, starts_line=None, is_jump_target=False), + Instruction(opname='LOAD_CONST', opcode=100, arg=5, argval=1, argrepr='1', offset=148, starts_line=21, is_jump_target=False), + Instruction(opname='LOAD_CONST', opcode=100, arg=7, argval=0, argrepr='0', offset=151, starts_line=None, is_jump_target=False), + Instruction(opname='BINARY_TRUE_DIVIDE', opcode=27, arg=None, argval=None, argrepr='', offset=154, starts_line=None, is_jump_target=False), + Instruction(opname='POP_TOP', opcode=1, arg=None, argval=None, argrepr='', offset=155, starts_line=None, is_jump_target=False), + Instruction(opname='POP_BLOCK', opcode=87, arg=None, argval=None, argrepr='', offset=156, starts_line=None, is_jump_target=False), + Instruction(opname='JUMP_FORWARD', opcode=110, arg=28, argval=188, argrepr='to 188', offset=157, starts_line=None, is_jump_target=False), + Instruction(opname='DUP_TOP', opcode=4, arg=None, argval=None, argrepr='', offset=160, starts_line=22, is_jump_target=True), + Instruction(opname='LOAD_GLOBAL', opcode=116, arg=2, argval='ZeroDivisionError', argrepr='ZeroDivisionError', offset=161, starts_line=None, is_jump_target=False), + Instruction(opname='COMPARE_OP', opcode=107, arg=10, argval='exception match', argrepr='exception match', offset=164, starts_line=None, is_jump_target=False), + Instruction(opname='POP_JUMP_IF_FALSE', opcode=114, arg=187, argval=187, argrepr='', offset=167, starts_line=None, is_jump_target=False), + Instruction(opname='POP_TOP', opcode=1, arg=None, argval=None, argrepr='', offset=170, starts_line=None, is_jump_target=False), + Instruction(opname='POP_TOP', opcode=1, arg=None, argval=None, argrepr='', offset=171, starts_line=None, is_jump_target=False), + Instruction(opname='POP_TOP', opcode=1, arg=None, argval=None, argrepr='', offset=172, starts_line=None, is_jump_target=False), + Instruction(opname='LOAD_GLOBAL', opcode=116, arg=1, argval='print', argrepr='print', offset=173, starts_line=23, is_jump_target=False), + Instruction(opname='LOAD_CONST', opcode=100, arg=8, argval='Here we go, here we go, here we go...', argrepr="'Here we go, here we go, here we go...'", offset=176, starts_line=None, is_jump_target=False), + Instruction(opname='CALL_FUNCTION', opcode=131, arg=1, argval=1, argrepr='1 positional, 0 keyword pair', offset=179, starts_line=None, is_jump_target=False), Instruction(opname='POP_TOP', opcode=1, arg=None, argval=None, argrepr='', offset=182, starts_line=None, is_jump_target=False), - Instruction(opname='POP_TOP', opcode=1, arg=None, argval=None, argrepr='', offset=183, starts_line=None, is_jump_target=False), - Instruction(opname='POP_TOP', opcode=1, arg=None, argval=None, argrepr='', offset=184, starts_line=None, is_jump_target=False), - Instruction(opname='LOAD_GLOBAL', opcode=116, arg=1, argval='print', argrepr='print', offset=185, starts_line=23, is_jump_target=False), - Instruction(opname='LOAD_CONST', opcode=100, arg=8, argval='Here we go, here we go, here we go...', argrepr="'Here we go, here we go, here we go...'", offset=188, starts_line=None, is_jump_target=False), - Instruction(opname='CALL_FUNCTION', opcode=131, arg=1, argval=1, argrepr='1 positional, 0 keyword pair', offset=191, starts_line=None, is_jump_target=False), - Instruction(opname='POP_TOP', opcode=1, arg=None, argval=None, argrepr='', offset=194, starts_line=None, is_jump_target=False), - Instruction(opname='POP_EXCEPT', opcode=89, arg=None, argval=None, argrepr='', offset=195, starts_line=None, is_jump_target=False), - Instruction(opname='JUMP_FORWARD', opcode=110, arg=26, argval=225, argrepr='to 225', offset=196, starts_line=None, is_jump_target=False), - Instruction(opname='END_FINALLY', opcode=88, arg=None, argval=None, argrepr='', offset=199, starts_line=None, is_jump_target=True), - Instruction(opname='LOAD_FAST', opcode=124, arg=0, argval='i', argrepr='i', offset=200, starts_line=25, is_jump_target=True), - Instruction(opname='SETUP_WITH', opcode=143, arg=17, argval=223, argrepr='to 223', offset=203, starts_line=None, is_jump_target=False), - Instruction(opname='STORE_FAST', opcode=125, arg=1, argval='dodgy', argrepr='dodgy', offset=206, starts_line=None, is_jump_target=False), - Instruction(opname='LOAD_GLOBAL', opcode=116, arg=1, argval='print', argrepr='print', offset=209, starts_line=26, is_jump_target=False), - Instruction(opname='LOAD_CONST', opcode=100, arg=9, argval='Never reach this', argrepr="'Never reach this'", offset=212, starts_line=None, is_jump_target=False), - Instruction(opname='CALL_FUNCTION', opcode=131, arg=1, argval=1, argrepr='1 positional, 0 keyword pair', offset=215, starts_line=None, is_jump_target=False), - Instruction(opname='POP_TOP', opcode=1, arg=None, argval=None, argrepr='', offset=218, starts_line=None, is_jump_target=False), - Instruction(opname='POP_BLOCK', opcode=87, arg=None, argval=None, argrepr='', offset=219, starts_line=None, is_jump_target=False), - Instruction(opname='LOAD_CONST', opcode=100, arg=0, argval=None, argrepr='None', offset=220, starts_line=None, is_jump_target=False), - Instruction(opname='WITH_CLEANUP', opcode=81, arg=None, argval=None, argrepr='', offset=223, starts_line=None, is_jump_target=True), - Instruction(opname='END_FINALLY', opcode=88, arg=None, argval=None, argrepr='', offset=224, starts_line=None, is_jump_target=False), - Instruction(opname='POP_BLOCK', opcode=87, arg=None, argval=None, argrepr='', offset=225, starts_line=None, is_jump_target=True), - Instruction(opname='LOAD_CONST', opcode=100, arg=0, argval=None, argrepr='None', offset=226, starts_line=None, is_jump_target=False), - Instruction(opname='LOAD_GLOBAL', opcode=116, arg=1, argval='print', argrepr='print', offset=229, starts_line=28, is_jump_target=True), - Instruction(opname='LOAD_CONST', opcode=100, arg=10, argval="OK, now we're done", argrepr='"OK, now we\'re done"', offset=232, starts_line=None, is_jump_target=False), - Instruction(opname='CALL_FUNCTION', opcode=131, arg=1, argval=1, argrepr='1 positional, 0 keyword pair', offset=235, starts_line=None, is_jump_target=False), - Instruction(opname='POP_TOP', opcode=1, arg=None, argval=None, argrepr='', offset=238, starts_line=None, is_jump_target=False), - Instruction(opname='END_FINALLY', opcode=88, arg=None, argval=None, argrepr='', offset=239, starts_line=None, is_jump_target=False), - Instruction(opname='LOAD_CONST', opcode=100, arg=0, argval=None, argrepr='None', offset=240, starts_line=None, is_jump_target=False), - Instruction(opname='RETURN_VALUE', opcode=83, arg=None, argval=None, argrepr='', offset=243, starts_line=None, is_jump_target=False), + Instruction(opname='POP_EXCEPT', opcode=89, arg=None, argval=None, argrepr='', offset=183, starts_line=None, is_jump_target=False), + Instruction(opname='JUMP_FORWARD', opcode=110, arg=26, argval=213, argrepr='to 213', offset=184, starts_line=None, is_jump_target=False), + Instruction(opname='END_FINALLY', opcode=88, arg=None, argval=None, argrepr='', offset=187, starts_line=None, is_jump_target=True), + Instruction(opname='LOAD_FAST', opcode=124, arg=0, argval='i', argrepr='i', offset=188, starts_line=25, is_jump_target=True), + Instruction(opname='SETUP_WITH', opcode=143, arg=17, argval=211, argrepr='to 211', offset=191, starts_line=None, is_jump_target=False), + Instruction(opname='STORE_FAST', opcode=125, arg=1, argval='dodgy', argrepr='dodgy', offset=194, starts_line=None, is_jump_target=False), + Instruction(opname='LOAD_GLOBAL', opcode=116, arg=1, argval='print', argrepr='print', offset=197, starts_line=26, is_jump_target=False), + Instruction(opname='LOAD_CONST', opcode=100, arg=9, argval='Never reach this', argrepr="'Never reach this'", offset=200, starts_line=None, is_jump_target=False), + Instruction(opname='CALL_FUNCTION', opcode=131, arg=1, argval=1, argrepr='1 positional, 0 keyword pair', offset=203, starts_line=None, is_jump_target=False), + Instruction(opname='POP_TOP', opcode=1, arg=None, argval=None, argrepr='', offset=206, starts_line=None, is_jump_target=False), + Instruction(opname='POP_BLOCK', opcode=87, arg=None, argval=None, argrepr='', offset=207, starts_line=None, is_jump_target=False), + Instruction(opname='LOAD_CONST', opcode=100, arg=0, argval=None, argrepr='None', offset=208, starts_line=None, is_jump_target=False), + Instruction(opname='WITH_CLEANUP', opcode=81, arg=None, argval=None, argrepr='', offset=211, starts_line=None, is_jump_target=True), + Instruction(opname='END_FINALLY', opcode=88, arg=None, argval=None, argrepr='', offset=212, starts_line=None, is_jump_target=False), + Instruction(opname='POP_BLOCK', opcode=87, arg=None, argval=None, argrepr='', offset=213, starts_line=None, is_jump_target=True), + Instruction(opname='LOAD_CONST', opcode=100, arg=0, argval=None, argrepr='None', offset=214, starts_line=None, is_jump_target=False), + Instruction(opname='LOAD_GLOBAL', opcode=116, arg=1, argval='print', argrepr='print', offset=217, starts_line=28, is_jump_target=True), + Instruction(opname='LOAD_CONST', opcode=100, arg=10, argval="OK, now we're done", argrepr='"OK, now we\'re done"', offset=220, starts_line=None, is_jump_target=False), + Instruction(opname='CALL_FUNCTION', opcode=131, arg=1, argval=1, argrepr='1 positional, 0 keyword pair', offset=223, starts_line=None, is_jump_target=False), + Instruction(opname='POP_TOP', opcode=1, arg=None, argval=None, argrepr='', offset=226, starts_line=None, is_jump_target=False), + Instruction(opname='END_FINALLY', opcode=88, arg=None, argval=None, argrepr='', offset=227, starts_line=None, is_jump_target=False), + Instruction(opname='LOAD_CONST', opcode=100, arg=0, argval=None, argrepr='None', offset=228, starts_line=None, is_jump_target=False), + Instruction(opname='RETURN_VALUE', opcode=83, arg=None, argval=None, argrepr='', offset=231, starts_line=None, is_jump_target=False), ] # One last piece of inspect fodder to check the default line number handling diff --git a/Lib/test/test_doctest.py b/Lib/test/test_doctest.py index 4137d5a..95700a3 100644 --- a/Lib/test/test_doctest.py +++ b/Lib/test/test_doctest.py @@ -4,6 +4,7 @@ Test script for doctest. from test import support import doctest +import functools import os import sys @@ -434,7 +435,7 @@ We'll simulate a __file__ attr that ends in pyc: >>> tests = finder.find(sample_func) >>> print(tests) # doctest: +ELLIPSIS - [<DocTest sample_func from ...:18 (1 example)>] + [<DocTest sample_func from ...:19 (1 example)>] The exact name depends on how test_doctest was invoked, so allow for leading path components. @@ -2096,22 +2097,9 @@ def test_DocTestSuite(): >>> suite.run(unittest.TestResult()) <unittest.result.TestResult run=0 errors=0 failures=0> - However, if DocTestSuite finds no docstrings, it raises an error: + The module need not contain any docstrings either: - >>> try: - ... doctest.DocTestSuite('test.sample_doctest_no_docstrings') - ... except ValueError as e: - ... error = e - - >>> print(error.args[1]) - has no docstrings - - You can prevent this error by passing a DocTestFinder instance with - the `exclude_empty` keyword argument set to False: - - >>> finder = doctest.DocTestFinder(exclude_empty=False) - >>> suite = doctest.DocTestSuite('test.sample_doctest_no_docstrings', - ... test_finder=finder) + >>> suite = doctest.DocTestSuite('test.sample_doctest_no_docstrings') >>> suite.run(unittest.TestResult()) <unittest.result.TestResult run=0 errors=0 failures=0> @@ -2121,6 +2109,22 @@ def test_DocTestSuite(): >>> suite.run(unittest.TestResult()) <unittest.result.TestResult run=9 errors=0 failures=4> + We can also provide a DocTestFinder: + + >>> finder = doctest.DocTestFinder() + >>> suite = doctest.DocTestSuite('test.sample_doctest', + ... test_finder=finder) + >>> suite.run(unittest.TestResult()) + <unittest.result.TestResult run=9 errors=0 failures=4> + + The DocTestFinder need not return any tests: + + >>> finder = doctest.DocTestFinder() + >>> suite = doctest.DocTestSuite('test.sample_doctest_no_docstrings', + ... test_finder=finder) + >>> suite.run(unittest.TestResult()) + <unittest.result.TestResult run=0 errors=0 failures=0> + We can supply global variables. If we pass globs, they will be used instead of the module globals. Here we'll pass an empty globals, triggering an extra error: @@ -2168,7 +2172,7 @@ def test_DocTestSuite(): >>> test.test_doctest.sillySetup Traceback (most recent call last): ... - AttributeError: 'module' object has no attribute 'sillySetup' + AttributeError: module 'test.test_doctest' has no attribute 'sillySetup' The setUp and tearDown funtions are passed test objects. Here we'll use the setUp function to supply the missing variable y: @@ -2314,7 +2318,7 @@ def test_DocFileSuite(): >>> test.test_doctest.sillySetup Traceback (most recent call last): ... - AttributeError: 'module' object has no attribute 'sillySetup' + AttributeError: module 'test.test_doctest' has no attribute 'sillySetup' The setUp and tearDown funtions are passed test objects. Here, we'll use a setUp function to set the favorite color in @@ -2361,6 +2365,22 @@ def test_trailing_space_in_test(): foo \n """ +class Wrapper: + def __init__(self, func): + self.func = func + functools.update_wrapper(self, func) + + def __call__(self, *args, **kwargs): + self.func(*args, **kwargs) + +@Wrapper +def test_look_in_unwrapped(): + """ + Docstrings in wrapped functions must be detected as well. + + >>> 'one other test' + 'one other test' + """ def test_unittest_reportflags(): """Default unittest reporting flags can be set to control reporting @@ -2927,7 +2947,7 @@ Invalid doctest option: def test_main(): # Check the doctest cases in doctest itself: - support.run_doctest(doctest, verbosity=True) + ret = support.run_doctest(doctest, verbosity=True) # Check the doctest cases defined here: from test import test_doctest support.run_doctest(test_doctest, verbosity=True) diff --git a/Lib/test/test_docxmlrpc.py b/Lib/test/test_docxmlrpc.py index 06161f2..d9fd917 100644 --- a/Lib/test/test_docxmlrpc.py +++ b/Lib/test/test_docxmlrpc.py @@ -87,10 +87,11 @@ class DocXMLRPCHTTPGETServer(unittest.TestCase): threading.Thread(target=server, args=(self.evt, 1)).start() # wait for port to be assigned - n = 1000 - while n > 0 and PORT is None: - time.sleep(0.001) - n -= 1 + deadline = time.monotonic() + 10.0 + while PORT is None: + time.sleep(0.010) + if time.monotonic() > deadline: + break self.client = http.client.HTTPConnection("localhost:%d" % PORT) diff --git a/Lib/test/test_eintr.py b/Lib/test/test_eintr.py new file mode 100644 index 0000000..8b5f507 --- /dev/null +++ b/Lib/test/test_eintr.py @@ -0,0 +1,20 @@ +import os +import signal +import unittest + +from test import script_helper, support + + +@unittest.skipUnless(os.name == "posix", "only supported on Unix") +class EINTRTests(unittest.TestCase): + + @unittest.skipUnless(hasattr(signal, "setitimer"), "requires setitimer()") + def test_all(self): + # Run the tester in a sub-process, to make sure there is only one + # thread (for reliable signal delivery). + tester = support.findfile("eintr_tester.py", subdir="eintrdata") + script_helper.assert_python_ok(tester) + + +if __name__ == "__main__": + unittest.main() diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py index 227110f..218ce0c 100644 --- a/Lib/test/test_email/test_email.py +++ b/Lib/test/test_email/test_email.py @@ -1636,6 +1636,10 @@ class TestMIMEText(unittest.TestCase): msg = MIMEText('hello there', _charset='us-ascii') eq(msg.get_charset().input_charset, 'us-ascii') eq(msg['content-type'], 'text/plain; charset="us-ascii"') + # Also accept a Charset instance + msg = MIMEText('hello there', _charset=Charset('utf-8')) + eq(msg.get_charset().input_charset, 'utf-8') + eq(msg['content-type'], 'text/plain; charset="utf-8"') def test_7bit_input(self): eq = self.assertEqual diff --git a/Lib/test/test_email/test_message.py b/Lib/test/test_email/test_message.py index 50e1a63..d78049e 100644 --- a/Lib/test/test_email/test_message.py +++ b/Lib/test/test_email/test_message.py @@ -723,24 +723,14 @@ class TestEmailMessageBase: def test_is_attachment(self): m = self._make_message() self.assertFalse(m.is_attachment()) - with self.assertWarns(DeprecationWarning): - self.assertFalse(m.is_attachment) m['Content-Disposition'] = 'inline' self.assertFalse(m.is_attachment()) - with self.assertWarns(DeprecationWarning): - self.assertFalse(m.is_attachment) m.replace_header('Content-Disposition', 'attachment') self.assertTrue(m.is_attachment()) - with self.assertWarns(DeprecationWarning): - self.assertTrue(m.is_attachment) m.replace_header('Content-Disposition', 'AtTachMent') self.assertTrue(m.is_attachment()) - with self.assertWarns(DeprecationWarning): - self.assertTrue(m.is_attachment) m.set_param('filename', 'abc.png', 'Content-Disposition') self.assertTrue(m.is_attachment()) - with self.assertWarns(DeprecationWarning): - self.assertTrue(m.is_attachment) class TestEmailMessage(TestEmailMessageBase, TestEmailBase): diff --git a/Lib/test/test_enum.py b/Lib/test/test_enum.py index dccaa4f..7d172c8 100644 --- a/Lib/test/test_enum.py +++ b/Lib/test/test_enum.py @@ -646,6 +646,23 @@ class TestEnum(unittest.TestCase): self.assertIn(e, SummerMonth) self.assertIs(type(e), SummerMonth) + def test_programatic_function_string_with_start(self): + SummerMonth = Enum('SummerMonth', 'june july august', start=10) + lst = list(SummerMonth) + self.assertEqual(len(lst), len(SummerMonth)) + self.assertEqual(len(SummerMonth), 3, SummerMonth) + self.assertEqual( + [SummerMonth.june, SummerMonth.july, SummerMonth.august], + lst, + ) + for i, month in enumerate('june july august'.split(), 10): + e = SummerMonth(i) + self.assertEqual(int(e.value), i) + self.assertNotEqual(e, i) + self.assertEqual(e.name, month) + self.assertIn(e, SummerMonth) + self.assertIs(type(e), SummerMonth) + def test_programatic_function_string_list(self): SummerMonth = Enum('SummerMonth', ['june', 'july', 'august']) lst = list(SummerMonth) @@ -663,6 +680,23 @@ class TestEnum(unittest.TestCase): self.assertIn(e, SummerMonth) self.assertIs(type(e), SummerMonth) + def test_programatic_function_string_list_with_start(self): + SummerMonth = Enum('SummerMonth', ['june', 'july', 'august'], start=20) + lst = list(SummerMonth) + self.assertEqual(len(lst), len(SummerMonth)) + self.assertEqual(len(SummerMonth), 3, SummerMonth) + self.assertEqual( + [SummerMonth.june, SummerMonth.july, SummerMonth.august], + lst, + ) + for i, month in enumerate('june july august'.split(), 20): + e = SummerMonth(i) + self.assertEqual(int(e.value), i) + self.assertNotEqual(e, i) + self.assertEqual(e.name, month) + self.assertIn(e, SummerMonth) + self.assertIs(type(e), SummerMonth) + def test_programatic_function_iterable(self): SummerMonth = Enum( 'SummerMonth', @@ -719,6 +753,22 @@ class TestEnum(unittest.TestCase): self.assertIn(e, SummerMonth) self.assertIs(type(e), SummerMonth) + def test_programatic_function_type_with_start(self): + SummerMonth = Enum('SummerMonth', 'june july august', type=int, start=30) + lst = list(SummerMonth) + self.assertEqual(len(lst), len(SummerMonth)) + self.assertEqual(len(SummerMonth), 3, SummerMonth) + self.assertEqual( + [SummerMonth.june, SummerMonth.july, SummerMonth.august], + lst, + ) + for i, month in enumerate('june july august'.split(), 30): + e = SummerMonth(i) + self.assertEqual(e, i) + self.assertEqual(e.name, month) + self.assertIn(e, SummerMonth) + self.assertIs(type(e), SummerMonth) + def test_programatic_function_type_from_subclass(self): SummerMonth = IntEnum('SummerMonth', 'june july august') lst = list(SummerMonth) @@ -735,6 +785,22 @@ class TestEnum(unittest.TestCase): self.assertIn(e, SummerMonth) self.assertIs(type(e), SummerMonth) + def test_programatic_function_type_from_subclass_with_start(self): + SummerMonth = IntEnum('SummerMonth', 'june july august', start=40) + lst = list(SummerMonth) + self.assertEqual(len(lst), len(SummerMonth)) + self.assertEqual(len(SummerMonth), 3, SummerMonth) + self.assertEqual( + [SummerMonth.june, SummerMonth.july, SummerMonth.august], + lst, + ) + for i, month in enumerate('june july august'.split(), 40): + e = SummerMonth(i) + self.assertEqual(e, i) + self.assertEqual(e.name, month) + self.assertIn(e, SummerMonth) + self.assertIs(type(e), SummerMonth) + def test_subclassing(self): if isinstance(Name, Exception): raise Name diff --git a/Lib/test/test_epoll.py b/Lib/test/test_epoll.py index b37f033..d727403 100644 --- a/Lib/test/test_epoll.py +++ b/Lib/test/test_epoll.py @@ -44,7 +44,7 @@ class TestEPoll(unittest.TestCase): def setUp(self): self.serverSocket = socket.socket() self.serverSocket.bind(('127.0.0.1', 0)) - self.serverSocket.listen(1) + self.serverSocket.listen() self.connections = [self.serverSocket] def tearDown(self): diff --git a/Lib/test/test_faulthandler.py b/Lib/test/test_faulthandler.py index e68a09e..35129b6 100644 --- a/Lib/test/test_faulthandler.py +++ b/Lib/test/test_faulthandler.py @@ -17,6 +17,10 @@ try: HAVE_THREADS = True except ImportError: HAVE_THREADS = False +try: + import _testcapi +except ImportError: + _testcapi = None TIMEOUT = 0.5 @@ -135,26 +139,32 @@ class FaultHandlerTests(unittest.TestCase): 3, 'Floating point exception') - @unittest.skipIf(not hasattr(faulthandler, '_sigbus'), - "need faulthandler._sigbus()") + @unittest.skipIf(_testcapi is None, 'need _testcapi') + @unittest.skipUnless(hasattr(signal, 'SIGBUS'), 'need signal.SIGBUS') def test_sigbus(self): self.check_fatal_error(""" + import _testcapi import faulthandler + import signal + faulthandler.enable() - faulthandler._sigbus() + _testcapi.raise_signal(signal.SIGBUS) """, - 3, + 6, 'Bus error') - @unittest.skipIf(not hasattr(faulthandler, '_sigill'), - "need faulthandler._sigill()") + @unittest.skipIf(_testcapi is None, 'need _testcapi') + @unittest.skipUnless(hasattr(signal, 'SIGILL'), 'need signal.SIGILL') def test_sigill(self): self.check_fatal_error(""" + import _testcapi import faulthandler + import signal + faulthandler.enable() - faulthandler._sigill() + _testcapi.raise_signal(signal.SIGILL) """, - 3, + 6, 'Illegal instruction') def test_fatal_error(self): diff --git a/Lib/test/test_fileio.py b/Lib/test/test_fileio.py index c37482e..743ca5c 100644 --- a/Lib/test/test_fileio.py +++ b/Lib/test/test_fileio.py @@ -60,6 +60,15 @@ class AutoFileTests(unittest.TestCase): self.assertRaises((AttributeError, TypeError), setattr, f, attr, 'oops') + def testBlksize(self): + # test private _blksize attribute + blksize = io.DEFAULT_BUFFER_SIZE + # try to get preferred blksize from stat.st_blksize, if available + if hasattr(os, 'fstat'): + fst = os.fstat(self.f.fileno()) + blksize = getattr(fst, 'st_blksize', blksize) + self.assertEqual(self.f._blksize, blksize) + def testReadinto(self): # verify readinto self.f.write(bytes([1, 2])) @@ -103,14 +112,26 @@ class AutoFileTests(unittest.TestCase): self.assertRaises(TypeError, self.f.write, "Hello!") def testRepr(self): - self.assertEqual(repr(self.f), "<_io.FileIO name=%r mode=%r>" - % (self.f.name, self.f.mode)) + self.assertEqual( + repr(self.f), "<_io.FileIO name=%r mode=%r closefd=True>" + % (self.f.name, self.f.mode)) del self.f.name - self.assertEqual(repr(self.f), "<_io.FileIO fd=%r mode=%r>" - % (self.f.fileno(), self.f.mode)) + self.assertEqual( + repr(self.f), "<_io.FileIO fd=%r mode=%r closefd=True>" + % (self.f.fileno(), self.f.mode)) self.f.close() self.assertEqual(repr(self.f), "<_io.FileIO [closed]>") + def testReprNoCloseFD(self): + fd = os.open(TESTFN, os.O_RDONLY) + try: + with _FileIO(fd, 'r', closefd=False) as f: + self.assertEqual(repr(f), + "<_io.FileIO name=%r mode=%r closefd=False>" + % (f.name, f.mode)) + finally: + os.close(fd) + def testErrors(self): f = self.f self.assertTrue(not f.isatty()) @@ -141,7 +162,7 @@ class AutoFileTests(unittest.TestCase): def testOpendir(self): # Issue 3703: opening a directory should fill the errno # Windows always returns "[Errno 13]: Permission denied - # Unix calls dircheck() and returns "[Errno 21]: Is a directory" + # Unix uses fstat and returns "[Errno 21]: Is a directory" try: _FileIO('.', 'r') except OSError as e: @@ -352,8 +373,8 @@ class OtherFileTests(unittest.TestCase): def testConstructorHandlesNULChars(self): fn_with_NUL = 'foo\0bar' - self.assertRaises(TypeError, _FileIO, fn_with_NUL, 'w') - self.assertRaises(TypeError, _FileIO, bytes(fn_with_NUL, 'ascii'), 'w') + self.assertRaises(ValueError, _FileIO, fn_with_NUL, 'w') + self.assertRaises(ValueError, _FileIO, bytes(fn_with_NUL, 'ascii'), 'w') def testInvalidFd(self): self.assertRaises(ValueError, _FileIO, -10) diff --git a/Lib/test/test_fork1.py b/Lib/test/test_fork1.py index e0626df..8bcbd46 100644 --- a/Lib/test/test_fork1.py +++ b/Lib/test/test_fork1.py @@ -18,13 +18,14 @@ get_attribute(os, 'fork') class ForkTest(ForkWait): def wait_impl(self, cpid): - for i in range(10): + deadline = time.monotonic() + 10.0 + while time.monotonic() <= deadline: # waitpid() shouldn't hang, but some of the buildbots seem to hang # in the forking tests. This is an attempt to fix the problem. spid, status = os.waitpid(cpid, os.WNOHANG) if spid == cpid: break - time.sleep(1.0) + time.sleep(0.1) self.assertEqual(spid, cpid) self.assertEqual(status, 0, "cause = %d, exit = %d" % (status&0xff, status>>8)) diff --git a/Lib/test/test_format.py b/Lib/test/test_format.py index fc71e48..9d1f5d3 100644 --- a/Lib/test/test_format.py +++ b/Lib/test/test_format.py @@ -9,7 +9,7 @@ maxsize = support.MAX_Py_ssize_t # test string formatting operator (I am not sure if this is being tested # elsewhere but, surely, some of the given cases are *not* tested because # they crash python) -# test on unicode strings as well +# test on bytes object as well def testformat(formatstr, args, output=None, limit=None, overflowok=False): if verbose: @@ -46,191 +46,209 @@ def testformat(formatstr, args, output=None, limit=None, overflowok=False): if verbose: print('yes') +def testcommon(formatstr, args, output=None, limit=None, overflowok=False): + # if formatstr is a str, test str, bytes, and bytearray; + # otherwise, test bytes and bytearry + if isinstance(formatstr, str): + testformat(formatstr, args, output, limit, overflowok) + b_format = formatstr.encode('ascii') + else: + b_format = formatstr + ba_format = bytearray(b_format) + b_args = [] + if not isinstance(args, tuple): + args = (args, ) + b_args = tuple(args) + if output is None: + b_output = ba_output = None + else: + if isinstance(output, str): + b_output = output.encode('ascii') + else: + b_output = output + ba_output = bytearray(b_output) + testformat(b_format, b_args, b_output, limit, overflowok) + testformat(ba_format, b_args, ba_output, limit, overflowok) + class FormatTest(unittest.TestCase): - def test_format(self): - testformat("%.1d", (1,), "1") - testformat("%.*d", (sys.maxsize,1), overflowok=True) # expect overflow - testformat("%.100d", (1,), '00000000000000000000000000000000000000' + + def test_common_format(self): + # test the format identifiers that work the same across + # str, bytes, and bytearrays (integer, float, oct, hex) + testcommon("%.1d", (1,), "1") + testcommon("%.*d", (sys.maxsize,1), overflowok=True) # expect overflow + testcommon("%.100d", (1,), '00000000000000000000000000000000000000' '000000000000000000000000000000000000000000000000000000' '00000001', overflowok=True) - testformat("%#.117x", (1,), '0x00000000000000000000000000000000000' + testcommon("%#.117x", (1,), '0x00000000000000000000000000000000000' '000000000000000000000000000000000000000000000000000000' '0000000000000000000000000001', overflowok=True) - testformat("%#.118x", (1,), '0x00000000000000000000000000000000000' + testcommon("%#.118x", (1,), '0x00000000000000000000000000000000000' '000000000000000000000000000000000000000000000000000000' '00000000000000000000000000001', overflowok=True) - testformat("%f", (1.0,), "1.000000") + testcommon("%f", (1.0,), "1.000000") # these are trying to test the limits of the internal magic-number-length # formatting buffer, if that number changes then these tests are less # effective - testformat("%#.*g", (109, -1.e+49/3.)) - testformat("%#.*g", (110, -1.e+49/3.)) - testformat("%#.*g", (110, -1.e+100/3.)) + testcommon("%#.*g", (109, -1.e+49/3.)) + testcommon("%#.*g", (110, -1.e+49/3.)) + testcommon("%#.*g", (110, -1.e+100/3.)) # test some ridiculously large precision, expect overflow - testformat('%12.*f', (123456, 1.0)) + testcommon('%12.*f', (123456, 1.0)) # check for internal overflow validation on length of precision # these tests should no longer cause overflow in Python # 2.7/3.1 and later. - testformat("%#.*g", (110, -1.e+100/3.)) - testformat("%#.*G", (110, -1.e+100/3.)) - testformat("%#.*f", (110, -1.e+100/3.)) - testformat("%#.*F", (110, -1.e+100/3.)) + testcommon("%#.*g", (110, -1.e+100/3.)) + testcommon("%#.*G", (110, -1.e+100/3.)) + testcommon("%#.*f", (110, -1.e+100/3.)) + testcommon("%#.*F", (110, -1.e+100/3.)) # Formatting of integers. Overflow is not ok - testformat("%x", 10, "a") - testformat("%x", 100000000000, "174876e800") - testformat("%o", 10, "12") - testformat("%o", 100000000000, "1351035564000") - testformat("%d", 10, "10") - testformat("%d", 100000000000, "100000000000") + testcommon("%x", 10, "a") + testcommon("%x", 100000000000, "174876e800") + testcommon("%o", 10, "12") + testcommon("%o", 100000000000, "1351035564000") + testcommon("%d", 10, "10") + testcommon("%d", 100000000000, "100000000000") big = 123456789012345678901234567890 - testformat("%d", big, "123456789012345678901234567890") - testformat("%d", -big, "-123456789012345678901234567890") - testformat("%5d", -big, "-123456789012345678901234567890") - testformat("%31d", -big, "-123456789012345678901234567890") - testformat("%32d", -big, " -123456789012345678901234567890") - testformat("%-32d", -big, "-123456789012345678901234567890 ") - testformat("%032d", -big, "-0123456789012345678901234567890") - testformat("%-032d", -big, "-123456789012345678901234567890 ") - testformat("%034d", -big, "-000123456789012345678901234567890") - testformat("%034d", big, "0000123456789012345678901234567890") - testformat("%0+34d", big, "+000123456789012345678901234567890") - testformat("%+34d", big, " +123456789012345678901234567890") - testformat("%34d", big, " 123456789012345678901234567890") - testformat("%.2d", big, "123456789012345678901234567890") - testformat("%.30d", big, "123456789012345678901234567890") - testformat("%.31d", big, "0123456789012345678901234567890") - testformat("%32.31d", big, " 0123456789012345678901234567890") - testformat("%d", float(big), "123456________________________", 6) + testcommon("%d", big, "123456789012345678901234567890") + testcommon("%d", -big, "-123456789012345678901234567890") + testcommon("%5d", -big, "-123456789012345678901234567890") + testcommon("%31d", -big, "-123456789012345678901234567890") + testcommon("%32d", -big, " -123456789012345678901234567890") + testcommon("%-32d", -big, "-123456789012345678901234567890 ") + testcommon("%032d", -big, "-0123456789012345678901234567890") + testcommon("%-032d", -big, "-123456789012345678901234567890 ") + testcommon("%034d", -big, "-000123456789012345678901234567890") + testcommon("%034d", big, "0000123456789012345678901234567890") + testcommon("%0+34d", big, "+000123456789012345678901234567890") + testcommon("%+34d", big, " +123456789012345678901234567890") + testcommon("%34d", big, " 123456789012345678901234567890") + testcommon("%.2d", big, "123456789012345678901234567890") + testcommon("%.30d", big, "123456789012345678901234567890") + testcommon("%.31d", big, "0123456789012345678901234567890") + testcommon("%32.31d", big, " 0123456789012345678901234567890") + testcommon("%d", float(big), "123456________________________", 6) big = 0x1234567890abcdef12345 # 21 hex digits - testformat("%x", big, "1234567890abcdef12345") - testformat("%x", -big, "-1234567890abcdef12345") - testformat("%5x", -big, "-1234567890abcdef12345") - testformat("%22x", -big, "-1234567890abcdef12345") - testformat("%23x", -big, " -1234567890abcdef12345") - testformat("%-23x", -big, "-1234567890abcdef12345 ") - testformat("%023x", -big, "-01234567890abcdef12345") - testformat("%-023x", -big, "-1234567890abcdef12345 ") - testformat("%025x", -big, "-0001234567890abcdef12345") - testformat("%025x", big, "00001234567890abcdef12345") - testformat("%0+25x", big, "+0001234567890abcdef12345") - testformat("%+25x", big, " +1234567890abcdef12345") - testformat("%25x", big, " 1234567890abcdef12345") - testformat("%.2x", big, "1234567890abcdef12345") - testformat("%.21x", big, "1234567890abcdef12345") - testformat("%.22x", big, "01234567890abcdef12345") - testformat("%23.22x", big, " 01234567890abcdef12345") - testformat("%-23.22x", big, "01234567890abcdef12345 ") - testformat("%X", big, "1234567890ABCDEF12345") - testformat("%#X", big, "0X1234567890ABCDEF12345") - testformat("%#x", big, "0x1234567890abcdef12345") - testformat("%#x", -big, "-0x1234567890abcdef12345") - testformat("%#.23x", -big, "-0x001234567890abcdef12345") - testformat("%#+.23x", big, "+0x001234567890abcdef12345") - testformat("%# .23x", big, " 0x001234567890abcdef12345") - testformat("%#+.23X", big, "+0X001234567890ABCDEF12345") - testformat("%#-+.23X", big, "+0X001234567890ABCDEF12345") - testformat("%#-+26.23X", big, "+0X001234567890ABCDEF12345") - testformat("%#-+27.23X", big, "+0X001234567890ABCDEF12345 ") - testformat("%#+27.23X", big, " +0X001234567890ABCDEF12345") + testcommon("%x", big, "1234567890abcdef12345") + testcommon("%x", -big, "-1234567890abcdef12345") + testcommon("%5x", -big, "-1234567890abcdef12345") + testcommon("%22x", -big, "-1234567890abcdef12345") + testcommon("%23x", -big, " -1234567890abcdef12345") + testcommon("%-23x", -big, "-1234567890abcdef12345 ") + testcommon("%023x", -big, "-01234567890abcdef12345") + testcommon("%-023x", -big, "-1234567890abcdef12345 ") + testcommon("%025x", -big, "-0001234567890abcdef12345") + testcommon("%025x", big, "00001234567890abcdef12345") + testcommon("%0+25x", big, "+0001234567890abcdef12345") + testcommon("%+25x", big, " +1234567890abcdef12345") + testcommon("%25x", big, " 1234567890abcdef12345") + testcommon("%.2x", big, "1234567890abcdef12345") + testcommon("%.21x", big, "1234567890abcdef12345") + testcommon("%.22x", big, "01234567890abcdef12345") + testcommon("%23.22x", big, " 01234567890abcdef12345") + testcommon("%-23.22x", big, "01234567890abcdef12345 ") + testcommon("%X", big, "1234567890ABCDEF12345") + testcommon("%#X", big, "0X1234567890ABCDEF12345") + testcommon("%#x", big, "0x1234567890abcdef12345") + testcommon("%#x", -big, "-0x1234567890abcdef12345") + testcommon("%#.23x", -big, "-0x001234567890abcdef12345") + testcommon("%#+.23x", big, "+0x001234567890abcdef12345") + testcommon("%# .23x", big, " 0x001234567890abcdef12345") + testcommon("%#+.23X", big, "+0X001234567890ABCDEF12345") + testcommon("%#-+.23X", big, "+0X001234567890ABCDEF12345") + testcommon("%#-+26.23X", big, "+0X001234567890ABCDEF12345") + testcommon("%#-+27.23X", big, "+0X001234567890ABCDEF12345 ") + testcommon("%#+27.23X", big, " +0X001234567890ABCDEF12345") # next one gets two leading zeroes from precision, and another from the # 0 flag and the width - testformat("%#+027.23X", big, "+0X0001234567890ABCDEF12345") + testcommon("%#+027.23X", big, "+0X0001234567890ABCDEF12345") # same, except no 0 flag - testformat("%#+27.23X", big, " +0X001234567890ABCDEF12345") - with self.assertWarns(DeprecationWarning): - testformat("%x", float(big), "123456_______________", 6) + testcommon("%#+27.23X", big, " +0X001234567890ABCDEF12345") big = 0o12345670123456701234567012345670 # 32 octal digits - testformat("%o", big, "12345670123456701234567012345670") - testformat("%o", -big, "-12345670123456701234567012345670") - testformat("%5o", -big, "-12345670123456701234567012345670") - testformat("%33o", -big, "-12345670123456701234567012345670") - testformat("%34o", -big, " -12345670123456701234567012345670") - testformat("%-34o", -big, "-12345670123456701234567012345670 ") - testformat("%034o", -big, "-012345670123456701234567012345670") - testformat("%-034o", -big, "-12345670123456701234567012345670 ") - testformat("%036o", -big, "-00012345670123456701234567012345670") - testformat("%036o", big, "000012345670123456701234567012345670") - testformat("%0+36o", big, "+00012345670123456701234567012345670") - testformat("%+36o", big, " +12345670123456701234567012345670") - testformat("%36o", big, " 12345670123456701234567012345670") - testformat("%.2o", big, "12345670123456701234567012345670") - testformat("%.32o", big, "12345670123456701234567012345670") - testformat("%.33o", big, "012345670123456701234567012345670") - testformat("%34.33o", big, " 012345670123456701234567012345670") - testformat("%-34.33o", big, "012345670123456701234567012345670 ") - testformat("%o", big, "12345670123456701234567012345670") - testformat("%#o", big, "0o12345670123456701234567012345670") - testformat("%#o", -big, "-0o12345670123456701234567012345670") - testformat("%#.34o", -big, "-0o0012345670123456701234567012345670") - testformat("%#+.34o", big, "+0o0012345670123456701234567012345670") - testformat("%# .34o", big, " 0o0012345670123456701234567012345670") - testformat("%#+.34o", big, "+0o0012345670123456701234567012345670") - testformat("%#-+.34o", big, "+0o0012345670123456701234567012345670") - testformat("%#-+37.34o", big, "+0o0012345670123456701234567012345670") - testformat("%#+37.34o", big, "+0o0012345670123456701234567012345670") + testcommon("%o", big, "12345670123456701234567012345670") + testcommon("%o", -big, "-12345670123456701234567012345670") + testcommon("%5o", -big, "-12345670123456701234567012345670") + testcommon("%33o", -big, "-12345670123456701234567012345670") + testcommon("%34o", -big, " -12345670123456701234567012345670") + testcommon("%-34o", -big, "-12345670123456701234567012345670 ") + testcommon("%034o", -big, "-012345670123456701234567012345670") + testcommon("%-034o", -big, "-12345670123456701234567012345670 ") + testcommon("%036o", -big, "-00012345670123456701234567012345670") + testcommon("%036o", big, "000012345670123456701234567012345670") + testcommon("%0+36o", big, "+00012345670123456701234567012345670") + testcommon("%+36o", big, " +12345670123456701234567012345670") + testcommon("%36o", big, " 12345670123456701234567012345670") + testcommon("%.2o", big, "12345670123456701234567012345670") + testcommon("%.32o", big, "12345670123456701234567012345670") + testcommon("%.33o", big, "012345670123456701234567012345670") + testcommon("%34.33o", big, " 012345670123456701234567012345670") + testcommon("%-34.33o", big, "012345670123456701234567012345670 ") + testcommon("%o", big, "12345670123456701234567012345670") + testcommon("%#o", big, "0o12345670123456701234567012345670") + testcommon("%#o", -big, "-0o12345670123456701234567012345670") + testcommon("%#.34o", -big, "-0o0012345670123456701234567012345670") + testcommon("%#+.34o", big, "+0o0012345670123456701234567012345670") + testcommon("%# .34o", big, " 0o0012345670123456701234567012345670") + testcommon("%#+.34o", big, "+0o0012345670123456701234567012345670") + testcommon("%#-+.34o", big, "+0o0012345670123456701234567012345670") + testcommon("%#-+37.34o", big, "+0o0012345670123456701234567012345670") + testcommon("%#+37.34o", big, "+0o0012345670123456701234567012345670") # next one gets one leading zero from precision - testformat("%.33o", big, "012345670123456701234567012345670") + testcommon("%.33o", big, "012345670123456701234567012345670") # base marker shouldn't change that, since "0" is redundant - testformat("%#.33o", big, "0o012345670123456701234567012345670") + testcommon("%#.33o", big, "0o012345670123456701234567012345670") # but reduce precision, and base marker should add a zero - testformat("%#.32o", big, "0o12345670123456701234567012345670") + testcommon("%#.32o", big, "0o12345670123456701234567012345670") # one leading zero from precision, and another from "0" flag & width - testformat("%034.33o", big, "0012345670123456701234567012345670") + testcommon("%034.33o", big, "0012345670123456701234567012345670") # base marker shouldn't change that - testformat("%0#34.33o", big, "0o012345670123456701234567012345670") - with self.assertWarns(DeprecationWarning): - testformat("%o", float(big), "123456__________________________", 6) + testcommon("%0#34.33o", big, "0o012345670123456701234567012345670") # Some small ints, in both Python int and flavors). - testformat("%d", 42, "42") - testformat("%d", -42, "-42") - testformat("%d", 42, "42") - testformat("%d", -42, "-42") - testformat("%d", 42.0, "42") - testformat("%#x", 1, "0x1") - testformat("%#x", 1, "0x1") - testformat("%#X", 1, "0X1") - testformat("%#X", 1, "0X1") - with self.assertWarns(DeprecationWarning): - testformat("%#x", 1.0, "0x1") - testformat("%#o", 1, "0o1") - testformat("%#o", 1, "0o1") - testformat("%#o", 0, "0o0") - testformat("%#o", 0, "0o0") - testformat("%o", 0, "0") - testformat("%o", 0, "0") - testformat("%d", 0, "0") - testformat("%d", 0, "0") - testformat("%#x", 0, "0x0") - testformat("%#x", 0, "0x0") - testformat("%#X", 0, "0X0") - testformat("%#X", 0, "0X0") - testformat("%x", 0x42, "42") - testformat("%x", -0x42, "-42") - testformat("%x", 0x42, "42") - testformat("%x", -0x42, "-42") - with self.assertWarns(DeprecationWarning): - testformat("%x", float(0x42), "42") - testformat("%o", 0o42, "42") - testformat("%o", -0o42, "-42") - testformat("%o", 0o42, "42") - testformat("%o", -0o42, "-42") - with self.assertWarns(DeprecationWarning): - testformat("%o", float(0o42), "42") + testcommon("%d", 42, "42") + testcommon("%d", -42, "-42") + testcommon("%d", 42, "42") + testcommon("%d", -42, "-42") + testcommon("%d", 42.0, "42") + testcommon("%#x", 1, "0x1") + testcommon("%#x", 1, "0x1") + testcommon("%#X", 1, "0X1") + testcommon("%#X", 1, "0X1") + testcommon("%#o", 1, "0o1") + testcommon("%#o", 1, "0o1") + testcommon("%#o", 0, "0o0") + testcommon("%#o", 0, "0o0") + testcommon("%o", 0, "0") + testcommon("%o", 0, "0") + testcommon("%d", 0, "0") + testcommon("%d", 0, "0") + testcommon("%#x", 0, "0x0") + testcommon("%#x", 0, "0x0") + testcommon("%#X", 0, "0X0") + testcommon("%#X", 0, "0X0") + testcommon("%x", 0x42, "42") + testcommon("%x", -0x42, "-42") + testcommon("%x", 0x42, "42") + testcommon("%x", -0x42, "-42") + testcommon("%o", 0o42, "42") + testcommon("%o", -0o42, "-42") + testcommon("%o", 0o42, "42") + testcommon("%o", -0o42, "-42") + # alternate float formatting + testcommon('%g', 1.1, '1.1') + testcommon('%#g', 1.1, '1.10000') + + def test_str_format(self): testformat("%r", "\u0378", "'\\u0378'") # non printable testformat("%a", "\u0378", "'\\u0378'") # non printable testformat("%r", "\u0374", "'\u0374'") # printable testformat("%a", "\u0374", "'\\u0374'") # printable - # alternate float formatting - testformat('%g', 1.1, '1.1') - testformat('%#g', 1.1, '1.10000') - - # Test exception for unknown format characters + # Test exception for unknown format characters, etc. if verbose: print('Testing exceptions') def test_exc(formatstr, args, exception, excmsg): @@ -257,8 +275,83 @@ class FormatTest(unittest.TestCase): test_exc('%g', '1', TypeError, "a float is required") test_exc('no format', '1', TypeError, "not all arguments converted during string formatting") - test_exc('no format', '1', TypeError, - "not all arguments converted during string formatting") + + if maxsize == 2**31-1: + # crashes 2.2.1 and earlier: + try: + "%*d"%(maxsize, -127) + except MemoryError: + pass + else: + raise TestFailed('"%*d"%(maxsize, -127) should fail') + + def test_bytes_and_bytearray_format(self): + # %c will insert a single byte, either from an int in range(256), or + # from a bytes argument of length 1, not from a str. + testcommon(b"%c", 7, b"\x07") + testcommon(b"%c", b"Z", b"Z") + testcommon(b"%c", bytearray(b"Z"), b"Z") + # %b will insert a series of bytes, either from a type that supports + # the Py_buffer protocol, or something that has a __bytes__ method + class FakeBytes(object): + def __bytes__(self): + return b'123' + fb = FakeBytes() + testcommon(b"%b", b"abc", b"abc") + testcommon(b"%b", bytearray(b"def"), b"def") + testcommon(b"%b", fb, b"123") + # # %s is an alias for %b -- should only be used for Py2/3 code + testcommon(b"%s", b"abc", b"abc") + testcommon(b"%s", bytearray(b"def"), b"def") + testcommon(b"%s", fb, b"123") + # %a will give the equivalent of + # repr(some_obj).encode('ascii', 'backslashreplace') + testcommon(b"%a", 3.14, b"3.14") + testcommon(b"%a", b"ghi", b"b'ghi'") + testcommon(b"%a", "jkl", b"'jkl'") + testcommon(b"%a", "\u0544", b"'\\u0544'") + + # Test exception for unknown format characters, etc. + if verbose: + print('Testing exceptions') + def test_exc(formatstr, args, exception, excmsg): + try: + testformat(formatstr, args) + except exception as exc: + if str(exc) == excmsg: + if verbose: + print("yes") + else: + if verbose: print('no') + print('Unexpected ', exception, ':', repr(str(exc))) + except: + if verbose: print('no') + print('Unexpected exception') + raise + else: + raise TestFailed('did not get expected exception: %s' % excmsg) + test_exc(b'%d', '1', TypeError, + "%d format: a number is required, not str") + test_exc(b'%d', b'1', TypeError, + "%d format: a number is required, not bytes") + test_exc(b'%g', '1', TypeError, "float argument required, not str") + test_exc(b'%g', b'1', TypeError, "float argument required, not bytes") + test_exc(b'no format', 7, TypeError, + "not all arguments converted during bytes formatting") + test_exc(b'no format', b'1', TypeError, + "not all arguments converted during bytes formatting") + test_exc(b'no format', bytearray(b'1'), TypeError, + "not all arguments converted during bytes formatting") + test_exc(b"%c", 256, TypeError, + "%c requires an integer in range(256) or a single byte") + test_exc(b"%c", b"Za", TypeError, + "%c requires an integer in range(256) or a single byte") + test_exc(b"%c", "Yb", TypeError, + "%c requires an integer in range(256) or a single byte") + test_exc(b"%b", "Xc", TypeError, + "%b requires bytes, or an object that implements __bytes__, not 'str'") + test_exc(b"%s", "Wd", TypeError, + "%b requires bytes, or an object that implements __bytes__, not 'str'") if maxsize == 2**31-1: # crashes 2.2.1 and earlier: diff --git a/Lib/test/test_fractions.py b/Lib/test/test_fractions.py index 3336532..e86d5ce 100644 --- a/Lib/test/test_fractions.py +++ b/Lib/test/test_fractions.py @@ -330,7 +330,6 @@ class FractionTest(unittest.TestCase): self.assertTypedEquals(F(-2, 10), round(F(-15, 100), 1)) self.assertTypedEquals(F(-2, 10), round(F(-25, 100), 1)) - def testArithmetic(self): self.assertEqual(F(1, 2), F(1, 10) + F(2, 5)) self.assertEqual(F(-3, 10), F(1, 10) - F(2, 5)) @@ -402,6 +401,8 @@ class FractionTest(unittest.TestCase): self.assertTypedEquals(2.0 , 4 ** F(1, 2)) self.assertTypedEquals(0.25, 2.0 ** F(-2, 1)) self.assertTypedEquals(1.0 + 0j, (1.0 + 0j) ** F(1, 10)) + self.assertRaises(ZeroDivisionError, operator.pow, + F(0, 1), -2) def testMixingWithDecimal(self): # Decimal refuses mixed arithmetic (but not mixed comparisons) diff --git a/Lib/test/test_ftplib.py b/Lib/test/test_ftplib.py index d3be7d6..aef66da 100644 --- a/Lib/test/test_ftplib.py +++ b/Lib/test/test_ftplib.py @@ -73,7 +73,7 @@ class DummyDTPHandler(asynchat.async_chat): super(DummyDTPHandler, self).push(what.encode('ascii')) def handle_error(self): - raise + raise Exception class DummyFTPHandler(asynchat.async_chat): @@ -118,7 +118,7 @@ class DummyFTPHandler(asynchat.async_chat): self.push('550 command "%s" not understood.' %cmd) def handle_error(self): - raise + raise Exception def push(self, data): asynchat.async_chat.push(self, data.encode('ascii') + b'\r\n') @@ -134,7 +134,7 @@ class DummyFTPHandler(asynchat.async_chat): def cmd_pasv(self, arg): with socket.socket() as sock: sock.bind((self.socket.getsockname()[0], 0)) - sock.listen(5) + sock.listen() sock.settimeout(TIMEOUT) ip, port = sock.getsockname()[:2] ip = ip.replace('.', ','); p1 = port / 256; p2 = port % 256 @@ -152,7 +152,7 @@ class DummyFTPHandler(asynchat.async_chat): def cmd_epsv(self, arg): with socket.socket(socket.AF_INET6) as sock: sock.bind((self.socket.getsockname()[0], 0)) - sock.listen(5) + sock.listen() sock.settimeout(TIMEOUT) port = sock.getsockname()[1] self.push('229 entering extended passive mode (|||%d|)' %port) @@ -296,7 +296,7 @@ class DummyFTPServer(asyncore.dispatcher, threading.Thread): return 0 def handle_error(self): - raise + raise Exception if ssl is not None: @@ -394,7 +394,7 @@ if ssl is not None: raise def handle_error(self): - raise + raise Exception def close(self): if (isinstance(self.socket, ssl.SSLSocket) and @@ -670,7 +670,7 @@ class TestFTPClass(TestCase): self.assertRaises(StopIteration, next, self.client.mlsd()) set_data('') for x in self.client.mlsd(): - self.fail("unexpected data %s" % data) + self.fail("unexpected data %s" % x) def test_makeport(self): with self.client.makeport(): @@ -979,7 +979,7 @@ class TestTimeouts(TestCase): # 1) when the connection is ready to be accepted. # 2) when it is safe for the caller to close the connection # 3) when we have closed the socket - self.sock.listen(5) + self.sock.listen() # (1) Signal the caller that we are ready to accept the connection. self.evt.set() try: @@ -1049,19 +1049,8 @@ class TestTimeouts(TestCase): ftp.close() -class TestNetrcDeprecation(TestCase): - - def test_deprecation(self): - with support.temp_cwd(), support.EnvironmentVarGuard() as env: - env['HOME'] = os.getcwd() - open('.netrc', 'w').close() - with self.assertWarns(DeprecationWarning): - ftplib.Netrc() - - - def test_main(): - tests = [TestFTPClass, TestTimeouts, TestNetrcDeprecation, + tests = [TestFTPClass, TestTimeouts, TestIPv6Environment, TestTLS_FTPClassMixin, TestTLS_FTPClass] diff --git a/Lib/test/test_functools.py b/Lib/test/test_functools.py index 0375601c..c549ac4 100644 --- a/Lib/test/test_functools.py +++ b/Lib/test/test_functools.py @@ -131,6 +131,16 @@ class TestPartial: join = self.partial(''.join) self.assertEqual(join(data), '0123456789') + def test_nested_optimization(self): + partial = self.partial + # Only "true" partial is optimized + if partial.__name__ != 'partial': + return + inner = partial(signature, 'asdf') + nested = partial(inner, bar=True) + flat = partial(signature, 'asdf', bar=True) + self.assertEqual(signature(nested), signature(flat)) + @unittest.skipUnless(c_functools, 'requires the C _functools module') class TestPartialC(TestPartial, unittest.TestCase): @@ -882,6 +892,24 @@ class TestTotalOrdering(unittest.TestCase): with self.assertRaises(TypeError): a <= b + def test_pickle(self): + for proto in range(4, pickle.HIGHEST_PROTOCOL + 1): + for name in '__lt__', '__gt__', '__le__', '__ge__': + with self.subTest(method=name, proto=proto): + method = getattr(Orderable_LT, name) + method_copy = pickle.loads(pickle.dumps(method, proto)) + self.assertIs(method_copy, method) + +@functools.total_ordering +class Orderable_LT: + def __init__(self, value): + self.value = value + def __lt__(self, other): + return self.value < other.value + def __eq__(self, other): + return self.value == other.value + + class TestLRU(unittest.TestCase): def test_lru(self): diff --git a/Lib/test/test_generators.py b/Lib/test/test_generators.py index 7825a77..9e61013 100644 --- a/Lib/test/test_generators.py +++ b/Lib/test/test_generators.py @@ -50,6 +50,45 @@ class FinalizationTest(unittest.TestCase): self.assertEqual(gc.garbage, old_garbage) +class GeneratorTest(unittest.TestCase): + + def test_name(self): + def func(): + yield 1 + + # check generator names + gen = func() + self.assertEqual(gen.__name__, "func") + self.assertEqual(gen.__qualname__, + "GeneratorTest.test_name.<locals>.func") + + # modify generator names + gen.__name__ = "name" + gen.__qualname__ = "qualname" + self.assertEqual(gen.__name__, "name") + self.assertEqual(gen.__qualname__, "qualname") + + # generator names must be a string and cannot be deleted + self.assertRaises(TypeError, setattr, gen, '__name__', 123) + self.assertRaises(TypeError, setattr, gen, '__qualname__', 123) + self.assertRaises(TypeError, delattr, gen, '__name__') + self.assertRaises(TypeError, delattr, gen, '__qualname__') + + # modify names of the function creating the generator + func.__qualname__ = "func_qualname" + func.__name__ = "func_name" + gen = func() + self.assertEqual(gen.__name__, "func_name") + self.assertEqual(gen.__qualname__, "func_qualname") + + # unnamed generator + gen = (x for x in range(10)) + self.assertEqual(gen.__name__, + "<genexpr>") + self.assertEqual(gen.__qualname__, + "GeneratorTest.test_name.<locals>.<genexpr>") + + class ExceptionTest(unittest.TestCase): # Tests for the issue #23353: check that the currently handled exception # is correctly saved/restored in PyEval_EvalFrameEx(). diff --git a/Lib/test/test_genericpath.py b/Lib/test/test_genericpath.py index e59ed4d..f2722bc 100644 --- a/Lib/test/test_genericpath.py +++ b/Lib/test/test_genericpath.py @@ -434,6 +434,40 @@ class CommonTest(GenericTest): with support.temp_cwd(name): self.test_abspath() + def test_join_errors(self): + # Check join() raises friendly TypeErrors. + with support.check_warnings(('', BytesWarning), quiet=True): + errmsg = "Can't mix strings and bytes in path components" + with self.assertRaisesRegex(TypeError, errmsg): + self.pathmodule.join(b'bytes', 'str') + with self.assertRaisesRegex(TypeError, errmsg): + self.pathmodule.join('str', b'bytes') + # regression, see #15377 + errmsg = r'join\(\) argument must be str or bytes, not %r' + with self.assertRaisesRegex(TypeError, errmsg % 'int'): + self.pathmodule.join(42, 'str') + with self.assertRaisesRegex(TypeError, errmsg % 'int'): + self.pathmodule.join('str', 42) + with self.assertRaisesRegex(TypeError, errmsg % 'bytearray'): + self.pathmodule.join(bytearray(b'foo'), bytearray(b'bar')) + + def test_relpath_errors(self): + # Check relpath() raises friendly TypeErrors. + with support.check_warnings(('', (BytesWarning, DeprecationWarning)), + quiet=True): + errmsg = "Can't mix strings and bytes in path components" + with self.assertRaisesRegex(TypeError, errmsg): + self.pathmodule.relpath(b'bytes', 'str') + with self.assertRaisesRegex(TypeError, errmsg): + self.pathmodule.relpath('str', b'bytes') + errmsg = r'relpath\(\) argument must be str or bytes, not %r' + with self.assertRaisesRegex(TypeError, errmsg % 'int'): + self.pathmodule.relpath(42, 'str') + with self.assertRaisesRegex(TypeError, errmsg % 'int'): + self.pathmodule.relpath('str', 42) + with self.assertRaisesRegex(TypeError, errmsg % 'bytearray'): + self.pathmodule.relpath(bytearray(b'foo'), bytearray(b'bar')) + if __name__=="__main__": unittest.main() diff --git a/Lib/test/test_getargs2.py b/Lib/test/test_getargs2.py index 1853a2d..71472cd 100644 --- a/Lib/test/test_getargs2.py +++ b/Lib/test/test_getargs2.py @@ -34,8 +34,8 @@ except ImportError: # > ** Changed from previous "range-and-a-half" to "none"; the # > range-and-a-half checking wasn't particularly useful. # -# Plus a C API or two, e.g. PyInt_AsLongMask() -> -# unsigned long and PyInt_AsLongLongMask() -> unsigned +# Plus a C API or two, e.g. PyLong_AsUnsignedLongMask() -> +# unsigned long and PyLong_AsUnsignedLongLongMask() -> unsigned # long long (if that exists). LARGE = 0x7FFFFFFF @@ -482,7 +482,7 @@ class Bytes_TestCase(unittest.TestCase): def test_s(self): from _testcapi import getargs_s self.assertEqual(getargs_s('abc\xe9'), b'abc\xc3\xa9') - self.assertRaises(TypeError, getargs_s, 'nul:\0') + self.assertRaises(ValueError, getargs_s, 'nul:\0') self.assertRaises(TypeError, getargs_s, b'bytes') self.assertRaises(TypeError, getargs_s, bytearray(b'bytearray')) self.assertRaises(TypeError, getargs_s, memoryview(b'memoryview')) @@ -509,7 +509,7 @@ class Bytes_TestCase(unittest.TestCase): def test_z(self): from _testcapi import getargs_z self.assertEqual(getargs_z('abc\xe9'), b'abc\xc3\xa9') - self.assertRaises(TypeError, getargs_z, 'nul:\0') + self.assertRaises(ValueError, getargs_z, 'nul:\0') self.assertRaises(TypeError, getargs_z, b'bytes') self.assertRaises(TypeError, getargs_z, bytearray(b'bytearray')) self.assertRaises(TypeError, getargs_z, memoryview(b'memoryview')) @@ -537,7 +537,7 @@ class Bytes_TestCase(unittest.TestCase): from _testcapi import getargs_y self.assertRaises(TypeError, getargs_y, 'abc\xe9') self.assertEqual(getargs_y(b'bytes'), b'bytes') - self.assertRaises(TypeError, getargs_y, b'nul:\0') + self.assertRaises(ValueError, getargs_y, b'nul:\0') self.assertRaises(TypeError, getargs_y, bytearray(b'bytearray')) self.assertRaises(TypeError, getargs_y, memoryview(b'memoryview')) self.assertRaises(TypeError, getargs_y, None) @@ -577,7 +577,7 @@ class Unicode_TestCase(unittest.TestCase): def test_u(self): from _testcapi import getargs_u self.assertEqual(getargs_u('abc\xe9'), 'abc\xe9') - self.assertRaises(TypeError, getargs_u, 'nul:\0') + self.assertRaises(ValueError, getargs_u, 'nul:\0') self.assertRaises(TypeError, getargs_u, b'bytes') self.assertRaises(TypeError, getargs_u, bytearray(b'bytearray')) self.assertRaises(TypeError, getargs_u, memoryview(b'memoryview')) @@ -595,7 +595,7 @@ class Unicode_TestCase(unittest.TestCase): def test_Z(self): from _testcapi import getargs_Z self.assertEqual(getargs_Z('abc\xe9'), 'abc\xe9') - self.assertRaises(TypeError, getargs_Z, 'nul:\0') + self.assertRaises(ValueError, getargs_Z, 'nul:\0') self.assertRaises(TypeError, getargs_Z, b'bytes') self.assertRaises(TypeError, getargs_Z, bytearray(b'bytearray')) self.assertRaises(TypeError, getargs_Z, memoryview(b'memoryview')) diff --git a/Lib/test/test_gettext.py b/Lib/test/test_gettext.py index abb312f..c7ceb3f 100644 --- a/Lib/test/test_gettext.py +++ b/Lib/test/test_gettext.py @@ -33,6 +33,55 @@ IHNiZSBsYmhlIENsZ3ViYSBjZWJ0ZW56ZiBvbCBjZWJpdnF2YXQgbmEgdmFncmVzbnByIGdiIGd1 ciBUQUgKdHJnZ3JrZyB6cmZmbnRyIHBuZ255YnQgeXZvZW5lbC4AYmFjb24Ad2luayB3aW5rAA== ''' +# This data contains an invalid major version number (5) +# An unexpected major version number should be treated as an error when +# parsing a .mo file + +GNU_MO_DATA_BAD_MAJOR_VERSION = b'''\ +3hIElQAABQAGAAAAHAAAAEwAAAALAAAAfAAAAAAAAACoAAAAFQAAAKkAAAAjAAAAvwAAAKEAAADj +AAAABwAAAIUBAAALAAAAjQEAAEUBAACZAQAAFgAAAN8CAAAeAAAA9gIAAKEAAAAVAwAABQAAALcD +AAAJAAAAvQMAAAEAAAADAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEAAAABQAAAAYAAAACAAAAAFJh +eW1vbmQgTHV4dXJ5IFlhY2gtdABUaGVyZSBpcyAlcyBmaWxlAFRoZXJlIGFyZSAlcyBmaWxlcwBU +aGlzIG1vZHVsZSBwcm92aWRlcyBpbnRlcm5hdGlvbmFsaXphdGlvbiBhbmQgbG9jYWxpemF0aW9u +CnN1cHBvcnQgZm9yIHlvdXIgUHl0aG9uIHByb2dyYW1zIGJ5IHByb3ZpZGluZyBhbiBpbnRlcmZh +Y2UgdG8gdGhlIEdOVQpnZXR0ZXh0IG1lc3NhZ2UgY2F0YWxvZyBsaWJyYXJ5LgBtdWxsdXNrAG51 +ZGdlIG51ZGdlAFByb2plY3QtSWQtVmVyc2lvbjogMi4wClBPLVJldmlzaW9uLURhdGU6IDIwMDAt +MDgtMjkgMTI6MTktMDQ6MDAKTGFzdC1UcmFuc2xhdG9yOiBKLiBEYXZpZCBJYsOhw7FleiA8ai1k +YXZpZEBub29zLmZyPgpMYW5ndWFnZS1UZWFtOiBYWCA8cHl0aG9uLWRldkBweXRob24ub3JnPgpN +SU1FLVZlcnNpb246IDEuMApDb250ZW50LVR5cGU6IHRleHQvcGxhaW47IGNoYXJzZXQ9aXNvLTg4 +NTktMQpDb250ZW50LVRyYW5zZmVyLUVuY29kaW5nOiBub25lCkdlbmVyYXRlZC1CeTogcHlnZXR0 +ZXh0LnB5IDEuMQpQbHVyYWwtRm9ybXM6IG5wbHVyYWxzPTI7IHBsdXJhbD1uIT0xOwoAVGhyb2F0 +d29iYmxlciBNYW5ncm92ZQBIYXkgJXMgZmljaGVybwBIYXkgJXMgZmljaGVyb3MAR3V2ZiB6YnFo +eXIgY2ViaXZxcmYgdmFncmVhbmd2YmFueXZtbmd2YmEgbmFxIHlicG55dm1uZ3ZiYQpmaGNjYmVn +IHNiZSBsYmhlIENsZ3ViYSBjZWJ0ZW56ZiBvbCBjZWJpdnF2YXQgbmEgdmFncmVzbnByIGdiIGd1 +ciBUQUgKdHJnZ3JrZyB6cmZmbnRyIHBuZ255YnQgeXZvZW5lbC4AYmFjb24Ad2luayB3aW5rAA== +''' + +# This data contains an invalid minor version number (7) +# An unexpected minor version number only indicates that some of the file's +# contents may not be able to be read. It does not indicate an error. + +GNU_MO_DATA_BAD_MINOR_VERSION = b'''\ +3hIElQcAAAAGAAAAHAAAAEwAAAALAAAAfAAAAAAAAACoAAAAFQAAAKkAAAAjAAAAvwAAAKEAAADj +AAAABwAAAIUBAAALAAAAjQEAAEUBAACZAQAAFgAAAN8CAAAeAAAA9gIAAKEAAAAVAwAABQAAALcD +AAAJAAAAvQMAAAEAAAADAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEAAAABQAAAAYAAAACAAAAAFJh +eW1vbmQgTHV4dXJ5IFlhY2gtdABUaGVyZSBpcyAlcyBmaWxlAFRoZXJlIGFyZSAlcyBmaWxlcwBU +aGlzIG1vZHVsZSBwcm92aWRlcyBpbnRlcm5hdGlvbmFsaXphdGlvbiBhbmQgbG9jYWxpemF0aW9u +CnN1cHBvcnQgZm9yIHlvdXIgUHl0aG9uIHByb2dyYW1zIGJ5IHByb3ZpZGluZyBhbiBpbnRlcmZh +Y2UgdG8gdGhlIEdOVQpnZXR0ZXh0IG1lc3NhZ2UgY2F0YWxvZyBsaWJyYXJ5LgBtdWxsdXNrAG51 +ZGdlIG51ZGdlAFByb2plY3QtSWQtVmVyc2lvbjogMi4wClBPLVJldmlzaW9uLURhdGU6IDIwMDAt +MDgtMjkgMTI6MTktMDQ6MDAKTGFzdC1UcmFuc2xhdG9yOiBKLiBEYXZpZCBJYsOhw7FleiA8ai1k +YXZpZEBub29zLmZyPgpMYW5ndWFnZS1UZWFtOiBYWCA8cHl0aG9uLWRldkBweXRob24ub3JnPgpN +SU1FLVZlcnNpb246IDEuMApDb250ZW50LVR5cGU6IHRleHQvcGxhaW47IGNoYXJzZXQ9aXNvLTg4 +NTktMQpDb250ZW50LVRyYW5zZmVyLUVuY29kaW5nOiBub25lCkdlbmVyYXRlZC1CeTogcHlnZXR0 +ZXh0LnB5IDEuMQpQbHVyYWwtRm9ybXM6IG5wbHVyYWxzPTI7IHBsdXJhbD1uIT0xOwoAVGhyb2F0 +d29iYmxlciBNYW5ncm92ZQBIYXkgJXMgZmljaGVybwBIYXkgJXMgZmljaGVyb3MAR3V2ZiB6YnFo +eXIgY2ViaXZxcmYgdmFncmVhbmd2YmFueXZtbmd2YmEgbmFxIHlicG55dm1uZ3ZiYQpmaGNjYmVn +IHNiZSBsYmhlIENsZ3ViYSBjZWJ0ZW56ZiBvbCBjZWJpdnF2YXQgbmEgdmFncmVzbnByIGdiIGd1 +ciBUQUgKdHJnZ3JrZyB6cmZmbnRyIHBuZ255YnQgeXZvZW5lbC4AYmFjb24Ad2luayB3aW5rAA== +''' + + UMO_DATA = b'''\ 3hIElQAAAAACAAAAHAAAACwAAAAFAAAAPAAAAAAAAABQAAAABAAAAFEAAAAPAQAAVgAAAAQAAABm AQAAAQAAAAIAAAAAAAAAAAAAAAAAAAAAYWLDngBQcm9qZWN0LUlkLVZlcnNpb246IDIuMApQTy1S @@ -56,6 +105,8 @@ bGUKR2VuZXJhdGVkLUJ5OiBweWdldHRleHQucHkgMS4zCgA= LOCALEDIR = os.path.join('xx', 'LC_MESSAGES') MOFILE = os.path.join(LOCALEDIR, 'gettext.mo') +MOFILE_BAD_MAJOR_VERSION = os.path.join(LOCALEDIR, 'gettext_bad_major_version.mo') +MOFILE_BAD_MINOR_VERSION = os.path.join(LOCALEDIR, 'gettext_bad_minor_version.mo') UMOFILE = os.path.join(LOCALEDIR, 'ugettext.mo') MMOFILE = os.path.join(LOCALEDIR, 'metadata.mo') @@ -66,6 +117,10 @@ class GettextBaseTest(unittest.TestCase): os.makedirs(LOCALEDIR) with open(MOFILE, 'wb') as fp: fp.write(base64.decodebytes(GNU_MO_DATA)) + with open(MOFILE_BAD_MAJOR_VERSION, 'wb') as fp: + fp.write(base64.decodebytes(GNU_MO_DATA_BAD_MAJOR_VERSION)) + with open(MOFILE_BAD_MINOR_VERSION, 'wb') as fp: + fp.write(base64.decodebytes(GNU_MO_DATA_BAD_MINOR_VERSION)) with open(UMOFILE, 'wb') as fp: fp.write(base64.decodebytes(UMO_DATA)) with open(MMOFILE, 'wb') as fp: @@ -166,6 +221,21 @@ class GettextTestCase2(GettextBaseTest): def test_textdomain(self): self.assertEqual(gettext.textdomain(), 'gettext') + def test_bad_major_version(self): + with open(MOFILE_BAD_MAJOR_VERSION, 'rb') as fp: + with self.assertRaises(OSError) as cm: + gettext.GNUTranslations(fp) + + exception = cm.exception + self.assertEqual(exception.errno, 0) + self.assertEqual(exception.strerror, "Bad version number 5") + self.assertEqual(exception.filename, MOFILE_BAD_MAJOR_VERSION) + + def test_bad_minor_version(self): + with open(MOFILE_BAD_MINOR_VERSION, 'rb') as fp: + # Check that no error is thrown with a bad minor version number + gettext.GNUTranslations(fp) + def test_some_translations(self): eq = self.assertEqual # test some translations diff --git a/Lib/test/test_glob.py b/Lib/test/test_glob.py index a5ab8d6..21b0153 100644 --- a/Lib/test/test_glob.py +++ b/Lib/test/test_glob.py @@ -4,8 +4,8 @@ import shutil import sys import unittest -from test.support import (run_unittest, TESTFN, skip_unless_symlink, - can_symlink, create_empty_file) +from test.support import (TESTFN, skip_unless_symlink, + can_symlink, create_empty_file, change_cwd) class GlobTests(unittest.TestCase): @@ -13,6 +13,9 @@ class GlobTests(unittest.TestCase): def norm(self, *parts): return os.path.normpath(os.path.join(self.tempdir, *parts)) + def joins(self, *tuples): + return [os.path.join(self.tempdir, *parts) for parts in tuples] + def mktemp(self, *parts): filename = self.norm(*parts) base, file = os.path.split(filename) @@ -38,17 +41,17 @@ class GlobTests(unittest.TestCase): def tearDown(self): shutil.rmtree(self.tempdir) - def glob(self, *parts): + def glob(self, *parts, **kwargs): if len(parts) == 1: pattern = parts[0] else: pattern = os.path.join(*parts) p = os.path.join(self.tempdir, pattern) - res = glob.glob(p) - self.assertEqual(list(glob.iglob(p)), res) + res = glob.glob(p, **kwargs) + self.assertEqual(list(glob.iglob(p, **kwargs)), res) bres = [os.fsencode(x) for x in res] - self.assertEqual(glob.glob(os.fsencode(p)), bres) - self.assertEqual(list(glob.iglob(os.fsencode(p))), bres) + self.assertEqual(glob.glob(os.fsencode(p), **kwargs), bres) + self.assertEqual(list(glob.iglob(os.fsencode(p), **kwargs)), bres) return res def assertSequencesEqual_noorder(self, l1, l2): @@ -192,9 +195,118 @@ class GlobTests(unittest.TestCase): check('//?/c:/?', '//?/c:/[?]') check('//*/*/*', '//*/*/[*]') -def test_main(): - run_unittest(GlobTests) + def rglob(self, *parts, **kwargs): + return self.glob(*parts, recursive=True, **kwargs) + + def test_recursive_glob(self): + eq = self.assertSequencesEqual_noorder + full = [('ZZZ',), + ('a',), ('a', 'D'), + ('a', 'bcd'), + ('a', 'bcd', 'EF'), + ('a', 'bcd', 'efg'), + ('a', 'bcd', 'efg', 'ha'), + ('aaa',), ('aaa', 'zzzF'), + ('aab',), ('aab', 'F'), + ] + if can_symlink(): + full += [('sym1',), ('sym2',), + ('sym3',), + ('sym3', 'EF'), + ('sym3', 'efg'), + ('sym3', 'efg', 'ha'), + ] + eq(self.rglob('**'), self.joins(('',), *full)) + eq(self.rglob('.', '**'), self.joins(('.',''), + *(('.',) + i for i in full))) + dirs = [('a', ''), ('a', 'bcd', ''), ('a', 'bcd', 'efg', ''), + ('aaa', ''), ('aab', '')] + if can_symlink(): + dirs += [('sym3', ''), ('sym3', 'efg', '')] + eq(self.rglob('**', ''), self.joins(('',), *dirs)) + + eq(self.rglob('a', '**'), self.joins( + ('a', ''), ('a', 'D'), ('a', 'bcd'), ('a', 'bcd', 'EF'), + ('a', 'bcd', 'efg'), ('a', 'bcd', 'efg', 'ha'))) + eq(self.rglob('a**'), self.joins(('a',), ('aaa',), ('aab',))) + expect = [('a', 'bcd', 'EF')] + if can_symlink(): + expect += [('sym3', 'EF')] + eq(self.rglob('**', 'EF'), self.joins(*expect)) + expect = [('a', 'bcd', 'EF'), ('aaa', 'zzzF'), ('aab', 'F')] + if can_symlink(): + expect += [('sym3', 'EF')] + eq(self.rglob('**', '*F'), self.joins(*expect)) + eq(self.rglob('**', '*F', ''), []) + eq(self.rglob('**', 'bcd', '*'), self.joins( + ('a', 'bcd', 'EF'), ('a', 'bcd', 'efg'))) + eq(self.rglob('a', '**', 'bcd'), self.joins(('a', 'bcd'))) + + predir = os.path.abspath(os.curdir) + try: + os.chdir(self.tempdir) + join = os.path.join + eq(glob.glob('**', recursive=True), [join(*i) for i in full]) + eq(glob.glob(join('**', ''), recursive=True), + [join(*i) for i in dirs]) + eq(glob.glob(join('**','zz*F'), recursive=True), + [join('aaa', 'zzzF')]) + eq(glob.glob('**zz*F', recursive=True), []) + expect = [join('a', 'bcd', 'EF')] + if can_symlink(): + expect += [join('sym3', 'EF')] + eq(glob.glob(join('**', 'EF'), recursive=True), expect) + finally: + os.chdir(predir) + + +@skip_unless_symlink +class SymlinkLoopGlobTests(unittest.TestCase): + + def test_selflink(self): + tempdir = TESTFN + "_dir" + os.makedirs(tempdir) + self.addCleanup(shutil.rmtree, tempdir) + with change_cwd(tempdir): + os.makedirs('dir') + create_empty_file(os.path.join('dir', 'file')) + os.symlink(os.curdir, os.path.join('dir', 'link')) + + results = glob.glob('**', recursive=True) + self.assertEqual(len(results), len(set(results))) + results = set(results) + depth = 0 + while results: + path = os.path.join(*(['dir'] + ['link'] * depth)) + self.assertIn(path, results) + results.remove(path) + if not results: + break + path = os.path.join(path, 'file') + self.assertIn(path, results) + results.remove(path) + depth += 1 + + results = glob.glob(os.path.join('**', 'file'), recursive=True) + self.assertEqual(len(results), len(set(results))) + results = set(results) + depth = 0 + while results: + path = os.path.join(*(['dir'] + ['link'] * depth + ['file'])) + self.assertIn(path, results) + results.remove(path) + depth += 1 + + results = glob.glob(os.path.join('**', ''), recursive=True) + self.assertEqual(len(results), len(set(results))) + results = set(results) + depth = 0 + while results: + path = os.path.join(*(['dir'] + ['link'] * depth + [''])) + self.assertIn(path, results) + results.remove(path) + depth += 1 if __name__ == "__main__": - test_main() + unittest.main() diff --git a/Lib/test/test_grammar.py b/Lib/test/test_grammar.py index 70d85b1..7069fb9 100644 --- a/Lib/test/test_grammar.py +++ b/Lib/test/test_grammar.py @@ -1016,6 +1016,20 @@ class GrammarTests(unittest.TestCase): self.assertFalse((False is 2) is 3) self.assertFalse(False is 2 is 3) + def test_matrix_mul(self): + # This is not intended to be a comprehensive test, rather just to be few + # samples of the @ operator in test_grammar.py. + class M: + def __matmul__(self, o): + return 4 + def __imatmul__(self, o): + self.other = o + return self + m = M() + self.assertEqual(m @ m, 4) + m @= 42 + self.assertEqual(m.other, 42) + def test_main(): run_unittest(TokenTests, GrammarTests) diff --git a/Lib/test/test_heapq.py b/Lib/test/test_heapq.py index b5a2fd8..0dcd8c5 100644 --- a/Lib/test/test_heapq.py +++ b/Lib/test/test_heapq.py @@ -6,14 +6,15 @@ import unittest from test import support from unittest import TestCase, skipUnless +from operator import itemgetter py_heapq = support.import_fresh_module('heapq', blocked=['_heapq']) c_heapq = support.import_fresh_module('heapq', fresh=['_heapq']) # _heapq.nlargest/nsmallest are saved in heapq._nlargest/_smallest when # _heapq is imported, so check them there -func_names = ['heapify', 'heappop', 'heappush', 'heappushpop', - 'heapreplace', '_nlargest', '_nsmallest'] +func_names = ['heapify', 'heappop', 'heappush', 'heappushpop', 'heapreplace', + '_heappop_max', '_heapreplace_max', '_heapify_max'] class TestModules(TestCase): def test_py_functions(self): @@ -152,11 +153,21 @@ class TestHeap: def test_merge(self): inputs = [] - for i in range(random.randrange(5)): - row = sorted(random.randrange(1000) for j in range(random.randrange(10))) + for i in range(random.randrange(25)): + row = [] + for j in range(random.randrange(100)): + tup = random.choice('ABC'), random.randrange(-500, 500) + row.append(tup) inputs.append(row) - self.assertEqual(sorted(chain(*inputs)), list(self.module.merge(*inputs))) - self.assertEqual(list(self.module.merge()), []) + + for key in [None, itemgetter(0), itemgetter(1), itemgetter(1, 0)]: + for reverse in [False, True]: + seqs = [] + for seq in inputs: + seqs.append(sorted(seq, key=key, reverse=reverse)) + self.assertEqual(sorted(chain(*inputs), key=key, reverse=reverse), + list(self.module.merge(*seqs, key=key, reverse=reverse))) + self.assertEqual(list(self.module.merge()), []) def test_merge_does_not_suppress_index_error(self): # Issue 19018: Heapq.merge suppresses IndexError from user generator diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py index 2d771a2..de8f3e8 100644 --- a/Lib/test/test_htmlparser.py +++ b/Lib/test/test_htmlparser.py @@ -85,7 +85,7 @@ class EventCollectorCharrefs(EventCollector): class TestCaseBase(unittest.TestCase): def get_collector(self): - raise NotImplementedError + return EventCollector(convert_charrefs=False) def _run_check(self, source, expected_events, collector=None): if collector is None: @@ -105,21 +105,8 @@ class TestCaseBase(unittest.TestCase): self._run_check(source, events, EventCollectorExtra(convert_charrefs=False)) - def _parse_error(self, source): - def parse(source=source): - parser = self.get_collector() - parser.feed(source) - parser.close() - with self.assertRaises(html.parser.HTMLParseError): - with self.assertWarns(DeprecationWarning): - parse() - -class HTMLParserStrictTestCase(TestCaseBase): - - def get_collector(self): - with support.check_warnings(("", DeprecationWarning), quite=False): - return EventCollector(strict=True, convert_charrefs=False) +class HTMLParserTestCase(TestCaseBase): def test_processing_instruction_only(self): self._run_check("<?processing instruction>", [ @@ -201,9 +188,6 @@ text ("data", "this < text > contains < bare>pointy< brackets"), ]) - def test_illegal_declarations(self): - self._parse_error('<!spacer type="block" height="25">') - def test_starttag_end_boundary(self): self._run_check("""<a b='<'>""", [("starttag", "a", [("b", "<")])]) self._run_check("""<a b='>'>""", [("starttag", "a", [("b", ">")])]) @@ -238,25 +222,6 @@ text self._run_check(["<!--abc--", ">"], output) self._run_check(["<!--abc-->", ""], output) - def test_starttag_junk_chars(self): - self._parse_error("</>") - self._parse_error("</$>") - self._parse_error("</") - self._parse_error("</a") - self._parse_error("<a<a>") - self._parse_error("</a<a>") - self._parse_error("<!") - self._parse_error("<a") - self._parse_error("<a foo='bar'") - self._parse_error("<a foo='bar") - self._parse_error("<a foo='>'") - self._parse_error("<a foo='>") - self._parse_error("<a$>") - self._parse_error("<a$b>") - self._parse_error("<a$b/>") - self._parse_error("<a$b >") - self._parse_error("<a$b />") - def test_valid_doctypes(self): # from http://www.w3.org/QA/2002/04/valid-dtd-list.html dtds = ['HTML', # HTML5 doctype @@ -281,9 +246,6 @@ text self._run_check("<!DOCTYPE %s>" % dtd, [('decl', 'DOCTYPE ' + dtd)]) - def test_declaration_junk_chars(self): - self._parse_error("<!DOCTYPE foo $ >") - def test_startendtag(self): self._run_check("<p/>", [ ("startendtag", "p", []), @@ -384,7 +346,8 @@ text self._run_check(html, expected) def test_convert_charrefs(self): - collector = lambda: EventCollectorCharrefs(convert_charrefs=True) + # default value for convert_charrefs is now True + collector = lambda: EventCollectorCharrefs() self.assertTrue(collector().convert_charrefs) charrefs = ['"', '"', '"', '"', '"', '"'] # check charrefs in the middle of the text/attributes @@ -421,23 +384,8 @@ text self._run_check('no charrefs here', [('data', 'no charrefs here')], collector=collector()) - -class HTMLParserTolerantTestCase(HTMLParserStrictTestCase): - - def get_collector(self): - return EventCollector(convert_charrefs=False) - - def test_deprecation_warnings(self): - with self.assertWarns(DeprecationWarning): - EventCollector() # convert_charrefs not passed explicitly - with self.assertWarns(DeprecationWarning): - EventCollector(strict=True) - with self.assertWarns(DeprecationWarning): - EventCollector(strict=False) - with self.assertRaises(html.parser.HTMLParseError): - with self.assertWarns(DeprecationWarning): - EventCollector().error('test') - + # the remaining tests were for the "tolerant" parser (which is now + # the default), and check various kind of broken markup def test_tolerant_parsing(self): self._run_check('<html <html>te>>xt&a<<bc</a></html>\n' '<img src="URL><//img></html</html>', [ @@ -686,11 +634,7 @@ class HTMLParserTolerantTestCase(HTMLParserStrictTestCase): self._run_check(html, expected) -class AttributesStrictTestCase(TestCaseBase): - - def get_collector(self): - with support.check_warnings(("", DeprecationWarning), quite=False): - return EventCollector(strict=True, convert_charrefs=False) +class AttributesTestCase(TestCaseBase): def test_attr_syntax(self): output = [ @@ -747,12 +691,6 @@ class AttributesStrictTestCase(TestCaseBase): [("starttag", "html", [("foo", "\u20AC&aa&unsupported;")])]) - -class AttributesTolerantTestCase(AttributesStrictTestCase): - - def get_collector(self): - return EventCollector(convert_charrefs=False) - def test_attr_funky_names2(self): self._run_check( "<a $><b $=%><c \=/>", diff --git a/Lib/test/test_http_cookies.py b/Lib/test/test_http_cookies.py index e984252..ee30f17 100644 --- a/Lib/test/test_http_cookies.py +++ b/Lib/test/test_http_cookies.py @@ -141,13 +141,6 @@ class CookieTests(unittest.TestCase): self.assertEqual(C['eggs']['httponly'], 'foo') self.assertEqual(C['eggs']['secure'], 'bar') - def test_bad_attrs(self): - # issue 16611: make sure we don't break backward compatibility. - C = cookies.SimpleCookie() - C.load('cookie=with; invalid; version; second=cookie;') - self.assertEqual(C.output(), - 'Set-Cookie: cookie=with\r\nSet-Cookie: second=cookie') - def test_extra_spaces(self): C = cookies.SimpleCookie() C.load('eggs = scrambled ; secure ; path = bar ; foo=foo ') @@ -182,7 +175,10 @@ class CookieTests(unittest.TestCase): def test_invalid_cookies(self): # Accepting these could be a security issue C = cookies.SimpleCookie() - for s in (']foo=x', '[foo=x', 'blah]foo=x', 'blah[foo=x'): + for s in (']foo=x', '[foo=x', 'blah]foo=x', 'blah[foo=x', + 'Set-Cookie: foo=bar', 'Set-Cookie: foo', + 'foo=bar; baz', 'baz; foo=bar', + 'secure;foo=bar', 'Version=1;foo=bar'): C.load(s) self.assertEqual(dict(C), {}) self.assertEqual(C.output(), '') diff --git a/Lib/test/test_httplib.py b/Lib/test/test_httplib.py index 4c57867..9c1550e 100644 --- a/Lib/test/test_httplib.py +++ b/Lib/test/test_httplib.py @@ -18,6 +18,26 @@ CERT_fakehostname = os.path.join(here, 'keycert2.pem') # Self-signed cert file for self-signed.pythontest.net CERT_selfsigned_pythontestdotnet = os.path.join(here, 'selfsigned_pythontestdotnet.pem') +# constants for testing chunked encoding +chunked_start = ( + 'HTTP/1.1 200 OK\r\n' + 'Transfer-Encoding: chunked\r\n\r\n' + 'a\r\n' + 'hello worl\r\n' + '3\r\n' + 'd! \r\n' + '8\r\n' + 'and now \r\n' + '22\r\n' + 'for something completely different\r\n' +) +chunked_expected = b'hello world! and now for something completely different' +chunk_extension = ";foo=bar" +last_chunk = "0\r\n" +last_chunk_extended = "0" + chunk_extension + "\r\n" +trailers = "X-Dummy: foo\r\nX-Dumm2: bar\r\n" +chunked_end = "\r\n" + HOST = support.HOST class FakeSocket: @@ -50,6 +70,9 @@ class FakeSocket: def close(self): pass + def setsockopt(self, level, optname, value): + pass + class EPipeSocket(FakeSocket): def __init__(self, text, pipe_trigger): @@ -452,20 +475,8 @@ class BasicTest(TestCase): conn.request('POST', 'test', conn) def test_chunked(self): - chunked_start = ( - 'HTTP/1.1 200 OK\r\n' - 'Transfer-Encoding: chunked\r\n\r\n' - 'a\r\n' - 'hello worl\r\n' - '3\r\n' - 'd! \r\n' - '8\r\n' - 'and now \r\n' - '22\r\n' - 'for something completely different\r\n' - ) - expected = b'hello world! and now for something completely different' - sock = FakeSocket(chunked_start + '0\r\n') + expected = chunked_expected + sock = FakeSocket(chunked_start + last_chunk + chunked_end) resp = client.HTTPResponse(sock, method="GET") resp.begin() self.assertEqual(resp.read(), expected) @@ -473,7 +484,7 @@ class BasicTest(TestCase): # Various read sizes for n in range(1, 12): - sock = FakeSocket(chunked_start + '0\r\n') + sock = FakeSocket(chunked_start + last_chunk + chunked_end) resp = client.HTTPResponse(sock, method="GET") resp.begin() self.assertEqual(resp.read(n) + resp.read(n) + resp.read(), expected) @@ -496,23 +507,12 @@ class BasicTest(TestCase): resp.close() def test_readinto_chunked(self): - chunked_start = ( - 'HTTP/1.1 200 OK\r\n' - 'Transfer-Encoding: chunked\r\n\r\n' - 'a\r\n' - 'hello worl\r\n' - '3\r\n' - 'd! \r\n' - '8\r\n' - 'and now \r\n' - '22\r\n' - 'for something completely different\r\n' - ) - expected = b'hello world! and now for something completely different' + + expected = chunked_expected nexpected = len(expected) b = bytearray(128) - sock = FakeSocket(chunked_start + '0\r\n') + sock = FakeSocket(chunked_start + last_chunk + chunked_end) resp = client.HTTPResponse(sock, method="GET") resp.begin() n = resp.readinto(b) @@ -522,7 +522,7 @@ class BasicTest(TestCase): # Various read sizes for n in range(1, 12): - sock = FakeSocket(chunked_start + '0\r\n') + sock = FakeSocket(chunked_start + last_chunk + chunked_end) resp = client.HTTPResponse(sock, method="GET") resp.begin() m = memoryview(b) @@ -558,7 +558,7 @@ class BasicTest(TestCase): '1\r\n' 'd\r\n' ) - sock = FakeSocket(chunked_start + '0\r\n') + sock = FakeSocket(chunked_start + last_chunk + chunked_end) resp = client.HTTPResponse(sock, method="HEAD") resp.begin() self.assertEqual(resp.read(), b'') @@ -578,7 +578,7 @@ class BasicTest(TestCase): '1\r\n' 'd\r\n' ) - sock = FakeSocket(chunked_start + '0\r\n') + sock = FakeSocket(chunked_start + last_chunk + chunked_end) resp = client.HTTPResponse(sock, method="HEAD") resp.begin() b = bytearray(5) @@ -653,6 +653,7 @@ class BasicTest(TestCase): + '0' * 65536 + 'a\r\n' 'hello world\r\n' '0\r\n' + '\r\n' ) resp = client.HTTPResponse(FakeSocket(body)) resp.begin() @@ -670,28 +671,6 @@ class BasicTest(TestCase): resp.close() self.assertTrue(resp.closed) - def test_delayed_ack_opt(self): - # Test that Nagle/delayed_ack optimistaion works correctly. - - # For small payloads, it should coalesce the body with - # headers, resulting in a single sendall() call - conn = client.HTTPConnection('example.com') - sock = FakeSocket(None) - conn.sock = sock - body = b'x' * (conn.mss - 1) - conn.request('POST', '/', body) - self.assertEqual(sock.sendall_calls, 1) - - # For large payloads, it should send the headers and - # then the body, resulting in more than one sendall() - # call - conn = client.HTTPConnection('example.com') - sock = FakeSocket(None) - conn.sock = sock - body = b'x' * conn.mss - conn.request('POST', '/', body) - self.assertGreater(sock.sendall_calls, 1) - def test_error_leak(self): # Test that the socket is not leaked if getresponse() fails conn = client.HTTPConnection('example.com') @@ -708,6 +687,239 @@ class BasicTest(TestCase): self.assertTrue(response.closed) self.assertTrue(conn.sock.file_closed) + def test_chunked_extension(self): + extra = '3;foo=bar\r\n' + 'abc\r\n' + expected = chunked_expected + b'abc' + + sock = FakeSocket(chunked_start + extra + last_chunk_extended + chunked_end) + resp = client.HTTPResponse(sock, method="GET") + resp.begin() + self.assertEqual(resp.read(), expected) + resp.close() + + def test_chunked_missing_end(self): + """some servers may serve up a short chunked encoding stream""" + expected = chunked_expected + sock = FakeSocket(chunked_start + last_chunk) #no terminating crlf + resp = client.HTTPResponse(sock, method="GET") + resp.begin() + self.assertEqual(resp.read(), expected) + resp.close() + + def test_chunked_trailers(self): + """See that trailers are read and ignored""" + expected = chunked_expected + sock = FakeSocket(chunked_start + last_chunk + trailers + chunked_end) + resp = client.HTTPResponse(sock, method="GET") + resp.begin() + self.assertEqual(resp.read(), expected) + # we should have reached the end of the file + self.assertEqual(sock.file.read(100), b"") #we read to the end + resp.close() + + def test_chunked_sync(self): + """Check that we don't read past the end of the chunked-encoding stream""" + expected = chunked_expected + extradata = "extradata" + sock = FakeSocket(chunked_start + last_chunk + trailers + chunked_end + extradata) + resp = client.HTTPResponse(sock, method="GET") + resp.begin() + self.assertEqual(resp.read(), expected) + # the file should now have our extradata ready to be read + self.assertEqual(sock.file.read(100), extradata.encode("ascii")) #we read to the end + resp.close() + + def test_content_length_sync(self): + """Check that we don't read past the end of the Content-Length stream""" + extradata = "extradata" + expected = b"Hello123\r\n" + sock = FakeSocket('HTTP/1.1 200 OK\r\nContent-Length: 10\r\n\r\nHello123\r\n' + extradata) + resp = client.HTTPResponse(sock, method="GET") + resp.begin() + self.assertEqual(resp.read(), expected) + # the file should now have our extradata ready to be read + self.assertEqual(sock.file.read(100), extradata.encode("ascii")) #we read to the end + resp.close() + +class ExtendedReadTest(TestCase): + """ + Test peek(), read1(), readline() + """ + lines = ( + 'HTTP/1.1 200 OK\r\n' + '\r\n' + 'hello world!