summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Doc/library/stdtypes.rst103
-rw-r--r--Doc/library/sys.rst24
-rw-r--r--Include/pyport.h14
-rw-r--r--Lib/decimal.py80
-rw-r--r--Lib/fractions.py31
-rw-r--r--Lib/test/test_float.py9
-rw-r--r--Lib/test/test_numeric_tower.py151
-rw-r--r--Lib/test/test_sys.py17
-rw-r--r--Misc/NEWS5
-rw-r--r--Objects/complexobject.c18
-rw-r--r--Objects/longobject.c39
-rw-r--r--Objects/object.c136
-rw-r--r--Objects/typeobject.c26
-rw-r--r--Python/sysmodule.c56
14 files changed, 569 insertions, 140 deletions
diff --git a/Doc/library/stdtypes.rst b/Doc/library/stdtypes.rst
index c5d6766..b07c7f8 100644
--- a/Doc/library/stdtypes.rst
+++ b/Doc/library/stdtypes.rst
@@ -595,6 +595,109 @@ hexadecimal string representing the same number::
'0x1.d380000000000p+11'
+.. _numeric-hash:
+
+Hashing of numeric types
+------------------------
+
+For numbers ``x`` and ``y``, possibly of different types, it's a requirement
+that ``hash(x) == hash(y)`` whenever ``x == y`` (see the :meth:`__hash__`
+method documentation for more details). For ease of implementation and
+efficiency across a variety of numeric types (including :class:`int`,
+:class:`float`, :class:`decimal.Decimal` and :class:`fractions.Fraction`)
+Python's hash for numeric types is based on a single mathematical function
+that's defined for any rational number, and hence applies to all instances of
+:class:`int` and :class:`fraction.Fraction`, and all finite instances of
+:class:`float` and :class:`decimal.Decimal`. Essentially, this function is
+given by reduction modulo ``P`` for a fixed prime ``P``. The value of ``P`` is
+made available to Python as the :attr:`modulus` attribute of
+:data:`sys.hash_info`.
+
+.. impl-detail::
+
+ Currently, the prime used is ``P = 2**31 - 1`` on machines with 32-bit C
+ longs and ``P = 2**61 - 1`` on machines with 64-bit C longs.
+
+Here are the rules in detail:
+
+ - If ``x = m / n`` is a nonnegative rational number and ``n`` is not divisible
+ by ``P``, define ``hash(x)`` as ``m * invmod(n, P) % P``, where ``invmod(n,
+ P)`` gives the inverse of ``n`` modulo ``P``.
+
+ - If ``x = m / n`` is a nonnegative rational number and ``n`` is
+ divisible by ``P`` (but ``m`` is not) then ``n`` has no inverse
+ modulo ``P`` and the rule above doesn't apply; in this case define
+ ``hash(x)`` to be the constant value ``sys.hash_info.inf``.
+
+ - If ``x = m / n`` is a negative rational number define ``hash(x)``
+ as ``-hash(-x)``. If the resulting hash is ``-1``, replace it with
+ ``-2``.
+
+ - The particular values ``sys.hash_info.inf``, ``-sys.hash_info.inf``
+ and ``sys.hash_info.nan`` are used as hash values for positive
+ infinity, negative infinity, or nans (respectively). (All hashable
+ nans have the same hash value.)
+
+ - For a :class:`complex` number ``z``, the hash values of the real
+ and imaginary parts are combined by computing ``hash(z.real) +
+ sys.hash_info.imag * hash(z.imag)``, reduced modulo
+ ``2**sys.hash_info.width`` so that it lies in
+ ``range(-2**(sys.hash_info.width - 1), 2**(sys.hash_info.width -
+ 1))``. Again, if the result is ``-1``, it's replaced with ``-2``.
+
+
+To clarify the above rules, here's some example Python code,
+equivalent to the builtin hash, for computing the hash of a rational
+number, :class:`float`, or :class:`complex`::
+
+
+ import sys, math
+
+ def hash_fraction(m, n):
+ """Compute the hash of a rational number m / n.
+
+ Assumes m and n are integers, with n positive.
+ Equivalent to hash(fractions.Fraction(m, n)).
+
+ """
+ P = sys.hash_info.modulus
+ # Remove common factors of P. (Unnecessary if m and n already coprime.)
+ while m % P == n % P == 0:
+ m, n = m // P, n // P
+
+ if n % P == 0:
+ hash_ = sys.hash_info.inf
+ else:
+ # Fermat's Little Theorem: pow(n, P-1, P) is 1, so
+ # pow(n, P-2, P) gives the inverse of n modulo P.
+ hash_ = (abs(m) % P) * pow(n, P - 2, P) % P
+ if m < 0:
+ hash_ = -hash_
+ if hash_ == -1:
+ hash_ = -2
+ return hash_
+
+ def hash_float(x):
+ """Compute the hash of a float x."""