\n' + 'and now \n' + 'for something completely different\n' + 'foo' + ) + lines_expected = lines[lines.find('hello'):].encode("ascii") + lines_chunked = ( + 'HTTP/1.1 200 OK\r\n' + 'Transfer-Encoding: chunked\r\n\r\n' + 'a\r\n' + 'hello worl\r\n' + '3\r\n' + 'd!\n\r\n' + '9\r\n' + 'and now \n\r\n' + '23\r\n' + 'for something completely different\n\r\n' + '3\r\n' + 'foo\r\n' + '0\r\n' # terminating chunk + '\r\n' # end of trailers + ) + + def setUp(self): + sock = FakeSocket(self.lines) + resp = client.HTTPResponse(sock, method="GET") + resp.begin() + resp.fp = io.BufferedReader(resp.fp) + self.resp = resp + + + + def test_peek(self): + resp = self.resp + # patch up the buffered peek so that it returns not too much stuff + oldpeek = resp.fp.peek + def mypeek(n=-1): + p = oldpeek(n) + if n >= 0: + return p[:n] + return p[:10] + resp.fp.peek = mypeek + + all = [] + while True: + # try a short peek + p = resp.peek(3) + if p: + self.assertGreater(len(p), 0) + # then unbounded peek + p2 = resp.peek() + self.assertGreaterEqual(len(p2), len(p)) + self.assertTrue(p2.startswith(p)) + next = resp.read(len(p2)) + self.assertEqual(next, p2) + else: + next = resp.read() + self.assertFalse(next) + all.append(next) + if not next: + break + self.assertEqual(b"".join(all), self.lines_expected) + + def test_readline(self): + resp = self.resp + self._verify_readline(self.resp.readline, self.lines_expected) + + def _verify_readline(self, readline, expected): + all = [] + while True: + # short readlines + line = readline(5) + if line and line != b"foo": + if len(line) < 5: + self.assertTrue(line.endswith(b"\n")) + all.append(line) + if not line: + break + self.assertEqual(b"".join(all), expected) + + def test_read1(self): + resp = self.resp + def r(): + res = resp.read1(4) + self.assertLessEqual(len(res), 4) + return res + readliner = Readliner(r) + self._verify_readline(readliner.readline, self.lines_expected) + + def test_read1_unbounded(self): + resp = self.resp + all = [] + while True: + data = resp.read1() + if not data: + break + all.append(data) + self.assertEqual(b"".join(all), self.lines_expected) + + def test_read1_bounded(self): + resp = self.resp + all = [] + while True: + data = resp.read1(10) + if not data: + break + self.assertLessEqual(len(data), 10) + all.append(data) + self.assertEqual(b"".join(all), self.lines_expected) + + def test_read1_0(self): + self.assertEqual(self.resp.read1(0), b"") + + def test_peek_0(self): + p = self.resp.peek(0) + self.assertLessEqual(0, len(p)) + +class ExtendedReadTestChunked(ExtendedReadTest): + """ + Test peek(), read1(), readline() in chunked mode + """ + lines = ( + 'HTTP/1.1 200 OK\r\n' + 'Transfer-Encoding: chunked\r\n\r\n' + 'a\r\n' + 'hello worl\r\n' + '3\r\n' + 'd!\n\r\n' + '9\r\n' + 'and now \n\r\n' + '23\r\n' + 'for something completely different\n\r\n' + '3\r\n' + 'foo\r\n' + '0\r\n' # terminating chunk + '\r\n' # end of trailers + ) + + +class Readliner: + """ + a simple readline class that uses an arbitrary read function and buffering + """ + def __init__(self, readfunc): + self.readfunc = readfunc + self.remainder = b"" + + def readline(self, limit): + data = [] + datalen = 0 + read = self.remainder + try: + while True: + idx = read.find(b'\n') + if idx != -1: + break + if datalen + len(read) >= limit: + idx = limit - datalen - 1 + # read more data + data.append(read) + read = self.readfunc() + if not read: + idx = 0 #eof condition + break + idx += 1 + data.append(read[:idx]) + self.remainder = read[idx:] + return b"".join(data) + except: + self.remainder = b"".join(data) + raise + class OfflineTest(TestCase): def test_all(self): @@ -727,13 +939,74 @@ class OfflineTest(TestCase): def test_responses(self): self.assertEqual(client.responses[client.NOT_FOUND], "Not Found") + def test_client_constants(self): + # Make sure we don't break backward compatibility with 3.4 + expected = [ + 'CONTINUE', + 'SWITCHING_PROTOCOLS', + 'PROCESSING', + 'OK', + 'CREATED', + 'ACCEPTED', + 'NON_AUTHORITATIVE_INFORMATION', + 'NO_CONTENT', + 'RESET_CONTENT', + 'PARTIAL_CONTENT', + 'MULTI_STATUS', + 'IM_USED', + 'MULTIPLE_CHOICES', + 'MOVED_PERMANENTLY', + 'FOUND', + 'SEE_OTHER', + 'NOT_MODIFIED', + 'USE_PROXY', + 'TEMPORARY_REDIRECT', + 'BAD_REQUEST', + 'UNAUTHORIZED', + 'PAYMENT_REQUIRED', + 'FORBIDDEN', + 'NOT_FOUND', + 'METHOD_NOT_ALLOWED', + 'NOT_ACCEPTABLE', + 'PROXY_AUTHENTICATION_REQUIRED', + 'REQUEST_TIMEOUT', + 'CONFLICT', + 'GONE', + 'LENGTH_REQUIRED', + 'PRECONDITION_FAILED', + 'REQUEST_ENTITY_TOO_LARGE', + 'REQUEST_URI_TOO_LONG', + 'UNSUPPORTED_MEDIA_TYPE', + 'REQUESTED_RANGE_NOT_SATISFIABLE', + 'EXPECTATION_FAILED', + 'UNPROCESSABLE_ENTITY', + 'LOCKED', + 'FAILED_DEPENDENCY', + 'UPGRADE_REQUIRED', + 'PRECONDITION_REQUIRED', + 'TOO_MANY_REQUESTS', + 'REQUEST_HEADER_FIELDS_TOO_LARGE', + 'INTERNAL_SERVER_ERROR', + 'NOT_IMPLEMENTED', + 'BAD_GATEWAY', + 'SERVICE_UNAVAILABLE', + 'GATEWAY_TIMEOUT', + 'HTTP_VERSION_NOT_SUPPORTED', + 'INSUFFICIENT_STORAGE', + 'NOT_EXTENDED', + 'NETWORK_AUTHENTICATION_REQUIRED', + ] + for const in expected: + with self.subTest(constant=const): + self.assertTrue(hasattr(client, const)) + class SourceAddressTest(TestCase): def setUp(self): self.serv = socket.socket(socket.AF_INET, socket.SOCK_STREAM) self.port = support.bind_port(self.serv) self.source_port = support.find_unused_port() - self.serv.listen(5) + self.serv.listen() self.conn = None def tearDown(self): @@ -765,7 +1038,7 @@ class TimeoutTest(TestCase): def setUp(self): self.serv = socket.socket(socket.AF_INET, socket.SOCK_STREAM) TimeoutTest.PORT = support.bind_port(self.serv) - self.serv.listen(5) + self.serv.listen() def tearDown(self): self.serv.close() @@ -1075,17 +1348,18 @@ class TunnelTests(TestCase): 'HTTP/1.1 200 OK\r\n' # Reply to HEAD 'Content-Length: 42\r\n\r\n' ) - - def create_connection(address, timeout=None, source_address=None): - return FakeSocket(response_text, host=address[0], port=address[1]) - self.host = 'proxy.com' self.conn = client.HTTPConnection(self.host) - self.conn._create_connection = create_connection + self.conn._create_connection = self._create_connection(response_text) def tearDown(self): self.conn.close() + def _create_connection(self, response_text): + def create_connection(address, timeout=None, source_address=None): + return FakeSocket(response_text, host=address[0], port=address[1]) + return create_connection + def test_set_tunnel_host_port_headers(self): tunnel_host = 'destination.com' tunnel_port = 8888 @@ -1126,13 +1400,26 @@ class TunnelTests(TestCase): self.assertIn(b'CONNECT destination.com', self.conn.sock.data) self.assertIn(b'Host: destination.com', self.conn.sock.data) + def test_tunnel_debuglog(self): + expected_header = 'X-Dummy: 1' + response_text = 'HTTP/1.0 200 OK\r\n{}\r\n\r\n'.format(expected_header) + + self.conn.set_debuglevel(1) + self.conn._create_connection = self._create_connection(response_text) + self.conn.set_tunnel('destination.com') + + with support.captured_stdout() as output: + self.conn.request('PUT', '/', '') + lines = output.getvalue().splitlines() + self.assertIn('header: {}'.format(expected_header), lines) @support.reap_threads def test_main(verbose=None): support.run_unittest(HeaderTests, OfflineTest, BasicTest, TimeoutTest, HTTPSTest, RequestBodyTest, SourceAddressTest, - HTTPResponseTest, TunnelTests) + HTTPResponseTest, ExtendedReadTest, + ExtendedReadTestChunked, TunnelTests) if __name__ == '__main__': test_main() diff --git a/Lib/test/test_imaplib.py b/Lib/test/test_imaplib.py index b34e652..5485a2a 100644 --- a/Lib/test/test_imaplib.py +++ b/Lib/test/test_imaplib.py @@ -11,7 +11,8 @@ import socketserver import time import calendar -from test.support import reap_threads, verbose, transient_internet, run_with_tz, run_with_locale +from test.support import (reap_threads, verbose, transient_internet, + run_with_tz, run_with_locale) import unittest from datetime import datetime, timezone, timedelta try: @@ -19,8 +20,8 @@ try: except ImportError: ssl = None -CERTFILE = None -CAFILE = None +CERTFILE = os.path.join(os.path.dirname(__file__) or os.curdir, "keycert3.pem") +CAFILE = os.path.join(os.path.dirname(__file__) or os.curdir, "pycacert.pem") class TestImaplib(unittest.TestCase): @@ -41,17 +42,15 @@ class TestImaplib(unittest.TestCase): def test_Internaldate2tuple_issue10941(self): self.assertNotEqual(imaplib.Internaldate2tuple( b'25 (INTERNALDATE "02-Apr-2000 02:30:00 +0000")'), - imaplib.Internaldate2tuple( - b'25 (INTERNALDATE "02-Apr-2000 03:30:00 +0000")')) - - + imaplib.Internaldate2tuple( + b'25 (INTERNALDATE "02-Apr-2000 03:30:00 +0000")')) def timevalues(self): return [2000000000, 2000000000.0, time.localtime(2000000000), (2033, 5, 18, 5, 33, 20, -1, -1, -1), (2033, 5, 18, 5, 33, 20, -1, -1, 1), datetime.fromtimestamp(2000000000, - timezone(timedelta(0, 2*60*60))), + timezone(timedelta(0, 2 * 60 * 60))), '"18-May-2033 05:33:20 +0200"'] @run_with_locale('LC_ALL', 'de_DE', 'fr_FR') @@ -72,7 +71,6 @@ class TestImaplib(unittest.TestCase): if ssl: - class SecureTCPServer(socketserver.TCPServer): def get_request(self): @@ -93,13 +91,17 @@ else: class SimpleIMAPHandler(socketserver.StreamRequestHandler): - timeout = 1 continuation = None capabilities = '' + def setup(self): + super().setup() + self.server.logged = None + def _send(self, message): - if verbose: print("SENT: %r" % message.strip()) + if verbose: + print("SENT: %r" % message.strip()) self.wfile.write(message) def _send_line(self, message): @@ -132,7 +134,8 @@ class SimpleIMAPHandler(socketserver.StreamRequestHandler): if line.endswith(b'\r\n'): break - if verbose: print('GOT: %r' % line.strip()) + if verbose: + print('GOT: %r' % line.strip()) if self.continuation: try: self.continuation.send(line) @@ -144,8 +147,8 @@ class SimpleIMAPHandler(socketserver.StreamRequestHandler): cmd = splitline[1] args = splitline[2:] - if hasattr(self, 'cmd_'+cmd): - continuation = getattr(self, 'cmd_'+cmd)(tag, args) + if hasattr(self, 'cmd_' + cmd): + continuation = getattr(self, 'cmd_' + cmd)(tag, args) if continuation: self.continuation = continuation next(continuation) @@ -153,16 +156,25 @@ class SimpleIMAPHandler(socketserver.StreamRequestHandler): self._send_tagged(tag, 'BAD', cmd + ' unknown') def cmd_CAPABILITY(self, tag, args): - caps = 'IMAP4rev1 ' + self.capabilities if self.capabilities else 'IMAP4rev1' + caps = ('IMAP4rev1 ' + self.capabilities + if self.capabilities + else 'IMAP4rev1') self._send_textline('* CAPABILITY ' + caps) self._send_tagged(tag, 'OK', 'CAPABILITY completed') def cmd_LOGOUT(self, tag, args): + self.server.logged = None self._send_textline('* BYE IMAP4ref1 Server logging out') self._send_tagged(tag, 'OK', 'LOGOUT completed') + def cmd_LOGIN(self, tag, args): + self.server.logged = args[0] + self._send_tagged(tag, 'OK', 'LOGIN completed') -class BaseThreadedNetworkedTests(unittest.TestCase): + +class ThreadedNetworkedTests(unittest.TestCase): + server_class = socketserver.TCPServer + imap_class = imaplib.IMAP4 def make_server(self, addr, hdlr): @@ -172,7 +184,8 @@ class BaseThreadedNetworkedTests(unittest.TestCase): self.server_close() raise - if verbose: print("creating server") + if verbose: + print("creating server") server = MyServer(addr, hdlr) self.assertEqual(server.server_address, server.socket.getsockname()) @@ -188,18 +201,21 @@ class BaseThreadedNetworkedTests(unittest.TestCase): # Short poll interval to make the test finish quickly. # Time between requests is short enough that we won't wake # up spuriously too many times. - kwargs={'poll_interval':0.01}) + kwargs={'poll_interval': 0.01}) t.daemon = True # In case this function raises. t.start() - if verbose: print("server running") + if verbose: + print("server running") return server, t def reap_server(self, server, thread): - if verbose: print("waiting for server") + if verbose: + print("waiting for server") server.shutdown() server.server_close() thread.join() - if verbose: print("done") + if verbose: + print("done") @contextmanager def reaped_server(self, hdlr): @@ -256,7 +272,7 @@ class BaseThreadedNetworkedTests(unittest.TestCase): def cmd_AUTHENTICATE(self, tag, args): self._send_tagged(tag, 'NO', 'unrecognized authentication ' - 'type {}'.format(args[0])) + 'type {}'.format(args[0])) with self.reaped_pair(MyServer) as (server, client): with self.assertRaises(imaplib.IMAP4.error): @@ -290,13 +306,13 @@ class BaseThreadedNetworkedTests(unittest.TestCase): code, data = client.authenticate('MYAUTH', lambda x: b'fake') self.assertEqual(code, 'OK') self.assertEqual(server.response, - b'ZmFrZQ==\r\n') #b64 encoded 'fake' + b'ZmFrZQ==\r\n') # b64 encoded 'fake' with self.reaped_pair(MyServer) as (server, client): code, data = client.authenticate('MYAUTH', lambda x: 'fake') self.assertEqual(code, 'OK') self.assertEqual(server.response, - b'ZmFrZQ==\r\n') #b64 encoded 'fake' + b'ZmFrZQ==\r\n') # b64 encoded 'fake' @reap_threads def test_login_cram_md5(self): @@ -307,9 +323,10 @@ class BaseThreadedNetworkedTests(unittest.TestCase): def cmd_AUTHENTICATE(self, tag, args): self._send_textline('+ PDE4OTYuNjk3MTcwOTUyQHBvc3RvZmZpY2Uucm' - 'VzdG9uLm1jaS5uZXQ=') + 'VzdG9uLm1jaS5uZXQ=') r = yield - if r == b'dGltIGYxY2E2YmU0NjRiOWVmYTFjY2E2ZmZkNmNmMmQ5ZjMy\r\n': + if (r == b'dGltIGYxY2E2YmU0NjRiOWVmYT' + b'FjY2E2ZmZkNmNmMmQ5ZjMy\r\n'): self._send_tagged(tag, 'OK', 'CRAM-MD5 successful') else: self._send_tagged(tag, 'NO', 'No access') @@ -324,27 +341,45 @@ class BaseThreadedNetworkedTests(unittest.TestCase): ret, data = client.login_cram_md5("tim", b"tanstaaftanstaaf") self.assertEqual(ret, "OK") - def test_linetoolong(self): class TooLongHandler(SimpleIMAPHandler): def handle(self): # Send a very long response line - self.wfile.write(b'* OK ' + imaplib._MAXLINE*b'x' + b'\r\n') + self.wfile.write(b'* OK ' + imaplib._MAXLINE * b'x' + b'\r\n') with self.reaped_server(TooLongHandler) as server: self.assertRaises(imaplib.IMAP4.error, self.imap_class, *server.server_address) + @reap_threads + def test_simple_with_statement(self): + # simplest call + with self.reaped_server(SimpleIMAPHandler) as server: + with self.imap_class(*server.server_address): + pass -class ThreadedNetworkedTests(BaseThreadedNetworkedTests): + @reap_threads + def test_with_statement(self): + with self.reaped_server(SimpleIMAPHandler) as server: + with self.imap_class(*server.server_address) as imap: + imap.login('user', 'pass') + self.assertEqual(server.logged, 'user') + self.assertIsNone(server.logged) - server_class = socketserver.TCPServer - imap_class = imaplib.IMAP4 + @reap_threads + def test_with_statement_logout(self): + # what happens if already logout in the block? + with self.reaped_server(SimpleIMAPHandler) as server: + with self.imap_class(*server.server_address) as imap: + imap.login('user', 'pass') + self.assertEqual(server.logged, 'user') + imap.logout() + self.assertIsNone(server.logged) + self.assertIsNone(server.logged) @unittest.skipUnless(ssl, "SSL not available") -class ThreadedNetworkedTestsSSL(BaseThreadedNetworkedTests): - +class ThreadedNetworkedTestsSSL(ThreadedNetworkedTests): server_class = SecureTCPServer imap_class = IMAP4_SSL @@ -355,8 +390,9 @@ class ThreadedNetworkedTestsSSL(BaseThreadedNetworkedTests): ssl_context.check_hostname = True ssl_context.load_verify_locations(CAFILE) - with self.assertRaisesRegex(ssl.CertificateError, - "hostname '127.0.0.1' doesn't match 'localhost'"): + with self.assertRaisesRegex( + ssl.CertificateError, + "hostname '127.0.0.1' doesn't match 'localhost'"): with self.reaped_server(SimpleIMAPHandler) as server: client = self.imap_class(*server.server_address, ssl_context=ssl_context) @@ -368,6 +404,8 @@ class ThreadedNetworkedTestsSSL(BaseThreadedNetworkedTests): client.shutdown() +@unittest.skipUnless( + support.is_resource_enabled('network'), 'network resource disabled') class RemoteIMAPTest(unittest.TestCase): host = 'cyrus.andrew.cmu.edu' port = 143 @@ -401,6 +439,8 @@ class RemoteIMAPTest(unittest.TestCase): @unittest.skipUnless(ssl, "SSL not available") +@unittest.skipUnless( + support.is_resource_enabled('network'), 'network resource disabled') class RemoteIMAP_STARTTLSTest(RemoteIMAPTest): def setUp(self): @@ -454,7 +494,8 @@ class RemoteIMAP_SSLTest(RemoteIMAPTest): def test_logincapa_with_client_ssl_context(self): with transient_internet(self.host): - _server = self.imap_class(self.host, self.port, ssl_context=self.create_ssl_context()) + _server = self.imap_class( + self.host, self.port, ssl_context=self.create_ssl_context()) self.check_logincapa(_server) def test_logout(self): @@ -465,35 +506,15 @@ class RemoteIMAP_SSLTest(RemoteIMAPTest): def test_ssl_context_certfile_exclusive(self): with transient_internet(self.host): - self.assertRaises(ValueError, self.imap_class, self.host, self.port, - certfile=CERTFILE, ssl_context=self.create_ssl_context()) + self.assertRaises( + ValueError, self.imap_class, self.host, self.port, + certfile=CERTFILE, ssl_context=self.create_ssl_context()) def test_ssl_context_keyfile_exclusive(self): with transient_internet(self.host): - self.assertRaises(ValueError, self.imap_class, self.host, self.port, - keyfile=CERTFILE, ssl_context=self.create_ssl_context()) - - -def load_tests(*args): - tests = [TestImaplib] - - if support.is_resource_enabled('network'): - if ssl: - global CERTFILE, CAFILE - CERTFILE = os.path.join(os.path.dirname(__file__) or os.curdir, - "keycert3.pem") - if not os.path.exists(CERTFILE): - raise support.TestFailed("Can't read certificate files!") - CAFILE = os.path.join(os.path.dirname(__file__) or os.curdir, - "pycacert.pem") - if not os.path.exists(CAFILE): - raise support.TestFailed("Can't read CA file!") - tests.extend([ - ThreadedNetworkedTests, ThreadedNetworkedTestsSSL, - RemoteIMAPTest, RemoteIMAP_SSLTest, RemoteIMAP_STARTTLSTest, - ]) - - return unittest.TestSuite([unittest.makeSuite(test) for test in tests]) + self.assertRaises( + ValueError, self.imap_class, self.host, self.port, + keyfile=CERTFILE, ssl_context=self.create_ssl_context()) if __name__ == "__main__": diff --git a/Lib/test/test_imghdr.py b/Lib/test/test_imghdr.py index 0ad4343..b54daf8 100644 --- a/Lib/test/test_imghdr.py +++ b/Lib/test/test_imghdr.py @@ -16,7 +16,9 @@ TEST_FILES = ( ('python.ras', 'rast'), ('python.sgi', 'rgb'), ('python.tiff', 'tiff'), - ('python.xbm', 'xbm') + ('python.xbm', 'xbm'), + ('python.webp', 'webp'), + ('python.exr', 'exr'), ) class UnseekableIO(io.FileIO): diff --git a/Lib/test/test_import.py b/Lib/test/test_import/__init__.py index b4842c5..fd21fa2 100644 --- a/Lib/test/test_import.py +++ b/Lib/test/test_import/__init__.py @@ -568,7 +568,7 @@ class RelativeImportTests(unittest.TestCase): def test_relimport_star(self): # This will import * from .test_import. - from . import relimport + from .. import relimport self.assertTrue(hasattr(relimport, "RelativeImportTests")) def test_issue3221(self): @@ -1068,6 +1068,46 @@ class ImportTracebackTests(unittest.TestCase): __isolated=False) +class CircularImportTests(unittest.TestCase): + + """See the docstrings of the modules being imported for the purpose of the + test.""" + + def tearDown(self): + """Make sure no modules pre-exist in sys.modules which are being used to + test.""" + for key in list(sys.modules.keys()): + if key.startswith('test.test_import.data.circular_imports'): + del sys.modules[key] + + def test_direct(self): + try: + import test.test_import.data.circular_imports.basic + except ImportError: + self.fail('circular import through relative imports failed') + + def test_indirect(self): + try: + import test.test_import.data.circular_imports.indirect + except ImportError: + self.fail('relative import in module contributing to circular ' + 'import failed') + + def test_subpackage(self): + try: + import test.test_import.data.circular_imports.subpackage + except ImportError: + self.fail('circular import involving a subpackage failed') + + def test_rebinding(self): + try: + import test.test_import.data.circular_imports.rebinding as rebinding + except ImportError: + self.fail('circular import with rebinding of module attribute failed') + from test.test_import.data.circular_imports.subpkg import util + self.assertIs(util.util, rebinding.util) + + if __name__ == '__main__': # Test needs to be a package, so we can do relative imports. unittest.main() diff --git a/Lib/test/test_import/__main__.py b/Lib/test/test_import/__main__.py new file mode 100644 index 0000000..24f02a1 --- /dev/null +++ b/Lib/test/test_import/__main__.py @@ -0,0 +1,3 @@ +import unittest + +unittest.main('test.test_import') diff --git a/Lib/test/test_import/data/circular_imports/basic.py b/Lib/test/test_import/data/circular_imports/basic.py new file mode 100644 index 0000000..3e41e39 --- /dev/null +++ b/Lib/test/test_import/data/circular_imports/basic.py @@ -0,0 +1,2 @@ +"""Circular imports through direct, relative imports.""" +from . import basic2 diff --git a/Lib/test/test_import/data/circular_imports/basic2.py b/Lib/test/test_import/data/circular_imports/basic2.py new file mode 100644 index 0000000..00bd2f2 --- /dev/null +++ b/Lib/test/test_import/data/circular_imports/basic2.py @@ -0,0 +1 @@ +from . import basic diff --git a/Lib/test/test_import/data/circular_imports/indirect.py b/Lib/test/test_import/data/circular_imports/indirect.py new file mode 100644 index 0000000..6925788 --- /dev/null +++ b/Lib/test/test_import/data/circular_imports/indirect.py @@ -0,0 +1 @@ +from . import basic, basic2 diff --git a/Lib/test/test_import/data/circular_imports/rebinding.py b/Lib/test/test_import/data/circular_imports/rebinding.py new file mode 100644 index 0000000..2b77375 --- /dev/null +++ b/Lib/test/test_import/data/circular_imports/rebinding.py @@ -0,0 +1,3 @@ +"""Test the binding of names when a circular import shares the same name as an +attribute.""" +from .rebinding2 import util diff --git a/Lib/test/test_import/data/circular_imports/rebinding2.py b/Lib/test/test_import/data/circular_imports/rebinding2.py new file mode 100644 index 0000000..57a9e69 --- /dev/null +++ b/Lib/test/test_import/data/circular_imports/rebinding2.py @@ -0,0 +1,3 @@ +from .subpkg import util +from . import rebinding +util = util.util diff --git a/Lib/test/test_import/data/circular_imports/subpackage.py b/Lib/test/test_import/data/circular_imports/subpackage.py new file mode 100644 index 0000000..7b412f7 --- /dev/null +++ b/Lib/test/test_import/data/circular_imports/subpackage.py @@ -0,0 +1,2 @@ +"""Circular import involving a sub-package.""" +from .subpkg import subpackage2 diff --git a/Lib/test/test_import/data/circular_imports/subpkg/subpackage2.py b/Lib/test/test_import/data/circular_imports/subpkg/subpackage2.py new file mode 100644 index 0000000..17b893a --- /dev/null +++ b/Lib/test/test_import/data/circular_imports/subpkg/subpackage2.py @@ -0,0 +1,2 @@ +#from .util import util +from .. import subpackage diff --git a/Lib/test/test_import/data/circular_imports/subpkg/util.py b/Lib/test/test_import/data/circular_imports/subpkg/util.py new file mode 100644 index 0000000..343bd84 --- /dev/null +++ b/Lib/test/test_import/data/circular_imports/subpkg/util.py @@ -0,0 +1,2 @@ +def util(): + pass diff --git a/Lib/test/test_import/data/circular_imports/util.py b/Lib/test/test_import/data/circular_imports/util.py new file mode 100644 index 0000000..343bd84 --- /dev/null +++ b/Lib/test/test_import/data/circular_imports/util.py @@ -0,0 +1,2 @@ +def util(): + pass diff --git a/Lib/test/test_importlib/builtin/test_finder.py b/Lib/test/test_importlib/builtin/test_finder.py index 934562f..a2e6e1e 100644 --- a/Lib/test/test_importlib/builtin/test_finder.py +++ b/Lib/test/test_importlib/builtin/test_finder.py @@ -1,21 +1,21 @@ from .. import abc from .. import util -from . import util as builtin_util -frozen_machinery, source_machinery = util.import_importlib('importlib.machinery') +machinery = util.import_importlib('importlib.machinery') import sys import unittest +@unittest.skipIf(util.BUILTINS.good_name is None, 'no reasonable builtin module') class FindSpecTests(abc.FinderTests): """Test find_spec() for built-in modules.""" def test_module(self): # Common case. - with util.uncache(builtin_util.NAME): - found = self.machinery.BuiltinImporter.find_spec(builtin_util.NAME) + with util.uncache(util.BUILTINS.good_name): + found = self.machinery.BuiltinImporter.find_spec(util.BUILTINS.good_name) self.assertTrue(found) self.assertEqual(found.origin, 'built-in') @@ -39,23 +39,26 @@ class FindSpecTests(abc.FinderTests): def test_ignore_path(self): # The value for 'path' should always trigger a failed import. - with util.uncache(builtin_util.NAME): - spec = self.machinery.BuiltinImporter.find_spec(builtin_util.NAME, + with util.uncache(util.BUILTINS.good_name): + spec = self.machinery.BuiltinImporter.find_spec(util.BUILTINS.good_name, ['pkg']) self.assertIsNone(spec) -Frozen_FindSpecTests, Source_FindSpecTests = util.test_both(FindSpecTests, - machinery=[frozen_machinery, source_machinery]) +(Frozen_FindSpecTests, + Source_FindSpecTests + ) = util.test_both(FindSpecTests, machinery=machinery) + +@unittest.skipIf(util.BUILTINS.good_name is None, 'no reasonable builtin module') class FinderTests(abc.FinderTests): """Test find_module() for built-in modules.""" def test_module(self): # Common case. - with util.uncache(builtin_util.NAME): - found = self.machinery.BuiltinImporter.find_module(builtin_util.NAME) + with util.uncache(util.BUILTINS.good_name): + found = self.machinery.BuiltinImporter.find_module(util.BUILTINS.good_name) self.assertTrue(found) self.assertTrue(hasattr(found, 'load_module')) @@ -72,13 +75,15 @@ class FinderTests(abc.FinderTests): def test_ignore_path(self): # The value for 'path' should always trigger a failed import. - with util.uncache(builtin_util.NAME): - loader = self.machinery.BuiltinImporter.find_module(builtin_util.NAME, + with util.uncache(util.BUILTINS.good_name): + loader = self.machinery.BuiltinImporter.find_module(util.BUILTINS.good_name, ['pkg']) self.assertIsNone(loader) -Frozen_FinderTests, Source_FinderTests = util.test_both(FinderTests, - machinery=[frozen_machinery, source_machinery]) + +(Frozen_FinderTests, + Source_FinderTests + ) = util.test_both(FinderTests, machinery=machinery) if __name__ == '__main__': diff --git a/Lib/test/test_importlib/builtin/test_loader.py b/Lib/test/test_importlib/builtin/test_loader.py index 1f83574..1684ab6 100644 --- a/Lib/test/test_importlib/builtin/test_loader.py +++ b/Lib/test/test_importlib/builtin/test_loader.py @@ -1,14 +1,13 @@ from .. import abc from .. import util -from . import util as builtin_util -frozen_machinery, source_machinery = util.import_importlib('importlib.machinery') +machinery = util.import_importlib('importlib.machinery') import sys import types import unittest - +@unittest.skipIf(util.BUILTINS.good_name is None, 'no reasonable builtin module') class LoaderTests(abc.LoaderTests): """Test load_module() for built-in modules.""" @@ -29,8 +28,8 @@ class LoaderTests(abc.LoaderTests): def test_module(self): # Common case. - with util.uncache(builtin_util.NAME): - module = self.load_module(builtin_util.NAME) + with util.uncache(util.BUILTINS.good_name): + module = self.load_module(util.BUILTINS.good_name) self.verify(module) # Built-in modules cannot be a package. @@ -41,9 +40,9 @@ class LoaderTests(abc.LoaderTests): def test_module_reuse(self): # Test that the same module is used in a reload. - with util.uncache(builtin_util.NAME): - module1 = self.load_module(builtin_util.NAME) - module2 = self.load_module(builtin_util.NAME) + with util.uncache(util.BUILTINS.good_name): + module1 = self.load_module(util.BUILTINS.good_name) + module2 = self.load_module(util.BUILTINS.good_name) self.assertIs(module1, module2) def test_unloadable(self): @@ -66,40 +65,44 @@ class LoaderTests(abc.LoaderTests): self.assertEqual(cm.exception.name, module_name) -Frozen_LoaderTests, Source_LoaderTests = util.test_both(LoaderTests, - machinery=[frozen_machinery, source_machinery]) +(Frozen_LoaderTests, + Source_LoaderTests + ) = util.test_both(LoaderTests, machinery=machinery) +@unittest.skipIf(util.BUILTINS.good_name is None, 'no reasonable builtin module') class InspectLoaderTests: """Tests for InspectLoader methods for BuiltinImporter.""" def test_get_code(self): # There is no code object. - result = self.machinery.BuiltinImporter.get_code(builtin_util.NAME) + result = self.machinery.BuiltinImporter.get_code(util.BUILTINS.good_name) self.assertIsNone(result) def test_get_source(self): # There is no source. - result = self.machinery.BuiltinImporter.get_source(builtin_util.NAME) + result = self.machinery.BuiltinImporter.get_source(util.BUILTINS.good_name) self.assertIsNone(result) def test_is_package(self): # Cannot be a package. - result = self.machinery.BuiltinImporter.is_package(builtin_util.NAME) + result = self.machinery.BuiltinImporter.is_package(util.BUILTINS.good_name) self.assertFalse(result) + @unittest.skipIf(util.BUILTINS.bad_name is None, 'all modules are built in') def test_not_builtin(self): # Modules not built-in should raise ImportError. for meth_name in ('get_code', 'get_source', 'is_package'): method = getattr(self.machinery.BuiltinImporter, meth_name) with self.assertRaises(ImportError) as cm: - method(builtin_util.BAD_NAME) - self.assertRaises(builtin_util.BAD_NAME) + method(util.BUILTINS.bad_name) + self.assertRaises(util.BUILTINS.bad_name) + -Frozen_InspectLoaderTests, Source_InspectLoaderTests = util.test_both( - InspectLoaderTests, - machinery=[frozen_machinery, source_machinery]) +(Frozen_InspectLoaderTests, + Source_InspectLoaderTests + ) = util.test_both(InspectLoaderTests, machinery=machinery) if __name__ == '__main__': diff --git a/Lib/test/test_importlib/builtin/util.py b/Lib/test/test_importlib/builtin/util.py deleted file mode 100644 index 5704699..0000000 --- a/Lib/test/test_importlib/builtin/util.py +++ /dev/null @@ -1,7 +0,0 @@ -import sys - -assert 'errno' in sys.builtin_module_names -NAME = 'errno' - -assert 'importlib' not in sys.builtin_module_names -BAD_NAME = 'importlib' diff --git a/Lib/test/test_importlib/extension/test_case_sensitivity.py b/Lib/test/test_importlib/extension/test_case_sensitivity.py index bb2528e..c7d6ca6 100644 --- a/Lib/test/test_importlib/extension/test_case_sensitivity.py +++ b/Lib/test/test_importlib/extension/test_case_sensitivity.py @@ -4,22 +4,21 @@ from test import support import unittest from .. import util -from . import util as ext_util -frozen_machinery, source_machinery = util.import_importlib('importlib.machinery') +machinery = util.import_importlib('importlib.machinery') # XXX find_spec tests -@unittest.skipIf(ext_util.FILENAME is None, '_testcapi not available') +@unittest.skipIf(util.EXTENSIONS.filename is None, '_testcapi not available') @util.case_insensitive_tests class ExtensionModuleCaseSensitivityTest: def find_module(self): - good_name = ext_util.NAME + good_name = util.EXTENSIONS.name bad_name = good_name.upper() assert good_name != bad_name - finder = self.machinery.FileFinder(ext_util.PATH, + finder = self.machinery.FileFinder(util.EXTENSIONS.path, (self.machinery.ExtensionFileLoader, self.machinery.EXTENSION_SUFFIXES)) return finder.find_module(bad_name) @@ -42,9 +41,10 @@ class ExtensionModuleCaseSensitivityTest: loader = self.find_module() self.assertTrue(hasattr(loader, 'load_module')) -Frozen_ExtensionCaseSensitivity, Source_ExtensionCaseSensitivity = util.test_both( - ExtensionModuleCaseSensitivityTest, - machinery=[frozen_machinery, source_machinery]) + +(Frozen_ExtensionCaseSensitivity, + Source_ExtensionCaseSensitivity + ) = util.test_both(ExtensionModuleCaseSensitivityTest, machinery=machinery) if __name__ == '__main__': diff --git a/Lib/test/test_importlib/extension/test_finder.py b/Lib/test/test_importlib/extension/test_finder.py index 990f29c..71bf67f 100644 --- a/Lib/test/test_importlib/extension/test_finder.py +++ b/Lib/test/test_importlib/extension/test_finder.py @@ -1,8 +1,7 @@ from .. import abc -from .. import util as test_util -from . import util +from .. import util -machinery = test_util.import_importlib('importlib.machinery') +machinery = util.import_importlib('importlib.machinery') import unittest import warnings @@ -14,7 +13,7 @@ class FinderTests(abc.FinderTests): """Test the finder for extension modules.""" def find_module(self, fullname): - importer = self.machinery.FileFinder(util.PATH, + importer = self.machinery.FileFinder(util.EXTENSIONS.path, (self.machinery.ExtensionFileLoader, self.machinery.EXTENSION_SUFFIXES)) with warnings.catch_warnings(): @@ -22,7 +21,7 @@ class FinderTests(abc.FinderTests): return importer.find_module(fullname) def test_module(self): - self.assertTrue(self.find_module(util.NAME)) + self.assertTrue(self.find_module(util.EXTENSIONS.name)) # No extension module as an __init__ available for testing. test_package = test_package_in_package = None @@ -36,8 +35,10 @@ class FinderTests(abc.FinderTests): def test_failure(self): self.assertIsNone(self.find_module('asdfjkl;')) -Frozen_FinderTests, Source_FinderTests = test_util.test_both( - FinderTests, machinery=machinery) + +(Frozen_FinderTests, + Source_FinderTests + ) = util.test_both(FinderTests, machinery=machinery) if __name__ == '__main__': diff --git a/Lib/test/test_importlib/extension/test_loader.py b/Lib/test/test_importlib/extension/test_loader.py index fd9abf2..aefd050 100644 --- a/Lib/test/test_importlib/extension/test_loader.py +++ b/Lib/test/test_importlib/extension/test_loader.py @@ -1,4 +1,3 @@ -from . import util as ext_util from .. import abc from .. import util @@ -15,8 +14,8 @@ class LoaderTests(abc.LoaderTests): """Test load_module() for extension modules.""" def setUp(self): - self.loader = self.machinery.ExtensionFileLoader(ext_util.NAME, - ext_util.FILEPATH) + self.loader = self.machinery.ExtensionFileLoader(util.EXTENSIONS.name, + util.EXTENSIONS.file_path) def load_module(self, fullname): return self.loader.load_module(fullname) @@ -29,23 +28,23 @@ class LoaderTests(abc.LoaderTests): self.load_module('XXX') def test_equality(self): - other = self.machinery.ExtensionFileLoader(ext_util.NAME, - ext_util.FILEPATH) + other = self.machinery.ExtensionFileLoader(util.EXTENSIONS.name, + util.EXTENSIONS.file_path) self.assertEqual(self.loader, other) def test_inequality(self): - other = self.machinery.ExtensionFileLoader('_' + ext_util.NAME, - ext_util.FILEPATH) + other = self.machinery.ExtensionFileLoader('_' + util.EXTENSIONS.name, + util.EXTENSIONS.file_path) self.assertNotEqual(self.loader, other) def test_module(self): - with util.uncache(ext_util.NAME): - module = self.load_module(ext_util.NAME) - for attr, value in [('__name__', ext_util.NAME), - ('__file__', ext_util.FILEPATH), + with util.uncache(util.EXTENSIONS.name): + module = self.load_module(util.EXTENSIONS.name) + for attr, value in [('__name__', util.EXTENSIONS.name), + ('__file__', util.EXTENSIONS.file_path), ('__package__', '')]: self.assertEqual(getattr(module, attr), value) - self.assertIn(ext_util.NAME, sys.modules) + self.assertIn(util.EXTENSIONS.name, sys.modules) self.assertIsInstance(module.__loader__, self.machinery.ExtensionFileLoader) @@ -56,9 +55,9 @@ class LoaderTests(abc.LoaderTests): test_lacking_parent = None def test_module_reuse(self): - with util.uncache(ext_util.NAME): - module1 = self.load_module(ext_util.NAME) - module2 = self.load_module(ext_util.NAME) + with util.uncache(util.EXTENSIONS.name): + module1 = self.load_module(util.EXTENSIONS.name) + module2 = self.load_module(util.EXTENSIONS.name) self.assertIs(module1, module2) # No easy way to trigger a failure after a successful import. @@ -71,14 +70,15 @@ class LoaderTests(abc.LoaderTests): self.assertEqual(cm.exception.name, name) def test_is_package(self): - self.assertFalse(self.loader.is_package(ext_util.NAME)) + self.assertFalse(self.loader.is_package(util.EXTENSIONS.name)) for suffix in self.machinery.EXTENSION_SUFFIXES: path = os.path.join('some', 'path', 'pkg', '__init__' + suffix) loader = self.machinery.ExtensionFileLoader('pkg', path) self.assertTrue(loader.is_package('pkg')) -Frozen_LoaderTests, Source_LoaderTests = util.test_both( - LoaderTests, machinery=machinery) +(Frozen_LoaderTests, + Source_LoaderTests + ) = util.test_both(LoaderTests, machinery=machinery) diff --git a/Lib/test/test_importlib/extension/test_path_hook.py b/Lib/test/test_importlib/extension/test_path_hook.py index 49d6734..8f4b8bb 100644 --- a/Lib/test/test_importlib/extension/test_path_hook.py +++ b/Lib/test/test_importlib/extension/test_path_hook.py @@ -1,7 +1,6 @@ -from .. import util as test_util -from . import util +from .. import util -machinery = test_util.import_importlib('importlib.machinery') +machinery = util.import_importlib('importlib.machinery') import collections import sys @@ -22,10 +21,12 @@ class PathHookTests: def test_success(self): # Path hook should handle a directory where a known extension module # exists. - self.assertTrue(hasattr(self.hook(util.PATH), 'find_module')) + self.assertTrue(hasattr(self.hook(util.EXTENSIONS.path), 'find_module')) -Frozen_PathHooksTests, Source_PathHooksTests = test_util.test_both( - PathHookTests, machinery=machinery) + +(Frozen_PathHooksTests, + Source_PathHooksTests + ) = util.test_both(PathHookTests, machinery=machinery) if __name__ == '__main__': diff --git a/Lib/test/test_importlib/extension/util.py b/Lib/test/test_importlib/extension/util.py deleted file mode 100644 index 8d089f0..0000000 --- a/Lib/test/test_importlib/extension/util.py +++ /dev/null @@ -1,19 +0,0 @@ -from importlib import machinery -import os -import sys - -PATH = None -EXT = None -FILENAME = None -NAME = '_testcapi' -try: - for PATH in sys.path: - for EXT in machinery.EXTENSION_SUFFIXES: - FILENAME = NAME + EXT - FILEPATH = os.path.join(PATH, FILENAME) - if os.path.exists(os.path.join(PATH, FILENAME)): - raise StopIteration - else: - PATH = EXT = FILENAME = FILEPATH = None -except StopIteration: - pass diff --git a/Lib/test/test_importlib/frozen/test_finder.py b/Lib/test/test_importlib/frozen/test_finder.py index f9f97f3..519aa02 100644 --- a/Lib/test/test_importlib/frozen/test_finder.py +++ b/Lib/test/test_importlib/frozen/test_finder.py @@ -37,8 +37,10 @@ class FindSpecTests(abc.FinderTests): spec = self.find('<not real>') self.assertIsNone(spec) -Frozen_FindSpecTests, Source_FindSpecTests = util.test_both(FindSpecTests, - machinery=machinery) + +(Frozen_FindSpecTests, + Source_FindSpecTests + ) = util.test_both(FindSpecTests, machinery=machinery) class FinderTests(abc.FinderTests): @@ -72,8 +74,10 @@ class FinderTests(abc.FinderTests): loader = self.find('<not real>') self.assertIsNone(loader) -Frozen_FinderTests, Source_FinderTests = util.test_both(FinderTests, - machinery=machinery) + +(Frozen_FinderTests, + Source_FinderTests + ) = util.test_both(FinderTests, machinery=machinery) if __name__ == '__main__': diff --git a/Lib/test/test_importlib/frozen/test_loader.py b/Lib/test/test_importlib/frozen/test_loader.py index 7c01464..603c7d7 100644 --- a/Lib/test/test_importlib/frozen/test_loader.py +++ b/Lib/test/test_importlib/frozen/test_loader.py @@ -85,8 +85,10 @@ class ExecModuleTests(abc.LoaderTests): self.exec_module('_not_real') self.assertEqual(cm.exception.name, '_not_real') -Frozen_ExecModuleTests, Source_ExecModuleTests = util.test_both(ExecModuleTests, - machinery=machinery) + +(Frozen_ExecModuleTests, + Source_ExecModuleTests + ) = util.test_both(ExecModuleTests, machinery=machinery) class LoaderTests(abc.LoaderTests): @@ -175,8 +177,10 @@ class LoaderTests(abc.LoaderTests): self.machinery.FrozenImporter.load_module('_not_real') self.assertEqual(cm.exception.name, '_not_real') -Frozen_LoaderTests, Source_LoaderTests = util.test_both(LoaderTests, - machinery=machinery) + +(Frozen_LoaderTests, + Source_LoaderTests + ) = util.test_both(LoaderTests, machinery=machinery) class InspectLoaderTests: @@ -214,8 +218,9 @@ class InspectLoaderTests: method('importlib') self.assertEqual(cm.exception.name, 'importlib') -Frozen_ILTests, Source_ILTests = util.test_both(InspectLoaderTests, - machinery=machinery) +(Frozen_ILTests, + Source_ILTests + ) = util.test_both(InspectLoaderTests, machinery=machinery) if __name__ == '__main__': diff --git a/Lib/test/test_importlib/import_/test___loader__.py b/Lib/test/test_importlib/import_/test___loader__.py index 6df8010..4b18093 100644 --- a/Lib/test/test_importlib/import_/test___loader__.py +++ b/Lib/test/test_importlib/import_/test___loader__.py @@ -4,7 +4,6 @@ import types import unittest from .. import util -from . import util as import_util class SpecLoaderMock: @@ -12,6 +11,9 @@ class SpecLoaderMock: def find_spec(self, fullname, path=None, target=None): return machinery.ModuleSpec(fullname, self) + def create_module(self, spec): + return None + def exec_module(self, module): pass @@ -24,8 +26,10 @@ class SpecLoaderAttributeTests: module = self.__import__('blah') self.assertEqual(loader, module.__loader__) -Frozen_SpecTests, Source_SpecTests = util.test_both( - SpecLoaderAttributeTests, __import__=import_util.__import__) + +(Frozen_SpecTests, + Source_SpecTests + ) = util.test_both(SpecLoaderAttributeTests, __import__=util.__import__) class LoaderMock: @@ -62,8 +66,9 @@ class LoaderAttributeTests: self.assertEqual(loader, module.__loader__) -Frozen_Tests, Source_Tests = util.test_both(LoaderAttributeTests, - __import__=import_util.__import__) +(Frozen_Tests, + Source_Tests + ) = util.test_both(LoaderAttributeTests, __import__=util.__import__) if __name__ == '__main__': diff --git a/Lib/test/test_importlib/import_/test___package__.py b/Lib/test/test_importlib/import_/test___package__.py index 2e19725..c7d3a2a 100644 --- a/Lib/test/test_importlib/import_/test___package__.py +++ b/Lib/test/test_importlib/import_/test___package__.py @@ -6,7 +6,6 @@ of using the typical __path__/__name__ test). """ import unittest from .. import util -from . import util as import_util class Using__package__: @@ -70,17 +69,23 @@ class Using__package__: with self.assertRaises(TypeError): self.__import__('', globals, {}, ['relimport'], 1) + class Using__package__PEP302(Using__package__): mock_modules = util.mock_modules -Frozen_UsingPackagePEP302, Source_UsingPackagePEP302 = util.test_both( - Using__package__PEP302, __import__=import_util.__import__) -class Using__package__PEP302(Using__package__): +(Frozen_UsingPackagePEP302, + Source_UsingPackagePEP302 + ) = util.test_both(Using__package__PEP302, __import__=util.__import__) + + +class Using__package__PEP451(Using__package__): mock_modules = util.mock_spec -Frozen_UsingPackagePEP451, Source_UsingPackagePEP451 = util.test_both( - Using__package__PEP302, __import__=import_util.__import__) + +(Frozen_UsingPackagePEP451, + Source_UsingPackagePEP451 + ) = util.test_both(Using__package__PEP451, __import__=util.__import__) class Setting__package__: @@ -95,7 +100,7 @@ class Setting__package__: """ - __import__ = import_util.__import__[1] + __import__ = util.__import__['Source'] # [top-level] def test_top_level(self): diff --git a/Lib/test/test_importlib/import_/test_api.py b/Lib/test/test_importlib/import_/test_api.py index 439c105..7069d9e 100644 --- a/Lib/test/test_importlib/import_/test_api.py +++ b/Lib/test/test_importlib/import_/test_api.py @@ -1,5 +1,4 @@ from .. import util -from . import util as import_util from importlib import machinery import sys @@ -18,6 +17,10 @@ class BadSpecFinderLoader: return spec @staticmethod + def create_module(spec): + return None + + @staticmethod def exec_module(module): if module.__name__ == SUBMOD_NAME: raise ImportError('I cannot be loaded!') @@ -79,15 +82,19 @@ class APITest: class OldAPITests(APITest): bad_finder_loader = BadLoaderFinder -Frozen_OldAPITests, Source_OldAPITests = util.test_both( - OldAPITests, __import__=import_util.__import__) + +(Frozen_OldAPITests, + Source_OldAPITests + ) = util.test_both(OldAPITests, __import__=util.__import__) class SpecAPITests(APITest): bad_finder_loader = BadSpecFinderLoader -Frozen_SpecAPITests, Source_SpecAPITests = util.test_both( - SpecAPITests, __import__=import_util.__import__) + +(Frozen_SpecAPITests, + Source_SpecAPITests + ) = util.test_both(SpecAPITests, __import__=util.__import__) if __name__ == '__main__': diff --git a/Lib/test/test_importlib/import_/test_caching.py b/Lib/test/test_importlib/import_/test_caching.py index c292ee4..8079add 100644 --- a/Lib/test/test_importlib/import_/test_caching.py +++ b/Lib/test/test_importlib/import_/test_caching.py @@ -1,6 +1,5 @@ """Test that sys.modules is used properly by import.""" from .. import util -from . import util as import_util import sys from types import MethodType import unittest @@ -39,15 +38,17 @@ class UseCache: self.__import__(name) self.assertEqual(cm.exception.name, name) -Frozen_UseCache, Source_UseCache = util.test_both( - UseCache, __import__=import_util.__import__) + +(Frozen_UseCache, + Source_UseCache + ) = util.test_both(UseCache, __import__=util.__import__) class ImportlibUseCache(UseCache, unittest.TestCase): # Pertinent only to PEP 302; exec_module() doesn't return a module. - __import__ = import_util.__import__[1] + __import__ = util.__import__['Source'] def create_mock(self, *names, return_=None): mock = util.mock_modules(*names) diff --git a/Lib/test/test_importlib/import_/test_fromlist.py b/Lib/test/test_importlib/import_/test_fromlist.py index a755b75..8045465 100644 --- a/Lib/test/test_importlib/import_/test_fromlist.py +++ b/Lib/test/test_importlib/import_/test_fromlist.py @@ -1,6 +1,5 @@ """Test that the semantics relating to the 'fromlist' argument are correct.""" from .. import util -from . import util as import_util import unittest @@ -29,8 +28,10 @@ class ReturnValue: module = self.__import__('pkg.module', fromlist=['attr']) self.assertEqual(module.__name__, 'pkg.module') -Frozen_ReturnValue, Source_ReturnValue = util.test_both( - ReturnValue, __import__=import_util.__import__) + +(Frozen_ReturnValue, + Source_ReturnValue + ) = util.test_both(ReturnValue, __import__=util.__import__) class HandlingFromlist: @@ -121,8 +122,10 @@ class HandlingFromlist: self.assertEqual(module.module1.__name__, 'pkg.module1') self.assertEqual(module.module2.__name__, 'pkg.module2') -Frozen_FromList, Source_FromList = util.test_both( - HandlingFromlist, __import__=import_util.__import__) + +(Frozen_FromList, + Source_FromList + ) = util.test_both(HandlingFromlist, __import__=util.__import__) if __name__ == '__main__': diff --git a/Lib/test/test_importlib/import_/test_meta_path.py b/Lib/test/test_importlib/import_/test_meta_path.py index 5eeb145..c452cdd 100644 --- a/Lib/test/test_importlib/import_/test_meta_path.py +++ b/Lib/test/test_importlib/import_/test_meta_path.py @@ -1,5 +1,4 @@ from .. import util -from . import util as import_util import importlib._bootstrap import sys from types import MethodType @@ -46,8 +45,10 @@ class CallingOrder: self.assertEqual(len(w), 1) self.assertTrue(issubclass(w[-1].category, ImportWarning)) -Frozen_CallingOrder, Source_CallingOrder = util.test_both( - CallingOrder, __import__=import_util.__import__) + +(Frozen_CallingOrder, + Source_CallingOrder + ) = util.test_both(CallingOrder, __import__=util.__import__) class CallSignature: @@ -100,19 +101,25 @@ class CallSignature: self.assertEqual(args[0], mod_name) self.assertIs(args[1], path) + class CallSignaturePEP302(CallSignature): mock_modules = util.mock_modules finder_name = 'find_module' -Frozen_CallSignaturePEP302, Source_CallSignaturePEP302 = util.test_both( - CallSignaturePEP302, __import__=import_util.__import__) + +(Frozen_CallSignaturePEP302, + Source_CallSignaturePEP302 + ) = util.test_both(CallSignaturePEP302, __import__=util.__import__) + class CallSignaturePEP451(CallSignature): mock_modules = util.mock_spec finder_name = 'find_spec' -Frozen_CallSignaturePEP451, Source_CallSignaturePEP451 = util.test_both( - CallSignaturePEP451, __import__=import_util.__import__) + +(Frozen_CallSignaturePEP451, + Source_CallSignaturePEP451 + ) = util.test_both(CallSignaturePEP451, __import__=util.__import__) if __name__ == '__main__': diff --git a/Lib/test/test_importlib/import_/test_packages.py b/Lib/test/test_importlib/import_/test_packages.py index 55a5d14..3755b84 100644 --- a/Lib/test/test_importlib/import_/test_packages.py +++ b/Lib/test/test_importlib/import_/test_packages.py @@ -1,5 +1,4 @@ from .. import util -from . import util as import_util import sys import unittest import importlib @@ -102,8 +101,10 @@ class ParentModuleTests: finally: support.unload(subname) -Frozen_ParentTests, Source_ParentTests = util.test_both( - ParentModuleTests, __import__=import_util.__import__) + +(Frozen_ParentTests, + Source_ParentTests + ) = util.test_both(ParentModuleTests, __import__=util.__import__) if __name__ == '__main__': diff --git a/Lib/test/test_importlib/import_/test_path.py b/Lib/test/test_importlib/import_/test_path.py index 1274f8c..c246d69 100644 --- a/Lib/test/test_importlib/import_/test_path.py +++ b/Lib/test/test_importlib/import_/test_path.py @@ -1,11 +1,12 @@ from .. import util -from . import util as import_util importlib = util.import_importlib('importlib') machinery = util.import_importlib('importlib.machinery') +import errno import os import sys +import tempfile from types import ModuleType import unittest import warnings @@ -58,7 +59,7 @@ class FinderTests: module = '<test module>' path = '<test path>' importer = util.mock_spec(module) - hook = import_util.mock_path_hook(path, importer=importer) + hook = util.mock_path_hook(path, importer=importer) with util.import_state(path_hooks=[hook]): loader = self.machinery.PathFinder.find_module(module, [path]) self.assertIs(loader, importer) @@ -83,7 +84,7 @@ class FinderTests: path = '' module = '<test module>' importer = util.mock_spec(module) - hook = import_util.mock_path_hook(os.getcwd(), importer=importer) + hook = util.mock_path_hook(os.getcwd(), importer=importer) with util.import_state(path=[path], path_hooks=[hook]): loader = self.machinery.PathFinder.find_module(module) self.assertIs(loader, importer) @@ -112,8 +113,74 @@ class FinderTests: if email is not missing: sys.modules['email'] = email -Frozen_FinderTests, Source_FinderTests = util.test_both( - FinderTests, importlib=importlib, machinery=machinery) + def test_finder_with_find_module(self): + class TestFinder: + def find_module(self, fullname): + return self.to_return + failing_finder = TestFinder() + failing_finder.to_return = None + path = 'testing path' + with util.import_state(path_importer_cache={path: failing_finder}): + self.assertIsNone( + self.machinery.PathFinder.find_spec('whatever', [path])) + success_finder = TestFinder() + success_finder.to_return = __loader__ + with util.import_state(path_importer_cache={path: success_finder}): + spec = self.machinery.PathFinder.find_spec('whatever', [path]) + self.assertEqual(spec.loader, __loader__) + + def test_finder_with_find_loader(self): + class TestFinder: + loader = None + portions = [] + def find_loader(self, fullname): + return self.loader, self.portions + path = 'testing path' + with util.import_state(path_importer_cache={path: TestFinder()}): + self.assertIsNone( + self.machinery.PathFinder.find_spec('whatever', [path])) + success_finder = TestFinder() + success_finder.loader = __loader__ + with util.import_state(path_importer_cache={path: success_finder}): + spec = self.machinery.PathFinder.find_spec('whatever', [path]) + self.assertEqual(spec.loader, __loader__) + + def test_finder_with_find_spec(self): + class TestFinder: + spec = None + def find_spec(self, fullname, target=None): + return self.spec + path = 'testing path' + with util.import_state(path_importer_cache={path: TestFinder()}): + self.assertIsNone( + self.machinery.PathFinder.find_spec('whatever', [path])) + success_finder = TestFinder() + success_finder.spec = self.machinery.ModuleSpec('whatever', __loader__) + with util.import_state(path_importer_cache={path: success_finder}): + got = self.machinery.PathFinder.find_spec('whatever', [path]) + self.assertEqual(got, success_finder.spec) + + @unittest.skipIf(sys.platform == 'win32', "cwd can't not exist on Windows") + def test_deleted_cwd(self): + # Issue #22834 + self.addCleanup(os.chdir, os.getcwd()) + try: + with tempfile.TemporaryDirectory() as path: + os.chdir(path) + except OSError as exc: + if exc.errno == errno.EINVAL: + self.skipTest("platform does not allow the deletion of the cwd") + raise + with util.import_state(path=['']): + # Do not want FileNotFoundError raised. + self.assertIsNone(self.machinery.PathFinder.find_spec('whatever')) + + + + +(Frozen_FinderTests, + Source_FinderTests + ) = util.test_both(FinderTests, importlib=importlib, machinery=machinery) class PathEntryFinderTests: @@ -136,8 +203,10 @@ class PathEntryFinderTests: path_hooks=[Finder]): self.machinery.PathFinder.find_spec('importlib') -Frozen_PEFTests, Source_PEFTests = util.test_both( - PathEntryFinderTests, machinery=machinery) + +(Frozen_PEFTests, + Source_PEFTests + ) = util.test_both(PathEntryFinderTests, machinery=machinery) if __name__ == '__main__': diff --git a/Lib/test/test_importlib/import_/test_relative_imports.py b/Lib/test/test_importlib/import_/test_relative_imports.py index b216e9c..28bb6f7 100644 --- a/Lib/test/test_importlib/import_/test_relative_imports.py +++ b/Lib/test/test_importlib/import_/test_relative_imports.py @@ -1,6 +1,5 @@ """Test relative imports (PEP 328).""" from .. import util -from . import util as import_util import sys import unittest @@ -208,8 +207,10 @@ class RelativeImports: with self.assertRaises(KeyError): self.__import__('sys', level=1) -Frozen_RelativeImports, Source_RelativeImports = util.test_both( - RelativeImports, __import__=import_util.__import__) + +(Frozen_RelativeImports, + Source_RelativeImports + ) = util.test_both(RelativeImports, __import__=util.__import__) if __name__ == '__main__': diff --git a/Lib/test/test_importlib/import_/util.py b/Lib/test/test_importlib/import_/util.py deleted file mode 100644 index dcb490f..0000000 --- a/Lib/test/test_importlib/import_/util.py +++ /dev/null @@ -1,20 +0,0 @@ -from .. import util - -frozen_importlib, source_importlib = util.import_importlib('importlib') - -import builtins -import functools -import importlib -import unittest - - -__import__ = staticmethod(builtins.__import__), staticmethod(source_importlib.__import__) - - -def mock_path_hook(*entries, importer): - """A mock sys.path_hooks entry.""" - def hook(entry): - if entry not in entries: - raise ImportError - return importer - return hook diff --git a/Lib/test/test_importlib/source/test_case_sensitivity.py b/Lib/test/test_importlib/source/test_case_sensitivity.py index efd3146..29e95b2 100644 --- a/Lib/test/test_importlib/source/test_case_sensitivity.py +++ b/Lib/test/test_importlib/source/test_case_sensitivity.py @@ -1,6 +1,5 @@ """Test case-sensitivity (PEP 235).""" from .. import util -from . import util as source_util importlib = util.import_importlib('importlib') machinery = util.import_importlib('importlib.machinery') @@ -32,7 +31,7 @@ class CaseSensitivityTest: """Look for a module with matching and non-matching sensitivity.""" sensitive_pkg = 'sensitive.{0}'.format(self.name) insensitive_pkg = 'insensitive.{0}'.format(self.name.lower()) - context = source_util.create_modules(insensitive_pkg, sensitive_pkg) + context = util.create_modules(insensitive_pkg, sensitive_pkg) with context as mapping: sensitive_path = os.path.join(mapping['.root'], 'sensitive') insensitive_path = os.path.join(mapping['.root'], 'insensitive') @@ -63,20 +62,28 @@ class CaseSensitivityTest: self.assertIsNotNone(insensitive) self.assertIn(self.name, insensitive.get_filename(self.name)) + class CaseSensitivityTestPEP302(CaseSensitivityTest): def find(self, finder): return finder.find_module(self.name) -Frozen_CaseSensitivityTestPEP302, Source_CaseSensitivityTestPEP302 = util.test_both( - CaseSensitivityTestPEP302, importlib=importlib, machinery=machinery) + +(Frozen_CaseSensitivityTestPEP302, + Source_CaseSensitivityTestPEP302 + ) = util.test_both(CaseSensitivityTestPEP302, importlib=importlib, + machinery=machinery) + class CaseSensitivityTestPEP451(CaseSensitivityTest): def find(self, finder): found = finder.find_spec(self.name) return found.loader if found is not None else found -Frozen_CaseSensitivityTestPEP451, Source_CaseSensitivityTestPEP451 = util.test_both( - CaseSensitivityTestPEP451, importlib=importlib, machinery=machinery) + +(Frozen_CaseSensitivityTestPEP451, + Source_CaseSensitivityTestPEP451 + ) = util.test_both(CaseSensitivityTestPEP451, importlib=importlib, + machinery=machinery) if __name__ == '__main__': diff --git a/Lib/test/test_importlib/source/test_file_loader.py b/Lib/test/test_importlib/source/test_file_loader.py index 2d415f9..73f4c62 100644 --- a/Lib/test/test_importlib/source/test_file_loader.py +++ b/Lib/test/test_importlib/source/test_file_loader.py @@ -1,6 +1,5 @@ from .. import abc from .. import util -from . import util as source_util importlib = util.import_importlib('importlib') importlib_abc = util.import_importlib('importlib.abc') @@ -71,7 +70,7 @@ class SimpleTest(abc.LoaderTests): # [basic] def test_module(self): - with source_util.create_modules('_temp') as mapping: + with util.create_modules('_temp') as mapping: loader = self.machinery.SourceFileLoader('_temp', mapping['_temp']) with warnings.catch_warnings(): warnings.simplefilter('ignore', DeprecationWarning) @@ -83,7 +82,7 @@ class SimpleTest(abc.LoaderTests): self.assertEqual(getattr(module, attr), value) def test_package(self): - with source_util.create_modules('_pkg.__init__') as mapping: + with util.create_modules('_pkg.__init__') as mapping: loader = self.machinery.SourceFileLoader('_pkg', mapping['_pkg.__init__']) with warnings.catch_warnings(): @@ -98,7 +97,7 @@ class SimpleTest(abc.LoaderTests): def test_lacking_parent(self): - with source_util.create_modules('_pkg.__init__', '_pkg.mod')as mapping: + with util.create_modules('_pkg.__init__', '_pkg.mod')as mapping: loader = self.machinery.SourceFileLoader('_pkg.mod', mapping['_pkg.mod']) with warnings.catch_warnings(): @@ -115,7 +114,7 @@ class SimpleTest(abc.LoaderTests): return lambda name: fxn(name) + 1 def test_module_reuse(self): - with source_util.create_modules('_temp') as mapping: + with util.create_modules('_temp') as mapping: loader = self.machinery.SourceFileLoader('_temp', mapping['_temp']) with warnings.catch_warnings(): warnings.simplefilter('ignore', DeprecationWarning) @@ -139,7 +138,7 @@ class SimpleTest(abc.LoaderTests): attributes = ('__file__', '__path__', '__package__') value = '<test>' name = '_temp' - with source_util.create_modules(name) as mapping: + with util.create_modules(name) as mapping: orig_module = types.ModuleType(name) for attr in attributes: setattr(orig_module, attr, value) @@ -159,7 +158,7 @@ class SimpleTest(abc.LoaderTests): # [syntax error] def test_bad_syntax(self): - with source_util.create_modules('_temp') as mapping: + with util.create_modules('_temp') as mapping: with open(mapping['_temp'], 'w') as file: file.write('=') loader = self.machinery.SourceFileLoader('_temp', mapping['_temp']) @@ -190,11 +189,11 @@ class SimpleTest(abc.LoaderTests): if os.path.exists(pycache): shutil.rmtree(pycache) - @source_util.writes_bytecode_files + @util.writes_bytecode_files def test_timestamp_overflow(self): # When a modification timestamp is larger than 2**32, it should be # truncated rather than raise an OverflowError. - with source_util.create_modules('_temp') as mapping: + with util.create_modules('_temp') as mapping: source = mapping['_temp'] compiled = self.util.cache_from_source(source) with open(source, 'w') as f: @@ -236,9 +235,11 @@ class SimpleTest(abc.LoaderTests): warnings.simplefilter('ignore', DeprecationWarning) loader.load_module('bad name') -Frozen_SimpleTest, Source_SimpleTest = util.test_both( - SimpleTest, importlib=importlib, machinery=machinery, abc=importlib_abc, - util=importlib_util) + +(Frozen_SimpleTest, + Source_SimpleTest + ) = util.test_both(SimpleTest, importlib=importlib, machinery=machinery, + abc=importlib_abc, util=importlib_util) class BadBytecodeTest: @@ -275,45 +276,45 @@ class BadBytecodeTest: return bytecode_path def _test_empty_file(self, test, *, del_source=False): - with source_util.create_modules('_temp') as mapping: + with util.create_modules('_temp') as mapping: bc_path = self.manipulate_bytecode('_temp', mapping, lambda bc: b'', del_source=del_source) test('_temp', mapping, bc_path) - @source_util.writes_bytecode_files + @util.writes_bytecode_files def _test_partial_magic(self, test, *, del_source=False): # When their are less than 4 bytes to a .pyc, regenerate it if # possible, else raise ImportError. - with source_util.create_modules('_temp') as mapping: + with util.create_modules('_temp') as mapping: bc_path = self.manipulate_bytecode('_temp', mapping, lambda bc: bc[:3], del_source=del_source) test('_temp', mapping, bc_path) def _test_magic_only(self, test, *, del_source=False): - with source_util.create_modules('_temp') as mapping: + with util.create_modules('_temp') as mapping: bc_path = self.manipulate_bytecode('_temp', mapping, lambda bc: bc[:4], del_source=del_source) test('_temp', mapping, bc_path) def _test_partial_timestamp(self, test, *, del_source=False): - with source_util.create_modules('_temp') as mapping: + with util.create_modules('_temp') as mapping: bc_path = self.manipulate_bytecode('_temp', mapping, lambda bc: bc[:7], del_source=del_source) test('_temp', mapping, bc_path) def _test_partial_size(self, test, *, del_source=False): - with source_util.create_modules('_temp') as mapping: + with util.create_modules('_temp') as mapping: bc_path = self.manipulate_bytecode('_temp', mapping, lambda bc: bc[:11], del_source=del_source) test('_temp', mapping, bc_path) def _test_no_marshal(self, *, del_source=False): - with source_util.create_modules('_temp') as mapping: + with util.create_modules('_temp') as mapping: bc_path = self.manipulate_bytecode('_temp', mapping, lambda bc: bc[:12], del_source=del_source) @@ -322,7 +323,7 @@ class BadBytecodeTest: self.import_(file_path, '_temp') def _test_non_code_marshal(self, *, del_source=False): - with source_util.create_modules('_temp') as mapping: + with util.create_modules('_temp') as mapping: bytecode_path = self.manipulate_bytecode('_temp', mapping, lambda bc: bc[:12] + marshal.dumps(b'abcd'), del_source=del_source) @@ -333,7 +334,7 @@ class BadBytecodeTest: self.assertEqual(cm.exception.path, bytecode_path) def _test_bad_marshal(self, *, del_source=False): - with source_util.create_modules('_temp') as mapping: + with util.create_modules('_temp') as mapping: bytecode_path = self.manipulate_bytecode('_temp', mapping, lambda bc: bc[:12] + b'<test>', del_source=del_source) @@ -342,11 +343,12 @@ class BadBytecodeTest: self.import_(file_path, '_temp') def _test_bad_magic(self, test, *, del_source=False): - with source_util.create_modules('_temp') as mapping: + with util.create_modules('_temp') as mapping: bc_path = self.manipulate_bytecode('_temp', mapping, lambda bc: b'\x00\x00\x00\x00' + bc[4:]) test('_temp', mapping, bc_path) + class BadBytecodeTestPEP451(BadBytecodeTest): def import_(self, file, module_name): @@ -355,6 +357,7 @@ class BadBytecodeTestPEP451(BadBytecodeTest): module.__spec__ = self.util.spec_from_loader(module_name, loader) loader.exec_module(module) + class BadBytecodeTestPEP302(BadBytecodeTest): def import_(self, file, module_name): @@ -371,7 +374,7 @@ class SourceLoaderBadBytecodeTest: def setUpClass(cls): cls.loader = cls.machinery.SourceFileLoader - @source_util.writes_bytecode_files + @util.writes_bytecode_files def test_empty_file(self): # When a .pyc is empty, regenerate it if possible, else raise # ImportError. @@ -390,7 +393,7 @@ class SourceLoaderBadBytecodeTest: self._test_partial_magic(test) - @source_util.writes_bytecode_files + @util.writes_bytecode_files def test_magic_only(self): # When there is only the magic number, regenerate the .pyc if possible, # else raise EOFError. @@ -401,7 +404,7 @@ class SourceLoaderBadBytecodeTest: self._test_magic_only(test) - @source_util.writes_bytecode_files + @util.writes_bytecode_files def test_bad_magic(self): # When the magic number is different, the bytecode should be # regenerated. @@ -413,7 +416,7 @@ class SourceLoaderBadBytecodeTest: self._test_bad_magic(test) - @source_util.writes_bytecode_files + @util.writes_bytecode_files def test_partial_timestamp(self): # When the timestamp is partial, regenerate the .pyc, else # raise EOFError. @@ -424,7 +427,7 @@ class SourceLoaderBadBytecodeTest: self._test_partial_timestamp(test) - @source_util.writes_bytecode_files + @util.writes_bytecode_files def test_partial_size(self): # When the size is partial, regenerate the .pyc, else # raise EOFError. @@ -435,29 +438,29 @@ class SourceLoaderBadBytecodeTest: self._test_partial_size(test) - @source_util.writes_bytecode_files + @util.writes_bytecode_files def test_no_marshal(self): # When there is only the magic number and timestamp, raise EOFError. self._test_no_marshal() - @source_util.writes_bytecode_files + @util.writes_bytecode_files def test_non_code_marshal(self): self._test_non_code_marshal() # XXX ImportError when sourceless # [bad marshal] - @source_util.writes_bytecode_files + @util.writes_bytecode_files def test_bad_marshal(self): # Bad marshal data should raise a ValueError. self._test_bad_marshal() # [bad timestamp] - @source_util.writes_bytecode_files + @util.writes_bytecode_files def test_old_timestamp(self): # When the timestamp is older than the source, bytecode should be # regenerated. zeros = b'\x00\x00\x00\x00' - with source_util.create_modules('_temp') as mapping: + with util.create_modules('_temp') as mapping: py_compile.compile(mapping['_temp']) bytecode_path = self.util.cache_from_source(mapping['_temp']) with open(bytecode_path, 'r+b') as bytecode_file: @@ -471,10 +474,10 @@ class SourceLoaderBadBytecodeTest: self.assertEqual(bytecode_file.read(4), source_timestamp) # [bytecode read-only] - @source_util.writes_bytecode_files + @util.writes_bytecode_files def test_read_only_bytecode(self): # When bytecode is read-only but should be rewritten, fail silently. - with source_util.create_modules('_temp') as mapping: + with util.create_modules('_temp') as mapping: # Create bytecode that will need to be re-created. py_compile.compile(mapping['_temp']) bytecode_path = self.util.cache_from_source(mapping['_temp']) @@ -491,21 +494,29 @@ class SourceLoaderBadBytecodeTest: # Make writable for eventual clean-up. os.chmod(bytecode_path, stat.S_IWUSR) + class SourceLoaderBadBytecodeTestPEP451( SourceLoaderBadBytecodeTest, BadBytecodeTestPEP451): pass -Frozen_SourceBadBytecodePEP451, Source_SourceBadBytecodePEP451 = util.test_both( - SourceLoaderBadBytecodeTestPEP451, importlib=importlib, machinery=machinery, - abc=importlib_abc, util=importlib_util) + +(Frozen_SourceBadBytecodePEP451, + Source_SourceBadBytecodePEP451 + ) = util.test_both(SourceLoaderBadBytecodeTestPEP451, importlib=importlib, + machinery=machinery, abc=importlib_abc, + util=importlib_util) + class SourceLoaderBadBytecodeTestPEP302( SourceLoaderBadBytecodeTest, BadBytecodeTestPEP302): pass -Frozen_SourceBadBytecodePEP302, Source_SourceBadBytecodePEP302 = util.test_both( - SourceLoaderBadBytecodeTestPEP302, importlib=importlib, machinery=machinery, - abc=importlib_abc, util=importlib_util) + +(Frozen_SourceBadBytecodePEP302, + Source_SourceBadBytecodePEP302 + ) = util.test_both(SourceLoaderBadBytecodeTestPEP302, importlib=importlib, + machinery=machinery, abc=importlib_abc, + util=importlib_util) class SourcelessLoaderBadBytecodeTest: @@ -567,21 +578,29 @@ class SourcelessLoaderBadBytecodeTest: def test_non_code_marshal(self): self._test_non_code_marshal(del_source=True) + class SourcelessLoaderBadBytecodeTestPEP451(SourcelessLoaderBadBytecodeTest, BadBytecodeTestPEP451): pass -Frozen_SourcelessBadBytecodePEP451, Source_SourcelessBadBytecodePEP451 = util.test_both( - SourcelessLoaderBadBytecodeTestPEP451, importlib=importlib, - machinery=machinery, abc=importlib_abc, util=importlib_util) + +(Frozen_SourcelessBadBytecodePEP451, + Source_SourcelessBadBytecodePEP451 + ) = util.test_both(SourcelessLoaderBadBytecodeTestPEP451, importlib=importlib, + machinery=machinery, abc=importlib_abc, + util=importlib_util) + class SourcelessLoaderBadBytecodeTestPEP302(SourcelessLoaderBadBytecodeTest, BadBytecodeTestPEP302): pass -Frozen_SourcelessBadBytecodePEP302, Source_SourcelessBadBytecodePEP302 = util.test_both( - SourcelessLoaderBadBytecodeTestPEP302, importlib=importlib, - machinery=machinery, abc=importlib_abc, util=importlib_util) + +(Frozen_SourcelessBadBytecodePEP302, + Source_SourcelessBadBytecodePEP302 + ) = util.test_both(SourcelessLoaderBadBytecodeTestPEP302, importlib=importlib, + machinery=machinery, abc=importlib_abc, + util=importlib_util) if __name__ == '__main__': diff --git a/Lib/test/test_importlib/source/test_finder.py b/Lib/test/test_importlib/source/test_finder.py index 473297b..f372b85 100644 --- a/Lib/test/test_importlib/source/test_finder.py +++ b/Lib/test/test_importlib/source/test_finder.py @@ -1,6 +1,5 @@ from .. import abc from .. import util -from . import util as source_util machinery = util.import_importlib('importlib.machinery') @@ -60,7 +59,7 @@ class FinderTests(abc.FinderTests): """ if create is None: create = {test} - with source_util.create_modules(*create) as mapping: + with util.create_modules(*create) as mapping: if compile_: for name in compile_: py_compile.compile(mapping[name]) @@ -100,14 +99,14 @@ class FinderTests(abc.FinderTests): # [sub module] def test_module_in_package(self): - with source_util.create_modules('pkg.__init__', 'pkg.sub') as mapping: + with util.create_modules('pkg.__init__', 'pkg.sub') as mapping: pkg_dir = os.path.dirname(mapping['pkg.__init__']) loader = self.import_(pkg_dir, 'pkg.sub') self.assertTrue(hasattr(loader, 'load_module')) # [sub package] def test_package_in_package(self): - context = source_util.create_modules('pkg.__init__', 'pkg.sub.__init__') + context = util.create_modules('pkg.__init__', 'pkg.sub.__init__') with context as mapping: pkg_dir = os.path.dirname(mapping['pkg.__init__']) loader = self.import_(pkg_dir, 'pkg.sub') @@ -120,7 +119,7 @@ class FinderTests(abc.FinderTests): self.assertIn('__init__', loader.get_filename(name)) def test_failure(self): - with source_util.create_modules('blah') as mapping: + with util.create_modules('blah') as mapping: nothing = self.import_(mapping['.root'], 'sdfsadsadf') self.assertIsNone(nothing) @@ -147,7 +146,7 @@ class FinderTests(abc.FinderTests): # Regression test for http://bugs.python.org/issue14846 def test_dir_removal_handling(self): mod = 'mod' - with source_util.create_modules(mod) as mapping: + with util.create_modules(mod) as mapping: finder = self.get_finder(mapping['.root']) found = self._find(finder, 'mod', loader_only=True) self.assertIsNotNone(found) @@ -196,8 +195,10 @@ class FinderTestsPEP451(FinderTests): spec = finder.find_spec(name) return spec.loader if spec is not None else spec -Frozen_FinderTestsPEP451, Source_FinderTestsPEP451 = util.test_both( - FinderTestsPEP451, machinery=machinery) + +(Frozen_FinderTestsPEP451, + Source_FinderTestsPEP451 + ) = util.test_both(FinderTestsPEP451, machinery=machinery) class FinderTestsPEP420(FinderTests): @@ -210,8 +211,10 @@ class FinderTestsPEP420(FinderTests): loader_portions = finder.find_loader(name) return loader_portions[0] if loader_only else loader_portions -Frozen_FinderTestsPEP420, Source_FinderTestsPEP420 = util.test_both( - FinderTestsPEP420, machinery=machinery) + +(Frozen_FinderTestsPEP420, + Source_FinderTestsPEP420 + ) = util.test_both(FinderTestsPEP420, machinery=machinery) class FinderTestsPEP302(FinderTests): @@ -223,9 +226,10 @@ class FinderTestsPEP302(FinderTests): warnings.simplefilter("ignore", DeprecationWarning) return finder.find_module(name) -Frozen_FinderTestsPEP302, Source_FinderTestsPEP302 = util.test_both( - FinderTestsPEP302, machinery=machinery) +(Frozen_FinderTestsPEP302, + Source_FinderTestsPEP302 + ) = util.test_both(FinderTestsPEP302, machinery=machinery) if __name__ == '__main__': diff --git a/Lib/test/test_importlib/source/test_path_hook.py b/Lib/test/test_importlib/source/test_path_hook.py index 92da772..e6a2415 100644 --- a/Lib/test/test_importlib/source/test_path_hook.py +++ b/Lib/test/test_importlib/source/test_path_hook.py @@ -1,5 +1,4 @@ from .. import util -from . import util as source_util machinery = util.import_importlib('importlib.machinery') @@ -15,7 +14,7 @@ class PathHookTest: self.machinery.SOURCE_SUFFIXES)) def test_success(self): - with source_util.create_modules('dummy') as mapping: + with util.create_modules('dummy') as mapping: self.assertTrue(hasattr(self.path_hook()(mapping['.root']), 'find_module')) @@ -23,7 +22,10 @@ class PathHookTest: # The empty string represents the cwd. self.assertTrue(hasattr(self.path_hook()(''), 'find_module')) -Frozen_PathHookTest, Source_PathHooktest = util.test_both(PathHookTest, machinery=machinery) + +(Frozen_PathHookTest, + Source_PathHooktest + ) = util.test_both(PathHookTest, machinery=machinery) if __name__ == '__main__': diff --git a/Lib/test/test_importlib/source/test_source_encoding.py b/Lib/test/test_importlib/source/test_source_encoding.py index c62dfa1..b604afb 100644 --- a/Lib/test/test_importlib/source/test_source_encoding.py +++ b/Lib/test/test_importlib/source/test_source_encoding.py @@ -1,5 +1,4 @@ from .. import util -from . import util as source_util machinery = util.import_importlib('importlib.machinery') @@ -37,7 +36,7 @@ class EncodingTest: module_name = '_temp' def run_test(self, source): - with source_util.create_modules(self.module_name) as mapping: + with util.create_modules(self.module_name) as mapping: with open(mapping[self.module_name], 'wb') as file: file.write(source) loader = self.machinery.SourceFileLoader(self.module_name, @@ -89,6 +88,7 @@ class EncodingTest: with self.assertRaises(SyntaxError): self.run_test(source) + class EncodingTestPEP451(EncodingTest): def load(self, loader): @@ -97,8 +97,11 @@ class EncodingTestPEP451(EncodingTest): loader.exec_module(module) return module -Frozen_EncodingTestPEP451, Source_EncodingTestPEP451 = util.test_both( - EncodingTestPEP451, machinery=machinery) + +(Frozen_EncodingTestPEP451, + Source_EncodingTestPEP451 + ) = util.test_both(EncodingTestPEP451, machinery=machinery) + class EncodingTestPEP302(EncodingTest): @@ -107,8 +110,10 @@ class EncodingTestPEP302(EncodingTest): warnings.simplefilter('ignore', DeprecationWarning) return loader.load_module(self.module_name) -Frozen_EncodingTestPEP302, Source_EncodingTestPEP302 = util.test_both( - EncodingTestPEP302, machinery=machinery) + +(Frozen_EncodingTestPEP302, + Source_EncodingTestPEP302 + ) = util.test_both(EncodingTestPEP302, machinery=machinery) class LineEndingTest: @@ -120,7 +125,7 @@ class LineEndingTest: module_name = '_temp' source_lines = [b"a = 42", b"b = -13", b''] source = line_ending.join(source_lines) - with source_util.create_modules(module_name) as mapping: + with util.create_modules(module_name) as mapping: with open(mapping[module_name], 'wb') as file: file.write(source) loader = self.machinery.SourceFileLoader(module_name, @@ -139,6 +144,7 @@ class LineEndingTest: def test_lf(self): self.run_test(b'\n') + class LineEndingTestPEP451(LineEndingTest): def load(self, loader, module_name): @@ -147,8 +153,11 @@ class LineEndingTestPEP451(LineEndingTest): loader.exec_module(module) return module -Frozen_LineEndingTestPEP451, Source_LineEndingTestPEP451 = util.test_both( - LineEndingTestPEP451, machinery=machinery) + +(Frozen_LineEndingTestPEP451, + Source_LineEndingTestPEP451 + ) = util.test_both(LineEndingTestPEP451, machinery=machinery) + class LineEndingTestPEP302(LineEndingTest): @@ -157,8 +166,10 @@ class LineEndingTestPEP302(LineEndingTest): warnings.simplefilter('ignore', DeprecationWarning) return loader.load_module(module_name) -Frozen_LineEndingTestPEP302, Source_LineEndingTestPEP302 = util.test_both( - LineEndingTestPEP302, machinery=machinery) + +(Frozen_LineEndingTestPEP302, + Source_LineEndingTestPEP302 + ) = util.test_both(LineEndingTestPEP302, machinery=machinery) if __name__ == '__main__': diff --git a/Lib/test/test_importlib/source/util.py b/Lib/test/test_importlib/source/util.py deleted file mode 100644 index 63cd25a..0000000 --- a/Lib/test/test_importlib/source/util.py +++ /dev/null @@ -1,96 +0,0 @@ -from .. import util -import contextlib -import errno -import functools -import os -import os.path -import sys -import tempfile -from test import support - - -def writes_bytecode_files(fxn): - """Decorator to protect sys.dont_write_bytecode from mutation and to skip - tests that require it to be set to False.""" - if sys.dont_write_bytecode: - return lambda *args, **kwargs: None - @functools.wraps(fxn) - def wrapper(*args, **kwargs): - original = sys.dont_write_bytecode - sys.dont_write_bytecode = False - try: - to_return = fxn(*args, **kwargs) - finally: - sys.dont_write_bytecode = original - return to_return - return wrapper - - -def ensure_bytecode_path(bytecode_path): - """Ensure that the __pycache__ directory for PEP 3147 pyc file exists. - - :param bytecode_path: File system path to PEP 3147 pyc file. - """ - try: - os.mkdir(os.path.dirname(bytecode_path)) - except OSError as error: - if error.errno != errno.EEXIST: - raise - - -@contextlib.contextmanager -def create_modules(*names): - """Temporarily create each named module with an attribute (named 'attr') - that contains the name passed into the context manager that caused the - creation of the module. - - All files are created in a temporary directory returned by - tempfile.mkdtemp(). This directory is inserted at the beginning of - sys.path. When the context manager exits all created files (source and - bytecode) are explicitly deleted. - - No magic is performed when creating packages! This means that if you create - a module within a package you must also create the package's __init__ as - well. - - """ - source = 'attr = {0!r}' - created_paths = [] - mapping = {} - state_manager = None - uncache_manager = None - try: - temp_dir = tempfile.mkdtemp() - mapping['.root'] = temp_dir - import_names = set() - for name in names: - if not name.endswith('__init__'): - import_name = name - else: - import_name = name[:-len('.__init__')] - import_names.add(import_name) - if import_name in sys.modules: - del sys.modules[import_name] - name_parts = name.split('.') - file_path = temp_dir - for directory in name_parts[:-1]: - file_path = os.path.join(file_path, directory) - if not os.path.exists(file_path): - os.mkdir(file_path) - created_paths.append(file_path) - file_path = os.path.join(file_path, name_parts[-1] + '.py') - with open(file_path, 'w') as file: - file.write(source.format(name)) - created_paths.append(file_path) - mapping[name] = file_path - uncache_manager = util.uncache(*import_names) - uncache_manager.__enter__() - state_manager = util.import_state(path=[temp_dir]) - state_manager.__enter__() - yield mapping - finally: - if state_manager is not None: - state_manager.__exit__(None, None, None) - if uncache_manager is not None: - uncache_manager.__exit__(None, None, None) - support.rmtree(temp_dir) diff --git a/Lib/test/test_importlib/test_abc.py b/Lib/test/test_importlib/test_abc.py index a1f8e76..d4bf915 100644 --- a/Lib/test/test_importlib/test_abc.py +++ b/Lib/test/test_importlib/test_abc.py @@ -10,12 +10,13 @@ import unittest from unittest import mock import warnings -from . import util +from . import util as test_util + +init = test_util.import_importlib('importlib') +abc = test_util.import_importlib('importlib.abc') +machinery = test_util.import_importlib('importlib.machinery') +util = test_util.import_importlib('importlib.util') -frozen_init, source_init = util.import_importlib('importlib') -frozen_abc, source_abc = util.import_importlib('importlib.abc') -machinery = util.import_importlib('importlib.machinery') -frozen_util, source_util = util.import_importlib('importlib.util') ##### Inheritance ############################################################## class InheritanceTests: @@ -26,8 +27,7 @@ class InheritanceTests: subclasses = [] superclasses = [] - def __init__(self, *args, **kwargs): - super().__init__(*args, **kwargs) + def setUp(self): self.superclasses = [getattr(self.abc, class_name) for class_name in self.superclass_names] if hasattr(self, 'subclass_names'): @@ -36,11 +36,11 @@ class InheritanceTests: # checking across module boundaries (i.e. the _bootstrap in abc is # not the same as the one in machinery). That means stealing one of # the modules from the other to make sure the same instance is used. - self.subclasses = [getattr(self.abc.machinery, class_name) - for class_name in self.subclass_names] + machinery = self.abc.machinery + self.subclasses = [getattr(machinery, class_name) + for class_name in self.subclass_names] assert self.subclasses or self.superclasses, self.__class__ - testing = self.__class__.__name__.partition('_')[2] - self.__test = getattr(self.abc, testing) + self.__test = getattr(self.abc, self._NAME) def test_subclasses(self): # Test that the expected subclasses inherit. @@ -54,94 +54,97 @@ class InheritanceTests: self.assertTrue(issubclass(self.__test, superclass), "{0} is not a superclass of {1}".format(superclass, self.__test)) -def create_inheritance_tests(base_class): - def set_frozen(ns): - ns['abc'] = frozen_abc - def set_source(ns): - ns['abc'] = source_abc - - classes = [] - for prefix, ns_set in [('Frozen', set_frozen), ('Source', set_source)]: - classes.append(types.new_class('_'.join([prefix, base_class.__name__]), - (base_class, unittest.TestCase), - exec_body=ns_set)) - return classes - class MetaPathFinder(InheritanceTests): superclass_names = ['Finder'] subclass_names = ['BuiltinImporter', 'FrozenImporter', 'PathFinder', 'WindowsRegistryFinder'] -tests = create_inheritance_tests(MetaPathFinder) -Frozen_MetaPathFinderInheritanceTests, Source_MetaPathFinderInheritanceTests = tests + +(Frozen_MetaPathFinderInheritanceTests, + Source_MetaPathFinderInheritanceTests + ) = test_util.test_both(MetaPathFinder, abc=abc) class PathEntryFinder(InheritanceTests): superclass_names = ['Finder'] subclass_names = ['FileFinder'] -tests = create_inheritance_tests(PathEntryFinder) -Frozen_PathEntryFinderInheritanceTests, Source_PathEntryFinderInheritanceTests = tests + +(Frozen_PathEntryFinderInheritanceTests, + Source_PathEntryFinderInheritanceTests + ) = test_util.test_both(PathEntryFinder, abc=abc) class ResourceLoader(InheritanceTests): superclass_names = ['Loader'] -tests = create_inheritance_tests(ResourceLoader) -Frozen_ResourceLoaderInheritanceTests, Source_ResourceLoaderInheritanceTests = tests + +(Frozen_ResourceLoaderInheritanceTests, + Source_ResourceLoaderInheritanceTests + ) = test_util.test_both(ResourceLoader, abc=abc) class InspectLoader(InheritanceTests): superclass_names = ['Loader'] subclass_names = ['BuiltinImporter', 'FrozenImporter', 'ExtensionFileLoader'] -tests = create_inheritance_tests(InspectLoader) -Frozen_InspectLoaderInheritanceTests, Source_InspectLoaderInheritanceTests = tests + +(Frozen_InspectLoaderInheritanceTests, + Source_InspectLoaderInheritanceTests + ) = test_util.test_both(InspectLoader, abc=abc) class ExecutionLoader(InheritanceTests): superclass_names = ['InspectLoader'] subclass_names = ['ExtensionFileLoader'] -tests = create_inheritance_tests(ExecutionLoader) -Frozen_ExecutionLoaderInheritanceTests, Source_ExecutionLoaderInheritanceTests = tests + +(Frozen_ExecutionLoaderInheritanceTests, + Source_ExecutionLoaderInheritanceTests + ) = test_util.test_both(ExecutionLoader, abc=abc) class FileLoader(InheritanceTests): superclass_names = ['ResourceLoader', 'ExecutionLoader'] subclass_names = ['SourceFileLoader', 'SourcelessFileLoader'] -tests = create_inheritance_tests(FileLoader) -Frozen_FileLoaderInheritanceTests, Source_FileLoaderInheritanceTests = tests + +(Frozen_FileLoaderInheritanceTests, + Source_FileLoaderInheritanceTests + ) = test_util.test_both(FileLoader, abc=abc) class SourceLoader(InheritanceTests): superclass_names = ['ResourceLoader', 'ExecutionLoader'] subclass_names = ['SourceFileLoader'] -tests = create_inheritance_tests(SourceLoader) -Frozen_SourceLoaderInheritanceTests, Source_SourceLoaderInheritanceTests = tests + +(Frozen_SourceLoaderInheritanceTests, + Source_SourceLoaderInheritanceTests + ) = test_util.test_both(SourceLoader, abc=abc) + ##### Default return values #################################################### -def make_abc_subclasses(base_class): - classes = [] - for kind, abc in [('Frozen', frozen_abc), ('Source', source_abc)]: - name = '_'.join([kind, base_class.__name__]) - base_classes = base_class, getattr(abc, base_class.__name__) - classes.append(types.new_class(name, base_classes)) - return classes - -def make_return_value_tests(base_class, test_class): - frozen_class, source_class = make_abc_subclasses(base_class) - tests = [] - for prefix, class_in_test in [('Frozen', frozen_class), ('Source', source_class)]: - def set_ns(ns): - ns['ins'] = class_in_test() - tests.append(types.new_class('_'.join([prefix, test_class.__name__]), - (test_class, unittest.TestCase), - exec_body=set_ns)) - return tests + +def make_abc_subclasses(base_class, name=None, inst=False, **kwargs): + if name is None: + name = base_class.__name__ + base = {kind: getattr(splitabc, name) + for kind, splitabc in abc.items()} + return {cls._KIND: cls() if inst else cls + for cls in test_util.split_frozen(base_class, base, **kwargs)} + + +class ABCTestHarness: + + @property + def ins(self): + # Lazily set ins on the class. + cls = self.SPLIT[self._KIND] + ins = cls() + self.__class__.ins = ins + return ins class MetaPathFinder: @@ -149,10 +152,10 @@ class MetaPathFinder: def find_module(self, fullname, path): return super().find_module(fullname, path) -Frozen_MPF, Source_MPF = make_abc_subclasses(MetaPathFinder) +class MetaPathFinderDefaultsTests(ABCTestHarness): -class MetaPathFinderDefaultsTests: + SPLIT = make_abc_subclasses(MetaPathFinder) def test_find_module(self): # Default should return None. @@ -163,8 +166,9 @@ class MetaPathFinderDefaultsTests: self.ins.invalidate_caches() -tests = make_return_value_tests(MetaPathFinder, MetaPathFinderDefaultsTests) -Frozen_MPFDefaultTests, Source_MPFDefaultTests = tests +(Frozen_MPFDefaultTests, + Source_MPFDefaultTests + ) = test_util.test_both(MetaPathFinderDefaultsTests) class PathEntryFinder: @@ -172,10 +176,10 @@ class PathEntryFinder: def find_loader(self, fullname): return super().find_loader(fullname) -Frozen_PEF, Source_PEF = make_abc_subclasses(PathEntryFinder) +class PathEntryFinderDefaultsTests(ABCTestHarness): -class PathEntryFinderDefaultsTests: + SPLIT = make_abc_subclasses(PathEntryFinder) def test_find_loader(self): self.assertEqual((None, []), self.ins.find_loader('something')) @@ -188,8 +192,9 @@ class PathEntryFinderDefaultsTests: self.ins.invalidate_caches() -tests = make_return_value_tests(PathEntryFinder, PathEntryFinderDefaultsTests) -Frozen_PEFDefaultTests, Source_PEFDefaultTests = tests +(Frozen_PEFDefaultTests, + Source_PEFDefaultTests + ) = test_util.test_both(PathEntryFinderDefaultsTests) class Loader: @@ -198,10 +203,9 @@ class Loader: return super().load_module(fullname) -Frozen_L, Source_L = make_abc_subclasses(Loader) +class LoaderDefaultsTests(ABCTestHarness): - -class LoaderDefaultsTests: + SPLIT = make_abc_subclasses(Loader) def test_load_module(self): with self.assertRaises(ImportError): @@ -217,8 +221,9 @@ class LoaderDefaultsTests: self.assertTrue(repr(mod)) -tests = make_return_value_tests(Loader, LoaderDefaultsTests) -Frozen_LDefaultTests, SourceLDefaultTests = tests +(Frozen_LDefaultTests, + SourceLDefaultTests + ) = test_util.test_both(LoaderDefaultsTests) class ResourceLoader(Loader): @@ -227,18 +232,18 @@ class ResourceLoader(Loader): return super().get_data(path) -Frozen_RL, Source_RL = make_abc_subclasses(ResourceLoader) - +class ResourceLoaderDefaultsTests(ABCTestHarness): -class ResourceLoaderDefaultsTests: + SPLIT = make_abc_subclasses(ResourceLoader) def test_get_data(self): with self.assertRaises(IOError): self.ins.get_data('/some/path') -tests = make_return_value_tests(ResourceLoader, ResourceLoaderDefaultsTests) -Frozen_RLDefaultTests, Source_RLDefaultTests = tests +(Frozen_RLDefaultTests, + Source_RLDefaultTests + ) = test_util.test_both(ResourceLoaderDefaultsTests) class InspectLoader(Loader): @@ -250,10 +255,12 @@ class InspectLoader(Loader): return super().get_source(fullname) -Frozen_IL, Source_IL = make_abc_subclasses(InspectLoader) +SPLIT_IL = make_abc_subclasses(InspectLoader) -class InspectLoaderDefaultsTests: +class InspectLoaderDefaultsTests(ABCTestHarness): + + SPLIT = SPLIT_IL def test_is_package(self): with self.assertRaises(ImportError): @@ -264,8 +271,9 @@ class InspectLoaderDefaultsTests: self.ins.get_source('blah') -tests = make_return_value_tests(InspectLoader, InspectLoaderDefaultsTests) -Frozen_ILDefaultTests, Source_ILDefaultTests = tests +(Frozen_ILDefaultTests, + Source_ILDefaultTests + ) = test_util.test_both(InspectLoaderDefaultsTests) class ExecutionLoader(InspectLoader): @@ -273,21 +281,25 @@ class ExecutionLoader(InspectLoader): def get_filename(self, fullname): return super().get_filename(fullname) -Frozen_EL, Source_EL = make_abc_subclasses(ExecutionLoader) + +SPLIT_EL = make_abc_subclasses(ExecutionLoader) -class ExecutionLoaderDefaultsTests: +class ExecutionLoaderDefaultsTests(ABCTestHarness): + + SPLIT = SPLIT_EL def test_get_filename(self): with self.assertRaises(ImportError): self.ins.get_filename('blah') -tests = make_return_value_tests(ExecutionLoader, InspectLoaderDefaultsTests) -Frozen_ELDefaultTests, Source_ELDefaultsTests = tests +(Frozen_ELDefaultTests, + Source_ELDefaultsTests + ) = test_util.test_both(InspectLoaderDefaultsTests) -##### MetaPathFinder concrete methods ########################################## +##### MetaPathFinder concrete methods ########################################## class MetaPathFinderFindModuleTests: @classmethod @@ -317,13 +329,12 @@ class MetaPathFinderFindModuleTests: self.assertIs(found, spec.loader) -Frozen_MPFFindModuleTests, Source_MPFFindModuleTests = util.test_both( - MetaPathFinderFindModuleTests, - abc=(frozen_abc, source_abc), - util=(frozen_util, source_util)) +(Frozen_MPFFindModuleTests, + Source_MPFFindModuleTests + ) = test_util.test_both(MetaPathFinderFindModuleTests, abc=abc, util=util) -##### PathEntryFinder concrete methods ######################################### +##### PathEntryFinder concrete methods ######################################### class PathEntryFinderFindLoaderTests: @classmethod @@ -361,11 +372,10 @@ class PathEntryFinderFindLoaderTests: self.assertEqual(paths, found[1]) -Frozen_PEFFindLoaderTests, Source_PEFFindLoaderTests = util.test_both( - PathEntryFinderFindLoaderTests, - abc=(frozen_abc, source_abc), - machinery=machinery, - util=(frozen_util, source_util)) +(Frozen_PEFFindLoaderTests, + Source_PEFFindLoaderTests + ) = test_util.test_both(PathEntryFinderFindLoaderTests, abc=abc, util=util, + machinery=machinery) ##### Loader concrete methods ################################################## @@ -386,7 +396,7 @@ class LoaderLoadModuleTests: def test_fresh(self): loader = self.loader() name = 'blah' - with util.uncache(name): + with test_util.uncache(name): loader.load_module(name) module = loader.found self.assertIs(sys.modules[name], module) @@ -404,7 +414,7 @@ class LoaderLoadModuleTests: module = types.ModuleType(name) module.__spec__ = self.util.spec_from_loader(name, loader) module.__loader__ = loader - with util.uncache(name): + with test_util.uncache(name): sys.modules[name] = module loader.load_module(name) found = loader.found @@ -412,10 +422,9 @@ class LoaderLoadModuleTests: self.assertIs(module, sys.modules[name]) -Frozen_LoaderLoadModuleTests, Source_LoaderLoadModuleTests = util.test_both( - LoaderLoadModuleTests, - abc=(frozen_abc, source_abc), - util=(frozen_util, source_util)) +(Frozen_LoaderLoadModuleTests, + Source_LoaderLoadModuleTests + ) = test_util.test_both(LoaderLoadModuleTests, abc=abc, util=util) ##### InspectLoader concrete methods ########################################### @@ -461,11 +470,10 @@ class InspectLoaderSourceToCodeTests: self.assertEqual(code.co_filename, '<string>') -class Frozen_ILSourceToCodeTests(InspectLoaderSourceToCodeTests, unittest.TestCase): - InspectLoaderSubclass = Frozen_IL - -class Source_ILSourceToCodeTests(InspectLoaderSourceToCodeTests, unittest.TestCase): - InspectLoaderSubclass = Source_IL +(Frozen_ILSourceToCodeTests, + Source_ILSourceToCodeTests + ) = test_util.test_both(InspectLoaderSourceToCodeTests, + InspectLoaderSubclass=SPLIT_IL) class InspectLoaderGetCodeTests: @@ -495,11 +503,10 @@ class InspectLoaderGetCodeTests: loader.get_code('blah') -class Frozen_ILGetCodeTests(InspectLoaderGetCodeTests, unittest.TestCase): - InspectLoaderSubclass = Frozen_IL - -class Source_ILGetCodeTests(InspectLoaderGetCodeTests, unittest.TestCase): - InspectLoaderSubclass = Source_IL +(Frozen_ILGetCodeTests, + Source_ILGetCodeTests + ) = test_util.test_both(InspectLoaderGetCodeTests, + InspectLoaderSubclass=SPLIT_IL) class InspectLoaderLoadModuleTests: @@ -543,11 +550,10 @@ class InspectLoaderLoadModuleTests: self.assertEqual(module, sys.modules[self.module_name]) -class Frozen_ILLoadModuleTests(InspectLoaderLoadModuleTests, unittest.TestCase): - InspectLoaderSubclass = Frozen_IL - -class Source_ILLoadModuleTests(InspectLoaderLoadModuleTests, unittest.TestCase): - InspectLoaderSubclass = Source_IL +(Frozen_ILLoadModuleTests, + Source_ILLoadModuleTests + ) = test_util.test_both(InspectLoaderLoadModuleTests, + InspectLoaderSubclass=SPLIT_IL) ##### ExecutionLoader concrete methods ######################################### @@ -608,15 +614,14 @@ class ExecutionLoaderGetCodeTests: self.assertEqual(module.attr, 42) -class Frozen_ELGetCodeTests(ExecutionLoaderGetCodeTests, unittest.TestCase): - ExecutionLoaderSubclass = Frozen_EL - -class Source_ELGetCodeTests(ExecutionLoaderGetCodeTests, unittest.TestCase): - ExecutionLoaderSubclass = Source_EL +(Frozen_ELGetCodeTests, + Source_ELGetCodeTests + ) = test_util.test_both(ExecutionLoaderGetCodeTests, + ExecutionLoaderSubclass=SPLIT_EL) ##### SourceLoader concrete methods ############################################ -class SourceLoader: +class SourceOnlyLoader: # Globals that should be defined for all modules. source = (b"_ = '::'.join([__name__, __file__, __cached__, __package__, " @@ -637,10 +642,10 @@ class SourceLoader: return '<module>' -Frozen_SourceOnlyL, Source_SourceOnlyL = make_abc_subclasses(SourceLoader) +SPLIT_SOL = make_abc_subclasses(SourceOnlyLoader, 'SourceLoader') -class SourceLoader(SourceLoader): +class SourceLoader(SourceOnlyLoader): source_mtime = 1 @@ -677,11 +682,7 @@ class SourceLoader(SourceLoader): return path == self.bytecode_path -Frozen_SL, Source_SL = make_abc_subclasses(SourceLoader) -Frozen_SL.util = frozen_util -Source_SL.util = source_util -Frozen_SL.init = frozen_init -Source_SL.init = source_init +SPLIT_SL = make_abc_subclasses(SourceLoader, util=util, init=init) class SourceLoaderTestHarness: @@ -765,7 +766,7 @@ class SourceOnlyLoaderTests(SourceLoaderTestHarness): # Loading a module should set __name__, __loader__, __package__, # __path__ (for packages), __file__, and __cached__. # The module should also be put into sys.modules. - with util.uncache(self.name): + with test_util.uncache(self.name): with warnings.catch_warnings(): warnings.simplefilter('ignore', DeprecationWarning) module = self.loader.load_module(self.name) @@ -778,7 +779,7 @@ class SourceOnlyLoaderTests(SourceLoaderTestHarness): # is a package. # Testing the values for a package are covered by test_load_module. self.setUp(is_package=False) - with util.uncache(self.name): + with test_util.uncache(self.name): with warnings.catch_warnings(): warnings.simplefilter('ignore', DeprecationWarning) module = self.loader.load_module(self.name) @@ -798,13 +799,10 @@ class SourceOnlyLoaderTests(SourceLoaderTestHarness): self.assertEqual(returned_source, source) -class Frozen_SourceOnlyLTests(SourceOnlyLoaderTests, unittest.TestCase): - loader_mock = Frozen_SourceOnlyL - util = frozen_util - -class Source_SourceOnlyLTests(SourceOnlyLoaderTests, unittest.TestCase): - loader_mock = Source_SourceOnlyL - util = source_util +(Frozen_SourceOnlyLoaderTests, + Source_SourceOnlyLoaderTests + ) = test_util.test_both(SourceOnlyLoaderTests, util=util, + loader_mock=SPLIT_SOL) @unittest.skipIf(sys.dont_write_bytecode, "sys.dont_write_bytecode is true") @@ -896,15 +894,10 @@ class SourceLoaderBytecodeTests(SourceLoaderTestHarness): self.verify_code(code_object) -class Frozen_SLBytecodeTests(SourceLoaderBytecodeTests, unittest.TestCase): - loader_mock = Frozen_SL - init = frozen_init - util = frozen_util - -class SourceSLBytecodeTests(SourceLoaderBytecodeTests, unittest.TestCase): - loader_mock = Source_SL - init = source_init - util = source_util +(Frozen_SLBytecodeTests, + SourceSLBytecodeTests + ) = test_util.test_both(SourceLoaderBytecodeTests, init=init, util=util, + loader_mock=SPLIT_SL) class SourceLoaderGetSourceTests: @@ -940,11 +933,10 @@ class SourceLoaderGetSourceTests: self.assertEqual(mock.get_source(name), expect) -class Frozen_SourceOnlyLGetSourceTests(SourceLoaderGetSourceTests, unittest.TestCase): - SourceOnlyLoaderMock = Frozen_SourceOnlyL - -class Source_SourceOnlyLGetSourceTests(SourceLoaderGetSourceTests, unittest.TestCase): - SourceOnlyLoaderMock = Source_SourceOnlyL +(Frozen_SourceOnlyLoaderGetSourceTests, + Source_SourceOnlyLoaderGetSourceTests + ) = test_util.test_both(SourceLoaderGetSourceTests, + SourceOnlyLoaderMock=SPLIT_SOL) if __name__ == '__main__': diff --git a/Lib/test/test_importlib/test_api.py b/Lib/test/test_importlib/test_api.py index 2a2d42b..6bc3c56 100644 --- a/Lib/test/test_importlib/test_api.py +++ b/Lib/test/test_importlib/test_api.py @@ -1,8 +1,8 @@ -from . import util +from . import util as test_util -frozen_init, source_init = util.import_importlib('importlib') -frozen_util, source_util = util.import_importlib('importlib.util') -frozen_machinery, source_machinery = util.import_importlib('importlib.machinery') +init = test_util.import_importlib('importlib') +util = test_util.import_importlib('importlib.util') +machinery = test_util.import_importlib('importlib.machinery') import os.path import sys @@ -18,8 +18,8 @@ class ImportModuleTests: def test_module_import(self): # Test importing a top-level module. - with util.mock_modules('top_level') as mock: - with util.import_state(meta_path=[mock]): + with test_util.mock_modules('top_level') as mock: + with test_util.import_state(meta_path=[mock]): module = self.init.import_module('top_level') self.assertEqual(module.__name__, 'top_level') @@ -28,8 +28,8 @@ class ImportModuleTests: pkg_name = 'pkg' pkg_long_name = '{0}.__init__'.format(pkg_name) name = '{0}.mod'.format(pkg_name) - with util.mock_modules(pkg_long_name, name) as mock: - with util.import_state(meta_path=[mock]): + with test_util.mock_modules(pkg_long_name, name) as mock: + with test_util.import_state(meta_path=[mock]): module = self.init.import_module(name) self.assertEqual(module.__name__, name) @@ -40,16 +40,16 @@ class ImportModuleTests: module_name = 'mod' absolute_name = '{0}.{1}'.format(pkg_name, module_name) relative_name = '.{0}'.format(module_name) - with util.mock_modules(pkg_long_name, absolute_name) as mock: - with util.import_state(meta_path=[mock]): + with test_util.mock_modules(pkg_long_name, absolute_name) as mock: + with test_util.import_state(meta_path=[mock]): self.init.import_module(pkg_name) module = self.init.import_module(relative_name, pkg_name) self.assertEqual(module.__name__, absolute_name) def test_deep_relative_package_import(self): modules = ['a.__init__', 'a.b.__init__', 'a.c'] - with util.mock_modules(*modules) as mock: - with util.import_state(meta_path=[mock]): + with test_util.mock_modules(*modules) as mock: + with test_util.import_state(meta_path=[mock]): self.init.import_module('a') self.init.import_module('a.b') module = self.init.import_module('..c', 'a.b') @@ -61,8 +61,8 @@ class ImportModuleTests: pkg_name = 'pkg' pkg_long_name = '{0}.__init__'.format(pkg_name) name = '{0}.mod'.format(pkg_name) - with util.mock_modules(pkg_long_name, name) as mock: - with util.import_state(meta_path=[mock]): + with test_util.mock_modules(pkg_long_name, name) as mock: + with test_util.import_state(meta_path=[mock]): self.init.import_module(pkg_name) module = self.init.import_module(name, pkg_name) self.assertEqual(module.__name__, name) @@ -86,16 +86,15 @@ class ImportModuleTests: b_load_count += 1 code = {'a': load_a, 'a.b': load_b} modules = ['a.__init__', 'a.b'] - with util.mock_modules(*modules, module_code=code) as mock: - with util.import_state(meta_path=[mock]): + with test_util.mock_modules(*modules, module_code=code) as mock: + with test_util.import_state(meta_path=[mock]): self.init.import_module('a.b') self.assertEqual(b_load_count, 1) -class Frozen_ImportModuleTests(ImportModuleTests, unittest.TestCase): - init = frozen_init -class Source_ImportModuleTests(ImportModuleTests, unittest.TestCase): - init = source_init +(Frozen_ImportModuleTests, + Source_ImportModuleTests + ) = test_util.test_both(ImportModuleTests, init=init) class FindLoaderTests: @@ -107,7 +106,7 @@ class FindLoaderTests: def test_sys_modules(self): # If a module with __loader__ is in sys.modules, then return it. name = 'some_mod' - with util.uncache(name): + with test_util.uncache(name): module = types.ModuleType(name) loader = 'a loader!' module.__loader__ = loader @@ -120,7 +119,7 @@ class FindLoaderTests: def test_sys_modules_loader_is_None(self): # If sys.modules[name].__loader__ is None, raise ValueError. name = 'some_mod' - with util.uncache(name): + with test_util.uncache(name): module = types.ModuleType(name) module.__loader__ = None sys.modules[name] = module @@ -133,7 +132,7 @@ class FindLoaderTests: # Should raise ValueError # Issue #17099 name = 'some_mod' - with util.uncache(name): + with test_util.uncache(name): module = types.ModuleType(name) try: del module.__loader__ @@ -148,8 +147,8 @@ class FindLoaderTests: def test_success(self): # Return the loader found on sys.meta_path. name = 'some_mod' - with util.uncache(name): - with util.import_state(meta_path=[self.FakeMetaFinder]): + with test_util.uncache(name): + with test_util.import_state(meta_path=[self.FakeMetaFinder]): with warnings.catch_warnings(): warnings.simplefilter('ignore', DeprecationWarning) self.assertEqual((name, None), self.init.find_loader(name)) @@ -158,8 +157,8 @@ class FindLoaderTests: # Searching on a path should work. name = 'some_mod' path = 'path to some place' - with util.uncache(name): - with util.import_state(meta_path=[self.FakeMetaFinder]): + with test_util.uncache(name): + with test_util.import_state(meta_path=[self.FakeMetaFinder]): with warnings.catch_warnings(): warnings.simplefilter('ignore', DeprecationWarning) self.assertEqual((name, path), @@ -171,11 +170,10 @@ class FindLoaderTests: warnings.simplefilter('ignore', DeprecationWarning) self.assertIsNone(self.init.find_loader('nevergoingtofindthismodule')) -class Frozen_FindLoaderTests(FindLoaderTests, unittest.TestCase): - init = frozen_init -class Source_FindLoaderTests(FindLoaderTests, unittest.TestCase): - init = source_init +(Frozen_FindLoaderTests, + Source_FindLoaderTests + ) = test_util.test_both(FindLoaderTests, init=init) class ReloadTests: @@ -195,10 +193,10 @@ class ReloadTests: module = type(sys)('top_level') module.spam = 3 sys.modules['top_level'] = module - mock = util.mock_modules('top_level', - module_code={'top_level': code}) + mock = test_util.mock_modules('top_level', + module_code={'top_level': code}) with mock: - with util.import_state(meta_path=[mock]): + with test_util.import_state(meta_path=[mock]): module = self.init.import_module('top_level') reloaded = self.init.reload(module) actual = sys.modules['top_level'] @@ -230,7 +228,7 @@ class ReloadTests: def test_reload_location_changed(self): name = 'spam' with support.temp_cwd(None) as cwd: - with util.uncache('spam'): + with test_util.uncache('spam'): with support.DirsOnSysPath(cwd): # Start as a plain module. self.init.invalidate_caches() @@ -281,7 +279,7 @@ class ReloadTests: def test_reload_namespace_changed(self): name = 'spam' with support.temp_cwd(None) as cwd: - with util.uncache('spam'): + with test_util.uncache('spam'): with support.DirsOnSysPath(cwd): # Start as a namespace package. self.init.invalidate_caches() @@ -338,20 +336,16 @@ class ReloadTests: # See #19851. name = 'spam' subname = 'ham' - with util.temp_module(name, pkg=True) as pkg_dir: - fullname, _ = util.submodule(name, subname, pkg_dir) + with test_util.temp_module(name, pkg=True) as pkg_dir: + fullname, _ = test_util.submodule(name, subname, pkg_dir) ham = self.init.import_module(fullname) reloaded = self.init.reload(ham) self.assertIs(reloaded, ham) -class Frozen_ReloadTests(ReloadTests, unittest.TestCase): - init = frozen_init - util = frozen_util - -class Source_ReloadTests(ReloadTests, unittest.TestCase): - init = source_init - util = source_util +(Frozen_ReloadTests, + Source_ReloadTests + ) = test_util.test_both(ReloadTests, init=init, util=util) class InvalidateCacheTests: @@ -384,11 +378,10 @@ class InvalidateCacheTests: self.addCleanup(lambda: sys.path_importer_cache.__delitem__(key)) self.init.invalidate_caches() # Shouldn't trigger an exception. -class Frozen_InvalidateCacheTests(InvalidateCacheTests, unittest.TestCase): - init = frozen_init -class Source_InvalidateCacheTests(InvalidateCacheTests, unittest.TestCase): - init = source_init +(Frozen_InvalidateCacheTests, + Source_InvalidateCacheTests + ) = test_util.test_both(InvalidateCacheTests, init=init) class FrozenImportlibTests(unittest.TestCase): @@ -398,6 +391,7 @@ class FrozenImportlibTests(unittest.TestCase): # Can't do an isinstance() check since separate copies of importlib # may have been used for import, so just check the name is not for the # frozen loader. + source_init = init['Source'] self.assertNotEqual(source_init.__loader__.__class__.__name__, 'FrozenImporter') @@ -426,11 +420,10 @@ class StartupTests: elif self.machinery.FrozenImporter.find_module(name): self.assertIsNot(module.__spec__, None) -class Frozen_StartupTests(StartupTests, unittest.TestCase): - machinery = frozen_machinery -class Source_StartupTests(StartupTests, unittest.TestCase): - machinery = source_machinery +(Frozen_StartupTests, + Source_StartupTests + ) = test_util.test_both(StartupTests, machinery=machinery) if __name__ == '__main__': diff --git a/Lib/test/test_importlib/test_lazy.py b/Lib/test/test_importlib/test_lazy.py new file mode 100644 index 0000000..2e191bb --- /dev/null +++ b/Lib/test/test_importlib/test_lazy.py @@ -0,0 +1,132 @@ +import importlib +from importlib import abc +from importlib import util +import unittest + +from . import util as test_util + + +class CollectInit: + + def __init__(self, *args, **kwargs): + self.args = args + self.kwargs = kwargs + + def exec_module(self, module): + return self + + +class LazyLoaderFactoryTests(unittest.TestCase): + + def test_init(self): + factory = util.LazyLoader.factory(CollectInit) + # E.g. what importlib.machinery.FileFinder instantiates loaders with + # plus keyword arguments. + lazy_loader = factory('module name', 'module path', kw='kw') + loader = lazy_loader.loader + self.assertEqual(('module name', 'module path'), loader.args) + self.assertEqual({'kw': 'kw'}, loader.kwargs) + + def test_validation(self): + # No exec_module(), no lazy loading. + with self.assertRaises(TypeError): + util.LazyLoader.factory(object) + + +class TestingImporter(abc.MetaPathFinder, abc.Loader): + + module_name = 'lazy_loader_test' + mutated_name = 'changed' + loaded = None + source_code = 'attr = 42; __name__ = {!r}'.format(mutated_name) + + def find_spec(self, name, path, target=None): + if name != self.module_name: + return None + return util.spec_from_loader(name, util.LazyLoader(self)) + + def exec_module(self, module): + exec(self.source_code, module.__dict__) + self.loaded = module + + +class LazyLoaderTests(unittest.TestCase): + + def test_init(self): + with self.assertRaises(TypeError): + util.LazyLoader(object) + + def new_module(self, source_code=None): + loader = TestingImporter() + if source_code is not None: + loader.source_code = source_code + spec = util.spec_from_loader(TestingImporter.module_name, + util.LazyLoader(loader)) + module = spec.loader.create_module(spec) + module.__spec__ = spec + module.__loader__ = spec.loader + spec.loader.exec_module(module) + # Module is now lazy. + self.assertIsNone(loader.loaded) + return module + + def test_e2e(self): + # End-to-end test to verify the load is in fact lazy. + importer = TestingImporter() + assert importer.loaded is None + with test_util.uncache(importer.module_name): + with test_util.import_state(meta_path=[importer]): + module = importlib.import_module(importer.module_name) + self.assertIsNone(importer.loaded) + # Trigger load. + self.assertEqual(module.__loader__, importer) + self.assertIsNotNone(importer.loaded) + self.assertEqual(module, importer.loaded) + + def test_attr_unchanged(self): + # An attribute only mutated as a side-effect of import should not be + # changed needlessly. + module = self.new_module() + self.assertEqual(TestingImporter.mutated_name, module.__name__) + + def test_new_attr(self): + # A new attribute should persist. + module = self.new_module() + module.new_attr = 42 + self.assertEqual(42, module.new_attr) + + def test_mutated_preexisting_attr(self): + # Changing an attribute that already existed on the module -- + # e.g. __name__ -- should persist. + module = self.new_module() + module.__name__ = 'bogus' + self.assertEqual('bogus', module.__name__) + + def test_mutated_attr(self): + # Changing an attribute that comes into existence after an import + # should persist. + module = self.new_module() + module.attr = 6 + self.assertEqual(6, module.attr) + + def test_delete_eventual_attr(self): + # Deleting an attribute should stay deleted. + module = self.new_module() + del module.attr + self.assertFalse(hasattr(module, 'attr')) + + def test_delete_preexisting_attr(self): + module = self.new_module() + del module.__name__ + self.assertFalse(hasattr(module, '__name__')) + + def test_module_substitution_error(self): + source_code = 'import sys; sys.modules[__name__] = 42' + module = self.new_module(source_code) + with test_util.uncache(TestingImporter.module_name): + with self.assertRaises(ValueError): + module.__name__ + + +if __name__ == '__main__': + unittest.main() diff --git a/Lib/test/test_importlib/test_locks.py b/Lib/test/test_importlib/test_locks.py index dc97ba1..df0af12 100644 --- a/Lib/test/test_importlib/test_locks.py +++ b/Lib/test/test_importlib/test_locks.py @@ -1,7 +1,6 @@ -from . import util -frozen_init, source_init = util.import_importlib('importlib') -frozen_bootstrap = frozen_init._bootstrap -source_bootstrap = source_init._bootstrap +from . import util as test_util + +init = test_util.import_importlib('importlib') import sys import time @@ -32,14 +31,20 @@ if threading is not None: test_timeout = None # _release_save() unsupported test_release_save_unacquired = None + # lock status in repr unsupported + test_repr = None + test_locked_repr = None - class Frozen_ModuleLockAsRLockTests(ModuleLockAsRLockTests, lock_tests.RLockTests): - LockType = frozen_bootstrap._ModuleLock - - class Source_ModuleLockAsRLockTests(ModuleLockAsRLockTests, lock_tests.RLockTests): - LockType = source_bootstrap._ModuleLock + LOCK_TYPES = {kind: splitinit._bootstrap._ModuleLock + for kind, splitinit in init.items()} + (Frozen_ModuleLockAsRLockTests, + Source_ModuleLockAsRLockTests + ) = test_util.test_both(ModuleLockAsRLockTests, lock_tests.RLockTests, + LockType=LOCK_TYPES) else: + LOCK_TYPES = {} + class Frozen_ModuleLockAsRLockTests(unittest.TestCase): pass @@ -47,78 +52,94 @@ else: pass -class DeadlockAvoidanceTests: - - def setUp(self): - try: - self.old_switchinterval = sys.getswitchinterval() - sys.setswitchinterval(0.000001) - except AttributeError: - self.old_switchinterval = None - - def tearDown(self): - if self.old_switchinterval is not None: - sys.setswitchinterval(self.old_switchinterval) - - def run_deadlock_avoidance_test(self, create_deadlock): - NLOCKS = 10 - locks = [self.LockType(str(i)) for i in range(NLOCKS)] - pairs = [(locks[i], locks[(i+1)%NLOCKS]) for i in range(NLOCKS)] - if create_deadlock: - NTHREADS = NLOCKS - else: - NTHREADS = NLOCKS - 1 - barrier = threading.Barrier(NTHREADS) - results = [] - def _acquire(lock): - """Try to acquire the lock. Return True on success, False on deadlock.""" +if threading is not None: + class DeadlockAvoidanceTests: + + def setUp(self): try: - lock.acquire() - except self.DeadlockError: - return False + self.old_switchinterval = sys.getswitchinterval() + sys.setswitchinterval(0.000001) + except AttributeError: + self.old_switchinterval = None + + def tearDown(self): + if self.old_switchinterval is not None: + sys.setswitchinterval(self.old_switchinterval) + + def run_deadlock_avoidance_test(self, create_deadlock): + NLOCKS = 10 + locks = [self.LockType(str(i)) for i in range(NLOCKS)] + pairs = [(locks[i], locks[(i+1)%NLOCKS]) for i in range(NLOCKS)] + if create_deadlock: + NTHREADS = NLOCKS else: - return True - def f(): - a, b = pairs.pop() - ra = _acquire(a) - barrier.wait() - rb = _acquire(b) - results.append((ra, rb)) - if rb: - b.release() - if ra: - a.release() - lock_tests.Bunch(f, NTHREADS).wait_for_finished() - self.assertEqual(len(results), NTHREADS) - return results - - def test_deadlock(self): - results = self.run_deadlock_avoidance_test(True) - # At least one of the threads detected a potential deadlock on its - # second acquire() call. It may be several of them, because the - # deadlock avoidance mechanism is conservative. - nb_deadlocks = results.count((True, False)) - self.assertGreaterEqual(nb_deadlocks, 1) - self.assertEqual(results.count((True, True)), len(results) - nb_deadlocks) - - def test_no_deadlock(self): - results = self.run_deadlock_avoidance_test(False) - self.assertEqual(results.count((True, False)), 0) - self.assertEqual(results.count((True, True)), len(results)) - -@unittest.skipUnless(threading, "threads needed for this test") -class Frozen_DeadlockAvoidanceTests(DeadlockAvoidanceTests, unittest.TestCase): - LockType = frozen_bootstrap._ModuleLock - DeadlockError = frozen_bootstrap._DeadlockError - -@unittest.skipUnless(threading, "threads needed for this test") -class Source_DeadlockAvoidanceTests(DeadlockAvoidanceTests, unittest.TestCase): - LockType = source_bootstrap._ModuleLock - DeadlockError = source_bootstrap._DeadlockError + NTHREADS = NLOCKS - 1 + barrier = threading.Barrier(NTHREADS) + results = [] + + def _acquire(lock): + """Try to acquire the lock. Return True on success, + False on deadlock.""" + try: + lock.acquire() + except self.DeadlockError: + return False + else: + return True + + def f(): + a, b = pairs.pop() + ra = _acquire(a) + barrier.wait() + rb = _acquire(b) + results.append((ra, rb)) + if rb: + b.release() + if ra: + a.release() + lock_tests.Bunch(f, NTHREADS).wait_for_finished() + self.assertEqual(len(results), NTHREADS) + return results + + def test_deadlock(self): + results = self.run_deadlock_avoidance_test(True) + # At least one of the threads detected a potential deadlock on its + # second acquire() call. It may be several of them, because the + # deadlock avoidance mechanism is conservative. + nb_deadlocks = results.count((True, False)) + self.assertGreaterEqual(nb_deadlocks, 1) + self.assertEqual(results.count((True, True)), len(results) - nb_deadlocks) + + def test_no_deadlock(self): + results = self.run_deadlock_avoidance_test(False) + self.assertEqual(results.count((True, False)), 0) + self.assertEqual(results.count((True, True)), len(results)) + + + DEADLOCK_ERRORS = {kind: splitinit._bootstrap._DeadlockError + for kind, splitinit in init.items()} + + (Frozen_DeadlockAvoidanceTests, + Source_DeadlockAvoidanceTests + ) = test_util.test_both(DeadlockAvoidanceTests, + LockType=LOCK_TYPES, + DeadlockError=DEADLOCK_ERRORS) +else: + DEADLOCK_ERRORS = {} + + class Frozen_DeadlockAvoidanceTests(unittest.TestCase): + pass + + class Source_DeadlockAvoidanceTests(unittest.TestCase): + pass class LifetimeTests: + @property + def bootstrap(self): + return self.init._bootstrap + def test_lock_lifetime(self): name = "xyzzy" self.assertNotIn(name, self.bootstrap._module_locks) @@ -135,11 +156,10 @@ class LifetimeTests: self.assertEqual(0, len(self.bootstrap._module_locks), self.bootstrap._module_locks) -class Frozen_LifetimeTests(LifetimeTests, unittest.TestCase): - bootstrap = frozen_bootstrap -class Source_LifetimeTests(LifetimeTests, unittest.TestCase): - bootstrap = source_bootstrap +(Frozen_LifetimeTests, + Source_LifetimeTests + ) = test_util.test_both(LifetimeTests, init=init) @support.reap_threads diff --git a/Lib/test/test_importlib/test_spec.py b/Lib/test/test_importlib/test_spec.py index 71541f6..8b333e8 100644 --- a/Lib/test/test_importlib/test_spec.py +++ b/Lib/test/test_importlib/test_spec.py @@ -1,10 +1,8 @@ -from . import util +from . import util as test_util -frozen_init, source_init = util.import_importlib('importlib') -frozen_bootstrap = frozen_init._bootstrap -source_bootstrap = source_init._bootstrap -frozen_machinery, source_machinery = util.import_importlib('importlib.machinery') -frozen_util, source_util = util.import_importlib('importlib.util') +init = test_util.import_importlib('importlib') +machinery = test_util.import_importlib('importlib.machinery') +util = test_util.import_importlib('importlib.util') import os.path from test.support import CleanImport @@ -36,6 +34,9 @@ class TestLoader: def _is_package(self, name): return self.package + def create_module(self, spec): + return None + class NewLoader(TestLoader): @@ -52,6 +53,8 @@ class LegacyLoader(TestLoader): with warnings.catch_warnings(): warnings.simplefilter("ignore", DeprecationWarning) + frozen_util = util['Frozen'] + @frozen_util.module_for_loader def load_module(self, module): module.ham = self.HAM @@ -221,18 +224,17 @@ class ModuleSpecTests: self.assertEqual(self.loc_spec.cached, 'spam.pyc') -class Frozen_ModuleSpecTests(ModuleSpecTests, unittest.TestCase): - util = frozen_util - machinery = frozen_machinery - - -class Source_ModuleSpecTests(ModuleSpecTests, unittest.TestCase): - util = source_util - machinery = source_machinery +(Frozen_ModuleSpecTests, + Source_ModuleSpecTests + ) = test_util.test_both(ModuleSpecTests, util=util, machinery=machinery) class ModuleSpecMethodsTests: + @property + def bootstrap(self): + return self.init._bootstrap + def setUp(self): self.name = 'spam' self.path = 'spam.py' @@ -243,152 +245,14 @@ class ModuleSpecMethodsTests: origin=self.path) self.loc_spec._set_fileattr = True - # init_module_attrs - - def test_init_module_attrs(self): - module = type(sys)(self.name) - spec = self.machinery.ModuleSpec(self.name, self.loader) - self.bootstrap._SpecMethods(spec).init_module_attrs(module) - - self.assertEqual(module.__name__, spec.name) - self.assertIs(module.__loader__, spec.loader) - self.assertEqual(module.__package__, spec.parent) - self.assertIs(module.__spec__, spec) - self.assertFalse(hasattr(module, '__path__')) - self.assertFalse(hasattr(module, '__file__')) - self.assertFalse(hasattr(module, '__cached__')) - - def test_init_module_attrs_package(self): - module = type(sys)(self.name) - spec = self.machinery.ModuleSpec(self.name, self.loader) - spec.submodule_search_locations = ['spam', 'ham'] - self.bootstrap._SpecMethods(spec).init_module_attrs(module) - - self.assertEqual(module.__name__, spec.name) - self.assertIs(module.__loader__, spec.loader) - self.assertEqual(module.__package__, spec.parent) - self.assertIs(module.__spec__, spec) - self.assertIs(module.__path__, spec.submodule_search_locations) - self.assertFalse(hasattr(module, '__file__')) - self.assertFalse(hasattr(module, '__cached__')) - - def test_init_module_attrs_location(self): - module = type(sys)(self.name) - spec = self.loc_spec - self.bootstrap._SpecMethods(spec).init_module_attrs(module) - - self.assertEqual(module.__name__, spec.name) - self.assertIs(module.__loader__, spec.loader) - self.assertEqual(module.__package__, spec.parent) - self.assertIs(module.__spec__, spec) - self.assertFalse(hasattr(module, '__path__')) - self.assertEqual(module.__file__, spec.origin) - self.assertEqual(module.__cached__, - self.util.cache_from_source(spec.origin)) - - def test_init_module_attrs_different_name(self): - module = type(sys)('eggs') - spec = self.machinery.ModuleSpec(self.name, self.loader) - self.bootstrap._SpecMethods(spec).init_module_attrs(module) - - self.assertEqual(module.__name__, spec.name) - - def test_init_module_attrs_different_spec(self): - module = type(sys)(self.name) - module.__spec__ = self.machinery.ModuleSpec('eggs', object()) - spec = self.machinery.ModuleSpec(self.name, self.loader) - self.bootstrap._SpecMethods(spec).init_module_attrs(module) - - self.assertEqual(module.__name__, spec.name) - self.assertIs(module.__loader__, spec.loader) - self.assertEqual(module.__package__, spec.parent) - self.assertIs(module.__spec__, spec) - - def test_init_module_attrs_already_set(self): - module = type(sys)('ham.eggs') - module.__loader__ = object() - module.__package__ = 'ham' - module.__path__ = ['eggs'] - module.__file__ = 'ham/eggs/__init__.py' - module.__cached__ = self.util.cache_from_source(module.__file__) - original = vars(module).copy() - spec = self.loc_spec - spec.submodule_search_locations = [''] - self.bootstrap._SpecMethods(spec).init_module_attrs(module) - - self.assertIs(module.__loader__, original['__loader__']) - self.assertEqual(module.__package__, original['__package__']) - self.assertIs(module.__path__, original['__path__']) - self.assertEqual(module.__file__, original['__file__']) - self.assertEqual(module.__cached__, original['__cached__']) - - def test_init_module_attrs_immutable(self): - module = object() - spec = self.loc_spec - spec.submodule_search_locations = [''] - self.bootstrap._SpecMethods(spec).init_module_attrs(module) - - self.assertFalse(hasattr(module, '__name__')) - self.assertFalse(hasattr(module, '__loader__')) - self.assertFalse(hasattr(module, '__package__')) - self.assertFalse(hasattr(module, '__spec__')) - self.assertFalse(hasattr(module, '__path__')) - self.assertFalse(hasattr(module, '__file__')) - self.assertFalse(hasattr(module, '__cached__')) - - # create() - - def test_create(self): - created = self.bootstrap._SpecMethods(self.spec).create() - - self.assertEqual(created.__name__, self.spec.name) - self.assertIs(created.__loader__, self.spec.loader) - self.assertEqual(created.__package__, self.spec.parent) - self.assertIs(created.__spec__, self.spec) - self.assertFalse(hasattr(created, '__path__')) - self.assertFalse(hasattr(created, '__file__')) - self.assertFalse(hasattr(created, '__cached__')) - - def test_create_from_loader(self): - module = type(sys.implementation)() - class CreatingLoader(TestLoader): - def create_module(self, spec): - return module - self.spec.loader = CreatingLoader() - created = self.bootstrap._SpecMethods(self.spec).create() - - self.assertIs(created, module) - self.assertEqual(created.__name__, self.spec.name) - self.assertIs(created.__loader__, self.spec.loader) - self.assertEqual(created.__package__, self.spec.parent) - self.assertIs(created.__spec__, self.spec) - self.assertFalse(hasattr(created, '__path__')) - self.assertFalse(hasattr(created, '__file__')) - self.assertFalse(hasattr(created, '__cached__')) - - def test_create_from_loader_not_handled(self): - class CreatingLoader(TestLoader): - def create_module(self, spec): - return None - self.spec.loader = CreatingLoader() - created = self.bootstrap._SpecMethods(self.spec).create() - - self.assertEqual(created.__name__, self.spec.name) - self.assertIs(created.__loader__, self.spec.loader) - self.assertEqual(created.__package__, self.spec.parent) - self.assertIs(created.__spec__, self.spec) - self.assertFalse(hasattr(created, '__path__')) - self.assertFalse(hasattr(created, '__file__')) - self.assertFalse(hasattr(created, '__cached__')) - # exec() def test_exec(self): self.spec.loader = NewLoader() - module = self.bootstrap._SpecMethods(self.spec).create() + module = self.util.module_from_spec(self.spec) sys.modules[self.name] = module self.assertFalse(hasattr(module, 'eggs')) - self.bootstrap._SpecMethods(self.spec).exec(module) + self.bootstrap._exec(self.spec, module) self.assertEqual(module.eggs, 1) @@ -397,7 +261,7 @@ class ModuleSpecMethodsTests: def test_load(self): self.spec.loader = NewLoader() with CleanImport(self.spec.name): - loaded = self.bootstrap._SpecMethods(self.spec).load() + loaded = self.bootstrap._load(self.spec) installed = sys.modules[self.spec.name] self.assertEqual(loaded.eggs, 1) @@ -410,7 +274,7 @@ class ModuleSpecMethodsTests: sys.modules[module.__name__] = replacement self.spec.loader = ReplacingLoader() with CleanImport(self.spec.name): - loaded = self.bootstrap._SpecMethods(self.spec).load() + loaded = self.bootstrap._load(self.spec) installed = sys.modules[self.spec.name] self.assertIs(loaded, replacement) @@ -423,7 +287,7 @@ class ModuleSpecMethodsTests: self.spec.loader = FailedLoader() with CleanImport(self.spec.name): with self.assertRaises(RuntimeError): - loaded = self.bootstrap._SpecMethods(self.spec).load() + loaded = self.bootstrap._load(self.spec) self.assertNotIn(self.spec.name, sys.modules) def test_load_failed_removed(self): @@ -434,20 +298,20 @@ class ModuleSpecMethodsTests: self.spec.loader = FailedLoader() with CleanImport(self.spec.name): with self.assertRaises(RuntimeError): - loaded = self.bootstrap._SpecMethods(self.spec).load() + loaded = self.bootstrap._load(self.spec) self.assertNotIn(self.spec.name, sys.modules) def test_load_legacy(self): self.spec.loader = LegacyLoader() with CleanImport(self.spec.name): - loaded = self.bootstrap._SpecMethods(self.spec).load() + loaded = self.bootstrap._load(self.spec) self.assertEqual(loaded.ham, -1) def test_load_legacy_attributes(self): self.spec.loader = LegacyLoader() with CleanImport(self.spec.name): - loaded = self.bootstrap._SpecMethods(self.spec).load() + loaded = self.bootstrap._load(self.spec) self.assertIs(loaded.__loader__, self.spec.loader) self.assertEqual(loaded.__package__, self.spec.parent) @@ -461,7 +325,7 @@ class ModuleSpecMethodsTests: return module self.spec.loader = ImmutableLoader() with CleanImport(self.spec.name): - loaded = self.bootstrap._SpecMethods(self.spec).load() + loaded = self.bootstrap._load(self.spec) self.assertIs(sys.modules[self.spec.name], module) @@ -470,8 +334,8 @@ class ModuleSpecMethodsTests: def test_reload(self): self.spec.loader = NewLoader() with CleanImport(self.spec.name): - loaded = self.bootstrap._SpecMethods(self.spec).load() - reloaded = self.bootstrap._SpecMethods(self.spec).exec(loaded) + loaded = self.bootstrap._load(self.spec) + reloaded = self.bootstrap._exec(self.spec, loaded) installed = sys.modules[self.spec.name] self.assertEqual(loaded.eggs, 1) @@ -481,9 +345,9 @@ class ModuleSpecMethodsTests: def test_reload_modified(self): self.spec.loader = NewLoader() with CleanImport(self.spec.name): - loaded = self.bootstrap._SpecMethods(self.spec).load() + loaded = self.bootstrap._load(self.spec) loaded.eggs = 2 - reloaded = self.bootstrap._SpecMethods(self.spec).exec(loaded) + reloaded = self.bootstrap._exec(self.spec, loaded) self.assertEqual(loaded.eggs, 1) self.assertIs(reloaded, loaded) @@ -491,9 +355,9 @@ class ModuleSpecMethodsTests: def test_reload_extra_attributes(self): self.spec.loader = NewLoader() with CleanImport(self.spec.name): - loaded = self.bootstrap._SpecMethods(self.spec).load() + loaded = self.bootstrap._load(self.spec) loaded.available = False - reloaded = self.bootstrap._SpecMethods(self.spec).exec(loaded) + reloaded = self.bootstrap._exec(self.spec, loaded) self.assertFalse(loaded.available) self.assertIs(reloaded, loaded) @@ -501,12 +365,12 @@ class ModuleSpecMethodsTests: def test_reload_init_module_attrs(self): self.spec.loader = NewLoader() with CleanImport(self.spec.name): - loaded = self.bootstrap._SpecMethods(self.spec).load() + loaded = self.bootstrap._load(self.spec) loaded.__name__ = 'ham' del loaded.__loader__ del loaded.__package__ del loaded.__spec__ - self.bootstrap._SpecMethods(self.spec).exec(loaded) + self.bootstrap._exec(self.spec, loaded) self.assertEqual(loaded.__name__, self.spec.name) self.assertIs(loaded.__loader__, self.spec.loader) @@ -519,8 +383,8 @@ class ModuleSpecMethodsTests: def test_reload_legacy(self): self.spec.loader = LegacyLoader() with CleanImport(self.spec.name): - loaded = self.bootstrap._SpecMethods(self.spec).load() - reloaded = self.bootstrap._SpecMethods(self.spec).exec(loaded) + loaded = self.bootstrap._load(self.spec) + reloaded = self.bootstrap._exec(self.spec, loaded) installed = sys.modules[self.spec.name] self.assertEqual(loaded.ham, -1) @@ -528,20 +392,18 @@ class ModuleSpecMethodsTests: self.assertIs(installed, loaded) -class Frozen_ModuleSpecMethodsTests(ModuleSpecMethodsTests, unittest.TestCase): - bootstrap = frozen_bootstrap - machinery = frozen_machinery - util = frozen_util - - -class Source_ModuleSpecMethodsTests(ModuleSpecMethodsTests, unittest.TestCase): - bootstrap = source_bootstrap - machinery = source_machinery - util = source_util +(Frozen_ModuleSpecMethodsTests, + Source_ModuleSpecMethodsTests + ) = test_util.test_both(ModuleSpecMethodsTests, init=init, util=util, + machinery=machinery) class ModuleReprTests: + @property + def bootstrap(self): + return self.init._bootstrap + def setUp(self): self.module = type(os)('spam') self.spec = self.machinery.ModuleSpec('spam', TestLoader()) @@ -625,16 +487,10 @@ class ModuleReprTests: self.assertEqual(modrepr, '<module {!r}>'.format('spam')) -class Frozen_ModuleReprTests(ModuleReprTests, unittest.TestCase): - bootstrap = frozen_bootstrap - machinery = frozen_machinery - util = frozen_util - - -class Source_ModuleReprTests(ModuleReprTests, unittest.TestCase): - bootstrap = source_bootstrap - machinery = source_machinery - util = source_util +(Frozen_ModuleReprTests, + Source_ModuleReprTests + ) = test_util.test_both(ModuleReprTests, init=init, util=util, + machinery=machinery) class FactoryTests: @@ -787,13 +643,14 @@ class FactoryTests: # spec_from_file_location() def test_spec_from_file_location_default(self): - if self.machinery is source_machinery: - raise unittest.SkipTest('not sure why this is breaking...') spec = self.util.spec_from_file_location(self.name, self.path) self.assertEqual(spec.name, self.name) + # Need to use a circuitous route to get at importlib.machinery to make + # sure the same class object is used in the isinstance() check as + # would have been used to create the loader. self.assertIsInstance(spec.loader, - self.machinery.SourceFileLoader) + self.util.abc.machinery.SourceFileLoader) self.assertEqual(spec.loader.name, self.name) self.assertEqual(spec.loader.path, self.path) self.assertEqual(spec.origin, self.path) @@ -947,11 +804,10 @@ class FactoryTests: self.assertTrue(spec.has_location) -class Frozen_FactoryTests(FactoryTests, unittest.TestCase): - util = frozen_util - machinery = frozen_machinery +(Frozen_FactoryTests, + Source_FactoryTests + ) = test_util.test_both(FactoryTests, util=util, machinery=machinery) -class Source_FactoryTests(FactoryTests, unittest.TestCase): - util = source_util - machinery = source_machinery +if __name__ == '__main__': + unittest.main() diff --git a/Lib/test/test_importlib/test_util.py b/Lib/test/test_importlib/test_util.py index b2823c6..2493af7 100644 --- a/Lib/test/test_importlib/test_util.py +++ b/Lib/test/test_importlib/test_util.py @@ -1,8 +1,8 @@ -from importlib import util -from . import util as test_util -frozen_init, source_init = test_util.import_importlib('importlib') -frozen_machinery, source_machinery = test_util.import_importlib('importlib.machinery') -frozen_util, source_util = test_util.import_importlib('importlib.util') +from . import util +abc = util.import_importlib('importlib.abc') +init = util.import_importlib('importlib') +machinery = util.import_importlib('importlib.machinery') +importlib_util = util.import_importlib('importlib.util') import os import sys @@ -32,8 +32,94 @@ class DecodeSourceBytesTests: self.assertEqual(self.util.decode_source(source_bytes), '\n'.join([self.source, self.source])) -Frozen_DecodeSourceBytesTests, Source_DecodeSourceBytesTests = test_util.test_both( - DecodeSourceBytesTests, util=[frozen_util, source_util]) + +(Frozen_DecodeSourceBytesTests, + Source_DecodeSourceBytesTests + ) = util.test_both(DecodeSourceBytesTests, util=importlib_util) + + +class ModuleFromSpecTests: + + def test_no_create_module(self): + class Loader: + def exec_module(self, module): + pass + spec = self.machinery.ModuleSpec('test', Loader()) + with warnings.catch_warnings(record=True) as w: + warnings.simplefilter('always') + module = self.util.module_from_spec(spec) + self.assertEqual(1, len(w)) + self.assertTrue(issubclass(w[0].category, DeprecationWarning)) + self.assertIn('create_module', str(w[0].message)) + self.assertIsInstance(module, types.ModuleType) + self.assertEqual(module.__name__, spec.name) + + def test_create_module_returns_None(self): + class Loader(self.abc.Loader): + def create_module(self, spec): + return None + spec = self.machinery.ModuleSpec('test', Loader()) + module = self.util.module_from_spec(spec) + self.assertIsInstance(module, types.ModuleType) + self.assertEqual(module.__name__, spec.name) + + def test_create_module(self): + name = 'already set' + class CustomModule(types.ModuleType): + pass + class Loader(self.abc.Loader): + def create_module(self, spec): + module = CustomModule(spec.name) + module.__name__ = name + return module + spec = self.machinery.ModuleSpec('test', Loader()) + module = self.util.module_from_spec(spec) + self.assertIsInstance(module, CustomModule) + self.assertEqual(module.__name__, name) + + def test___name__(self): + spec = self.machinery.ModuleSpec('test', object()) + module = self.util.module_from_spec(spec) + self.assertEqual(module.__name__, spec.name) + + def test___spec__(self): + spec = self.machinery.ModuleSpec('test', object()) + module = self.util.module_from_spec(spec) + self.assertEqual(module.__spec__, spec) + + def test___loader__(self): + loader = object() + spec = self.machinery.ModuleSpec('test', loader) + module = self.util.module_from_spec(spec) + self.assertIs(module.__loader__, loader) + + def test___package__(self): + spec = self.machinery.ModuleSpec('test.pkg', object()) + module = self.util.module_from_spec(spec) + self.assertEqual(module.__package__, spec.parent) + + def test___path__(self): + spec = self.machinery.ModuleSpec('test', object(), is_package=True) + module = self.util.module_from_spec(spec) + self.assertEqual(module.__path__, spec.submodule_search_locations) + + def test___file__(self): + spec = self.machinery.ModuleSpec('test', object(), origin='some/path') + spec.has_location = True + module = self.util.module_from_spec(spec) + self.assertEqual(module.__file__, spec.origin) + + def test___cached__(self): + spec = self.machinery.ModuleSpec('test', object()) + spec.cached = 'some/path' + spec.has_location = True + module = self.util.module_from_spec(spec) + self.assertEqual(module.__cached__, spec.cached) + +(Frozen_ModuleFromSpecTests, + Source_ModuleFromSpecTests +) = util.test_both(ModuleFromSpecTests, abc=abc, machinery=machinery, + util=importlib_util) class ModuleForLoaderTests: @@ -70,7 +156,7 @@ class ModuleForLoaderTests: # Test that when no module exists in sys.modules a new module is # created. module_name = 'a.b.c' - with test_util.uncache(module_name): + with util.uncache(module_name): module = self.return_module(module_name) self.assertIn(module_name, sys.modules) self.assertIsInstance(module, types.ModuleType) @@ -88,7 +174,7 @@ class ModuleForLoaderTests: module = types.ModuleType('a.b.c') module.__loader__ = 42 module.__package__ = 42 - with test_util.uncache(name): + with util.uncache(name): sys.modules[name] = module loader = FakeLoader() returned_module = loader.load_module(name) @@ -100,7 +186,7 @@ class ModuleForLoaderTests: # Test that a module is removed from sys.modules if added but an # exception is raised. name = 'a.b.c' - with test_util.uncache(name): + with util.uncache(name): self.raise_exception(name) self.assertNotIn(name, sys.modules) @@ -108,7 +194,7 @@ class ModuleForLoaderTests: # Test that a failure on reload leaves the module in-place. name = 'a.b.c' module = types.ModuleType(name) - with test_util.uncache(name): + with util.uncache(name): sys.modules[name] = module self.raise_exception(name) self.assertIs(module, sys.modules[name]) @@ -127,7 +213,7 @@ class ModuleForLoaderTests: name = 'mod' module = FalseModule(name) - with test_util.uncache(name): + with util.uncache(name): self.assertFalse(module) sys.modules[name] = module given = self.return_module(name) @@ -146,7 +232,7 @@ class ModuleForLoaderTests: return module name = 'pkg.mod' - with test_util.uncache(name): + with util.uncache(name): loader = FakeLoader(False) module = loader.load_module(name) self.assertEqual(module.__name__, name) @@ -154,15 +240,17 @@ class ModuleForLoaderTests: self.assertEqual(module.__package__, 'pkg') name = 'pkg.sub' - with test_util.uncache(name): + with util.uncache(name): loader = FakeLoader(True) module = loader.load_module(name) self.assertEqual(module.__name__, name) self.assertIs(module.__loader__, loader) self.assertEqual(module.__package__, name) -Frozen_ModuleForLoaderTests, Source_ModuleForLoaderTests = test_util.test_both( - ModuleForLoaderTests, util=[frozen_util, source_util]) + +(Frozen_ModuleForLoaderTests, + Source_ModuleForLoaderTests + ) = util.test_both(ModuleForLoaderTests, util=importlib_util) class SetPackageTests: @@ -222,18 +310,25 @@ class SetPackageTests: self.assertEqual(wrapped.__name__, fxn.__name__) self.assertEqual(wrapped.__qualname__, fxn.__qualname__) -Frozen_SetPackageTests, Source_SetPackageTests = test_util.test_both( - SetPackageTests, util=[frozen_util, source_util]) + +(Frozen_SetPackageTests, + Source_SetPackageTests + ) = util.test_both(SetPackageTests, util=importlib_util) class SetLoaderTests: """Tests importlib.util.set_loader().""" - class DummyLoader: - @util.set_loader - def load_module(self, module): - return self.module + @property + def DummyLoader(self): + # Set DummyLoader on the class lazily. + class DummyLoader: + @self.util.set_loader + def load_module(self, module): + return self.module + self.__class__.DummyLoader = DummyLoader + return DummyLoader def test_no_attribute(self): loader = self.DummyLoader() @@ -262,17 +357,10 @@ class SetLoaderTests: warnings.simplefilter('ignore', DeprecationWarning) self.assertEqual(42, loader.load_module('blah').__loader__) -class Frozen_SetLoaderTests(SetLoaderTests, unittest.TestCase): - class DummyLoader: - @frozen_util.set_loader - def load_module(self, module): - return self.module -class Source_SetLoaderTests(SetLoaderTests, unittest.TestCase): - class DummyLoader: - @source_util.set_loader - def load_module(self, module): - return self.module +(Frozen_SetLoaderTests, + Source_SetLoaderTests + ) = util.test_both(SetLoaderTests, util=importlib_util) class ResolveNameTests: @@ -307,9 +395,10 @@ class ResolveNameTests: with self.assertRaises(ValueError): self.util.resolve_name('..bacon', 'spam') -Frozen_ResolveNameTests, Source_ResolveNameTests = test_util.test_both( - ResolveNameTests, - util=[frozen_util, source_util]) + +(Frozen_ResolveNameTests, + Source_ResolveNameTests + ) = util.test_both(ResolveNameTests, util=importlib_util) class FindSpecTests: @@ -320,7 +409,7 @@ class FindSpecTests: def test_sys_modules(self): name = 'some_mod' - with test_util.uncache(name): + with util.uncache(name): module = types.ModuleType(name) loader = 'a loader!' spec = self.machinery.ModuleSpec(name, loader) @@ -332,7 +421,7 @@ class FindSpecTests: def test_sys_modules_without___loader__(self): name = 'some_mod' - with test_util.uncache(name): + with util.uncache(name): module = types.ModuleType(name) del module.__loader__ loader = 'a loader!' @@ -344,7 +433,7 @@ class FindSpecTests: def test_sys_modules_spec_is_None(self): name = 'some_mod' - with test_util.uncache(name): + with util.uncache(name): module = types.ModuleType(name) module.__spec__ = None sys.modules[name] = module @@ -353,7 +442,7 @@ class FindSpecTests: def test_sys_modules_loader_is_None(self): name = 'some_mod' - with test_util.uncache(name): + with util.uncache(name): module = types.ModuleType(name) spec = self.machinery.ModuleSpec(name, None) module.__spec__ = spec @@ -363,7 +452,7 @@ class FindSpecTests: def test_sys_modules_spec_is_not_set(self): name = 'some_mod' - with test_util.uncache(name): + with util.uncache(name): module = types.ModuleType(name) try: del module.__spec__ @@ -375,8 +464,8 @@ class FindSpecTests: def test_success(self): name = 'some_mod' - with test_util.uncache(name): - with test_util.import_state(meta_path=[self.FakeMetaFinder]): + with util.uncache(name): + with util.import_state(meta_path=[self.FakeMetaFinder]): self.assertEqual((name, None, None), self.util.find_spec(name)) @@ -384,8 +473,8 @@ class FindSpecTests: # # Searching on a path should work. # name = 'some_mod' # path = 'path to some place' -# with test_util.uncache(name): -# with test_util.import_state(meta_path=[self.FakeMetaFinder]): +# with util.uncache(name): +# with util.import_state(meta_path=[self.FakeMetaFinder]): # self.assertEqual((name, path, None), # self.util.find_spec(name, path)) @@ -396,8 +485,8 @@ class FindSpecTests: def test_find_submodule(self): name = 'spam' subname = 'ham' - with test_util.temp_module(name, pkg=True) as pkg_dir: - fullname, _ = test_util.submodule(name, subname, pkg_dir) + with util.temp_module(name, pkg=True) as pkg_dir: + fullname, _ = util.submodule(name, subname, pkg_dir) spec = self.util.find_spec(fullname) self.assertIsNot(spec, None) self.assertIn(name, sorted(sys.modules)) @@ -409,9 +498,9 @@ class FindSpecTests: def test_find_submodule_parent_already_imported(self): name = 'spam' subname = 'ham' - with test_util.temp_module(name, pkg=True) as pkg_dir: + with util.temp_module(name, pkg=True) as pkg_dir: self.init.import_module(name) - fullname, _ = test_util.submodule(name, subname, pkg_dir) + fullname, _ = util.submodule(name, subname, pkg_dir) spec = self.util.find_spec(fullname) self.assertIsNot(spec, None) self.assertIn(name, sorted(sys.modules)) @@ -423,8 +512,8 @@ class FindSpecTests: def test_find_relative_module(self): name = 'spam' subname = 'ham' - with test_util.temp_module(name, pkg=True) as pkg_dir: - fullname, _ = test_util.submodule(name, subname, pkg_dir) + with util.temp_module(name, pkg=True) as pkg_dir: + fullname, _ = util.submodule(name, subname, pkg_dir) relname = '.' + subname spec = self.util.find_spec(relname, name) self.assertIsNot(spec, None) @@ -437,8 +526,8 @@ class FindSpecTests: def test_find_relative_module_missing_package(self): name = 'spam' subname = 'ham' - with test_util.temp_module(name, pkg=True) as pkg_dir: - fullname, _ = test_util.submodule(name, subname, pkg_dir) + with util.temp_module(name, pkg=True) as pkg_dir: + fullname, _ = util.submodule(name, subname, pkg_dir) relname = '.' + subname with self.assertRaises(ValueError): self.util.find_spec(relname) @@ -446,15 +535,10 @@ class FindSpecTests: self.assertNotIn(fullname, sorted(sys.modules)) -class Frozen_FindSpecTests(FindSpecTests, unittest.TestCase): - init = frozen_init - machinery = frozen_machinery - util = frozen_util - -class Source_FindSpecTests(FindSpecTests, unittest.TestCase): - init = source_init - machinery = source_machinery - util = source_util +(Frozen_FindSpecTests, + Source_FindSpecTests + ) = util.test_both(FindSpecTests, init=init, util=importlib_util, + machinery=machinery) class MagicNumberTests: @@ -467,8 +551,10 @@ class MagicNumberTests: # The magic number uses \r\n to come out wrong when splitting on lines. self.assertTrue(self.util.MAGIC_NUMBER.endswith(b'\r\n')) -Frozen_MagicNumberTests, Source_MagicNumberTests = test_util.test_both( - MagicNumberTests, util=[frozen_util, source_util]) + +(Frozen_MagicNumberTests, + Source_MagicNumberTests + ) = util.test_both(MagicNumberTests, util=importlib_util) class PEP3147Tests: @@ -583,9 +669,10 @@ class PEP3147Tests: ValueError, self.util.source_from_cache, '/foo/bar/foo.cpython-32.foo.pyc') -Frozen_PEP3147Tests, Source_PEP3147Tests = test_util.test_both( - PEP3147Tests, - util=[frozen_util, source_util]) + +(Frozen_PEP3147Tests, + Source_PEP3147Tests + ) = util.test_both(PEP3147Tests, util=importlib_util) if __name__ == '__main__': diff --git a/Lib/test/test_importlib/test_windows.py b/Lib/test/test_importlib/test_windows.py index 96b4adc..c893bcf 100644 --- a/Lib/test/test_importlib/test_windows.py +++ b/Lib/test/test_importlib/test_windows.py @@ -1,14 +1,64 @@ -from . import util -frozen_machinery, source_machinery = util.import_importlib('importlib.machinery') +from . import util as test_util +machinery = test_util.import_importlib('importlib.machinery') +import os +import re import sys import unittest +from test import support +from distutils.util import get_platform +from contextlib import contextmanager +from .util import temp_module + +support.import_module('winreg', required_on=['win']) +from winreg import ( + CreateKey, HKEY_CURRENT_USER, + SetValue, REG_SZ, KEY_ALL_ACCESS, + EnumKey, CloseKey, DeleteKey, OpenKey +) + +def delete_registry_tree(root, subkey): + try: + hkey = OpenKey(root, subkey, access=KEY_ALL_ACCESS) + except OSError: + # subkey does not exist + return + while True: + try: + subsubkey = EnumKey(hkey, 0) + except OSError: + # no more subkeys + break + delete_registry_tree(hkey, subsubkey) + CloseKey(hkey) + DeleteKey(root, subkey) + +@contextmanager +def setup_module(machinery, name, path=None): + if machinery.WindowsRegistryFinder.DEBUG_BUILD: + root = machinery.WindowsRegistryFinder.REGISTRY_KEY_DEBUG + else: + root = machinery.WindowsRegistryFinder.REGISTRY_KEY + key = root.format(fullname=name, + sys_version=sys.version[:3]) + try: + with temp_module(name, "a = 1") as location: + subkey = CreateKey(HKEY_CURRENT_USER, key) + if path is None: + path = location + ".py" + SetValue(subkey, "", REG_SZ, path) + yield + finally: + if machinery.WindowsRegistryFinder.DEBUG_BUILD: + key = os.path.dirname(key) + delete_registry_tree(HKEY_CURRENT_USER, key) @unittest.skipUnless(sys.platform.startswith('win'), 'requires Windows') class WindowsRegistryFinderTests: - - # XXX Need a test that finds the spec via the registry. + # The module name is process-specific, allowing for + # simultaneous runs of the same test on a single machine. + test_module = "spamham{}".format(os.getpid()) def test_find_spec_missing(self): spec = self.machinery.WindowsRegistryFinder.find_spec('spam') @@ -18,12 +68,42 @@ class WindowsRegistryFinderTests: loader = self.machinery.WindowsRegistryFinder.find_module('spam') self.assertIs(loader, None) + def test_module_found(self): + with setup_module(self.machinery, self.test_module): + loader = self.machinery.WindowsRegistryFinder.find_module(self.test_module) + spec = self.machinery.WindowsRegistryFinder.find_spec(self.test_module) + self.assertIsNot(loader, None) + self.assertIsNot(spec, None) + + def test_module_not_found(self): + with setup_module(self.machinery, self.test_module, path="."): + loader = self.machinery.WindowsRegistryFinder.find_module(self.test_module) + spec = self.machinery.WindowsRegistryFinder.find_spec(self.test_module) + self.assertIsNone(loader) + self.assertIsNone(spec) + +(Frozen_WindowsRegistryFinderTests, + Source_WindowsRegistryFinderTests + ) = test_util.test_both(WindowsRegistryFinderTests, machinery=machinery) + +@unittest.skipUnless(sys.platform.startswith('win'), 'requires Windows') +class WindowsExtensionSuffixTests: + def test_tagged_suffix(self): + suffixes = self.machinery.EXTENSION_SUFFIXES + expected_tag = ".cp{0.major}{0.minor}-{1}.pyd".format(sys.version_info, + re.sub('[^a-zA-Z0-9]', '_', get_platform())) + try: + untagged_i = suffixes.index(".pyd") + except ValueError: + untagged_i = suffixes.index("_d.pyd") + expected_tag = "_d" + expected_tag -class Frozen_WindowsRegistryFinderTests(WindowsRegistryFinderTests, - unittest.TestCase): - machinery = frozen_machinery + self.assertIn(expected_tag, suffixes) + # Ensure the tags are in the correct order + tagged_i = suffixes.index(expected_tag) + self.assertLess(tagged_i, untagged_i) -class Source_WindowsRegistryFinderTests(WindowsRegistryFinderTests, - unittest.TestCase): - machinery = source_machinery +(Frozen_WindowsExtensionSuffixTests, + Source_WindowsExtensionSuffixTests + ) = test_util.test_both(WindowsExtensionSuffixTests, machinery=machinery) diff --git a/Lib/test/test_importlib/util.py b/Lib/test/test_importlib/util.py index 885cec3..aa4cd7e 100644 --- a/Lib/test/test_importlib/util.py +++ b/Lib/test/test_importlib/util.py @@ -1,31 +1,85 @@ -from contextlib import contextmanager -from importlib import util, invalidate_caches +import builtins +import contextlib +import errno +import functools +import importlib +from importlib import machinery, util, invalidate_caches +import os import os.path from test import support import unittest import sys +import tempfile import types +BUILTINS = types.SimpleNamespace() +BUILTINS.good_name = None +BUILTINS.bad_name = None +if 'errno' in sys.builtin_module_names: + BUILTINS.good_name = 'errno' +if 'importlib' not in sys.builtin_module_names: + BUILTINS.bad_name = 'importlib' + +EXTENSIONS = types.SimpleNamespace() +EXTENSIONS.path = None +EXTENSIONS.ext = None +EXTENSIONS.filename = None +EXTENSIONS.file_path = None +EXTENSIONS.name = '_testcapi' + +def _extension_details(): + global EXTENSIONS + for path in sys.path: + for ext in machinery.EXTENSION_SUFFIXES: + filename = EXTENSIONS.name + ext + file_path = os.path.join(path, filename) + if os.path.exists(file_path): + EXTENSIONS.path = path + EXTENSIONS.ext = ext + EXTENSIONS.filename = filename + EXTENSIONS.file_path = file_path + return + +_extension_details() + + def import_importlib(module_name): """Import a module from importlib both w/ and w/o _frozen_importlib.""" fresh = ('importlib',) if '.' in module_name else () frozen = support.import_fresh_module(module_name) source = support.import_fresh_module(module_name, fresh=fresh, blocked=('_frozen_importlib',)) + return {'Frozen': frozen, 'Source': source} + + +def specialize_class(cls, kind, base=None, **kwargs): + # XXX Support passing in submodule names--load (and cache) them? + # That would clean up the test modules a bit more. + if base is None: + base = unittest.TestCase + elif not isinstance(base, type): + base = base[kind] + name = '{}_{}'.format(kind, cls.__name__) + bases = (cls, base) + specialized = types.new_class(name, bases) + specialized.__module__ = cls.__module__ + specialized._NAME = cls.__name__ + specialized._KIND = kind + for attr, values in kwargs.items(): + value = values[kind] + setattr(specialized, attr, value) + return specialized + + +def split_frozen(cls, base=None, **kwargs): + frozen = specialize_class(cls, 'Frozen', base, **kwargs) + source = specialize_class(cls, 'Source', base, **kwargs) return frozen, source -def test_both(test_class, **kwargs): - frozen_tests = types.new_class('Frozen_'+test_class.__name__, - (test_class, unittest.TestCase)) - source_tests = types.new_class('Source_'+test_class.__name__, - (test_class, unittest.TestCase)) - frozen_tests.__module__ = source_tests.__module__ = test_class.__module__ - for attr, (frozen_value, source_value) in kwargs.items(): - setattr(frozen_tests, attr, frozen_value) - setattr(source_tests, attr, source_value) - return frozen_tests, source_tests +def test_both(test_class, base=None, **kwargs): + return split_frozen(test_class, base, **kwargs) CASE_INSENSITIVE_FS = True @@ -38,6 +92,10 @@ if sys.platform not in ('win32', 'cygwin'): if not os.path.exists(changed_name): CASE_INSENSITIVE_FS = False +source_importlib = import_importlib('importlib')['Source'] +__import__ = {'Frozen': staticmethod(builtins.__import__), + 'Source': staticmethod(source_importlib.__import__)} + def case_insensitive_tests(test): """Class decorator that nullifies tests requiring a case-insensitive @@ -53,7 +111,7 @@ def submodule(parent, name, pkg_dir, content=''): return '{}.{}'.format(parent, name), path -@contextmanager +@contextlib.contextmanager def uncache(*names): """Uncache a module from sys.modules. @@ -79,7 +137,7 @@ def uncache(*names): pass -@contextmanager +@contextlib.contextmanager def temp_module(name, content='', *, pkg=False): conflicts = [n for n in sys.modules if n.partition('.')[0] == name] with support.temp_cwd(None) as cwd: @@ -103,7 +161,7 @@ def temp_module(name, content='', *, pkg=False): yield location -@contextmanager +@contextlib.contextmanager def import_state(**kwargs): """Context manager to manage the various importers and stored state in the sys module. @@ -198,6 +256,7 @@ class mock_modules(_ImporterMock): raise return self.modules[fullname] + class mock_spec(_ImporterMock): """Importer mock using PEP 451 APIs.""" @@ -223,3 +282,99 @@ class mock_spec(_ImporterMock): self.module_code[module.__spec__.name]() except KeyError: pass + + +def writes_bytecode_files(fxn): + """Decorator to protect sys.dont_write_bytecode from mutation and to skip + tests that require it to be set to False.""" + if sys.dont_write_bytecode: + return lambda *args, **kwargs: None + @functools.wraps(fxn) + def wrapper(*args, **kwargs): + original = sys.dont_write_bytecode + sys.dont_write_bytecode = False + try: + to_return = fxn(*args, **kwargs) + finally: + sys.dont_write_bytecode = original + return to_return + return wrapper + + +def ensure_bytecode_path(bytecode_path): + """Ensure that the __pycache__ directory for PEP 3147 pyc file exists. + + :param bytecode_path: File system path to PEP 3147 pyc file. + """ + try: + os.mkdir(os.path.dirname(bytecode_path)) + except OSError as error: + if error.errno != errno.EEXIST: + raise + + +@contextlib.contextmanager +def create_modules(*names): + """Temporarily create each named module with an attribute (named 'attr') + that contains the name passed into the context manager that caused the + creation of the module. + + All files are created in a temporary directory returned by + tempfile.mkdtemp(). This directory is inserted at the beginning of + sys.path. When the context manager exits all created files (source and + bytecode) are explicitly deleted. + + No magic is performed when creating packages! This means that if you create + a module within a package you must also create the package's __init__ as + well. + + """ + source = 'attr = {0!r}' + created_paths = [] + mapping = {} + state_manager = None + uncache_manager = None + try: + temp_dir = tempfile.mkdtemp() + mapping['.root'] = temp_dir + import_names = set() + for name in names: + if not name.endswith('__init__'): + import_name = name + else: + import_name = name[:-len('.__init__')] + import_names.add(import_name) + if import_name in sys.modules: + del sys.modules[import_name] + name_parts = name.split('.') + file_path = temp_dir + for directory in name_parts[:-1]: + file_path = os.path.join(file_path, directory) + if not os.path.exists(file_path): + os.mkdir(file_path) + created_paths.append(file_path) + file_path = os.path.join(file_path, name_parts[-1] + '.py') + with open(file_path, 'w') as file: + file.write(source.format(name)) + created_paths.append(file_path) + mapping[name] = file_path + uncache_manager = uncache(*import_names) + uncache_manager.__enter__() + state_manager = import_state(path=[temp_dir]) + state_manager.__enter__() + yield mapping + finally: + if state_manager is not None: + state_manager.__exit__(None, None, None) + if uncache_manager is not None: + uncache_manager.__exit__(None, None, None) + support.rmtree(temp_dir) + + +def mock_path_hook(*entries, importer): + """A mock sys.path_hooks entry.""" + def hook(entry): + if entry not in entries: + raise ImportError + return importer + return hook diff --git a/Lib/test/test_inspect.py b/Lib/test/test_inspect.py index fc3bf07..bbc5385 100644 --- a/Lib/test/test_inspect.py +++ b/Lib/test/test_inspect.py @@ -1,3 +1,4 @@ +import builtins import collections import datetime import functools @@ -8,6 +9,7 @@ import linecache import os from os.path import normcase import _pickle +import pickle import re import shutil import sys @@ -23,7 +25,7 @@ except ImportError: ThreadPoolExecutor = None from test.support import run_unittest, TESTFN, DirsOnSysPath, cpython_only -from test.support import MISSING_C_DOCSTRINGS +from test.support import MISSING_C_DOCSTRINGS, cpython_only from test.script_helper import assert_python_ok, assert_python_failure from test import inspect_fodder as mod from test import inspect_fodder2 as mod2 @@ -76,6 +78,7 @@ def generator_function_example(self): for i in range(2): yield i + class TestPredicates(IsTestBase): def test_sixteen(self): count = len([x for x in dir(inspect) if x.startswith('is')]) @@ -182,6 +185,14 @@ class TestInterpreterStack(IsTestBase): (modfile, 43, 'argue', [' spam(a, b, c)\n'], 0)) self.assertEqual(revise(*mod.st[3][1:]), (modfile, 39, 'abuse', [' self.argue(a, b, c)\n'], 0)) + # Test named tuple fields + record = mod.st[0] + self.assertIs(record.frame, mod.fr) + self.assertEqual(record.lineno, 16) + self.assertEqual(record.filename, mod.__file__) + self.assertEqual(record.function, 'eggs') + self.assertIn('inspect.stack()', record.code_context[0]) + self.assertEqual(record.index, 0) def test_trace(self): self.assertEqual(len(git.tr), 3) @@ -369,6 +380,9 @@ class TestDecorators(GetSourceBase): def test_replacing_decorator(self): self.assertSourceEqual(mod2.gone, 9, 10) + def test_getsource_unwrap(self): + self.assertSourceEqual(mod2.real, 122, 124) + class TestOneliners(GetSourceBase): fodderModule = mod2 def test_oneline_lambda(self): @@ -1615,6 +1629,68 @@ class TestGetGeneratorState(unittest.TestCase): self.assertRaises(TypeError, inspect.getgeneratorlocals, (2,3)) +class MySignature(inspect.Signature): + # Top-level to make it picklable; + # used in test_signature_object_pickle + pass + +class MyParameter(inspect.Parameter): + # Top-level to make it picklable; + # used in test_signature_object_pickle + pass + + @cpython_only + @unittest.skipIf(MISSING_C_DOCSTRINGS, + "Signature information for builtins requires docstrings") + def test_builtins_have_signatures(self): + # This checks all builtin callables in CPython have signatures + # A few have signatures Signature can't yet handle, so we skip those + # since they will have to wait until PEP 457 adds the required + # introspection support to the inspect module + # Some others also haven't been converted yet for various other + # reasons, so we also skip those for the time being, but design + # the test to fail in order to indicate when it needs to be + # updated. + no_signature = set() + # These need PEP 457 groups + needs_groups = ["range", "slice", "dir", "getattr", + "next", "iter", "vars"] + no_signature |= needs_groups + # These need PEP 457 groups or a signature change to accept None + needs_semantic_update = ["round"] + no_signature |= needs_semantic_update + # These need *args support in Argument Clinic + needs_varargs = ["min", "max", "print", "__build_class__"] + no_signature |= needs_varargs + # These simply weren't covered in the initial AC conversion + # for builtin callables + not_converted_yet = ["open", "__import__"] + no_signature |= not_converted_yet + # These builtin types are expected to provide introspection info + types_with_signatures = set() + # Check the signatures we expect to be there + ns = vars(builtins) + for name, obj in sorted(ns.items()): + if not callable(obj): + continue + # The builtin types haven't been converted to AC yet + if isinstance(obj, type) and (name not in types_with_signatures): + # Note that this also skips all the exception types + no_signature.append(name) + if (name in no_signature): + # Not yet converted + continue + with self.subTest(builtin=name): + self.assertIsNotNone(inspect.signature(obj)) + # Check callables that haven't been converted don't claim a signature + # This ensures this test will start failing as more signatures are + # added, so the affected items can be moved into the scope of the + # regression test above + for name in no_signature: + with self.subTest(builtin=name): + self.assertIsNone(ns[name].