+
+ if math.isnan(x):
+ return sys.hash_info.nan
+ elif math.isinf(x):
+ return sys.hash_info.inf if x > 0 else -sys.hash_info.inf
+ else:
+ return hash_fraction(*x.as_integer_ratio())
+
+ def hash_complex(z):
+ """Compute the hash of a complex number z."""
+
+ hash_ = hash_float(z.real) + sys.hash_info.imag * hash_float(z.imag)
+ # do a signed reduction modulo 2**sys.hash_info.width
+ M = 2**(sys.hash_info.width - 1)
+ hash_ = (hash_ & (M - 1)) - (hash & M)
+ if hash_ == -1:
+ hash_ == -2
+ return hash_
+
.. _typeiter:
Iterator Types
diff --git a/Doc/library/sys.rst b/Doc/library/sys.rst
index 3b9bbb0..e2a2f72 100644
--- a/Doc/library/sys.rst
+++ b/Doc/library/sys.rst
@@ -446,6 +446,30 @@ always available.
Changed to a named tuple and added *service_pack_minor*,
*service_pack_major*, *suite_mask*, and *product_type*.
+
+.. data:: hash_info
+
+ A structseq giving parameters of the numeric hash implementation. For
+ more details about hashing of numeric types, see :ref:`numeric-hash`.
+
+ +---------------------+--------------------------------------------------+
+ | attribute | explanation |
+ +=====================+==================================================+
+ | :const:`width` | width in bits used for hash values |
+ +---------------------+--------------------------------------------------+
+ | :const:`modulus` | prime modulus P used for numeric hash scheme |
+ +---------------------+--------------------------------------------------+
+ | :const:`inf` | hash value returned for a positive infinity |
+ +---------------------+--------------------------------------------------+
+ | :const:`nan` | hash value returned for a nan |
+ +---------------------+--------------------------------------------------+
+ | :const:`imag` | multiplier used for the imaginary part of a |
+ | | complex number |
+ +---------------------+--------------------------------------------------+
+
+ .. versionadded:: 3.2
+
+
.. data:: hexversion
The version number encoded as a single integer. This is guaranteed to increase
diff --git a/Include/pyport.h b/Include/pyport.h
index dc5c1fd..9561285 100644
--- a/Include/pyport.h
+++ b/Include/pyport.h
@@ -126,6 +126,20 @@ Used in: PY_LONG_LONG
#endif
#endif
+/* Parameters used for the numeric hash implementation. See notes for
+ _PyHash_Double in Objects/object.c. Numeric hashes are based on
+ reduction modulo the prime 2**_PyHASH_BITS - 1. */
+
+#if SIZEOF_LONG >= 8
+#define _PyHASH_BITS 61
+#else
+#define _PyHASH_BITS 31
+#endif
+#define _PyHASH_MODULUS ((1UL << _PyHASH_BITS) - 1)
+#define _PyHASH_INF 314159
+#define _PyHASH_NAN 0
+#define _PyHASH_IMAG 1000003UL
+
/* uintptr_t is the C9X name for an unsigned integral type such that a
* legitimate void* can be cast to uintptr_t and then back to void* again
* without loss of information. Similarly for intptr_t, wrt a signed
diff --git a/Lib/decimal.py b/Lib/decimal.py
index cc71cd8..29ce398 100644
--- a/Lib/decimal.py
+++ b/Lib/decimal.py
@@ -862,7 +862,7 @@ class Decimal(object):
# that specified by IEEE 754.
def __eq__(self, other, context=None):
- other = _convert_other(other, allow_float=True)
+ other = _convert_other(other, allow_float = True)
if other is NotImplemented:
return other
if self._check_nans(other, context):
@@ -870,7 +870,7 @@ class Decimal(object):
return self._cmp(other) == 0
def __ne__(self, other, context=None):
- other = _convert_other(other, allow_float=True)
+ other = _convert_other(other, allow_float = True)
if other is NotImplemented:
return other
if self._check_nans(other, context):
@@ -879,7 +879,7 @@ class Decimal(object):
def __lt__(self, other, context=None):
- other = _convert_other(other, allow_float=True)
+ other = _convert_other(other, allow_float = True)
if other is NotImplemented:
return other
ans = self._compare_check_nans(other, context)
@@ -888,7 +888,7 @@ class Decimal(object):
return self._cmp(other) < 0
def __le__(self, other, context=None):
- other = _convert_other(other, allow_float=True)
+ other = _convert_other(other, allow_float = True)
if other is NotImplemented:
return other
ans = self._compare_check_nans(other, context)
@@ -897,7 +897,7 @@ class Decimal(object):
return self._cmp(other) <= 0
def __gt__(self, other, context=None):
- other = _convert_other(other, allow_float=True)
+ other = _convert_other(other, allow_float = True)
if other is NotImplemented:
return other
ans = self._compare_check_nans(other, context)
@@ -906,7 +906,7 @@ class Decimal(object):
return self._cmp(other) > 0
def __ge__(self, other, context=None):
- other = _convert_other(other, allow_float=True)
+ other = _convert_other(other, allow_float = True)
if other is NotImplemented:
return other
ans = self._compare_check_nans(other, context)
@@ -935,55 +935,28 @@ class Decimal(object):
def __hash__(self):
"""x.__hash__() <==> hash(x)"""
- # Decimal integers must hash the same as the ints
- #
- # The hash of a nonspecial noninteger Decimal must depend only
- # on the value of that Decimal, and not on its representation.
- # For example: hash(Decimal('100E-1')) == hash(Decimal('10')).
-
- # Equality comparisons involving signaling nans can raise an
- # exception; since equality checks are implicitly and
- # unpredictably used when checking set and dict membership, we
- # prevent signaling nans from being used as set elements or
- # dict keys by making __hash__ raise an exception.
+
+ # 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():
- # 0 to match hash(float('nan'))
- return 0
+ return _PyHASH_NAN
else:
- # values chosen to match hash(float('inf')) and
- # hash(float('-inf')).
if self._sign:
- return -271828
+ return -_PyHASH_INF
else:
- return 314159
-
- # In Python 2.7, we're allowing comparisons (but not
- # arithmetic operations) between floats and Decimals; so if
- # a Decimal instance is exactly representable as a float then
- # its hash should match that of the float.
- self_as_float = float(self)
- if Decimal.from_float(self_as_float) == self:
- return hash(self_as_float)
-
- if self._isinteger():
- op = _WorkRep(self.to_integral_value())
- # to make computation feasible for Decimals with large
- # exponent, we use the fact that hash(n) == hash(m) for
- # any two nonzero integers n and m such that (i) n and m
- # have the same sign, and (ii) n is congruent to m modulo
- # 2**64-1. So we can replace hash((-1)**s*c*10**e) with
- # hash((-1)**s*c*pow(10, e, 2**64-1).
- return hash((-1)**op.sign*op.int*pow(10, op.exp, 2**64-1))
- # The value of a nonzero nonspecial Decimal instance is
- # faithfully represented by the triple consisting of its sign,
- # its adjusted exponent, and its coefficient with trailing
- # zeros removed.
- return hash((self._sign,
- self._exp+len(self._int),
- self._int.rstrip('0')))
+ 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
+ return hash_ if self >= 0 else -hash_
def as_tuple(self):
"""Represents the number as a triple tuple.
@@ -6218,6 +6191,17 @@ _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
+import sys
+_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
+del sys
+
+# _PyHASH_10INV is the inverse of 10 modulo the prime _PyHASH_MODULUS
+_PyHASH_10INV = pow(10, _PyHASH_MODULUS - 2, _PyHASH_MODULUS)
if __name__ == '__main__':
diff --git a/Lib/fractions.py b/Lib/fractions.py
index fc8a12c..51e67e2 100644
--- a/Lib/fractions.py
+++ b/Lib/fractions.py
@@ -8,6 +8,7 @@ import math
import numbers
import operator
import re
+import sys
__all__ = ['Fraction', 'gcd']
@@ -23,6 +24,12 @@ def gcd(a, b):
a, b = b, a%b
return a
+# Constants related to the hash implementation; hash(x) is based
+# on the reduction of x modulo the prime _PyHASH_MODULUS.
+_PyHASH_MODULUS = sys.hash_info.modulus
+# Value to be used for rationals that reduce to infinity modulo
+# _PyHASH_MODULUS.
+_PyHASH_INF = sys.hash_info.inf
_RATIONAL_FORMAT = re.compile(r"""
\A\s* # optional whitespace at the start, then
@@ -528,16 +535,22 @@ class Fraction(numbers.Rational):
"""
# XXX since this method is expensive, consider caching the result
- if self._denominator == 1:
- # Get integers right.
- return hash(self._numerator)
- # Expensive check, but definitely correct.
- if self == float(self):
- return hash(float(self))
+
+ # In order to make sure that the hash of a Fraction agrees
+ # with the hash of a numerically equal integer, float or
+ # Decimal instance, we follow the rules for numeric hashes
+ # outlined in the documentation. (See library docs, 'Built-in
+ # Types').
+
+ # dinv is the inverse of self._denominator modulo the prime
+ # _PyHASH_MODULUS, or 0 if self._denominator is divisible by
+ # _PyHASH_MODULUS.
+ dinv = pow(self._denominator, _PyHASH_MODULUS - 2, _PyHASH_MODULUS)
+ if not dinv:
+ hash_ = _PyHASH_INF
else:
- # Use tuple's hash to avoid a high collision rate on
- # simple fractions.