__text_signature__) + + class TestSignatureObject(unittest.TestCase): @staticmethod def signature(func): @@ -1672,6 +1748,37 @@ class TestSignatureObject(unittest.TestCase): with self.assertRaisesRegex(ValueError, 'follows default argument'): S((pkd, pk)) + self.assertTrue(repr(sig).startswith('<Signature')) + self.assertTrue('"(po, pk' in repr(sig)) + + def test_signature_object_pickle(self): + def foo(a, b, *, c:1={}, **kw) -> {42:'ham'}: pass + foo_partial = functools.partial(foo, a=1) + + sig = inspect.signature(foo_partial) + + for ver in range(pickle.HIGHEST_PROTOCOL + 1): + with self.subTest(pickle_ver=ver, subclass=False): + sig_pickled = pickle.loads(pickle.dumps(sig, ver)) + self.assertEqual(sig, sig_pickled) + + # Test that basic sub-classing works + sig = inspect.signature(foo) + myparam = MyParameter(name='z', kind=inspect.Parameter.POSITIONAL_ONLY) + myparams = collections.OrderedDict(sig.parameters, a=myparam) + mysig = MySignature().replace(parameters=myparams.values(), + return_annotation=sig.return_annotation) + self.assertTrue(isinstance(mysig, MySignature)) + self.assertTrue(isinstance(mysig.parameters['z'], MyParameter)) + + for ver in range(pickle.HIGHEST_PROTOCOL + 1): + with self.subTest(pickle_ver=ver, subclass=True): + sig_pickled = pickle.loads(pickle.dumps(mysig, ver)) + self.assertEqual(mysig, sig_pickled) + self.assertTrue(isinstance(sig_pickled, MySignature)) + self.assertTrue(isinstance(sig_pickled.parameters['z'], + MyParameter)) + def test_signature_immutability(self): def test(a): pass @@ -2435,49 +2542,91 @@ class TestSignatureObject(unittest.TestCase): def bar(a, *, b:int) -> float: pass self.assertEqual(inspect.signature(foo), inspect.signature(bar)) + self.assertEqual( + hash(inspect.signature(foo)), hash(inspect.signature(bar))) def bar(a, *, b:int) -> int: pass self.assertNotEqual(inspect.signature(foo), inspect.signature(bar)) + self.assertNotEqual( + hash(inspect.signature(foo)), hash(inspect.signature(bar))) def bar(a, *, b:int): pass self.assertNotEqual(inspect.signature(foo), inspect.signature(bar)) + self.assertNotEqual( + hash(inspect.signature(foo)), hash(inspect.signature(bar))) def bar(a, *, b:int=42) -> float: pass self.assertNotEqual(inspect.signature(foo), inspect.signature(bar)) + self.assertNotEqual( + hash(inspect.signature(foo)), hash(inspect.signature(bar))) def bar(a, *, c) -> float: pass self.assertNotEqual(inspect.signature(foo), inspect.signature(bar)) + self.assertNotEqual( + hash(inspect.signature(foo)), hash(inspect.signature(bar))) def bar(a, b:int) -> float: pass self.assertNotEqual(inspect.signature(foo), inspect.signature(bar)) + self.assertNotEqual( + hash(inspect.signature(foo)), hash(inspect.signature(bar))) def spam(b:int, a) -> float: pass self.assertNotEqual(inspect.signature(spam), inspect.signature(bar)) + self.assertNotEqual( + hash(inspect.signature(spam)), hash(inspect.signature(bar))) def foo(*, a, b, c): pass def bar(*, c, b, a): pass self.assertEqual(inspect.signature(foo), inspect.signature(bar)) + self.assertEqual( + hash(inspect.signature(foo)), hash(inspect.signature(bar))) def foo(*, a=1, b, c): pass def bar(*, c, b, a=1): pass self.assertEqual(inspect.signature(foo), inspect.signature(bar)) + self.assertEqual( + hash(inspect.signature(foo)), hash(inspect.signature(bar))) def foo(pos, *, a=1, b, c): pass def bar(pos, *, c, b, a=1): pass self.assertEqual(inspect.signature(foo), inspect.signature(bar)) + self.assertEqual( + hash(inspect.signature(foo)), hash(inspect.signature(bar))) def foo(pos, *, a, b, c): pass def bar(pos, *, c, b, a=1): pass self.assertNotEqual(inspect.signature(foo), inspect.signature(bar)) + self.assertNotEqual( + hash(inspect.signature(foo)), hash(inspect.signature(bar))) def foo(pos, *args, a=42, b, c, **kwargs:int): pass def bar(pos, *args, c, b, a=42, **kwargs:int): pass self.assertEqual(inspect.signature(foo), inspect.signature(bar)) + self.assertEqual( + hash(inspect.signature(foo)), hash(inspect.signature(bar))) + + def test_signature_hashable(self): + S = inspect.Signature + P = inspect.Parameter - def test_signature_unhashable(self): def foo(a): pass - sig = inspect.signature(foo) + foo_sig = inspect.signature(foo) + + manual_sig = S(parameters=[P('a', P.POSITIONAL_OR_KEYWORD)]) + + self.assertEqual(hash(foo_sig), hash(manual_sig)) + self.assertNotEqual(hash(foo_sig), + hash(manual_sig.replace(return_annotation='spam'))) + + def bar(a) -> 1: pass + self.assertNotEqual(hash(foo_sig), hash(inspect.signature(bar))) + + def foo(a={}): pass with self.assertRaisesRegex(TypeError, 'unhashable type'): - hash(sig) + hash(inspect.signature(foo)) + + def foo(a) -> {}: pass + with self.assertRaisesRegex(TypeError, 'unhashable type'): + hash(inspect.signature(foo)) def test_signature_str(self): def foo(a:int=1, *, b, c=None, **kwargs) -> 42: @@ -2551,6 +2700,19 @@ class TestSignatureObject(unittest.TestCase): self.assertEqual(self.signature(Spam.foo), self.signature(Ham.foo)) + def test_signature_from_callable_python_obj(self): + class MySignature(inspect.Signature): pass + def foo(a, *, b:1): pass + foo_sig = MySignature.from_callable(foo) + self.assertTrue(isinstance(foo_sig, MySignature)) + + @unittest.skipIf(MISSING_C_DOCSTRINGS, + "Signature information for builtins requires docstrings") + def test_signature_from_callable_builtin_obj(self): + class MySignature(inspect.Signature): pass + sig = MySignature.from_callable(_pickle.Pickler) + self.assertTrue(isinstance(sig, MySignature)) + class TestParameterObject(unittest.TestCase): def test_signature_parameter_kinds(self): @@ -2596,6 +2758,16 @@ class TestParameterObject(unittest.TestCase): p.replace(kind=inspect.Parameter.VAR_POSITIONAL) self.assertTrue(repr(p).startswith('<Parameter')) + self.assertTrue('"a=42"' in repr(p)) + + def test_signature_parameter_hashable(self): + P = inspect.Parameter + foo = P('foo', kind=P.POSITIONAL_ONLY) + self.assertEqual(hash(foo), hash(P('foo', kind=P.POSITIONAL_ONLY))) + self.assertNotEqual(hash(foo), hash(P('foo', kind=P.POSITIONAL_ONLY, + default=42))) + self.assertNotEqual(hash(foo), + hash(foo.replace(kind=P.VAR_POSITIONAL))) def test_signature_parameter_equality(self): P = inspect.Parameter @@ -2607,13 +2779,6 @@ class TestParameterObject(unittest.TestCase): self.assertEqual(p, P('foo', default=42, kind=inspect.Parameter.KEYWORD_ONLY)) - def test_signature_parameter_unhashable(self): - p = inspect.Parameter('foo', default=42, - kind=inspect.Parameter.KEYWORD_ONLY) - - with self.assertRaisesRegex(TypeError, 'unhashable type'): - hash(p) - def test_signature_parameter_replace(self): p = inspect.Parameter('foo', default=42, kind=inspect.Parameter.KEYWORD_ONLY) @@ -2922,6 +3087,16 @@ class TestBoundArguments(unittest.TestCase): ba4 = inspect.signature(bar).bind(1) self.assertNotEqual(ba, ba4) + def test_signature_bound_arguments_pickle(self): + def foo(a, b, *, c:1={}, **kw) -> {42:'ham'}: pass + sig = inspect.signature(foo) + ba = sig.bind(20, 30, z={}) + + for ver in range(pickle.HIGHEST_PROTOCOL + 1): + with self.subTest(pickle_ver=ver): + ba_pickled = pickle.loads(pickle.dumps(ba, ver)) + self.assertEqual(ba, ba_pickled) + class TestSignaturePrivateHelpers(unittest.TestCase): def test_signature_get_bound_param(self): diff --git a/Lib/test/test_io.py b/Lib/test/test_io.py index 668b023..a0a4670 100644 --- a/Lib/test/test_io.py +++ b/Lib/test/test_io.py @@ -44,10 +44,6 @@ try: import threading except ImportError: threading = None -try: - import fcntl -except ImportError: - fcntl = None def _default_chunk_size(): """Get the default TextIOWrapper chunk size""" @@ -367,8 +363,8 @@ class IOTest(unittest.TestCase): def test_open_handles_NUL_chars(self): fn_with_NUL = 'foo\0bar' - self.assertRaises(TypeError, self.open, fn_with_NUL, 'w') - self.assertRaises(TypeError, self.open, bytes(fn_with_NUL, 'ascii'), 'w') + self.assertRaises(ValueError, self.open, fn_with_NUL, 'w') + self.assertRaises(ValueError, self.open, bytes(fn_with_NUL, 'ascii'), 'w') def test_raw_file_io(self): with self.open(support.TESTFN, "wb", buffering=0) as f: @@ -811,7 +807,7 @@ class CommonBufferedTests: def test_repr(self): raw = self.MockRawIO() b = self.tp(raw) - clsname = "%s.%s" % (self.tp.__module__, self.tp.__name__) + clsname = "%s.%s" % (self.tp.__module__, self.tp.__qualname__) self.assertEqual(repr(b), "<%s>" % clsname) raw.name = "dummy" self.assertEqual(repr(b), "<%s name='dummy'>" % clsname) @@ -985,6 +981,71 @@ class BufferedReaderTest(unittest.TestCase, CommonBufferedTests): self.assertEqual(bufio.readinto(b), 1) self.assertEqual(b, b"cb") + def test_readinto1(self): + buffer_size = 10 + rawio = self.MockRawIO((b"abc", b"de", b"fgh", b"jkl")) + bufio = self.tp(rawio, buffer_size=buffer_size) + b = bytearray(2) + self.assertEqual(bufio.peek(3), b'abc') + self.assertEqual(rawio._reads, 1) + self.assertEqual(bufio.readinto1(b), 2) + self.assertEqual(b, b"ab") + self.assertEqual(rawio._reads, 1) + self.assertEqual(bufio.readinto1(b), 1) + self.assertEqual(b[:1], b"c") + self.assertEqual(rawio._reads, 1) + self.assertEqual(bufio.readinto1(b), 2) + self.assertEqual(b, b"de") + self.assertEqual(rawio._reads, 2) + b = bytearray(2*buffer_size) + self.assertEqual(bufio.peek(3), b'fgh') + self.assertEqual(rawio._reads, 3) + self.assertEqual(bufio.readinto1(b), 6) + self.assertEqual(b[:6], b"fghjkl") + self.assertEqual(rawio._reads, 4) + + def test_readinto_array(self): + buffer_size = 60 + data = b"a" * 26 + rawio = self.MockRawIO((data,)) + bufio = self.tp(rawio, buffer_size=buffer_size) + + # Create an array with element size > 1 byte + b = array.array('i', b'x' * 32) + assert len(b) != 16 + + # Read into it. We should get as many *bytes* as we can fit into b + # (which is more than the number of elements) + n = bufio.readinto(b) + self.assertGreater(n, len(b)) + + # Check that old contents of b are preserved + bm = memoryview(b).cast('B') + self.assertLess(n, len(bm)) + self.assertEqual(bm[:n], data[:n]) + self.assertEqual(bm[n:], b'x' * (len(bm[n:]))) + + def test_readinto1_array(self): + buffer_size = 60 + data = b"a" * 26 + rawio = self.MockRawIO((data,)) + bufio = self.tp(rawio, buffer_size=buffer_size) + + # Create an array with element size > 1 byte + b = array.array('i', b'x' * 32) + assert len(b) != 16 + + # Read into it. We should get as many *bytes* as we can fit into b + # (which is more than the number of elements) + n = bufio.readinto1(b) + self.assertGreater(n, len(b)) + + # Check that old contents of b are preserved + bm = memoryview(b).cast('B') + self.assertLess(n, len(bm)) + self.assertEqual(bm[:n], data[:n]) + self.assertEqual(bm[n:], b'x' * (len(bm[n:]))) + def test_readlines(self): def bufio(): rawio = self.MockRawIO((b"abc\n", b"d\n", b"ef")) @@ -2844,6 +2905,17 @@ class TextIOWrapperTest(unittest.TestCase): self.assertFalse(err) self.assertEqual("ok", out.decode().strip()) + def test_read_byteslike(self): + r = MemviewBytesIO(b'Just some random string\n') + t = self.TextIOWrapper(r, 'utf-8') + + # TextIOwrapper will not read the full string, because + # we truncate it to a multiple of the native int size + # so that we can construct a more complex memoryview. + bytes_val = _to_memoryview(r.getvalue()).tobytes() + + self.assertEqual(t.read(200), bytes_val.decode('utf-8')) + def test_issue22849(self): class F(object): def readable(self): return True @@ -2860,6 +2932,25 @@ class TextIOWrapperTest(unittest.TestCase): t = self.TextIOWrapper(F(), encoding='utf-8') +class MemviewBytesIO(io.BytesIO): + '''A BytesIO object whose read method returns memoryviews + rather than bytes''' + + def read1(self, len_): + return _to_memoryview(super().read1(len_)) + + def read(self, len_): + return _to_memoryview(super().read(len_)) + +def _to_memoryview(buf): + '''Convert bytes-object *buf* to a non-trivial memoryview''' + + arr = array.array('i') + idx = len(buf) - len(buf) % arr.itemsize + arr.frombytes(buf[:idx]) + return memoryview(arr) + + class CTextIOWrapperTest(TextIOWrapperTest): io = io shutdown_error = "RuntimeError: could not find io module state" @@ -3106,6 +3197,8 @@ class MiscIOTest(unittest.TestCase): self.assertRaises(ValueError, f.readall) if hasattr(f, "readinto"): self.assertRaises(ValueError, f.readinto, bytearray(1024)) + if hasattr(f, "readinto1"): + self.assertRaises(ValueError, f.readinto1, bytearray(1024)) self.assertRaises(ValueError, f.readline) self.assertRaises(ValueError, f.readlines) self.assertRaises(ValueError, f.seek, 0) @@ -3219,26 +3312,20 @@ class MiscIOTest(unittest.TestCase): with self.open(support.TESTFN, **kwargs) as f: self.assertRaises(TypeError, pickle.dumps, f, protocol) - @unittest.skipUnless(fcntl, 'fcntl required for this test') def test_nonblock_pipe_write_bigbuf(self): self._test_nonblock_pipe_write(16*1024) - @unittest.skipUnless(fcntl, 'fcntl required for this test') def test_nonblock_pipe_write_smallbuf(self): self._test_nonblock_pipe_write(1024) - def _set_non_blocking(self, fd): - flags = fcntl.fcntl(fd, fcntl.F_GETFL) - self.assertNotEqual(flags, -1) - res = fcntl.fcntl(fd, fcntl.F_SETFL, flags | os.O_NONBLOCK) - self.assertEqual(res, 0) - + @unittest.skipUnless(hasattr(os, 'set_blocking'), + 'os.set_blocking() required for this test') def _test_nonblock_pipe_write(self, bufsize): sent = [] received = [] r, w = os.pipe() - self._set_non_blocking(r) - self._set_non_blocking(w) + os.set_blocking(r, False) + os.set_blocking(w, False) # To exercise all code paths in the C implementation we need # to play with buffer sizes. For instance, if we choose a diff --git a/Lib/test/test_ipaddress.py b/Lib/test/test_ipaddress.py index bfb5699..e985329 100644 --- a/Lib/test/test_ipaddress.py +++ b/Lib/test/test_ipaddress.py @@ -9,6 +9,7 @@ import re import contextlib import functools import operator +import pickle import ipaddress @@ -83,6 +84,13 @@ class CommonTestMixin: self.assertRaises(TypeError, hex, self.factory(1)) self.assertRaises(TypeError, bytes, self.factory(1)) + def pickle_test(self, addr): + for proto in range(pickle.HIGHEST_PROTOCOL + 1): + with self.subTest(proto=proto): + x = self.factory(addr) + y = pickle.loads(pickle.dumps(x, proto)) + self.assertEqual(y, x) + class CommonTestMixin_v4(CommonTestMixin): @@ -248,6 +256,9 @@ class AddressTestCase_v4(BaseTestCase, CommonTestMixin_v4): assertBadOctet("257.0.0.0", 257) assertBadOctet("192.168.0.999", 999) + def test_pickle(self): + self.pickle_test('192.0.2.1') + class AddressTestCase_v6(BaseTestCase, CommonTestMixin_v6): factory = ipaddress.IPv6Address @@ -380,6 +391,9 @@ class AddressTestCase_v6(BaseTestCase, CommonTestMixin_v6): assertBadPart("02001:db8::", "02001") assertBadPart('2001:888888::1', "888888") + def test_pickle(self): + self.pickle_test('2001:db8::') + class NetmaskTestMixin_v4(CommonTestMixin_v4): """Input validation on interfaces and networks is very similar""" @@ -443,6 +457,11 @@ class NetmaskTestMixin_v4(CommonTestMixin_v4): assertBadNetmask("1.1.1.1", "pudding") assertBadNetmask("1.1.1.1", "::") + def test_pickle(self): + self.pickle_test('192.0.2.0/27') + self.pickle_test('192.0.2.0/31') # IPV4LENGTH - 1 + self.pickle_test('192.0.2.0') # IPV4LENGTH + class InterfaceTestCase_v4(BaseTestCase, NetmaskTestMixin_v4): factory = ipaddress.IPv4Interface @@ -501,6 +520,11 @@ class NetmaskTestMixin_v6(CommonTestMixin_v6): assertBadNetmask("::1", "pudding") assertBadNetmask("::", "::") + def test_pickle(self): + self.pickle_test('2001:db8::1000/124') + self.pickle_test('2001:db8::1000/127') # IPV6LENGTH - 1 + self.pickle_test('2001:db8::1000') # IPV6LENGTH + class InterfaceTestCase_v6(BaseTestCase, NetmaskTestMixin_v6): factory = ipaddress.IPv6Interface @@ -670,6 +694,119 @@ class IpaddrUnitTest(unittest.TestCase): self.assertEqual("IPv6Interface('::1/128')", repr(ipaddress.IPv6Interface('::1'))) + # issue #16531: constructing IPv4Network from a (address, mask) tuple + def testIPv4Tuple(self): + # /32 + ip = ipaddress.IPv4Address('192.0.2.1') + net = ipaddress.IPv4Network('192.0.2.1/32') + self.assertEqual(ipaddress.IPv4Network(('192.0.2.1', 32)), net) + self.assertEqual(ipaddress.IPv4Network((ip, 32)), net) + self.assertEqual(ipaddress.IPv4Network((3221225985, 32)), net) + self.assertEqual(ipaddress.IPv4Network(('192.0.2.1', + '255.255.255.255')), net) + self.assertEqual(ipaddress.IPv4Network((ip, + '255.255.255.255')), net) + self.assertEqual(ipaddress.IPv4Network((3221225985, + '255.255.255.255')), net) + # strict=True and host bits set + with self.assertRaises(ValueError): + ipaddress.IPv4Network(('192.0.2.1', 24)) + with self.assertRaises(ValueError): + ipaddress.IPv4Network((ip, 24)) + with self.assertRaises(ValueError): + ipaddress.IPv4Network((3221225985, 24)) + with self.assertRaises(ValueError): + ipaddress.IPv4Network(('192.0.2.1', '255.255.255.0')) + with self.assertRaises(ValueError): + ipaddress.IPv4Network((ip, '255.255.255.0')) + with self.assertRaises(ValueError): + ipaddress.IPv4Network((3221225985, '255.255.255.0')) + # strict=False and host bits set + net = ipaddress.IPv4Network('192.0.2.0/24') + self.assertEqual(ipaddress.IPv4Network(('192.0.2.1', 24), + strict=False), net) + self.assertEqual(ipaddress.IPv4Network((ip, 24), + strict=False), net) + self.assertEqual(ipaddress.IPv4Network((3221225985, 24), + strict=False), net) + self.assertEqual(ipaddress.IPv4Network(('192.0.2.1', + '255.255.255.0'), + strict=False), net) + self.assertEqual(ipaddress.IPv4Network((ip, + '255.255.255.0'), + strict=False), net) + self.assertEqual(ipaddress.IPv4Network((3221225985, + '255.255.255.0'), + strict=False), net) + + # /24 + ip = ipaddress.IPv4Address('192.0.2.0') + net = ipaddress.IPv4Network('192.0.2.0/24') + self.assertEqual(ipaddress.IPv4Network(('192.0.2.0', + '255.255.255.0')), net) + self.assertEqual(ipaddress.IPv4Network((ip, + '255.255.255.0')), net) + self.assertEqual(ipaddress.IPv4Network((3221225984, + '255.255.255.0')), net) + self.assertEqual(ipaddress.IPv4Network(('192.0.2.0', 24)), net) + self.assertEqual(ipaddress.IPv4Network((ip, 24)), net) + self.assertEqual(ipaddress.IPv4Network((3221225984, 24)), net) + + self.assertEqual(ipaddress.IPv4Interface(('192.0.2.1', 24)), + ipaddress.IPv4Interface('192.0.2.1/24')) + self.assertEqual(ipaddress.IPv4Interface((3221225985, 24)), + ipaddress.IPv4Interface('192.0.2.1/24')) + + # issue #16531: constructing IPv6Network from a (address, mask) tuple + def testIPv6Tuple(self): + # /128 + ip = ipaddress.IPv6Address('2001:db8::') + net = ipaddress.IPv6Network('2001:db8::/128') + self.assertEqual(ipaddress.IPv6Network(('2001:db8::', '128')), + net) + self.assertEqual(ipaddress.IPv6Network( + (42540766411282592856903984951653826560, 128)), + net) + self.assertEqual(ipaddress.IPv6Network((ip, '128')), + net) + ip = ipaddress.IPv6Address('2001:db8::') + net = ipaddress.IPv6Network('2001:db8::/96') + self.assertEqual(ipaddress.IPv6Network(('2001:db8::', '96')), + net) + self.assertEqual(ipaddress.IPv6Network( + (42540766411282592856903984951653826560, 96)), + net) + self.assertEqual(ipaddress.IPv6Network((ip, '96')), + net) + + # strict=True and host bits set + ip = ipaddress.IPv6Address('2001:db8::1') + with self.assertRaises(ValueError): + ipaddress.IPv6Network(('2001:db8::1', 96)) + with self.assertRaises(ValueError): + ipaddress.IPv6Network(( + 42540766411282592856903984951653826561, 96)) + with self.assertRaises(ValueError): + ipaddress.IPv6Network((ip, 96)) + # strict=False and host bits set + net = ipaddress.IPv6Network('2001:db8::/96') + self.assertEqual(ipaddress.IPv6Network(('2001:db8::1', 96), + strict=False), + net) + self.assertEqual(ipaddress.IPv6Network( + (42540766411282592856903984951653826561, 96), + strict=False), + net) + self.assertEqual(ipaddress.IPv6Network((ip, 96), strict=False), + net) + + # /96 + self.assertEqual(ipaddress.IPv6Interface(('2001:db8::1', '96')), + ipaddress.IPv6Interface('2001:db8::1/96')) + self.assertEqual(ipaddress.IPv6Interface( + (42540766411282592856903984951653826561, '96')), + ipaddress.IPv6Interface('2001:db8::1/96')) + # issue57 def testAddressIntMath(self): self.assertEqual(ipaddress.IPv4Address('1.1.1.1') + 255, @@ -690,20 +827,18 @@ class IpaddrUnitTest(unittest.TestCase): 2 ** ipaddress.IPV6LENGTH) def testInternals(self): - first, last = ipaddress._find_address_range([ - ipaddress.IPv4Address('10.10.10.10'), - ipaddress.IPv4Address('10.10.10.12')]) - self.assertEqual(first, last) + ip1 = ipaddress.IPv4Address('10.10.10.10') + ip2 = ipaddress.IPv4Address('10.10.10.11') + ip3 = ipaddress.IPv4Address('10.10.10.12') + self.assertEqual(list(ipaddress._find_address_range([ip1])), + [(ip1, ip1)]) + self.assertEqual(list(ipaddress._find_address_range([ip1, ip3])), + [(ip1, ip1), (ip3, ip3)]) + self.assertEqual(list(ipaddress._find_address_range([ip1, ip2, ip3])), + [(ip1, ip3)]) self.assertEqual(128, ipaddress._count_righthand_zero_bits(0, 128)) self.assertEqual("IPv4Network('1.2.3.0/24')", repr(self.ipv4_network)) - def testMissingAddressVersion(self): - class Broken(ipaddress._BaseAddress): - pass - broken = Broken('127.0.0.1') - with self.assertRaisesRegex(NotImplementedError, "Broken.*version"): - broken.version - def testMissingNetworkVersion(self): class Broken(ipaddress._BaseNetwork): pass @@ -1635,6 +1770,14 @@ class IpaddrUnitTest(unittest.TestCase): addr3.exploded) self.assertEqual('192.168.178.1', addr4.exploded) + def testReversePointer(self): + addr1 = ipaddress.IPv4Address('127.0.0.1') + addr2 = ipaddress.IPv6Address('2001:db8::1') + self.assertEqual('1.0.0.127.in-addr.arpa', addr1.reverse_pointer) + self.assertEqual('1.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.8.' + + 'b.d.0.1.0.0.2.ip6.arpa', + addr2.reverse_pointer) + def testIntRepresentation(self): self.assertEqual(16909060, int(self.ipv4_address)) self.assertEqual(42540616829182469433547762482097946625, diff --git a/Lib/test/test_itertools.py b/Lib/test/test_itertools.py index 244598b..6a0130e 100644 --- a/Lib/test/test_itertools.py +++ b/Lib/test/test_itertools.py @@ -1856,8 +1856,6 @@ class RegressionTests(unittest.TestCase): hist.append(3) yield 2 hist.append(4) - if x: - raise StopIteration hist = [] self.assertRaises(AssertionError, list, chain(gen1(), gen2(False))) diff --git a/Lib/test/test_json/__init__.py b/Lib/test/test_json/__init__.py index 2cf1032..0807e6f 100644 --- a/Lib/test/test_json/__init__.py +++ b/Lib/test/test_json/__init__.py @@ -9,12 +9,15 @@ from test import support # import json with and without accelerations cjson = support.import_fresh_module('json', fresh=['_json']) pyjson = support.import_fresh_module('json', blocked=['_json']) +# JSONDecodeError is cached inside the _json module +cjson.JSONDecodeError = cjson.decoder.JSONDecodeError = json.JSONDecodeError # create two base classes that will be used by the other tests class PyTest(unittest.TestCase): json = pyjson loads = staticmethod(pyjson.loads) dumps = staticmethod(pyjson.dumps) + JSONDecodeError = staticmethod(pyjson.JSONDecodeError) @unittest.skipUnless(cjson, 'requires _json') class CTest(unittest.TestCase): @@ -22,6 +25,7 @@ class CTest(unittest.TestCase): json = cjson loads = staticmethod(cjson.loads) dumps = staticmethod(cjson.dumps) + JSONDecodeError = staticmethod(cjson.JSONDecodeError) # test PyTest and CTest checking if the functions come from the right module class TestPyTest(PyTest): diff --git a/Lib/test/test_json/test_decode.py b/Lib/test/test_json/test_decode.py index 591b2e2..cc83b45 100644 --- a/Lib/test/test_json/test_decode.py +++ b/Lib/test/test_json/test_decode.py @@ -63,12 +63,12 @@ class TestDecode: def test_extra_data(self): s = '[1, 2, 3]5' msg = 'Extra data' - self.assertRaisesRegex(ValueError, msg, self.loads, s) + self.assertRaisesRegex(self.JSONDecodeError, msg, self.loads, s) def test_invalid_escape(self): s = '["abc\\y"]' msg = 'escape' - self.assertRaisesRegex(ValueError, msg, self.loads, s) + self.assertRaisesRegex(self.JSONDecodeError, msg, self.loads, s) def test_invalid_input_type(self): msg = 'the JSON object must be str' @@ -80,10 +80,10 @@ class TestDecode: def test_string_with_utf8_bom(self): # see #18958 bom_json = "[1,2,3]".encode('utf-8-sig').decode('utf-8') - with self.assertRaises(ValueError) as cm: + with self.assertRaises(self.JSONDecodeError) as cm: self.loads(bom_json) self.assertIn('BOM', str(cm.exception)) - with self.assertRaises(ValueError) as cm: + with self.assertRaises(self.JSONDecodeError) as cm: self.json.load(StringIO(bom_json)) self.assertIn('BOM', str(cm.exception)) # make sure that the BOM is not detected in the middle of a string diff --git a/Lib/test/test_json/test_encode_basestring_ascii.py b/Lib/test/test_json/test_encode_basestring_ascii.py index 2122da1..4bbc6c7 100644 --- a/Lib/test/test_json/test_encode_basestring_ascii.py +++ b/Lib/test/test_json/test_encode_basestring_ascii.py @@ -12,9 +12,6 @@ CASES = [ (' s p a c e d ', '" s p a c e d "'), ('\U0001d120', '"\\ud834\\udd20"'), ('\u03b1\u03a9', '"\\u03b1\\u03a9"'), - ('\u03b1\u03a9', '"\\u03b1\\u03a9"'), - ('\u03b1\u03a9', '"\\u03b1\\u03a9"'), - ('\u03b1\u03a9', '"\\u03b1\\u03a9"'), ("`1~!@#$%^&*()_+-={':[,]}|;.</>?", '"`1~!@#$%^&*()_+-={\':[,]}|;.</>?"'), ('\x08\x0c\n\r\t', '"\\b\\f\\n\\r\\t"'), ('\u0123\u4567\u89ab\ucdef\uabcd\uef4a', '"\\u0123\\u4567\\u89ab\\ucdef\\uabcd\\uef4a"'), diff --git a/Lib/test/test_json/test_fail.py b/Lib/test/test_json/test_fail.py index 7caafdb..95ff5b8 100644 --- a/Lib/test/test_json/test_fail.py +++ b/Lib/test/test_json/test_fail.py @@ -87,7 +87,7 @@ class TestFail: continue try: self.loads(doc) - except ValueError: + except self.JSONDecodeError: pass else: self.fail("Expected failure for fail{0}.json: {1!r}".format(idx, doc)) @@ -124,10 +124,16 @@ class TestFail: ('"spam', 'Unterminated string starting at', 0), ] for data, msg, idx in test_cases: - self.assertRaisesRegex(ValueError, - r'^{0}: line 1 column {1} \(char {2}\)'.format( - re.escape(msg), idx + 1, idx), - self.loads, data) + with self.assertRaises(self.JSONDecodeError) as cm: + self.loads(data) + err = cm.exception + self.assertEqual(err.msg, msg) + self.assertEqual(err.pos, idx) + self.assertEqual(err.lineno, 1) + self.assertEqual(err.colno, idx + 1) + self.assertEqual(str(err), + '%s: line 1 column %d (char %d)' % + (msg, idx + 1, idx)) def test_unexpected_data(self): test_cases = [ @@ -154,10 +160,16 @@ class TestFail: ('{"spam":42,}', 'Expecting property name enclosed in double quotes', 11), ] for data, msg, idx in test_cases: - self.assertRaisesRegex(ValueError, - r'^{0}: line 1 column {1} \(char {2}\)'.format( - re.escape(msg), idx + 1, idx), - self.loads, data) + with self.assertRaises(self.JSONDecodeError) as cm: + self.loads(data) + err = cm.exception + self.assertEqual(err.msg, msg) + self.assertEqual(err.pos, idx) + self.assertEqual(err.lineno, 1) + self.assertEqual(err.colno, idx + 1) + self.assertEqual(str(err), + '%s: line 1 column %d (char %d)' % + (msg, idx + 1, idx)) def test_extra_data(self): test_cases = [ @@ -171,11 +183,16 @@ class TestFail: ('"spam",42', 'Extra data', 6), ] for data, msg, idx in test_cases: - self.assertRaisesRegex(ValueError, - r'^{0}: line 1 column {1} - line 1 column {2}' - r' \(char {3} - {4}\)'.format( - re.escape(msg), idx + 1, len(data) + 1, idx, len(data)), - self.loads, data) + with self.assertRaises(self.JSONDecodeError) as cm: + self.loads(data) + err = cm.exception + self.assertEqual(err.msg, msg) + self.assertEqual(err.pos, idx) + self.assertEqual(err.lineno, 1) + self.assertEqual(err.colno, idx + 1) + self.assertEqual(str(err), + '%s: line 1 column %d (char %d)' % + (msg, idx + 1, idx)) def test_linecol(self): test_cases = [ @@ -185,10 +202,16 @@ class TestFail: ('\n \n\n !', 4, 6, 10), ] for data, line, col, idx in test_cases: - self.assertRaisesRegex(ValueError, - r'^Expecting value: line {0} column {1}' - r' \(char {2}\)$'.format(line, col, idx), - self.loads, data) + with self.assertRaises(self.JSONDecodeError) as cm: + self.loads(data) + err = cm.exception + self.assertEqual(err.msg, 'Expecting value') + self.assertEqual(err.pos, idx) + self.assertEqual(err.lineno, line) + self.assertEqual(err.colno, col) + self.assertEqual(str(err), + 'Expecting value: line %s column %d (char %d)' % + (line, col, idx)) class TestPyFail(TestFail, PyTest): pass class TestCFail(TestFail, CTest): pass diff --git a/Lib/test/test_json/test_scanstring.py b/Lib/test/test_json/test_scanstring.py index 07f4358..2d3ee8a 100644 --- a/Lib/test/test_json/test_scanstring.py +++ b/Lib/test/test_json/test_scanstring.py @@ -129,7 +129,7 @@ class TestScanstring: '"\\ud834\\u0X20"', ] for s in bad_escapes: - with self.assertRaises(ValueError, msg=s): + with self.assertRaises(self.JSONDecodeError, msg=s): scanstring(s, 1, True) def test_overflow(self): diff --git a/Lib/test/test_json/test_tool.py b/Lib/test/test_json/test_tool.py index 0c39e56..bd63e2b 100644 --- a/Lib/test/test_json/test_tool.py +++ b/Lib/test/test_json/test_tool.py @@ -6,6 +6,7 @@ import subprocess from test import support from test.script_helper import assert_python_ok + class TestTool(unittest.TestCase): data = """ @@ -15,7 +16,7 @@ class TestTool(unittest.TestCase): :"yes"} ] """ - expect = textwrap.dedent("""\ + expect_without_sort_keys = textwrap.dedent("""\ [ [ "blorpie" @@ -37,6 +38,28 @@ class TestTool(unittest.TestCase): ] """) + expect = textwrap.dedent("""\ + [ + [ + "blorpie" + ], + [ + "whoops" + ], + [], + "d-shtaeou", + "d-nthiouh", + "i-vhbjkhnth", + { + "nifty": 87 + }, + { + "morefield": false, + "field": "yes" + } + ] + """) + def test_stdin_stdout(self): with subprocess.Popen( (sys.executable, '-m', 'json.tool'), @@ -55,6 +78,7 @@ class TestTool(unittest.TestCase): def test_infile_stdout(self): infile = self._create_infile() rc, out, err = assert_python_ok('-m', 'json.tool', infile) + self.assertEqual(rc, 0) self.assertEqual(out.splitlines(), self.expect.encode().splitlines()) self.assertEqual(err, b'') @@ -65,5 +89,20 @@ class TestTool(unittest.TestCase): self.addCleanup(os.remove, outfile) with open(outfile, "r") as fp: self.assertEqual(fp.read(), self.expect) + self.assertEqual(rc, 0) self.assertEqual(out, b'') self.assertEqual(err, b'') + + def test_help_flag(self): + rc, out, err = assert_python_ok('-m', 'json.tool', '-h') + self.assertEqual(rc, 0) + self.assertTrue(out.startswith(b'usage: ')) + self.assertEqual(err, b'') + + def test_sort_keys_flag(self): + infile = self._create_infile() + rc, out, err = assert_python_ok('-m', 'json.tool', '--sort-keys', infile) + self.assertEqual(rc, 0) + self.assertEqual(out.splitlines(), + self.expect_without_sort_keys.encode().splitlines()) + self.assertEqual(err, b'') diff --git a/Lib/test/test_kqueue.py b/Lib/test/test_kqueue.py index f79bd89..2585ca6 100644 --- a/Lib/test/test_kqueue.py +++ b/Lib/test/test_kqueue.py @@ -114,7 +114,7 @@ class TestKQueue(unittest.TestCase): def test_queue_event(self): serverSocket = socket.socket() serverSocket.bind(('127.0.0.1', 0)) - serverSocket.listen(1) + serverSocket.listen() client = socket.socket() client.setblocking(False) try: diff --git a/Lib/test/test_linecache.py b/Lib/test/test_linecache.py index 5fe0554..2fb8662 100644 --- a/Lib/test/test_linecache.py +++ b/Lib/test/test_linecache.py @@ -7,6 +7,7 @@ from test import support FILENAME = linecache.__file__ +NONEXISTENT_FILENAME = FILENAME + '.missing' INVALID_NAME = '!@$)(!@#_1' EMPTY = '' TESTS = 'inspect_fodder inspect_fodder2 mapping_tests' @@ -126,6 +127,49 @@ class LineCacheTests(unittest.TestCase): self.assertEqual(line, getline(source_name, index + 1)) source_list.append(line) + def test_lazycache_no_globals(self): + lines = linecache.getlines(FILENAME) + linecache.clearcache() + self.assertEqual(False, linecache.lazycache(FILENAME, None)) + self.assertEqual(lines, linecache.getlines(FILENAME)) + + def test_lazycache_smoke(self): + lines = linecache.getlines(NONEXISTENT_FILENAME, globals()) + linecache.clearcache() + self.assertEqual( + True, linecache.lazycache(NONEXISTENT_FILENAME, globals())) + self.assertEqual(1, len(linecache.cache[NONEXISTENT_FILENAME])) + # Note here that we're looking up a non existant filename with no + # globals: this would error if the lazy value wasn't resolved. + self.assertEqual(lines, linecache.getlines(NONEXISTENT_FILENAME)) + + def test_lazycache_provide_after_failed_lookup(self): + linecache.clearcache() + lines = linecache.getlines(NONEXISTENT_FILENAME, globals()) + linecache.clearcache() + linecache.getlines(NONEXISTENT_FILENAME) + linecache.lazycache(NONEXISTENT_FILENAME, globals()) + self.assertEqual(lines, linecache.updatecache(NONEXISTENT_FILENAME)) + + def test_lazycache_check(self): + linecache.clearcache() + linecache.lazycache(NONEXISTENT_FILENAME, globals()) + linecache.checkcache() + + def test_lazycache_bad_filename(self): + linecache.clearcache() + self.assertEqual(False, linecache.lazycache('', globals())) + self.assertEqual(False, linecache.lazycache('<foo>', globals())) + + def test_lazycache_already_cached(self): + linecache.clearcache() + lines = linecache.getlines(NONEXISTENT_FILENAME, globals()) + self.assertEqual( + False, + linecache.lazycache(NONEXISTENT_FILENAME, globals())) + self.assertEqual(4, len(linecache.cache[NONEXISTENT_FILENAME])) + + def test_main(): support.run_unittest(LineCacheTests) diff --git a/Lib/test/test_locale.py b/Lib/test/test_locale.py index 9369a25..fae2c3d 100644 --- a/Lib/test/test_locale.py +++ b/Lib/test/test_locale.py @@ -524,5 +524,59 @@ class TestMiscellaneous(unittest.TestCase): locale.setlocale(locale.LC_ALL, (b'not', b'valid')) +class BaseDelocalizeTest(BaseLocalizedTest): + + def _test_delocalize(self, value, out): + self.assertEqual(locale.delocalize(value), out) + + def _test_atof(self, value, out): + self.assertEqual(locale.atof(value), out) + + def _test_atoi(self, value, out): + self.assertEqual(locale.atoi(value), out) + + +class TestEnUSDelocalize(EnUSCookedTest, BaseDelocalizeTest): + + def test_delocalize(self): + self._test_delocalize('50000.00', '50000.00') + self._test_delocalize('50,000.00', '50000.00') + + def test_atof(self): + self._test_atof('50000.00', 50000.) + self._test_atof('50,000.00', 50000.) + + def test_atoi(self): + self._test_atoi('50000', 50000) + self._test_atoi('50,000', 50000) + + +class TestCDelocalizeTest(CCookedTest, BaseDelocalizeTest): + + def test_delocalize(self): + self._test_delocalize('50000.00', '50000.00') + + def test_atof(self): + self._test_atof('50000.00', 50000.) + + def test_atoi(self): + self._test_atoi('50000', 50000) + + +class TestfrFRDelocalizeTest(FrFRCookedTest, BaseDelocalizeTest): + + def test_delocalize(self): + self._test_delocalize('50000,00', '50000.00') + self._test_delocalize('50 000,00', '50000.00') + + def test_atof(self): + self._test_atof('50000,00', 50000.) + self._test_atof('50 000,00', 50000.) + + def test_atoi(self): + self._test_atoi('50000', 50000) + self._test_atoi('50 000', 50000) + + if __name__ == '__main__': unittest.main() diff --git a/Lib/test/test_logging.py b/Lib/test/test_logging.py index 54be217..c8b6a98 100644 --- a/Lib/test/test_logging.py +++ b/Lib/test/test_logging.py @@ -1,4 +1,4 @@ -# Copyright 2001-2013 by Vinay Sajip. All Rights Reserved. +# Copyright 2001-2014 by Vinay Sajip. All Rights Reserved. # # Permission to use, copy, modify, and distribute this software and its # documentation for any purpose and without fee is hereby granted, @@ -16,7 +16,7 @@ """Test harness for the logging module. Run all tests. -Copyright (C) 2001-2013 Vinay Sajip. All Rights Reserved. +Copyright (C) 2001-2014 Vinay Sajip. All Rights Reserved. """ import logging @@ -34,14 +34,12 @@ import os import queue import random import re -import select import socket import struct import sys import tempfile from test.script_helper import assert_python_ok -from test.support import (captured_stdout, run_with_locale, run_unittest, - patch, requires_zlib, TestHandler, Matcher, HOST) +from test import support import textwrap import time import unittest @@ -51,16 +49,12 @@ try: import threading # The following imports are needed only for tests which # require threading - import asynchat import asyncore - import errno from http.server import HTTPServer, BaseHTTPRequestHandler import smtpd from urllib.parse import urlparse, parse_qs from socketserver import (ThreadingUDPServer, DatagramRequestHandler, - ThreadingTCPServer, StreamRequestHandler, - ThreadingUnixStreamServer, - ThreadingUnixDatagramServer) + ThreadingTCPServer, StreamRequestHandler) except ImportError: threading = None try: @@ -645,22 +639,23 @@ class StreamHandlerTest(BaseTest): h = TestStreamHandler(BadStream()) r = logging.makeLogRecord({}) old_raise = logging.raiseExceptions - old_stderr = sys.stderr + try: h.handle(r) self.assertIs(h.error_record, r) + h = logging.StreamHandler(BadStream()) - sys.stderr = sio = io.StringIO() - h.handle(r) - self.assertIn('\nRuntimeError: deliberate mistake\n', - sio.getvalue()) + with support.captured_stderr() as stderr: + h.handle(r) + msg = '\nRuntimeError: deliberate mistake\n' + self.assertIn(msg, stderr.getvalue()) + logging.raiseExceptions = False - sys.stderr = sio = io.StringIO() - h.handle(r) - self.assertEqual('', sio.getvalue()) + with support.captured_stderr() as stderr: + h.handle(r) + self.assertEqual('', stderr.getvalue()) finally: logging.raiseExceptions = old_raise - sys.stderr = old_stderr # -- The following section could be moved into a server_helper.py module # -- if it proves to be of wider utility than just test_logging @@ -688,7 +683,8 @@ if threading: """ def __init__(self, addr, handler, poll_interval, sockmap): - smtpd.SMTPServer.__init__(self, addr, None, map=sockmap) + smtpd.SMTPServer.__init__(self, addr, None, map=sockmap, + decode_data=True) self.port = self.socket.getsockname()[1] self._handler = handler self._thread = None @@ -930,10 +926,10 @@ class SMTPHandlerTest(BaseTest): TIMEOUT = 8.0 def test_basic(self): sockmap = {} - server = TestSMTPServer((HOST, 0), self.process_message, 0.001, + server = TestSMTPServer((support.HOST, 0), self.process_message, 0.001, sockmap) server.start() - addr = (HOST, server.port) + addr = (support.HOST, server.port) h = logging.handlers.SMTPHandler(addr, 'me', 'you', 'Log', timeout=self.TIMEOUT) self.assertEqual(h.toaddrs, ['you']) @@ -1249,7 +1245,7 @@ class ConfigFileTest(BaseTest): def test_config0_ok(self): # A simple config file which overrides the default settings. - with captured_stdout() as output: + with support.captured_stdout() as output: self.apply_config(self.config0) logger = logging.getLogger() # Won't output anything @@ -1264,7 +1260,7 @@ class ConfigFileTest(BaseTest): def test_config0_using_cp_ok(self): # A simple config file which overrides the default settings. - with captured_stdout() as output: + with support.captured_stdout() as output: file = io.StringIO(textwrap.dedent(self.config0)) cp = configparser.ConfigParser() cp.read_file(file) @@ -1282,7 +1278,7 @@ class ConfigFileTest(BaseTest): def test_config1_ok(self, config=config1): # A config file defining a sub-parser as well. - with captured_stdout() as output: + with support.captured_stdout() as output: self.apply_config(config) logger = logging.getLogger("compiler.parser") # Both will output a message @@ -1305,7 +1301,7 @@ class ConfigFileTest(BaseTest): def test_config4_ok(self): # A config file specifying a custom formatter class. - with captured_stdout() as output: + with support.captured_stdout() as output: self.apply_config(self.config4) logger = logging.getLogger() try: @@ -1325,7 +1321,7 @@ class ConfigFileTest(BaseTest): self.test_config1_ok(config=self.config6) def test_config7_ok(self): - with captured_stdout() as output: + with support.captured_stdout() as output: self.apply_config(self.config1a) logger = logging.getLogger("compiler.parser") # See issue #11424. compiler-hyphenated sorts @@ -1345,7 +1341,7 @@ class ConfigFileTest(BaseTest): ], stream=output) # Original logger output is empty. self.assert_log_lines([]) - with captured_stdout() as output: + with support.captured_stdout() as output: self.apply_config(self.config7) logger = logging.getLogger("compiler.parser") self.assertFalse(logger.disabled) @@ -2492,7 +2488,7 @@ class ConfigDictTest(BaseTest): def test_config0_ok(self): # A simple config which overrides the default settings. - with captured_stdout() as output: + with support.captured_stdout() as output: self.apply_config(self.config0) logger = logging.getLogger() # Won't output anything @@ -2507,7 +2503,7 @@ class ConfigDictTest(BaseTest): def test_config1_ok(self, config=config1): # A config defining a sub-parser as well. - with captured_stdout() as output: + with support.captured_stdout() as output: self.apply_config(config) logger = logging.getLogger("compiler.parser") # Both will output a message @@ -2538,7 +2534,7 @@ class ConfigDictTest(BaseTest): def test_config4_ok(self): # A config specifying a custom formatter class. - with captured_stdout() as output: + with support.captured_stdout() as output: self.apply_config(self.config4) #logger = logging.getLogger() try: @@ -2553,7 +2549,7 @@ class ConfigDictTest(BaseTest): def test_config4a_ok(self): # A config specifying a custom formatter class. - with captured_stdout() as output: + with support.captured_stdout() as output: self.apply_config(self.config4a) #logger = logging.getLogger() try: @@ -2573,7 +2569,7 @@ class ConfigDictTest(BaseTest): self.assertRaises(Exception, self.apply_config, self.config6) def test_config7_ok(self): - with captured_stdout() as output: + with support.captured_stdout() as output: self.apply_config(self.config1) logger = logging.getLogger("compiler.parser") # Both will output a message @@ -2585,7 +2581,7 @@ class ConfigDictTest(BaseTest): ], stream=output) # Original logger output is empty. self.assert_log_lines([]) - with captured_stdout() as output: + with support.captured_stdout() as output: self.apply_config(self.config7) logger = logging.getLogger("compiler.parser") self.assertTrue(logger.disabled) @@ -2602,7 +2598,7 @@ class ConfigDictTest(BaseTest): #Same as test_config_7_ok but don't disable old loggers. def test_config_8_ok(self): - with captured_stdout() as output: + with support.captured_stdout() as output: self.apply_config(self.config1) logger = logging.getLogger("compiler.parser") # All will output a message @@ -2614,7 +2610,7 @@ class ConfigDictTest(BaseTest): ], stream=output) # Original logger output is empty. self.assert_log_lines([]) - with captured_stdout() as output: + with support.captured_stdout() as output: self.apply_config(self.config8) logger = logging.getLogger("compiler.parser") self.assertFalse(logger.disabled) @@ -2635,7 +2631,7 @@ class ConfigDictTest(BaseTest): self.assert_log_lines([]) def test_config_8a_ok(self): - with captured_stdout() as output: + with support.captured_stdout() as output: self.apply_config(self.config1a) logger = logging.getLogger("compiler.parser") # See issue #11424. compiler-hyphenated sorts @@ -2655,7 +2651,7 @@ class ConfigDictTest(BaseTest): ], stream=output) # Original logger output is empty. self.assert_log_lines([]) - with captured_stdout() as output: + with support.captured_stdout() as output: self.apply_config(self.config8a) logger = logging.getLogger("compiler.parser") self.assertFalse(logger.disabled) @@ -2678,7 +2674,7 @@ class ConfigDictTest(BaseTest): self.assert_log_lines([]) def test_config_9_ok(self): - with captured_stdout() as output: + with support.captured_stdout() as output: self.apply_config(self.config9) logger = logging.getLogger("compiler.parser") #Nothing will be output since both handler and logger are set to WARNING @@ -2696,7 +2692,7 @@ class ConfigDictTest(BaseTest): ], stream=output) def test_config_10_ok(self): - with captured_stdout() as output: + with support.captured_stdout() as output: self.apply_config(self.config10) logger = logging.getLogger("compiler.parser") logger.warning(self.next_message()) @@ -2724,7 +2720,7 @@ class ConfigDictTest(BaseTest): self.assertRaises(Exception, self.apply_config, self.config13) def test_config14_ok(self): - with captured_stdout() as output: + with support.captured_stdout() as output: self.apply_config(self.config14) h = logging._handlers['hand1'] self.assertEqual(h.foo, 'bar') @@ -2763,7 +2759,7 @@ class ConfigDictTest(BaseTest): @unittest.skipUnless(threading, 'Threading required for this test.') def test_listen_config_10_ok(self): - with captured_stdout() as output: + with support.captured_stdout() as output: self.setup_via_listener(json.dumps(self.config10)) logger = logging.getLogger("compiler.parser") logger.warning(self.next_message()) @@ -2783,7 +2779,7 @@ class ConfigDictTest(BaseTest): @unittest.skipUnless(threading, 'Threading required for this test.') def test_listen_config_1_ok(self): - with captured_stdout() as output: + with support.captured_stdout() as output: self.setup_via_listener(textwrap.dedent(ConfigFileTest.config1)) logger = logging.getLogger("compiler.parser") # Both will output a message @@ -2810,7 +2806,7 @@ class ConfigDictTest(BaseTest): # First, specify a verification function that will fail. # We expect to see no output, since our configuration # never took effect. - with captured_stdout() as output: + with support.captured_stdout() as output: self.setup_via_listener(to_send, verify_fail) # Both will output a message logger.info(self.next_message()) @@ -2825,7 +2821,7 @@ class ConfigDictTest(BaseTest): # Now, perform no verification. Our configuration # should take effect. - with captured_stdout() as output: + with support.captured_stdout() as output: self.setup_via_listener(to_send) # no verify callable specified logger = logging.getLogger("compiler.parser") # Both will output a message @@ -2843,7 +2839,7 @@ class ConfigDictTest(BaseTest): # Now, perform verification which transforms the bytes. - with captured_stdout() as output: + with support.captured_stdout() as output: self.setup_via_listener(to_send[::-1], verify_reverse) logger = logging.getLogger("compiler.parser") # Both will output a message @@ -2998,7 +2994,7 @@ class QueueHandlerTest(BaseTest): @unittest.skipUnless(hasattr(logging.handlers, 'QueueListener'), 'logging.handlers.QueueListener required for this test') def test_queue_listener(self): - handler = TestHandler(Matcher()) + handler = support.TestHandler(support.Matcher()) listener = logging.handlers.QueueListener(self.queue, handler) listener.start() try: @@ -3010,6 +3006,25 @@ class QueueHandlerTest(BaseTest): self.assertTrue(handler.matches(levelno=logging.WARNING, message='1')) self.assertTrue(handler.matches(levelno=logging.ERROR, message='2')) self.assertTrue(handler.matches(levelno=logging.CRITICAL, message='3')) + handler.close() + + # Now test with respect_handler_level set + + handler = support.TestHandler(support.Matcher()) + handler.setLevel(logging.CRITICAL) + listener = logging.handlers.QueueListener(self.queue, handler, + respect_handler_level=True) + listener.start() + try: + self.que_logger.warning(self.next_message()) + self.que_logger.error(self.next_message()) + self.que_logger.critical(self.next_message()) + finally: + listener.stop() + self.assertFalse(handler.matches(levelno=logging.WARNING, message='4')) + self.assertFalse(handler.matches(levelno=logging.ERROR, message='5')) + self.assertTrue(handler.matches(levelno=logging.CRITICAL, message='6')) + ZERO = datetime.timedelta(0) @@ -3166,32 +3181,35 @@ class LastResortTest(BaseTest): # Test the last resort handler root = self.root_logger root.removeHandler(self.root_hdlr) - old_stderr = sys.stderr old_lastresort = logging.lastResort old_raise_exceptions = logging.raiseExceptions + try: - sys.stderr = sio = io.StringIO() - root.debug('This should not appear') - self.assertEqual(sio.getvalue(), '') - root.warning('This is your final chance!') - self.assertEqual(sio.getvalue(), 'This is your final chance!\n') - #No handlers and no last resort, so 'No handlers' message + with support.captured_stderr() as stderr: + root.debug('This should not appear') + self.assertEqual(stderr.getvalue(), '') + root.warning('Final chance!') + self.assertEqual(stderr.getvalue(), 'Final chance!\n') + + # No handlers and no last resort, so 'No handlers' message logging.lastResort = None - sys.stderr = sio = io.StringIO() - root.warning('This is your final chance!') - self.assertEqual(sio.getvalue(), 'No handlers could be found for logger "root"\n') + with support.captured_stderr() as stderr: + root.warning('Final chance!') + msg = 'No handlers could be found for logger "root"\n' + self.assertEqual(stderr.getvalue(), msg) + # 'No handlers' message only printed once - sys.stderr = sio = io.StringIO() - root.warning('This is your final chance!') - self.assertEqual(sio.getvalue(), '') + with support.captured_stderr() as stderr: + root.warning('Final chance!') + self.assertEqual(stderr.getvalue(), '') + + # If raiseExceptions is False, no message is printed root.manager.emittedNoHandlerWarning = False - #If raiseExceptions is False, no message is printed logging.raiseExceptions = False - sys.stderr = sio = io.StringIO() - root.warning('This is your final chance!') - self.assertEqual(sio.getvalue(), '') + with support.captured_stderr() as stderr: + root.warning('Final chance!') + self.assertEqual(stderr.getvalue(), '') finally: - sys.stderr = old_stderr root.addHandler(self.root_hdlr) logging.lastResort = old_lastresort logging.raiseExceptions = old_raise_exceptions @@ -3322,8 +3340,8 @@ class ModuleLevelMiscTest(BaseTest): def _test_log(self, method, level=None): called = [] - patch(self, logging, 'basicConfig', - lambda *a, **kw: called.append((a, kw))) + support.patch(self, logging, 'basicConfig', + lambda *a, **kw: called.append((a, kw))) recording = RecordingHandler() logging.root.addHandler(recording) @@ -3494,7 +3512,7 @@ class BasicConfigTest(unittest.TestCase): self.assertEqual(logging.root.level, self.original_logging_level) def test_strformatstyle(self): - with captured_stdout() as output: + with support.captured_stdout() as output: logging.basicConfig(stream=sys.stdout, style="{") logging.error("Log an error") sys.stdout.seek(0) @@ -3502,7 +3520,7 @@ class BasicConfigTest(unittest.TestCase): "ERROR:root:Log an error") def test_stringtemplatestyle(self): - with captured_stdout() as output: + with support.captured_stdout() as output: logging.basicConfig(stream=sys.stdout, style="$") logging.error("Log an error") sys.stdout.seek(0) @@ -3619,7 +3637,7 @@ class BasicConfigTest(unittest.TestCase): self.addCleanup(logging.root.setLevel, old_level) called.append((a, kw)) - patch(self, logging, 'basicConfig', my_basic_config) + support.patch(self, logging, 'basicConfig', my_basic_config) log_method = getattr(logging, method) if level is not None: @@ -3685,6 +3703,19 @@ class LoggerAdapterTest(unittest.TestCase): self.assertEqual(record.exc_info, (exc.__class__, exc, exc.__traceback__)) + def test_exception_excinfo(self): + try: + 1 / 0 + except ZeroDivisionError as e: + exc = e + + self.adapter.exception('exc_info test', exc_info=exc) + + self.assertEqual(len(self.recording.records), 1) + record = self.recording.records[0] + self.assertEqual(record.exc_info, + (exc.__class__, exc, exc.__traceback__)) + def test_critical(self): msg = 'critical test! %r' self.adapter.critical(msg, self.recording) @@ -3759,8 +3790,8 @@ class LoggerTest(BaseTest): def test_find_caller_with_stack_info(self): called = [] - patch(self, logging.traceback, 'print_stack', - lambda f, file: called.append(file.getvalue())) + support.patch(self, logging.traceback, 'print_stack', + lambda f, file: called.append(file.getvalue())) self.logger.findCaller(stack_info=True) @@ -3897,7 +3928,7 @@ class RotatingFileHandlerTest(BaseFileTest): self.assertFalse(os.path.exists(namer(self.fn + ".3"))) rh.close() - @requires_zlib + @support.requires_zlib def test_rotator(self): def namer(name): return name + ".gz" @@ -4130,22 +4161,20 @@ class NTEventLogHandlerTest(BaseTest): # Set the locale to the platform-dependent default. I have no idea # why the test does this, but in any case we save the current locale # first and restore it at the end. -@run_with_locale('LC_ALL', '') +@support.run_with_locale('LC_ALL', '') def test_main(): - run_unittest(BuiltinLevelsTest, BasicFilterTest, - CustomLevelsAndFiltersTest, HandlerTest, MemoryHandlerTest, - ConfigFileTest, SocketHandlerTest, DatagramHandlerTest, - MemoryTest, EncodingTest, WarningsTest, ConfigDictTest, - ManagerTest, FormatterTest, BufferingFormatterTest, - StreamHandlerTest, LogRecordFactoryTest, ChildLoggerTest, - QueueHandlerTest, ShutdownTest, ModuleLevelMiscTest, - BasicConfigTest, LoggerAdapterTest, LoggerTest, - SMTPHandlerTest, FileHandlerTest, RotatingFileHandlerTest, - LastResortTest, LogRecordTest, ExceptionTest, - SysLogHandlerTest, HTTPHandlerTest, NTEventLogHandlerTest, - TimedRotatingFileHandlerTest, UnixSocketHandlerTest, - UnixDatagramHandlerTest, UnixSysLogHandlerTest - ) + support.run_unittest( + BuiltinLevelsTest, BasicFilterTest, CustomLevelsAndFiltersTest, + HandlerTest, MemoryHandlerTest, ConfigFileTest, SocketHandlerTest, + DatagramHandlerTest, MemoryTest, EncodingTest, WarningsTest, + ConfigDictTest, ManagerTest, FormatterTest, BufferingFormatterTest, + StreamHandlerTest, LogRecordFactoryTest, ChildLoggerTest, + QueueHandlerTest, ShutdownTest, ModuleLevelMiscTest, BasicConfigTest, + LoggerAdapterTest, LoggerTest, SMTPHandlerTest, FileHandlerTest, + RotatingFileHandlerTest, LastResortTest, LogRecordTest, + ExceptionTest, SysLogHandlerTest, HTTPHandlerTest, + NTEventLogHandlerTest, TimedRotatingFileHandlerTest, + UnixSocketHandlerTest, UnixDatagramHandlerTest, UnixSysLogHandlerTest) if __name__ == "__main__": test_main() diff --git a/Lib/test/test_long.py b/Lib/test/test_long.py index 5f14795..57847d8 100644 --- a/Lib/test/test_long.py +++ b/Lib/test/test_long.py @@ -599,8 +599,6 @@ class LongTest(unittest.TestCase): return (x > y) - (x < y) def __eq__(self, other): return self._cmp__(other) == 0 - def __ne__(self, other): - return self._cmp__(other) != 0 def __ge__(self, other): return self._cmp__(other) >= 0 def __gt__(self, other): diff --git a/Lib/test/test_lzma.py b/Lib/test/test_lzma.py index 07fadbd..cded28c 100644 --- a/Lib/test/test_lzma.py +++ b/Lib/test/test_lzma.py @@ -135,6 +135,97 @@ class CompressorDecompressorTestCase(unittest.TestCase): self.assertTrue(lzd.eof) self.assertEqual(lzd.unused_data, b"") + def test_decompressor_chunks_maxsize(self): + lzd = LZMADecompressor() + max_length = 100 + out = [] + + # Feed first half the input + len_ = len(COMPRESSED_XZ) // 2 + out.append(lzd.decompress(COMPRESSED_XZ[:len_], + max_length=max_length)) + self.assertFalse(lzd.needs_input) + self.assertEqual(len(out[-1]), max_length) + + # Retrieve more data without providing more input + out.append(lzd.decompress(b'', max_length=max_length)) + self.assertFalse(lzd.needs_input) + self.assertEqual(len(out[-1]), max_length) + + # Retrieve more data while providing more input + out.append(lzd.decompress(COMPRESSED_XZ[len_:], + max_length=max_length)) + self.assertLessEqual(len(out[-1]), max_length) + + # Retrieve remaining uncompressed data + while not lzd.eof: + out.append(lzd.decompress(b'', max_length=max_length)) + self.assertLessEqual(len(out[-1]), max_length) + + out = b"".join(out) + self.assertEqual(out, INPUT) + self.assertEqual(lzd.check, lzma.CHECK_CRC64) + self.assertEqual(lzd.unused_data, b"") + + def test_decompressor_inputbuf_1(self): + # Test reusing input buffer after moving existing + # contents to beginning + lzd = LZMADecompressor() + out = [] + + # Create input buffer and fill it + self.assertEqual(lzd.decompress(COMPRESSED_XZ[:100], + max_length=0), b'') + + # Retrieve some results, freeing capacity at beginning + # of input buffer + out.append(lzd.decompress(b'', 2)) + + # Add more data that fits into input buffer after + # moving existing data to beginning + out.append(lzd.decompress(COMPRESSED_XZ[100:105], 15)) + + # Decompress rest of data + out.append(lzd.decompress(COMPRESSED_XZ[105:])) + self.assertEqual(b''.join(out), INPUT) + + def test_decompressor_inputbuf_2(self): + # Test reusing input buffer by appending data at the + # end right away + lzd = LZMADecompressor() + out = [] + + # Create input buffer and empty it + self.assertEqual(lzd.decompress(COMPRESSED_XZ[:200], + max_length=0), b'') + out.append(lzd.decompress(b'')) + + # Fill buffer with new data + out.append(lzd.decompress(COMPRESSED_XZ[200:280], 2)) + + # Append some more data, not enough to require resize + out.append(lzd.decompress(COMPRESSED_XZ[280:300], 2)) + + # Decompress rest of data + out.append(lzd.decompress(COMPRESSED_XZ[300:])) + self.assertEqual(b''.join(out), INPUT) + + def test_decompressor_inputbuf_3(self): + # Test reusing input buffer after extending it + + lzd = LZMADecompressor() + out = [] + + # Create almost full input buffer + out.append(lzd.decompress(COMPRESSED_XZ[:200], 5)) + + # Add even more data to it, requiring resize + out.append(lzd.decompress(COMPRESSED_XZ[200:300], 5)) + + # Decompress rest of data + out.append(lzd.decompress(COMPRESSED_XZ[300:])) + self.assertEqual(b''.join(out), INPUT) + def test_decompressor_unused_data(self): lzd = LZMADecompressor() extra = b"fooblibar" diff --git a/Lib/test/test_macpath.py b/Lib/test/test_macpath.py index 22f8491..80bec7a 100644 --- a/Lib/test/test_macpath.py +++ b/Lib/test/test_macpath.py @@ -142,6 +142,8 @@ class MacPathTestCase(unittest.TestCase): class MacCommonTest(test_genericpath.CommonTest, unittest.TestCase): pathmodule = macpath + test_relpath_errors = None + if __name__ == "__main__": unittest.main() diff --git a/Lib/test/test_marshal.py b/Lib/test/test_marshal.py index 903e12c..c7def9a 100644 --- a/Lib/test/test_marshal.py +++ b/Lib/test/test_marshal.py @@ -193,7 +193,7 @@ class BugsTestCase(unittest.TestCase): head = last = [] # The max stack depth should match the value in Python/marshal.c. if os.name == 'nt' and hasattr(sys, 'gettotalrefcount'): - MAX_MARSHAL_STACK_DEPTH = 1500 + MAX_MARSHAL_STACK_DEPTH = 1000 else: MAX_MARSHAL_STACK_DEPTH = 2000 for i in range(MAX_MARSHAL_STACK_DEPTH - 2): diff --git a/Lib/test/test_math.py b/Lib/test/test_math.py index 48f84ba..023dea9 100644 --- a/Lib/test/test_math.py +++ b/Lib/test/test_math.py @@ -422,9 +422,17 @@ class MathTests(unittest.TestCase): self.assertEqual(math.factorial(i), py_factorial(i)) self.assertRaises(ValueError, math.factorial, -1) self.assertRaises(ValueError, math.factorial, -1.0) + self.assertRaises(ValueError, math.factorial, -10**100) + self.assertRaises(ValueError, math.factorial, -1e100) self.assertRaises(ValueError, math.factorial, math.pi) - self.assertRaises(OverflowError, math.factorial, sys.maxsize+1) - self.assertRaises(OverflowError, math.factorial, 10e100) + + # Other implementations may place different upper bounds. + @support.cpython_only + def testFactorialHugeInputs(self): + # Currently raises ValueError for inputs that are too large + # to fit into a C long. + self.assertRaises(OverflowError, math.factorial, 10**100) + self.assertRaises(OverflowError, math.factorial, 1e100) def testFloor(self): self.assertRaises(TypeError, math.floor) @@ -975,6 +983,17 @@ class MathTests(unittest.TestCase): self.assertFalse(math.isinf(0.)) self.assertFalse(math.isinf(1.)) + @requires_IEEE_754 + def test_nan_constant(self): + self.assertTrue(math.isnan(math.nan)) + + @requires_IEEE_754 + def test_inf_constant(self): + self.assertTrue(math.isinf(math.inf)) + self.assertGreater(math.inf, 0.0) + self.assertEqual(math.inf, float("inf")) + self.assertEqual(-math.inf, float("-inf")) + # RED_FLAG 16-Oct-2000 Tim # While 2.0 is more consistent about exceptions than previous releases, it # still fails this part of the test on some platforms. For now, we only diff --git a/Lib/test/test_memoryio.py b/Lib/test/test_memoryio.py index 9a2461d..77749e7 100644 --- a/Lib/test/test_memoryio.py +++ b/Lib/test/test_memoryio.py @@ -9,6 +9,7 @@ from test import support import io import _pyio as pyio import pickle +import sys class MemorySeekTestMixin: @@ -717,12 +718,56 @@ class CBytesIOTest(PyBytesIOTest): @support.cpython_only def test_sizeof(self): - basesize = support.calcobjsize('P2nN2Pn') + basesize = support.calcobjsize('P2n2Pn') check = self.check_sizeof self.assertEqual(object.__sizeof__(io.BytesIO()), basesize) check(io.BytesIO(), basesize ) - check(io.BytesIO(b'a'), basesize + 1 + 1 ) - check(io.BytesIO(b'a' * 1000), basesize + 1000 + 1 ) + check(io.BytesIO(b'a' * 1000), basesize + sys.getsizeof(b'a' * 1000)) + + # Various tests of copy-on-write behaviour for BytesIO. + + def _test_cow_mutation(self, mutation): + # Common code for all BytesIO copy-on-write mutation tests. + imm = b' ' * 1024 + old_rc = sys.getrefcount(imm) + memio = self.ioclass(imm) + self.assertEqual(sys.getrefcount(imm), old_rc + 1) + mutation(memio) + self.assertEqual(sys.getrefcount(imm), old_rc) + + @support.cpython_only + def test_cow_truncate(self): + # Ensure truncate causes a copy. + def mutation(memio): + memio.truncate(1) + self._test_cow_mutation(mutation) + + @support.cpython_only + def test_cow_write(self): + # Ensure write that would not cause a resize still results in a copy. + def mutation(memio): + memio.seek(0) + memio.write(b'foo') + self._test_cow_mutation(mutation) + + @support.cpython_only + def test_cow_setstate(self): + # __setstate__ should cause buffer to be released. + memio = self.ioclass(b'foooooo') + state = memio.__getstate__() + def mutation(memio): + memio.__setstate__(state) + self._test_cow_mutation(mutation) + + @support.cpython_only + def test_cow_mutable(self): + # BytesIO should accept only Bytes for copy-on-write sharing, since + # arbitrary buffer-exporting objects like bytearray() aren't guaranteed + # to be immutable. + ba = bytearray(1024) + old_rc = sys.getrefcount(ba) + memio = self.ioclass(ba) + self.assertEqual(sys.getrefcount(ba), old_rc) class CStringIOTest(PyStringIOTest): ioclass = io.StringIO diff --git a/Lib/test/test_memoryview.py b/Lib/test/test_memoryview.py index 4bc3133..e9bd9fd 100644 --- a/Lib/test/test_memoryview.py +++ b/Lib/test/test_memoryview.py @@ -369,12 +369,12 @@ class AbstractMemoryTests: d = memoryview(b) del b - + self.assertEqual(c[0], 256) self.assertEqual(d[0], 256) self.assertEqual(c.format, "H") self.assertEqual(d.format, "H") - + _ = m.cast('I') self.assertEqual(c[0], 256) self.assertEqual(d[0], 256) diff --git a/Lib/test/test_module.py b/Lib/test/test_module.py index 1230293..9da3536 100644 --- a/Lib/test/test_module.py +++ b/Lib/test/test_module.py @@ -30,6 +30,22 @@ class ModuleTests(unittest.TestCase): pass self.assertEqual(foo.__doc__, ModuleType.__doc__) + def test_unintialized_missing_getattr(self): + # Issue 8297 + # test the text in the AttributeError of an uninitialized module + foo = ModuleType.__new__(ModuleType) + self.assertRaisesRegex( + AttributeError, "module has no attribute 'not_here'", + getattr, foo, "not_here") + + def test_missing_getattr(self): + # Issue 8297 + # test the text in the AttributeError + foo = ModuleType("foo") + self.assertRaisesRegex( + AttributeError, "module 'foo' has no attribute 'not_here'", + getattr, foo, "not_here") + def test_no_docstring(self): # Regularly initialized module, no docstring foo = ModuleType("foo") @@ -211,6 +227,14 @@ a = A(destroyed)""" b"len = len", b"shutil.rmtree = rmtree"}) + def test_descriptor_errors_propogate(self): + class Descr: + def __get__(self, o, t): + raise RuntimeError + class M(ModuleType): + melon = Descr() + self.assertRaises(RuntimeError, getattr, M("mymod"), "melon") + # frozen and namespace module reprs are tested in importlib. diff --git a/Lib/test/test_operator.py b/Lib/test/test_operator.py index ab58a98..1bd0391 100644 --- a/Lib/test/test_operator.py +++ b/Lib/test/test_operator.py @@ -203,6 +203,15 @@ class OperatorTestCase: self.assertRaises(TypeError, operator.mul, None, None) self.assertTrue(operator.mul(5, 2) == 10) + def test_matmul(self): + operator = self.module + self.assertRaises(TypeError, operator.matmul) + self.assertRaises(TypeError, operator.matmul, 42, 42) + class M: + def __matmul__(self, other): + return other - 1 + self.assertEqual(M() @ 42, 41) + def test_neg(self): operator = self.module self.assertRaises(TypeError, operator.neg) @@ -416,6 +425,7 @@ class OperatorTestCase: def __ilshift__ (self, other): return "ilshift" def __imod__ (self, other): return "imod" def __imul__ (self, other): return "imul" + def __imatmul__ (self, other): return "imatmul" def __ior__ (self, other): return "ior" def __ipow__ (self, other): return "ipow" def __irshift__ (self, other): return "irshift" @@ -430,6 +440,7 @@ class OperatorTestCase: self.assertEqual(operator.ilshift (c, 5), "ilshift") self.assertEqual(operator.imod (c, 5), "imod") self.assertEqual(operator.imul (c, 5), "imul") + self.assertEqual(operator.imatmul (c, 5), "imatmul") self.assertEqual(operator.ior (c, 5), "ior") self.assertEqual(operator.ipow (c, 5), "ipow") self.assertEqual(operator.irshift (c, 5), "irshift") diff --git a/Lib/test/test_os.py b/Lib/test/test_os.py index 152ba93..afa7a4a 100644 --- a/Lib/test/test_os.py +++ b/Lib/test/test_os.py @@ -4,6 +4,7 @@ import os import errno +import getpass import unittest import warnings import sys @@ -40,9 +41,35 @@ try: import fcntl except ImportError: fcntl = None +try: + import _winapi +except ImportError: + _winapi = None +try: + import grp + groups = [g.gr_gid for g in grp.getgrall() if getpass.getuser() in g.gr_mem] + if hasattr(os, 'getgid'): + process_gid = os.getgid() + if process_gid not in groups: + groups.append(process_gid) +except ImportError: + groups = [] +try: + import pwd + all_users = [u.pw_uid for u in pwd.getpwall()] +except ImportError: + all_users = [] +try: + from _testcapi import INT_MAX, PY_SSIZE_T_MAX +except ImportError: + INT_MAX = PY_SSIZE_T_MAX = sys.maxsize from test.script_helper import assert_python_ok +root_in_posix = False +if hasattr(os, 'geteuid'): + root_in_posix = (os.geteuid() == 0) + with warnings.catch_warnings(): warnings.simplefilter("ignore", DeprecationWarning) os.stat_float_times(True) @@ -116,6 +143,26 @@ class FileTests(unittest.TestCase): self.assertEqual(type(s), bytes) self.assertEqual(s, b"spam") + @support.cpython_only + # Skip the test on 32-bit platforms: the number of bytes must fit in a + # Py_ssize_t type + @unittest.skipUnless(INT_MAX < PY_SSIZE_T_MAX, + "needs INT_MAX < PY_SSIZE_T_MAX") + @support.bigmemtest(size=INT_MAX + 10, memuse=1, dry_run=False) + def test_large_read(self, size): + with open(support.TESTFN, "wb") as fp: + fp.write(b'test') + self.addCleanup(support.unlink, support.TESTFN) + + # Issue #21932: Make sure that os.read() does not raise an + # OverflowError for size larger than INT_MAX + with open(support.TESTFN, "rb") as fp: + data = os.read(fp.fileno(), size) + + # The test does not try to read more than 2 GB at once because the + # operating system is free to return less bytes than requested. + self.assertEqual(data, b'test') + def test_write(self): # os.write() accepts bytes- and buffer-like objects but not strings fd = os.open(support.TESTFN, os.O_CREAT | os.O_WRONLY) @@ -533,6 +580,28 @@ class StatAttributeTests(unittest.TestCase): os.stat(r) self.assertEqual(ctx.exception.errno, errno.EBADF) + def check_file_attributes(self, result): + self.assertTrue(hasattr(result, 'st_file_attributes')) + self.assertTrue(isinstance(result.st_file_attributes, int)) + self.assertTrue(0 <= result.st_file_attributes <= 0xFFFFFFFF) + + @unittest.skipUnless(sys.platform == "win32", + "st_file_attributes is Win32 specific") + def test_file_attributes(self): + # test file st_file_attributes (FILE_ATTRIBUTE_DIRECTORY not set) + result = os.stat(self.fname) + self.check_file_attributes(result) + self.assertEqual( + result.st_file_attributes & stat.FILE_ATTRIBUTE_DIRECTORY, + 0) + + # test directory st_file_attributes (FILE_ATTRIBUTE_DIRECTORY set) + result = os.stat(support.TESTFN) + self.check_file_attributes(result) + self.assertEqual( + result.st_file_attributes & stat.FILE_ATTRIBUTE_DIRECTORY, + stat.FILE_ATTRIBUTE_DIRECTORY) + from test import mapping_tests class EnvironTests(mapping_tests.BasicTestMappingProtocol): @@ -912,17 +981,6 @@ class MakedirTests(unittest.TestCase): os.makedirs(path, mode=mode, exist_ok=True) os.umask(old_mask) - @unittest.skipUnless(hasattr(os, 'chown'), 'test needs os.chown') - def test_chown_uid_gid_arguments_must_be_index(self): - stat = os.stat(support.TESTFN) - uid = stat.st_uid - gid = stat.st_gid - for value in (-1.0, -1j, decimal.Decimal(-1), fractions.Fraction(-2, 2)): - self.assertRaises(TypeError, os.chown, support.TESTFN, value, gid) - self.assertRaises(TypeError, os.chown, support.TESTFN, uid, value) - self.assertIsNone(os.chown(support.TESTFN, uid, gid)) - self.assertIsNone(os.chown(support.TESTFN, -1, -1)) - def test_exist_ok_s_isgid_directory(self): path = os.path.join(support.TESTFN, 'dir1') S_ISGID = stat.S_ISGID @@ -973,6 +1031,58 @@ class MakedirTests(unittest.TestCase): os.removedirs(path) +@unittest.skipUnless(hasattr(os, 'chown'), "Test needs chown") +class ChownFileTests(unittest.TestCase): + + def setUpClass(): + os.mkdir(support.TESTFN) + + def test_chown_uid_gid_arguments_must_be_index(self): + stat = os.stat(support.TESTFN) + uid = stat.st_uid + gid = stat.st_gid + for value in (-1.0, -1j, decimal.Decimal(-1), fractions.Fraction(-2, 2)): + self.assertRaises(TypeError, os.chown, support.TESTFN, value, gid) + self.assertRaises(TypeError, os.chown, support.TESTFN, uid, value) + self.assertIsNone(os.chown(support.TESTFN, uid, gid)) + self.assertIsNone(os.chown(support.TESTFN, -1, -1)) + + @unittest.skipUnless(len(groups) > 1, "test needs more than one group") + def test_chown(self): + gid_1, gid_2 = groups[:2] + uid = os.stat(support.TESTFN).st_uid + os.chown(support.TESTFN, uid, gid_1) + gid = os.stat(support.TESTFN).st_gid + self.assertEqual(gid, gid_1) + os.chown(support.TESTFN, uid, gid_2) + gid = os.stat(support.TESTFN).st_gid + self.assertEqual(gid, gid_2) + + @unittest.skipUnless(root_in_posix and len(all_users) > 1, + "test needs root privilege and more than one user") + def test_chown_with_root(self): + uid_1, uid_2 = all_users[:2] + gid = os.stat(support.TESTFN).st_gid + os.chown(support.TESTFN, uid_1, gid) + uid = os.stat(support.TESTFN).st_uid + self.assertEqual(uid, uid_1) + os.chown(support.TESTFN, uid_2, gid) + uid = os.stat(support.TESTFN).st_uid + self.assertEqual(uid, uid_2) + + @unittest.skipUnless(not root_in_posix and len(all_users) > 1, + "test needs non-root account and more than one user") + def test_chown_without_permission(self): + uid_1, uid_2 = all_users[:2] + gid = os.stat(support.TESTFN).st_gid + with self.assertRaises(PermissionError): + os.chown(support.TESTFN, uid_1, gid) + os.chown(support.TESTFN, uid_2, gid) + + def tearDownClass(): + os.rmdir(support.TESTFN) + + class RemoveDirsTests(unittest.TestCase): def setUp(self): os.makedirs(support.TESTFN) @@ -1339,6 +1449,16 @@ class TestInvalidFD(unittest.TestCase): def test_writev(self): self.check(os.writev, [b'abc']) + def test_inheritable(self): + self.check(os.get_inheritable) + self.check(os.set_inheritable, True) + + @unittest.skipUnless(hasattr(os, 'get_blocking'), + 'needs os.get_blocking() and os.set_blocking()') + def test_blocking(self): + self.check(os.get_blocking) + self.check(os.set_blocking, True) + class LinkTests(unittest.TestCase): def setUp(self): @@ -1786,6 +1906,37 @@ class Win32SymlinkTests(unittest.TestCase): shutil.rmtree(level1) +@unittest.skipUnless(sys.platform == "win32", "Win32 specific tests") +class Win32JunctionTests(unittest.TestCase): + junction = 'junctiontest' + junction_target = os.path.dirname(os.path.abspath(__file__)) + + def setUp(self): + assert os.path.exists(self.junction_target) + assert not os.path.exists(self.junction) + + def tearDown(self): + if os.path.exists(self.junction): + # os.rmdir delegates to Windows' RemoveDirectoryW, + # which removes junction points safely. + os.rmdir(self.junction) + + def test_create_junction(self): + _winapi.CreateJunction(self.junction_target, self.junction) + self.assertTrue(os.path.exists(self.junction)) + self.assertTrue(os.path.isdir(self.junction)) + + # Junctions are not recognized as links. + self.assertFalse(os.path.islink(self.junction)) + + def test_unlink_removes_junction(self): + _winapi.CreateJunction(self.junction_target, self.junction) + self.assertTrue(os.path.exists(self.junction)) + + os.unlink(self.junction) + self.assertFalse(os.path.exists(self.junction)) + + @support.skip_unless_symlink class NonLocalSymlinkTests(unittest.TestCase): @@ -1992,11 +2143,13 @@ class TestSendfile(unittest.TestCase): @classmethod def setUpClass(cls): + cls.key = support.threading_setup() with open(support.TESTFN, "wb") as f: f.write(cls.DATA) @classmethod def tearDownClass(cls): + support.threading_cleanup(*cls.key) support.unlink(support.TESTFN) def setUp(self): @@ -2523,41 +2676,27 @@ class FDInheritanceTests(unittest.TestCase): self.assertEqual(os.get_inheritable(slave_fd), False) -@support.reap_threads -def test_main(): - support.run_unittest( - FileTests, - StatAttributeTests, - EnvironTests, - WalkTests, - FwalkTests, - MakedirTests, - DevNullTests, - URandomTests, - ExecTests, - Win32ErrorTests, - TestInvalidFD, - PosixUidGidTests, - Pep383Tests, - Win32KillTests, - Win32ListdirTests, - Win32SymlinkTests, - NonLocalSymlinkTests, - FSEncodingTests, - DeviceEncodingTests, - PidTests, - LoginTests, - LinkTests, - TestSendfile, - ProgramPriorityTests, - ExtendedAttributeTests, - Win32DeprecatedBytesAPI, - TermsizeTests, - OSErrorTests, - RemoveDirsTests, - CPUCountTests, - FDInheritanceTests, - ) +@unittest.skipUnless(hasattr(os, 'get_blocking'), + 'needs os.get_blocking() and os.set_blocking()') +class BlockingTests(unittest.TestCase): + def test_blocking(self): + fd = os.open(__file__, os.O_RDONLY) + self.addCleanup(os.close, fd) + self.assertEqual(os.get_blocking(fd), True) + + os.set_blocking(fd, False) + self.assertEqual(os.get_blocking(fd), False) + + os.set_blocking(fd, True) + self.assertEqual(os.get_blocking(fd), True) + + + +class ExportsTests(unittest.TestCase): + def test_os_all(self): + self.assertIn('open', os.__all__) + self.assertIn('walk', os.__all__) + if __name__ == "__main__": - test_main() + unittest.main() diff --git a/Lib/test/test_pathlib.py b/Lib/test/test_pathlib.py index 11420e2..1c53ab7 100644 --- a/Lib/test/test_pathlib.py +++ b/Lib/test/test_pathlib.py @@ -4,13 +4,10 @@ import os import errno import pathlib import pickle -import shutil import socket import stat -import sys import tempfile import unittest -from contextlib import contextmanager from test import support TESTFN = support.TESTFN @@ -747,7 +744,6 @@ class PureWindowsPathTest(_BasePurePathTest, unittest.TestCase): self.assertEqual(P('//Some/SHARE/a/B'), P('//somE/share/A/b')) def test_as_uri(self): - from urllib.parse import quote_from_bytes P = self.cls with self.assertRaises(ValueError): P('/a/b').as_uri() @@ -1269,11 +1265,55 @@ class _BasePathTest(object): p = self.cls.cwd() self._test_cwd(p) + def _test_home(self, p): + q = self.cls(os.path.expanduser('~')) + self.assertEqual(p, q) + self.assertEqual(str(p), str(q)) + self.assertIs(type(p), type(q)) + self.assertTrue(p.is_absolute()) + + def test_home(self): + p = self.cls.home() + self._test_home(p) + + def test_samefile(self): + fileA_path = os.path.join(BASE, 'fileA') + fileB_path = os.path.join(BASE, 'dirB', 'fileB') + p = self.cls(fileA_path) + pp = self.cls(fileA_path) + q = self.cls(fileB_path) + self.assertTrue(p.samefile(fileA_path)) + self.assertTrue(p.samefile(pp)) + self.assertFalse(p.samefile(fileB_path)) + self.assertFalse(p.samefile(q)) + # Test the non-existent file case + non_existent = os.path.join(BASE, 'foo') + r = self.cls(non_existent) + self.assertRaises(FileNotFoundError, p.samefile, r) + self.assertRaises(FileNotFoundError, p.samefile, non_existent) + self.assertRaises(FileNotFoundError, r.samefile, p) + self.assertRaises(FileNotFoundError, r.samefile, non_existent) + self.assertRaises(FileNotFoundError, r.samefile, r) + self.assertRaises(FileNotFoundError, r.samefile, non_existent) + def test_empty_path(self): # The empty path points to '.' p = self.cls('') self.assertEqual(p.stat(), os.stat('.')) + def test_expanduser_common(self): + P = self.cls + p = P('~') + self.assertEqual(p.expanduser(), P(os.path.expanduser('~'))) + p = P('foo') + self.assertEqual(p.expanduser(), p) + p = P('/~') + self.assertEqual(p.expanduser(), p) + p = P('../~') + self.assertEqual(p.expanduser(), p) + p = P(P('').absolute().anchor) / '~' + self.assertEqual(p.expanduser(), p) + def test_exists(self): P = self.cls p = P(BASE) @@ -1301,6 +1341,23 @@ class _BasePathTest(object): self.assertIsInstance(f, io.RawIOBase) self.assertEqual(f.read().strip(), b"this is file A") + def test_read_write_bytes(self): + p = self.cls(BASE) + (p / 'fileA').write_bytes(b'abcdefg') + self.assertEqual((p / 'fileA').read_bytes(), b'abcdefg') + # check that trying to write str does not truncate the file + self.assertRaises(TypeError, (p / 'fileA').write_bytes, 'somestr') + self.assertEqual((p / 'fileA').read_bytes(), b'abcdefg') + + def test_read_write_text(self): + p = self.cls(BASE) + (p / 'fileA').write_text('äbcdefg', encoding='latin-1') + self.assertEqual((p / 'fileA').read_text( + encoding='utf-8', errors='ignore'), 'bcdefg') + # check that trying to write bytes does not truncate the file + self.assertRaises(TypeError, (p / 'fileA').write_text, b'somebytes') + self.assertEqual((p / 'fileA').read_text(encoding='latin-1'), 'äbcdefg') + def test_iterdir(self): P = self.cls p = P(BASE) @@ -1604,6 +1661,59 @@ class _BasePathTest(object): # the parent's permissions follow the default process settings self.assertEqual(stat.S_IMODE(p.parent.stat().st_mode), mode) + def test_mkdir_exist_ok(self): + p = self.cls(BASE, 'dirB') + st_ctime_first = p.stat().st_ctime + self.assertTrue(p.exists()) + self.assertTrue(p.is_dir()) + with self.assertRaises(FileExistsError) as cm: + p.mkdir() + self.assertEqual(cm.exception.errno, errno.EEXIST) + p.mkdir(exist_ok=True) + self.assertTrue(p.exists()) + self.assertEqual(p.stat().st_ctime, st_ctime_first) + + def test_mkdir_exist_ok_with_parent(self): + p = self.cls(BASE, 'dirC') + self.assertTrue(p.exists()) + with self.assertRaises(FileExistsError) as cm: + p.mkdir() + self.assertEqual(cm.exception.errno, errno.EEXIST) + p = p / 'newdirC' + p.mkdir(parents=True) + st_ctime_first = p.stat().st_ctime + self.assertTrue(p.exists()) + with self.assertRaises(FileExistsError) as cm: + p.mkdir(parents=True) + self.assertEqual(cm.exception.errno, errno.EEXIST) + p.mkdir(parents=True, exist_ok=True) + self.assertTrue(p.exists()) + self.assertEqual(p.stat().st_ctime, st_ctime_first) + + def test_mkdir_with_child_file(self): + p = self.cls(BASE, 'dirB', 'fileB') + self.assertTrue(p.exists()) + # An exception is raised when the last path component is an existing + # regular file, regardless of whether exist_ok is true or not. + with self.assertRaises(FileExistsError) as cm: + p.mkdir(parents=True) + self.assertEqual(cm.exception.errno, errno.EEXIST) + with self.assertRaises(FileExistsError) as cm: + p.mkdir(parents=True, exist_ok=True) + self.assertEqual(cm.exception.errno, errno.EEXIST) + + def test_mkdir_no_parents_file(self): + p = self.cls(BASE, 'fileA') + self.assertTrue(p.exists()) + # An exception is raised when the last path component is an existing + # regular file, regardless of whether exist_ok is true or not. + with self.assertRaises(FileExistsError) as cm: + p.mkdir() + self.assertEqual(cm.exception.errno, errno.EEXIST) + with self.assertRaises(FileExistsError) as cm: + p.mkdir(exist_ok=True) + self.assertEqual(cm.exception.errno, errno.EEXIST) + @with_symlinks def test_symlink_to(self): P = self.cls(BASE) @@ -1846,7 +1956,6 @@ class PosixPathTest(_BasePathTest, unittest.TestCase): @with_symlinks def test_resolve_loop(self): # Loop detection for broken symlinks under POSIX - P = self.cls # Loops with relative symlinks os.symlink('linkX/inside', join('linkX')) self._check_symlink_loop(BASE, 'linkX') @@ -1878,6 +1987,48 @@ class PosixPathTest(_BasePathTest, unittest.TestCase): self.assertEqual(given, expect) self.assertEqual(set(p.rglob("FILEd*")), set()) + def test_expanduser(self): + P = self.cls + support.import_module('pwd') + import pwd + pwdent = pwd.getpwuid(os.getuid()) + username = pwdent.pw_name + userhome = pwdent.pw_dir.rstrip('/') + # find arbitrary different user (if exists) + for pwdent in pwd.getpwall(): + othername = pwdent.pw_name + otherhome = pwdent.pw_dir.rstrip('/') + if othername != username and otherhome: + break + + p1 = P('~/Documents') + p2 = P('~' + username + '/Documents') + p3 = P('~' + othername + '/Documents') + p4 = P('../~' + username + '/Documents') + p5 = P('/~' + username + '/Documents') + p6 = P('') + p7 = P('~fakeuser/Documents') + + with support.EnvironmentVarGuard() as env: + env.pop('HOME', None) + + self.assertEqual(p1.expanduser(), P(userhome) / 'Documents') + self.assertEqual(p2.expanduser(), P(userhome) / 'Documents') + self.assertEqual(p3.expanduser(), P(otherhome) / 'Documents') + self.assertEqual(p4.expanduser(), p4) + self.assertEqual(p5.expanduser(), p5) + self.assertEqual(p6.expanduser(), p6) + self.assertRaises(RuntimeError, p7.expanduser) + + env['HOME'] = '/tmp' + self.assertEqual(p1.expanduser(), P('/tmp/Documents')) + self.assertEqual(p2.expanduser(), P(userhome) / 'Documents') + self.assertEqual(p3.expanduser(), P(otherhome) / 'Documents') + self.assertEqual(p4.expanduser(), p4) + self.assertEqual(p5.expanduser(), p5) + self.assertEqual(p6.expanduser(), p6) + self.assertRaises(RuntimeError, p7.expanduser) + @only_nt class WindowsPathTest(_BasePathTest, unittest.TestCase): @@ -1893,6 +2044,61 @@ class WindowsPathTest(_BasePathTest, unittest.TestCase): p = P(BASE, "dirC") self.assertEqual(set(p.rglob("FILEd")), { P(BASE, "dirC/dirD/fileD") }) + def test_expanduser(self): + P = self.cls + with support.EnvironmentVarGuard() as env: + env.pop('HOME', None) + env.pop('USERPROFILE', None) + env.pop('HOMEPATH', None) + env.pop('HOMEDRIVE', None) + env['USERNAME'] = 'alice' + + # test that the path returns unchanged + p1 = P('~/My Documents') + p2 = P('~alice/My Documents') + p3 = P('~bob/My Documents') + p4 = P('/~/My Documents') + p5 = P('d:~/My Documents') + p6 = P('') + self.assertRaises(RuntimeError, p1.expanduser) + self.assertRaises(RuntimeError, p2.expanduser) + self.assertRaises(RuntimeError, p3.expanduser) + self.assertEqual(p4.expanduser(), p4) + self.assertEqual(p5.expanduser(), p5) + self.assertEqual(p6.expanduser(), p6) + + def check(): + env.pop('USERNAME', None) + self.assertEqual(p1.expanduser(), + P('C:/Users/alice/My Documents')) + self.assertRaises(KeyError, p2.expanduser) + env['USERNAME'] = 'alice' + self.assertEqual(p2.expanduser(), + P('C:/Users/alice/My Documents')) + self.assertEqual(p3.expanduser(), + P('C:/Users/bob/My Documents')) + self.assertEqual(p4.expanduser(), p4) + self.assertEqual(p5.expanduser(), p5) + self.assertEqual(p6.expanduser(), p6) + + # test the first lookup key in the env vars + env['HOME'] = 'C:\\Users\\alice' + check() + + # test that HOMEPATH is available instead + env.pop('HOME', None) + env['HOMEPATH'] = 'C:\\Users\\alice' + check() + + env['HOMEDRIVE'] = 'C:\\' + env['HOMEPATH'] = 'Users\\alice' + check() + + env.pop('HOMEDRIVE', None) + env.pop('HOMEPATH', None) + env['USERPROFILE'] = 'C:\\Users\\alice' + check() + if __name__ == "__main__": unittest.main() diff --git a/Lib/test/test_pkgutil.py b/Lib/test/test_pkgutil.py index e0c8635de..57ebf1f 100644 --- a/Lib/test/test_pkgutil.py +++ b/Lib/test/test_pkgutil.py @@ -104,6 +104,9 @@ class PkgutilTests(unittest.TestCase): class PkgutilPEP302Tests(unittest.TestCase): class MyTestLoader(object): + def create_module(self, spec): + return None + def exec_module(self, mod): # Count how many times the module is reloaded mod.__dict__['loads'] = mod.__dict__.get('loads', 0) + 1 diff --git a/Lib/test/test_platform.py b/Lib/test/test_platform.py index b3de43b..ededbdb 100644 --- a/Lib/test/test_platform.py +++ b/Lib/test/test_platform.py @@ -307,7 +307,7 @@ class PlatformTest(unittest.TestCase): with mock.patch('platform._UNIXCONFDIR', tempdir): distname, version, distid = platform.linux_distribution() - self.assertEqual(distname, 'Fedora') + self.assertEqual(distname, 'Fedora') self.assertEqual(version, '19') self.assertEqual(distid, 'Schr\xf6dinger\u2019s Cat') diff --git a/Lib/test/test_poplib.py b/Lib/test/test_poplib.py index 8a3c9f4..14a519d 100644 --- a/Lib/test/test_poplib.py +++ b/Lib/test/test_poplib.py @@ -345,23 +345,18 @@ class TestPOP3Class(TestCase): if SUPPORTS_SSL: + from test.test_ftplib import SSLConnection - class DummyPOP3_SSLHandler(DummyPOP3Handler): + class DummyPOP3_SSLHandler(SSLConnection, DummyPOP3Handler): def __init__(self, conn): asynchat.async_chat.__init__(self, conn) - ssl_socket = ssl.wrap_socket(self.socket, certfile=CERTFILE, - server_side=True, - do_handshake_on_connect=False) - self.del_channel() - self.set_socket(ssl_socket) - # Must try handshake before calling push() - self.tls_active = True - self.tls_starting = True - self._do_tls_handshake() + self.secure_connection() self.set_terminator(b"\r\n") self.in_buffer = [] self.push('+OK dummy pop3 server ready. <timestamp>') + self.tls_active = True + self.tls_starting = False @requires_ssl @@ -452,7 +447,7 @@ class TestTimeouts(TestCase): del self.thread # Clear out any dangling Thread objects. def server(self, evt, serv): - serv.listen(5) + serv.listen() evt.set() try: conn, addr = serv.accept() diff --git a/Lib/test/test_posix.py b/Lib/test/test_posix.py index 72fdd16..f37f2de 100644 --- a/Lib/test/test_posix.py +++ b/Lib/test/test_posix.py @@ -9,7 +9,6 @@ import errno import sys import time import os -import fcntl import platform import pwd import shutil @@ -355,7 +354,7 @@ class PosixTester(unittest.TestCase): def test_oscloexec(self): fd = os.open(support.TESTFN, os.O_RDONLY|os.O_CLOEXEC) self.addCleanup(os.close, fd) - self.assertTrue(fcntl.fcntl(fd, fcntl.F_GETFD) & fcntl.FD_CLOEXEC) + self.assertFalse(os.get_inheritable(fd)) @unittest.skipUnless(hasattr(posix, 'O_EXLOCK'), 'test needs posix.O_EXLOCK') @@ -605,8 +604,8 @@ class PosixTester(unittest.TestCase): self.addCleanup(os.close, w) self.assertFalse(os.get_inheritable(r)) self.assertFalse(os.get_inheritable(w)) - self.assertTrue(fcntl.fcntl(r, fcntl.F_GETFL) & os.O_NONBLOCK) - self.assertTrue(fcntl.fcntl(w, fcntl.F_GETFL) & os.O_NONBLOCK) + self.assertFalse(os.get_blocking(r)) + self.assertFalse(os.get_blocking(w)) # try reading from an empty pipe: this should fail, not block self.assertRaises(OSError, os.read, r, 1) # try a write big enough to fill-up the pipe: this should either diff --git a/Lib/test/test_posixpath.py b/Lib/test/test_posixpath.py index ec2fbae..b2454794 100644 --- a/Lib/test/test_posixpath.py +++ b/Lib/test/test_posixpath.py @@ -57,18 +57,6 @@ class PosixPathTest(unittest.TestCase): self.assertEqual(posixpath.join(b"/foo/", b"bar/", b"baz/"), b"/foo/bar/baz/") - def test_join_errors(self): - # Check posixpath.join raises friendly TypeErrors. - errmsg = "Can't mix strings and bytes in path components" - with self.assertRaisesRegex(TypeError, errmsg): - posixpath.join(b'bytes', 'str') - with self.assertRaisesRegex(TypeError, errmsg): - posixpath.join('str', b'bytes') - # regression, see #15377 - with self.assertRaises(TypeError) as cm: - posixpath.join(None, 'str') - self.assertNotEqual(cm.exception.args[0], errmsg) - def test_split(self): self.assertEqual(posixpath.split("/foo/bar"), ("/foo", "bar")) self.assertEqual(posixpath.split("/"), ("/", "")) diff --git a/Lib/test/test_pprint.py b/Lib/test/test_pprint.py index ad6a7a1..c056880 100644 --- a/Lib/test/test_pprint.py +++ b/Lib/test/test_pprint.py @@ -192,10 +192,52 @@ class QueryTestCase(unittest.TestCase): o = [o1, o2] expected = """\ [ [0, 1, 2, 3, 4, 5, 6, 7, 8, 9], + {'first': 1, 'second': 2, 'third': 3}]""" + self.assertEqual(pprint.pformat(o, indent=4, width=42), expected) + expected = """\ +[ [0, 1, 2, 3, 4, 5, 6, 7, 8, 9], { 'first': 1, 'second': 2, 'third': 3}]""" - self.assertEqual(pprint.pformat(o, indent=4, width=42), expected) + self.assertEqual(pprint.pformat(o, indent=4, width=41), expected) + + def test_width(self): + expected = """\ +[[[[[[1, 2, 3], + '1 2']]]], + {1: [1, 2, 3], + 2: [12, 34]}, + 'abc def ghi', + ('ab cd ef',), + set2({1, 23}), + [[[[[1, 2, 3], + '1 2']]]]]""" + o = eval(expected) + self.assertEqual(pprint.pformat(o, width=15), expected) + self.assertEqual(pprint.pformat(o, width=16), expected) + self.assertEqual(pprint.pformat(o, width=25), expected) + self.assertEqual(pprint.pformat(o, width=14), """\ +[[[[[[1, + 2, + 3], + '1 ' + '2']]]], + {1: [1, + 2, + 3], + 2: [12, + 34]}, + 'abc def ' + 'ghi', + ('ab cd ' + 'ef',), + set2({1, + 23}), + [[[[[1, + 2, + 3], + '1 ' + '2']]]]]""") def test_sorted_dict(self): # Starting in Python 2.5, pprint sorts dict displays by key regardless @@ -535,13 +577,12 @@ frozenset2({0, def test_str_wrap(self): # pprint tries to wrap strings intelligently fox = 'the quick brown fox jumped over a lazy dog' - self.assertEqual(pprint.pformat(fox, width=20), """\ -('the quick ' - 'brown fox ' - 'jumped over a ' - 'lazy dog')""") + self.assertEqual(pprint.pformat(fox, width=19), """\ +('the quick brown ' + 'fox jumped over ' + 'a lazy dog')""") self.assertEqual(pprint.pformat({'a': 1, 'b': fox, 'c': 2}, - width=26), """\ + width=25), """\ {'a': 1, 'b': 'the quick brown ' 'fox jumped over ' @@ -553,12 +594,34 @@ frozenset2({0, # - non-ASCII is allowed # - an apostrophe doesn't disrupt the pprint special = "Portons dix bons \"whiskys\"\nà l'avocat goujat\t qui fumait au zoo" - self.assertEqual(pprint.pformat(special, width=21), """\ -('Portons dix ' - 'bons "whiskys"\\n' + self.assertEqual(pprint.pformat(special, width=68), repr(special)) + self.assertEqual(pprint.pformat(special, width=31), """\ +('Portons dix bons "whiskys"\\n' + "à l'avocat goujat\\t qui " + 'fumait au zoo')""") + self.assertEqual(pprint.pformat(special, width=20), """\ +('Portons dix bons ' + '"whiskys"\\n' "à l'avocat " 'goujat\\t qui ' 'fumait au zoo')""") + self.assertEqual(pprint.pformat([[[[[special]]]]], width=35), """\ +[[[[['Portons dix bons "whiskys"\\n' + "à l'avocat goujat\\t qui " + 'fumait au zoo']]]]]""") + self.assertEqual(pprint.pformat([[[[[special]]]]], width=25), """\ +[[[[['Portons dix bons ' + '"whiskys"\\n' + "à l'avocat " + 'goujat\\t qui ' + 'fumait au zoo']]]]]""") + self.assertEqual(pprint.pformat([[[[[special]]]]], width=23), """\ +[[[[['Portons dix ' + 'bons "whiskys"\\n' + "à l'avocat " + 'goujat\\t qui ' + 'fumait au ' + 'zoo']]]]]""") # An unwrappable string is formatted as its repr unwrappable = "x" * 100 self.assertEqual(pprint.pformat(unwrappable, width=80), repr(unwrappable)) @@ -581,7 +644,19 @@ frozenset2({0, 14, 15], [], [0], [0, 1], [0, 1, 2], [0, 1, 2, 3], [0, 1, 2, 3, 4]]""" - self.assertEqual(pprint.pformat(o, width=48, compact=True), expected) + self.assertEqual(pprint.pformat(o, width=47, compact=True), expected) + + def test_compact_width(self): + levels = 20 + number = 10 + o = [0] * number + for i in range(levels - 1): + o = [o] + for w in range(levels * 2 + 1, levels + 3 * number - 1): + lines = pprint.pformat(o, width=w, compact=True).splitlines() + maxwidth = max(map(len, lines)) + self.assertLessEqual(maxwidth, w) + self.assertGreater(maxwidth, w - 3) class DottedPrettyPrinter(pprint.PrettyPrinter): diff --git a/Lib/test/test_pty.py b/Lib/test/test_pty.py index 8916861..9b783c3 100644 --- a/Lib/test/test_pty.py +++ b/Lib/test/test_pty.py @@ -1,7 +1,6 @@ from test.support import verbose, run_unittest, import_module, reap_children -#Skip these tests if either fcntl or termios is not available -fcntl = import_module('fcntl') +# Skip these tests if termios is not available import_module('termios') import errno @@ -84,16 +83,18 @@ class PtyTest(unittest.TestCase): # in master_open(), we need to read the EOF. # Ensure the fd is non-blocking in case there's nothing to read. - orig_flags = fcntl.fcntl(master_fd, fcntl.F_GETFL) - fcntl.fcntl(master_fd, fcntl.F_SETFL, orig_flags | os.O_NONBLOCK) + blocking = os.get_blocking(master_fd) try: - s1 = os.read(master_fd, 1024) - self.assertEqual(b'', s1) - except OSError as e: - if e.errno != errno.EAGAIN: - raise - # Restore the original flags. - fcntl.fcntl(master_fd, fcntl.F_SETFL, orig_flags) + os.set_blocking(master_fd, False) + try: + s1 = os.read(master_fd, 1024) + self.assertEqual(b'', s1) + except OSError as e: + if e.errno != errno.EAGAIN: + raise + finally: + # Restore the original flags. + os.set_blocking(master_fd, blocking) debug("Writing to slave_fd") os.write(slave_fd, TEST_STRING_1) diff --git a/Lib/test/test_pydoc.py b/Lib/test/test_pydoc.py index 83f2ec9..50ed4d5 100644 --- a/Lib/test/test_pydoc.py +++ b/Lib/test/test_pydoc.py @@ -2,7 +2,6 @@ import os import sys import builtins import contextlib -import difflib import importlib.util import inspect import pydoc @@ -257,7 +256,10 @@ expected_html_data_docstrings = tuple(s.replace(' ', ' ') for s in expected_data_docstrings) # output pattern for missing module -missing_pattern = "no Python documentation found for '%s'" +missing_pattern = '''\ +No Python documentation found for %r. +Use help() to get the interactive help utility. +Use help(str) for help on the str class.'''.replace('\n', os.linesep) # output pattern for module with bad imports badimport_pattern = "problem in %s - ImportError: No module named %r" @@ -364,15 +366,6 @@ def get_pydoc_text(module): output = patt.sub('', output) return output.strip(), loc -def print_diffs(text1, text2): - "Prints unified diffs for two texts" - # XXX now obsolete, use unittest built-in support - lines1 = text1.splitlines(keepends=True) - lines2 = text2.splitlines(keepends=True) - diffs = difflib.unified_diff(lines1, lines2, n=0, fromfile='expected', - tofile='got') - print('\n' + ''.join(diffs)) - def get_html_title(text): # Bit of hack, but good enough for test purposes header, _, _ = text.partition("</head>") @@ -418,9 +411,7 @@ class PydocDocTest(unittest.TestCase): expected_html = expected_html_pattern % ( (mod_url, mod_file, doc_loc) + expected_html_data_docstrings) - if result != expected_html: - print_diffs(expected_html, result) - self.fail("outputs are not equal, see diff above") + self.assertEqual(result, expected_html) @unittest.skipIf(sys.flags.optimize >= 2, "Docstrings are omitted with -O2 and above") @@ -433,9 +424,7 @@ class PydocDocTest(unittest.TestCase): (doc_loc,) + expected_text_data_docstrings + (inspect.getabsfile(pydoc_mod),)) - if result != expected_text: - print_diffs(expected_text, result) - self.fail("outputs are not equal, see diff above") + self.assertEqual(expected_text, result) def test_text_enum_member_with_value_zero(self): # Test issue #20654 to ensure enum member with value 0 can be @@ -931,9 +920,7 @@ class PydocWithMetaClasses(unittest.TestCase): expected_text = expected_dynamicattribute_pattern % ( (__name__,) + expected_text_data_docstrings[:2]) result = output.getvalue().strip() - if result != expected_text: - print_diffs(expected_text, result) - self.fail("outputs are not equal, see diff above") + self.assertEqual(expected_text, result) @unittest.skipIf(sys.flags.optimize >= 2, "Docstrings are omitted with -O2 and above") @@ -954,9 +941,7 @@ class PydocWithMetaClasses(unittest.TestCase): helper(Class) expected_text = expected_virtualattribute_pattern1 % __name__ result = output.getvalue().strip() - if result != expected_text: - print_diffs(expected_text, result) - self.fail("outputs are not equal, see diff above") + self.assertEqual(expected_text, result) @unittest.skipIf(sys.flags.optimize >= 2, "Docstrings are omitted with -O2 and above") @@ -996,19 +981,13 @@ class PydocWithMetaClasses(unittest.TestCase): helper(Class1) expected_text1 = expected_virtualattribute_pattern2 % __name__ result1 = output.getvalue().strip() - if result1 != expected_text1: - print_diffs(expected_text1, result1) - fail1 = True + self.assertEqual(expected_text1, result1) output = StringIO() helper = pydoc.Helper(output=output) helper(Class2) expected_text2 = expected_virtualattribute_pattern3 % __name__ result2 = output.getvalue().strip() - if result2 != expected_text2: - print_diffs(expected_text2, result2) - fail2 = True - if fail1 or fail2: - self.fail("outputs are not equal, see diff above") + self.assertEqual(expected_text2, result2) @unittest.skipIf(sys.flags.optimize >= 2, "Docstrings are omitted with -O2 and above") @@ -1025,9 +1004,7 @@ class PydocWithMetaClasses(unittest.TestCase): helper(C) expected_text = expected_missingattribute_pattern % __name__ result = output.getvalue().strip() - if result != expected_text: - print_diffs(expected_text, result) - self.fail("outputs are not equal, see diff above") + self.assertEqual(expected_text, result) @reap_threads diff --git a/Lib/test/test_re.py b/Lib/test/test_re.py index 7348af3..0fbf8c5 100644 --- a/Lib/test/test_re.py +++ b/Lib/test/test_re.py @@ -84,7 +84,7 @@ class ReTests(unittest.TestCase): self.assertEqual(re.sub("(?i)b+", "x", "bbbb BBBB"), 'x x') self.assertEqual(re.sub(r'\d+', self.bump_num, '08.2 -2 23x99y'), '9.3 -3 24x100y') - self.assertEqual(re.sub(r'\d+', self.bump_num, '08.2 -2 23x99y', 3), + self.assertEqual(re.sub(r'\d+', self.bump_num, '08.2 -2 23x99y', count=3), '9.3 -3 23x99y') self.assertEqual(re.sub('.', lambda m: r"\n", 'x'), '\\n') @@ -155,8 +155,8 @@ class ReTests(unittest.TestCase): self.assertEqual(re.sub('x', r'\09', 'x'), '\0' + '9') self.assertEqual(re.sub('x', r'\0a', 'x'), '\0' + 'a') - self.assertEqual(re.sub('x', r'\400', 'x'), '\0') - self.assertEqual(re.sub('x', r'\777', 'x'), '\377') + self.assertRaises(re.error, re.sub, 'x', r'\400', 'x') + self.assertRaises(re.error, re.sub, 'x', r'\777', 'x') self.assertRaises(re.error, re.sub, 'x', r'\1', 'x') self.assertRaises(re.error, re.sub, 'x', r'\8', 'x') @@ -180,7 +180,7 @@ class ReTests(unittest.TestCase): def test_qualified_re_sub(self): self.assertEqual(re.sub('a', 'b', 'aaaaa'), 'bbbbb') - self.assertEqual(re.sub('a', 'b', 'aaaaa', 1), 'baaaa') + self.assertEqual(re.sub('a', 'b', 'aaaaa', count=1), 'baaaa') def test_bug_114660(self): self.assertEqual(re.sub(r'(\S)\s+(\S)', r'\1 \2', 'hello there'), @@ -194,6 +194,7 @@ class ReTests(unittest.TestCase): def test_symbolic_groups(self): re.compile('(?P<a>x)(?P=a)(?(a)y)') re.compile('(?P<a1>x)(?P=a1)(?(a1)y)') + re.compile('(?P<a1>x)\1(?(1)y)') self.assertRaises(re.error, re.compile, '(?P<a>)(?P<a>)') self.assertRaises(re.error, re.compile, '(?Px)') self.assertRaises(re.error, re.compile, '(?P=)') @@ -213,6 +214,10 @@ class ReTests(unittest.TestCase): re.compile('(?P<µ>x)(?P=µ)(?(µ)y)') re.compile('(?P<𝔘𝔫𝔦𝔠𝔬𝔡𝔢>x)(?P=𝔘𝔫𝔦𝔠𝔬𝔡𝔢)(?(𝔘𝔫𝔦𝔠𝔬𝔡𝔢)y)') self.assertRaises(re.error, re.compile, '(?P<©>x)') + # Support > 100 groups. + pat = '|'.join('x(?P<a%d>%x)y' % (i, i) for i in range(1, 200 + 1)) + pat = '(?:%s)(?(200)z|t)' % pat + self.assertEqual(re.match(pat, 'xc8yz').span(), (0, 5)) def test_symbolic_refs(self): self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<a', 'xx') @@ -221,48 +226,53 @@ class ReTests(unittest.TestCase): self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<a a>', 'xx') self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<>', 'xx') self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<1a1>', 'xx') + self.assertRaises(re.error, re.sub, '(?P<a>x)', r'\g<2>', 'xx') + self.assertRaises(re.error, re.sub, '(?P<a>x)', r'\2', 'xx') self.assertRaises(IndexError, re.sub, '(?P<a>x)', '\g<ab>', 'xx') - self.assertRaises(re.error, re.sub, '(?P<a>x)|(?P<b>y)', '\g<b>', 'xx') - self.assertRaises(re.error, re.sub, '(?P<a>x)|(?P<b>y)', '\\2', 'xx') + self.assertEqual(re.sub('(?P<a>x)|(?P<b>y)', r'\g<b>', 'xx'), '') + self.assertEqual(re.sub('(?P<a>x)|(?P<b>y)', r'\2', 'xx'), '') self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<-1>', 'xx') # New valid/invalid identifiers in Python 3 self.assertEqual(re.sub('(?P<µ>x)', r'\g<µ>', 'xx'), 'xx') self.assertEqual(re.sub('(?P<𝔘𝔫𝔦𝔠𝔬𝔡𝔢>x)', r'\g<𝔘𝔫𝔦𝔠𝔬𝔡𝔢>', 'xx'), 'xx') self.assertRaises(re.error, re.sub, '(?P<a>x)', r'\g<©>', 'xx') + # Support > 100 groups. + pat = '|'.join('x(?P<a%d>%x)y' % (i, i) for i in range(1, 200 + 1)) + self.assertEqual(re.sub(pat, '\g<200>', 'xc8yzxc8y'), 'c8zc8') def test_re_subn(self): self.assertEqual(re.subn("(?i)b+", "x", "bbbb BBBB"), ('x x', 2)) self.assertEqual(re.subn("b+", "x", "bbbb BBBB"), ('x BBBB', 1)) self.assertEqual(re.subn("b+", "x", "xyz"), ('xyz', 0)) self.assertEqual(re.subn("b*", "x", "xyz"), ('xxxyxzx', 4)) - self.assertEqual(re.subn("b*", "x", "xyz", 2), ('xxxyz', 2)) + self.assertEqual(re.subn("b*", "x", "xyz", count=2), ('xxxyz', 2)) def test_re_split(self): for string in ":a:b::c", S(":a:b::c"): self.assertTypedEqual(re.split(":", string), ['', 'a', 'b', '', 'c']) - self.assertTypedEqual(re.split(":*", string), + self.assertTypedEqual(re.split(":+", string), ['', 'a', 'b', 'c']) - self.assertTypedEqual(re.split("(:*)", string), + self.assertTypedEqual(re.split("(:+)", string), ['', ':', 'a', ':', 'b', '::', 'c']) for string in (b":a:b::c", B(b":a:b::c"), bytearray(b":a:b::c"), memoryview(b":a:b::c")): self.assertTypedEqual(re.split(b":", string), [b'', b'a', b'b', b'', b'c']) - self.assertTypedEqual(re.split(b":*", string), + self.assertTypedEqual(re.split(b":+", string), [b'', b'a', b'b', b'c']) - self.assertTypedEqual(re.split(b"(:*)", string), + self.assertTypedEqual(re.split(b"(:+)", string), [b'', b':', b'a', b':', b'b', b'::', b'c']) for a, b, c in ("\xe0\xdf\xe7", "\u0430\u0431\u0432", "\U0001d49c\U0001d49e\U0001d4b5"): string = ":%s:%s::%s" % (a, b, c) self.assertEqual(re.split(":", string), ['', a, b, '', c]) - self.assertEqual(re.split(":*", string), ['', a, b, c]) - self.assertEqual(re.split("(:*)", string), + self.assertEqual(re.split(":+", string), ['', a, b, c]) + self.assertEqual(re.split("(:+)", string), ['', ':', a, ':', b, '::', c]) - self.assertEqual(re.split("(?::*)", ":a:b::c"), ['', 'a', 'b', 'c']) - self.assertEqual(re.split("(:)*", ":a:b::c"), + self.assertEqual(re.split("(?::+)", ":a:b::c"), ['', 'a', 'b', 'c']) + self.assertEqual(re.split("(:)+", ":a:b::c"), ['', ':', 'a', ':', 'b', ':', 'c']) self.assertEqual(re.split("([b:]+)", ":a:b::c"), ['', ':', 'a', ':b::', 'c']) @@ -272,13 +282,34 @@ class ReTests(unittest.TestCase): self.assertEqual(re.split("(?:b)|(?::+)", ":a:b::c"), ['', 'a', '', '', 'c']) + for sep, expected in [ + (':*', ['', 'a', 'b', 'c']), + ('(?::*)', ['', 'a', 'b', 'c']), + ('(:*)', ['', ':', 'a', ':', 'b', '::', 'c']), + ('(:)*', ['', ':', 'a', ':', 'b', ':', 'c']), + ]: + with self.subTest(sep=sep), self.assertWarns(FutureWarning): + self.assertTypedEqual(re.split(sep, ':a:b::c'), expected) + + for sep, expected in [ + ('', [':a:b::c']), + (r'\b', [':a:b::c']), + (r'(?=:)', [':a:b::c']), + (r'(?<=:)', [':a:b::c']), + ]: + with self.subTest(sep=sep), self.assertRaises(ValueError): + self.assertTypedEqual(re.split(sep, ':a:b::c'), expected) + def test_qualified_re_split(self): - self.assertEqual(re.split(":", ":a:b::c", 2), ['', 'a', 'b::c']) - self.assertEqual(re.split(':', 'a:b:c:d', 2), ['a', 'b', 'c:d']) - self.assertEqual(re.split("(:)", ":a:b::c", 2), + self.assertEqual(re.split(":", ":a:b::c", maxsplit=2), ['', 'a', 'b::c']) + self.assertEqual(re.split(':', 'a:b:c:d', maxsplit=2), ['a', 'b', 'c:d']) + self.assertEqual(re.split("(:)", ":a:b::c", maxsplit=2), ['', ':', 'a', ':', 'b::c']) - self.assertEqual(re.split("(:*)", ":a:b::c", 2), + self.assertEqual(re.split("(:+)", ":a:b::c", maxsplit=2), ['', ':', 'a', ':', 'b::c']) + with self.assertWarns(FutureWarning): + self.assertEqual(re.split("(:*)", ":a:b::c", maxsplit=2), + ['', ':', 'a', ':', 'b::c']) def test_re_findall(self): self.assertEqual(re.findall(":+", "abc"), []) @@ -405,6 +436,10 @@ class ReTests(unittest.TestCase): self.assertIsNone(p.match('abd')) self.assertIsNone(p.match('ac')) + # Support > 100 groups. + pat = '|'.join('x(?P<a%d>%x)y' % (i, i) for i in range(1, 200 + 1)) + pat = '(?:%s)(?(200)z)' % pat + self.assertEqual(re.match(pat, 'xc8yz').span(), (0, 5)) def test_re_groupref(self): self.assertEqual(re.match(r'^(\|)?([^()]+)\1$', '|a|').groups(), @@ -428,6 +463,10 @@ class ReTests(unittest.TestCase): "first second") .expand(r"\2 \1 \g<second> \g<first>"), "second first second first") + self.assertEqual(re.match("(?P<first>first)|(?P<second>second)", + "first") + .expand(r"\2 \g<second>"), + " ") def test_repeat_minmax(self): self.assertIsNone(re.match("^(\w){1}$", "abc")) @@ -484,10 +523,6 @@ class ReTests(unittest.TestCase): "abcd abc bcd bx", re.ASCII).group(1), "bx") self.assertEqual(re.search(r"\B(b.)\B", "abc bcd bc abxd", re.ASCII).group(1), "bx") - self.assertEqual(re.search(r"\b(b.)\b", - "abcd abc bcd bx", re.LOCALE).group(1), "bx") - self.assertEqual(re.search(r"\B(b.)\B", - "abc bcd bc abxd", re.LOCALE).group(1), "bx") self.assertEqual(re.search(r"^abc$", "\nabc\n", re.M).group(0), "abc") self.assertEqual(re.search(r"^\Aabc\Z$", "abc", re.M).group(0), "abc") self.assertIsNone(re.search(r"^\Aabc\Z$", "\nabc\n", re.M)) @@ -508,11 +543,23 @@ class ReTests(unittest.TestCase): b"1aa! a").group(0), b"1aa! a") self.assertEqual(re.search(r"\d\D\w\W\s\S", "1aa! a", re.ASCII).group(0), "1aa! a") - self.assertEqual(re.search(r"\d\D\w\W\s\S", - "1aa! a", re.LOCALE).group(0), "1aa! a") self.assertEqual(re.search(br"\d\D\w\W\s\S", b"1aa! a", re.LOCALE).group(0), b"1aa! a") + def test_other_escapes(self): + self.assertRaises(re.error, re.compile, "\\") + self.assertEqual(re.match(r"\(", '(').group(), '(') + self.assertIsNone(re.match(r"\(", ')')) + self.assertEqual(re.match(r"\\", '\\').group(), '\\') + self.assertEqual(re.match(r"\y", 'y').group(), 'y') + self.assertIsNone(re.match(r"\y", 'z')) + self.assertEqual(re.match(r"[\]]", ']').group(), ']') + self.assertIsNone(re.match(r"[\]]", '[')) + self.assertEqual(re.match(r"[a\-c]", '-').group(), '-') + self.assertIsNone(re.match(r"[a\-c]", 'b')) + self.assertEqual(re.match(r"[\^a]+", 'a^').group(), 'a^') + self.assertIsNone(re.match(r"[\^a]+", 'b')) + def test_string_boundaries(self): # See http://bugs.python.org/issue10713 self.assertEqual(re.search(r"\b(abc)\b", "abc").group(1), @@ -574,9 +621,6 @@ class ReTests(unittest.TestCase): # Group reference. self.assertTrue(re.match(r'(a)b(?=\1)a', 'aba')) self.assertIsNone(re.match(r'(a)b(?=\1)c', 'abac')) - # Named group reference. - self.assertTrue(re.match(r'(?P<g>a)b(?=(?P=g))a', 'aba')) - self.assertIsNone(re.match(r'(?P<g>a)b(?=(?P=g))c', 'abac')) # Conditional group reference. self.assertTrue(re.match(r'(?:(a)|(x))b(?=(?(2)x|c))c', 'abc')) self.assertIsNone(re.match(r'(?:(a)|(x))b(?=(?(2)c|x))c', 'abc')) @@ -594,13 +638,25 @@ class ReTests(unittest.TestCase): self.assertIsNone(re.match(r'ab(?<!b)c', 'abc')) self.assertTrue(re.match(r'ab(?<!c)c', 'abc')) # Group reference. - self.assertWarns(RuntimeWarning, re.compile, r'(a)a(?<=\1)c') - # Named group reference. - self.assertWarns(RuntimeWarning, re.compile, r'(?P<g>a)a(?<=(?P=g))c') + self.assertTrue(re.match(r'(a)a(?<=\1)c', 'aac')) + self.assertIsNone(re.match(r'(a)b(?<=\1)a', 'abaa')) + self.assertIsNone(re.match(r'(a)a(?<!\1)c', 'aac')) + self.assertTrue(re.match(r'(a)b(?<!\1)a', 'abaa')) # Conditional group reference. - self.assertWarns(RuntimeWarning, re.compile, r'(a)b(?<=(?(1)b|x))c') + self.assertIsNone(re.match(r'(?:(a)|(x))b(?<=(?(2)x|c))c', 'abc')) + self.assertIsNone(re.match(r'(?:(a)|(x))b(?<=(?(2)b|x))c', 'abc')) + self.assertTrue(re.match(r'(?:(a)|(x))b(?<=(?(2)x|b))c', 'abc')) + self.assertIsNone(re.match(r'(?:(a)|(x))b(?<=(?(1)c|x))c', 'abc')) + self.assertTrue(re.match(r'(?:(a)|(x))b(?<=(?(1)b|x))c', 'abc')) # Group used before defined. - self.assertWarns(RuntimeWarning, re.compile, r'(a)b(?<=(?(2)b|x))(c)') + self.assertRaises(re.error, re.compile, r'(a)b(?<=(?(2)b|x))(c)') + self.assertIsNone(re.match(r'(a)b(?<=(?(1)c|x))(c)', 'abc')) + self.assertTrue(re.match(r'(a)b(?<=(?(1)b|x))(c)', 'abc')) + # Group defined in the same lookbehind pattern + self.assertRaises(re.error, re.compile, r'(a)b(?<=(.)\2)(c)') + self.assertRaises(re.error, re.compile, r'(a)b(?<=(?P<a>.)(?P=a))(c)') + self.assertRaises(re.error, re.compile, r'(a)b(?<=(a)(?(2)b|x))(c)') + self.assertRaises(re.error, re.compile, r'(a)b(?<=(.)(?<=\2))(c)') def test_ignore_case(self): self.assertEqual(re.match("abc", "ABC", re.I).group(0), "ABC") @@ -692,9 +748,12 @@ class ReTests(unittest.TestCase): self.assertEqual(_sre.getlower(ord('A'), 0), ord('a')) self.assertEqual(_sre.getlower(ord('A'), re.LOCALE), ord('a')) self.assertEqual(_sre.getlower(ord('A'), re.UNICODE), ord('a')) + self.assertEqual(_sre.getlower(ord('A'), re.ASCII), ord('a')) self.assertEqual(re.match("abc", "ABC", re.I).group(0), "ABC") self.assertEqual(re.match(b"abc", b"ABC", re.I).group(0), b"ABC") + self.assertEqual(re.match("abc", "ABC", re.I|re.A).group(0), "ABC") + self.assertEqual(re.match(b"abc", b"ABC", re.I|re.L).group(0), b"ABC") def test_not_literal(self): self.assertEqual(re.search("\s([^a])", " b").group(1), "b") @@ -779,8 +838,10 @@ class ReTests(unittest.TestCase): self.assertEqual(re.X, re.VERBOSE) def test_flags(self): - for flag in [re.I, re.M, re.X, re.S, re.L]: + for flag in [re.I, re.M, re.X, re.S, re.A, re.U]: self.assertTrue(re.compile('^pattern$', flag)) + for flag in [re.I, re.M, re.X, re.S, re.A, re.L]: + self.assertTrue(re.compile(b'^pattern$', flag)) def test_sre_character_literals(self): for i in [0, 8, 16, 32, 64, 127, 128, 255, 256, 0xFFFF, 0x10000, 0x10FFFF]: @@ -802,7 +863,7 @@ class ReTests(unittest.TestCase): self.assertTrue(re.match(r"\08", "\0008")) self.assertTrue(re.match(r"\01", "\001")) self.assertTrue(re.match(r"\018", "\0018")) - self.assertTrue(re.match(r"\567", chr(0o167))) + self.assertRaises(re.error, re.match, r"\567", "") self.assertRaises(re.error, re.match, r"\911", "") self.assertRaises(re.error, re.match, r"\x1", "") self.assertRaises(re.error, re.match, r"\x1z", "") @@ -830,12 +891,13 @@ class ReTests(unittest.TestCase): self.assertTrue(re.match(r"[\U%08x]" % i, chr(i))) self.assertTrue(re.match(r"[\U%08x0]" % i, chr(i)+"0")) self.assertTrue(re.match(r"[\U%08xz]" % i, chr(i)+"z")) - self.assertTrue(re.match(r"[\U0001d49c-\U0001d4b5]", "\U0001d49e")) + self.assertRaises(re.error, re.match, r"[\567]", "") self.assertRaises(re.error, re.match, r"[\911]", "") self.assertRaises(re.error, re.match, r"[\x1z]", "") self.assertRaises(re.error, re.match, r"[\u123z]", "") self.assertRaises(re.error, re.match, r"[\U0001234z]", "") self.assertRaises(re.error, re.match, r"[\U00110000]", "") + self.assertTrue(re.match(r"[\U0001d49c-\U0001d4b5]", "\U0001d49e")) def test_sre_byte_literals(self): for i in [0, 8, 16, 32, 64, 127, 128, 255]: @@ -851,7 +913,7 @@ class ReTests(unittest.TestCase): self.assertTrue(re.match(br"\08", b"\0008")) self.assertTrue(re.match(br"\01", b"\001")) self.assertTrue(re.match(br"\018", b"\0018")) - self.assertTrue(re.match(br"\567", bytes([0o167]))) + self.assertRaises(re.error, re.match, br"\567", b"") self.assertRaises(re.error, re.match, br"\911", b"") self.assertRaises(re.error, re.match, br"\x1", b"") self.assertRaises(re.error, re.match, br"\x1z", b"") @@ -868,6 +930,7 @@ class ReTests(unittest.TestCase): self.assertTrue(re.match((r"[\x%02xz]" % i).encode(), bytes([i]))) self.assertTrue(re.match(br"[\u]", b'u')) self.assertTrue(re.match(br"[\U]", b'U')) + self.assertRaises(re.error, re.match, br"[\567]", b"") self.assertRaises(re.error, re.match, br"[\911]", b"") self.assertRaises(re.error, re.match, br"[\x1z]", b"") @@ -1062,8 +1125,8 @@ class ReTests(unittest.TestCase): def test_inline_flags(self): # Bug #1700 - upper_char = chr(0x1ea0) # Latin Capital Letter A with Dot Bellow - lower_char = chr(0x1ea1) # Latin Small Letter A with Dot Bellow + upper_char = '\u1ea0' # Latin Capital Letter A with Dot Below + lower_char = '\u1ea1' # Latin Small Letter A with Dot Below p = re.compile(upper_char, re.I | re.U) q = p.match(lower_char) @@ -1143,6 +1206,52 @@ class ReTests(unittest.TestCase): self.assertRaises(ValueError, re.compile, '(?a)\w', re.UNICODE) self.assertRaises(ValueError, re.compile, '(?au)\w') + def test_locale_flag(self): + import locale + _, enc = locale.getlocale(locale.LC_CTYPE) + # Search non-ASCII letter + for i in range(128, 256): + try: + c = bytes([i]).decode(enc) + sletter = c.lower() + if sletter == c: continue + bletter = sletter.encode(enc) + if len(bletter) != 1: continue + if bletter.decode(enc) != sletter: continue + bpat = re.escape(bytes([i])) + break + except (UnicodeError, TypeError): + pass + else: + bletter = None + bpat = b'A' + # Bytes patterns + pat = re.compile(bpat, re.LOCALE | re.IGNORECASE) + if bletter: + self.assertTrue(pat.match(bletter)) + pat = re.compile(b'(?L)' + bpat, re.IGNORECASE) + if bletter: + self.assertTrue(pat.match(bletter)) + pat = re.compile(bpat, re.IGNORECASE) + if bletter: + self.assertIsNone(pat.match(bletter)) + pat = re.compile(b'\w', re.LOCALE) + if bletter: + self.assertTrue(pat.match(bletter)) + pat = re.compile(b'(?L)\w') + if bletter: + self.assertTrue(pat.match(bletter)) + pat = re.compile(b'\w') + if bletter: + self.assertIsNone(pat.match(bletter)) + # Incompatibilities + self.assertWarns(DeprecationWarning, re.compile, '', re.LOCALE) + self.assertWarns(DeprecationWarning, re.compile, '(?L)') + self.assertWarns(DeprecationWarning, re.compile, b'', re.LOCALE | re.ASCII) + self.assertWarns(DeprecationWarning, re.compile, b'(?L)', re.ASCII) + self.assertWarns(DeprecationWarning, re.compile, b'(?a)', re.LOCALE) + self.assertWarns(DeprecationWarning, re.compile, b'(?aL)') + def test_bug_6509(self): # Replacement strings of both types must parse properly. # all strings @@ -1170,8 +1279,10 @@ class ReTests(unittest.TestCase): # a RuntimeError is raised instead of OverflowError. long_overflow = 2**128 self.assertRaises(TypeError, re.finditer, "a", {}) - self.assertRaises(OverflowError, _sre.compile, "abc", 0, [long_overflow]) - self.assertRaises(TypeError, _sre.compile, {}, 0, []) + with self.assertRaises(OverflowError): + _sre.compile("abc", 0, [long_overflow], 0, [], []) + with self.assertRaises(TypeError): + _sre.compile({}, 0, [], 0, [], []) def test_search_dot_unicode(self): self.assertTrue(re.search("123.*-", '123abc-')) @@ -1309,22 +1420,22 @@ class ReTests(unittest.TestCase): with captured_stdout() as out: re.compile(pat, re.DEBUG) dump = '''\ -subpattern 1 - literal 46 -subpattern None - branch - in - literal 99 - literal 104 - or - literal 112 - literal 121 -subpattern None - groupref_exists 1 - at at_end - else - literal 58 - literal 32 +SUBPATTERN 1 + LITERAL 46 +SUBPATTERN None + BRANCH + IN + LITERAL 99 + LITERAL 104 + OR + LITERAL 112 + LITERAL 121 +SUBPATTERN None + GROUPREF_EXISTS 1 + AT AT_END + ELSE + LITERAL 58 + LITERAL 32 ''' self.assertEqual(out.getvalue(), dump) # Debug output is output again even a second time (bypassing @@ -1392,6 +1503,42 @@ subpattern None self.assertIsNone(re.match(b'(?Li)\xc5', b'\xe5')) self.assertIsNone(re.match(b'(?Li)\xe5', b'\xc5')) + def test_error(self): + with self.assertRaises(re.error) as cm: + re.compile('(\u20ac))') + err = cm.exception + self.assertIsInstance(err.pattern, str) + self.assertEqual(err.pattern, '(\u20ac))') + self.assertEqual(err.pos, 3) + self.assertEqual(err.lineno, 1) + self.assertEqual(err.colno, 4) + self.assertIn(err.msg, str(err)) + self.assertIn(' at position 3', str(err)) + self.assertNotIn(' at position 3', err.msg) + # Bytes pattern + with self.assertRaises(re.error) as cm: + re.compile(b'(\xa4))') + err = cm.exception + self.assertIsInstance(err.pattern, bytes) + self.assertEqual(err.pattern, b'(\xa4))') + self.assertEqual(err.pos, 3) + # Multiline pattern + with self.assertRaises(re.error) as cm: + re.compile(""" + ( + abc + ) + ) + ( + """, re.VERBOSE) + err = cm.exception + self.assertEqual(err.pos, 77) + self.assertEqual(err.lineno, 5) + self.assertEqual(err.colno, 17) + self.assertIn(err.msg, str(err)) + self.assertIn(' at position 77', str(err)) + self.assertIn('(line 5, column 17)', str(err)) + class PatternReprTests(unittest.TestCase): def check(self, pattern, expected): @@ -1436,6 +1583,10 @@ class PatternReprTests(unittest.TestCase): self.check_flags(b'bytes pattern', re.A, "re.compile(b'bytes pattern', re.ASCII)") + def test_locale(self): + self.check_flags(b'bytes pattern', re.L, + "re.compile(b'bytes pattern', re.LOCALE)") + def test_quotes(self): self.check('random "double quoted" pattern', '''re.compile('random "double quoted" pattern')''') @@ -1549,8 +1700,16 @@ class ExternalTests(unittest.TestCase): pass else: with self.subTest('bytes pattern match'): - bpat = re.compile(bpat) - self.assertTrue(bpat.search(bs)) + obj = re.compile(bpat) + self.assertTrue(obj.search(bs)) + + # Try the match with LOCALE enabled, and check that it + # still succeeds. + with self.subTest('locale-sensitive match'): + obj = re.compile(bpat, re.LOCALE) + result = obj.search(bs) + if result is None: + print('=== Fails on locale-sensitive match', t) # Try the match with the search area limited to the extent # of the match and see if it still succeeds. \B will @@ -1568,13 +1727,6 @@ class ExternalTests(unittest.TestCase): obj = re.compile(pattern, re.IGNORECASE) self.assertTrue(obj.search(s)) - # Try the match with LOCALE enabled, and check that it - # still succeeds. - if '(?u)' not in pattern: - with self.subTest('locale-sensitive match'): - obj = re.compile(pattern, re.LOCALE) - self.assertTrue(obj.search(s)) - # Try the match with UNICODE locale enabled, and check # that it still succeeds. with self.subTest('unicode-sensitive match'): diff --git a/Lib/test/test_readline.py b/Lib/test/test_readline.py index 0b2b0a5..23d6194 100644 --- a/Lib/test/test_readline.py +++ b/Lib/test/test_readline.py @@ -2,8 +2,9 @@ Very minimal unittests for parts of the readline module. """ import os +import tempfile import unittest -from test.support import run_unittest, import_module +from test.support import run_unittest, import_module, unlink from test.script_helper import assert_python_ok # Skip tests if there is no readline module @@ -42,6 +43,45 @@ class TestHistoryManipulation (unittest.TestCase): self.assertEqual(readline.get_current_history_length(), 1) + @unittest.skipUnless(hasattr(readline, "append_history_file"), + "append_history not available") + def test_write_read_append(self): + hfile = tempfile.NamedTemporaryFile(delete=False) + hfile.close() + hfilename = hfile.name + self.addCleanup(unlink, hfilename) + + # test write-clear-read == nop + readline.clear_history() + readline.add_history("first line") + readline.add_history("second line") + readline.write_history_file(hfilename) + + readline.clear_history() + self.assertEqual(readline.get_current_history_length(), 0) + + readline.read_history_file(hfilename) + self.assertEqual(readline.get_current_history_length(), 2) + self.assertEqual(readline.get_history_item(1), "first line") + self.assertEqual(readline.get_history_item(2), "second line") + + # test append + readline.append_history_file(1, hfilename) + readline.clear_history() + readline.read_history_file(hfilename) + self.assertEqual(readline.get_current_history_length(), 3) + self.assertEqual(readline.get_history_item(1), "first line") + self.assertEqual(readline.get_history_item(2), "second line") + self.assertEqual(readline.get_history_item(3), "second line") + + # test 'no such file' behaviour + os.unlink(hfilename) + with self.assertRaises(FileNotFoundError): + readline.append_history_file(1, hfilename) + + # write_history_file can create the target + readline.write_history_file(hfilename) + class TestReadline(unittest.TestCase): diff --git a/Lib/test/test_reprlib.py b/Lib/test/test_reprlib.py index ae67f06..a51c4d7 100644 --- a/Lib/test/test_reprlib.py +++ b/Lib/test/test_reprlib.py @@ -10,7 +10,7 @@ import importlib import importlib.util import unittest -from test.support import run_unittest, create_empty_file, verbose +from test.support import create_empty_file, verbose from reprlib import repr as r # Don't shadow builtin repr from reprlib import Repr from reprlib import recursive_repr @@ -70,18 +70,18 @@ class ReprTests(unittest.TestCase): eq(r([1, 2, 3, 4, 5, 6, 7]), "[1, 2, 3, 4, 5, 6, ...]") # Sets give up after 6 as well - eq(r(set([])), "set([])") - eq(r(set([1])), "set([1])") - eq(r(set([1, 2, 3])), "set([1, 2, 3])") - eq(r(set([1, 2, 3, 4, 5, 6])), "set([1, 2, 3, 4, 5, 6])") - eq(r(set([1, 2, 3, 4, 5, 6, 7])), "set([1, 2, 3, 4, 5, 6, ...])") + eq(r(set([])), "set()") + eq(r(set([1])), "{1}") + eq(r(set([1, 2, 3])), "{1, 2, 3}") + eq(r(set([1, 2, 3, 4, 5, 6])), "{1, 2, 3, 4, 5, 6}") + eq(r(set([1, 2, 3, 4, 5, 6, 7])), "{1, 2, 3, 4, 5, 6, ...}") # Frozensets give up after 6 as well - eq(r(frozenset([])), "frozenset([])") - eq(r(frozenset([1])), "frozenset([1])") - eq(r(frozenset([1, 2, 3])), "frozenset([1, 2, 3])") - eq(r(frozenset([1, 2, 3, 4, 5, 6])), "frozenset([1, 2, 3, 4, 5, 6])") - eq(r(frozenset([1, 2, 3, 4, 5, 6, 7])), "frozenset([1, 2, 3, 4, 5, 6, ...])") + eq(r(frozenset([])), "frozenset()") + eq(r(frozenset([1])), "frozenset({1})") + eq(r(frozenset([1, 2, 3])), "frozenset({1, 2, 3})") + eq(r(frozenset([1, 2, 3, 4, 5, 6])), "frozenset({1, 2, 3, 4, 5, 6})") + eq(r(frozenset([1, 2, 3, 4, 5, 6, 7])), "frozenset({1, 2, 3, 4, 5, 6, ...})") # collections.deque after 6 eq(r(deque([1, 2, 3, 4, 5, 6, 7])), "deque([1, 2, 3, 4, 5, 6, ...])") @@ -94,7 +94,7 @@ class ReprTests(unittest.TestCase): eq(r(d), "{'alice': 1, 'arthur': 1, 'bob': 2, 'charles': 3, ...}") # array.array after 5. - eq(r(array('i')), "array('i', [])") + eq(r(array('i')), "array('i')") eq(r(array('i', [1])), "array('i', [1])") eq(r(array('i', [1, 2])), "array('i', [1, 2])") eq(r(array('i', [1, 2, 3])), "array('i', [1, 2, 3])") @@ -103,6 +103,20 @@ class ReprTests(unittest.TestCase): eq(r(array('i', [1, 2, 3, 4, 5, 6])), "array('i', [1, 2, 3, 4, 5, ...])") + def test_set_literal(self): + eq = self.assertEqual + eq(r({1}), "{1}") + eq(r({1, 2, 3}), "{1, 2, 3}") + eq(r({1, 2, 3, 4, 5, 6}), "{1, 2, 3, 4, 5, 6}") + eq(r({1, 2, 3, 4, 5, 6, 7}), "{1, 2, 3, 4, 5, 6, ...}") + + def test_frozenset(self): + eq = self.assertEqual + eq(r(frozenset({1})), "frozenset({1})") + eq(r(frozenset({1, 2, 3})), "frozenset({1, 2, 3})") + eq(r(frozenset({1, 2, 3, 4, 5, 6})), "frozenset({1, 2, 3, 4, 5, 6})") + eq(r(frozenset({1, 2, 3, 4, 5, 6, 7})), "frozenset({1, 2, 3, 4, 5, 6, ...})") + def test_numbers(self): eq = self.assertEqual eq(r(123), repr(123)) @@ -123,7 +137,7 @@ class ReprTests(unittest.TestCase): eq(r(i2), expected) i3 = ClassWithFailingRepr() - eq(r(i3), ("<ClassWithFailingRepr instance at %x>"%id(i3))) + eq(r(i3), ("<ClassWithFailingRepr instance at %#x>"%id(i3))) s = r(ClassWithFailingRepr) self.assertTrue(s.startswith("<class ")) @@ -373,11 +387,5 @@ class TestRecursiveRepr(unittest.TestCase): m.append(m) self.assertEqual(repr(m), '<a, b, c, d, e, +++, x, +++>') -def test_main(): - run_unittest(ReprTests) - run_unittest(LongReprTest) - run_unittest(TestRecursiveRepr) - - if __name__ == "__main__": - test_main() + unittest.main() diff --git a/Lib/test/test_script_helper.py b/Lib/test/test_script_helper.py index 7540e2e..74333c9 100755 --- a/Lib/test/test_script_helper.py +++ b/Lib/test/test_script_helper.py @@ -36,7 +36,7 @@ class TestScriptHelper(unittest.TestCase): @mock.patch('subprocess.Popen') def test_assert_python_isolated_when_env_not_required(self, mock_popen): with mock.patch.object(script_helper, - '_interpreter_requires_environment', + 'interpreter_requires_environment', return_value=False) as mock_ire_func: mock_popen.side_effect = RuntimeError('bail out of unittest') try: @@ -55,7 +55,7 @@ class TestScriptHelper(unittest.TestCase): def test_assert_python_not_isolated_when_env_is_required(self, mock_popen): """Ensure that -I is not passed when the environment is required.""" with mock.patch.object(script_helper, - '_interpreter_requires_environment', + 'interpreter_requires_environment', return_value=True) as mock_ire_func: mock_popen.side_effect = RuntimeError('bail out of unittest') try: @@ -68,7 +68,7 @@ class TestScriptHelper(unittest.TestCase): class TestScriptHelperEnvironment(unittest.TestCase): - """Code coverage for _interpreter_requires_environment().""" + """Code coverage for interpreter_requires_environment().""" def setUp(self): self.assertTrue( @@ -83,22 +83,22 @@ class TestScriptHelperEnvironment(unittest.TestCase): @mock.patch('subprocess.check_call') def test_interpreter_requires_environment_true(self, mock_check_call): mock_check_call.side_effect = subprocess.CalledProcessError('', '') - self.assertTrue(script_helper._interpreter_requires_environment()) - self.assertTrue(script_helper._interpreter_requires_environment()) + self.assertTrue(script_helper.interpreter_requires_environment()) + self.assertTrue(script_helper.interpreter_requires_environment()) self.assertEqual(1, mock_check_call.call_count) @mock.patch('subprocess.check_call') def test_interpreter_requires_environment_false(self, mock_check_call): # The mocked subprocess.check_call fakes a no-error process. - script_helper._interpreter_requires_environment() - self.assertFalse(script_helper._interpreter_requires_environment()) + script_helper.interpreter_requires_environment() + self.assertFalse(script_helper.interpreter_requires_environment()) self.assertEqual(1, mock_check_call.call_count) @mock.patch('subprocess.check_call') def test_interpreter_requires_environment_details(self, mock_check_call): - script_helper._interpreter_requires_environment() - self.assertFalse(script_helper._interpreter_requires_environment()) - self.assertFalse(script_helper._interpreter_requires_environment()) + script_helper.interpreter_requires_environment() + self.assertFalse(script_helper.interpreter_requires_environment()) + self.assertFalse(script_helper.interpreter_requires_environment()) self.assertEqual(1, mock_check_call.call_count) check_call_command = mock_check_call.call_args[0][0] self.assertEqual(sys.executable, check_call_command[0]) diff --git a/Lib/test/test_selectors.py b/Lib/test/test_selectors.py index 952fda6..9521481 100644 --- a/Lib/test/test_selectors.py +++ b/Lib/test/test_selectors.py @@ -9,10 +9,7 @@ from test import support from time import sleep import unittest import unittest.mock -try: - from time import monotonic as time -except ImportError: - from time import time as time +from time import monotonic as time try: import resource except ImportError: @@ -25,7 +22,7 @@ else: def socketpair(family=socket.AF_INET, type=socket.SOCK_STREAM, proto=0): with socket.socket(family, type, proto) as l: l.bind((support.HOST, 0)) - l.listen(3) + l.listen() c = socket.socket(family, type, proto) try: c.connect(l.getsockname()) @@ -188,8 +185,8 @@ class BaseSelectorTestCase(unittest.TestCase): s.register(wr, selectors.EVENT_WRITE) s.close() - self.assertRaises(KeyError, s.get_key, rd) - self.assertRaises(KeyError, s.get_key, wr) + self.assertRaises(RuntimeError, s.get_key, rd) + self.assertRaises(RuntimeError, s.get_key, wr) self.assertRaises(KeyError, mapping.__getitem__, rd) self.assertRaises(KeyError, mapping.__getitem__, wr) @@ -258,8 +255,8 @@ class BaseSelectorTestCase(unittest.TestCase): sel.register(rd, selectors.EVENT_READ) sel.register(wr, selectors.EVENT_WRITE) - self.assertRaises(KeyError, s.get_key, rd) - self.assertRaises(KeyError, s.get_key, wr) + self.assertRaises(RuntimeError, s.get_key, rd) + self.assertRaises(RuntimeError, s.get_key, wr) def test_fileno(self): s = self.SELECTOR() @@ -455,10 +452,18 @@ class KqueueSelectorTestCase(BaseSelectorTestCase, ScalableSelectorMixIn): SELECTOR = getattr(selectors, 'KqueueSelector', None) +@unittest.skipUnless(hasattr(selectors, 'DevpollSelector'), + "Test needs selectors.DevpollSelector") +class DevpollSelectorTestCase(BaseSelectorTestCase, ScalableSelectorMixIn): + + SELECTOR = getattr(selectors, 'DevpollSelector', None) + + + def test_main(): tests = [DefaultSelectorTestCase, SelectSelectorTestCase, PollSelectorTestCase, EpollSelectorTestCase, - KqueueSelectorTestCase] + KqueueSelectorTestCase, DevpollSelectorTestCase] support.run_unittest(*tests) support.reap_children() diff --git a/Lib/test/test_set.py b/Lib/test/test_set.py index 65e4243..c25386f 100644 --- a/Lib/test/test_set.py +++ b/Lib/test/test_set.py @@ -931,7 +931,7 @@ class TestBasicOpsString(TestBasicOps, unittest.TestCase): class TestBasicOpsBytes(TestBasicOps, unittest.TestCase): def setUp(self): - self.case = "string set" + self.case = "bytes set" self.values = [b"a", b"b", b"c"] self.set = set(self.values) self.dup = set(self.values) diff --git a/Lib/test/test_shutil.py b/Lib/test/test_shutil.py index 9325bc7..c5545ba 100644 --- a/Lib/test/test_shutil.py +++ b/Lib/test/test_shutil.py @@ -34,6 +34,12 @@ try: except ImportError: BZ2_SUPPORTED = False +try: + import lzma + LZMA_SUPPORTED = True +except ImportError: + LZMA_SUPPORTED = False + TESTFN2 = TESTFN + "2" try: @@ -1189,6 +1195,8 @@ class TestShutil(unittest.TestCase): formats = ['tar', 'gztar', 'zip'] if BZ2_SUPPORTED: formats.append('bztar') + if LZMA_SUPPORTED: + formats.append('xztar') for format in formats: tmpdir = self.mkdtemp() @@ -1625,6 +1633,24 @@ class TestMove(unittest.TestCase): rv = shutil.move(self.src_file, os.path.join(self.dst_dir, 'bar')) self.assertEqual(rv, os.path.join(self.dst_dir, 'bar')) + @mock_rename + def test_move_file_special_function(self): + moved = [] + def _copy(src, dst): + moved.append((src, dst)) + shutil.move(self.src_file, self.dst_dir, copy_function=_copy) + self.assertEqual(len(moved), 1) + + @mock_rename + def test_move_dir_special_function(self): + moved = [] + def _copy(src, dst): + moved.append((src, dst)) + support.create_empty_file(os.path.join(self.src_dir, 'child')) + support.create_empty_file(os.path.join(self.src_dir, 'child1')) + shutil.move(self.src_dir, self.dst_dir, copy_function=_copy) + self.assertEqual(len(moved), 3) + class TestCopyFile(unittest.TestCase): diff --git a/Lib/test/test_signal.py b/Lib/test/test_signal.py index 74f74af..774fc80 100644 --- a/Lib/test/test_signal.py +++ b/Lib/test/test_signal.py @@ -1,10 +1,12 @@ import unittest from test import support from contextlib import closing +import enum import gc import pickle import select import signal +import socket import struct import subprocess import traceback @@ -14,6 +16,10 @@ try: import threading except ImportError: threading = None +try: + import _testcapi +except ImportError: + _testcapi = None class HandlerBCalled(Exception): @@ -39,6 +45,23 @@ def ignoring_eintr(__func, *args, **kwargs): return None +class GenericTests(unittest.TestCase): + + @unittest.skipIf(threading is None, "test needs threading module") + def test_enums(self): + for name in dir(signal): + sig = getattr(signal, name) + if name in {'SIG_DFL', 'SIG_IGN'}: + self.assertIsInstance(sig, signal.Handlers) + elif name in {'SIG_BLOCK', 'SIG_UNBLOCK', 'SIG_SETMASK'}: + self.assertIsInstance(sig, signal.Sigmasks) + elif name.startswith('SIG') and not name.startswith('SIG_'): + self.assertIsInstance(sig, signal.Signals) + elif name.startswith('CTRL_'): + self.assertIsInstance(sig, signal.Signals) + self.assertEqual(sys.platform, "win32") + + @unittest.skipIf(sys.platform == "win32", "Not valid on Windows") class InterProcessSignalTests(unittest.TestCase): MAX_DURATION = 20 # Entire test should last at most 20 sec. @@ -195,6 +218,7 @@ class PosixTests(unittest.TestCase): def test_getsignal(self): hup = signal.signal(signal.SIGHUP, self.trivial_signal_handler) + self.assertIsInstance(hup, signal.Handlers) self.assertEqual(signal.getsignal(signal.SIGHUP), self.trivial_signal_handler) signal.signal(signal.SIGHUP, hup) @@ -229,15 +253,77 @@ class WakeupFDTests(unittest.TestCase): def test_invalid_fd(self): fd = support.make_bad_fd() - self.assertRaises(ValueError, signal.set_wakeup_fd, fd) + self.assertRaises((ValueError, OSError), + signal.set_wakeup_fd, fd) + + def test_invalid_socket(self): + sock = socket.socket() + fd = sock.fileno() + sock.close() + self.assertRaises((ValueError, OSError), + signal.set_wakeup_fd, fd) + + def test_set_wakeup_fd_result(self): + r1, w1 = os.pipe() + self.addCleanup(os.close, r1) + self.addCleanup(os.close, w1) + r2, w2 = os.pipe() + self.addCleanup(os.close, r2) + self.addCleanup(os.close, w2) + + if hasattr(os, 'set_blocking'): + os.set_blocking(w1, False) + os.set_blocking(w2, False) + + signal.set_wakeup_fd(w1) + self.assertEqual(signal.set_wakeup_fd(w2), w1) + self.assertEqual(signal.set_wakeup_fd(-1), w2) + self.assertEqual(signal.set_wakeup_fd(-1), -1) + + def test_set_wakeup_fd_socket_result(self): + sock1 = socket.socket() + self.addCleanup(sock1.close) + sock1.setblocking(False) + fd1 = sock1.fileno() + + sock2 = socket.socket() + self.addCleanup(sock2.close) + sock2.setblocking(False) + fd2 = sock2.fileno() + + signal.set_wakeup_fd(fd1) + self.assertEqual(signal.set_wakeup_fd(fd2), fd1) + self.assertEqual(signal.set_wakeup_fd(-1), fd2) + self.assertEqual(signal.set_wakeup_fd(-1), -1) + + # On Windows, files are always blocking and Windows does not provide a + # function to test if a socket is in non-blocking mode. + @unittest.skipIf(sys.platform == "win32", "tests specific to POSIX") + def test_set_wakeup_fd_blocking(self): + rfd, wfd = os.pipe() + self.addCleanup(os.close, rfd) + self.addCleanup(os.close, wfd) + + # fd must be non-blocking + os.set_blocking(wfd, True) + with self.assertRaises(ValueError) as cm: + signal.set_wakeup_fd(wfd) + self.assertEqual(str(cm.exception), + "the fd %s must be in non-blocking mode" % wfd) + + # non-blocking is ok + os.set_blocking(wfd, False) + signal.set_wakeup_fd(wfd) + signal.set_wakeup_fd(-1) @unittest.skipIf(sys.platform == "win32", "Not valid on Windows") class WakeupSignalTests(unittest.TestCase): + @unittest.skipIf(_testcapi is None, 'need _testcapi') def check_wakeup(self, test_body, *signals, ordered=True): # use a subprocess to have only one thread code = """if 1: - import fcntl + import _testcapi import os import signal import struct @@ -260,10 +346,7 @@ class WakeupSignalTests(unittest.TestCase): signal.signal(signal.SIGALRM, handler) read, write = os.pipe() - for fd in (read, write): - flags = fcntl.fcntl(fd, fcntl.F_GETFL, 0) - flags = flags | os.O_NONBLOCK - fcntl.fcntl(fd, fcntl.F_SETFL, flags) + os.set_blocking(write, False) signal.set_wakeup_fd(write) test() @@ -271,21 +354,21 @@ class WakeupSignalTests(unittest.TestCase): os.close(read) os.close(write) - """.format(signals, ordered, test_body) + """.format(tuple(map(int, signals)), ordered, test_body) assert_python_ok('-c', code) + @unittest.skipIf(_testcapi is None, 'need _testcapi') def test_wakeup_write_error(self): # Issue #16105: write() errors in the C signal handler should not # pass silently. # Use a subprocess to have only one thread. code = """if 1: + import _testcapi import errno - import fcntl import os import signal import sys - import time from test.support import captured_stderr def handler(signum, frame): @@ -293,15 +376,13 @@ class WakeupSignalTests(unittest.TestCase): signal.signal(signal.SIGALRM, handler) r, w = os.pipe() - flags = fcntl.fcntl(r, fcntl.F_GETFL, 0) - fcntl.fcntl(r, fcntl.F_SETFL, flags | os.O_NONBLOCK) + os.set_blocking(r, False) # Set wakeup_fd a read-only file descriptor to trigger the error signal.set_wakeup_fd(r) try: with captured_stderr() as err: - signal.alarm(1) - time.sleep(5.0) + _testcapi.raise_signal(signal.SIGALRM) except ZeroDivisionError: # An ignored exception should have been printed out on stderr err = err.getvalue() @@ -312,6 +393,9 @@ class WakeupSignalTests(unittest.TestCase): raise AssertionError(err) else: raise AssertionError("ZeroDivisionError not raised") + + os.close(r) + os.close(w) """ r, w = os.pipe() try: @@ -375,9 +459,10 @@ class WakeupSignalTests(unittest.TestCase): def test_signum(self): self.check_wakeup("""def test(): + import _testcapi signal.signal(signal.SIGUSR1, handler) - os.kill(os.getpid(), signal.SIGUSR1) - os.kill(os.getpid(), signal.SIGALRM) + _testcapi.raise_signal(signal.SIGUSR1) + _testcapi.raise_signal(signal.SIGALRM) """, signal.SIGUSR1, signal.SIGALRM) @unittest.skipUnless(hasattr(signal, 'pthread_sigmask'), @@ -391,13 +476,97 @@ class WakeupSignalTests(unittest.TestCase): signal.signal(signum2, handler) signal.pthread_sigmask(signal.SIG_BLOCK, (signum1, signum2)) - os.kill(os.getpid(), signum1) - os.kill(os.getpid(), signum2) + _testcapi.raise_signal(signum1) + _testcapi.raise_signal(signum2) # Unblocking the 2 signals calls the C signal handler twice signal.pthread_sigmask(signal.SIG_UNBLOCK, (signum1, signum2)) """, signal.SIGUSR1, signal.SIGUSR2, ordered=False) +@unittest.skipUnless(hasattr(socket, 'socketpair'), 'need socket.socketpair') +class WakeupSocketSignalTests(unittest.TestCase): + + @unittest.skipIf(_testcapi is None, 'need _testcapi') + def test_socket(self): + # use a subprocess to have only one thread + code = """if 1: + import signal + import socket + import struct + import _testcapi + + signum = signal.SIGINT + signals = (signum,) + + def handler(signum, frame): + pass + + signal.signal(signum, handler) + + read, write = socket.socketpair() + read.setblocking(False) + write.setblocking(False) + signal.set_wakeup_fd(write.fileno()) + + _testcapi.raise_signal(signum) + + data = read.recv(1) + if not data: + raise Exception("no signum written") + raised = struct.unpack('B', data) + if raised != signals: + raise Exception("%r != %r" % (raised, signals)) + + read.close() + write.close() + """ + + assert_python_ok('-c', code) + + @unittest.skipIf(_testcapi is None, 'need _testcapi') + def test_send_error(self): + # Use a subprocess to have only one thread. + if os.name == 'nt': + action = 'send' + else: + action = 'write' + code = """if 1: + import errno + import signal + import socket + import sys + import time + import _testcapi + from test.support import captured_stderr + + signum = signal.SIGINT + + def handler(signum, frame): + pass + + signal.signal(signum, handler) + + read, write = socket.socketpair() + read.setblocking(False) + write.setblocking(False) + + signal.set_wakeup_fd(write.fileno()) + + # Close sockets: send() will fail + read.close() + write.close() + + with captured_stderr() as err: + _testcapi.raise_signal(signum) + + err = err.getvalue() + if ('Exception ignored when trying to {action} to the signal wakeup fd' + not in err): + raise AssertionError(err) + """.format(action=action) + assert_python_ok('-c', code) + + @unittest.skipIf(sys.platform == "win32", "Not valid on Windows") class SiginterruptTest(unittest.TestCase): @@ -418,7 +587,7 @@ class SiginterruptTest(unittest.TestCase): r, w = os.pipe() def handler(signum, frame): - pass + 1 / 0 signal.signal(signal.SIGALRM, handler) if interrupt is not None: @@ -428,18 +597,21 @@ class SiginterruptTest(unittest.TestCase): sys.stdout.flush() # run the test twice - for loop in range(2): - # send a SIGALRM in a second (during the read) - signal.alarm(1) - try: - # blocking call: read from a pipe without data - os.read(r, 1) - except OSError as err: - if err.errno != errno.EINTR: - raise - else: - sys.exit(2) - sys.exit(3) + try: + for loop in range(2): + # send a SIGALRM in a second (during the read) + signal.alarm(1) + try: + # blocking call: read from a pipe without data + os.read(r, 1) + except ZeroDivisionError: + pass + else: + sys.exit(2) + sys.exit(3) + finally: + os.close(r) + os.close(w) """ % (interrupt,) with spawn_python('-c', code) as process: try: @@ -604,6 +776,8 @@ class PendingSignalsTests(unittest.TestCase): signal.pthread_sigmask(signal.SIG_BLOCK, [signum]) os.kill(os.getpid(), signum) pending = signal.sigpending() + for sig in pending: + assert isinstance(sig, signal.Signals), repr(pending) if pending != {signum}: raise Exception('%s != {%s}' % (pending, signum)) try: @@ -660,6 +834,7 @@ class PendingSignalsTests(unittest.TestCase): code = '''if 1: import signal import sys + from signal import Signals def handler(signum, frame): 1/0 @@ -702,6 +877,7 @@ class PendingSignalsTests(unittest.TestCase): def test(signum): signal.alarm(1) received = signal.sigwait([signum]) + assert isinstance(received, signal.Signals), received if received != signum: raise Exception('received %s, not %s' % (received, signum)) ''') @@ -842,8 +1018,14 @@ class PendingSignalsTests(unittest.TestCase): def kill(signum): os.kill(os.getpid(), signum) + def check_mask(mask): + for sig in mask: + assert isinstance(sig, signal.Signals), repr(sig) + def read_sigmask(): - return signal.pthread_sigmask(signal.SIG_BLOCK, []) + sigmask = signal.pthread_sigmask(signal.SIG_BLOCK, []) + check_mask(sigmask) + return sigmask signum = signal.SIGUSR1 @@ -852,6 +1034,7 @@ class PendingSignalsTests(unittest.TestCase): # Unblock SIGUSR1 (and copy the old mask) to test our signal handler old_mask = signal.pthread_sigmask(signal.SIG_UNBLOCK, [signum]) + check_mask(old_mask) try: kill(signum) except ZeroDivisionError: @@ -861,11 +1044,13 @@ class PendingSignalsTests(unittest.TestCase): # Block and then raise SIGUSR1. The signal is blocked: the signal # handler is not called, and the signal is now pending - signal.pthread_sigmask(signal.SIG_BLOCK, [signum]) + mask = signal.pthread_sigmask(signal.SIG_BLOCK, [signum]) + check_mask(mask) kill(signum) # Check the new mask blocked = read_sigmask() + check_mask(blocked) if signum not in blocked: raise Exception("%s not in %s" % (signum, blocked)) if old_mask ^ blocked != {signum}: @@ -928,8 +1113,9 @@ class PendingSignalsTests(unittest.TestCase): def test_main(): try: - support.run_unittest(PosixTests, InterProcessSignalTests, + support.run_unittest(GenericTests, PosixTests, InterProcessSignalTests, WakeupFDTests, WakeupSignalTests, + WakeupSocketSignalTests, SiginterruptTest, ItimerTest, WindowsSignalTests, PendingSignalsTests) finally: diff --git a/Lib/test/test_site.py b/Lib/test/test_site.py index f71cf73..e234164 100644 --- a/Lib/test/test_site.py +++ b/Lib/test/test_site.py @@ -147,7 +147,7 @@ class HelperFunctionsTests(unittest.TestCase): re.escape(os.path.join(pth_dir, pth_fn))) # XXX: ditto previous XXX comment. self.assertRegex(err_out.getvalue(), 'Traceback') - self.assertRegex(err_out.getvalue(), 'TypeError') + self.assertRegex(err_out.getvalue(), 'ValueError') def test_addsitedir(self): # Same tests for test_addpackage since addsitedir() essentially just @@ -235,20 +235,18 @@ class HelperFunctionsTests(unittest.TestCase): # OS X framework builds site.PREFIXES = ['Python.framework'] dirs = site.getsitepackages() - self.assertEqual(len(dirs), 3) + self.assertEqual(len(dirs), 2) wanted = os.path.join('/Library', sysconfig.get_config_var("PYTHONFRAMEWORK"), sys.version[:3], 'site-packages') - self.assertEqual(dirs[2], wanted) + self.assertEqual(dirs[1], wanted) elif os.sep == '/': # OS X non-framwework builds, Linux, FreeBSD, etc - self.assertEqual(len(dirs), 2) + self.assertEqual(len(dirs), 1) wanted = os.path.join('xoxo', 'lib', 'python' + sys.version[:3], 'site-packages') self.assertEqual(dirs[0], wanted) - wanted = os.path.join('xoxo', 'lib', 'site-python') - self.assertEqual(dirs[1], wanted) else: # other platforms self.assertEqual(len(dirs), 2) diff --git a/Lib/test/test_smtpd.py b/Lib/test/test_smtpd.py index 93f14c4..6eb47f1 100644 --- a/Lib/test/test_smtpd.py +++ b/Lib/test/test_smtpd.py @@ -1,4 +1,5 @@ import unittest +import textwrap from test import support, mock_socket import socket import io @@ -7,15 +8,22 @@ import asyncore class DummyServer(smtpd.SMTPServer): - def __init__(self, localaddr, remoteaddr): - smtpd.SMTPServer.__init__(self, localaddr, remoteaddr) + def __init__(self, *args, **kwargs): + smtpd.SMTPServer.__init__(self, *args, **kwargs) self.messages = [] + if self._decode_data: + self.return_status = 'return status' + else: + self.return_status = b'return status' def process_message(self, peer, mailfrom, rcpttos, data): self.messages.append((peer, mailfrom, rcpttos, data)) - if data == 'return status': + if data == self.return_status: return '250 Okish' + def process_smtputf8_message(self, *args, **kwargs): + return '250 SMTPUTF8 message okish' + class DummyDispatcherBroken(Exception): pass @@ -31,9 +39,10 @@ class SMTPDServerTest(unittest.TestCase): smtpd.socket = asyncore.socket = mock_socket def test_process_message_unimplemented(self): - server = smtpd.SMTPServer('a', 'b') + server = smtpd.SMTPServer((support.HOST, 0), ('b', 0), + decode_data=True) conn, addr = server.accept() - channel = smtpd.SMTPChannel(server, conn, addr) + channel = smtpd.SMTPChannel(server, conn, addr, decode_data=True) def write_line(line): channel.socket.queue_recv(line) @@ -45,19 +54,163 @@ class SMTPDServerTest(unittest.TestCase): write_line(b'DATA') self.assertRaises(NotImplementedError, write_line, b'spam\r\n.\r\n') + def test_process_smtputf8_message_unimplemented(self): + server = smtpd.SMTPServer((support.HOST, 0), ('b', 0), + enable_SMTPUTF8=True) + conn, addr = server.accept() + channel = smtpd.SMTPChannel(server, conn, addr, enable_SMTPUTF8=True) + + def write_line(line): + channel.socket.queue_recv(line) + channel.handle_read() + + write_line(b'EHLO example') + write_line(b'MAIL From: <eggs@example> BODY=8BITMIME SMTPUTF8') + write_line(b'RCPT To: <spam@example>') + write_line(b'DATA') + self.assertRaises(NotImplementedError, write_line, b'spam\r\n.\r\n') + + def test_decode_data_default_warns(self): + with self.assertWarns(DeprecationWarning): + smtpd.SMTPServer((support.HOST, 0), ('b', 0)) + + def test_decode_data_and_enable_SMTPUTF8_raises(self): + self.assertRaises( + ValueError, + smtpd.SMTPServer, + (support.HOST, 0), + ('b', 0), + enable_SMTPUTF8=True, + decode_data=True) + + def tearDown(self): + asyncore.close_all() + asyncore.socket = smtpd.socket = socket + + +class DebuggingServerTest(unittest.TestCase): + + def setUp(self): + smtpd.socket = asyncore.socket = mock_socket + + def send_data(self, channel, data, enable_SMTPUTF8=False): + def write_line(line): + channel.socket.queue_recv(line) + channel.handle_read() + write_line(b'EHLO example') + if enable_SMTPUTF8: + write_line(b'MAIL From:eggs@example BODY=8BITMIME SMTPUTF8') + else: + write_line(b'MAIL From:eggs@example') + write_line(b'RCPT To:spam@example') + write_line(b'DATA') + write_line(data) + write_line(b'.') + + def test_process_message_with_decode_data_true(self): + server = smtpd.DebuggingServer((support.HOST, 0), ('b', 0), + decode_data=True) + conn, addr = server.accept() + channel = smtpd.SMTPChannel(server, conn, addr, decode_data=True) + with support.captured_stdout() as s: + self.send_data(channel, b'From: test\n\nhello\n') + stdout = s.getvalue() + self.assertEqual(stdout, textwrap.dedent("""\ + ---------- MESSAGE FOLLOWS ---------- + From: test + X-Peer: peer-address + + hello + ------------ END MESSAGE ------------ + """)) + + def test_process_message_with_decode_data_false(self): + server = smtpd.DebuggingServer((support.HOST, 0), ('b', 0), + decode_data=False) + conn, addr = server.accept() + channel = smtpd.SMTPChannel(server, conn, addr, decode_data=False) + with support.captured_stdout() as s: + self.send_data(channel, b'From: test\n\nh\xc3\xa9llo\xff\n') + stdout = s.getvalue() + self.assertEqual(stdout, textwrap.dedent("""\ + ---------- MESSAGE FOLLOWS ---------- + b'From: test' + b'X-Peer: peer-address' + b'' + b'h\\xc3\\xa9llo\\xff' + ------------ END MESSAGE ------------ + """)) + + def test_process_message_with_enable_SMTPUTF8_true(self): + server = smtpd.DebuggingServer((support.HOST, 0), ('b', 0), + enable_SMTPUTF8=True) + conn, addr = server.accept() + channel = smtpd.SMTPChannel(server, conn, addr, enable_SMTPUTF8=True) + with support.captured_stdout() as s: + self.send_data(channel, b'From: test\n\nh\xc3\xa9llo\xff\n') + stdout = s.getvalue() + self.assertEqual(stdout, textwrap.dedent("""\ + ---------- MESSAGE FOLLOWS ---------- + b'From: test' + b'X-Peer: peer-address' + b'' + b'h\\xc3\\xa9llo\\xff' + ------------ END MESSAGE ------------ + """)) + + def test_process_SMTPUTF8_message_with_enable_SMTPUTF8_true(self): + server = smtpd.DebuggingServer((support.HOST, 0), ('b', 0), + enable_SMTPUTF8=True) + conn, addr = server.accept() + channel = smtpd.SMTPChannel(server, conn, addr, enable_SMTPUTF8=True) + with support.captured_stdout() as s: + self.send_data(channel, b'From: test\n\nh\xc3\xa9llo\xff\n', + enable_SMTPUTF8=True) + stdout = s.getvalue() + self.assertEqual(stdout, textwrap.dedent("""\ + ----- SMTPUTF8 MESSAGE FOLLOWS ------ + b'From: test' + b'X-Peer: peer-address' + b'' + b'h\\xc3\\xa9llo\\xff' + ------------ END MESSAGE ------------ + """)) + def tearDown(self): asyncore.close_all() asyncore.socket = smtpd.socket = socket +class TestFamilyDetection(unittest.TestCase): + def setUp(self): + smtpd.socket = asyncore.socket = mock_socket + + def tearDown(self): + asyncore.close_all() + asyncore.socket = smtpd.socket = socket + + @unittest.skipUnless(support.IPV6_ENABLED, "IPv6 not enabled") + def test_socket_uses_IPv6(self): + server = smtpd.SMTPServer((support.HOSTv6, 0), (support.HOST, 0), + decode_data=False) + self.assertEqual(server.socket.family, socket.AF_INET6) + + def test_socket_uses_IPv4(self): + server = smtpd.SMTPServer((support.HOST, 0), (support.HOSTv6, 0), + decode_data=False) + self.assertEqual(server.socket.family, socket.AF_INET) + + class SMTPDChannelTest(unittest.TestCase): def setUp(self): smtpd.socket = asyncore.socket = mock_socket self.old_debugstream = smtpd.DEBUGSTREAM self.debug = smtpd.DEBUGSTREAM = io.StringIO() - self.server = DummyServer('a', 'b') + self.server = DummyServer((support.HOST, 0), ('b', 0), + decode_data=True) conn, addr = self.server.accept() - self.channel = smtpd.SMTPChannel(self.server, conn, addr) + self.channel = smtpd.SMTPChannel(self.server, conn, addr, + decode_data=True) def tearDown(self): asyncore.close_all() @@ -69,7 +222,9 @@ class SMTPDChannelTest(unittest.TestCase): self.channel.handle_read() def test_broken_connect(self): - self.assertRaises(DummyDispatcherBroken, BrokenDummyServer, 'a', 'b') + self.assertRaises( + DummyDispatcherBroken, BrokenDummyServer, + (support.HOST, 0), ('b', 0), decode_data=True) def test_server_accept(self): self.server.handle_accept() @@ -214,6 +369,12 @@ class SMTPDChannelTest(unittest.TestCase): self.assertEqual(self.channel.socket.last, b'500 Error: line too long\r\n') + def test_MAIL_command_rejects_SMTPUTF8_by_default(self): + self.write_line(b'EHLO example') + self.write_line( + b'MAIL from: <naive@example.com> BODY=8BITMIME SMTPUTF8') + self.assertEqual(self.channel.socket.last[0:1], b'5') + def test_data_longer_than_default_data_size_limit(self): # Hack the default so we don't have to generate so much data. self.channel.data_size_limit = 1048 @@ -387,7 +548,10 @@ class SMTPDChannelTest(unittest.TestCase): self.write_line(b'data\r\nmore\r\n.') self.assertEqual(self.channel.socket.last, b'250 OK\r\n') self.assertEqual(self.server.messages, - [('peer', 'eggs@example', ['spam@example'], 'data\nmore')]) + [(('peer-address', 'peer-port'), + 'eggs@example', + ['spam@example'], + 'data\nmore')]) def test_DATA_syntax(self): self.write_line(b'HELO example') @@ -417,7 +581,10 @@ class SMTPDChannelTest(unittest.TestCase): self.write_line(b'DATA') self.write_line(b'data\r\n.') self.assertEqual(self.server.messages, - [('peer', 'eggs@example', ['spam@example','ham@example'], 'data')]) + [(('peer-address', 'peer-port'), + 'eggs@example', + ['spam@example','ham@example'], + 'data')]) def test_manual_status(self): # checks that the Channel is able to return a custom status message @@ -439,7 +606,10 @@ class SMTPDChannelTest(unittest.TestCase): self.write_line(b'DATA') self.write_line(b'data\r\n.') self.assertEqual(self.server.messages, - [('peer', 'foo@example', ['eggs@example'], 'data')]) + [(('peer-address', 'peer-port'), + 'foo@example', + ['eggs@example'], + 'data')]) def test_HELO_RSET(self): self.write_line(b'HELO example') @@ -502,6 +672,24 @@ class SMTPDChannelTest(unittest.TestCase): with support.check_warnings(('', DeprecationWarning)): self.channel._SMTPChannel__addr = 'spam' + def test_decode_data_default_warning(self): + with self.assertWarns(DeprecationWarning): + server = DummyServer((support.HOST, 0), ('b', 0)) + conn, addr = self.server.accept() + with self.assertWarns(DeprecationWarning): + smtpd.SMTPChannel(server, conn, addr) + +@unittest.skipUnless(support.IPV6_ENABLED, "IPv6 not enabled") +class SMTPDChannelIPv6Test(SMTPDChannelTest): + def setUp(self): + smtpd.socket = asyncore.socket = mock_socket + self.old_debugstream = smtpd.DEBUGSTREAM + self.debug = smtpd.DEBUGSTREAM = io.StringIO() + self.server = DummyServer((support.HOSTv6, 0), ('b', 0), + decode_data=True) + conn, addr = self.server.accept() + self.channel = smtpd.SMTPChannel(self.server, conn, addr, + decode_data=True) class SMTPDChannelWithDataSizeLimitTest(unittest.TestCase): @@ -509,10 +697,12 @@ class SMTPDChannelWithDataSizeLimitTest(unittest.TestCase): smtpd.socket = asyncore.socket = mock_socket self.old_debugstream = smtpd.DEBUGSTREAM self.debug = smtpd.DEBUGSTREAM = io.StringIO() - self.server = DummyServer('a', 'b') + self.server = DummyServer((support.HOST, 0), ('b', 0), + decode_data=True) conn, addr = self.server.accept() # Set DATA size limit to 32 bytes for easy testing - self.channel = smtpd.SMTPChannel(self.server, conn, addr, 32) + self.channel = smtpd.SMTPChannel(self.server, conn, addr, 32, + decode_data=True) def tearDown(self): asyncore.close_all() @@ -536,7 +726,10 @@ class SMTPDChannelWithDataSizeLimitTest(unittest.TestCase): self.write_line(b'data\r\nmore\r\n.') self.assertEqual(self.channel.socket.last, b'250 OK\r\n') self.assertEqual(self.server.messages, - [('peer', 'eggs@example', ['spam@example'], 'data\nmore')]) + [(('peer-address', 'peer-port'), + 'eggs@example', + ['spam@example'], + 'data\nmore')]) def test_data_limit_dialog_too_much_data(self): self.write_line(b'HELO example') @@ -553,5 +746,181 @@ class SMTPDChannelWithDataSizeLimitTest(unittest.TestCase): b'552 Error: Too much mail data\r\n') +class SMTPDChannelWithDecodeDataFalse(unittest.TestCase): + + def setUp(self): + smtpd.socket = asyncore.socket = mock_socket + self.old_debugstream = smtpd.DEBUGSTREAM + self.debug = smtpd.DEBUGSTREAM = io.StringIO() + self.server = DummyServer((support.HOST, 0), ('b', 0), + decode_data=False) + conn, addr = self.server.accept() + # Set decode_data to False + self.channel = smtpd.SMTPChannel(self.server, conn, addr, + decode_data=False) + + def tearDown(self): + asyncore.close_all() + asyncore.socket = smtpd.socket = socket + smtpd.DEBUGSTREAM = self.old_debugstream + + def write_line(self, line): + self.channel.socket.queue_recv(line) + self.channel.handle_read() + + def test_ascii_data(self): + self.write_line(b'HELO example') + self.write_line(b'MAIL From:eggs@example') + self.write_line(b'RCPT To:spam@example') + self.write_line(b'DATA') + self.write_line(b'plain ascii text') + self.write_line(b'.') + self.assertEqual(self.channel.received_data, b'plain ascii text') + + def test_utf8_data(self): + self.write_line(b'HELO example') + self.write_line(b'MAIL From:eggs@example') + self.write_line(b'RCPT To:spam@example') + self.write_line(b'DATA') + self.write_line(b'utf8 enriched text: \xc5\xbc\xc5\xba\xc4\x87') + self.write_line(b'and some plain ascii') + self.write_line(b'.') + self.assertEqual( + self.channel.received_data, + b'utf8 enriched text: \xc5\xbc\xc5\xba\xc4\x87\n' + b'and some plain ascii') + + +class SMTPDChannelWithDecodeDataTrue(unittest.TestCase): + + def setUp(self): + smtpd.socket = asyncore.socket = mock_socket + self.old_debugstream = smtpd.DEBUGSTREAM + self.debug = smtpd.DEBUGSTREAM = io.StringIO() + self.server = DummyServer((support.HOST, 0), ('b', 0), + decode_data=True) + conn, addr = self.server.accept() + # Set decode_data to True + self.channel = smtpd.SMTPChannel(self.server, conn, addr, + decode_data=True) + + def tearDown(self): + asyncore.close_all() + asyncore.socket = smtpd.socket = socket + smtpd.DEBUGSTREAM = self.old_debugstream + + def write_line(self, line): + self.channel.socket.queue_recv(line) + self.channel.handle_read() + + def test_ascii_data(self): + self.write_line(b'HELO example') + self.write_line(b'MAIL From:eggs@example') + self.write_line(b'RCPT To:spam@example') + self.write_line(b'DATA') + self.write_line(b'plain ascii text') + self.write_line(b'.') + self.assertEqual(self.channel.received_data, 'plain ascii text') + + def test_utf8_data(self): + self.write_line(b'HELO example') + self.write_line(b'MAIL From:eggs@example') + self.write_line(b'RCPT To:spam@example') + self.write_line(b'DATA') + self.write_line(b'utf8 enriched text: \xc5\xbc\xc5\xba\xc4\x87') + self.write_line(b'and some plain ascii') + self.write_line(b'.') + self.assertEqual( + self.channel.received_data, + 'utf8 enriched text: żźć\nand some plain ascii') + + +class SMTPDChannelTestWithEnableSMTPUTF8True(unittest.TestCase): + def setUp(self): + smtpd.socket = asyncore.socket = mock_socket + self.old_debugstream = smtpd.DEBUGSTREAM + self.debug = smtpd.DEBUGSTREAM = io.StringIO() + self.server = DummyServer((support.HOST, 0), ('b', 0), + enable_SMTPUTF8=True) + conn, addr = self.server.accept() + self.channel = smtpd.SMTPChannel(self.server, conn, addr, + enable_SMTPUTF8=True) + + def tearDown(self): + asyncore.close_all() + asyncore.socket = smtpd.socket = socket + smtpd.DEBUGSTREAM = self.old_debugstream + + def write_line(self, line): + self.channel.socket.queue_recv(line) + self.channel.handle_read() + + def test_MAIL_command_accepts_SMTPUTF8_when_announced(self): + self.write_line(b'EHLO example') + self.write_line( + 'MAIL from: <naïve@example.com> BODY=8BITMIME SMTPUTF8'.encode( + 'utf-8') + ) + self.assertEqual(self.channel.socket.last, b'250 OK\r\n') + + def test_process_smtputf8_message(self): + self.write_line(b'EHLO example') + for mail_parameters in [b'', b'BODY=8BITMIME SMTPUTF8']: + self.write_line(b'MAIL from: <a@example> ' + mail_parameters) + self.assertEqual(self.channel.socket.last[0:3], b'250') + self.write_line(b'rcpt to:<b@example.com>') + self.assertEqual(self.channel.socket.last[0:3], b'250') + self.write_line(b'data') + self.assertEqual(self.channel.socket.last[0:3], b'354') + self.write_line(b'c\r\n.') + if mail_parameters == b'': + self.assertEqual(self.channel.socket.last, b'250 OK\r\n') + else: + self.assertEqual(self.channel.socket.last, + b'250 SMTPUTF8 message okish\r\n') + + def test_utf8_data(self): + self.write_line(b'EHLO example') + self.write_line( + 'MAIL From: naïve@examplé BODY=8BITMIME SMTPUTF8'.encode('utf-8')) + self.assertEqual(self.channel.socket.last[0:3], b'250') + self.write_line('RCPT To:späm@examplé'.encode('utf-8')) + self.assertEqual(self.channel.socket.last[0:3], b'250') + self.write_line(b'DATA') + self.assertEqual(self.channel.socket.last[0:3], b'354') + self.write_line(b'utf8 enriched text: \xc5\xbc\xc5\xba\xc4\x87') + self.write_line(b'.') + self.assertEqual( + self.channel.received_data, + b'utf8 enriched text: \xc5\xbc\xc5\xba\xc4\x87') + + def test_MAIL_command_limit_extended_with_SIZE_and_SMTPUTF8(self): + self.write_line(b'ehlo example') + fill_len = (512 + 26 + 10) - len('mail from:<@example>') + self.write_line(b'MAIL from:<' + + b'a' * (fill_len + 1) + + b'@example>') + self.assertEqual(self.channel.socket.last, + b'500 Error: line too long\r\n') + self.write_line(b'MAIL from:<' + + b'a' * fill_len + + b'@example>') + self.assertEqual(self.channel.socket.last, b'250 OK\r\n') + + def test_multiple_emails_with_extended_command_length(self): + self.write_line(b'ehlo example') + fill_len = (512 + 26 + 10) - len('mail from:<@example>') + for char in [b'a', b'b', b'c']: + self.write_line(b'MAIL from:<' + char * fill_len + b'a@example>') + self.assertEqual(self.channel.socket.last[0:3], b'500') + self.write_line(b'MAIL from:<' + char * fill_len + b'@example>') + self.assertEqual(self.channel.socket.last[0:3], b'250') + self.write_line(b'rcpt to:<hans@example.com>') + self.assertEqual(self.channel.socket.last[0:3], b'250') + self.write_line(b'data') + self.assertEqual(self.channel.socket.last[0:3], b'354') + self.write_line(b'test\r\n.') + self.assertEqual(self.channel.socket.last[0:3], b'250') + if __name__ == "__main__": unittest.main() diff --git a/Lib/test/test_smtplib.py b/Lib/test/test_smtplib.py index 95a9dbe..5f12d28 100644 --- a/Lib/test/test_smtplib.py +++ b/Lib/test/test_smtplib.py @@ -10,6 +10,7 @@ import sys import time import select import errno +import base64 import unittest from test import support, mock_socket @@ -30,7 +31,7 @@ if sys.platform == 'darwin': def server(evt, buf, serv): - serv.listen(5) + serv.listen() evt.set() try: conn, addr = serv.accept() @@ -184,7 +185,8 @@ class DebuggingServerTests(unittest.TestCase): self.old_DEBUGSTREAM = smtpd.DEBUGSTREAM smtpd.DEBUGSTREAM = io.StringIO() # Pick a random unused port by passing 0 for the port number - self.serv = smtpd.DebuggingServer((HOST, 0), ('nowhere', -1)) + self.serv = smtpd.DebuggingServer((HOST, 0), ('nowhere', -1), + decode_data=True) # Keep a note of what port was assigned self.port = self.serv.socket.getsockname()[1] serv_args = (self.serv, self.serv_evt, self.client_evt) @@ -604,7 +606,8 @@ sim_auth_credentials = { 'cram-md5': ('TXIUQUBZB21LD2HLCMUUY29TIDG4OWQ0MJ' 'KWZGQ4ODNMNDA4NTGXMDRLZWMYZJDMODG1'), } -sim_auth_login_password = 'C29TZXBHC3N3B3JK' +sim_auth_login_user = 'TXIUQUBZB21LD2HLCMUUY29T' +sim_auth_plain = 'AE1YLKFAC29TZXDOZXJLLMNVBQBZB21LCGFZC3DVCMQ=' sim_lists = {'list-1':['Mr.A@somewhere.com','Mrs.C@somewhereesle.com'], 'list-2':['Ms.B@xn--fo-fka.com',], @@ -658,18 +661,16 @@ class SimSMTPChannel(smtpd.SMTPChannel): self.push('550 No access for you!') def smtp_AUTH(self, arg): - if arg.strip().lower()=='cram-md5': + mech = arg.strip().lower() + if mech=='cram-md5': self.push('334 {}'.format(sim_cram_md5_challenge)) - return - mech, auth = arg.split() - mech = mech.lower() - if mech not in sim_auth_credentials: + elif mech not in sim_auth_credentials: self.push('504 auth type unimplemented') return - if mech == 'plain' and auth==sim_auth_credentials['plain']: - self.push('235 plain auth ok') - elif mech=='login' and auth==sim_auth_credentials['login']: - self.push('334 Password:') + elif mech=='plain': + self.push('334 ') + elif mech=='login': + self.push('334 ') else: self.push('550 No access for you!') @@ -719,7 +720,8 @@ class SimSMTPServer(smtpd.SMTPServer): def handle_accepted(self, conn, addr): self._SMTPchannel = self.channel_class( - self._extra_features, self, conn, addr) + self._extra_features, self, conn, addr, + decode_data=self._decode_data) def process_message(self, peer, mailfrom, rcpttos, data): pass @@ -742,7 +744,7 @@ class SMTPSimTests(unittest.TestCase): self.serv_evt = threading.Event() self.client_evt = threading.Event() # Pick a random unused port by passing 0 for the port number - self.serv = SimSMTPServer((HOST, 0), ('nowhere', -1)) + self.serv = SimSMTPServer((HOST, 0), ('nowhere', -1), decode_data=True) # Keep a note of what port was assigned self.port = self.serv.socket.getsockname()[1] serv_args = (self.serv, self.serv_evt, self.client_evt) @@ -816,28 +818,28 @@ class SMTPSimTests(unittest.TestCase): self.assertEqual(smtp.expn(u), expected_unknown) smtp.quit() - def testAUTH_PLAIN(self): - self.serv.add_feature("AUTH PLAIN") - smtp = smtplib.SMTP(HOST, self.port, local_hostname='localhost', timeout=15) - - expected_auth_ok = (235, b'plain auth ok') - self.assertEqual(smtp.login(sim_auth[0], sim_auth[1]), expected_auth_ok) - smtp.close() - - # SimSMTPChannel doesn't fully support LOGIN or CRAM-MD5 auth because they - # require a synchronous read to obtain the credentials...so instead smtpd + # SimSMTPChannel doesn't fully support AUTH because it requires a + # synchronous read to obtain the credentials...so instead smtpd # sees the credential sent by smtplib's login method as an unknown command, # which results in smtplib raising an auth error. Fortunately the error # message contains the encoded credential, so we can partially check that it # was generated correctly (partially, because the 'word' is uppercased in # the error message). + def testAUTH_PLAIN(self): + self.serv.add_feature("AUTH PLAIN") + smtp = smtplib.SMTP(HOST, self.port, local_hostname='localhost', timeout=15) + try: smtp.login(sim_auth[0], sim_auth[1]) + except smtplib.SMTPAuthenticationError as err: + self.assertIn(sim_auth_plain, str(err)) + smtp.close() + def testAUTH_LOGIN(self): self.serv.add_feature("AUTH LOGIN") smtp = smtplib.SMTP(HOST, self.port, local_hostname='localhost', timeout=15) try: smtp.login(sim_auth[0], sim_auth[1]) except smtplib.SMTPAuthenticationError as err: - self.assertIn(sim_auth_login_password, str(err)) + self.assertIn(sim_auth_login_user, str(err)) smtp.close() def testAUTH_CRAM_MD5(self): @@ -855,7 +857,23 @@ class SMTPSimTests(unittest.TestCase): smtp = smtplib.SMTP(HOST, self.port, local_hostname='localhost', timeout=15) try: smtp.login(sim_auth[0], sim_auth[1]) except smtplib.SMTPAuthenticationError as err: - self.assertIn(sim_auth_login_password, str(err)) + self.assertIn(sim_auth_login_user, str(err)) + smtp.close() + + def test_auth_function(self): + smtp = smtplib.SMTP(HOST, self.port, + local_hostname='localhost', timeout=15) + self.serv.add_feature("AUTH CRAM-MD5") + smtp.user, smtp.password = sim_auth[0], sim_auth[1] + supported = {'CRAM-MD5': smtp.auth_cram_md5, + 'PLAIN': smtp.auth_plain, + 'LOGIN': smtp.auth_login, + } + for mechanism, method in supported.items(): + try: smtp.auth(mechanism, method) + except smtplib.SMTPAuthenticationError as err: + self.assertIn(sim_auth_credentials[mechanism.lower()].upper(), + str(err)) smtp.close() def test_quit_resets_greeting(self): diff --git a/Lib/test/test_sndhdr.py b/Lib/test/test_sndhdr.py index 5e0abe0..426417c 100644 --- a/Lib/test/test_sndhdr.py +++ b/Lib/test/test_sndhdr.py @@ -1,4 +1,5 @@ import sndhdr +import pickle import unittest from test.support import findfile @@ -18,6 +19,19 @@ class TestFormats(unittest.TestCase): what = sndhdr.what(filename) self.assertNotEqual(what, None, filename) self.assertSequenceEqual(what, expected) + self.assertEqual(what.filetype, expected[0]) + self.assertEqual(what.framerate, expected[1]) + self.assertEqual(what.nchannels, expected[2]) + self.assertEqual(what.nframes, expected[3]) + self.assertEqual(what.sampwidth, expected[4]) + + def test_pickleable(self): + filename = findfile('sndhdr.aifc', subdir="sndhdrdata") + what = sndhdr.what(filename) + for proto in range(pickle.HIGHEST_PROTOCOL + 1): + dump = pickle.dumps(what, proto) + self.assertEqual(pickle.loads(dump), what) + if __name__ == '__main__': unittest.main() diff --git a/Lib/test/test_socket.py b/Lib/test/test_socket.py index b412386..cf45b73 100644 --- a/Lib/test/test_socket.py +++ b/Lib/test/test_socket.py @@ -20,6 +20,8 @@ import signal import math import pickle import struct +import random +import string try: import multiprocessing except ImportError: @@ -76,7 +78,7 @@ class SocketTCPTest(unittest.TestCase): def setUp(self): self.serv = socket.socket(socket.AF_INET, socket.SOCK_STREAM) self.port = support.bind_port(self.serv) - self.serv.listen(1) + self.serv.listen() def tearDown(self): self.serv.close() @@ -445,7 +447,7 @@ class SocketListeningTestMixin(SocketTestBase): def setUp(self): super().setUp() - self.serv.listen(1) + self.serv.listen() class ThreadedSocketTestMixin(ThreadSafeCleanupTestCase, SocketTestBase, @@ -716,11 +718,11 @@ class GeneralModuleTests(unittest.TestCase): with self.assertRaises(TypeError) as cm: s.sendto('\u2620', sockname) self.assertEqual(str(cm.exception), - "'str' does not support the buffer interface") + "a bytes-like object is required, not 'str'") with self.assertRaises(TypeError) as cm: s.sendto(5j, sockname) self.assertEqual(str(cm.exception), - "'complex' does not support the buffer interface") + "a bytes-like object is required, not 'complex'") with self.assertRaises(TypeError) as cm: s.sendto(b'foo', None) self.assertIn('not NoneType',str(cm.exception)) @@ -728,11 +730,11 @@ class GeneralModuleTests(unittest.TestCase): with self.assertRaises(TypeError) as cm: s.sendto('\u2620', 0, sockname) self.assertEqual(str(cm.exception), - "'str' does not support the buffer interface") + "a bytes-like object is required, not 'str'") with self.assertRaises(TypeError) as cm: s.sendto(5j, 0, sockname) self.assertEqual(str(cm.exception), - "'complex' does not support the buffer interface") + "a bytes-like object is required, not 'complex'") with self.assertRaises(TypeError) as cm: s.sendto(b'foo', 0, None) self.assertIn('not NoneType', str(cm.exception)) @@ -1378,10 +1380,13 @@ class GeneralModuleTests(unittest.TestCase): def test_listen_backlog(self): for backlog in 0, -1: - srv = socket.socket(socket.AF_INET, socket.SOCK_STREAM) + with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as srv: + srv.bind((HOST, 0)) + srv.listen(backlog) + + with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as srv: srv.bind((HOST, 0)) - srv.listen(backlog) - srv.close() + srv.listen() @support.cpython_only def test_listen_backlog_overflow(self): @@ -3585,7 +3590,7 @@ class InterruptedTimeoutBase(unittest.TestCase): def setUp(self): super().setUp() orig_alrm_handler = signal.signal(signal.SIGALRM, - lambda signum, frame: None) + lambda signum, frame: 1 / 0) self.addCleanup(signal.signal, signal.SIGALRM, orig_alrm_handler) self.addCleanup(self.setAlarm, 0) @@ -3622,13 +3627,11 @@ class InterruptedRecvTimeoutTest(InterruptedTimeoutBase, UDPTestBase): self.serv.settimeout(self.timeout) def checkInterruptedRecv(self, func, *args, **kwargs): - # Check that func(*args, **kwargs) raises OSError with an + # Check that func(*args, **kwargs) raises # errno of EINTR when interrupted by a signal. self.setAlarm(self.alarm_time) - with self.assertRaises(OSError) as cm: + with self.assertRaises(ZeroDivisionError) as cm: func(*args, **kwargs) - self.assertNotIsInstance(cm.exception, socket.timeout) - self.assertEqual(cm.exception.errno, errno.EINTR) def testInterruptedRecvTimeout(self): self.checkInterruptedRecv(self.serv.recv, 1024) @@ -3684,12 +3687,10 @@ class InterruptedSendTimeoutTest(InterruptedTimeoutBase, # Check that func(*args, **kwargs), run in a loop, raises # OSError with an errno of EINTR when interrupted by a # signal. - with self.assertRaises(OSError) as cm: + with self.assertRaises(ZeroDivisionError) as cm: while True: self.setAlarm(self.alarm_time) func(*args, **kwargs) - self.assertNotIsInstance(cm.exception, socket.timeout) - self.assertEqual(cm.exception.errno, errno.EINTR) # Issue #12958: The following tests have problems on OS X prior to 10.7 @support.requires_mac_ver(10, 7) @@ -3731,8 +3732,6 @@ class TCPCloserTest(ThreadedTCPSocketTest): self.cli.connect((HOST, self.port)) time.sleep(1.0) -@unittest.skipUnless(hasattr(socket, 'socketpair'), - 'test needs socket.socketpair()') @unittest.skipUnless(thread, 'Threading required for this test.') class BasicSocketPairTest(SocketPairTest): @@ -3813,7 +3812,7 @@ class NonBlockingTCPTests(ThreadedTCPSocketTest): self.serv = socket.socket(socket.AF_INET, socket.SOCK_STREAM | socket.SOCK_NONBLOCK) self.port = support.bind_port(self.serv) - self.serv.listen(1) + self.serv.listen() # actual testing start = time.time() try: @@ -4059,117 +4058,6 @@ class FileObjectClassTestCase(SocketConnectedTest): pass -class FileObjectInterruptedTestCase(unittest.TestCase): - """Test that the file object correctly handles EINTR internally.""" - - class MockSocket(object): - def __init__(self, recv_funcs=()): - # A generator that returns callables that we'll call for each - # call to recv(). - self._recv_step = iter(recv_funcs) - - def recv_into(self, buffer): - data = next(self._recv_step)() - assert len(buffer) >= len(data) - buffer[:len(data)] = data - return len(data) - - def _decref_socketios(self): - pass - - def _textiowrap_for_test(self, buffering=-1): - raw = socket.SocketIO(self, "r") - if buffering < 0: - buffering = io.DEFAULT_BUFFER_SIZE - if buffering == 0: - return raw - buffer = io.BufferedReader(raw, buffering) - text = io.TextIOWrapper(buffer, None, None) - text.mode = "rb" - return text - - @staticmethod - def _raise_eintr(): - raise OSError(errno.EINTR, "interrupted") - - def _textiowrap_mock_socket(self, mock, buffering=-1): - raw = socket.SocketIO(mock, "r") - if buffering < 0: - buffering = io.DEFAULT_BUFFER_SIZE - if buffering == 0: - return raw - buffer = io.BufferedReader(raw, buffering) - text = io.TextIOWrapper(buffer, None, None) - text.mode = "rb" - return text - - def _test_readline(self, size=-1, buffering=-1): - mock_sock = self.MockSocket(recv_funcs=[ - lambda : b"This is the first line\nAnd the sec", - self._raise_eintr, - lambda : b"ond line is here\n", - lambda : b"", - lambda : b"", # XXX(gps): io library does an extra EOF read - ]) - fo = mock_sock._textiowrap_for_test(buffering=buffering) - self.assertEqual(fo.readline(size), "This is the first line\n") - self.assertEqual(fo.readline(size), "And the second line is here\n") - - def _test_read(self, size=-1, buffering=-1): - mock_sock = self.MockSocket(recv_funcs=[ - lambda : b"This is the first line\nAnd the sec", - self._raise_eintr, - lambda : b"ond line is here\n", - lambda : b"", - lambda : b"", # XXX(gps): io library does an extra EOF read - ]) - expecting = (b"This is the first line\n" - b"And the second line is here\n") - fo = mock_sock._textiowrap_for_test(buffering=buffering) - if buffering == 0: - data = b'' - else: - data = '' - expecting = expecting.decode('utf-8') - while len(data) != len(expecting): - part = fo.read(size) - if not part: - break - data += part - self.assertEqual(data, expecting) - - def test_default(self): - self._test_readline() - self._test_readline(size=100) - self._test_read() - self._test_read(size=100) - - def test_with_1k_buffer(self): - self._test_readline(buffering=1024) - self._test_readline(size=100, buffering=1024) - self._test_read(buffering=1024) - self._test_read(size=100, buffering=1024) - - def _test_readline_no_buffer(self, size=-1): - mock_sock = self.MockSocket(recv_funcs=[ - lambda : b"a", - lambda : b"\n", - lambda : b"B", - self._raise_eintr, - lambda : b"b", - lambda : b"", - ]) - fo = mock_sock._textiowrap_for_test(buffering=0) - self.assertEqual(fo.readline(size), b"a\n") - self.assertEqual(fo.readline(size), b"Bb") - - def test_no_buffer(self): - self._test_readline_no_buffer() - self._test_readline_no_buffer(size=4) - self._test_read(buffering=0) - self._test_read(size=100, buffering=0) - - class UnbufferedFileObjectClassTestCase(FileObjectClassTestCase): """Repeat the tests from FileObjectClassTestCase with bufsize==0. @@ -4588,7 +4476,7 @@ class TestLinuxAbstractNamespace(unittest.TestCase): address = b"\x00python-test-hello\x00\xff" with socket.socket(socket.AF_UNIX, socket.SOCK_STREAM) as s1: s1.bind(address) - s1.listen(1) + s1.listen() with socket.socket(socket.AF_UNIX, socket.SOCK_STREAM) as s2: s2.connect(s1.getsockname()) with s1.accept()[0] as s3: @@ -4820,7 +4708,7 @@ class TIPCThreadableTest(unittest.TestCase, ThreadableTest): srvaddr = (socket.TIPC_ADDR_NAMESEQ, TIPC_STYPE, TIPC_LOWER, TIPC_UPPER) self.srv.bind(srvaddr) - self.srv.listen(5) + self.srv.listen() self.serverExplicitReady() self.conn, self.connaddr = self.srv.accept() self.addCleanup(self.conn.close) @@ -5109,6 +4997,275 @@ class TestSocketSharing(SocketTCPTest): source.close() +@unittest.skipUnless(thread, 'Threading required for this test.') +class SendfileUsingSendTest(ThreadedTCPSocketTest): + """ + Test the send() implementation of socket.sendfile(). + """ + + FILESIZE = (10 * 1024 * 1024) # 10MB + BUFSIZE = 8192 + FILEDATA = b"" + TIMEOUT = 2 + + @classmethod + def setUpClass(cls): + def chunks(total, step): + assert total >= step + while total > step: + yield step + total -= step + if total: + yield total + + chunk = b"".join([random.choice(string.ascii_letters).encode() + for i in range(cls.BUFSIZE)]) + with open(support.TESTFN, 'wb') as f: + for csize in chunks(cls.FILESIZE, cls.BUFSIZE): + f.write(chunk) + with open(support.TESTFN, 'rb') as f: + cls.FILEDATA = f.read() + assert len(cls.FILEDATA) == cls.FILESIZE + + @classmethod + def tearDownClass(cls): + support.unlink(support.TESTFN) + + def accept_conn(self): + self.serv.settimeout(self.TIMEOUT) + conn, addr = self.serv.accept() + conn.settimeout(self.TIMEOUT) + self.addCleanup(conn.close) + return conn + + def recv_data(self, conn): + received = [] + while True: + chunk = conn.recv(self.BUFSIZE) + if not chunk: + break + received.append(chunk) + return b''.join(received) + + def meth_from_sock(self, sock): + # Depending on the mixin class being run return either send() + # or sendfile() method implementation. + return getattr(sock, "_sendfile_use_send") + + # regular file + + def _testRegularFile(self): + address = self.serv.getsockname() + file = open(support.TESTFN, 'rb') + with socket.create_connection(address) as sock, file as file: + meth = self.meth_from_sock(sock) + sent = meth(file) + self.assertEqual(sent, self.FILESIZE) + self.assertEqual(file.tell(), self.FILESIZE) + + def testRegularFile(self): + conn = self.accept_conn() + data = self.recv_data(conn) + self.assertEqual(len(data), self.FILESIZE) + self.assertEqual(data, self.FILEDATA) + + # non regular file + + def _testNonRegularFile(self): + address = self.serv.getsockname() + file = io.BytesIO(self.FILEDATA) + with socket.create_connection(address) as sock, file as file: + sent = sock.sendfile(file) + self.assertEqual(sent, self.FILESIZE) + self.assertEqual(file.tell(), self.FILESIZE) + self.assertRaises(socket._GiveupOnSendfile, + sock._sendfile_use_sendfile, file) + + def testNonRegularFile(self): + conn = self.accept_conn() + data = self.recv_data(conn) + self.assertEqual(len(data), self.FILESIZE) + self.assertEqual(data, self.FILEDATA) + + # empty file + + def _testEmptyFileSend(self): + address = self.serv.getsockname() + filename = support.TESTFN + "2" + with open(filename, 'wb'): + self.addCleanup(support.unlink, filename) + file = open(filename, 'rb') + with socket.create_connection(address) as sock, file as file: + meth = self.meth_from_sock(sock) + sent = meth(file) + self.assertEqual(sent, 0) + self.assertEqual(file.tell(), 0) + + def testEmptyFileSend(self): + conn = self.accept_conn() + data = self.recv_data(conn) + self.assertEqual(data, b"") + + # offset + + def _testOffset(self): + address = self.serv.getsockname() + file = open(support.TESTFN, 'rb') + with socket.create_connection(address) as sock, file as file: + meth = self.meth_from_sock(sock) + sent = meth(file, offset=5000) + self.assertEqual(sent, self.FILESIZE - 5000) + self.assertEqual(file.tell(), self.FILESIZE) + + def testOffset(self): + conn = self.accept_conn() + data = self.recv_data(conn) + self.assertEqual(len(data), self.FILESIZE - 5000) + self.assertEqual(data, self.FILEDATA[5000:]) + + # count + + def _testCount(self): + address = self.serv.getsockname() + file = open(support.TESTFN, 'rb') + with socket.create_connection(address, timeout=2) as sock, file as file: + count = 5000007 + meth = self.meth_from_sock(sock) + sent = meth(file, count=count) + self.assertEqual(sent, count) + self.assertEqual(file.tell(), count) + + def testCount(self): + count = 5000007 + conn = self.accept_conn() + data = self.recv_data(conn) + self.assertEqual(len(data), count) + self.assertEqual(data, self.FILEDATA[:count]) + + # count small + + def _testCountSmall(self): + address = self.serv.getsockname() + file = open(support.TESTFN, 'rb') + with socket.create_connection(address, timeout=2) as sock, file as file: + count = 1 + meth = self.meth_from_sock(sock) + sent = meth(file, count=count) + self.assertEqual(sent, count) + self.assertEqual(file.tell(), count) + + def testCountSmall(self): + count = 1 + conn = self.accept_conn() + data = self.recv_data(conn) + self.assertEqual(len(data), count) + self.assertEqual(data, self.FILEDATA[:count]) + + # count + offset + + def _testCountWithOffset(self): + address = self.serv.getsockname() + file = open(support.TESTFN, 'rb') + with socket.create_connection(address, timeout=2) as sock, file as file: + count = 100007 + meth = self.meth_from_sock(sock) + sent = meth(file, offset=2007, count=count) + self.assertEqual(sent, count) + self.assertEqual(file.tell(), count + 2007) + + def testCountWithOffset(self): + count = 100007 + conn = self.accept_conn() + data = self.recv_data(conn) + self.assertEqual(len(data), count) + self.assertEqual(data, self.FILEDATA[2007:count+2007]) + + # non blocking sockets are not supposed to work + + def _testNonBlocking(self): + address = self.serv.getsockname() + file = open(support.TESTFN, 'rb') + with socket.create_connection(address) as sock, file as file: + sock.setblocking(False) + meth = self.meth_from_sock(sock) + self.assertRaises(ValueError, meth, file) + self.assertRaises(ValueError, sock.sendfile, file) + + def testNonBlocking(self): + conn = self.accept_conn() + if conn.recv(8192): + self.fail('was not supposed to receive any data') + + # timeout (non-triggered) + + def _testWithTimeout(self): + address = self.serv.getsockname() + file = open(support.TESTFN, 'rb') + with socket.create_connection(address, timeout=2) as sock, file as file: + meth = self.meth_from_sock(sock) + sent = meth(file) + self.assertEqual(sent, self.FILESIZE) + + def testWithTimeout(self): + conn = self.accept_conn() + data = self.recv_data(conn) + self.assertEqual(len(data), self.FILESIZE) + self.assertEqual(data, self.FILEDATA) + + # timeout (triggered) + + def _testWithTimeoutTriggeredSend(self): + address = self.serv.getsockname() + file = open(support.TESTFN, 'rb') + with socket.create_connection(address, timeout=0.01) as sock, \ + file as file: + meth = self.meth_from_sock(sock) + self.assertRaises(socket.timeout, meth, file) + + def testWithTimeoutTriggeredSend(self): + conn = self.accept_conn() + conn.recv(88192) + + # errors + + def _test_errors(self): + pass + + def test_errors(self): + with open(support.TESTFN, 'rb') as file: + with socket.socket(type=socket.SOCK_DGRAM) as s: + meth = self.meth_from_sock(s) + self.assertRaisesRegex( + ValueError, "SOCK_STREAM", meth, file) + with open(support.TESTFN, 'rt') as file: + with socket.socket() as s: + meth = self.meth_from_sock(s) + self.assertRaisesRegex( + ValueError, "binary mode", meth, file) + with open(support.TESTFN, 'rb') as file: + with socket.socket() as s: + meth = self.meth_from_sock(s) + self.assertRaisesRegex(TypeError, "positive integer", + meth, file, count='2') + self.assertRaisesRegex(TypeError, "positive integer", + meth, file, count=0.1) + self.assertRaisesRegex(ValueError, "positive integer", + meth, file, count=0) + self.assertRaisesRegex(ValueError, "positive integer", + meth, file, count=-1) + + +@unittest.skipUnless(thread, 'Threading required for this test.') +@unittest.skipUnless(hasattr(os, "sendfile"), + 'os.sendfile() required for this test.') +class SendfileUsingSendfileTest(SendfileUsingSendTest): + """ + Test the sendfile() implementation of socket.sendfile(). + """ + def meth_from_sock(self, sock): + return getattr(sock, "_sendfile_use_sendfile") + + def test_main(): tests = [GeneralModuleTests, BasicTCPTest, TCPCloserTest, TCPTimeoutTest, TestExceptions, BufferIOTest, BasicTCPTest2, BasicUDPTest, UDPTimeoutTest ] @@ -5116,7 +5273,6 @@ def test_main(): tests.extend([ NonBlockingTCPTests, FileObjectClassTestCase, - FileObjectInterruptedTestCase, UnbufferedFileObjectClassTestCase, LineBufferedFileObjectClassTestCase, SmallBufferedFileObjectClassTestCase, @@ -5161,6 +5317,8 @@ def test_main(): InterruptedRecvTimeoutTest, InterruptedSendTimeoutTest, TestSocketSharing, + SendfileUsingSendTest, + SendfileUsingSendfileTest, ]) thread_info = support.threading_setup() diff --git a/Lib/test/test_socketserver.py b/Lib/test/test_socketserver.py index 924b9c4..31ab3b6 100644 --- a/Lib/test/test_socketserver.py +++ b/Lib/test/test_socketserver.py @@ -221,38 +221,6 @@ class SocketServerTest(unittest.TestCase): socketserver.DatagramRequestHandler, self.dgram_examine) - @contextlib.contextmanager - def mocked_select_module(self): - """Mocks the select.select() call to raise EINTR for first call""" - old_select = select.select - - class MockSelect: - def __init__(self): - self.called = 0 - - def __call__(self, *args): - self.called += 1 - if self.called == 1: - # raise the exception on first call - raise OSError(errno.EINTR, os.strerror(errno.EINTR)) - else: - # Return real select value for consecutive calls - return old_select(*args) - - select.select = MockSelect() - try: - yield select.select - finally: - select.select = old_select - - def test_InterruptServerSelectCall(self): - with self.mocked_select_module() as mock_select: - pid = self.run_server(socketserver.TCPServer, - socketserver.StreamRequestHandler, - self.stream_examine) - # Make sure select was called again: - self.assertGreater(mock_select.called, 1) - # Alas, on Linux (at least) recvfrom() doesn't return a meaningful # client address so this cannot work: diff --git a/Lib/test/test_ssl.py b/Lib/test/test_ssl.py index 779b622..ea619fd 100644 --- a/Lib/test/test_ssl.py +++ b/Lib/test/test_ssl.py @@ -86,6 +86,12 @@ def have_verify_flags(): # 0.9.8 or higher return ssl.OPENSSL_VERSION_INFO >= (0, 9, 8, 0, 15) +def utc_offset(): #NOTE: ignore issues like #1647654 + # local time = utc time + utc offset + if time.daylight and time.localtime().tm_isdst > 0: + return -time.altzone # seconds + return -time.timezone + def asn1time(cert_time): # Some versions of OpenSSL ignore seconds, see #18207 # 0.9.8.i @@ -134,6 +140,14 @@ class BasicSocketTests(unittest.TestCase): self.assertIn(ssl.HAS_SNI, {True, False}) self.assertIn(ssl.HAS_ECDH, {True, False}) + def test_str_for_enums(self): + # Make sure that the PROTOCOL_* constants have enum-like string + # reprs. + proto = ssl.PROTOCOL_SSLv23 + self.assertEqual(str(proto), '_SSLMethod.PROTOCOL_SSLv23') + ctx = ssl.SSLContext(proto) + self.assertIs(ctx.protocol, proto) + def test_random(self): v = ssl.RAND_status() if support.verbose: @@ -298,10 +312,10 @@ class BasicSocketTests(unittest.TestCase): # Version string as returned by {Open,Libre}SSL, the format might change if "LibreSSL" in s: self.assertTrue(s.startswith("LibreSSL {:d}.{:d}".format(major, minor)), - (s, t)) + (s, t, hex(n))) else: self.assertTrue(s.startswith("OpenSSL {:d}.{:d}.{:d}".format(major, minor, fix)), - (s, t)) + (s, t, hex(n))) @support.cpython_only def test_refcycle(self): @@ -369,6 +383,8 @@ class BasicSocketTests(unittest.TestCase): self.assertRaises(ssl.CertificateError, ssl.match_hostname, cert, hostname) + # -- Hostname matching -- + cert = {'subject': ((('commonName', 'example.com'),),)} ok(cert, 'example.com') ok(cert, 'ExAmple.cOm') @@ -454,6 +470,28 @@ class BasicSocketTests(unittest.TestCase): # Only commonName is considered fail(cert, 'California') + # -- IPv4 matching -- + cert = {'subject': ((('commonName', 'example.com'),),), + 'subjectAltName': (('DNS', 'example.com'), + ('IP Address', '10.11.12.13'), + ('IP Address', '14.15.16.17'))} + ok(cert, '10.11.12.13') + ok(cert, '14.15.16.17') + fail(cert, '14.15.16.18') + fail(cert, 'example.net') + + # -- IPv6 matching -- + cert = {'subject': ((('commonName', 'example.com'),),), + 'subjectAltName': (('DNS', 'example.com'), + ('IP Address', '2001:0:0:0:0:0:0:CAFE\n'), + ('IP Address', '2003:0:0:0:0:0:0:BABA\n'))} + ok(cert, '2001::cafe') + ok(cert, '2003::baba') + fail(cert, '2003::bebe') + fail(cert, 'example.net') + + # -- Miscellaneous -- + # Neither commonName nor subjectAltName cert = {'notAfter': 'Dec 18 23:59:59 2011 GMT', 'subject': ((('countryName', 'US'),), @@ -505,9 +543,14 @@ class BasicSocketTests(unittest.TestCase): def test_unknown_channel_binding(self): # should raise ValueError for unknown type s = socket.socket(socket.AF_INET) - with ssl.wrap_socket(s) as ss: + s.bind(('127.0.0.1', 0)) + s.listen() + c = socket.socket(socket.AF_INET) + c.connect(s.getsockname()) + with ssl.wrap_socket(c, do_handshake_on_connect=False) as ss: with self.assertRaises(ValueError): ss.get_channel_binding("unknown-type") + s.close() @unittest.skipUnless("tls-unique" in ssl.CHANNEL_BINDING_TYPES, "'tls-unique' channel binding not available") @@ -648,6 +691,71 @@ class BasicSocketTests(unittest.TestCase): ctx.wrap_socket(s) self.assertEqual(str(cx.exception), "only stream sockets are supported") + def cert_time_ok(self, timestring, timestamp): + self.assertEqual(ssl.cert_time_to_seconds(timestring), timestamp) + + def cert_time_fail(self, timestring): + with self.assertRaises(ValueError): + ssl.cert_time_to_seconds(timestring) + + @unittest.skipUnless(utc_offset(), + 'local time needs to be different from UTC') + def test_cert_time_to_seconds_timezone(self): + # Issue #19940: ssl.cert_time_to_seconds() returns wrong + # results if local timezone is not UTC + self.cert_time_ok("May 9 00:00:00 2007 GMT", 1178668800.0) + self.cert_time_ok("Jan 5 09:34:43 2018 GMT", 1515144883.0) + + def test_cert_time_to_seconds(self): + timestring = "Jan 5 09:34:43 2018 GMT" + ts = 1515144883.0 + self.cert_time_ok(timestring, ts) + # accept keyword parameter, assert its name + self.assertEqual(ssl.cert_time_to_seconds(cert_time=timestring), ts) + # accept both %e and %d (space or zero generated by strftime) + self.cert_time_ok("Jan 05 09:34:43 2018 GMT", ts) + # case-insensitive + self.cert_time_ok("JaN 5 09:34:43 2018 GmT", ts) + self.cert_time_fail("Jan 5 09:34 2018 GMT") # no seconds + self.cert_time_fail("Jan 5 09:34:43 2018") # no GMT + self.cert_time_fail("Jan 5 09:34:43 2018 UTC") # not GMT timezone + self.cert_time_fail("Jan 35 09:34:43 2018 GMT") # invalid day + self.cert_time_fail("Jon 5 09:34:43 2018 GMT") # invalid month + self.cert_time_fail("Jan 5 24:00:00 2018 GMT") # invalid hour + self.cert_time_fail("Jan 5 09:60:43 2018 GMT") # invalid minute + + newyear_ts = 1230768000.0 + # leap seconds + self.cert_time_ok("Dec 31 23:59:60 2008 GMT", newyear_ts) + # same timestamp + self.cert_time_ok("Jan 1 00:00:00 2009 GMT", newyear_ts) + + self.cert_time_ok("Jan 5 09:34:59 2018 GMT", 1515144899) + # allow 60th second (even if it is not a leap second) + self.cert_time_ok("Jan 5 09:34:60 2018 GMT", 1515144900) + # allow 2nd leap second for compatibility with time.strptime() + self.cert_time_ok("Jan 5 09:34:61 2018 GMT", 1515144901) + self.cert_time_fail("Jan 5 09:34:62 2018 GMT") # invalid seconds + + # no special treatement for the special value: + # 99991231235959Z (rfc 5280) + self.cert_time_ok("Dec 31 23:59:59 9999 GMT", 253402300799.0) + + @support.run_with_locale('LC_ALL', '') + def test_cert_time_to_seconds_locale(self): + # `cert_time_to_seconds()` should be locale independent + + def local_february_name(): + return time.strftime('%b', (1, 2, 3, 4, 5, 6, 0, 0, 0)) + + if local_february_name().lower() == 'feb': + self.skipTest("locale-specific month name needs to be " + "different from C locale") + + # locale-independent + self.cert_time_ok("Feb 9 00:00:00 2007 GMT", 1170979200.0) + self.cert_time_fail(local_february_name() + " 9 00:00:00 2007 GMT") + class ContextTests(unittest.TestCase): @@ -1157,7 +1265,7 @@ class SSLErrorTests(unittest.TestCase): ctx = ssl.SSLContext(ssl.PROTOCOL_TLSv1) with socket.socket() as s: s.bind(("127.0.0.1", 0)) - s.listen(5) + s.listen() c = socket.socket() c.connect(s.getsockname()) c.setblocking(False) @@ -1170,6 +1278,69 @@ class SSLErrorTests(unittest.TestCase): self.assertEqual(cm.exception.errno, ssl.SSL_ERROR_WANT_READ) +class MemoryBIOTests(unittest.TestCase): + + def test_read_write(self): + bio = ssl.MemoryBIO() + bio.write(b'foo') + self.assertEqual(bio.read(), b'foo') + self.assertEqual(bio.read(), b'') + bio.write(b'foo') + bio.write(b'bar') + self.assertEqual(bio.read(), b'foobar') + self.assertEqual(bio.read(), b'') + bio.write(b'baz') + self.assertEqual(bio.read(2), b'ba') + self.assertEqual(bio.read(1), b'z') + self.assertEqual(bio.read(1), b'') + + def test_eof(self): + bio = ssl.MemoryBIO() + self.assertFalse(bio.eof) + self.assertEqual(bio.read(), b'') + self.assertFalse(bio.eof) + bio.write(b'foo') + self.assertFalse(bio.eof) + bio.write_eof() + self.assertFalse(bio.eof) + self.assertEqual(bio.read(2), b'fo') + self.assertFalse(bio.eof) + self.assertEqual(bio.read(1), b'o') + self.assertTrue(bio.eof) + self.assertEqual(bio.read(), b'') + self.assertTrue(bio.eof) + + def test_pending(self): + bio = ssl.MemoryBIO() + self.assertEqual(bio.pending, 0) + bio.write(b'foo') + self.assertEqual(bio.pending, 3) + for i in range(3): + bio.read(1) + self.assertEqual(bio.pending, 3-i-1) + for i in range(3): + bio.write(b'x') + self.assertEqual(bio.pending, i+1) + bio.read() + self.assertEqual(bio.pending, 0) + + def test_buffer_types(self): + bio = ssl.MemoryBIO() + bio.write(b'foo') + self.assertEqual(bio.read(), b'foo') + bio.write(bytearray(b'bar')) + self.assertEqual(bio.read(), b'bar') + bio.write(memoryview(b'baz')) + self.assertEqual(bio.read(), b'baz') + + def test_error_types(self): + bio = ssl.MemoryBIO() + self.assertRaises(TypeError, bio.write, 'foo') + self.assertRaises(TypeError, bio.write, None) + self.assertRaises(TypeError, bio.write, True) + self.assertRaises(TypeError, bio.write, 1) + + class NetworkedTests(unittest.TestCase): def test_connect(self): @@ -1397,14 +1568,12 @@ class NetworkedTests(unittest.TestCase): def test_get_server_certificate(self): def _test_get_server_certificate(host, port, cert=None): with support.transient_internet(host): - pem = ssl.get_server_certificate((host, port), - ssl.PROTOCOL_SSLv23) + pem = ssl.get_server_certificate((host, port)) if not pem: self.fail("No server certificate on %s:%s!" % (host, port)) try: pem = ssl.get_server_certificate((host, port), - ssl.PROTOCOL_SSLv23, ca_certs=CERTFILE) except ssl.SSLError as x: #should fail @@ -1414,7 +1583,6 @@ class NetworkedTests(unittest.TestCase): self.fail("Got server certificate %s for %s:%s!" % (pem, host, port)) pem = ssl.get_server_certificate((host, port), - ssl.PROTOCOL_SSLv23, ca_certs=cert) if not pem: self.fail("No server certificate on %s:%s!" % (host, port)) @@ -1500,6 +1668,93 @@ class NetworkedTests(unittest.TestCase): self.assertIs(ss.context, ctx2) self.assertIs(ss._sslobj.context, ctx2) + +class NetworkedBIOTests(unittest.TestCase): + + def ssl_io_loop(self, sock, incoming, outgoing, func, *args, **kwargs): + # A simple IO loop. Call func(*args) depending on the error we get + # (WANT_READ or WANT_WRITE) move data between the socket and the BIOs. + timeout = kwargs.get('timeout', 10) + count = 0 + while True: + errno = None + count += 1 + try: + ret = func(*args) + except ssl.SSLError as e: + # Note that we get a spurious -1/SSL_ERROR_SYSCALL for + # non-blocking IO. The SSL_shutdown manpage hints at this. + # It *should* be safe to just ignore SYS_ERROR_SYSCALL because + # with a Memory BIO there's no syscalls (for IO at least). + if e.errno not in (ssl.SSL_ERROR_WANT_READ, + ssl.SSL_ERROR_WANT_WRITE, + ssl.SSL_ERROR_SYSCALL): + raise + errno = e.errno + # Get any data from the outgoing BIO irrespective of any error, and + # send it to the socket. + buf = outgoing.read() + sock.sendall(buf) + # If there's no error, we're done. For WANT_READ, we need to get + # data from the socket and put it in the incoming BIO. + if errno is None: + break + elif errno == ssl.SSL_ERROR_WANT_READ: + buf = sock.recv(32768) + if buf: + incoming.write(buf) + else: + incoming.write_eof() + if support.verbose: + sys.stdout.write("Needed %d calls to complete %s().\n" + % (count, func.__name__)) + return ret + + def test_handshake(self): + with support.transient_internet("svn.python.org"): + sock = socket.socket(socket.AF_INET) + sock.connect(("svn.python.org", 443)) + incoming = ssl.MemoryBIO() + outgoing = ssl.MemoryBIO() + ctx = ssl.SSLContext(ssl.PROTOCOL_SSLv23) + ctx.verify_mode = ssl.CERT_REQUIRED + ctx.load_verify_locations(SVN_PYTHON_ORG_ROOT_CERT) + ctx.check_hostname = True + sslobj = ctx.wrap_bio(incoming, outgoing, False, 'svn.python.org') + self.assertIs(sslobj._sslobj.owner, sslobj) + self.assertIsNone(sslobj.cipher()) + self.assertIsNone(sslobj.shared_ciphers()) + self.assertRaises(ValueError, sslobj.getpeercert) + if 'tls-unique' in ssl.CHANNEL_BINDING_TYPES: + self.assertIsNone(sslobj.get_channel_binding('tls-unique')) + self.ssl_io_loop(sock, incoming, outgoing, sslobj.do_handshake) + self.assertTrue(sslobj.cipher()) + self.assertIsNone(sslobj.shared_ciphers()) + self.assertTrue(sslobj.getpeercert()) + if 'tls-unique' in ssl.CHANNEL_BINDING_TYPES: + self.assertTrue(sslobj.get_channel_binding('tls-unique')) + self.ssl_io_loop(sock, incoming, outgoing, sslobj.unwrap) + self.assertRaises(ssl.SSLError, sslobj.write, b'foo') + sock.close() + + def test_read_write_data(self): + with support.transient_internet("svn.python.org"): + sock = socket.socket(socket.AF_INET) + sock.connect(("svn.python.org", 443)) + incoming = ssl.MemoryBIO() + outgoing = ssl.MemoryBIO() + ctx = ssl.SSLContext(ssl.PROTOCOL_SSLv23) + ctx.verify_mode = ssl.CERT_NONE + sslobj = ctx.wrap_bio(incoming, outgoing, False) + self.ssl_io_loop(sock, incoming, outgoing, sslobj.do_handshake) + req = b'GET / HTTP/1.0\r\n\r\n' + self.ssl_io_loop(sock, incoming, outgoing, sslobj.write, req) + buf = self.ssl_io_loop(sock, incoming, outgoing, sslobj.read, 1024) + self.assertEqual(buf[:5], b'HTTP/') + self.ssl_io_loop(sock, incoming, outgoing, sslobj.unwrap) + sock.close() + + try: import threading except ImportError: @@ -1531,7 +1786,8 @@ else: try: self.sslconn = self.server.context.wrap_socket( self.sock, server_side=True) - self.server.selected_protocols.append(self.sslconn.selected_npn_protocol()) + self.server.selected_npn_protocols.append(self.sslconn.selected_npn_protocol()) + self.server.selected_alpn_protocols.append(self.sslconn.selected_alpn_protocol()) except (ssl.SSLError, ConnectionResetError) as e: # We treat ConnectionResetError as though it were an # SSLError - OpenSSL on Ubuntu abruptly closes the @@ -1548,6 +1804,7 @@ else: self.close() return False else: + self.server.shared_ciphers.append(self.sslconn.shared_ciphers()) if self.server.context.verify_mode == ssl.CERT_REQUIRED: cert = self.sslconn.getpeercert() if support.verbose and self.server.chatty: @@ -1638,7 +1895,8 @@ else: def __init__(self, certificate=None, ssl_version=None, certreqs=None, cacerts=None, chatty=True, connectionchatty=False, starttls_server=False, - npn_protocols=None, ciphers=None, context=None): + npn_protocols=None, alpn_protocols=None, + ciphers=None, context=None): if context: self.context = context else: @@ -1653,6 +1911,8 @@ else: self.context.load_cert_chain(certificate) if npn_protocols: self.context.set_npn_protocols(npn_protocols) + if alpn_protocols: + self.context.set_alpn_protocols(alpn_protocols) if ciphers: self.context.set_ciphers(ciphers) self.chatty = chatty @@ -1662,7 +1922,9 @@ else: self.port = support.bind_port(self.sock) self.flag = None self.active = False - self.selected_protocols = [] + self.selected_npn_protocols = [] + self.selected_alpn_protocols = [] + self.shared_ciphers = [] self.conn_errors = [] threading.Thread.__init__(self) self.daemon = True @@ -1682,7 +1944,7 @@ else: def run(self): self.sock.settimeout(0.05) - self.sock.listen(5) + self.sock.listen() self.active = True if self.flag: # signal an event @@ -1888,14 +2150,25 @@ else: 'compression': s.compression(), 'cipher': s.cipher(), 'peercert': s.getpeercert(), - 'client_npn_protocol': s.selected_npn_protocol() + 'client_alpn_protocol': s.selected_alpn_protocol(), + 'client_npn_protocol': s.selected_npn_protocol(), + 'version': s.version(), }) s.close() - stats['server_npn_protocols'] = server.selected_protocols + stats['server_alpn_protocols'] = server.selected_alpn_protocols + stats['server_npn_protocols'] = server.selected_npn_protocols + stats['server_shared_ciphers'] = server.shared_ciphers return stats def try_protocol_combo(server_protocol, client_protocol, expect_success, certsreqs=None, server_options=0, client_options=0): + """ + Try to SSL-connect using *client_protocol* to *server_protocol*. + If *expect_success* is true, assert that the connection succeeds, + if it's false, assert that the connection fails. + Also, if *expect_success* is a string, assert that it is the protocol + version actually used by the connection. + """ if certsreqs is None: certsreqs = ssl.CERT_NONE certtype = { @@ -1925,8 +2198,8 @@ else: ctx.load_cert_chain(CERTFILE) ctx.load_verify_locations(CERTFILE) try: - server_params_test(client_context, server_context, - chatty=False, connectionchatty=False) + stats = server_params_test(client_context, server_context, + chatty=False, connectionchatty=False) # Protocol mismatch can result in either an SSLError, or a # "Connection reset by peer" error. except ssl.SSLError: @@ -1941,6 +2214,10 @@ else: "Client protocol %s succeeded with server protocol %s!" % (ssl.get_protocol_name(client_protocol), ssl.get_protocol_name(server_protocol))) + elif (expect_success is not True + and expect_success != stats['version']): + raise AssertionError("version mismatch: expected %r, got %r" + % (expect_success, stats['version'])) class ThreadedTests(unittest.TestCase): @@ -2108,7 +2385,7 @@ else: # and sets Event `listener_gone` to let the main thread know # the socket is gone. def listener(): - s.listen(5) + s.listen() listener_ready.set() newsock, addr = s.accept() newsock.close() @@ -2173,19 +2450,19 @@ else: " SSL2 client to SSL23 server test unexpectedly failed:\n %s\n" % str(x)) if hasattr(ssl, 'PROTOCOL_SSLv3'): - try_protocol_combo(ssl.PROTOCOL_SSLv23, ssl.PROTOCOL_SSLv3, True) + try_protocol_combo(ssl.PROTOCOL_SSLv23, ssl.PROTOCOL_SSLv3, 'SSLv3') try_protocol_combo(ssl.PROTOCOL_SSLv23, ssl.PROTOCOL_SSLv23, True) - try_protocol_combo(ssl.PROTOCOL_SSLv23, ssl.PROTOCOL_TLSv1, True) + try_protocol_combo(ssl.PROTOCOL_SSLv23, ssl.PROTOCOL_TLSv1, 'TLSv1') if hasattr(ssl, 'PROTOCOL_SSLv3'): - try_protocol_combo(ssl.PROTOCOL_SSLv23, ssl.PROTOCOL_SSLv3, True, ssl.CERT_OPTIONAL) + try_protocol_combo(ssl.PROTOCOL_SSLv23, ssl.PROTOCOL_SSLv3, 'SSLv3', ssl.CERT_OPTIONAL) try_protocol_combo(ssl.PROTOCOL_SSLv23, ssl.PROTOCOL_SSLv23, True, ssl.CERT_OPTIONAL) - try_protocol_combo(ssl.PROTOCOL_SSLv23, ssl.PROTOCOL_TLSv1, True, ssl.CERT_OPTIONAL) + try_protocol_combo(ssl.PROTOCOL_SSLv23, ssl.PROTOCOL_TLSv1, 'TLSv1', ssl.CERT_OPTIONAL) if hasattr(ssl, 'PROTOCOL_SSLv3'): - try_protocol_combo(ssl.PROTOCOL_SSLv23, ssl.PROTOCOL_SSLv3, True, ssl.CERT_REQUIRED) + try_protocol_combo(ssl.PROTOCOL_SSLv23, ssl.PROTOCOL_SSLv3, 'SSLv3', ssl.CERT_REQUIRED) try_protocol_combo(ssl.PROTOCOL_SSLv23, ssl.PROTOCOL_SSLv23, True, ssl.CERT_REQUIRED) - try_protocol_combo(ssl.PROTOCOL_SSLv23, ssl.PROTOCOL_TLSv1, True, ssl.CERT_REQUIRED) + try_protocol_combo(ssl.PROTOCOL_SSLv23, ssl.PROTOCOL_TLSv1, 'TLSv1', ssl.CERT_REQUIRED) # Server with specific SSL options if hasattr(ssl, 'PROTOCOL_SSLv3'): @@ -2205,9 +2482,9 @@ else: """Connecting to an SSLv3 server with various client options""" if support.verbose: sys.stdout.write("\n") - try_protocol_combo(ssl.PROTOCOL_SSLv3, ssl.PROTOCOL_SSLv3, True) - try_protocol_combo(ssl.PROTOCOL_SSLv3, ssl.PROTOCOL_SSLv3, True, ssl.CERT_OPTIONAL) - try_protocol_combo(ssl.PROTOCOL_SSLv3, ssl.PROTOCOL_SSLv3, True, ssl.CERT_REQUIRED) + try_protocol_combo(ssl.PROTOCOL_SSLv3, ssl.PROTOCOL_SSLv3, 'SSLv3') + try_protocol_combo(ssl.PROTOCOL_SSLv3, ssl.PROTOCOL_SSLv3, 'SSLv3', ssl.CERT_OPTIONAL) + try_protocol_combo(ssl.PROTOCOL_SSLv3, ssl.PROTOCOL_SSLv3, 'SSLv3', ssl.CERT_REQUIRED) if hasattr(ssl, 'PROTOCOL_SSLv2'): try_protocol_combo(ssl.PROTOCOL_SSLv3, ssl.PROTOCOL_SSLv2, False) try_protocol_combo(ssl.PROTOCOL_SSLv3, ssl.PROTOCOL_SSLv23, False, @@ -2215,7 +2492,7 @@ else: try_protocol_combo(ssl.PROTOCOL_SSLv3, ssl.PROTOCOL_TLSv1, False) if no_sslv2_implies_sslv3_hello(): # No SSLv2 => client will use an SSLv3 hello on recent OpenSSLs - try_protocol_combo(ssl.PROTOCOL_SSLv3, ssl.PROTOCOL_SSLv23, True, + try_protocol_combo(ssl.PROTOCOL_SSLv3, ssl.PROTOCOL_SSLv23, 'SSLv3', client_options=ssl.OP_NO_SSLv2) @skip_if_broken_ubuntu_ssl @@ -2223,9 +2500,9 @@ else: """Connecting to a TLSv1 server with various client options""" if support.verbose: sys.stdout.write("\n") - try_protocol_combo(ssl.PROTOCOL_TLSv1, ssl.PROTOCOL_TLSv1, True) - try_protocol_combo(ssl.PROTOCOL_TLSv1, ssl.PROTOCOL_TLSv1, True, ssl.CERT_OPTIONAL) - try_protocol_combo(ssl.PROTOCOL_TLSv1, ssl.PROTOCOL_TLSv1, True, ssl.CERT_REQUIRED) + try_protocol_combo(ssl.PROTOCOL_TLSv1, ssl.PROTOCOL_TLSv1, 'TLSv1') + try_protocol_combo(ssl.PROTOCOL_TLSv1, ssl.PROTOCOL_TLSv1, 'TLSv1', ssl.CERT_OPTIONAL) + try_protocol_combo(ssl.PROTOCOL_TLSv1, ssl.PROTOCOL_TLSv1, 'TLSv1', ssl.CERT_REQUIRED) if hasattr(ssl, 'PROTOCOL_SSLv2'): try_protocol_combo(ssl.PROTOCOL_TLSv1, ssl.PROTOCOL_SSLv2, False) if hasattr(ssl, 'PROTOCOL_SSLv3'): @@ -2241,7 +2518,7 @@ else: Testing against older TLS versions.""" if support.verbose: sys.stdout.write("\n") - try_protocol_combo(ssl.PROTOCOL_TLSv1_1, ssl.PROTOCOL_TLSv1_1, True) + try_protocol_combo(ssl.PROTOCOL_TLSv1_1, ssl.PROTOCOL_TLSv1_1, 'TLSv1.1') if hasattr(ssl, 'PROTOCOL_SSLv2'): try_protocol_combo(ssl.PROTOCOL_TLSv1_1, ssl.PROTOCOL_SSLv2, False) if hasattr(ssl, 'PROTOCOL_SSLv3'): @@ -2249,7 +2526,7 @@ else: try_protocol_combo(ssl.PROTOCOL_TLSv1_1, ssl.PROTOCOL_SSLv23, False, client_options=ssl.OP_NO_TLSv1_1) - try_protocol_combo(ssl.PROTOCOL_SSLv23, ssl.PROTOCOL_TLSv1_1, True) + try_protocol_combo(ssl.PROTOCOL_SSLv23, ssl.PROTOCOL_TLSv1_1, 'TLSv1.1') try_protocol_combo(ssl.PROTOCOL_TLSv1_1, ssl.PROTOCOL_TLSv1, False) try_protocol_combo(ssl.PROTOCOL_TLSv1, ssl.PROTOCOL_TLSv1_1, False) @@ -2262,7 +2539,7 @@ else: Testing against older TLS versions.""" if support.verbose: sys.stdout.write("\n") - try_protocol_combo(ssl.PROTOCOL_TLSv1_2, ssl.PROTOCOL_TLSv1_2, True, + try_protocol_combo(ssl.PROTOCOL_TLSv1_2, ssl.PROTOCOL_TLSv1_2, 'TLSv1.2', server_options=ssl.OP_NO_SSLv3|ssl.OP_NO_SSLv2, client_options=ssl.OP_NO_SSLv3|ssl.OP_NO_SSLv2,) if hasattr(ssl, 'PROTOCOL_SSLv2'): @@ -2272,7 +2549,7 @@ else: try_protocol_combo(ssl.PROTOCOL_TLSv1_2, ssl.PROTOCOL_SSLv23, False, client_options=ssl.OP_NO_TLSv1_2) - try_protocol_combo(ssl.PROTOCOL_SSLv23, ssl.PROTOCOL_TLSv1_2, True) + try_protocol_combo(ssl.PROTOCOL_SSLv23, ssl.PROTOCOL_TLSv1_2, 'TLSv1.2') try_protocol_combo(ssl.PROTOCOL_TLSv1_2, ssl.PROTOCOL_TLSv1, False) try_protocol_combo(ssl.PROTOCOL_TLSv1, ssl.PROTOCOL_TLSv1_2, False) try_protocol_combo(ssl.PROTOCOL_TLSv1_2, ssl.PROTOCOL_TLSv1_1, False) @@ -2508,6 +2785,36 @@ else: s.write(b"over\n") s.close() + def test_nonblocking_send(self): + server = ThreadedEchoServer(CERTFILE, + certreqs=ssl.CERT_NONE, + ssl_version=ssl.PROTOCOL_TLSv1, + cacerts=CERTFILE, + chatty=True, + connectionchatty=False) + with server: + s = ssl.wrap_socket(socket.socket(), + server_side=False, + certfile=CERTFILE, + ca_certs=CERTFILE, + cert_reqs=ssl.CERT_NONE, + ssl_version=ssl.PROTOCOL_TLSv1) + s.connect((HOST, server.port)) + s.setblocking(False) + + # If we keep sending data, at some point the buffers + # will be full and the call will block + buf = bytearray(8192) + def fill_buffer(): + while True: + s.send(buf) + self.assertRaises((ssl.SSLWantWriteError, + ssl.SSLWantReadError), fill_buffer) + + # Now read all the output and discard it + s.setblocking(True) + s.close() + def test_handshake_timeout(self): # Issue #5103: SSL handshake must respect the socket timeout server = socket.socket(socket.AF_INET) @@ -2517,7 +2824,7 @@ else: finish = False def serve(): - server.listen(5) + server.listen() started.set() conns = [] while not finish: @@ -2574,7 +2881,7 @@ else: peer = None def serve(): nonlocal remote, peer - server.listen(5) + server.listen() # Block on the accept and wait on the connection to close. evt.set() remote, peer = server.accept() @@ -2624,6 +2931,21 @@ else: s.connect((HOST, server.port)) self.assertIn("no shared cipher", str(server.conn_errors[0])) + def test_version_basic(self): + """ + Basic tests for SSLSocket.version(). + More tests are done in the test_protocol_*() methods. + """ + context = ssl.SSLContext(ssl.PROTOCOL_TLSv1) + with ThreadedEchoServer(CERTFILE, + ssl_version=ssl.PROTOCOL_TLSv1, + chatty=False) as server: + with context.wrap_socket(socket.socket()) as s: + self.assertIs(s.version(), None) + s.connect((HOST, server.port)) + self.assertEqual(s.version(), "TLSv1") + self.assertIs(s.version(), None) + @unittest.skipUnless(ssl.HAS_ECDH, "test requires ECDH-enabled OpenSSL") def test_default_ecdh_curve(self): # Issue #21015: elliptic curve-based Diffie Hellman key exchange @@ -2733,6 +3055,55 @@ else: if "ADH" not in parts and "EDH" not in parts and "DHE" not in parts: self.fail("Non-DH cipher: " + cipher[0]) + def test_selected_alpn_protocol(self): + # selected_alpn_protocol() is None unless ALPN is used. + context = ssl.SSLContext(ssl.PROTOCOL_TLSv1) + context.load_cert_chain(CERTFILE) + stats = server_params_test(context, context, + chatty=True, connectionchatty=True) + self.assertIs(stats['client_alpn_protocol'], None) + + @unittest.skipUnless(ssl.HAS_ALPN, "ALPN support required") + def test_selected_alpn_protocol_if_server_uses_alpn(self): + # selected_alpn_protocol() is None unless ALPN is used by the client. + client_context = ssl.SSLContext(ssl.PROTOCOL_TLSv1) + client_context.load_verify_locations(CERTFILE) + server_context = ssl.SSLContext(ssl.PROTOCOL_TLSv1) + server_context.load_cert_chain(CERTFILE) + server_context.set_alpn_protocols(['foo', 'bar']) + stats = server_params_test(client_context, server_context, + chatty=True, connectionchatty=True) + self.assertIs(stats['client_alpn_protocol'], None) + + @unittest.skipUnless(ssl.HAS_ALPN, "ALPN support needed for this test") + def test_alpn_protocols(self): + server_protocols = ['foo', 'bar', 'milkshake'] + protocol_tests = [ + (['foo', 'bar'], 'foo'), + (['bar', 'foo'], 'foo'), + (['milkshake'], 'milkshake'), + (['http/3.0', 'http/4.0'], None) + ] + for client_protocols, expected in protocol_tests: + server_context = ssl.SSLContext(ssl.PROTOCOL_TLSv1) + server_context.load_cert_chain(CERTFILE) + server_context.set_alpn_protocols(server_protocols) + client_context = ssl.SSLContext(ssl.PROTOCOL_TLSv1) + client_context.load_cert_chain(CERTFILE) + client_context.set_alpn_protocols(client_protocols) + stats = server_params_test(client_context, server_context, + chatty=True, connectionchatty=True) + + msg = "failed trying %s (s) and %s (c).\n" \ + "was expecting %s, but got %%s from the %%s" \ + % (str(server_protocols), str(client_protocols), + str(expected)) + client_result = stats['client_alpn_protocol'] + self.assertEqual(client_result, expected, msg % (client_result, "client")) + server_result = stats['server_alpn_protocols'][-1] \ + if len(stats['server_alpn_protocols']) else 'nothing' + self.assertEqual(server_result, expected, msg % (server_result, "server")) + def test_selected_npn_protocol(self): # selected_npn_protocol() is None unless NPN is used context = ssl.SSLContext(ssl.PROTOCOL_TLSv1) @@ -2873,6 +3244,20 @@ else: self.assertEqual(cm.exception.reason, 'TLSV1_ALERT_INTERNAL_ERROR') self.assertIn("TypeError", stderr.getvalue()) + def test_shared_ciphers(self): + server_context = ssl.SSLContext(ssl.PROTOCOL_TLSv1) + server_context.load_cert_chain(SIGNED_CERTFILE) + client_context = ssl.SSLContext(ssl.PROTOCOL_TLSv1) + client_context.verify_mode = ssl.CERT_REQUIRED + client_context.load_verify_locations(SIGNING_CA) + client_context.set_ciphers("RC4") + server_context.set_ciphers("AES:RC4") + stats = server_params_test(client_context, server_context) + ciphers = stats['server_shared_ciphers'][0] + self.assertGreater(len(ciphers), 0) + for name, tls_version, bits in ciphers: + self.assertIn("RC4", name.split("-")) + def test_read_write_after_close_raises_valuerror(self): context = ssl.SSLContext(ssl.PROTOCOL_SSLv23) context.verify_mode = ssl.CERT_REQUIRED @@ -2888,6 +3273,23 @@ else: self.assertRaises(ValueError, s.read, 1024) self.assertRaises(ValueError, s.write, b'hello') + def test_sendfile(self): + TEST_DATA = b"x" * 512 + with open(support.TESTFN, 'wb') as f: + f.write(TEST_DATA) + self.addCleanup(support.unlink, support.TESTFN) + context = ssl.SSLContext(ssl.PROTOCOL_SSLv23) + context.verify_mode = ssl.CERT_REQUIRED + context.load_verify_locations(CERTFILE) + context.load_cert_chain(CERTFILE) + server = ThreadedEchoServer(context=context, chatty=False) + with server: + with context.wrap_socket(socket.socket()) as s: + s.connect((HOST, server.port)) + with open(support.TESTFN, 'rb') as file: + s.sendfile(file) + self.assertEqual(s.recv(1024), TEST_DATA) + def test_main(verbose=False): if support.verbose: @@ -2921,10 +3323,11 @@ def test_main(verbose=False): if not os.path.exists(filename): raise support.TestFailed("Can't read certificate file %r" % filename) - tests = [ContextTests, BasicSocketTests, SSLErrorTests] + tests = [ContextTests, BasicSocketTests, SSLErrorTests, MemoryBIOTests] if support.is_resource_enabled('network'): tests.append(NetworkedTests) + tests.append(NetworkedBIOTests) if _have_threads: thread_info = support.threading_setup() diff --git a/Lib/test/test_stat.py b/Lib/test/test_stat.py index af6ced4..f1a5938 100644 --- a/Lib/test/test_stat.py +++ b/Lib/test/test_stat.py @@ -1,5 +1,6 @@ import unittest import os +import sys from test.support import TESTFN, import_fresh_module c_stat = import_fresh_module('stat', fresh=['_stat']) @@ -52,6 +53,26 @@ class TestFilemode: 'S_IWOTH': 0o002, 'S_IXOTH': 0o001} + # defined by the Windows API documentation + file_attributes = { + 'FILE_ATTRIBUTE_ARCHIVE': 32, + 'FILE_ATTRIBUTE_COMPRESSED': 2048, + 'FILE_ATTRIBUTE_DEVICE': 64, + 'FILE_ATTRIBUTE_DIRECTORY': 16, + 'FILE_ATTRIBUTE_ENCRYPTED': 16384, + 'FILE_ATTRIBUTE_HIDDEN': 2, + 'FILE_ATTRIBUTE_INTEGRITY_STREAM': 32768, + 'FILE_ATTRIBUTE_NORMAL': 128, + 'FILE_ATTRIBUTE_NOT_CONTENT_INDEXED': 8192, + 'FILE_ATTRIBUTE_NO_SCRUB_DATA': 131072, + 'FILE_ATTRIBUTE_OFFLINE': 4096, + 'FILE_ATTRIBUTE_READONLY': 1, + 'FILE_ATTRIBUTE_REPARSE_POINT': 1024, + 'FILE_ATTRIBUTE_SPARSE_FILE': 512, + 'FILE_ATTRIBUTE_SYSTEM': 4, + 'FILE_ATTRIBUTE_TEMPORARY': 256, + 'FILE_ATTRIBUTE_VIRTUAL': 65536} + def setUp(self): try: os.remove(TESTFN) @@ -185,6 +206,14 @@ class TestFilemode: self.assertTrue(callable(func)) self.assertEqual(func(0), 0) + @unittest.skipUnless(sys.platform == "win32", + "FILE_ATTRIBUTE_* constants are Win32 specific") + def test_file_attribute_constants(self): + for key, value in sorted(self.file_attributes.items()): + self.assertTrue(hasattr(self.statmod, key), key) + modvalue = getattr(self.statmod, key) + self.assertEqual(value, modvalue, key) + class TestFilemodeCStat(TestFilemode, unittest.TestCase): statmod = c_stat diff --git a/Lib/test/test_subprocess.py b/Lib/test/test_subprocess.py index aaec322..cbdbb17 100644 --- a/Lib/test/test_subprocess.py +++ b/Lib/test/test_subprocess.py @@ -2421,25 +2421,6 @@ class ProcessTestCaseNoPoll(ProcessTestCase): ProcessTestCase.tearDown(self) -class HelperFunctionTests(unittest.TestCase): - @unittest.skipIf(mswindows, "errno and EINTR make no sense on windows") - def test_eintr_retry_call(self): - record_calls = [] - def fake_os_func(*args): - record_calls.append(args) - if len(record_calls) == 2: - raise OSError(errno.EINTR, "fake interrupted system call") - return tuple(reversed(args)) - - self.assertEqual((999, 256), - subprocess._eintr_retry_call(fake_os_func, 256, 999)) - self.assertEqual([(256, 999)], record_calls) - # This time there will be an EINTR so it will loop once. - self.assertEqual((666,), - subprocess._eintr_retry_call(fake_os_func, 666)) - self.assertEqual([(256, 999), (666,), (666,)], record_calls) - - @unittest.skipUnless(mswindows, "Windows-specific tests") class CommandsWithSpaces (BaseTestCase): @@ -2546,7 +2527,6 @@ def test_main(): Win32ProcessTestCase, CommandTests, ProcessTestCaseNoPoll, - HelperFunctionTests, CommandsWithSpaces, ContextManagerTests, ) diff --git a/Lib/test/test_support.py b/Lib/test/test_support.py index 03ce9d1..a02d2f4 100644 --- a/Lib/test/test_support.py +++ b/Lib/test/test_support.py @@ -85,7 +85,7 @@ class TestSupport(unittest.TestCase): def test_bind_port(self): s = socket.socket() support.bind_port(s) - s.listen(1) + s.listen() s.close() # Tests for temp_dir() diff --git a/Lib/test/test_sys.py b/Lib/test/test_sys.py index 2f66eb7..ed6b47d 100644 --- a/Lib/test/test_sys.py +++ b/Lib/test/test_sys.py @@ -636,6 +636,53 @@ class SysModuleTest(unittest.TestCase): expected = None self.check_fsencoding(fs_encoding, expected) + def c_locale_get_error_handler(self, isolated=False, encoding=None): + # Force the POSIX locale + env = os.environ.copy() + env["LC_ALL"] = "C" + code = '\n'.join(( + 'import sys', + 'def dump(name):', + ' std = getattr(sys, name)', + ' print("%s: %s" % (name, std.errors))', + 'dump("stdin")', + 'dump("stdout")', + 'dump("stderr")', + )) + args = [sys.executable, "-c", code] + if isolated: + args.append("-I") + elif encoding: + env['PYTHONIOENCODING'] = encoding + p = subprocess.Popen(args, + stdout=subprocess.PIPE, + stderr=subprocess.STDOUT, + env=env, + universal_newlines=True) + stdout, stderr = p.communicate() + return stdout + + def test_c_locale_surrogateescape(self): + out = self.c_locale_get_error_handler(isolated=True) + self.assertEqual(out, + 'stdin: surrogateescape\n' + 'stdout: surrogateescape\n' + 'stderr: backslashreplace\n') + + # replace the default error handler + out = self.c_locale_get_error_handler(encoding=':strict') + self.assertEqual(out, + 'stdin: strict\n' + 'stdout: strict\n' + 'stderr: backslashreplace\n') + + # force the encoding + out = self.c_locale_get_error_handler(encoding='iso8859-1') + self.assertEqual(out, + 'stdin: surrogateescape\n' + 'stdout: surrogateescape\n' + 'stderr: backslashreplace\n') + def test_implementation(self): # This test applies to all implementations equally. @@ -698,6 +745,27 @@ class SysModuleTest(unittest.TestCase): c = sys.getallocatedblocks() self.assertIn(c, range(b - 50, b + 50)) + def test_is_finalizing(self): + self.assertIs(sys.is_finalizing(), False) + # Don't use the atexit module because _Py_Finalizing is only set + # after calling atexit callbacks + code = """if 1: + import sys + + class AtExit: + is_finalizing = sys.is_finalizing + print = print + + def __del__(self): + self.print(self.is_finalizing(), flush=True) + + # Keep a reference in the __main__ module namespace, so the + # AtExit destructor will be called at Python exit + ref = AtExit() + """ + rc, stdout, stderr = assert_python_ok('-c', code) + self.assertEqual(stdout.rstrip(), b'True') + @test.support.cpython_only class SizeofTest(unittest.TestCase): @@ -770,7 +838,7 @@ class SizeofTest(unittest.TestCase): # buffer # XXX # builtin_function_or_method - check(len, size('3P')) # XXX check layout + check(len, size('4P')) # XXX check layout # bytearray samples = [b'', b'u'*100000] for sample in samples: @@ -871,7 +939,7 @@ class SizeofTest(unittest.TestCase): check(bar, size('PP')) # generator def get_gen(): yield 1 - check(get_gen(), size('Pb2P')) + check(get_gen(), size('Pb2PPP')) # iterator check(iter('abc'), size('lP')) # callable-iterator @@ -898,7 +966,7 @@ class SizeofTest(unittest.TestCase): check(int(PyLong_BASE**2-1), vsize('') + 2*self.longdigit) check(int(PyLong_BASE**2), vsize('') + 3*self.longdigit) # memoryview - check(memoryview(b''), size('Pnin 2P2n2i5P 3cPn')) + check(memoryview(b''), size('Pnin 2P2n2i5P Pn')) # module check(unittest, size('PnPPP')) # None @@ -927,7 +995,7 @@ class SizeofTest(unittest.TestCase): # frozenset PySet_MINSIZE = 8 samples = [[], range(10), range(50)] - s = size('3n2P' + PySet_MINSIZE*'nP' + 'nP') + s = size('3nP' + PySet_MINSIZE*'nP' + '2nP') for sample in samples: minused = len(sample) if minused == 0: tmp = 1 @@ -958,7 +1026,7 @@ class SizeofTest(unittest.TestCase): check(int, s) # (PyTypeObject + PyNumberMethods + PyMappingMethods + # PySequenceMethods + PyBufferProcs + 4P) - s = vsize('P2n15Pl4Pn9Pn11PIP') + struct.calcsize('34P 3P 10P 2P 4P') + s = vsize('P2n17Pl4Pn9Pn11PIP') + struct.calcsize('34P 3P 10P 2P 4P') # Separate block for PyDictKeysObject with 4 entries s += struct.calcsize("2nPn") + 4*struct.calcsize("n2P") # class diff --git a/Lib/test/test_sys_setprofile.py b/Lib/test/test_sys_setprofile.py index 9816e3e..e59320b 100644 --- a/Lib/test/test_sys_setprofile.py +++ b/Lib/test/test_sys_setprofile.py @@ -260,7 +260,6 @@ class ProfileHookTestCase(TestCaseBase): def f(): for i in range(2): yield i - raise StopIteration def g(p): for i in f(): pass diff --git a/Lib/test/test_tarfile.py b/Lib/test/test_tarfile.py index c135304..01d1a92 100644 --- a/Lib/test/test_tarfile.py +++ b/Lib/test/test_tarfile.py @@ -285,6 +285,18 @@ class ListTest(ReadTest, unittest.TestCase): self.assertIn(b'pax' + (b'/123' * 125) + b'/longlink link to pax' + (b'/123' * 125) + b'/longname', out) + def test_list_members(self): + tio = io.TextIOWrapper(io.BytesIO(), 'ascii', newline='\n') + def members(tar): + for tarinfo in tar.getmembers(): + if 'reg' in tarinfo.name: + yield tarinfo + with support.swap_attr(sys, 'stdout', tio): + self.tar.list(verbose=False, members=members(self.tar)) + out = tio.detach().getvalue() + self.assertIn(b'ustar/regtype', out) + self.assertNotIn(b'ustar/conttype', out) + class GzipListTest(GzipTest, ListTest): pass @@ -1416,6 +1428,88 @@ class GNUWriteTest(unittest.TestCase): ("longlnk/" * 127) + "longlink_") +class CreateTest(TarTest, unittest.TestCase): + + prefix = "x:" + + file_path = os.path.join(TEMPDIR, "spameggs42") + + def setUp(self): + support.unlink(tmpname) + + @classmethod + def setUpClass(cls): + with open(cls.file_path, "wb") as fobj: + fobj.write(b"aaa") + + @classmethod + def tearDownClass(cls): + support.unlink(cls.file_path) + + def test_create(self): + with tarfile.open(tmpname, self.mode) as tobj: + tobj.add(self.file_path) + + with self.taropen(tmpname) as tobj: + names = tobj.getnames() + self.assertEqual(len(names), 1) + self.assertIn('spameggs42', names[0]) + + def test_create_existing(self): + with tarfile.open(tmpname, self.mode) as tobj: + tobj.add(self.file_path) + + with self.assertRaises(FileExistsError): + tobj = tarfile.open(tmpname, self.mode) + + with self.taropen(tmpname) as tobj: + names = tobj.getnames() + self.assertEqual(len(names), 1) + self.assertIn('spameggs42', names[0]) + + def test_create_taropen(self): + with self.taropen(tmpname, "x") as tobj: + tobj.add(self.file_path) + + with self.taropen(tmpname) as tobj: + names = tobj.getnames() + self.assertEqual(len(names), 1) + self.assertIn('spameggs42', names[0]) + + def test_create_existing_taropen(self): + with self.taropen(tmpname, "x") as tobj: + tobj.add(self.file_path) + + with self.assertRaises(FileExistsError): + with self.taropen(tmpname, "x"): + pass + + with self.taropen(tmpname) as tobj: + names = tobj.getnames() + self.assertEqual(len(names), 1) + self.assertIn("spameggs42", names[0]) + + +class GzipCreateTest(GzipTest, CreateTest): + pass + + +class Bz2CreateTest(Bz2Test, CreateTest): + pass + + +class LzmaCreateTest(LzmaTest, CreateTest): + pass + + +class CreateWithXModeTest(CreateTest): + + prefix = "x" + + test_create_taropen = None + test_create_existing_taropen = None + + @unittest.skipUnless(hasattr(os, "link"), "Missing hardlink implementation") class HardlinkTest(unittest.TestCase): # Test the creation of LNKTYPE (hardlink) members in an archive. diff --git a/Lib/test/test_tcl.py b/Lib/test/test_tcl.py index da8f629..d0251aa 100644 --- a/Lib/test/test_tcl.py +++ b/Lib/test/test_tcl.py @@ -415,6 +415,8 @@ class TclTest(unittest.TestCase): # XXX NaN representation can be not parsable by float() self.assertEqual(passValue((1, '2', (3.4,))), (1, '2', (3.4,)) if self.wantobjects else '1 2 3.4') + self.assertEqual(passValue(['a', ['b', 'c']]), + ('a', ('b', 'c')) if self.wantobjects else 'a {b c}') def test_user_command(self): result = None @@ -466,6 +468,7 @@ class TclTest(unittest.TestCase): # XXX NaN representation can be not parsable by float() check((), '') check((1, (2,), (3, 4), '5 6', ()), '1 2 {3 4} {5 6} {}') + check([1, [2,], [3, 4], '5 6', []], '1 2 {3 4} {5 6} {}') def test_splitlist(self): splitlist = self.interp.tk.splitlist @@ -491,12 +494,15 @@ class TclTest(unittest.TestCase): ('a 3.4', ('a', '3.4')), (('a', 3.4), ('a', 3.4)), ((), ()), + ([], ()), + (['a', ['b', 'c']], ('a', ['b', 'c'])), (call('list', 1, '2', (3.4,)), (1, '2', (3.4,)) if self.wantobjects else ('1', '2', '3.4')), ] + tk_patchlevel = get_tk_patchlevel() if tcl_version >= (8, 5): - if not self.wantobjects or get_tk_patchlevel() < (8, 5, 5): + if not self.wantobjects or tk_patchlevel < (8, 5, 5): # Before 8.5.5 dicts were converted to lists through string expected = ('12', '\u20ac', '\xe2\x82\xac', '3.4') else: @@ -505,8 +511,11 @@ class TclTest(unittest.TestCase): (call('dict', 'create', 12, '\u20ac', b'\xe2\x82\xac', (3.4,)), expected), ] + dbg_info = ('want objects? %s, Tcl version: %s, Tk patchlevel: %s' + % (self.wantobjects, tcl_version, tk_patchlevel)) for arg, res in testcases: - self.assertEqual(splitlist(arg), res, msg=arg) + self.assertEqual(splitlist(arg), res, + 'arg=%a, %s' % (arg, dbg_info)) self.assertRaises(TclError, splitlist, '{') def test_split(self): @@ -538,6 +547,9 @@ class TclTest(unittest.TestCase): (('a', 3.4), ('a', 3.4)), (('a', (2, 3.4)), ('a', (2, 3.4))), ((), ()), + ([], ()), + (['a', 'b c'], ('a', ('b', 'c'))), + (['a', ['b', 'c']], ('a', ('b', 'c'))), (call('list', 1, '2', (3.4,)), (1, '2', (3.4,)) if self.wantobjects else ('1', '2', '3.4')), diff --git a/Lib/test/test_telnetlib.py b/Lib/test/test_telnetlib.py index ee1c357..e1ef99a 100644 --- a/Lib/test/test_telnetlib.py +++ b/Lib/test/test_telnetlib.py @@ -11,7 +11,7 @@ threading = support.import_module('threading') HOST = support.HOST def server(evt, serv): - serv.listen(5) + serv.listen() evt.set() try: conn, addr = serv.accept() diff --git a/Lib/test/test_threaded_import.py b/Lib/test/test_threaded_import.py index 192fa08..5bf670c 100644 --- a/Lib/test/test_threaded_import.py +++ b/Lib/test/test_threaded_import.py @@ -115,12 +115,18 @@ class ThreadedImportTests(unittest.TestCase): errors = [] done_tasks = [] done.clear() + t0 = time.monotonic() for i in range(N): t = threading.Thread(target=task, args=(N, done, done_tasks, errors,)) t.start() - self.assertTrue(done.wait(60)) - self.assertFalse(errors) + completed = done.wait(10 * 60) + dt = time.monotonic() - t0 + if verbose: + print("%.1f ms" % (dt*1e3), flush=True, end=" ") + dbg_info = 'done: %s/%s' % (len(done_tasks), N) + self.assertFalse(errors, dbg_info) + self.assertTrue(completed, dbg_info) if verbose: print("OK.") diff --git a/Lib/test/test_timeit.py b/Lib/test/test_timeit.py index 09e76e0..267d2c8 100644 --- a/Lib/test/test_timeit.py +++ b/Lib/test/test_timeit.py @@ -98,9 +98,10 @@ class TestTimeit(unittest.TestCase): def fake_callable_stmt(self): self.fake_timer.inc() - def timeit(self, stmt, setup, number=None): + def timeit(self, stmt, setup, number=None, globals=None): self.fake_timer = FakeTimer() - t = timeit.Timer(stmt=stmt, setup=setup, timer=self.fake_timer) + t = timeit.Timer(stmt=stmt, setup=setup, timer=self.fake_timer, + globals=globals) kwargs = {} if number is None: number = DEFAULT_NUMBER @@ -139,6 +140,17 @@ class TestTimeit(unittest.TestCase): timer=FakeTimer()) self.assertEqual(delta_time, 0) + def test_timeit_globals_args(self): + global _global_timer + _global_timer = FakeTimer() + t = timeit.Timer(stmt='_global_timer.inc()', timer=_global_timer) + self.assertRaises(NameError, t.timeit, number=3) + timeit.timeit(stmt='_global_timer.inc()', timer=_global_timer, + globals=globals(), number=3) + local_timer = FakeTimer() + timeit.timeit(stmt='local_timer.inc()', timer=local_timer, + globals=locals(), number=3) + def repeat(self, stmt, setup, repeat=None, number=None): self.fake_timer = FakeTimer() t = timeit.Timer(stmt=stmt, setup=setup, timer=self.fake_timer) diff --git a/Lib/test/test_timeout.py b/Lib/test/test_timeout.py index 703c43a..3c75dcc 100644 --- a/Lib/test/test_timeout.py +++ b/Lib/test/test_timeout.py @@ -243,14 +243,14 @@ class TCPTimeoutTestCase(TimeoutTestCase): def testAcceptTimeout(self): # Test accept() timeout support.bind_port(self.sock, self.localhost) - self.sock.listen(5) + self.sock.listen() self._sock_operation(1, 1.5, 'accept') def testSend(self): # Test send() timeout with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as serv: support.bind_port(serv, self.localhost) - serv.listen(5) + serv.listen() self.sock.connect(serv.getsockname()) # Send a lot of data in order to bypass buffering in the TCP stack. self._sock_operation(100, 1.5, 'send', b"X" * 200000) @@ -259,7 +259,7 @@ class TCPTimeoutTestCase(TimeoutTestCase): # Test sendto() timeout with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as serv: support.bind_port(serv, self.localhost) - serv.listen(5) + serv.listen() self.sock.connect(serv.getsockname()) # The address argument is ignored since we already connected. self._sock_operation(100, 1.5, 'sendto', b"X" * 200000, @@ -269,7 +269,7 @@ class TCPTimeoutTestCase(TimeoutTestCase): # Test sendall() timeout with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as serv: support.bind_port(serv, self.localhost) - serv.listen(5) + serv.listen() self.sock.connect(serv.getsockname()) # Send a lot of data in order to bypass buffering in the TCP stack. self._sock_operation(100, 1.5, 'sendall', b"X" * 200000) diff --git a/Lib/test/test_tokenize.py b/Lib/test/test_tokenize.py index 38611a7..8f74a06 100644 --- a/Lib/test/test_tokenize.py +++ b/Lib/test/test_tokenize.py @@ -464,7 +464,7 @@ Additive Multiplicative - >>> dump_tokens("x = 1//1*1/5*12%0x12") + >>> dump_tokens("x = 1//1*1/5*12%0x12@42") ENCODING 'utf-8' (0, 0) (0, 0) NAME 'x' (1, 0) (1, 1) OP '=' (1, 2) (1, 3) @@ -479,6 +479,8 @@ Multiplicative NUMBER '12' (1, 13) (1, 15) OP '%' (1, 15) (1, 16) NUMBER '0x12' (1, 16) (1, 20) + OP '@' (1, 20) (1, 21) + NUMBER '42' (1, 21) (1, 23) Unary @@ -1154,6 +1156,7 @@ class TestTokenize(TestCase): self.assertExactTypeEqual('//', token.DOUBLESLASH) self.assertExactTypeEqual('//=', token.DOUBLESLASHEQUAL) self.assertExactTypeEqual('@', token.AT) + self.assertExactTypeEqual('@=', token.ATEQUAL) self.assertExactTypeEqual('a**2+b**2==c**2', NAME, token.DOUBLESTAR, NUMBER, diff --git a/Lib/test/test_trace.py b/Lib/test/test_trace.py index 1cec710..05bf274 100644 --- a/Lib/test/test_trace.py +++ b/Lib/test/test_trace.py @@ -10,7 +10,6 @@ from trace import CoverageResults, Trace from test.tracedmodules import testmod - #------------------------------- Utilities -----------------------------------# def fix_ext_py(filename): @@ -224,6 +223,11 @@ class TestFuncs(unittest.TestCase): self.addCleanup(sys.settrace, sys.gettrace()) self.tracer = Trace(count=0, trace=0, countfuncs=1) self.filemod = my_file_and_modname() + self._saved_tracefunc = sys.gettrace() + + def tearDown(self): + if self._saved_tracefunc is not None: + sys.settrace(self._saved_tracefunc) def test_simple_caller(self): self.tracer.runfunc(traced_func_simple_caller, 1) diff --git a/Lib/test/test_traceback.py b/Lib/test/test_traceback.py index c295563..3c32273 100644 --- a/Lib/test/test_traceback.py +++ b/Lib/test/test_traceback.py @@ -1,15 +1,24 @@ """Test cases for traceback module""" +from collections import namedtuple from io import StringIO +import linecache import sys import unittest import re from test.support import run_unittest, Error, captured_output from test.support import TESTFN, unlink, cpython_only +from test.script_helper import assert_python_ok +import textwrap import traceback +test_code = namedtuple('code', ['co_filename', 'co_name']) +test_frame = namedtuple('frame', ['f_code', 'f_globals']) +test_tb = namedtuple('tb', ['tb_frame', 'tb_lineno', 'tb_next']) + + class SyntaxTracebackCases(unittest.TestCase): # For now, a very minimal set of tests. I want to be sure that # formatting of SyntaxErrors works based on changes for 2.1. @@ -92,9 +101,9 @@ class SyntaxTracebackCases(unittest.TestCase): self.assertEqual(len(err), 1) str_value = '<unprintable %s object>' % X.__name__ if X.__module__ in ('__main__', 'builtins'): - str_name = X.__name__ + str_name = X.__qualname__ else: - str_name = '.'.join([X.__module__, X.__name__]) + str_name = '.'.join([X.__module__, X.__qualname__]) self.assertEqual(err[0], "%s: %s\n" % (str_name, str_value)) def test_without_exception(self): @@ -169,6 +178,37 @@ class SyntaxTracebackCases(unittest.TestCase): # Issue #18960: coding spec should has no effect do_test("0\n# coding: GBK\n", "h\xe9 ho", 'utf-8', 5) + def test_print_traceback_at_exit(self): + # Issue #22599: Ensure that it is possible to use the traceback module + # to display an exception at Python exit + code = textwrap.dedent(""" + import sys + import traceback + + class PrintExceptionAtExit(object): + def __init__(self): + try: + x = 1 / 0 + except Exception: + self.exc_info = sys.exc_info() + # self.exc_info[1] (traceback) contains frames: + # explicitly clear the reference to self in the current + # frame to break a reference cycle + self = None + + def __del__(self): + traceback.print_exception(*self.exc_info) + + # Keep a reference in the module namespace to call the destructor + # when the module is unloaded + obj = PrintExceptionAtExit() + """) + rc, stdout, stderr = assert_python_ok('-c', code) + expected = [b'Traceback (most recent call last):', + b' File "<string>", line 8, in __init__', + b'ZeroDivisionError: division by zero'] + self.assertEqual(stderr.splitlines(), expected) + class TracebackFormatTests(unittest.TestCase): @@ -444,6 +484,194 @@ class MiscTracebackCases(unittest.TestCase): self.assertEqual(len(inner_frame.f_locals), 0) +class TestFrame(unittest.TestCase): + + def test_basics(self): + linecache.clearcache() + linecache.lazycache("f", globals()) + f = traceback.FrameSummary("f", 1, "dummy") + self.assertEqual( + ("f", 1, "dummy", '"""Test cases for traceback module"""'), + tuple(f)) + self.assertEqual(None, f.locals) + + def test_lazy_lines(self): + linecache.clearcache() + f = traceback.FrameSummary("f", 1, "dummy", lookup_line=False) + self.assertEqual(None, f._line) + linecache.lazycache("f", globals()) + self.assertEqual( + '"""Test cases for traceback module"""', + f.line) + + def test_explicit_line(self): + f = traceback.FrameSummary("f", 1, "dummy", line="line") + self.assertEqual("line", f.line) + + +class TestStack(unittest.TestCase): + + def test_walk_stack(self): + s = list(traceback.walk_stack(None)) + self.assertGreater(len(s), 10) + + def test_walk_tb(self): + try: + 1/0 + except Exception: + _, _, tb = sys.exc_info() + s = list(traceback.walk_tb(tb)) + self.assertEqual(len(s), 1) + + def test_extract_stack(self): + s = traceback.StackSummary.extract(traceback.walk_stack(None)) + self.assertIsInstance(s, traceback.StackSummary) + + def test_extract_stack_limit(self): + s = traceback.StackSummary.extract(traceback.walk_stack(None), limit=5) + self.assertEqual(len(s), 5) + + def test_extract_stack_lookup_lines(self): + linecache.clearcache() + linecache.updatecache('/foo.py', globals()) + c = test_code('/foo.py', 'method') + f = test_frame(c, None) + s = traceback.StackSummary.extract(iter([(f, 6)]), lookup_lines=True) + linecache.clearcache() + self.assertEqual(s[0].line, "import sys") + + def test_extract_stackup_deferred_lookup_lines(self): + linecache.clearcache() + c = test_code('/foo.py', 'method') + f = test_frame(c, None) + s = traceback.StackSummary.extract(iter([(f, 6)]), lookup_lines=False) + self.assertEqual({}, linecache.cache) + linecache.updatecache('/foo.py', globals()) + self.assertEqual(s[0].line, "import sys") + + def test_from_list(self): + s = traceback.StackSummary([('foo.py', 1, 'fred', 'line')]) + self.assertEqual( + [' File "foo.py", line 1, in fred\n line\n'], + s.format()) + + def test_format_smoke(self): + # For detailed tests see the format_list tests, which consume the same + # code. + s = traceback.StackSummary([('foo.py', 1, 'fred', 'line')]) + self.assertEqual( + [' File "foo.py", line 1, in fred\n line\n'], + s.format()) + + + +class TestTracebackException(unittest.TestCase): + + def test_smoke(self): + try: + 1/0 + except Exception: + exc_info = sys.exc_info() + exc = traceback.TracebackException(*exc_info) + expected_stack = traceback.StackSummary.extract( + traceback.walk_tb(exc_info[2])) + self.assertEqual(None, exc.__cause__) + self.assertEqual(None, exc.__context__) + self.assertEqual(False, exc.__suppress_context__) + self.assertEqual(expected_stack, exc.stack) + self.assertEqual(exc_info[0], exc.exc_type) + self.assertEqual(str(exc_info[1]), str(exc)) + + def test_from_exception(self): + # Check all the parameters are accepted. + def foo(): + 1/0 + try: + foo() + except Exception as e: + exc_info = sys.exc_info() + self.expected_stack = traceback.StackSummary.extract( + traceback.walk_tb(exc_info[2]), limit=1, lookup_lines=False) + self.exc = traceback.TracebackException.from_exception( + e, limit=1, lookup_lines=False) + expected_stack = self.expected_stack + exc = self.exc + self.assertEqual(None, exc.__cause__) + self.assertEqual(None, exc.__context__) + self.assertEqual(False, exc.__suppress_context__) + self.assertEqual(expected_stack, exc.stack) + self.assertEqual(exc_info[0], exc.exc_type) + self.assertEqual(str(exc_info[1]), str(exc)) + + def test_cause(self): + try: + try: + 1/0 + finally: + exc_info_context = sys.exc_info() + exc_context = traceback.TracebackException(*exc_info_context) + cause = Exception("cause") + raise Exception("uh oh") from cause + except Exception: + exc_info = sys.exc_info() + exc = traceback.TracebackException(*exc_info) + expected_stack = traceback.StackSummary.extract( + traceback.walk_tb(exc_info[2])) + exc_cause = traceback.TracebackException(Exception, cause, None) + self.assertEqual(exc_cause, exc.__cause__) + self.assertEqual(exc_context, exc.__context__) + self.assertEqual(True, exc.__suppress_context__) + self.assertEqual(expected_stack, exc.stack) + self.assertEqual(exc_info[0], exc.exc_type) + self.assertEqual(str(exc_info[1]), str(exc)) + + def test_context(self): + try: + try: + 1/0 + finally: + exc_info_context = sys.exc_info() + exc_context = traceback.TracebackException(*exc_info_context) + raise Exception("uh oh") + except Exception: + exc_info = sys.exc_info() + exc = traceback.TracebackException(*exc_info) + expected_stack = traceback.StackSummary.extract( + traceback.walk_tb(exc_info[2])) + self.assertEqual(None, exc.__cause__) + self.assertEqual(exc_context, exc.__context__) + self.assertEqual(False, exc.__suppress_context__) + self.assertEqual(expected_stack, exc.stack) + self.assertEqual(exc_info[0], exc.exc_type) + self.assertEqual(str(exc_info[1]), str(exc)) + + def test_limit(self): + def recurse(n): + if n: + recurse(n-1) + else: + 1/0 + try: + recurse(10) + except Exception: + exc_info = sys.exc_info() + exc = traceback.TracebackException(*exc_info, limit=5) + expected_stack = traceback.StackSummary.extract( + traceback.walk_tb(exc_info[2]), limit=5) + self.assertEqual(expected_stack, exc.stack) + + def test_lookup_lines(self): + linecache.clearcache() + e = Exception("uh oh") + c = test_code('/foo.py', 'method') + f = test_frame(c, None) + tb = test_tb(f, 6, None) + exc = traceback.TracebackException(Exception, e, tb, lookup_lines=False) + self.assertEqual({}, linecache.cache) + linecache.updatecache('/foo.py', globals()) + self.assertEqual(exc.stack[0].line, "import sys") + + def test_main(): run_unittest(__name__) diff --git a/Lib/test/test_tracemalloc.py b/Lib/test/test_tracemalloc.py index 48ccab2..19d3fd8 100644 --- a/Lib/test/test_tracemalloc.py +++ b/Lib/test/test_tracemalloc.py @@ -755,7 +755,7 @@ class TestCommandLine(unittest.TestCase): stdout = stdout.rstrip() self.assertEqual(stdout, b'False') - @unittest.skipIf(script_helper._interpreter_requires_environment(), + @unittest.skipIf(script_helper.interpreter_requires_environment(), 'Cannot run -E tests when PYTHON env vars are required.') def test_env_var_ignored_with_E(self): """PYTHON* environment variables must be ignored when -E is present.""" diff --git a/Lib/test/test_tuple.py b/Lib/test/test_tuple.py index 51875a1..d711116 100644 --- a/Lib/test/test_tuple.py +++ b/Lib/test/test_tuple.py @@ -6,6 +6,11 @@ import pickle class TupleTest(seq_tests.CommonTest): type2test = tuple + def test_getitem_error(self): + msg = "tuple indices must be integers or slices" + with self.assertRaisesRegex(TypeError, msg): + ()['a'] + def test_constructors(self): super().test_constructors() # calling built-in types without argument must return empty @@ -203,6 +208,14 @@ class TupleTest(seq_tests.CommonTest): with self.assertRaises(TypeError): [3,] + T((1,2)) + def test_lexicographic_ordering(self): + # Issue 21100 + a = self.type2test([1, 2]) + b = self.type2test([1, 2, 0]) + c = self.type2test([1, 3]) + self.assertLess(a, b) + self.assertLess(b, c) + def test_main(): support.run_unittest(TupleTest) diff --git a/Lib/test/test_types.py b/Lib/test/test_types.py index ec10752..11d9546 100644 --- a/Lib/test/test_types.py +++ b/Lib/test/test_types.py @@ -343,6 +343,8 @@ class TypesTests(unittest.TestCase): self.assertRaises(ValueError, 3 .__format__, ",n") # can't have ',' with 'c' self.assertRaises(ValueError, 3 .__format__, ",c") + # can't have '#' with 'c' + self.assertRaises(ValueError, 3 .__format__, "#c") # ensure that only int and float type specifiers work for format_spec in ([chr(x) for x in range(ord('a'), ord('z')+1)] + diff --git a/Lib/test/test_unicode.py b/Lib/test/test_unicode.py index 7735a6b..e4cd99b 100644 --- a/Lib/test/test_unicode.py +++ b/Lib/test/test_unicode.py @@ -8,6 +8,7 @@ Written by Marc-Andre Lemburg (mal@lemburg.com). import _string import codecs import itertools +import operator import struct import sys import unittest @@ -250,6 +251,7 @@ class UnicodeTest(string_tests.CommonTest, {ord('a'): None, ord('b'): ''}) self.checkequalnofix('xyyx', 'xzx', 'translate', {ord('z'): 'yy'}) + # this needs maketrans() self.checkequalnofix('abababc', 'abababc', 'translate', {'b': '<i>'}) @@ -259,6 +261,33 @@ class UnicodeTest(string_tests.CommonTest, tbl = self.type2test.maketrans('abc', 'xyz', 'd') self.checkequalnofix('xyzzy', 'abdcdcbdddd', 'translate', tbl) + # various tests switching from ASCII to latin1 or the opposite; + # same length, remove a letter, or replace with a longer string. + self.assertEqual("[a]".translate(str.maketrans('a', 'X')), + "[X]") + self.assertEqual("[a]".translate(str.maketrans({'a': 'X'})), + "[X]") + self.assertEqual("[a]".translate(str.maketrans({'a': None})), + "[]") + self.assertEqual("[a]".translate(str.maketrans({'a': 'XXX'})), + "[XXX]") + self.assertEqual("[a]".translate(str.maketrans({'a': '\xe9'})), + "[\xe9]") + self.assertEqual("[a]".translate(str.maketrans({'a': '<\xe9>'})), + "[<\xe9>]") + self.assertEqual("[\xe9]".translate(str.maketrans({'\xe9': 'a'})), + "[a]") + self.assertEqual("[\xe9]".translate(str.maketrans({'\xe9': None})), + "[]") + + # invalid Unicode characters + invalid_char = 0x10ffff+1 + for before in "a\xe9\u20ac\U0010ffff": + mapping = str.maketrans({before: invalid_char}) + text = "[%s]" % before + self.assertRaises(ValueError, text.translate, mapping) + + # errors self.assertRaises(TypeError, self.type2test.maketrans) self.assertRaises(ValueError, self.type2test.maketrans, 'abc', 'defg') self.assertRaises(TypeError, self.type2test.maketrans, 2, 'def') @@ -1154,20 +1183,20 @@ class UnicodeTest(string_tests.CommonTest, self.assertEqual('%.2s' % "a\xe9\u20ac", 'a\xe9') #issue 19995 - class PsuedoInt: + class PseudoInt: def __init__(self, value): self.value = int(value) def __int__(self): return self.value def __index__(self): return self.value - class PsuedoFloat: + class PseudoFloat: def __init__(self, value): self.value = float(value) def __int__(self): return int(self.value) - pi = PsuedoFloat(3.1415) - letter_m = PsuedoInt(109) + pi = PseudoFloat(3.1415) + letter_m = PseudoInt(109) self.assertEqual('%x' % 42, '2a') self.assertEqual('%X' % 15, 'F') self.assertEqual('%o' % 9, '11') @@ -1176,11 +1205,11 @@ class UnicodeTest(string_tests.CommonTest, self.assertEqual('%X' % letter_m, '6D') self.assertEqual('%o' % letter_m, '155') self.assertEqual('%c' % letter_m, 'm') - self.assertWarns(DeprecationWarning, '%x'.__mod__, pi), - self.assertWarns(DeprecationWarning, '%x'.__mod__, 3.14), - self.assertWarns(DeprecationWarning, '%X'.__mod__, 2.11), - self.assertWarns(DeprecationWarning, '%o'.__mod__, 1.79), - self.assertWarns(DeprecationWarning, '%c'.__mod__, pi), + self.assertRaisesRegex(TypeError, '%x format: an integer is required, not float', operator.mod, '%x', 3.14), + self.assertRaisesRegex(TypeError, '%X format: an integer is required, not float', operator.mod, '%X', 2.11), + self.assertRaisesRegex(TypeError, '%o format: an integer is required, not float', operator.mod, '%o', 1.79), + self.assertRaisesRegex(TypeError, '%x format: an integer is required, not PseudoFloat', operator.mod, '%x', pi), + self.assertRaises(TypeError, operator.mod, '%c', pi), def test_formatting_with_enum(self): # issue18780 diff --git a/Lib/test/test_unicodedata.py b/Lib/test/test_unicodedata.py index 707b30e..f8788a0 100644 --- a/Lib/test/test_unicodedata.py +++ b/Lib/test/test_unicodedata.py @@ -21,7 +21,7 @@ errors = 'surrogatepass' class UnicodeMethodsTest(unittest.TestCase): # update this, if the database changes - expectedchecksum = 'e74e878de71b6e780ffac271785c3cb58f6251f3' + expectedchecksum = '618e2c1a22ee79d2235319709f16c50f987ee21f' def test_method_checksum(self): h = hashlib.sha1() @@ -79,8 +79,9 @@ class UnicodeDatabaseTest(unittest.TestCase): class UnicodeFunctionsTest(UnicodeDatabaseTest): - # update this, if the database changes - expectedchecksum = 'f0b74d26776331cc7bdc3a4698f037d73f2cee2b' + # Update this if the database changes. Make sure to do a full rebuild + # (e.g. 'make distclean && make') to get the correct checksum. + expectedchecksum = '585302895deead0c1c8478c51da9241d4efedca9' def test_function_checksum(self): data = [] h = hashlib.sha1() diff --git a/Lib/test/test_urllib.py b/Lib/test/test_urllib.py index 16236ef..58ca2a5 100644 --- a/Lib/test/test_urllib.py +++ b/Lib/test/test_urllib.py @@ -10,7 +10,10 @@ import unittest from unittest.mock import patch from test import support import os -import ssl +try: + import ssl +except ImportError: + ssl = None import sys import tempfile from nturl2path import url2pathname, pathname2url @@ -380,6 +383,7 @@ Content-Type: text/html; charset=iso-8859-1 with support.check_warnings(('',DeprecationWarning)): urllib.request.URLopener() + @unittest.skipUnless(ssl, "ssl module required") def test_cafile_and_context(self): context = ssl.create_default_context() with self.assertRaises(ValueError): @@ -1331,7 +1335,7 @@ class URLopener_Tests(unittest.TestCase): # serv.settimeout(3) # serv.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1) # serv.bind(("", 9093)) -# serv.listen(5) +# serv.listen() # try: # conn, addr = serv.accept() # conn.send("1 Hola mundo\n") diff --git a/Lib/test/test_urllib2.py b/Lib/test/test_urllib2.py index 7d41ea1..36d7e87 100644 --- a/Lib/test/test_urllib2.py +++ b/Lib/test/test_urllib2.py @@ -1422,6 +1422,21 @@ class HandlerTests(unittest.TestCase): handler.do_open(conn, req) self.assertTrue(conn.fakesock.closed, "Connection not closed") + def test_auth_prior_handler(self): + pwd_manager = MockPasswordManager() + pwd_manager.add_password(None, 'https://example.com', + 'somebody', 'verysecret') + auth_prior_handler = urllib.request.HTTPBasicPriorAuthHandler( + pwd_manager) + http_hand = MockHTTPSHandler() + + opener = OpenerDirector() + opener.add_handler(http_hand) + opener.add_handler(auth_prior_handler) + + req = Request("https://example.com") + opener.open(req) + self.assertNotIn('Authorization', http_hand.httpconn.req_headers) class MiscTests(unittest.TestCase): diff --git a/Lib/test/test_urllibnet.py b/Lib/test/test_urllibnet.py index 4c8ba2d..42ebb6e 100644 --- a/Lib/test/test_urllibnet.py +++ b/Lib/test/test_urllibnet.py @@ -91,7 +91,8 @@ class urlopenNetworkTests(unittest.TestCase): # test getcode() with the fancy opener to get 404 error codes URL = "http://www.example.com/XXXinvalidXXX" with support.transient_internet(URL): - open_url = urllib.request.FancyURLopener().open(URL) + with self.assertWarns(DeprecationWarning): + open_url = urllib.request.FancyURLopener().open(URL) try: code = open_url.getcode() finally: diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py index ad9820b..0481f0b 100644 --- a/Lib/test/test_urlparse.py +++ b/Lib/test/test_urlparse.py @@ -210,10 +210,6 @@ class UrlParseTestCase(unittest.TestCase): # "abnormal" cases from RFC 1808: self.checkJoin(RFC1808_BASE, '', 'http://a/b/c/d;p?q#f') - self.checkJoin(RFC1808_BASE, '../../../g', 'http://a/../g') - self.checkJoin(RFC1808_BASE, '../../../../g', 'http://a/../../g') - self.checkJoin(RFC1808_BASE, '/./g', 'http://a/./g') - self.checkJoin(RFC1808_BASE, '/../g', 'http://a/../g') self.checkJoin(RFC1808_BASE, 'g.', 'http://a/b/c/g.') self.checkJoin(RFC1808_BASE, '.g', 'http://a/b/c/.g') self.checkJoin(RFC1808_BASE, 'g..', 'http://a/b/c/g..') @@ -228,6 +224,13 @@ class UrlParseTestCase(unittest.TestCase): #self.checkJoin(RFC1808_BASE, 'http:g', 'http:g') #self.checkJoin(RFC1808_BASE, 'http:', 'http:') + # XXX: The following tests are no longer compatible with RFC3986 + # self.checkJoin(RFC1808_BASE, '../../../g', 'http://a/../g') + # self.checkJoin(RFC1808_BASE, '../../../../g', 'http://a/../../g') + # self.checkJoin(RFC1808_BASE, '/./g', 'http://a/./g') + # self.checkJoin(RFC1808_BASE, '/../g', 'http://a/../g') + + def test_RFC2368(self): # Issue 11467: path that starts with a number is not parsed correctly self.assertEqual(urllib.parse.urlparse('mailto:1337@example.org'), @@ -258,10 +261,6 @@ class UrlParseTestCase(unittest.TestCase): self.checkJoin(RFC2396_BASE, '../../', 'http://a/') self.checkJoin(RFC2396_BASE, '../../g', 'http://a/g') self.checkJoin(RFC2396_BASE, '', RFC2396_BASE) - self.checkJoin(RFC2396_BASE, '../../../g', 'http://a/../g') - self.checkJoin(RFC2396_BASE, '../../../../g', 'http://a/../../g') - self.checkJoin(RFC2396_BASE, '/./g', 'http://a/./g') - self.checkJoin(RFC2396_BASE, '/../g', 'http://a/../g') self.checkJoin(RFC2396_BASE, 'g.', 'http://a/b/c/g.') self.checkJoin(RFC2396_BASE, '.g', 'http://a/b/c/.g') self.checkJoin(RFC2396_BASE, 'g..', 'http://a/b/c/g..') @@ -277,10 +276,17 @@ class UrlParseTestCase(unittest.TestCase): self.checkJoin(RFC2396_BASE, 'g#s/./x', 'http://a/b/c/g#s/./x') self.checkJoin(RFC2396_BASE, 'g#s/../x', 'http://a/b/c/g#s/../x') + # XXX: The following tests are no longer compatible with RFC3986 + # self.checkJoin(RFC2396_BASE, '../../../g', 'http://a/../g') + # self.checkJoin(RFC2396_BASE, '../../../../g', 'http://a/../../g') + # self.checkJoin(RFC2396_BASE, '/./g', 'http://a/./g') + # self.checkJoin(RFC2396_BASE, '/../g', 'http://a/../g') + + def test_RFC3986(self): # Test cases from RFC3986 self.checkJoin(RFC3986_BASE, '?y','http://a/b/c/d;p?y') - self.checkJoin(RFC2396_BASE, ';x', 'http://a/b/c/;x') + self.checkJoin(RFC3986_BASE, ';x', 'http://a/b/c/;x') self.checkJoin(RFC3986_BASE, 'g:h','g:h') self.checkJoin(RFC3986_BASE, 'g','http://a/b/c/g') self.checkJoin(RFC3986_BASE, './g','http://a/b/c/g') @@ -304,17 +310,17 @@ class UrlParseTestCase(unittest.TestCase): self.checkJoin(RFC3986_BASE, '../..','http://a/') self.checkJoin(RFC3986_BASE, '../../','http://a/') self.checkJoin(RFC3986_BASE, '../../g','http://a/g') + self.checkJoin(RFC3986_BASE, '../../../g', 'http://a/g') #Abnormal Examples # The 'abnormal scenarios' are incompatible with RFC2986 parsing # Tests are here for reference. - #self.checkJoin(RFC3986_BASE, '../../../g','http://a/g') - #self.checkJoin(RFC3986_BASE, '../../../../g','http://a/g') - #self.checkJoin(RFC3986_BASE, '/./g','http://a/g') - #self.checkJoin(RFC3986_BASE, '/../g','http://a/g') - + self.checkJoin(RFC3986_BASE, '../../../g','http://a/g') + self.checkJoin(RFC3986_BASE, '../../../../g','http://a/g') + self.checkJoin(RFC3986_BASE, '/./g','http://a/g') + self.checkJoin(RFC3986_BASE, '/../g','http://a/g') self.checkJoin(RFC3986_BASE, 'g.','http://a/b/c/g.') self.checkJoin(RFC3986_BASE, '.g','http://a/b/c/.g') self.checkJoin(RFC3986_BASE, 'g..','http://a/b/c/g..') @@ -354,10 +360,8 @@ class UrlParseTestCase(unittest.TestCase): self.checkJoin(SIMPLE_BASE, '../g','http://a/b/g') self.checkJoin(SIMPLE_BASE, '../..','http://a/') self.checkJoin(SIMPLE_BASE, '../../g','http://a/g') - self.checkJoin(SIMPLE_BASE, '../../../g','http://a/../g') self.checkJoin(SIMPLE_BASE, './../g','http://a/b/g') self.checkJoin(SIMPLE_BASE, './g/.','http://a/b/c/g/') - self.checkJoin(SIMPLE_BASE, '/./g','http://a/./g') self.checkJoin(SIMPLE_BASE, 'g/./h','http://a/b/c/g/h') self.checkJoin(SIMPLE_BASE, 'g/../h','http://a/b/c/h') self.checkJoin(SIMPLE_BASE, 'http:g','http://a/b/c/g') @@ -371,6 +375,22 @@ class UrlParseTestCase(unittest.TestCase): self.checkJoin('svn://pathtorepo/dir1', 'dir2', 'svn://pathtorepo/dir2') self.checkJoin('svn+ssh://pathtorepo/dir1', 'dir2', 'svn+ssh://pathtorepo/dir2') + # XXX: The following tests are no longer compatible with RFC3986 + # self.checkJoin(SIMPLE_BASE, '../../../g','http://a/../g') + # self.checkJoin(SIMPLE_BASE, '/./g','http://a/./g') + + # test for issue22118 duplicate slashes + self.checkJoin(SIMPLE_BASE + '/', 'foo', SIMPLE_BASE + '/foo') + + # Non-RFC-defined tests, covering variations of base and trailing + # slashes + self.checkJoin('http://a/b/c/d/e/', '../../f/g/', 'http://a/b/c/f/g/') + self.checkJoin('http://a/b/c/d/e', '../../f/g/', 'http://a/b/f/g/') + self.checkJoin('http://a/b/c/d/e/', '/../../f/g/', 'http://a/f/g/') + self.checkJoin('http://a/b/c/d/e', '/../../f/g/', 'http://a/f/g/') + self.checkJoin('http://a/b/c/d/e/', '../../f/g', 'http://a/b/c/f/g') + self.checkJoin('http://a/b/', '../../f/g/', 'http://a/f/g/') + def test_RFC2732(self): str_cases = [ ('http://Test.python.org:5432/foo/', 'test.python.org', 5432), diff --git a/Lib/test/test_uuid.py b/Lib/test/test_uuid.py index 1e8cba3..fcb8454 100644 --- a/Lib/test/test_uuid.py +++ b/Lib/test/test_uuid.py @@ -1,9 +1,10 @@ -import unittest +import unittest.mock from test import support import builtins import io import os import shutil +import subprocess import uuid def importable(name): @@ -412,28 +413,27 @@ class TestUUID(unittest.TestCase): class TestInternals(unittest.TestCase): @unittest.skipUnless(os.name == 'posix', 'requires Posix') def test_find_mac(self): - data = '''\ - + data = ''' fake hwaddr cscotun0 Link encap:UNSPEC HWaddr 00-00-00-00-00-00-00-00-00-00-00-00-00-00-00-00 eth0 Link encap:Ethernet HWaddr 12:34:56:78:90:ab ''' - def mock_popen(cmd): - return io.StringIO(data) - - if shutil.which('ifconfig') is None: - path = os.pathsep.join(('/sbin', '/usr/sbin')) - if shutil.which('ifconfig', path=path) is None: - self.skipTest('requires ifconfig') - - with support.swap_attr(os, 'popen', mock_popen): - mac = uuid._find_mac( - command='ifconfig', - args='', - hw_identifiers=['hwaddr'], - get_index=lambda x: x + 1, - ) - self.assertEqual(mac, 0x1234567890ab) + + popen = unittest.mock.MagicMock() + popen.stdout = io.BytesIO(data.encode()) + + with unittest.mock.patch.object(shutil, 'which', + return_value='/sbin/ifconfig'): + with unittest.mock.patch.object(subprocess, 'Popen', + return_value=popen): + mac = uuid._find_mac( + command='ifconfig', + args='', + hw_identifiers=[b'hwaddr'], + get_index=lambda x: x + 1, + ) + + self.assertEqual(mac, 0x1234567890ab) def check_node(self, node, requires=None, network=False): if requires and node is None: @@ -454,6 +454,11 @@ eth0 Link encap:Ethernet HWaddr 12:34:56:78:90:ab self.check_node(node, 'ifconfig', True) @unittest.skipUnless(os.name == 'posix', 'requires Posix') + def test_ip_getnode(self): + node = uuid._ip_getnode() + self.check_node(node, 'ip', True) + + @unittest.skipUnless(os.name == 'posix', 'requires Posix') def test_arp_getnode(self): node = uuid._arp_getnode() self.check_node(node, 'arp', True) diff --git a/Lib/test/test_wait3.py b/Lib/test/test_wait3.py index f6a065d..bb71481 100644 --- a/Lib/test/test_wait3.py +++ b/Lib/test/test_wait3.py @@ -18,7 +18,8 @@ class Wait3Test(ForkWait): # This many iterations can be required, since some previously run # tests (e.g. test_ctypes) could have spawned a lot of children # very quickly. - for i in range(30): + deadline = time.monotonic() + 10.0 + while time.monotonic() <= deadline: # wait3() shouldn't hang, but some of the buildbots seem to hang # in the forking tests. This is an attempt to fix the problem. spid, status, rusage = os.wait3(os.WNOHANG) diff --git a/Lib/test/test_wait4.py b/Lib/test/test_wait4.py index 352c11a..b427a9b 100644 --- a/Lib/test/test_wait4.py +++ b/Lib/test/test_wait4.py @@ -19,13 +19,14 @@ class Wait4Test(ForkWait): # Issue #11185: wait4 is broken on AIX and will always return 0 # with WNOHANG. option = 0 - for i in range(10): + deadline = time.monotonic() + 10.0 + while time.monotonic() <= deadline: # wait4() shouldn't hang, but some of the buildbots seem to hang # in the forking tests. This is an attempt to fix the problem. spid, status, rusage = os.wait4(cpid, option) if spid == cpid: break - time.sleep(1.0) + time.sleep(0.1) self.assertEqual(spid, cpid) self.assertEqual(status, 0, "cause = %d, exit = %d" % (status&0xff, status>>8)) self.assertTrue(rusage) diff --git a/Lib/test/test_warnings.py b/Lib/test/test_warnings.py index fb01b83..9ac2139 100644 --- a/Lib/test/test_warnings.py +++ b/Lib/test/test_warnings.py @@ -5,7 +5,7 @@ from io import StringIO import sys import unittest from test import support -from test.script_helper import assert_python_ok +from test.script_helper import assert_python_ok, assert_python_failure from test import warning_tests @@ -432,6 +432,41 @@ class WarnTests(BaseTest): with self.assertRaises(ValueError): self.module.warn(BadStrWarning()) + def test_warning_classes(self): + class MyWarningClass(Warning): + pass + + class NonWarningSubclass: + pass + + # passing a non-subclass of Warning should raise a TypeError + with self.assertRaises(TypeError) as cm: + self.module.warn('bad warning category', '') + self.assertIn('category must be a Warning subclass, not ', + str(cm.exception)) + + with self.assertRaises(TypeError) as cm: + self.module.warn('bad warning category', NonWarningSubclass) + self.assertIn('category must be a Warning subclass, not ', + str(cm.exception)) + + # check that warning instances also raise a TypeError + with self.assertRaises(TypeError) as cm: + self.module.warn('bad warning category', MyWarningClass()) + self.assertIn('category must be a Warning subclass, not ', + str(cm.exception)) + + with self.assertWarns(MyWarningClass) as cm: + self.module.warn('good warning category', MyWarningClass) + self.assertEqual('good warning category', str(cm.warning)) + + with self.assertWarns(UserWarning) as cm: + self.module.warn('good warning category', None) + self.assertEqual('good warning category', str(cm.warning)) + + with self.assertWarns(MyWarningClass) as cm: + self.module.warn('good warning category', MyWarningClass) + self.assertIsInstance(cm.warning, Warning) class CWarnTests(WarnTests, unittest.TestCase): module = c_warnings @@ -821,7 +856,19 @@ class EnvironmentVariableTests(BaseTest): "import sys; sys.stdout.write(str(sys.warnoptions))", PYTHONWARNINGS="ignore::DeprecationWarning") self.assertEqual(stdout, - b"['ignore::UnicodeWarning', 'ignore::DeprecationWarning']") + b"['ignore::DeprecationWarning', 'ignore::UnicodeWarning']") + + def test_conflicting_envvar_and_command_line(self): + rc, stdout, stderr = assert_python_failure("-Werror::DeprecationWarning", "-c", + "import sys, warnings; sys.stdout.write(str(sys.warnoptions)); " + "warnings.warn('Message', DeprecationWarning)", + PYTHONWARNINGS="default::DeprecationWarning") + self.assertEqual(stdout, + b"['default::DeprecationWarning', 'error::DeprecationWarning']") + self.assertEqual(stderr.splitlines(), + [b"Traceback (most recent call last):", + b" File \"<string>\", line 1, in <module>", + b"DeprecationWarning: Message"]) @unittest.skipUnless(sys.getfilesystemencoding() != 'ascii', 'requires non-ascii filesystemencoding') diff --git a/Lib/test/test_weakref.py b/Lib/test/test_weakref.py index 3e7347c..e735376 100644 --- a/Lib/test/test_weakref.py +++ b/Lib/test/test_weakref.py @@ -92,6 +92,18 @@ class ReferencesTestCase(TestBase): self.check_basic_callback(create_function) self.check_basic_callback(create_bound_method) + @support.cpython_only + def test_cfunction(self): + import _testcapi + create_cfunction = _testcapi.create_cfunction + f = create_cfunction() + wr = weakref.ref(f) + self.assertIs(wr(), f) + del f + self.assertIsNone(wr()) + self.check_basic_ref(create_cfunction) + self.check_basic_callback(create_cfunction) + def test_multiple_callbacks(self): o = C() ref1 = weakref.ref(o, self.callback) @@ -1574,6 +1586,14 @@ class MappingTestCase(TestBase): self.assertEqual(len(d), 0) self.assertEqual(count, 2) + def test_make_weak_valued_dict_repr(self): + dict = weakref.WeakValueDictionary() + self.assertRegex(repr(dict), '<WeakValueDictionary at 0x.*>') + + def test_make_weak_keyed_dict_repr(self): + dict = weakref.WeakKeyDictionary() + self.assertRegex(repr(dict), '<WeakKeyDictionary at 0x.*>') + from test import mapping_tests class WeakValueDictionaryTestCase(mapping_tests.BasicTestMappingProtocol): diff --git a/Lib/test/test_wsgiref.py b/Lib/test/test_wsgiref.py index 5704fc7..29f64f3 100644 --- a/Lib/test/test_wsgiref.py +++ b/Lib/test/test_wsgiref.py @@ -368,6 +368,7 @@ class HeaderTests(TestCase): def testMappingInterface(self): test = [('x','y')] + self.assertEqual(len(Headers()), 0) self.assertEqual(len(Headers([])),0) self.assertEqual(len(Headers(test[:])),1) self.assertEqual(Headers(test[:]).keys(), ['x']) @@ -375,7 +376,7 @@ class HeaderTests(TestCase): self.assertEqual(Headers(test[:]).items(), test) self.assertIsNot(Headers(test).items(), test) # must be copy! - h=Headers([]) + h = Headers() del h['foo'] # should not raise an error h['Foo'] = 'bar' @@ -400,9 +401,8 @@ class HeaderTests(TestCase): def testRequireList(self): self.assertRaises(TypeError, Headers, "foo") - def testExtras(self): - h = Headers([]) + h = Headers() self.assertEqual(str(h),'\r\n') h.add_header('foo','bar',baz="spam") diff --git a/Lib/test/test_xml_etree_c.py b/Lib/test/test_xml_etree_c.py index 816aa86..d0df38d 100644 --- a/Lib/test/test_xml_etree_c.py +++ b/Lib/test/test_xml_etree_c.py @@ -55,7 +55,7 @@ class SizeofTest(unittest.TestCase): def setUp(self): self.elementsize = support.calcobjsize('5P') # extra - self.extra = struct.calcsize('PiiP4P') + self.extra = struct.calcsize('PnnP4P') check_sizeof = support.check_sizeof diff --git a/Lib/test/test_xmlrpc.py b/Lib/test/test_xmlrpc.py index 71b590c..dc37be2 100644 --- a/Lib/test/test_xmlrpc.py +++ b/Lib/test/test_xmlrpc.py @@ -287,7 +287,7 @@ class DateTimeTestCase(unittest.TestCase): def test_repr(self): d = datetime.datetime(2007,1,2,3,4,5) t = xmlrpclib.DateTime(d) - val ="<DateTime '20070102T03:04:05' at %x>" % id(t) + val ="<DateTime '20070102T03:04:05' at %#x>" % id(t) self.assertEqual(repr(t), val) def test_decode(self): @@ -713,6 +713,23 @@ class SimpleServerTestCase(BaseServerTestCase): conn.request('POST', '/RPC2 HTTP/1.0\r\nContent-Length: 100\r\n\r\nbye') conn.close() + def test_context_manager(self): + with xmlrpclib.ServerProxy(URL) as server: + server.add(2, 3) + self.assertNotEqual(server('transport')._connection, + (None, None)) + self.assertEqual(server('transport')._connection, + (None, None)) + + def test_context_manager_method_error(self): + try: + with xmlrpclib.ServerProxy(URL) as server: + server.add(2, "a") + except xmlrpclib.Fault: + pass + self.assertEqual(server('transport')._connection, + (None, None)) + class MultiPathServerTestCase(BaseServerTestCase): threadFunc = staticmethod(http_multi_server) @@ -891,7 +908,7 @@ class GzipUtilTestCase(unittest.TestCase): data = b'\0' * (max_gzip_decode + 1) encoded = xmlrpclib.gzip_encode(data) - with self.assertRaisesRegexp(ValueError, + with self.assertRaisesRegex(ValueError, "max gzipped payload length exceeded"): xmlrpclib.gzip_decode(encoded) @@ -919,6 +936,7 @@ class ServerProxyTestCase(unittest.TestCase): p = xmlrpclib.ServerProxy(self.url, transport=t) self.assertEqual(p('transport'), t) + # This is a contrived way to make a failure occur on the server side # in order to test the _send_traceback_header flag on the server class FailingMessageClass(http.client.HTTPMessage): diff --git a/Lib/test/test_zipfile.py b/Lib/test/test_zipfile.py index 3d8f9bc..f458f30 100644 --- a/Lib/test/test_zipfile.py +++ b/Lib/test/test_zipfile.py @@ -330,6 +330,37 @@ class AbstractTestsWithSourceFile: while zipopen.read1(100): pass + def test_repr(self): + fname = 'file.name' + for f in get_files(self): + with zipfile.ZipFile(f, 'w', self.compression) as zipfp: + zipfp.write(TESTFN, fname) + r = repr(zipfp) + self.assertIn("mode='w'", r) + + with zipfile.ZipFile(f, 'r') as zipfp: + r = repr(zipfp) + if isinstance(f, str): + self.assertIn('filename=%r' % f, r) + else: + self.assertIn('file=%r' % f, r) + self.assertIn("mode='r'", r) + r = repr(zipfp.getinfo(fname)) + self.assertIn('filename=%r' % fname, r) + self.assertIn('filemode=', r) + self.assertIn('file_size=', r) + if self.compression != zipfile.ZIP_STORED: + self.assertIn('compress_type=', r) + self.assertIn('compress_size=', r) + with zipfp.open(fname) as zipopen: + r = repr(zipopen) + self.assertIn('name=%r' % fname, r) + self.assertIn("mode='r'", r) + if self.compression != zipfile.ZIP_STORED: + self.assertIn('compress_type=', r) + self.assertIn('[closed]', repr(zipopen)) + self.assertIn('[closed]', repr(zipfp)) + def tearDown(self): unlink(TESTFN) unlink(TESTFN2) @@ -1647,6 +1678,34 @@ class LzmaTestsWithRandomBinaryFiles(AbstractTestsWithRandomBinaryFiles, compression = zipfile.ZIP_LZMA +# Privide the tell() method but not seek() +class Tellable: + def __init__(self, fp): + self.fp = fp + self.offset = 0 + + def write(self, data): + self.offset += self.fp.write(data) + + def tell(self): + return self.offset + + def flush(self): + pass + +class UnseekableTests(unittest.TestCase): + def test_writestr_tellable(self): + f = io.BytesIO() + with zipfile.ZipFile(Tellable(f), 'w', zipfile.ZIP_STORED) as zipfp: + zipfp.writestr('ones', b'111') + zipfp.writestr('twos', b'222') + with zipfile.ZipFile(f, mode='r') as zipf: + with zipf.open('ones') as zopen: + self.assertEqual(zopen.read(), b'111') + with zipf.open('twos') as zopen: + self.assertEqual(zopen.read(), b'222') + + @requires_zlib class TestsWithMultipleOpens(unittest.TestCase): @classmethod @@ -1663,35 +1722,52 @@ class TestsWithMultipleOpens(unittest.TestCase): def test_same_file(self): # Verify that (when the ZipFile is in control of creating file objects) # multiple open() calls can be made without interfering with each other. - self.make_test_archive(TESTFN2) - with zipfile.ZipFile(TESTFN2, mode="r") as zipf: - with zipf.open('ones') as zopen1, zipf.open('ones') as zopen2: - data1 = zopen1.read(500) - data2 = zopen2.read(500) - data1 += zopen1.read() - data2 += zopen2.read() - self.assertEqual(data1, data2) - self.assertEqual(data1, self.data1) + for f in get_files(self): + self.make_test_archive(f) + with zipfile.ZipFile(f, mode="r") as zipf: + with zipf.open('ones') as zopen1, zipf.open('ones') as zopen2: + data1 = zopen1.read(500) + data2 = zopen2.read(500) + data1 += zopen1.read() + data2 += zopen2.read() + self.assertEqual(data1, data2) + self.assertEqual(data1, self.data1) def test_different_file(self): # Verify that (when the ZipFile is in control of creating file objects) # multiple open() calls can be made without interfering with each other. - self.make_test_archive(TESTFN2) - with zipfile.ZipFile(TESTFN2, mode="r") as zipf: - with zipf.open('ones') as zopen1, zipf.open('twos') as zopen2: - data1 = zopen1.read(500) - data2 = zopen2.read(500) - data1 += zopen1.read() - data2 += zopen2.read() - self.assertEqual(data1, self.data1) - self.assertEqual(data2, self.data2) + for f in get_files(self): + self.make_test_archive(f) + with zipfile.ZipFile(f, mode="r") as zipf: + with zipf.open('ones') as zopen1, zipf.open('twos') as zopen2: + data1 = zopen1.read(500) + data2 = zopen2.read(500) + data1 += zopen1.read() + data2 += zopen2.read() + self.assertEqual(data1, self.data1) + self.assertEqual(data2, self.data2) def test_interleaved(self): # Verify that (when the ZipFile is in control of creating file objects) # multiple open() calls can be made without interfering with each other. - self.make_test_archive(TESTFN2) - with zipfile.ZipFile(TESTFN2, mode="r") as zipf: - with zipf.open('ones') as zopen1, zipf.open('twos') as zopen2: + for f in get_files(self): + self.make_test_archive(f) + with zipfile.ZipFile(f, mode="r") as zipf: + with zipf.open('ones') as zopen1, zipf.open('twos') as zopen2: + data1 = zopen1.read(500) + data2 = zopen2.read(500) + data1 += zopen1.read() + data2 += zopen2.read() + self.assertEqual(data1, self.data1) + self.assertEqual(data2, self.data2) + + def test_read_after_close(self): + for f in get_files(self): + self.make_test_archive(f) + with contextlib.ExitStack() as stack: + with zipfile.ZipFile(f, 'r') as zipf: + zopen1 = stack.enter_context(zipf.open('ones')) + zopen2 = stack.enter_context(zipf.open('twos')) data1 = zopen1.read(500) data2 = zopen2.read(500) data1 += zopen1.read() @@ -1699,43 +1775,32 @@ class TestsWithMultipleOpens(unittest.TestCase): self.assertEqual(data1, self.data1) self.assertEqual(data2, self.data2) - def test_read_after_close(self): - self.make_test_archive(TESTFN2) - with contextlib.ExitStack() as stack: - with zipfile.ZipFile(TESTFN2, 'r') as zipf: - zopen1 = stack.enter_context(zipf.open('ones')) - zopen2 = stack.enter_context(zipf.open('twos')) - data1 = zopen1.read(500) - data2 = zopen2.read(500) - data1 += zopen1.read() - data2 += zopen2.read() - self.assertEqual(data1, self.data1) - self.assertEqual(data2, self.data2) - def test_read_after_write(self): - with zipfile.ZipFile(TESTFN2, 'w', zipfile.ZIP_DEFLATED) as zipf: - zipf.writestr('ones', self.data1) - zipf.writestr('twos', self.data2) - with zipf.open('ones') as zopen1: - data1 = zopen1.read(500) - self.assertEqual(data1, self.data1[:500]) - with zipfile.ZipFile(TESTFN2, 'r') as zipf: - data1 = zipf.read('ones') - data2 = zipf.read('twos') - self.assertEqual(data1, self.data1) - self.assertEqual(data2, self.data2) + for f in get_files(self): + with zipfile.ZipFile(f, 'w', zipfile.ZIP_DEFLATED) as zipf: + zipf.writestr('ones', self.data1) + zipf.writestr('twos', self.data2) + with zipf.open('ones') as zopen1: + data1 = zopen1.read(500) + self.assertEqual(data1, self.data1[:500]) + with zipfile.ZipFile(f, 'r') as zipf: + data1 = zipf.read('ones') + data2 = zipf.read('twos') + self.assertEqual(data1, self.data1) + self.assertEqual(data2, self.data2) def test_write_after_read(self): - with zipfile.ZipFile(TESTFN2, "w", zipfile.ZIP_DEFLATED) as zipf: - zipf.writestr('ones', self.data1) - with zipf.open('ones') as zopen1: - zopen1.read(500) - zipf.writestr('twos', self.data2) - with zipfile.ZipFile(TESTFN2, 'r') as zipf: - data1 = zipf.read('ones') - data2 = zipf.read('twos') - self.assertEqual(data1, self.data1) - self.assertEqual(data2, self.data2) + for f in get_files(self): + with zipfile.ZipFile(f, "w", zipfile.ZIP_DEFLATED) as zipf: + zipf.writestr('ones', self.data1) + with zipf.open('ones') as zopen1: + zopen1.read(500) + zipf.writestr('twos', self.data2) + with zipfile.ZipFile(f, 'r') as zipf: + data1 = zipf.read('ones') + data2 = zipf.read('twos') + self.assertEqual(data1, self.data1) + self.assertEqual(data2, self.data2) def test_many_opens(self): # Verify that read() and open() promptly close the file descriptor, diff --git a/Lib/test/test_zipimport_support.py b/Lib/test/test_zipimport_support.py index 66c3557..2e801a8 100644 --- a/Lib/test/test_zipimport_support.py +++ b/Lib/test/test_zipimport_support.py @@ -39,7 +39,7 @@ def _run_object_doctest(obj, module): # Use the object's fully qualified name if it has one # Otherwise, use the module's name try: - name = "%s.%s" % (obj.__module__, obj.__name__) + name = "%s.%s" % (obj.__module__, obj.__qualname__) except AttributeError: name = module.__name__ for example in finder.find(obj, name, module): diff --git a/Lib/test/tf_inherit_check.py b/Lib/test/tf_inherit_check.py index afe50d2..138f25a 100644 --- a/Lib/test/tf_inherit_check.py +++ b/Lib/test/tf_inherit_check.py @@ -4,22 +4,24 @@ import sys import os +from test.support import SuppressCrashReport -verbose = (sys.argv[1] == 'v') -try: - fd = int(sys.argv[2]) - +with SuppressCrashReport(): + verbose = (sys.argv[1] == 'v') try: - os.write(fd, b"blat") - except OSError: - # Success -- could not write to fd. - sys.exit(0) - else: + fd = int(sys.argv[2]) + + try: + os.write(fd, b"blat") + except OSError: + # Success -- could not write to fd. + sys.exit(0) + else: + if verbose: + sys.stderr.write("fd %d is open in child" % fd) + sys.exit(1) + + except Exception: if verbose: - sys.stderr.write("fd %d is open in child" % fd) + raise sys.exit(1) - -except Exception: - if verbose: - raise - sys.exit(1) diff --git a/Lib/threading.py b/Lib/threading.py index 37aa3b8..24cc911 100644 --- a/Lib/threading.py +++ b/Lib/threading.py @@ -3,10 +3,7 @@ import sys as _sys import _thread -try: - from time import monotonic as _time -except ImportError: - from time import time as _time +from time import monotonic as _time from traceback import format_exc as _format_exc from _weakrefset import WeakSet from itertools import islice as _islice, count as _count @@ -106,8 +103,14 @@ class _RLock: owner = _active[owner].name except KeyError: pass - return "<%s owner=%r count=%d>" % ( - self.__class__.__name__, owner, self._count) + return "<%s %s.%s object owner=%r count=%d at %s>" % ( + "locked" if self._block.locked() else "unlocked", + self.__class__.__module__, + self.__class__.__qualname__, + owner, + self._count, + hex(id(self)) + ) def acquire(self, blocking=True, timeout=-1): """Acquire a lock, blocking or non-blocking. diff --git a/Lib/timeit.py b/Lib/timeit.py index 9cec000..3807794 100755 --- a/Lib/timeit.py +++ b/Lib/timeit.py @@ -60,6 +60,8 @@ default_number = 1000000 default_repeat = 3 default_timer = time.perf_counter +_globals = globals + # Don't change the indentation of the template; the reindent() calls # in Timer.__init__() depend on setup being indented 4 spaces and stmt # being indented 8 spaces. @@ -94,7 +96,9 @@ class Timer: The constructor takes a statement to be timed, an additional statement used for setup, and a timer function. Both statements default to 'pass'; the timer function is platform-dependent (see - module doc string). + module doc string). If 'globals' is specified, the code will be + executed within that namespace (as opposed to inside timeit's + namespace). To measure the execution time of the first statement, use the timeit() method. The repeat() method is a convenience to call @@ -104,10 +108,12 @@ class Timer: multi-line string literals. """ - def __init__(self, stmt="pass", setup="pass", timer=default_timer): + def __init__(self, stmt="pass", setup="pass", timer=default_timer, + globals=None): """Constructor. See class doc string.""" self.timer = timer - ns = {} + local_ns = {} + global_ns = _globals() if globals is None else globals if isinstance(stmt, str): # Check that the code can be compiled outside a function if isinstance(setup, str): @@ -121,19 +127,19 @@ class Timer: src = template.format(stmt=stmt, setup=setup) elif callable(setup): src = template.format(stmt=stmt, setup='_setup()') - ns['_setup'] = setup + local_ns['_setup'] = setup else: raise ValueError("setup is neither a string nor callable") - self.src = src # Save for traceback display + self.src = src # Save for traceback display code = compile(src, dummy_src_name, "exec") - exec(code, globals(), ns) - self.inner = ns["inner"] + exec(code, global_ns, local_ns) + self.inner = local_ns["inner"] elif callable(stmt): self.src = None if isinstance(setup, str): _setup = setup def setup(): - exec(_setup, globals(), ns) + exec(_setup, global_ns, local_ns) elif not callable(setup): raise ValueError("setup is neither a string nor callable") self.inner = _template_func(setup, stmt) @@ -214,14 +220,14 @@ class Timer: return r def timeit(stmt="pass", setup="pass", timer=default_timer, - number=default_number): + number=default_number, globals=None): """Convenience function to create Timer object and call timeit method.""" - return Timer(stmt, setup, timer).timeit(number) + return Timer(stmt, setup, timer, globals).timeit(number) def repeat(stmt="pass", setup="pass", timer=default_timer, - repeat=default_repeat, number=default_number): + repeat=default_repeat, number=default_number, globals=None): """Convenience function to create Timer object and call repeat method.""" - return Timer(stmt, setup, timer).repeat(repeat, number) + return Timer(stmt, setup, timer, globals).repeat(repeat, number) def main(args=None, *, _wrap_timer=None): """Main program, used when run as a script. diff --git a/Lib/tkinter/__init__.py b/Lib/tkinter/__init__.py index a1ffca1..beb0a73 100644 --- a/Lib/tkinter/__init__.py +++ b/Lib/tkinter/__init__.py @@ -770,9 +770,6 @@ class Misc: """Raise this widget in the stacking order.""" self.tk.call('raise', self._w, aboveThis) lift = tkraise - def colormodel(self, value=None): - """Useless. Not implemented in Tk.""" - return self.tk.call('tk', 'colormodel', self._w, value) def winfo_atom(self, name, displayof=0): """Return integer which represents atom NAME.""" args = ('winfo', 'atom') + self._displayof(displayof) + (name,) @@ -1331,6 +1328,11 @@ class Misc: def __str__(self): """Return the window path name of this widget.""" return self._w + + def __repr__(self): + return '<%s.%s object %s>' % ( + self.__class__.__module__, self.__class__.__qualname__, self._w) + # Pack methods that apply to the master _noarg_ = ['_noarg_'] def pack_propagate(self, flag=_noarg_): @@ -2191,21 +2193,6 @@ class Button(Widget): """ Widget.__init__(self, master, 'button', cnf, kw) - def tkButtonEnter(self, *dummy): - self.tk.call('tkButtonEnter', self._w) - - def tkButtonLeave(self, *dummy): - self.tk.call('tkButtonLeave', self._w) - - def tkButtonDown(self, *dummy): - self.tk.call('tkButtonDown', self._w) - - def tkButtonUp(self, *dummy): - self.tk.call('tkButtonUp', self._w) - - def tkButtonInvoke(self, *dummy): - self.tk.call('tkButtonInvoke', self._w) - def flash(self): """Flash the button. @@ -2704,35 +2691,15 @@ class Menu(Widget): disabledforeground, fg, font, foreground, postcommand, relief, selectcolor, takefocus, tearoff, tearoffcommand, title, type.""" Widget.__init__(self, master, 'menu', cnf, kw) + def tk_popup(self, x, y, entry=""): + """Post the menu at position X,Y with entry ENTRY.""" + self.tk.call('tk_popup', self._w, x, y, entry) def tk_bindForTraversal(self): # obsolete since Tk 4.0 import warnings warnings.warn('tk_bindForTraversal() does nothing and ' 'will be removed in 3.6', DeprecationWarning, stacklevel=2) - def tk_mbPost(self): - self.tk.call('tk_mbPost', self._w) - def tk_mbUnpost(self): - self.tk.call('tk_mbUnpost') - def tk_traverseToMenu(self, char): - self.tk.call('tk_traverseToMenu', self._w, char) - def tk_traverseWithinMenu(self, char): - self.tk.call('tk_traverseWithinMenu', self._w, char) - def tk_getMenuButtons(self): - return self.tk.call('tk_getMenuButtons', self._w) - def tk_nextMenu(self, count): - self.tk.call('tk_nextMenu', count) - def tk_nextMenuEntry(self, count): - self.tk.call('tk_nextMenuEntry', count) - def tk_invokeMenu(self): - self.tk.call('tk_invokeMenu', self._w) - def tk_firstMenu(self): - self.tk.call('tk_firstMenu', self._w) - def tk_mbButtonDown(self): - self.tk.call('tk_mbButtonDown', self._w) - def tk_popup(self, x, y, entry=""): - """Post the menu at position X,Y with entry ENTRY.""" - self.tk.call('tk_popup', self._w, x, y, entry) def activate(self, index): """Activate entry at INDEX.""" self.tk.call(self._w, 'activate', index) @@ -2905,10 +2872,14 @@ class Scrollbar(Widget): relief, repeatdelay, repeatinterval, takefocus, troughcolor, width.""" Widget.__init__(self, master, 'scrollbar', cnf, kw) - def activate(self, index): - """Display the element at INDEX with activebackground and activerelief. - INDEX can be "arrow1","slider" or "arrow2".""" - self.tk.call(self._w, 'activate', index) + def activate(self, index=None): + """Marks the element indicated by index as active. + The only index values understood by this method are "arrow1", + "slider", or "arrow2". If any other value is specified then no + element of the scrollbar will be active. If index is not specified, + the method returns the name of the element that is currently active, + or None if no element is active.""" + return self.tk.call(self._w, 'activate', index) or None def delta(self, deltax, deltay): """Return the fractional change of the scrollbar setting if it would be moved by DELTAX or DELTAY pixels.""" @@ -2926,10 +2897,10 @@ class Scrollbar(Widget): """Return the current fractional values (upper and lower end) of the slider position.""" return self._getdoubles(self.tk.call(self._w, 'get')) - def set(self, *args): + def set(self, first, last): """Set the fractional values of the slider position (upper and lower ends as value between 0 and 1).""" - self.tk.call((self._w, 'set') + args) + self.tk.call(self._w, 'set', first, last) @@ -2964,14 +2935,6 @@ class Text(Widget, XView, YView): box of the visible part of the character at the given index.""" return self._getints( self.tk.call(self._w, 'bbox', index)) or None - def tk_textSelectTo(self, index): - self.tk.call('tk_textSelectTo', self._w, index) - def tk_textBackspace(self): - self.tk.call('tk_textBackspace', self._w) - def tk_textIndexCloser(self, a, b, c): - self.tk.call('tk_textIndexCloser', self._w, a, b, c) - def tk_textResetAnchor(self, index): - self.tk.call('tk_textResetAnchor', self._w, index) def compare(self, index1, op, index2): """Return whether between index INDEX1 and index INDEX2 the relation OP is satisfied. OP is one of <, <=, ==, >=, >, or !=.""" @@ -3849,35 +3812,12 @@ class PanedWindow(Widget): """Returns an ordered list of the child panes.""" return self.tk.splitlist(self.tk.call(self._w, 'panes')) -###################################################################### -# Extensions: - -class Studbutton(Button): - def __init__(self, master=None, cnf={}, **kw): - Widget.__init__(self, master, 'studbutton', cnf, kw) - self.bind('<Any-Enter>', self.tkButtonEnter) - self.bind('<Any-Leave>', self.tkButtonLeave) - self.bind('<1>', self.tkButtonDown) - self.bind('<ButtonRelease-1>', self.tkButtonUp) - -class Tributton(Button): - def __init__(self, master=None, cnf={}, **kw): - Widget.__init__(self, master, 'tributton', cnf, kw) - self.bind('<Any-Enter>', self.tkButtonEnter) - self.bind('<Any-Leave>', self.tkButtonLeave) - self.bind('<1>', self.tkButtonDown) - self.bind('<ButtonRelease-1>', self.tkButtonUp) - self['fg'] = self['bg'] - self['activebackground'] = self['bg'] - -###################################################################### # Test: def _test(): root = Tk() text = "This is Tcl/Tk version %s" % TclVersion - if TclVersion >= 8.1: - text += "\nThis should be a cedilla: \xe7" + text += "\nThis should be a cedilla: \xe7" label = Label(root, text=text) label.pack() test = Button(root, text="Click me!", diff --git a/Lib/tkinter/test/test_tkinter/test_misc.py b/Lib/tkinter/test/test_tkinter/test_misc.py index d8de949..85ee2c7 100644 --- a/Lib/tkinter/test/test_tkinter/test_misc.py +++ b/Lib/tkinter/test/test_tkinter/test_misc.py @@ -7,6 +7,11 @@ support.requires('gui') class MiscTest(AbstractTkTest, unittest.TestCase): + def test_repr(self): + t = tkinter.Toplevel(self.root, name='top') + f = tkinter.Frame(t, name='child') + self.assertEqual(repr(f), '<tkinter.Frame object .top.child>') + def test_tk_setPalette(self): root = self.root root.tk_setPalette('black') diff --git a/Lib/tkinter/test/test_tkinter/test_widgets.py b/Lib/tkinter/test/test_tkinter/test_widgets.py index 58c8ea1..25b1a02 100644 --- a/Lib/tkinter/test/test_tkinter/test_widgets.py +++ b/Lib/tkinter/test/test_tkinter/test_widgets.py @@ -920,8 +920,9 @@ class ScrollbarTest(AbstractWidgetTest, unittest.TestCase): sb = self.create() for e in ('arrow1', 'slider', 'arrow2'): sb.activate(e) + self.assertEqual(sb.activate(), e) sb.activate('') - self.assertRaises(TypeError, sb.activate) + self.assertIsNone(sb.activate()) self.assertRaises(TypeError, sb.activate, 'arrow1', 'arrow2') def test_set(self): @@ -931,8 +932,8 @@ class ScrollbarTest(AbstractWidgetTest, unittest.TestCase): self.assertRaises(TclError, sb.set, 'abc', 'def') self.assertRaises(TclError, sb.set, 0.6, 'def') self.assertRaises(TclError, sb.set, 0.6, None) - self.assertRaises(TclError, sb.set, 0.6) - self.assertRaises(TclError, sb.set, 0.6, 0.7, 0.8) + self.assertRaises(TypeError, sb.set, 0.6) + self.assertRaises(TypeError, sb.set, 0.6, 0.7, 0.8) @add_standard_options(StandardOptionsTests) diff --git a/Lib/token.py b/Lib/token.py index 7470c8c..bdfcec8 100644 --- a/Lib/token.py +++ b/Lib/token.py @@ -60,11 +60,12 @@ DOUBLESTAREQUAL = 46 DOUBLESLASH = 47 DOUBLESLASHEQUAL = 48 AT = 49 -RARROW = 50 -ELLIPSIS = 51 -OP = 52 -ERRORTOKEN = 53 -N_TOKENS = 54 +ATEQUAL = 50 +RARROW = 51 +ELLIPSIS = 52 +OP = 53 +ERRORTOKEN = 54 +N_TOKENS = 55 NT_OFFSET = 256 #--end constants-- diff --git a/Lib/tokenize.py b/Lib/tokenize.py index 5b47ebd..0659c55 100644 --- a/Lib/tokenize.py +++ b/Lib/tokenize.py @@ -90,7 +90,8 @@ EXACT_TOKEN_TYPES = { '**=': DOUBLESTAREQUAL, '//': DOUBLESLASH, '//=': DOUBLESLASHEQUAL, - '@': AT + '@': AT, + '@=': ATEQUAL, } class TokenInfo(collections.namedtuple('TokenInfo', 'type string start end line')): @@ -149,7 +150,7 @@ String = group(StringPrefix + r"'[^\n'\\]*(?:\\.[^\n'\\]*)*'", # recognized as two instances of =). Operator = group(r"\*\*=?", r">>=?", r"<<=?", r"!=", r"//=?", r"->", - r"[+\-*/%&|^=<>]=?", + r"[+\-*/%&@|^=<>]=?", r"~") Bracket = '[][(){}]' @@ -185,7 +186,6 @@ endpats = {"'": Single, '"': Double, "rB'''": Single3, 'rB"""': Double3, "RB'''": Single3, 'RB"""': Double3, "u'''": Single3, 'u"""': Double3, - "R'''": Single3, 'R"""': Double3, "U'''": Single3, 'U"""': Double3, 'r': None, 'R': None, 'b': None, 'B': None, 'u': None, 'U': None} diff --git a/Lib/trace.py b/Lib/trace.py index 09fe9ee..fe84973 100755 --- a/Lib/trace.py +++ b/Lib/trace.py @@ -59,10 +59,7 @@ import gc import dis import pickle from warnings import warn as _warn -try: - from time import monotonic as _time -except ImportError: - from time import time as _time +from time import monotonic as _time try: import threading @@ -326,16 +323,17 @@ class CoverageResults: lnotab = _find_executable_linenos(filename) else: lnotab = {} + if lnotab: + source = linecache.getlines(filename) + coverpath = os.path.join(dir, modulename + ".cover") + with open(filename, 'rb') as fp: + encoding, _ = tokenize.detect_encoding(fp.readline) + n_hits, n_lines = self.write_results_file(coverpath, source, + lnotab, count, encoding) + if summary and n_lines: + percent = int(100 * n_hits / n_lines) + sums[modulename] = n_lines, percent, modulename, filename - source = linecache.getlines(filename) - coverpath = os.path.join(dir, modulename + ".cover") - with open(filename, 'rb') as fp: - encoding, _ = tokenize.detect_encoding(fp.readline) - n_hits, n_lines = self.write_results_file(coverpath, source, - lnotab, count, encoding) - if summary and n_lines: - percent = int(100 * n_hits / n_lines) - sums[modulename] = n_lines, percent, modulename, filename if summary and sums: print("lines cov% module (path)") diff --git a/Lib/traceback.py b/Lib/traceback.py index faf593a..72e1e2a 100644 --- a/Lib/traceback.py +++ b/Lib/traceback.py @@ -14,19 +14,12 @@ __all__ = ['extract_stack', 'extract_tb', 'format_exception', # Formatting and printing lists of traceback lines. # -def _format_list_iter(extracted_list): - for filename, lineno, name, line in extracted_list: - item = ' File "{}", line {}, in {}\n'.format(filename, lineno, name) - if line: - item = item + ' {}\n'.format(line.strip()) - yield item - def print_list(extracted_list, file=None): """Print the list of tuples as returned by extract_tb() or extract_stack() as a formatted stack trace to the given file.""" if file is None: file = sys.stderr - for item in _format_list_iter(extracted_list): + for item in StackSummary.from_list(extracted_list).format(): print(item, file=file, end="") def format_list(extracted_list): @@ -39,45 +32,12 @@ def format_list(extracted_list): the strings may contain internal newlines as well, for those items whose source text line is not None. """ - return list(_format_list_iter(extracted_list)) + return StackSummary.from_list(extracted_list).format() # # Printing and Extracting Tracebacks. # -# extractor takes curr and needs to return a tuple of: -# - Frame object -# - Line number -# - Next item (same type as curr) -# In practice, curr is either a traceback or a frame. -def _extract_tb_or_stack_iter(curr, limit, extractor): - if limit is None: - limit = getattr(sys, 'tracebacklimit', None) - - n = 0 - while curr is not None and (limit is None or n < limit): - f, lineno, next_item = extractor(curr) - co = f.f_code - filename = co.co_filename - name = co.co_name - - linecache.checkcache(filename) - line = linecache.getline(filename, lineno, f.f_globals) - - if line: - line = line.strip() - else: - line = None - - yield (filename, lineno, name, line) - curr = next_item - n += 1 - -def _extract_tb_iter(tb, limit): - return _extract_tb_or_stack_iter( - tb, limit, - operator.attrgetter("tb_frame", "tb_lineno", "tb_next")) - def print_tb(tb, limit=None, file=None): """Print up to 'limit' stack trace entries from the traceback 'tb'. @@ -90,7 +50,7 @@ def print_tb(tb, limit=None, file=None): def format_tb(tb, limit=None): """A shorthand for 'format_list(extract_tb(tb, limit))'.""" - return format_list(extract_tb(tb, limit=limit)) + return extract_tb(tb, limit=limit).format() def extract_tb(tb, limit=None): """Return list of up to limit pre-processed entries from traceback. @@ -103,7 +63,7 @@ def extract_tb(tb, limit=None): leading and trailing whitespace stripped; if the source is not available it is None. """ - return list(_extract_tb_iter(tb, limit=limit)) + return StackSummary.extract(walk_tb(tb), limit=limit) # # Exception formatting and output. @@ -111,47 +71,12 @@ def extract_tb(tb, limit=None): _cause_message = ( "\nThe above exception was the direct cause " - "of the following exception:\n") + "of the following exception:\n\n") _context_message = ( "\nDuring handling of the above exception, " - "another exception occurred:\n") - -def _iter_chain(exc, custom_tb=None, seen=None): - if seen is None: - seen = set() - seen.add(exc) - its = [] - context = exc.__context__ - cause = exc.__cause__ - if cause is not None and cause not in seen: - its.append(_iter_chain(cause, False, seen)) - its.append([(_cause_message, None)]) - elif (context is not None and - not exc.__suppress_context__ and - context not in seen): - its.append(_iter_chain(context, None, seen)) - its.append([(_context_message, None)]) - its.append([(exc, custom_tb or exc.__traceback__)]) - # itertools.chain is in an extension module and may be unavailable - for it in its: - yield from it - -def _format_exception_iter(etype, value, tb, limit, chain): - if chain: - values = _iter_chain(value, tb) - else: - values = [(value, tb)] - - for value, tb in values: - if isinstance(value, str): - # This is a cause/context message line - yield value + '\n' - continue - if tb: - yield 'Traceback (most recent call last):\n' - yield from _format_list_iter(_extract_tb_iter(tb, limit=limit)) - yield from _format_exception_only_iter(type(value), value) + "another exception occurred:\n\n") + def print_exception(etype, value, tb, limit=None, file=None, chain=True): """Print exception up to 'limit' stack trace entries from 'tb' to 'file'. @@ -164,11 +89,16 @@ def print_exception(etype, value, tb, limit=None, file=None, chain=True): occurred with a caret on the next line indicating the approximate position of the error. """ + # format_exception has ignored etype for some time, and code such as cgitb + # passes in bogus values as a result. For compatibility with such code we + # ignore it here (rather than in the new TracebackException API). if file is None: file = sys.stderr - for line in _format_exception_iter(etype, value, tb, limit, chain): + for line in TracebackException( + type(value), value, tb, limit=limit).format(chain=chain): print(line, file=file, end="") + def format_exception(etype, value, tb, limit=None, chain=True): """Format a stack trace and the exception information. @@ -178,7 +108,12 @@ def format_exception(etype, value, tb, limit=None, chain=True): these lines are concatenated and printed, exactly the same text is printed as does print_exception(). """ - return list(_format_exception_iter(etype, value, tb, limit, chain)) + # format_exception has ignored etype for some time, and code such as cgitb + # passes in bogus values as a result. For compatibility with such code we + # ignore it here (rather than in the new TracebackException API). + return list(TracebackException( + type(value), value, tb, limit=limit).format(chain=chain)) + def format_exception_only(etype, value): """Format the exception part of a traceback. @@ -196,46 +131,14 @@ def format_exception_only(etype, value): string in the list. """ - return list(_format_exception_only_iter(etype, value)) - -def _format_exception_only_iter(etype, value): - # Gracefully handle (the way Python 2.4 and earlier did) the case of - # being called with (None, None). - if etype is None: - yield _format_final_exc_line(etype, value) - return - - stype = etype.__name__ - smod = etype.__module__ - if smod not in ("__main__", "builtins"): - stype = smod + '.' + stype - - if not issubclass(etype, SyntaxError): - yield _format_final_exc_line(stype, value) - return - - # It was a syntax error; show exactly where the problem was found. - filename = value.filename or "<string>" - lineno = str(value.lineno) or '?' - yield ' File "{}", line {}\n'.format(filename, lineno) - - badline = value.text - offset = value.offset - if badline is not None: - yield ' {}\n'.format(badline.strip()) - if offset is not None: - caretspace = badline.rstrip('\n') - offset = min(len(caretspace), offset) - 1 - caretspace = caretspace[:offset].lstrip() - # non-space whitespace (likes tabs) must be kept for alignment - caretspace = ((c.isspace() and c or ' ') for c in caretspace) - yield ' {}^\n'.format(''.join(caretspace)) - msg = value.msg or "<no detail available>" - yield "{}: {}\n".format(stype, msg) + return list(TracebackException(etype, value, None).format_exception_only()) + + +# -- not offical API but folk probably use these two functions. def _format_final_exc_line(etype, value): valuestr = _some_str(value) - if value is None or not valuestr: + if value == 'None' or value is None or not valuestr: line = "%s\n" % etype else: line = "%s: %s\n" % (etype, valuestr) @@ -247,6 +150,8 @@ def _some_str(value): except: return '<unprintable %s object>' % type(value).__name__ +# -- + def print_exc(limit=None, file=None, chain=True): """Shorthand for 'print_exception(*sys.exc_info(), limit, file)'.""" print_exception(*sys.exc_info(), limit=limit, file=file, chain=chain) @@ -267,15 +172,6 @@ def print_last(limit=None, file=None, chain=True): # Printing and Extracting Stacks. # -def _extract_stack_iter(f, limit=None): - return _extract_tb_or_stack_iter( - f, limit, lambda f: (f, f.f_lineno, f.f_back)) - -def _get_stack(f): - if f is None: - f = sys._getframe().f_back.f_back - return f - def print_stack(f=None, limit=None, file=None): """Print a stack trace from its invocation point. @@ -283,11 +179,13 @@ def print_stack(f=None, limit=None, file=None): stack frame at which to start. The optional 'limit' and 'file' arguments have the same meaning as for print_exception(). """ - print_list(extract_stack(_get_stack(f), limit=limit), file=file) + print_list(extract_stack(f, limit=limit), file=file) + def format_stack(f=None, limit=None): """Shorthand for 'format_list(extract_stack(f, limit))'.""" - return format_list(extract_stack(_get_stack(f), limit=limit)) + return format_list(extract_stack(f, limit=limit)) + def extract_stack(f=None, limit=None): """Extract the raw traceback from the current stack frame. @@ -298,10 +196,11 @@ def extract_stack(f=None, limit=None): line number, function name, text), and the entries are in order from oldest to newest stack frame. """ - stack = list(_extract_stack_iter(_get_stack(f), limit=limit)) + stack = StackSummary.extract(walk_stack(f), limit=limit) stack.reverse() return stack + def clear_frames(tb): "Clear all references to local variables in the frames of a traceback." while tb is not None: @@ -311,3 +210,328 @@ def clear_frames(tb): # Ignore the exception raised if the frame is still executing. pass tb = tb.tb_next + + +class FrameSummary: + """A single frame from a traceback. + + - :attr:`filename` The filename for the frame. + - :attr:`lineno` The line within filename for the frame that was + active when the frame was captured. + - :attr:`name` The name of the function or method that was executing + when the frame was captured. + - :attr:`line` The text from the linecache module for the + of code that was running when the frame was captured. + - :attr:`locals` Either None if locals were not supplied, or a dict + mapping the name to the str() of the variable. + """ + + __slots__ = ('filename', 'lineno', 'name', '_line', 'locals') + + def __init__(self, filename, lineno, name, lookup_line=True, locals=None, + line=None): + """Construct a FrameSummary. + + :param lookup_line: If True, `linecache` is consulted for the source + code line. Otherwise, the line will be looked up when first needed. + :param locals: If supplied the frame locals, which will be captured as + strings. + :param line: If provided, use this instead of looking up the line in + the linecache. + """ + self.filename = filename + self.lineno = lineno + self.name = name + self._line = line + if lookup_line: + self.line + self.locals = \ + dict((k, str(v)) for k, v in locals.items()) if locals else None + + def __eq__(self, other): + return (self.filename == other.filename and + self.lineno == other.lineno and + self.name == other.name and + self.locals == other.locals) + + def __getitem__(self, pos): + return (self.filename, self.lineno, self.name, self.line)[pos] + + def __iter__(self): + return iter([self.filename, self.lineno, self.name, self.line]) + + def __repr__(self): + return "<FrameSummary file {filename}, line {lineno} in {name}>".format( + filename=self.filename, lineno=self.lineno, name=self.name) + + @property + def line(self): + if self._line is None: + self._line = linecache.getline(self.filename, self.lineno).strip() + return self._line + + +def walk_stack(f): + """Walk a stack yielding the frame and line number for each frame. + + This will follow f.f_back from the given frame. If no frame is given, the + current stack is used. Usually used with StackSummary.extract. + """ + if f is None: + f = sys._getframe().f_back.f_back + while f is not None: + yield f, f.f_lineno + f = f.f_back + + +def walk_tb(tb): + """Walk a traceback yielding the frame and line number for each frame. + + This will follow tb.tb_next (and thus is in the opposite order to + walk_stack). Usually used with StackSummary.extract. + """ + while tb is not None: + yield tb.tb_frame, tb.tb_lineno + tb = tb.tb_next + + +class StackSummary(list): + """A stack of frames.""" + + @classmethod + def extract(klass, frame_gen, limit=None, lookup_lines=True): + """Create a StackSummary from a traceback or stack object. + + :param frame_gen: A generator that yields (frame, lineno) tuples to + include in the stack. + :param limit: None to include all frames or the number of frames to + include. + :param lookup_lines: If True, lookup lines for each frame immediately, + otherwise lookup is deferred until the frame is rendered. + """ + if limit is None: + limit = getattr(sys, 'tracebacklimit', None) + + result = klass() + fnames = set() + for pos, (f, lineno) in enumerate(frame_gen): + if limit is not None and pos >= limit: + break + co = f.f_code + filename = co.co_filename + name = co.co_name + + fnames.add(filename) + linecache.lazycache(filename, f.f_globals) + # Must defer line lookups until we have called checkcache. + result.append(FrameSummary(filename, lineno, name, lookup_line=False)) + for filename in fnames: + linecache.checkcache(filename) + # If immediate lookup was desired, trigger lookups now. + if lookup_lines: + for f in result: + f.line + return result + + @classmethod + def from_list(klass, a_list): + """Create a StackSummary from a simple list of tuples. + + This method supports the older Python API. Each tuple should be a + 4-tuple with (filename, lineno, name, line) elements. + """ + if isinstance(a_list, StackSummary): + return StackSummary(a_list) + result = StackSummary() + for filename, lineno, name, line in a_list: + result.append(FrameSummary(filename, lineno, name, line=line)) + return result + + def format(self): + """Format the stack ready for printing. + + Returns a list of strings ready for printing. Each string in the + resulting list corresponds to a single frame from the stack. + Each string ends in a newline; the strings may contain internal + newlines as well, for those items with source text lines. + """ + result = [] + for filename, lineno, name, line in self: + item = ' File "{}", line {}, in {}\n'.format(filename, lineno, name) + if line: + item = item + ' {}\n'.format(line.strip()) + result.append(item) + return result + + +class TracebackException: + """An exception ready for rendering. + + The traceback module captures enough attributes from the original exception + to this intermediary form to ensure that no references are held, while + still being able to fully print or format it. + + Use `from_exception` to create TracebackException instances from exception + objects, or the constructor to create TracebackException instances from + individual components. + + - :attr:`__cause__` A TracebackException of the original *__cause__*. + - :attr:`__context__` A TracebackException of the original *__context__*. + - :attr:`__suppress_context__` The *__suppress_context__* value from the + original exception. + - :attr:`stack` A `StackSummary` representing the traceback. + - :attr:`exc_type` The class of the original traceback. + - :attr:`filename` For syntax errors - the filename where the error + occured. + - :attr:`lineno` For syntax errors - the linenumber where the error + occured. + - :attr:`text` For syntax errors - the text where the error + occured. + - :attr:`offset` For syntax errors - the offset into the text where the + error occured. + - :attr:`msg` For syntax errors - the compiler error message. + """ + + def __init__(self, exc_type, exc_value, exc_traceback, limit=None, + lookup_lines=True, _seen=None): + # NB: we need to accept exc_traceback, exc_value, exc_traceback to + # permit backwards compat with the existing API, otherwise we + # need stub thunk objects just to glue it together. + # Handle loops in __cause__ or __context__. + if _seen is None: + _seen = set() + _seen.add(exc_value) + # Gracefully handle (the way Python 2.4 and earlier did) the case of + # being called with no type or value (None, None, None). + if (exc_value and exc_value.__cause__ is not None + and exc_value.__cause__ not in _seen): + cause = TracebackException( + type(exc_value.__cause__), + exc_value.__cause__, + exc_value.__cause__.__traceback__, + limit=limit, + lookup_lines=False, + _seen=_seen) + else: + cause = None + if (exc_value and exc_value.__context__ is not None + and exc_value.__context__ not in _seen): + context = TracebackException( + type(exc_value.__context__), + exc_value.__context__, + exc_value.__context__.__traceback__, + limit=limit, + lookup_lines=False, + _seen=_seen) + else: + context = None + self.__cause__ = cause + self.__context__ = context + self.__suppress_context__ = \ + exc_value.__suppress_context__ if exc_value else False + # TODO: locals. + self.stack = StackSummary.extract( + walk_tb(exc_traceback), limit=limit, lookup_lines=lookup_lines) + self.exc_type = exc_type + # Capture now to permit freeing resources: only complication is in the + # unofficial API _format_final_exc_line + self._str = _some_str(exc_value) + if exc_type and issubclass(exc_type, SyntaxError): + # Handle SyntaxError's specially + self.filename = exc_value.filename + self.lineno = str(exc_value.lineno) + self.text = exc_value.text + self.offset = exc_value.offset + self.msg = exc_value.msg + if lookup_lines: + self._load_lines() + + @classmethod + def from_exception(self, exc, *args, **kwargs): + """Create a TracebackException from an exception.""" + return TracebackException( + type(exc), exc, exc.__traceback__, *args, **kwargs) + + def _load_lines(self): + """Private API. force all lines in the stack to be loaded.""" + for frame in self.stack: + frame.line + if self.__context__: + self.__context__._load_lines() + if self.__cause__: + self.__cause__._load_lines() + + def __eq__(self, other): + return self.__dict__ == other.__dict__ + + def __str__(self): + return self._str + + def format_exception_only(self): + """Format the exception part of the traceback. + + The return value is a generator of strings, each ending in a newline. + + Normally, the generator emits a single string; however, for + SyntaxError exceptions, it emites several lines that (when + printed) display detailed information about where the syntax + error occurred. + + The message indicating which exception occurred is always the last + string in the output. + """ + if self.exc_type is None: + yield _format_final_exc_line(None, self._str) + return + + stype = self.exc_type.__qualname__ + smod = self.exc_type.__module__ + if smod not in ("__main__", "builtins"): + stype = smod + '.' + stype + + if not issubclass(self.exc_type, SyntaxError): + yield _format_final_exc_line(stype, self._str) + return + + # It was a syntax error; show exactly where the problem was found. + filename = self.filename or "<string>" + lineno = str(self.lineno) or '?' + yield ' File "{}", line {}\n'.format(filename, lineno) + + badline = self.text + offset = self.offset + if badline is not None: + yield ' {}\n'.format(badline.strip()) + if offset is not None: + caretspace = badline.rstrip('\n') + offset = min(len(caretspace), offset) - 1 + caretspace = caretspace[:offset].lstrip() + # non-space whitespace (likes tabs) must be kept for alignment + caretspace = ((c.isspace() and c or ' ') for c in caretspace) + yield ' {}^\n'.format(''.join(caretspace)) + msg = self.msg or "<no detail available>" + yield "{}: {}\n".format(stype, msg) + + def format(self, chain=True): + """Format the exception. + + If chain is not *True*, *__cause__* and *__context__* will not be formatted. + + The return value is a generator of strings, each ending in a newline and + some containing internal newlines. `print_exception` is a wrapper around + this method which just prints the lines to a file. + + The message indicating which exception occurred is always the last + string in the output. + """ + if chain: + if self.__cause__ is not None: + yield from self.__cause__.format(chain=chain) + yield _cause_message + elif (self.__context__ is not None and + not self.__suppress_context__): + yield from self.__context__.format(chain=chain) + yield _context_message + yield 'Traceback (most recent call last):\n' + yield from self.stack.format() + yield from self.format_exception_only() diff --git a/Lib/turtledemo/__main__.py b/Lib/turtledemo/__main__.py index 106d058..106d058 100755..100644 --- a/Lib/turtledemo/__main__.py +++ b/Lib/turtledemo/__main__.py diff --git a/Lib/turtledemo/sorting_animate.py b/Lib/turtledemo/sorting_animate.py new file mode 100644 index 0000000..d25a0ab --- /dev/null +++ b/Lib/turtledemo/sorting_animate.py @@ -0,0 +1,204 @@ +#!/usr/bin/env python3 +""" + + sorting_animation.py + +A minimal sorting algorithm animation: +Sorts a shelf of 10 blocks using insertion +sort, selection sort and quicksort. + +Shelfs are implemented using builtin lists. + +Blocks are turtles with shape "square", but +stretched to rectangles by shapesize() + --------------------------------------- + To exit press space button + --------------------------------------- +""" +from turtle import * +import random + + +class Block(Turtle): + + def __init__(self, size): + self.size = size + Turtle.__init__(self, shape="square", visible=False) + self.pu() + self.shapesize(size * 1.5, 1.5, 2) # square-->rectangle + self.fillcolor("black") + self.st() + + def glow(self): + self.fillcolor("red") + + def unglow(self): + self.fillcolor("black") + + def __repr__(self): + return "Block size: {0}".format(self.size) + + +class Shelf(list): + + def __init__(self, y): + "create a shelf. y is y-position of first block" + self.y = y + self.x = -150 + + def push(self, d): + width, _, _ = d.shapesize() + # align blocks by the bottom edge + y_offset = width / 2 * 20 + d.sety(self.y + y_offset) + d.setx(self.x + 34 * len(self)) + self.append(d) + + def _close_gap_from_i(self, i): + for b in self[i:]: + xpos, _ = b.pos() + b.setx(xpos - 34) + + def _open_gap_from_i(self, i): + for b in self[i:]: + xpos, _ = b.pos() + b.setx(xpos + 34) + + def pop(self, key): + b = list.pop(self, key) + b.glow() + b.sety(200) + self._close_gap_from_i(key) + return b + + def insert(self, key, b): + self._open_gap_from_i(key) + list.insert(self, key, b) + b.setx(self.x + 34 * key) + width, _, _ = b.shapesize() + # align blocks by the bottom edge + y_offset = width / 2 * 20 + b.sety(self.y + y_offset) + b.unglow() + +def isort(shelf): + length = len(shelf) + for i in range(1, length): + hole = i + while hole > 0 and shelf[i].size < shelf[hole - 1].size: + hole = hole - 1 + shelf.insert(hole, shelf.pop(i)) + return + +def ssort(shelf): + length = len(shelf) + for j in range(0, length - 1): + imin = j + for i in range(j + 1, length): + if shelf[i].size < shelf[imin].size: + imin = i + if imin != j: + shelf.insert(j, shelf.pop(imin)) + +def partition(shelf, left, right, pivot_index): + pivot = shelf[pivot_index] + shelf.insert(right, shelf.pop(pivot_index)) + store_index = left + for i in range(left, right): # range is non-inclusive of ending value + if shelf[i].size < pivot.size: + shelf.insert(store_index, shelf.pop(i)) + store_index = store_index + 1 + shelf.insert(store_index, shelf.pop(right)) # move pivot to correct position + return store_index + +def qsort(shelf, left, right): + if left < right: + pivot_index = left + pivot_new_index = partition(shelf, left, right, pivot_index) + qsort(shelf, left, pivot_new_index - 1) + qsort(shelf, pivot_new_index + 1, right) + +def randomize(): + disable_keys() + clear() + target = list(range(10)) + random.shuffle(target) + for i, t in enumerate(target): + for j in range(i, len(s)): + if s[j].size == t + 1: + s.insert(i, s.pop(j)) + show_text(instructions1) + show_text(instructions2, line=1) + enable_keys() + +def show_text(text, line=0): + line = 20 * line + goto(0,-250 - line) + write(text, align="center", font=("Courier", 16, "bold")) + +def start_ssort(): + disable_keys() + clear() + show_text("Selection Sort") + ssort(s) + clear() + show_text(instructions1) + show_text(instructions2, line=1) + enable_keys() + +def start_isort(): + disable_keys() + clear() + show_text("Insertion Sort") + isort(s) + clear() + show_text(instructions1) + show_text(instructions2, line=1) + enable_keys() + +def start_qsort(): + disable_keys() + clear() + show_text("Quicksort") + qsort(s, 0, len(s) - 1) + clear() + show_text(instructions1) + show_text(instructions2, line=1) + enable_keys() + +def init_shelf(): + global s + s = Shelf(-200) + vals = (4, 2, 8, 9, 1, 5, 10, 3, 7, 6) + for i in vals: + s.push(Block(i)) + +def disable_keys(): + onkey(None, "s") + onkey(None, "i") + onkey(None, "q") + onkey(None, "r") + +def enable_keys(): + onkey(start_isort, "i") + onkey(start_ssort, "s") + onkey(start_qsort, "q") + onkey(randomize, "r") + onkey(bye, "space") + +def main(): + getscreen().clearscreen() + ht(); penup() + init_shelf() + show_text(instructions1) + show_text(instructions2, line=1) + enable_keys() + listen() + return "EVENTLOOP" + +instructions1 = "press i for insertion sort, s for selection sort, q for quicksort" +instructions2 = "spacebar to quit, r to randomize" + +if __name__=="__main__": + msg = main() + mainloop() diff --git a/Lib/unittest/__init__.py b/Lib/unittest/__init__.py index a5d50af..f6d7ae2 100644 --- a/Lib/unittest/__init__.py +++ b/Lib/unittest/__init__.py @@ -67,3 +67,12 @@ from .signals import installHandler, registerResult, removeResult, removeHandler # deprecated _TextTestResult = TextTestResult + +# There are no tests here, so don't try to run anything discovered from +# introspecting the symbols (e.g. FunctionTestCase). Instead, all our +# tests come from within unittest.test. +def load_tests(loader, tests, pattern): + import os.path + # top level directory cached on loader instance + this_dir = os.path.dirname(__file__) + return loader.discover(start_dir=this_dir, pattern=pattern) diff --git a/Lib/unittest/loader.py b/Lib/unittest/loader.py index 808c50e..8ee6c56 100644 --- a/Lib/unittest/loader.py +++ b/Lib/unittest/loader.py @@ -6,6 +6,7 @@ import sys import traceback import types import functools +import warnings from fnmatch import fnmatch @@ -20,19 +21,22 @@ VALID_MODULE_NAME = re.compile(r'[_a-z]\w*\.py$', re.IGNORECASE) def _make_failed_import_test(name, suiteClass): - message = 'Failed to import test module: %s\n%s' % (name, traceback.format_exc()) + message = 'Failed to import test module: %s\n%s' % ( + name, traceback.format_exc()) return _make_failed_test('ModuleImportFailure', name, ImportError(message), - suiteClass) + suiteClass, message) def _make_failed_load_tests(name, exception, suiteClass): - return _make_failed_test('LoadTestsFailure', name, exception, suiteClass) + message = 'Failed to call load_tests:\n%s' % (traceback.format_exc(),) + return _make_failed_test( + 'LoadTestsFailure', name, exception, suiteClass, message) -def _make_failed_test(classname, methodname, exception, suiteClass): +def _make_failed_test(classname, methodname, exception, suiteClass, message): def testFailure(self): raise exception attrs = {methodname: testFailure} TestClass = type(classname, (case.TestCase,), attrs) - return suiteClass((TestClass(methodname),)) + return suiteClass((TestClass(methodname),)), message def _make_skipped_test(methodname, exception, suiteClass): @case.skip(str(exception)) @@ -58,6 +62,13 @@ class TestLoader(object): suiteClass = suite.TestSuite _top_level_dir = None + def __init__(self): + super(TestLoader, self).__init__() + self.errors = [] + # Tracks packages which we have called into via load_tests, to + # avoid infinite re-entrancy. + self._loading_packages = set() + def loadTestsFromTestCase(self, testCaseClass): """Return a suite of all tests cases contained in testCaseClass""" if issubclass(testCaseClass, suite.TestSuite): @@ -70,8 +81,30 @@ class TestLoader(object): loaded_suite = self.suiteClass(map(testCaseClass, testCaseNames)) return loaded_suite - def loadTestsFromModule(self, module, use_load_tests=True): + # XXX After Python 3.5, remove backward compatibility hacks for + # use_load_tests deprecation via *args and **kws. See issue 16662. + def loadTestsFromModule(self, module, *args, pattern=None, **kws): """Return a suite of all tests cases contained in the given module""" + # This method used to take an undocumented and unofficial + # use_load_tests argument. For backward compatibility, we still + # accept the argument (which can also be the first position) but we + # ignore it and issue a deprecation warning if it's present. + if len(args) > 0 or 'use_load_tests' in kws: + warnings.warn('use_load_tests is deprecated and ignored', + DeprecationWarning) + kws.pop('use_load_tests', None) + if len(args) > 1: + # Complain about the number of arguments, but don't forget the + # required `module` argument. + complaint = len(args) + 1 + raise TypeError('loadTestsFromModule() takes 1 positional argument but {} were given'.format(complaint)) + if len(kws) != 0: + # Since the keyword arguments are unsorted (see PEP 468), just + # pick the alphabetically sorted first argument to complain about, + # if multiple were given. At least the error message will be + # predictable. + complaint = sorted(kws)[0] + raise TypeError("loadTestsFromModule() got an unexpected keyword argument '{}'".format(complaint)) tests = [] for name in dir(module): obj = getattr(module, name) @@ -80,12 +113,14 @@ class TestLoader(object): load_tests = getattr(module, 'load_tests', None) tests = self.suiteClass(tests) - if use_load_tests and load_tests is not None: + if load_tests is not None: try: - return load_tests(self, tests, None) + return load_tests(self, tests, pattern) except Exception as e: - return _make_failed_load_tests(module.__name__, e, - self.suiteClass) + error_case, error_message = _make_failed_load_tests( + module.__name__, e, self.suiteClass) + self.errors.append(error_message) + return error_case return tests def loadTestsFromName(self, name, module=None): @@ -98,20 +133,47 @@ class TestLoader(object): The method optionally resolves the names relative to a given module. """ parts = name.split('.') + error_case, error_message = None, None if module is None: parts_copy = parts[:] while parts_copy: try: - module = __import__('.'.join(parts_copy)) + module_name = '.'.join(parts_copy) + module = __import__(module_name) break except ImportError: - del parts_copy[-1] + next_attribute = parts_copy.pop() + # Last error so we can give it to the user if needed. + error_case, error_message = _make_failed_import_test( + next_attribute, self.suiteClass) if not parts_copy: - raise + # Even the top level import failed: report that error. + self.errors.append(error_message) + return error_case parts = parts[1:] obj = module for part in parts: - parent, obj = obj, getattr(obj, part) + try: + parent, obj = obj, getattr(obj, part) + except AttributeError as e: + # We can't traverse some part of the name. + if (getattr(obj, '__path__', None) is not None + and error_case is not None): + # This is a package (no __path__ per importlib docs), and we + # encountered an error importing something. We cannot tell + # the difference between package.WrongNameTestClass and + # package.wrong_module_name so we just report the + # ImportError - it is more informative. + self.errors.append(error_message) + return error_case + else: + # Otherwise, we signal that an AttributeError has occurred. + error_case, error_message = _make_failed_test( + 'AttributeError', part, e, self.suiteClass, + 'Failed to access attribute:\n%s' % ( + traceback.format_exc(),)) + self.errors.append(error_message) + return error_case if isinstance(obj, types.ModuleType): return self.loadTestsFromModule(obj) @@ -170,9 +232,13 @@ class TestLoader(object): If a test package name (directory with '__init__.py') matches the pattern then the package will be checked for a 'load_tests' function. If - this exists then it will be called with loader, tests, pattern. + this exists then it will be called with (loader, tests, pattern) unless + the package has already had load_tests called from the same discovery + invocation, in which case the package module object is not scanned for + tests - this ensures that when a package uses discover to further + discover child tests that infinite recursion does not happen. - If load_tests exists then discovery does *not* recurse into the package, + If load_tests exists then discovery does *not* recurse into the package, load_tests is responsible for loading all tests in the package. The pattern is deliberately not stored as a loader attribute so that @@ -277,6 +343,8 @@ class TestLoader(object): return os.path.dirname(full_path) def _get_name_from_path(self, path): + if path == self._top_level_dir: + return '.' path = _jython_aware_splitext(os.path.normpath(path)) _relpath = os.path.relpath(path, self._top_level_dir) @@ -296,63 +364,111 @@ class TestLoader(object): def _find_tests(self, start_dir, pattern, namespace=False): """Used by discovery. Yields test suites it loads.""" + # Handle the __init__ in this package + name = self._get_name_from_path(start_dir) + # name is '.' when start_dir == top_level_dir (and top_level_dir is by + # definition not a package). + if name != '.' and name not in self._loading_packages: + # name is in self._loading_packages while we have called into + # loadTestsFromModule with name. + tests, should_recurse = self._find_test_path( + start_dir, pattern, namespace) + if tests is not None: + yield tests + if not should_recurse: + # Either an error occured, or load_tests was used by the + # package. + return + # Handle the contents. paths = sorted(os.listdir(start_dir)) - for path in paths: full_path = os.path.join(start_dir, path) - if os.path.isfile(full_path): - if not VALID_MODULE_NAME.match(path): - # valid Python identifiers only - continue - if not self._match_path(path, full_path, pattern): - continue - # if the test file matches, load it + tests, should_recurse = self._find_test_path( + full_path, pattern, namespace) + if tests is not None: + yield tests + if should_recurse: + # we found a package that didn't use load_tests. name = self._get_name_from_path(full_path) + self._loading_packages.add(name) try: - module = self._get_module_from_name(name) - except case.SkipTest as e: - yield _make_skipped_test(name, e, self.suiteClass) - except: - yield _make_failed_import_test(name, self.suiteClass) - else: - mod_file = os.path.abspath(getattr(module, '__file__', full_path)) - realpath = _jython_aware_splitext(os.path.realpath(mod_file)) - fullpath_noext = _jython_aware_splitext(os.path.realpath(full_path)) - if realpath.lower() != fullpath_noext.lower(): - module_dir = os.path.dirname(realpath) - mod_name = _jython_aware_splitext(os.path.basename(full_path)) - expected_dir = os.path.dirname(full_path) - msg = ("%r module incorrectly imported from %r. Expected %r. " - "Is this module globally installed?") - raise ImportError(msg % (mod_name, module_dir, expected_dir)) - yield self.loadTestsFromModule(module) - elif os.path.isdir(full_path): - if (not namespace and - not os.path.isfile(os.path.join(full_path, '__init__.py'))): - continue - - load_tests = None - tests = None - if fnmatch(path, pattern): - # only check load_tests if the package directory itself matches the filter - name = self._get_name_from_path(full_path) - package = self._get_module_from_name(name) - load_tests = getattr(package, 'load_tests', None) - tests = self.loadTestsFromModule(package, use_load_tests=False) - - if load_tests is None: - if tests is not None: - # tests loaded from package file - yield tests - # recurse into the package - yield from self._find_tests(full_path, pattern, - namespace=namespace) - else: - try: - yield load_tests(self, tests, pattern) - except Exception as e: - yield _make_failed_load_tests(package.__name__, e, - self.suiteClass) + yield from self._find_tests(full_path, pattern, namespace) + finally: + self._loading_packages.discard(name) + + def _find_test_path(self, full_path, pattern, namespace=False): + """Used by discovery. + + Loads tests from a single file, or a directories' __init__.py when + passed the directory. + + Returns a tuple (None_or_tests_from_file, should_recurse). + """ + basename = os.path.basename(full_path) + if os.path.isfile(full_path): + if not VALID_MODULE_NAME.match(basename): + # valid Python identifiers only + return None, False + if not self._match_path(basename, full_path, pattern): + return None, False + # if the test file matches, load it + name = self._get_name_from_path(full_path) + try: + module = self._get_module_from_name(name) + except case.SkipTest as e: + return _make_skipped_test(name, e, self.suiteClass), False + except: + error_case, error_message = \ + _make_failed_import_test(name, self.suiteClass) + self.errors.append(error_message) + return error_case, False + else: + mod_file = os.path.abspath( + getattr(module, '__file__', full_path)) + realpath = _jython_aware_splitext( + os.path.realpath(mod_file)) + fullpath_noext = _jython_aware_splitext( + os.path.realpath(full_path)) + if realpath.lower() != fullpath_noext.lower(): + module_dir = os.path.dirname(realpath) + mod_name = _jython_aware_splitext( + os.path.basename(full_path)) + expected_dir = os.path.dirname(full_path) + msg = ("%r module incorrectly imported from %r. Expected " + "%r. Is this module globally installed?") + raise ImportError( + msg % (mod_name, module_dir, expected_dir)) + return self.loadTestsFromModule(module, pattern=pattern), False + elif os.path.isdir(full_path): + if (not namespace and + not os.path.isfile(os.path.join(full_path, '__init__.py'))): + return None, False + + load_tests = None + tests = None + name = self._get_name_from_path(full_path) + try: + package = self._get_module_from_name(name) + except case.SkipTest as e: + return _make_skipped_test(name, e, self.suiteClass), False + except: + error_case, error_message = \ + _make_failed_import_test(name, self.suiteClass) + self.errors.append(error_message) + return error_case, False + else: + load_tests = getattr(package, 'load_tests', None) + # Mark this package as being in load_tests (possibly ;)) + self._loading_packages.add(name) + try: + tests = self.loadTestsFromModule(package, pattern=pattern) + if load_tests is not None: + # loadTestsFromModule(package) has loaded tests for us. + return tests, False + return tests, True + finally: + self._loading_packages.discard(name) + defaultTestLoader = TestLoader() diff --git a/Lib/unittest/mock.py b/Lib/unittest/mock.py index 5555774..3b7c157 100644 --- a/Lib/unittest/mock.py +++ b/Lib/unittest/mock.py @@ -27,9 +27,13 @@ __version__ = '1.0' import inspect import pprint import sys +import builtins +from types import ModuleType from functools import wraps, partial +_builtins = {name for name in dir(builtins) if not name.startswith('_')} + BaseExceptions = (BaseException,) if 'java' in sys.platform: # jython @@ -271,13 +275,11 @@ def _copy(value): return value -_allowed_names = set( - [ - 'return_value', '_mock_return_value', 'side_effect', - '_mock_side_effect', '_mock_parent', '_mock_new_parent', - '_mock_name', '_mock_new_name' - ] -) +_allowed_names = { + 'return_value', '_mock_return_value', 'side_effect', + '_mock_side_effect', '_mock_parent', '_mock_new_parent', + '_mock_name', '_mock_new_name' +} def _delegating_property(name): @@ -375,7 +377,7 @@ class NonCallableMock(Base): def __init__( self, spec=None, wraps=None, name=None, spec_set=None, parent=None, _spec_state=None, _new_name='', _new_parent=None, - _spec_as_instance=False, _eat_self=None, **kwargs + _spec_as_instance=False, _eat_self=None, unsafe=False, **kwargs ): if _new_parent is None: _new_parent = parent @@ -405,6 +407,7 @@ class NonCallableMock(Base): __dict__['_mock_mock_calls'] = _CallList() __dict__['method_calls'] = _CallList() + __dict__['_mock_unsafe'] = unsafe if kwargs: self.configure_mock(**kwargs) @@ -561,13 +564,16 @@ class NonCallableMock(Base): def __getattr__(self, name): - if name == '_mock_methods': + if name in {'_mock_methods', '_mock_unsafe'}: raise AttributeError(name) elif self._mock_methods is not None: if name not in self._mock_methods or name in _all_magics: raise AttributeError("Mock object has no attribute %r" % name) elif _is_magic(name): raise AttributeError(name) + if not self._mock_unsafe: + if name.startswith(('assert', 'assret')): + raise AttributeError(name) result = self._mock_children.get(name) if result is _deleted: @@ -750,6 +756,14 @@ class NonCallableMock(Base): else: return _call + def assert_not_called(_mock_self): + """assert that the mock was never called. + """ + self = _mock_self + if self.call_count != 0: + msg = ("Expected '%s' to not have been called. Called %s times." % + (self._mock_name or 'mock', self.call_count)) + raise AssertionError(msg) def assert_called_with(_mock_self, *args, **kwargs): """assert that the mock was called with the specified arguments. @@ -1166,6 +1180,9 @@ class _patch(object): else: local = True + if name in _builtins and isinstance(target, ModuleType): + self.create = True + if not self.create and original is DEFAULT: raise AttributeError( "%s does not have the attribute %r" % (target, name) @@ -1660,11 +1677,12 @@ right = ' '.join('r%s' % n for n in numerics.split()) # (as they are metaclass methods) # __del__ is not supported at all as it causes problems if it exists -_non_defaults = set('__%s__' % method for method in [ - 'get', 'set', 'delete', 'reversed', 'missing', 'reduce', 'reduce_ex', - 'getinitargs', 'getnewargs', 'getstate', 'setstate', 'getformat', - 'setformat', 'repr', 'dir', 'subclasses', 'format', -]) +_non_defaults = { + '__get__', '__set__', '__delete__', '__reversed__', '__missing__', + '__reduce__', '__reduce_ex__', '__getinitargs__', '__getnewargs__', + '__getstate__', '__setstate__', '__getformat__', '__setformat__', + '__repr__', '__dir__', '__subclasses__', '__format__', +} def _get_method(name, func): @@ -1675,19 +1693,19 @@ def _get_method(name, func): return method -_magics = set( +_magics = { '__%s__' % method for method in ' '.join([magic_methods, numerics, inplace, right]).split() -) +} _all_magics = _magics | _non_defaults -_unsupported_magics = set([ +_unsupported_magics = { '__getattr__', '__setattr__', '__init__', '__new__', '__prepare__' '__instancecheck__', '__subclasscheck__', '__del__' -]) +} _calculate_return_value = { '__hash__': lambda self: object.__hash__(self), @@ -1875,7 +1893,7 @@ def _format_call_signature(name, args, kwargs): formatted_args = '' args_string = ', '.join([repr(arg) for arg in args]) kwargs_string = ', '.join([ - '%s=%r' % (key, value) for key, value in kwargs.items() + '%s=%r' % (key, value) for key, value in sorted(kwargs.items()) ]) if args_string: formatted_args = args_string @@ -1997,10 +2015,6 @@ class _Call(tuple): return (other_args, other_kwargs) == (self_args, self_kwargs) - def __ne__(self, other): - return not self.__eq__(other) - - def __call__(self, *args, **kwargs): if self.name is None: return _Call(('', args, kwargs), name='()') @@ -2016,6 +2030,12 @@ class _Call(tuple): return _Call(name=name, parent=self, from_kall=False) + def count(self, *args, **kwargs): + return self.__getattr__('count')(*args, **kwargs) + + def index(self, *args, **kwargs): + return self.__getattr__('index')(*args, **kwargs) + def __repr__(self): if not self.from_kall: name = self.name or 'call' diff --git a/Lib/unittest/test/test_case.py b/Lib/unittest/test/test_case.py index c7ff3b0..503ad2f 100644 --- a/Lib/unittest/test/test_case.py +++ b/Lib/unittest/test/test_case.py @@ -1103,12 +1103,9 @@ test case except self.failureException as e: # need to remove the first line of the error message error = str(e).split('\n', 1)[1] + self.assertEqual(sample_text_error, error) - # no fair testing ourself with ourself, and assertEqual is used for strings - # so can't use assertEqual either. Just use assertTrue. - self.assertTrue(sample_text_error == error) - - def testAsertEqualSingleLine(self): + def testAssertEqualSingleLine(self): sample_text = "laden swallows fly slowly" revised_sample_text = "unladen swallows fly quickly" sample_text_error = """\ @@ -1120,8 +1117,9 @@ test case try: self.assertEqual(sample_text, revised_sample_text) except self.failureException as e: + # need to remove the first line of the error message error = str(e).split('\n', 1)[1] - self.assertTrue(sample_text_error == error) + self.assertEqual(sample_text_error, error) def testAssertIsNone(self): self.assertIsNone(None) diff --git a/Lib/unittest/test/test_discovery.py b/Lib/unittest/test/test_discovery.py index abb9066..4f61314 100644 --- a/Lib/unittest/test/test_discovery.py +++ b/Lib/unittest/test/test_discovery.py @@ -1,4 +1,5 @@ -import os +import os.path +from os.path import abspath import re import sys import types @@ -68,7 +69,13 @@ class TestDiscovery(unittest.TestCase): self.addCleanup(restore_isfile) loader._get_module_from_name = lambda path: path + ' module' - loader.loadTestsFromModule = lambda module: module + ' tests' + orig_load_tests = loader.loadTestsFromModule + def loadTestsFromModule(module, pattern=None): + # This is where load_tests is called. + base = orig_load_tests(module, pattern=pattern) + return base + [module + ' tests'] + loader.loadTestsFromModule = loadTestsFromModule + loader.suiteClass = lambda thing: thing top_level = os.path.abspath('/foo') loader._top_level_dir = top_level @@ -76,9 +83,9 @@ class TestDiscovery(unittest.TestCase): # The test suites found should be sorted alphabetically for reliable # execution order. - expected = [name + ' module tests' for name in - ('test1', 'test2')] - expected.extend([('test_dir.%s' % name) + ' module tests' for name in + expected = [[name + ' module tests'] for name in + ('test1', 'test2', 'test_dir')] + expected.extend([[('test_dir.%s' % name) + ' module tests'] for name in ('test3', 'test4')]) self.assertEqual(suite, expected) @@ -116,34 +123,204 @@ class TestDiscovery(unittest.TestCase): if os.path.basename(path) == 'test_directory': def load_tests(loader, tests, pattern): self.load_tests_args.append((loader, tests, pattern)) - return 'load_tests' + return [self.path + ' load_tests'] self.load_tests = load_tests def __eq__(self, other): return self.path == other.path loader._get_module_from_name = lambda name: Module(name) - def loadTestsFromModule(module, use_load_tests): - if use_load_tests: - raise self.failureException('use_load_tests should be False for packages') - return module.path + ' module tests' + orig_load_tests = loader.loadTestsFromModule + def loadTestsFromModule(module, pattern=None): + # This is where load_tests is called. + base = orig_load_tests(module, pattern=pattern) + return base + [module.path + ' module tests'] loader.loadTestsFromModule = loadTestsFromModule + loader.suiteClass = lambda thing: thing loader._top_level_dir = '/foo' # this time no '.py' on the pattern so that it can match # a test package suite = list(loader._find_tests('/foo', 'test*')) - # We should have loaded tests from the test_directory package by calling load_tests - # and directly from the test_directory2 package + # We should have loaded tests from the a_directory and test_directory2 + # directly and via load_tests for the test_directory package, which + # still calls the baseline module loader. self.assertEqual(suite, - ['load_tests', 'test_directory2' + ' module tests']) + [['a_directory module tests'], + ['test_directory load_tests', + 'test_directory module tests'], + ['test_directory2 module tests']]) + + # The test module paths should be sorted for reliable execution order - self.assertEqual(Module.paths, ['test_directory', 'test_directory2']) + self.assertEqual(Module.paths, + ['a_directory', 'test_directory', 'test_directory2']) # load_tests should have been called once with loader, tests and pattern + # (but there are no tests in our stub module itself, so thats [] at the + # time of call. + self.assertEqual(Module.load_tests_args, + [(loader, [], 'test*')]) + + def test_find_tests_default_calls_package_load_tests(self): + loader = unittest.TestLoader() + + original_listdir = os.listdir + def restore_listdir(): + os.listdir = original_listdir + original_isfile = os.path.isfile + def restore_isfile(): + os.path.isfile = original_isfile + original_isdir = os.path.isdir + def restore_isdir(): + os.path.isdir = original_isdir + + directories = ['a_directory', 'test_directory', 'test_directory2'] + path_lists = [directories, [], [], []] + os.listdir = lambda path: path_lists.pop(0) + self.addCleanup(restore_listdir) + + os.path.isdir = lambda path: True + self.addCleanup(restore_isdir) + + os.path.isfile = lambda path: os.path.basename(path) not in directories + self.addCleanup(restore_isfile) + + class Module(object): + paths = [] + load_tests_args = [] + + def __init__(self, path): + self.path = path + self.paths.append(path) + if os.path.basename(path) == 'test_directory': + def load_tests(loader, tests, pattern): + self.load_tests_args.append((loader, tests, pattern)) + return [self.path + ' load_tests'] + self.load_tests = load_tests + + def __eq__(self, other): + return self.path == other.path + + loader._get_module_from_name = lambda name: Module(name) + orig_load_tests = loader.loadTestsFromModule + def loadTestsFromModule(module, pattern=None): + # This is where load_tests is called. + base = orig_load_tests(module, pattern=pattern) + return base + [module.path + ' module tests'] + loader.loadTestsFromModule = loadTestsFromModule + loader.suiteClass = lambda thing: thing + + loader._top_level_dir = '/foo' + # this time no '.py' on the pattern so that it can match + # a test package + suite = list(loader._find_tests('/foo', 'test*.py')) + + # We should have loaded tests from the a_directory and test_directory2 + # directly and via load_tests for the test_directory package, which + # still calls the baseline module loader. + self.assertEqual(suite, + [['a_directory module tests'], + ['test_directory load_tests', + 'test_directory module tests'], + ['test_directory2 module tests']]) + # The test module paths should be sorted for reliable execution order + self.assertEqual(Module.paths, + ['a_directory', 'test_directory', 'test_directory2']) + + + # load_tests should have been called once with loader, tests and pattern + self.assertEqual(Module.load_tests_args, + [(loader, [], 'test*.py')]) + + def test_find_tests_customise_via_package_pattern(self): + # This test uses the example 'do-nothing' load_tests from + # https://docs.python.org/3/library/unittest.html#load-tests-protocol + # to make sure that that actually works. + # Housekeeping + original_listdir = os.listdir + def restore_listdir(): + os.listdir = original_listdir + self.addCleanup(restore_listdir) + original_isfile = os.path.isfile + def restore_isfile(): + os.path.isfile = original_isfile + self.addCleanup(restore_isfile) + original_isdir = os.path.isdir + def restore_isdir(): + os.path.isdir = original_isdir + self.addCleanup(restore_isdir) + self.addCleanup(sys.path.remove, abspath('/foo')) + + # Test data: we expect the following: + # a listdir to find our package, and a isfile and isdir check on it. + # a module-from-name call to turn that into a module + # followed by load_tests. + # then our load_tests will call discover() which is messy + # but that finally chains into find_tests again for the child dir - + # which is why we don't have a infinite loop. + # We expect to see: + # the module load tests for both package and plain module called, + # and the plain module result nested by the package module load_tests + # indicating that it was processed and could have been mutated. + vfs = {abspath('/foo'): ['my_package'], + abspath('/foo/my_package'): ['__init__.py', 'test_module.py']} + def list_dir(path): + return list(vfs[path]) + os.listdir = list_dir + os.path.isdir = lambda path: not path.endswith('.py') + os.path.isfile = lambda path: path.endswith('.py') + + class Module(object): + paths = [] + load_tests_args = [] + + def __init__(self, path): + self.path = path + self.paths.append(path) + if path.endswith('test_module'): + def load_tests(loader, tests, pattern): + self.load_tests_args.append((loader, tests, pattern)) + return [self.path + ' load_tests'] + else: + def load_tests(loader, tests, pattern): + self.load_tests_args.append((loader, tests, pattern)) + # top level directory cached on loader instance + __file__ = '/foo/my_package/__init__.py' + this_dir = os.path.dirname(__file__) + pkg_tests = loader.discover( + start_dir=this_dir, pattern=pattern) + return [self.path + ' load_tests', tests + ] + pkg_tests + self.load_tests = load_tests + + def __eq__(self, other): + return self.path == other.path + + loader = unittest.TestLoader() + loader._get_module_from_name = lambda name: Module(name) + loader.suiteClass = lambda thing: thing + + loader._top_level_dir = abspath('/foo') + # this time no '.py' on the pattern so that it can match + # a test package + suite = list(loader._find_tests(abspath('/foo'), 'test*.py')) + + # We should have loaded tests from both my_package and + # my_pacakge.test_module, and also run the load_tests hook in both. + # (normally this would be nested TestSuites.) + self.assertEqual(suite, + [['my_package load_tests', [], + ['my_package.test_module load_tests']]]) + # Parents before children. + self.assertEqual(Module.paths, + ['my_package', 'my_package.test_module']) + + # load_tests should have been called twice with loader, tests and pattern self.assertEqual(Module.load_tests_args, - [(loader, 'test_directory' + ' module tests', 'test*')]) + [(loader, [], 'test*.py'), + (loader, [], 'test*.py')]) def test_discover(self): loader = unittest.TestLoader() @@ -191,6 +368,51 @@ class TestDiscovery(unittest.TestCase): self.assertEqual(_find_tests_args, [(start_dir, 'pattern')]) self.assertIn(top_level_dir, sys.path) + def test_discover_start_dir_is_package_calls_package_load_tests(self): + # This test verifies that the package load_tests in a package is indeed + # invoked when the start_dir is a package (and not the top level). + # http://bugs.python.org/issue22457 + + # Test data: we expect the following: + # an isfile to verify the package, then importing and scanning + # as per _find_tests' normal behaviour. + # We expect to see our load_tests hook called once. + vfs = {abspath('/toplevel'): ['startdir'], + abspath('/toplevel/startdir'): ['__init__.py']} + def list_dir(path): + return list(vfs[path]) + self.addCleanup(setattr, os, 'listdir', os.listdir) + os.listdir = list_dir + self.addCleanup(setattr, os.path, 'isfile', os.path.isfile) + os.path.isfile = lambda path: path.endswith('.py') + self.addCleanup(setattr, os.path, 'isdir', os.path.isdir) + os.path.isdir = lambda path: not path.endswith('.py') + self.addCleanup(sys.path.remove, abspath('/toplevel')) + + class Module(object): + paths = [] + load_tests_args = [] + + def __init__(self, path): + self.path = path + + def load_tests(self, loader, tests, pattern): + return ['load_tests called ' + self.path] + + def __eq__(self, other): + return self.path == other.path + + loader = unittest.TestLoader() + loader._get_module_from_name = lambda name: Module(name) + loader.suiteClass = lambda thing: thing + + suite = loader.discover('/toplevel/startdir', top_level_dir='/toplevel') + + # We should have loaded tests from the package __init__. + # (normally this would be nested TestSuites.) + self.assertEqual(suite, + [['load_tests called startdir']]) + def setup_import_issue_tests(self, fakefile): listdir = os.listdir os.listdir = lambda _: [fakefile] @@ -203,6 +425,17 @@ class TestDiscovery(unittest.TestCase): sys.path[:] = orig_sys_path self.addCleanup(restore) + def setup_import_issue_package_tests(self, vfs): + self.addCleanup(setattr, os, 'listdir', os.listdir) + self.addCleanup(setattr, os.path, 'isfile', os.path.isfile) + self.addCleanup(setattr, os.path, 'isdir', os.path.isdir) + self.addCleanup(sys.path.__setitem__, slice(None), list(sys.path)) + def list_dir(path): + return list(vfs[path]) + os.listdir = list_dir + os.path.isdir = lambda path: not path.endswith('.py') + os.path.isfile = lambda path: path.endswith('.py') + def test_discover_with_modules_that_fail_to_import(self): loader = unittest.TestLoader() @@ -211,11 +444,44 @@ class TestDiscovery(unittest.TestCase): suite = loader.discover('.') self.assertIn(os.getcwd(), sys.path) self.assertEqual(suite.countTestCases(), 1) + # Errors loading the suite are also captured for introspection. + self.assertNotEqual([], loader.errors) + self.assertEqual(1, len(loader.errors)) + error = loader.errors[0] + self.assertTrue( + 'Failed to import test module: test_this_does_not_exist' in error, + 'missing error string in %r' % error) test = list(list(suite)[0])[0] # extract test from suite with self.assertRaises(ImportError): test.test_this_does_not_exist() + def test_discover_with_init_modules_that_fail_to_import(self): + vfs = {abspath('/foo'): ['my_package'], + abspath('/foo/my_package'): ['__init__.py', 'test_module.py']} + self.setup_import_issue_package_tests(vfs) + import_calls = [] + def _get_module_from_name(name): + import_calls.append(name) + raise ImportError("Cannot import Name") + loader = unittest.TestLoader() + loader._get_module_from_name = _get_module_from_name + suite = loader.discover(abspath('/foo')) + + self.assertIn(abspath('/foo'), sys.path) + self.assertEqual(suite.countTestCases(), 1) + # Errors loading the suite are also captured for introspection. + self.assertNotEqual([], loader.errors) + self.assertEqual(1, len(loader.errors)) + error = loader.errors[0] + self.assertTrue( + 'Failed to import test module: my_package' in error, + 'missing error string in %r' % error) + test = list(list(suite)[0])[0] # extract test from suite + with self.assertRaises(ImportError): + test.my_package() + self.assertEqual(import_calls, ['my_package']) + def test_discover_with_module_that_raises_SkipTest_on_import(self): loader = unittest.TestLoader() @@ -232,6 +498,26 @@ class TestDiscovery(unittest.TestCase): suite.run(result) self.assertEqual(len(result.skipped), 1) + def test_discover_with_init_module_that_raises_SkipTest_on_import(self): + vfs = {abspath('/foo'): ['my_package'], + abspath('/foo/my_package'): ['__init__.py', 'test_module.py']} + self.setup_import_issue_package_tests(vfs) + import_calls = [] + def _get_module_from_name(name): + import_calls.append(name) + raise unittest.SkipTest('skipperoo') + loader = unittest.TestLoader() + loader._get_module_from_name = _get_module_from_name + suite = loader.discover(abspath('/foo')) + + self.assertIn(abspath('/foo'), sys.path) + self.assertEqual(suite.countTestCases(), 1) + result = unittest.TestResult() + suite.run(result) + self.assertEqual(len(result.skipped), 1) + self.assertEqual(result.testsRun, 1) + self.assertEqual(import_calls, ['my_package']) + def test_command_line_handling_parseArgs(self): program = TestableTestProgram() diff --git a/Lib/unittest/test/test_loader.py b/Lib/unittest/test/test_loader.py index b62a1b5..68f1036 100644 --- a/Lib/unittest/test/test_loader.py +++ b/Lib/unittest/test/test_loader.py @@ -1,12 +1,36 @@ import sys import types - +import warnings import unittest +# Decorator used in the deprecation tests to reset the warning registry for +# test isolation and reproducibility. +def warningregistry(func): + def wrapper(*args, **kws): + missing = object() + saved = getattr(warnings, '__warningregistry__', missing).copy() + try: + return func(*args, **kws) + finally: + if saved is missing: + try: + del warnings.__warningregistry__ + except AttributeError: + pass + else: + warnings.__warningregistry__ = saved + class Test_TestLoader(unittest.TestCase): + ### Basic object tests + ################################################################ + + def test___init__(self): + loader = unittest.TestLoader() + self.assertEqual([], loader.errors) + ### Tests for TestLoader.loadTestsFromTestCase ################################################################ @@ -150,6 +174,7 @@ class Test_TestLoader(unittest.TestCase): # Check that loadTestsFromModule honors (or not) a module # with a load_tests function. + @warningregistry def test_loadTestsFromModule__load_tests(self): m = types.ModuleType('m') class MyTestCase(unittest.TestCase): @@ -168,10 +193,144 @@ class Test_TestLoader(unittest.TestCase): suite = loader.loadTestsFromModule(m) self.assertIsInstance(suite, unittest.TestSuite) self.assertEqual(load_tests_args, [loader, suite, None]) + # With Python 3.5, the undocumented and unofficial use_load_tests is + # ignored (and deprecated). + load_tests_args = [] + with warnings.catch_warnings(record=False): + warnings.simplefilter('never') + suite = loader.loadTestsFromModule(m, use_load_tests=False) + self.assertEqual(load_tests_args, [loader, suite, None]) + + @warningregistry + def test_loadTestsFromModule__use_load_tests_deprecated_positional(self): + m = types.ModuleType('m') + class MyTestCase(unittest.TestCase): + def test(self): + pass + m.testcase_1 = MyTestCase + + load_tests_args = [] + def load_tests(loader, tests, pattern): + self.assertIsInstance(tests, unittest.TestSuite) + load_tests_args.extend((loader, tests, pattern)) + return tests + m.load_tests = load_tests + # The method still works. + loader = unittest.TestLoader() + # use_load_tests=True as a positional argument. + with warnings.catch_warnings(record=True) as w: + warnings.simplefilter('always') + suite = loader.loadTestsFromModule(m, False) + self.assertIsInstance(suite, unittest.TestSuite) + # load_tests was still called because use_load_tests is deprecated + # and ignored. + self.assertEqual(load_tests_args, [loader, suite, None]) + # We got a warning. + self.assertIs(w[-1].category, DeprecationWarning) + self.assertEqual(str(w[-1].message), + 'use_load_tests is deprecated and ignored') + + @warningregistry + def test_loadTestsFromModule__use_load_tests_deprecated_keyword(self): + m = types.ModuleType('m') + class MyTestCase(unittest.TestCase): + def test(self): + pass + m.testcase_1 = MyTestCase + + load_tests_args = [] + def load_tests(loader, tests, pattern): + self.assertIsInstance(tests, unittest.TestSuite) + load_tests_args.extend((loader, tests, pattern)) + return tests + m.load_tests = load_tests + # The method still works. + loader = unittest.TestLoader() + with warnings.catch_warnings(record=True) as w: + warnings.simplefilter('always') + suite = loader.loadTestsFromModule(m, use_load_tests=False) + self.assertIsInstance(suite, unittest.TestSuite) + # load_tests was still called because use_load_tests is deprecated + # and ignored. + self.assertEqual(load_tests_args, [loader, suite, None]) + # We got a warning. + self.assertIs(w[-1].category, DeprecationWarning) + self.assertEqual(str(w[-1].message), + 'use_load_tests is deprecated and ignored') + + @warningregistry + def test_loadTestsFromModule__too_many_positional_args(self): + m = types.ModuleType('m') + class MyTestCase(unittest.TestCase): + def test(self): + pass + m.testcase_1 = MyTestCase load_tests_args = [] - suite = loader.loadTestsFromModule(m, use_load_tests=False) - self.assertEqual(load_tests_args, []) + def load_tests(loader, tests, pattern): + self.assertIsInstance(tests, unittest.TestSuite) + load_tests_args.extend((loader, tests, pattern)) + return tests + m.load_tests = load_tests + loader = unittest.TestLoader() + with self.assertRaises(TypeError) as cm, \ + warnings.catch_warning(record=True) as w: + loader.loadTestsFromModule(m, False, 'testme.*') + # We still got the deprecation warning. + self.assertIs(w[-1].category, DeprecationWarning) + self.assertEqual(str(w[-1].message), + 'use_load_tests is deprecated and ignored') + # We also got a TypeError for too many positional arguments. + self.assertEqual(type(cm.exception), TypeError) + self.assertEqual( + str(cm.exception), + 'loadTestsFromModule() takes 1 positional argument but 3 were given') + + @warningregistry + def test_loadTestsFromModule__use_load_tests_other_bad_keyword(self): + m = types.ModuleType('m') + class MyTestCase(unittest.TestCase): + def test(self): + pass + m.testcase_1 = MyTestCase + + load_tests_args = [] + def load_tests(loader, tests, pattern): + self.assertIsInstance(tests, unittest.TestSuite) + load_tests_args.extend((loader, tests, pattern)) + return tests + m.load_tests = load_tests + loader = unittest.TestLoader() + with warnings.catch_warnings(): + warnings.simplefilter('never') + with self.assertRaises(TypeError) as cm: + loader.loadTestsFromModule( + m, use_load_tests=False, very_bad=True, worse=False) + self.assertEqual(type(cm.exception), TypeError) + # The error message names the first bad argument alphabetically, + # however use_load_tests (which sorts first) is ignored. + self.assertEqual( + str(cm.exception), + "loadTestsFromModule() got an unexpected keyword argument 'very_bad'") + + def test_loadTestsFromModule__pattern(self): + m = types.ModuleType('m') + class MyTestCase(unittest.TestCase): + def test(self): + pass + m.testcase_1 = MyTestCase + + load_tests_args = [] + def load_tests(loader, tests, pattern): + self.assertIsInstance(tests, unittest.TestSuite) + load_tests_args.extend((loader, tests, pattern)) + return tests + m.load_tests = load_tests + + loader = unittest.TestLoader() + suite = loader.loadTestsFromModule(m, pattern='testme.*') + self.assertIsInstance(suite, unittest.TestSuite) + self.assertEqual(load_tests_args, [loader, suite, 'testme.*']) def test_loadTestsFromModule__faulty_load_tests(self): m = types.ModuleType('m') @@ -184,6 +343,13 @@ class Test_TestLoader(unittest.TestCase): suite = loader.loadTestsFromModule(m) self.assertIsInstance(suite, unittest.TestSuite) self.assertEqual(suite.countTestCases(), 1) + # Errors loading the suite are also captured for introspection. + self.assertNotEqual([], loader.errors) + self.assertEqual(1, len(loader.errors)) + error = loader.errors[0] + self.assertTrue( + 'Failed to call load_tests:' in error, + 'missing error string in %r' % error) test = list(suite)[0] self.assertRaisesRegex(TypeError, "some failure", test.m) @@ -219,15 +385,15 @@ class Test_TestLoader(unittest.TestCase): def test_loadTestsFromName__malformed_name(self): loader = unittest.TestLoader() - # XXX Should this raise ValueError or ImportError? - try: - loader.loadTestsFromName('abc () //') - except ValueError: - pass - except ImportError: - pass - else: - self.fail("TestLoader.loadTestsFromName failed to raise ValueError") + suite = loader.loadTestsFromName('abc () //') + error, test = self.check_deferred_error(loader, suite) + expected = "Failed to import test module: abc () //" + expected_regex = "Failed to import test module: abc \(\) //" + self.assertIn( + expected, error, + 'missing error string in %r' % error) + self.assertRaisesRegex( + ImportError, expected_regex, getattr(test, 'abc () //')) # "The specifier name is a ``dotted name'' that may resolve ... to a # module" @@ -236,28 +402,47 @@ class Test_TestLoader(unittest.TestCase): def test_loadTestsFromName__unknown_module_name(self): loader = unittest.TestLoader() - try: - loader.loadTestsFromName('sdasfasfasdf') - except ImportError as e: - self.assertEqual(str(e), "No module named 'sdasfasfasdf'") - else: - self.fail("TestLoader.loadTestsFromName failed to raise ImportError") + suite = loader.loadTestsFromName('sdasfasfasdf') + expected = "No module named 'sdasfasfasdf'" + error, test = self.check_deferred_error(loader, suite) + self.assertIn( + expected, error, + 'missing error string in %r' % error) + self.assertRaisesRegex(ImportError, expected, test.sdasfasfasdf) # "The specifier name is a ``dotted name'' that may resolve either to # a module, a test case class, a TestSuite instance, a test method # within a test case class, or a callable object which returns a # TestCase or TestSuite instance." # - # What happens when the module is found, but the attribute can't? - def test_loadTestsFromName__unknown_attr_name(self): + # What happens when the module is found, but the attribute isn't? + def test_loadTestsFromName__unknown_attr_name_on_module(self): loader = unittest.TestLoader() - try: - loader.loadTestsFromName('unittest.sdasfasfasdf') - except AttributeError as e: - self.assertEqual(str(e), "'module' object has no attribute 'sdasfasfasdf'") - else: - self.fail("TestLoader.loadTestsFromName failed to raise AttributeError") + suite = loader.loadTestsFromName('unittest.loader.sdasfasfasdf') + expected = "module 'unittest.loader' has no attribute 'sdasfasfasdf'" + error, test = self.check_deferred_error(loader, suite) + self.assertIn( + expected, error, + 'missing error string in %r' % error) + self.assertRaisesRegex(AttributeError, expected, test.sdasfasfasdf) + + # "The specifier name is a ``dotted name'' that may resolve either to + # a module, a test case class, a TestSuite instance, a test method + # within a test case class, or a callable object which returns a + # TestCase or TestSuite instance." + # + # What happens when the module is found, but the attribute isn't? + def test_loadTestsFromName__unknown_attr_name_on_package(self): + loader = unittest.TestLoader() + + suite = loader.loadTestsFromName('unittest.sdasfasfasdf') + expected = "No module named 'unittest.sdasfasfasdf'" + error, test = self.check_deferred_error(loader, suite) + self.assertIn( + expected, error, + 'missing error string in %r' % error) + self.assertRaisesRegex(ImportError, expected, test.sdasfasfasdf) # "The specifier name is a ``dotted name'' that may resolve either to # a module, a test case class, a TestSuite instance, a test method @@ -269,12 +454,13 @@ class Test_TestLoader(unittest.TestCase): def test_loadTestsFromName__relative_unknown_name(self): loader = unittest.TestLoader() - try: - loader.loadTestsFromName('sdasfasfasdf', unittest) - except AttributeError as e: - self.assertEqual(str(e), "'module' object has no attribute 'sdasfasfasdf'") - else: - self.fail("TestLoader.loadTestsFromName failed to raise AttributeError") + suite = loader.loadTestsFromName('sdasfasfasdf', unittest) + expected = "module 'unittest' has no attribute 'sdasfasfasdf'" + error, test = self.check_deferred_error(loader, suite) + self.assertIn( + expected, error, + 'missing error string in %r' % error) + self.assertRaisesRegex(AttributeError, expected, test.sdasfasfasdf) # "The specifier name is a ``dotted name'' that may resolve either to # a module, a test case class, a TestSuite instance, a test method @@ -290,12 +476,13 @@ class Test_TestLoader(unittest.TestCase): def test_loadTestsFromName__relative_empty_name(self): loader = unittest.TestLoader() - try: - loader.loadTestsFromName('', unittest) - except AttributeError as e: - pass - else: - self.fail("Failed to raise AttributeError") + suite = loader.loadTestsFromName('', unittest) + error, test = self.check_deferred_error(loader, suite) + expected = "has no attribute ''" + self.assertIn( + expected, error, + 'missing error string in %r' % error) + self.assertRaisesRegex(AttributeError, expected, getattr(test, '')) # "The specifier name is a ``dotted name'' that may resolve either to # a module, a test case class, a TestSuite instance, a test method @@ -310,14 +497,15 @@ class Test_TestLoader(unittest.TestCase): loader = unittest.TestLoader() # XXX Should this raise AttributeError or ValueError? - try: - loader.loadTestsFromName('abc () //', unittest) - except ValueError: - pass - except AttributeError: - pass - else: - self.fail("TestLoader.loadTestsFromName failed to raise ValueError") + suite = loader.loadTestsFromName('abc () //', unittest) + error, test = self.check_deferred_error(loader, suite) + expected = "module 'unittest' has no attribute 'abc () //'" + expected_regex = "module 'unittest' has no attribute 'abc \(\) //'" + self.assertIn( + expected, error, + 'missing error string in %r' % error) + self.assertRaisesRegex( + AttributeError, expected_regex, getattr(test, 'abc () //')) # "The method optionally resolves name relative to the given module" # @@ -423,12 +611,13 @@ class Test_TestLoader(unittest.TestCase): m.testcase_1 = MyTestCase loader = unittest.TestLoader() - try: - loader.loadTestsFromName('testcase_1.testfoo', m) - except AttributeError as e: - self.assertEqual(str(e), "type object 'MyTestCase' has no attribute 'testfoo'") - else: - self.fail("Failed to raise AttributeError") + suite = loader.loadTestsFromName('testcase_1.testfoo', m) + expected = "type object 'MyTestCase' has no attribute 'testfoo'" + error, test = self.check_deferred_error(loader, suite) + self.assertIn( + expected, error, + 'missing error string in %r' % error) + self.assertRaisesRegex(AttributeError, expected, test.testfoo) # "The specifier name is a ``dotted name'' that may resolve ... to # ... a callable object which returns a ... TestSuite instance" @@ -546,6 +735,23 @@ class Test_TestLoader(unittest.TestCase): ### Tests for TestLoader.loadTestsFromNames() ################################################################ + def check_deferred_error(self, loader, suite): + """Helper function for checking that errors in loading are reported. + + :param loader: A loader with some errors. + :param suite: A suite that should have a late bound error. + :return: The first error message from the loader and the test object + from the suite. + """ + self.assertIsInstance(suite, unittest.TestSuite) + self.assertEqual(suite.countTestCases(), 1) + # Errors loading the suite are also captured for introspection. + self.assertNotEqual([], loader.errors) + self.assertEqual(1, len(loader.errors)) + error = loader.errors[0] + test = list(suite)[0] + return error, test + # "Similar to loadTestsFromName(), but takes a sequence of names rather # than a single name." # @@ -598,14 +804,15 @@ class Test_TestLoader(unittest.TestCase): loader = unittest.TestLoader() # XXX Should this raise ValueError or ImportError? - try: - loader.loadTestsFromNames(['abc () //']) - except ValueError: - pass - except ImportError: - pass - else: - self.fail("TestLoader.loadTestsFromNames failed to raise ValueError") + suite = loader.loadTestsFromNames(['abc () //']) + error, test = self.check_deferred_error(loader, list(suite)[0]) + expected = "Failed to import test module: abc () //" + expected_regex = "Failed to import test module: abc \(\) //" + self.assertIn( + expected, error, + 'missing error string in %r' % error) + self.assertRaisesRegex( + ImportError, expected_regex, getattr(test, 'abc () //')) # "The specifier name is a ``dotted name'' that may resolve either to # a module, a test case class, a TestSuite instance, a test method @@ -616,12 +823,13 @@ class Test_TestLoader(unittest.TestCase): def test_loadTestsFromNames__unknown_module_name(self): loader = unittest.TestLoader() - try: - loader.loadTestsFromNames(['sdasfasfasdf']) - except ImportError as e: - self.assertEqual(str(e), "No module named 'sdasfasfasdf'") - else: - self.fail("TestLoader.loadTestsFromNames failed to raise ImportError") + suite = loader.loadTestsFromNames(['sdasfasfasdf']) + error, test = self.check_deferred_error(loader, list(suite)[0]) + expected = "Failed to import test module: sdasfasfasdf" + self.assertIn( + expected, error, + 'missing error string in %r' % error) + self.assertRaisesRegex(ImportError, expected, test.sdasfasfasdf) # "The specifier name is a ``dotted name'' that may resolve either to # a module, a test case class, a TestSuite instance, a test method @@ -632,12 +840,14 @@ class Test_TestLoader(unittest.TestCase): def test_loadTestsFromNames__unknown_attr_name(self): loader = unittest.TestLoader() - try: - loader.loadTestsFromNames(['unittest.sdasfasfasdf', 'unittest']) - except AttributeError as e: - self.assertEqual(str(e), "'module' object has no attribute 'sdasfasfasdf'") - else: - self.fail("TestLoader.loadTestsFromNames failed to raise AttributeError") + suite = loader.loadTestsFromNames( + ['unittest.loader.sdasfasfasdf', 'unittest.test.dummy']) + error, test = self.check_deferred_error(loader, list(suite)[0]) + expected = "module 'unittest.loader' has no attribute 'sdasfasfasdf'" + self.assertIn( + expected, error, + 'missing error string in %r' % error) + self.assertRaisesRegex(AttributeError, expected, test.sdasfasfasdf) # "The specifier name is a ``dotted name'' that may resolve either to # a module, a test case class, a TestSuite instance, a test method @@ -651,12 +861,13 @@ class Test_TestLoader(unittest.TestCase): def test_loadTestsFromNames__unknown_name_relative_1(self): loader = unittest.TestLoader() - try: - loader.loadTestsFromNames(['sdasfasfasdf'], unittest) - except AttributeError as e: - self.assertEqual(str(e), "'module' object has no attribute 'sdasfasfasdf'") - else: - self.fail("TestLoader.loadTestsFromName failed to raise AttributeError") + suite = loader.loadTestsFromNames(['sdasfasfasdf'], unittest) + error, test = self.check_deferred_error(loader, list(suite)[0]) + expected = "module 'unittest' has no attribute 'sdasfasfasdf'" + self.assertIn( + expected, error, + 'missing error string in %r' % error) + self.assertRaisesRegex(AttributeError, expected, test.sdasfasfasdf) # "The specifier name is a ``dotted name'' that may resolve either to # a module, a test case class, a TestSuite instance, a test method @@ -670,12 +881,13 @@ class Test_TestLoader(unittest.TestCase): def test_loadTestsFromNames__unknown_name_relative_2(self): loader = unittest.TestLoader() - try: - loader.loadTestsFromNames(['TestCase', 'sdasfasfasdf'], unittest) - except AttributeError as e: - self.assertEqual(str(e), "'module' object has no attribute 'sdasfasfasdf'") - else: - self.fail("TestLoader.loadTestsFromName failed to raise AttributeError") + suite = loader.loadTestsFromNames(['TestCase', 'sdasfasfasdf'], unittest) + error, test = self.check_deferred_error(loader, list(suite)[1]) + expected = "module 'unittest' has no attribute 'sdasfasfasdf'" + self.assertIn( + expected, error, + 'missing error string in %r' % error) + self.assertRaisesRegex(AttributeError, expected, test.sdasfasfasdf) # "The specifier name is a ``dotted name'' that may resolve either to # a module, a test case class, a TestSuite instance, a test method @@ -691,12 +903,13 @@ class Test_TestLoader(unittest.TestCase): def test_loadTestsFromNames__relative_empty_name(self): loader = unittest.TestLoader() - try: - loader.loadTestsFromNames([''], unittest) - except AttributeError: - pass - else: - self.fail("Failed to raise ValueError") + suite = loader.loadTestsFromNames([''], unittest) + error, test = self.check_deferred_error(loader, list(suite)[0]) + expected = "has no attribute ''" + self.assertIn( + expected, error, + 'missing error string in %r' % error) + self.assertRaisesRegex(AttributeError, expected, getattr(test, '')) # "The specifier name is a ``dotted name'' that may resolve either to # a module, a test case class, a TestSuite instance, a test method @@ -710,14 +923,15 @@ class Test_TestLoader(unittest.TestCase): loader = unittest.TestLoader() # XXX Should this raise AttributeError or ValueError? - try: - loader.loadTestsFromNames(['abc () //'], unittest) - except AttributeError: - pass - except ValueError: - pass - else: - self.fail("TestLoader.loadTestsFromNames failed to raise ValueError") + suite = loader.loadTestsFromNames(['abc () //'], unittest) + error, test = self.check_deferred_error(loader, list(suite)[0]) + expected = "module 'unittest' has no attribute 'abc () //'" + expected_regex = "module 'unittest' has no attribute 'abc \(\) //'" + self.assertIn( + expected, error, + 'missing error string in %r' % error) + self.assertRaisesRegex( + AttributeError, expected_regex, getattr(test, 'abc () //')) # "The method optionally resolves name relative to the given module" # @@ -835,12 +1049,13 @@ class Test_TestLoader(unittest.TestCase): m.testcase_1 = MyTestCase loader = unittest.TestLoader() - try: - loader.loadTestsFromNames(['testcase_1.testfoo'], m) - except AttributeError as e: - self.assertEqual(str(e), "type object 'MyTestCase' has no attribute 'testfoo'") - else: - self.fail("Failed to raise AttributeError") + suite = loader.loadTestsFromNames(['testcase_1.testfoo'], m) + error, test = self.check_deferred_error(loader, list(suite)[0]) + expected = "type object 'MyTestCase' has no attribute 'testfoo'" + self.assertIn( + expected, error, + 'missing error string in %r' % error) + self.assertRaisesRegex(AttributeError, expected, test.testfoo) # "The specifier name is a ``dotted name'' that may resolve ... to # ... a callable object which returns a ... TestSuite instance" diff --git a/Lib/unittest/test/test_setups.py b/Lib/unittest/test/test_setups.py index 392f95e..2df703e 100644 --- a/Lib/unittest/test/test_setups.py +++ b/Lib/unittest/test/test_setups.py @@ -111,7 +111,7 @@ class TestSetups(unittest.TestCase): self.assertEqual(len(result.errors), 1) error, _ = result.errors[0] self.assertEqual(str(error), - 'setUpClass (%s.BrokenTest)' % __name__) + 'setUpClass (%s.%s)' % (__name__, BrokenTest.__qualname__)) def test_error_in_teardown_class(self): class Test(unittest.TestCase): @@ -144,7 +144,7 @@ class TestSetups(unittest.TestCase): error, _ = result.errors[0] self.assertEqual(str(error), - 'tearDownClass (%s.Test)' % __name__) + 'tearDownClass (%s.%s)' % (__name__, Test.__qualname__)) def test_class_not_torndown_when_setup_fails(self): class Test(unittest.TestCase): @@ -414,7 +414,8 @@ class TestSetups(unittest.TestCase): self.assertEqual(len(result.errors), 0) self.assertEqual(len(result.skipped), 1) skipped = result.skipped[0][0] - self.assertEqual(str(skipped), 'setUpClass (%s.Test)' % __name__) + self.assertEqual(str(skipped), + 'setUpClass (%s.%s)' % (__name__, Test.__qualname__)) def test_skiptest_in_setupmodule(self): class Test(unittest.TestCase): diff --git a/Lib/unittest/test/testmock/testmock.py b/Lib/unittest/test/testmock/testmock.py index 23675b9..3a104cb 100644 --- a/Lib/unittest/test/testmock/testmock.py +++ b/Lib/unittest/test/testmock/testmock.py @@ -1187,6 +1187,42 @@ class MockTest(unittest.TestCase): m = mock.create_autospec(object(), name='sweet_func') self.assertIn('sweet_func', repr(m)) + #Issue21238 + def test_mock_unsafe(self): + m = Mock() + with self.assertRaises(AttributeError): + m.assert_foo_call() + with self.assertRaises(AttributeError): + m.assret_foo_call() + m = Mock(unsafe=True) + m.assert_foo_call() + m.assret_foo_call() + + #Issue21262 + def test_assert_not_called(self): + m = Mock() + m.hello.assert_not_called() + m.hello() + with self.assertRaises(AssertionError): + m.hello.assert_not_called() + + #Issue21256 printout of keyword args should be in deterministic order + def test_sorted_call_signature(self): + m = Mock() + m.hello(name='hello', daddy='hero') + text = "call(daddy='hero', name='hello')" + self.assertEqual(repr(m.hello.call_args), text) + + #Issue21270 overrides tuple methods for mock.call objects + def test_override_tuple_methods(self): + c = call.count() + i = call.index(132,'hello') + m = Mock() + m.count() + m.index(132,"hello") + self.assertEqual(m.method_calls[0], c) + self.assertEqual(m.method_calls[1], i) + def test_mock_add_spec(self): class _One(object): one = 1 diff --git a/Lib/unittest/test/testmock/testpatch.py b/Lib/unittest/test/testmock/testpatch.py index b516f42..28fe86b 100644 --- a/Lib/unittest/test/testmock/testpatch.py +++ b/Lib/unittest/test/testmock/testpatch.py @@ -377,7 +377,7 @@ class PatchTest(unittest.TestCase): def test_patchobject_wont_create_by_default(self): try: - @patch.object(SomeClass, 'frooble', sentinel.Frooble) + @patch.object(SomeClass, 'ord', sentinel.Frooble) def test(): self.fail('Patching non existent attributes should fail') @@ -386,7 +386,27 @@ class PatchTest(unittest.TestCase): pass else: self.fail('Patching non existent attributes should fail') - self.assertFalse(hasattr(SomeClass, 'frooble')) + self.assertFalse(hasattr(SomeClass, 'ord')) + + + def test_patch_builtins_without_create(self): + @patch(__name__+'.ord') + def test_ord(mock_ord): + mock_ord.return_value = 101 + return ord('c') + + @patch(__name__+'.open') + def test_open(mock_open): + m = mock_open.return_value + m.read.return_value = 'abcd' + + fobj = open('doesnotexists.txt') + data = fobj.read() + fobj.close() + return data + + self.assertEqual(test_ord(), 101) + self.assertEqual(test_open(), 'abcd') def test_patch_with_static_methods(self): diff --git a/Lib/unittest/util.py b/Lib/unittest/util.py index aee498f..45485dc 100644 --- a/Lib/unittest/util.py +++ b/Lib/unittest/util.py @@ -52,7 +52,7 @@ def safe_repr(obj, short=False): return result[:_MAX_LENGTH] + ' [truncated]...' def strclass(cls): - return "%s.%s" % (cls.__module__, cls.__name__) + return "%s.%s" % (cls.__module__, cls.__qualname__) def sorted_list_difference(expected, actual): """Finds elements in only one or the other of two, sorted input lists. diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py index d368331..66420d2 100644 --- a/Lib/urllib/parse.py +++ b/Lib/urllib/parse.py @@ -409,11 +409,13 @@ def urljoin(base, url, allow_fragments=True): return url if not url: return base + base, url, _coerce_result = _coerce_args(base, url) bscheme, bnetloc, bpath, bparams, bquery, bfragment = \ urlparse(base, '', allow_fragments) scheme, netloc, path, params, query, fragment = \ urlparse(url, bscheme, allow_fragments) + if scheme != bscheme or scheme not in uses_relative: return _coerce_result(url) if scheme in uses_netloc: @@ -421,9 +423,7 @@ def urljoin(base, url, allow_fragments=True): return _coerce_result(urlunparse((scheme, netloc, path, params, query, fragment))) netloc = bnetloc - if path[:1] == '/': - return _coerce_result(urlunparse((scheme, netloc, path, - params, query, fragment))) + if not path and not params: path = bpath params = bparams @@ -431,29 +431,46 @@ def urljoin(base, url, allow_fragments=True): query = bquery return _coerce_result(urlunparse((scheme, netloc, path, params, query, fragment))) - segments = bpath.split('/')[:-1] + path.split('/') - # XXX The stuff below is bogus in various ways... - if segments[-1] == '.': - segments[-1] = '' - while '.' in segments: - segments.remove('.') - while 1: - i = 1 - n = len(segments) - 1 - while i < n: - if (segments[i] == '..' - and segments[i-1] not in ('', '..')): - del segments[i-1:i+1] - break - i = i+1 + + base_parts = bpath.split('/') + if base_parts[-1] != '': + # the last item is not a directory, so will not be taken into account + # in resolving the relative path + del base_parts[-1] + + # for rfc3986, ignore all base path should the first character be root. + if path[:1] == '/': + segments = path.split('/') + else: + segments = base_parts + path.split('/') + # filter out elements that would cause redundant slashes on re-joining + # the resolved_path + segments = segments[0:1] + [ + s for s in segments[1:-1] if len(s) > 0] + segments[-1:] + + resolved_path = [] + + for seg in segments: + if seg == '..': + try: + resolved_path.pop() + except IndexError: + # ignore any .. segments that would otherwise cause an IndexError + # when popped from resolved_path if resolving for rfc3986 + pass + elif seg == '.': + continue else: - break - if segments == ['', '..']: - segments[-1] = '' - elif len(segments) >= 2 and segments[-1] == '..': - segments[-2:] = [''] - return _coerce_result(urlunparse((scheme, netloc, '/'.join(segments), - params, query, fragment))) + resolved_path.append(seg) + + if segments[-1] in ('.', '..'): + # do some post-processing here. if the last segment was a relative dir, + # then we need to append the trailing '/' + resolved_path.append('') + + return _coerce_result(urlunparse((scheme, netloc, '/'.join( + resolved_path) or '/', params, query, fragment))) + def urldefrag(url): """Removes any existing fragment from URL. @@ -641,7 +658,7 @@ class Quoter(collections.defaultdict): def __repr__(self): # Without this, will just display as a defaultdict - return "<Quoter %r>" % dict(self) + return "<%s %r>" % (self.__class__.__name__, dict(self)) def __missing__(self, b): # Handle a cache miss. Store quoted string in cache and return. @@ -852,12 +869,12 @@ def splittype(url): """splittype('type:opaquestring') --> 'type', 'opaquestring'.""" global _typeprog if _typeprog is None: - _typeprog = re.compile('^([^/:]+):') + _typeprog = re.compile('([^/:]+):(.*)', re.DOTALL) match = _typeprog.match(url) if match: - scheme = match.group(1) - return scheme.lower(), url[len(scheme) + 1:] + scheme, data = match.groups() + return scheme.lower(), data return None, url _hostprog = None @@ -865,38 +882,25 @@ def splithost(url): """splithost('//host[:port]/path') --> 'host[:port]', '/path'.""" global _hostprog if _hostprog is None: - _hostprog = re.compile('^//([^/?]*)(.*)$') + _hostprog = re.compile('//([^/?]*)(.*)', re.DOTALL) match = _hostprog.match(url) if match: - host_port = match.group(1) - path = match.group(2) - if path and not path.startswith('/'): + host_port, path = match.groups() + if path and path[0] != '/': path = '/' + path return host_port, path return None, url -_userprog = None def splituser(host): """splituser('user[:passwd]@host[:port]') --> 'user[:passwd]', 'host[:port]'.""" - global _userprog - if _userprog is None: - _userprog = re.compile('^(.*)@(.*)$') + user, delim, host = host.rpartition('@') + return (user if delim else None), host - match = _userprog.match(host) - if match: return match.group(1, 2) - return None, host - -_passwdprog = None def splitpasswd(user): """splitpasswd('user:passwd') -> 'user', 'passwd'.""" - global _passwdprog - if _passwdprog is None: - _passwdprog = re.compile('^([^:]*):(.*)$',re.S) - - match = _passwdprog.match(user) - if match: return match.group(1, 2) - return user, None + user, delim, passwd = user.partition(':') + return user, (passwd if delim else None) # splittag('/path#tag') --> '/path', 'tag' _portprog = None @@ -904,7 +908,7 @@ def splitport(host): """splitport('host:port') --> 'host', 'port'.""" global _portprog if _portprog is None: - _portprog = re.compile('^(.*):([0-9]*)$') + _portprog = re.compile('(.*):([0-9]*)$', re.DOTALL) match = _portprog.match(host) if match: @@ -913,47 +917,34 @@ def splitport(host): return host, port return host, None -_nportprog = None def splitnport(host, defport=-1): """Split host and port, returning numeric port. Return given default port if no ':' found; defaults to -1. Return numerical port if a valid number are found after ':'. Return None if ':' but not a valid number.""" - global _nportprog - if _nportprog is None: - _nportprog = re.compile('^(.*):(.*)$') - - match = _nportprog.match(host) - if match: - host, port = match.group(1, 2) - if port: - try: - nport = int(port) - except ValueError: - nport = None - return host, nport + host, delim, port = host.rpartition(':') + if not delim: + host = port + elif port: + try: + nport = int(port) + except ValueError: + nport = None + return host, nport return host, defport -_queryprog = None def splitquery(url): """splitquery('/path?query') --> '/path', 'query'.""" - global _queryprog - if _queryprog is None: - _queryprog = re.compile('^(.*)\?([^?]*)$') - - match = _queryprog.match(url) - if match: return match.group(1, 2) + path, delim, query = url.rpartition('?') + if delim: + return path, query return url, None -_tagprog = None def splittag(url): """splittag('/path#tag') --> '/path', 'tag'.""" - global _tagprog - if _tagprog is None: - _tagprog = re.compile('^(.*)#([^#]*)$') - - match = _tagprog.match(url) - if match: return match.group(1, 2) + path, delim, tag = url.rpartition('#') + if delim: + return path, tag return url, None def splitattr(url): @@ -962,13 +953,7 @@ def splitattr(url): words = url.split(';') return words[0], words[1:] -_valueprog = None def splitvalue(attr): """splitvalue('attr=value') --> 'attr', 'value'.""" - global _valueprog - if _valueprog is None: - _valueprog = re.compile('^([^=]*)=(.*)$') - - match = _valueprog.match(attr) - if match: return match.group(1, 2) - return attr, None + attr, delim, value = attr.partition('=') + return attr, (value if delim else None) diff --git a/Lib/urllib/request.py b/Lib/urllib/request.py index 6da9007..3ba7c01 100644 --- a/Lib/urllib/request.py +++ b/Lib/urllib/request.py @@ -916,6 +916,21 @@ class ProxyBasicAuthHandler(AbstractBasicAuthHandler, BaseHandler): return response +class HTTPBasicPriorAuthHandler(HTTPBasicAuthHandler): + handler_order = 400 + + def http_request(self, req): + if not req.has_header('Authorization'): + user, passwd = self.passwd.find_user_password(None, req.host) + credentials = '{0}:{1}'.format(user, passwd).encode() + auth_str = base64.standard_b64encode(credentials).decode() + req.add_unredirected_header('Authorization', + 'Basic {}'.format(auth_str.strip())) + return req + + https_request = http_request + + # Return n random bytes. _randombytes = os.urandom diff --git a/Lib/urllib/robotparser.py b/Lib/urllib/robotparser.py index 1d7b751..4fbb0cb 100644 --- a/Lib/urllib/robotparser.py +++ b/Lib/urllib/robotparser.py @@ -172,7 +172,7 @@ class RuleLine: return self.path == "*" or filename.startswith(self.path) def __str__(self): - return (self.allowance and "Allow" or "Disallow") + ": " + self.path + return ("Allow" if self.allowance else "Disallow") + ": " + self.path class Entry: diff --git a/Lib/uuid.py b/Lib/uuid.py index 1061bff..e627573 100644 --- a/Lib/uuid.py +++ b/Lib/uuid.py @@ -139,10 +139,8 @@ class UUID(object): if bytes_le is not None: if len(bytes_le) != 16: raise ValueError('bytes_le is not a 16-char string') - bytes = (bytes_(reversed(bytes_le[0:4])) + - bytes_(reversed(bytes_le[4:6])) + - bytes_(reversed(bytes_le[6:8])) + - bytes_le[8:]) + bytes = (bytes_le[4-1::-1] + bytes_le[6-1:4-1:-1] + + bytes_le[8-1:6-1:-1] + bytes_le[8:]) if bytes is not None: if len(bytes) != 16: raise ValueError('bytes is not a 16-char string') @@ -187,11 +185,6 @@ class UUID(object): return self.int == other.int return NotImplemented - def __ne__(self, other): - if isinstance(other, UUID): - return self.int != other.int - return NotImplemented - # Q. What's the value of being able to sort UUIDs? # A. Use them as keys in a B-Tree or similar mapping. @@ -222,7 +215,7 @@ class UUID(object): return self.int def __repr__(self): - return 'UUID(%r)' % str(self) + return '%s(%r)' % (self.__class__.__name__, str(self)) def __setattr__(self, name, value): raise TypeError('UUID objects are immutable') @@ -234,17 +227,12 @@ class UUID(object): @property def bytes(self): - bytes = bytearray() - for shift in range(0, 128, 8): - bytes.insert(0, (self.int >> shift) & 0xff) - return bytes_(bytes) + return self.int.to_bytes(16, 'big') @property def bytes_le(self): bytes = self.bytes - return (bytes_(reversed(bytes[0:4])) + - bytes_(reversed(bytes[4:6])) + - bytes_(reversed(bytes[6:8])) + + return (bytes[4-1::-1] + bytes[6-1:4-1:-1] + bytes[8-1:6-1:-1] + bytes[8:]) @property @@ -311,33 +299,38 @@ class UUID(object): if self.variant == RFC_4122: return int((self.int >> 76) & 0xf) -def _popen(command, args): - import os, shutil +def _popen(command, *args): + import os, shutil, subprocess executable = shutil.which(command) if executable is None: path = os.pathsep.join(('/sbin', '/usr/sbin')) executable = shutil.which(command, path=path) if executable is None: return None - # LC_ALL to ensure English output, 2>/dev/null to prevent output on - # stderr (Note: we don't have an example where the words we search for - # are actually localized, but in theory some system could do so.) - cmd = 'LC_ALL=C %s %s 2>/dev/null' % (executable, args) - return os.popen(cmd) + # LC_ALL=C to ensure English output, stderr=DEVNULL to prevent output + # on stderr (Note: we don't have an example where the words we search + # for are actually localized, but in theory some system could do so.) + env = dict(os.environ) + env['LC_ALL'] = 'C' + proc = subprocess.Popen((executable,) + args, + stdout=subprocess.PIPE, + stderr=subprocess.DEVNULL, + env=env) + return proc def _find_mac(command, args, hw_identifiers, get_index): try: - pipe = _popen(command, args) - if not pipe: + proc = _popen(command, *args.split()) + if not proc: return - with pipe: - for line in pipe: + with proc: + for line in proc.stdout: words = line.lower().rstrip().split() for i in range(len(words)): if words[i] in hw_identifiers: try: word = words[get_index(i)] - mac = int(word.replace(':', ''), 16) + mac = int(word.replace(b':', b''), 16) if mac: return mac except (ValueError, IndexError): @@ -354,10 +347,17 @@ def _ifconfig_getnode(): """Get the hardware address on Unix by running ifconfig.""" # This works on Linux ('' or '-a'), Tru64 ('-av'), but not all Unixes. for args in ('', '-a', '-av'): - mac = _find_mac('ifconfig', args, ['hwaddr', 'ether'], lambda i: i+1) + mac = _find_mac('ifconfig', args, [b'hwaddr', b'ether'], lambda i: i+1) if mac: return mac +def _ip_getnode(): + """Get the hardware address on Unix by running ip.""" + # This works on Linux with iproute2. + mac = _find_mac('ip', 'link list', [b'link/ether'], lambda i: i+1) + if mac: + return mac + def _arp_getnode(): """Get the hardware address on Unix by running arp.""" import os, socket @@ -367,32 +367,32 @@ def _arp_getnode(): return None # Try getting the MAC addr from arp based on our IP address (Solaris). - return _find_mac('arp', '-an', [ip_addr], lambda i: -1) + return _find_mac('arp', '-an', [os.fsencode(ip_addr)], lambda i: -1) def _lanscan_getnode(): """Get the hardware address on Unix by running lanscan.""" # This might work on HP-UX. - return _find_mac('lanscan', '-ai', ['lan0'], lambda i: 0) + return _find_mac('lanscan', '-ai', [b'lan0'], lambda i: 0) def _netstat_getnode(): """Get the hardware address on Unix by running netstat.""" # This might work on AIX, Tru64 UNIX and presumably on IRIX. try: - pipe = _popen('netstat', '-ia') - if not pipe: + proc = _popen('netstat', '-ia') + if not proc: return - with pipe: - words = pipe.readline().rstrip().split() + with proc: + words = proc.stdout.readline().rstrip().split() try: - i = words.index('Address') + i = words.index(b'Address') except ValueError: return - for line in pipe: + for line in proc.stdout: try: words = line.rstrip().split() word = words[i] - if len(word) == 17 and word.count(':') == 5: - mac = int(word.replace(':', ''), 16) + if len(word) == 17 and word.count(b':') == 5: + mac = int(word.replace(b':', b''), 16) if mac: return mac except (ValueError, IndexError): @@ -447,9 +447,10 @@ def _netbios_getnode(): if win32wnet.Netbios(ncb) != 0: continue status._unpack() - bytes = status.adapter_address - return ((bytes[0]<<40) + (bytes[1]<<32) + (bytes[2]<<24) + - (bytes[3]<<16) + (bytes[4]<<8) + bytes[5]) + bytes = status.adapter_address[:6] + if len(bytes) != 6: + continue + return int.from_bytes(bytes, 'big') # Thanks to Thomas Heller for ctypes and for his help with its use here. @@ -518,7 +519,7 @@ def _windll_getnode(): def _random_getnode(): """Get a random node ID, with eighth bit set as suggested by RFC 4122.""" import random - return random.randrange(0, 1<<48) | 0x010000000000 + return random.getrandbits(48) | 0x010000000000 _node = None @@ -539,8 +540,8 @@ def getnode(): if sys.platform == 'win32': getters = [_windll_getnode, _netbios_getnode, _ipconfig_getnode] else: - getters = [_unixdll_getnode, _ifconfig_getnode, _arp_getnode, - _lanscan_getnode, _netstat_getnode] + getters = [_unixdll_getnode, _ifconfig_getnode, _ip_getnode, + _arp_getnode, _lanscan_getnode, _netstat_getnode] for getter in getters + [_random_getnode]: try: @@ -576,7 +577,7 @@ def uuid1(node=None, clock_seq=None): _last_timestamp = timestamp if clock_seq is None: import random - clock_seq = random.randrange(1<<14) # instead of stable storage + clock_seq = random.getrandbits(14) # instead of stable storage time_low = timestamp & 0xffffffff time_mid = (timestamp >> 32) & 0xffff time_hi_version = (timestamp >> 48) & 0x0fff @@ -608,8 +609,7 @@ def uuid4(): return UUID(bytes=os.urandom(16), version=4) except: import random - bytes = bytes_(random.randrange(256) for i in range(16)) - return UUID(bytes=bytes, version=4) + return UUID(int=random.getrandbits(128), version=4) def uuid5(namespace, name): """Generate a UUID from the SHA-1 hash of a namespace UUID and a name.""" diff --git a/Lib/warnings.py b/Lib/warnings.py index 70d087e..5ca4b9c 100644 --- a/Lib/warnings.py +++ b/Lib/warnings.py @@ -169,7 +169,9 @@ def warn(message, category=None, stacklevel=1): # Check category argument if category is None: category = UserWarning - assert issubclass(category, Warning) + if not (isinstance(category, type) and issubclass(category, Warning)): + raise TypeError("category must be a Warning subclass, " + "not '{:s}'".format(type(category).__name__)) # Get context information try: caller = sys._getframe(stacklevel) diff --git a/Lib/weakref.py b/Lib/weakref.py index 12bf975..a4ecadc 100644 --- a/Lib/weakref.py +++ b/Lib/weakref.py @@ -144,7 +144,7 @@ class WeakValueDictionary(collections.MutableMapping): return o is not None def __repr__(self): - return "<WeakValueDictionary at %s>" % id(self) + return "<%s at %#x>" % (self.__class__.__name__, id(self)) def __setitem__(self, key, value): if self._pending_removals: @@ -359,7 +359,7 @@ class WeakKeyDictionary(collections.MutableMapping): return len(self.data) - len(self._pending_removals) def __repr__(self): - return "<WeakKeyDictionary at %s>" % id(self) + return "<%s at %#x>" % (self.__class__.__name__, id(self)) def __setitem__(self, key, value): self.data[ref(key, self._remove)] = value diff --git a/Lib/wsgiref/headers.py b/Lib/wsgiref/headers.py index d939628..7e670b3 100644 --- a/Lib/wsgiref/headers.py +++ b/Lib/wsgiref/headers.py @@ -26,10 +26,10 @@ def _formatparam(param, value=None, quote=1): class Headers: - """Manage a collection of HTTP response headers""" - def __init__(self,headers): + def __init__(self, headers=None): + headers = headers if headers is not None else [] if type(headers) is not list: raise TypeError("Headers must be a list of name/value tuples") self._headers = headers @@ -131,7 +131,7 @@ class Headers: return self._headers[:] def __repr__(self): - return "Headers(%r)" % self._headers + return "%s(%r)" % (self.__class__.__name__, self._headers) def __str__(self): """str() returns the formatted headers, complete with end line, diff --git a/Lib/xml/dom/minidom.py b/Lib/xml/dom/minidom.py index c379a33..a5d813f 100644 --- a/Lib/xml/dom/minidom.py +++ b/Lib/xml/dom/minidom.py @@ -545,9 +545,6 @@ class NamedNodeMap(object): def __lt__(self, other): return self._cmp(other) < 0 - def __ne__(self, other): - return self._cmp(other) != 0 - def __getitem__(self, attname_or_tuple): if isinstance(attname_or_tuple, tuple): return self._attrsNS[attname_or_tuple] @@ -648,9 +645,10 @@ class TypeInfo(object): def __repr__(self): if self.namespace: - return "<TypeInfo %r (from %r)>" % (self.name, self.namespace) + return "<%s %r (from %r)>" % (self.__class__.__name__, self.name, + self.namespace) else: - return "<TypeInfo %r>" % self.name + return "<%s %r>" % (self.__class__.__name__, self.name) def _get_name(self): return self.name diff --git a/Lib/xml/etree/ElementPath.py b/Lib/xml/etree/ElementPath.py index d914ddb..5de4232 100644 --- a/Lib/xml/etree/ElementPath.py +++ b/Lib/xml/etree/ElementPath.py @@ -114,7 +114,10 @@ def prepare_self(next, token): return select def prepare_descendant(next, token): - token = next() + try: + token = next() + except StopIteration: + return if token[0] == "*": tag = "*" elif not token[0]: @@ -148,7 +151,10 @@ def prepare_predicate(next, token): signature = [] predicate = [] while 1: - token = next() + try: + token = next() + except StopIteration: + return if token[0] == "]": break if token[0] and token[0][:1] in "'\"": @@ -261,7 +267,10 @@ def iterfind(elem, path, namespaces=None): if path[:1] == "/": raise SyntaxError("cannot use absolute path on element") next = iter(xpath_tokenizer(path, namespaces)).__next__ - token = next() + try: + token = next() + except StopIteration: + return selector = [] while 1: try: @@ -286,10 +295,7 @@ def iterfind(elem, path, namespaces=None): # Find first matching object. def find(elem, path, namespaces=None): - try: - return next(iterfind(elem, path, namespaces)) - except StopIteration: - return None + return next(iterfind(elem, path, namespaces), None) ## # Find all matching objects. diff --git a/Lib/xml/etree/ElementTree.py b/Lib/xml/etree/ElementTree.py index a8585b6..4c109a2 100644 --- a/Lib/xml/etree/ElementTree.py +++ b/Lib/xml/etree/ElementTree.py @@ -174,7 +174,7 @@ class Element: self._children = [] def __repr__(self): - return "<Element %s at 0x%x>" % (repr(self.tag), id(self)) + return "<%s %r at %#x>" % (self.__class__.__name__, self.tag, id(self)) def makeelement(self, tag, attrib): """Create a new element with the same type. @@ -509,7 +509,7 @@ class QName: def __str__(self): return self.text def __repr__(self): - return '<QName %r>' % (self.text,) + return '<%s %r>' % (self.__class__.__name__, self.text) def __hash__(self): return hash(self.text) def __le__(self, other): @@ -532,10 +532,6 @@ class QName: if isinstance(other, QName): return self.text == other.text return self.text == other - def __ne__(self, other): - if isinstance(other, QName): - return self.text != other.text - return self.text != other # -------------------------------------------------------------------- diff --git a/Lib/xmlrpc/client.py b/Lib/xmlrpc/client.py index e8c1944..047929a 100644 --- a/Lib/xmlrpc/client.py +++ b/Lib/xmlrpc/client.py @@ -208,8 +208,8 @@ class ProtocolError(Error): self.headers = headers def __repr__(self): return ( - "<ProtocolError for %s: %s %s>" % - (self.url, self.errcode, self.errmsg) + "<%s for %s: %s %s>" % + (self.__class__.__name__, self.url, self.errcode, self.errmsg) ) ## @@ -237,7 +237,8 @@ class Fault(Error): self.faultCode = faultCode self.faultString = faultString def __repr__(self): - return "<Fault %s: %r>" % (self.faultCode, self.faultString) + return "<%s %s: %r>" % (self.__class__.__name__, + self.faultCode, self.faultString) # -------------------------------------------------------------------- # Special values @@ -339,10 +340,6 @@ class DateTime: s, o = self.make_comparable(other) return s == o - def __ne__(self, other): - s, o = self.make_comparable(other) - return s != o - def timetuple(self): return time.strptime(self.value, "%Y%m%dT%H:%M:%S") @@ -355,7 +352,7 @@ class DateTime: return self.value def __repr__(self): - return "<DateTime %r at %x>" % (self.value, id(self)) + return "<%s %r at %#x>" % (self.__class__.__name__, self.value, id(self)) def decode(self, data): self.value = str(data).strip() @@ -406,11 +403,6 @@ class Binary: other = other.data return self.data == other - def __ne__(self, other): - if isinstance(other, Binary): - other = other.data - return self.data != other - def decode(self, data): self.data = base64.decodebytes(data) @@ -847,7 +839,7 @@ class MultiCall: self.__call_list = [] def __repr__(self): - return "<MultiCall at %x>" % id(self) + return "<%s at %#x>" % (self.__class__.__name__, id(self)) __str__ = __repr__ @@ -1444,8 +1436,8 @@ class ServerProxy: def __repr__(self): return ( - "<ServerProxy for %s%s>" % - (self.__host, self.__handler) + "<%s for %s%s>" % + (self.__class__.__name__, self.__host, self.__handler) ) __str__ = __repr__ @@ -1467,6 +1459,12 @@ class ServerProxy: return self.__transport raise AttributeError("Attribute %r not found" % (attr,)) + def __enter__(self): + return self + + def __exit__(self, *args): + self.__close() + # compatibility Server = ServerProxy diff --git a/Lib/zipfile.py b/Lib/zipfile.py index bda6134..8c2950f 100644 --- a/Lib/zipfile.py +++ b/Lib/zipfile.py @@ -13,6 +13,7 @@ import stat import shutil import struct import binascii +import threading try: @@ -355,6 +356,28 @@ class ZipInfo (object): # compress_size Size of the compressed file # file_size Size of the uncompressed file + def __repr__(self): + result = ['<%s filename=%r' % (self.__class__.__name__, self.filename)] + if self.compress_type != ZIP_STORED: + result.append(' compress_type=%s' % + compressor_names.get(self.compress_type, + self.compress_type)) + hi = self.external_attr >> 16 + lo = self.external_attr & 0xFFFF + if hi: + result.append(' filemode=%r' % stat.filemode(hi)) + if lo: + result.append(' external_attr=%#x' % lo) + isdir = self.filename[-1:] == '/' + if not isdir or self.file_size: + result.append(' file_size=%r' % self.file_size) + if ((not isdir or self.compress_size) and + (self.compress_type != ZIP_STORED or + self.file_size != self.compress_size)): + result.append(' compress_size=%r' % self.compress_size) + result.append('>') + return ''.join(result) + def FileHeader(self, zip64=None): """Return the per-file header as a string.""" dt = self.date_time @@ -624,6 +647,27 @@ def _get_decompressor(compress_type): raise NotImplementedError("compression type %d" % (compress_type,)) +class _SharedFile: + def __init__(self, file, pos, close, lock): + self._file = file + self._pos = pos + self._close = close + self._lock = lock + + def read(self, n=-1): + with self._lock: + self._file.seek(self._pos) + data = self._file.read(n) + self._pos = self._file.tell() + return data + + def close(self): + if self._file is not None: + fileobj = self._file + self._file = None + self._close(fileobj) + + class ZipExtFile(io.BufferedIOBase): """File-like object for reading an archive member. Is returned by ZipFile.open(). @@ -671,6 +715,20 @@ class ZipExtFile(io.BufferedIOBase): else: self._expected_crc = None + def __repr__(self): + result = ['<%s.%s' % (self.__class__.__module__, + self.__class__.__qualname__)] + if not self.closed: + result.append(' name=%r mode=%r' % (self.name, self.mode)) + if self._compress_type != ZIP_STORED: + result.append(' compress_type=%s' % + compressor_names.get(self._compress_type, + self._compress_type)) + else: + result.append(' [closed]') + result.append('>') + return ''.join(result) + def readline(self, limit=-1): """Read and return a line from the stream. @@ -909,7 +967,7 @@ class ZipFile: self.NameToInfo = {} # Find file info given name self.filelist = [] # List of ZipInfo instances for archive self.compression = compression # Method of compression - self.mode = key = mode.replace('b', '')[0] + self.mode = mode self.pwd = None self._comment = b'' @@ -918,28 +976,34 @@ class ZipFile: # No, it's a filename self._filePassed = 0 self.filename = file - modeDict = {'r' : 'rb', 'w': 'wb', 'a' : 'r+b'} - try: - self.fp = io.open(file, modeDict[mode]) - except OSError: - if mode == 'a': - mode = key = 'w' - self.fp = io.open(file, modeDict[mode]) - else: + modeDict = {'r' : 'rb', 'w': 'w+b', 'a' : 'r+b', + 'r+b': 'w+b', 'w+b': 'wb'} + filemode = modeDict[mode] + while True: + try: + self.fp = io.open(file, filemode) + except OSError: + if filemode in modeDict: + filemode = modeDict[filemode] + continue raise + break else: self._filePassed = 1 self.fp = file self.filename = getattr(file, 'name', None) + self._fileRefCnt = 1 + self._lock = threading.RLock() try: - if key == 'r': + if mode == 'r': self._RealGetContents() - elif key == 'w': + elif mode == 'w': # set the modified flag so central directory gets written # even if no files are added to the archive self._didModify = True - elif key == 'a': + self.start_dir = self.fp.tell() + elif mode == 'a': try: # See if file is a zip file self._RealGetContents() @@ -952,13 +1016,13 @@ class ZipFile: # set the modified flag so central directory gets written # even if no files are added to the archive self._didModify = True + self.start_dir = self.fp.tell() else: raise RuntimeError('Mode must be "r", "w" or "a"') except: fp = self.fp self.fp = None - if not self._filePassed: - fp.close() + self._fpclose(fp) raise def __enter__(self): @@ -967,6 +1031,20 @@ class ZipFile: def __exit__(self, type, value, traceback): self.close() + def __repr__(self): + result = ['<%s.%s' % (self.__class__.__module__, + self.__class__.__qualname__)] + if self.fp is not None: + if self._filePassed: + result.append(' file=%r' % self.fp) + elif self.filename is not None: + result.append(' filename=%r' % self.filename) + result.append(' mode=%r' % self.mode) + else: + result.append(' [closed]') + result.append('>') + return ''.join(result) + def _RealGetContents(self): """Read in the table of contents for the ZIP file.""" fp = self.fp @@ -1131,23 +1209,17 @@ class ZipFile: raise RuntimeError( "Attempt to read ZIP archive that was already closed") - # Only open a new file for instances where we were not - # given a file object in the constructor - if self._filePassed: - zef_file = self.fp + # Make sure we have an info object + if isinstance(name, ZipInfo): + # 'name' is already an info object + zinfo = name else: - zef_file = io.open(self.filename, 'rb') + # Get info object for name + zinfo = self.getinfo(name) + self._fileRefCnt += 1 + zef_file = _SharedFile(self.fp, zinfo.header_offset, self._fpclose, self._lock) try: - # Make sure we have an info object - if isinstance(name, ZipInfo): - # 'name' is already an info object - zinfo = name - else: - # Get info object for name - zinfo = self.getinfo(name) - zef_file.seek(zinfo.header_offset, 0) - # Skip the file header: fheader = zef_file.read(sizeFileHeader) if len(fheader) != sizeFileHeader: @@ -1206,11 +1278,9 @@ class ZipFile: if h[11] != check_byte: raise RuntimeError("Bad password for file", name) - return ZipExtFile(zef_file, mode, zinfo, zd, - close_fileobj=not self._filePassed) + return ZipExtFile(zef_file, mode, zinfo, zd, True) except: - if not self._filePassed: - zef_file.close() + zef_file.close() raise def extract(self, member, path=None, pwd=None): @@ -1344,66 +1414,69 @@ class ZipFile: zinfo.file_size = st.st_size zinfo.flag_bits = 0x00 - zinfo.header_offset = self.fp.tell() # Start of header bytes - if zinfo.compress_type == ZIP_LZMA: - # Compressed data includes an end-of-stream (EOS) marker - zinfo.flag_bits |= 0x02 - - self._writecheck(zinfo) - self._didModify = True - - if isdir: - zinfo.file_size = 0 - zinfo.compress_size = 0 - zinfo.CRC = 0 - zinfo.external_attr |= 0x10 # MS-DOS directory flag + with self._lock: + self.fp.seek(self.start_dir, 0) + zinfo.header_offset = self.fp.tell() # Start of header bytes + if zinfo.compress_type == ZIP_LZMA: + # Compressed data includes an end-of-stream (EOS) marker + zinfo.flag_bits |= 0x02 + + self._writecheck(zinfo) + self._didModify = True + + if isdir: + zinfo.file_size = 0 + zinfo.compress_size = 0 + zinfo.CRC = 0 + zinfo.external_attr |= 0x10 # MS-DOS directory flag + self.filelist.append(zinfo) + self.NameToInfo[zinfo.filename] = zinfo + self.fp.write(zinfo.FileHeader(False)) + self.start_dir = self.fp.tell() + return + + cmpr = _get_compressor(zinfo.compress_type) + with open(filename, "rb") as fp: + # Must overwrite CRC and sizes with correct data later + zinfo.CRC = CRC = 0 + zinfo.compress_size = compress_size = 0 + # Compressed size can be larger than uncompressed size + zip64 = self._allowZip64 and \ + zinfo.file_size * 1.05 > ZIP64_LIMIT + self.fp.write(zinfo.FileHeader(zip64)) + file_size = 0 + while 1: + buf = fp.read(1024 * 8) + if not buf: + break + file_size = file_size + len(buf) + CRC = crc32(buf, CRC) & 0xffffffff + if cmpr: + buf = cmpr.compress(buf) + compress_size = compress_size + len(buf) + self.fp.write(buf) + if cmpr: + buf = cmpr.flush() + compress_size = compress_size + len(buf) + self.fp.write(buf) + zinfo.compress_size = compress_size + else: + zinfo.compress_size = file_size + zinfo.CRC = CRC + zinfo.file_size = file_size + if not zip64 and self._allowZip64: + if file_size > ZIP64_LIMIT: + raise RuntimeError('File size has increased during compressing') + if compress_size > ZIP64_LIMIT: + raise RuntimeError('Compressed size larger than uncompressed size') + # Seek backwards and write file header (which will now include + # correct CRC and file sizes) + self.start_dir = self.fp.tell() # Preserve current position in file + self.fp.seek(zinfo.header_offset, 0) + self.fp.write(zinfo.FileHeader(zip64)) + self.fp.seek(self.start_dir, 0) self.filelist.append(zinfo) self.NameToInfo[zinfo.filename] = zinfo - self.fp.write(zinfo.FileHeader(False)) - return - - cmpr = _get_compressor(zinfo.compress_type) - with open(filename, "rb") as fp: - # Must overwrite CRC and sizes with correct data later - zinfo.CRC = CRC = 0 - zinfo.compress_size = compress_size = 0 - # Compressed size can be larger than uncompressed size - zip64 = self._allowZip64 and \ - zinfo.file_size * 1.05 > ZIP64_LIMIT - self.fp.write(zinfo.FileHeader(zip64)) - file_size = 0 - while 1: - buf = fp.read(1024 * 8) - if not buf: - break - file_size = file_size + len(buf) - CRC = crc32(buf, CRC) & 0xffffffff - if cmpr: - buf = cmpr.compress(buf) - compress_size = compress_size + len(buf) - self.fp.write(buf) - if cmpr: - buf = cmpr.flush() - compress_size = compress_size + len(buf) - self.fp.write(buf) - zinfo.compress_size = compress_size - else: - zinfo.compress_size = file_size - zinfo.CRC = CRC - zinfo.file_size = file_size - if not zip64 and self._allowZip64: - if file_size > ZIP64_LIMIT: - raise RuntimeError('File size has increased during compressing') - if compress_size > ZIP64_LIMIT: - raise RuntimeError('Compressed size larger than uncompressed size') - # Seek backwards and write file header (which will now include - # correct CRC and file sizes) - position = self.fp.tell() # Preserve current position in file - self.fp.seek(zinfo.header_offset, 0) - self.fp.write(zinfo.FileHeader(zip64)) - self.fp.seek(position, 0) - self.filelist.append(zinfo) - self.NameToInfo[zinfo.filename] = zinfo def writestr(self, zinfo_or_arcname, data, compress_type=None): """Write a file into the archive. The contents is 'data', which @@ -1430,36 +1503,46 @@ class ZipFile: "Attempt to write to ZIP archive that was already closed") zinfo.file_size = len(data) # Uncompressed size - zinfo.header_offset = self.fp.tell() # Start of header data - if compress_type is not None: - zinfo.compress_type = compress_type - if zinfo.compress_type == ZIP_LZMA: - # Compressed data includes an end-of-stream (EOS) marker - zinfo.flag_bits |= 0x02 - - self._writecheck(zinfo) - self._didModify = True - zinfo.CRC = crc32(data) & 0xffffffff # CRC-32 checksum - co = _get_compressor(zinfo.compress_type) - if co: - data = co.compress(data) + co.flush() - zinfo.compress_size = len(data) # Compressed size - else: - zinfo.compress_size = zinfo.file_size - zip64 = zinfo.file_size > ZIP64_LIMIT or \ - zinfo.compress_size > ZIP64_LIMIT - if zip64 and not self._allowZip64: - raise LargeZipFile("Filesize would require ZIP64 extensions") - self.fp.write(zinfo.FileHeader(zip64)) - self.fp.write(data) - if zinfo.flag_bits & 0x08: - # Write CRC and file sizes after the file data - fmt = '<LQQ' if zip64 else '<LLL' - self.fp.write(struct.pack(fmt, zinfo.CRC, zinfo.compress_size, - zinfo.file_size)) - self.fp.flush() - self.filelist.append(zinfo) - self.NameToInfo[zinfo.filename] = zinfo + with self._lock: + try: + self.fp.seek(self.start_dir) + except (AttributeError, io.UnsupportedOperation): + # Some file-like objects can provide tell() but not seek() + pass + zinfo.header_offset = self.fp.tell() # Start of header data + if compress_type is not None: + zinfo.compress_type = compress_type + zinfo.header_offset = self.fp.tell() # Start of header data + if compress_type is not None: + zinfo.compress_type = compress_type + if zinfo.compress_type == ZIP_LZMA: + # Compressed data includes an end-of-stream (EOS) marker + zinfo.flag_bits |= 0x02 + + self._writecheck(zinfo) + self._didModify = True + zinfo.CRC = crc32(data) & 0xffffffff # CRC-32 checksum + co = _get_compressor(zinfo.compress_type) + if co: + data = co.compress(data) + co.flush() + zinfo.compress_size = len(data) # Compressed size + else: + zinfo.compress_size = zinfo.file_size + zip64 = zinfo.file_size > ZIP64_LIMIT or \ + zinfo.compress_size > ZIP64_LIMIT + if zip64 and not self._allowZip64: + raise LargeZipFile("Filesize would require ZIP64 extensions") + self.fp.write(zinfo.FileHeader(zip64)) + self.fp.write(data) + if zinfo.flag_bits & 0x08: + # Write CRC and file sizes after the file data + fmt = '<LQQ' if zip64 else '<LLL' + self.fp.write(struct.pack(fmt, zinfo.CRC, zinfo.compress_size, + zinfo.file_size)) + self.fp.flush() + self.start_dir = self.fp.tell() + self.filelist.append(zinfo) + self.NameToInfo[zinfo.filename] = zinfo def __del__(self): """Call the "close()" method in case the user forgot.""" @@ -1473,111 +1556,124 @@ class ZipFile: try: if self.mode in ("w", "a") and self._didModify: # write ending records - pos1 = self.fp.tell() - for zinfo in self.filelist: # write central directory - dt = zinfo.date_time - dosdate = (dt[0] - 1980) << 9 | dt[1] << 5 | dt[2] - dostime = dt[3] << 11 | dt[4] << 5 | (dt[5] // 2) - extra = [] - if zinfo.file_size > ZIP64_LIMIT \ - or zinfo.compress_size > ZIP64_LIMIT: - extra.append(zinfo.file_size) - extra.append(zinfo.compress_size) - file_size = 0xffffffff - compress_size = 0xffffffff - else: - file_size = zinfo.file_size - compress_size = zinfo.compress_size - - if zinfo.header_offset > ZIP64_LIMIT: - extra.append(zinfo.header_offset) - header_offset = 0xffffffff - else: - header_offset = zinfo.header_offset - - extra_data = zinfo.extra - min_version = 0 - if extra: - # Append a ZIP64 field to the extra's - extra_data = struct.pack( - '<HH' + 'Q'*len(extra), - 1, 8*len(extra), *extra) + extra_data - - min_version = ZIP64_VERSION - - if zinfo.compress_type == ZIP_BZIP2: - min_version = max(BZIP2_VERSION, min_version) - elif zinfo.compress_type == ZIP_LZMA: - min_version = max(LZMA_VERSION, min_version) - - extract_version = max(min_version, zinfo.extract_version) - create_version = max(min_version, zinfo.create_version) + with self._lock: try: - filename, flag_bits = zinfo._encodeFilenameFlags() - centdir = struct.pack(structCentralDir, - stringCentralDir, create_version, - zinfo.create_system, extract_version, zinfo.reserved, - flag_bits, zinfo.compress_type, dostime, dosdate, - zinfo.CRC, compress_size, file_size, - len(filename), len(extra_data), len(zinfo.comment), - 0, zinfo.internal_attr, zinfo.external_attr, - header_offset) - except DeprecationWarning: - print((structCentralDir, stringCentralDir, create_version, - zinfo.create_system, extract_version, zinfo.reserved, - zinfo.flag_bits, zinfo.compress_type, dostime, dosdate, - zinfo.CRC, compress_size, file_size, - len(zinfo.filename), len(extra_data), len(zinfo.comment), - 0, zinfo.internal_attr, zinfo.external_attr, - header_offset), file=sys.stderr) - raise - self.fp.write(centdir) - self.fp.write(filename) - self.fp.write(extra_data) - self.fp.write(zinfo.comment) - - pos2 = self.fp.tell() - # Write end-of-zip-archive record - centDirCount = len(self.filelist) - centDirSize = pos2 - pos1 - centDirOffset = pos1 - requires_zip64 = None - if centDirCount > ZIP_FILECOUNT_LIMIT: - requires_zip64 = "Files count" - elif centDirOffset > ZIP64_LIMIT: - requires_zip64 = "Central directory offset" - elif centDirSize > ZIP64_LIMIT: - requires_zip64 = "Central directory size" - if requires_zip64: - # Need to write the ZIP64 end-of-archive records - if not self._allowZip64: - raise LargeZipFile(requires_zip64 + - " would require ZIP64 extensions") - zip64endrec = struct.pack( - structEndArchive64, stringEndArchive64, - 44, 45, 45, 0, 0, centDirCount, centDirCount, - centDirSize, centDirOffset) - self.fp.write(zip64endrec) - - zip64locrec = struct.pack( - structEndArchive64Locator, - stringEndArchive64Locator, 0, pos2, 1) - self.fp.write(zip64locrec) - centDirCount = min(centDirCount, 0xFFFF) - centDirSize = min(centDirSize, 0xFFFFFFFF) - centDirOffset = min(centDirOffset, 0xFFFFFFFF) - - endrec = struct.pack(structEndArchive, stringEndArchive, - 0, 0, centDirCount, centDirCount, - centDirSize, centDirOffset, len(self._comment)) - self.fp.write(endrec) - self.fp.write(self._comment) - self.fp.flush() + self.fp.seek(self.start_dir) + except (AttributeError, io.UnsupportedOperation): + # Some file-like objects can provide tell() but not seek() + pass + self._write_end_record() finally: fp = self.fp self.fp = None - if not self._filePassed: - fp.close() + self._fpclose(fp) + + def _write_end_record(self): + for zinfo in self.filelist: # write central directory + dt = zinfo.date_time + dosdate = (dt[0] - 1980) << 9 | dt[1] << 5 | dt[2] + dostime = dt[3] << 11 | dt[4] << 5 | (dt[5] // 2) + extra = [] + if zinfo.file_size > ZIP64_LIMIT \ + or zinfo.compress_size > ZIP64_LIMIT: + extra.append(zinfo.file_size) + extra.append(zinfo.compress_size) + file_size = 0xffffffff + compress_size = 0xffffffff + else: + file_size = zinfo.file_size + compress_size = zinfo.compress_size + + if zinfo.header_offset > ZIP64_LIMIT: + extra.append(zinfo.header_offset) + header_offset = 0xffffffff + else: + header_offset = zinfo.header_offset + + extra_data = zinfo.extra + min_version = 0 + if extra: + # Append a ZIP64 field to the extra's + extra_data = struct.pack( + '<HH' + 'Q'*len(extra), + 1, 8*len(extra), *extra) + extra_data + + min_version = ZIP64_VERSION + + if zinfo.compress_type == ZIP_BZIP2: + min_version = max(BZIP2_VERSION, min_version) + elif zinfo.compress_type == ZIP_LZMA: + min_version = max(LZMA_VERSION, min_version) + + extract_version = max(min_version, zinfo.extract_version) + create_version = max(min_version, zinfo.create_version) + try: + filename, flag_bits = zinfo._encodeFilenameFlags() + centdir = struct.pack(structCentralDir, + stringCentralDir, create_version, + zinfo.create_system, extract_version, zinfo.reserved, + flag_bits, zinfo.compress_type, dostime, dosdate, + zinfo.CRC, compress_size, file_size, + len(filename), len(extra_data), len(zinfo.comment), + 0, zinfo.internal_attr, zinfo.external_attr, + header_offset) + except DeprecationWarning: + print((structCentralDir, stringCentralDir, create_version, + zinfo.create_system, extract_version, zinfo.reserved, + zinfo.flag_bits, zinfo.compress_type, dostime, dosdate, + zinfo.CRC, compress_size, file_size, + len(zinfo.filename), len(extra_data), len(zinfo.comment), + 0, zinfo.internal_attr, zinfo.external_attr, + header_offset), file=sys.stderr) + raise + self.fp.write(centdir) + self.fp.write(filename) + self.fp.write(extra_data) + self.fp.write(zinfo.comment) + + pos2 = self.fp.tell() + # Write end-of-zip-archive record + centDirCount = len(self.filelist) + centDirSize = pos2 - self.start_dir + centDirOffset = self.start_dir + requires_zip64 = None + if centDirCount > ZIP_FILECOUNT_LIMIT: + requires_zip64 = "Files count" + elif centDirOffset > ZIP64_LIMIT: + requires_zip64 = "Central directory offset" + elif centDirSize > ZIP64_LIMIT: + requires_zip64 = "Central directory size" + if requires_zip64: + # Need to write the ZIP64 end-of-archive records + if not self._allowZip64: + raise LargeZipFile(requires_zip64 + + " would require ZIP64 extensions") + zip64endrec = struct.pack( + structEndArchive64, stringEndArchive64, + 44, 45, 45, 0, 0, centDirCount, centDirCount, + centDirSize, centDirOffset) + self.fp.write(zip64endrec) + + zip64locrec = struct.pack( + structEndArchive64Locator, + stringEndArchive64Locator, 0, pos2, 1) + self.fp.write(zip64locrec) + centDirCount = min(centDirCount, 0xFFFF) + centDirSize = min(centDirSize, 0xFFFFFFFF) + centDirOffset = min(centDirOffset, 0xFFFFFFFF) + + endrec = struct.pack(structEndArchive, stringEndArchive, + 0, 0, centDirCount, centDirCount, + centDirSize, centDirOffset, len(self._comment)) + self.fp.write(endrec) + self.fp.write(self._comment) + self.fp.flush() + + def _fpclose(self, fp): + assert self._fileRefCnt > 0 + self._fileRefCnt -= 1 + if not self._fileRefCnt and not self._filePassed: + fp.close() class PyZipFile(ZipFile): |