- return hash((self._numerator, self._denominator))
+ hash_ = abs(self._numerator) * dinv % _PyHASH_MODULUS
+ return hash_ if self >= 0 else -hash_
def __eq__(a, b):
"""a == b"""
diff --git a/Lib/test/test_float.py b/Lib/test/test_float.py
index b52b1db..cabeb16 100644
--- a/Lib/test/test_float.py
+++ b/Lib/test/test_float.py
@@ -914,15 +914,6 @@ class InfNanTest(unittest.TestCase):
self.assertFalse(NAN.is_inf())
self.assertFalse((0.).is_inf())
- def test_hash_inf(self):
- # the actual values here should be regarded as an
- # implementation detail, but they need to be
- # identical to those used in the Decimal module.
- self.assertEqual(hash(float('inf')), 314159)
- self.assertEqual(hash(float('-inf')), -271828)
- self.assertEqual(hash(float('nan')), 0)
-
-
fromHex = float.fromhex
toHex = float.hex
class HexFloatTestCase(unittest.TestCase):
diff --git a/Lib/test/test_numeric_tower.py b/Lib/test/test_numeric_tower.py
new file mode 100644
index 0000000..eafdb0f
--- /dev/null
+++ b/Lib/test/test_numeric_tower.py
@@ -0,0 +1,151 @@
+# test interactions betwen int, float, Decimal and Fraction
+
+import unittest
+import random
+import math
+import sys
+import operator
+from test.support import run_unittest
+
+from decimal import Decimal as D
+from fractions import Fraction as F
+
+# Constants related to the hash implementation; hash(x) is based
+# on the reduction of x modulo the prime _PyHASH_MODULUS.
+_PyHASH_MODULUS = sys.hash_info.modulus
+_PyHASH_INF = sys.hash_info.inf
+
+class HashTest(unittest.TestCase):
+ def check_equal_hash(self, x, y):
+ # check both that x and y are equal and that their hashes are equal
+ self.assertEqual(hash(x), hash(y),
+ "got different hashes for {!r} and {!r}".format(x, y))
+ self.assertEqual(x, y)
+
+ def test_bools(self):
+ self.check_equal_hash(False, 0)
+ self.check_equal_hash(True, 1)
+
+ def test_integers(self):
+ # check that equal values hash equal
+
+ # exact integers
+ for i in range(-1000, 1000):
+ self.check_equal_hash(i, float(i))
+ self.check_equal_hash(i, D(i))
+ self.check_equal_hash(i, F(i))
+
+ # the current hash is based on reduction modulo 2**n-1 for some
+ # n, so pay special attention to numbers of the form 2**n and 2**n-1.
+ for i in range(100):
+ n = 2**i - 1
+ if n == int(float(n)):
+ self.check_equal_hash(n, float(n))
+ self.check_equal_hash(-n, -float(n))
+ self.check_equal_hash(n, D(n))
+ self.check_equal_hash(n, F(n))
+ self.check_equal_hash(-n, D(-n))
+ self.check_equal_hash(-n, F(-n))
+
+ n = 2**i
+ self.check_equal_hash(n, float(n))
+ self.check_equal_hash(-n, -float(n))
+ self.check_equal_hash(n, D(n))
+ self.check_equal_hash(n, F(n))
+ self.check_equal_hash(-n, D(-n))
+ self.check_equal_hash(-n, F(-n))
+
+ # random values of various sizes
+ for _ in range(1000):
+ e = random.randrange(300)
+ n = random.randrange(-10**e, 10**e)
+ self.check_equal_hash(n, D(n))
+ self.check_equal_hash(n, F(n))
+ if n == int(float(n)):
+ self.check_equal_hash(n, float(n))
+
+ def test_binary_floats(self):
+ # check that floats hash equal to corresponding Fractions and Decimals
+
+ # floats that are distinct but numerically equal should hash the same
+ self.check_equal_hash(0.0, -0.0)
+
+ # zeros
+ self.check_equal_hash(0.0, D(0))
+ self.check_equal_hash(-0.0, D(0))
+ self.check_equal_hash(-0.0, D('-0.0'))
+ self.check_equal_hash(0.0, F(0))
+
+ # infinities and nans
+ self.check_equal_hash(float('inf'), D('inf'))
+ self.check_equal_hash(float('-inf'), D('-inf'))
+
+ for _ in range(1000):
+ x = random.random() * math.exp(random.random()*200.0 - 100.0)
+ self.check_equal_hash(x, D.from_float(x))
+ self.check_equal_hash(x, F.from_float(x))
+
+ def test_complex(self):
+ # complex numbers with zero imaginary part should hash equal to
+ # the corresponding float
+
+ test_values = [0.0, -0.0, 1.0, -1.0, 0.40625, -5136.5,
+ float('inf'), float('-inf')]
+
+ for zero in -0.0, 0.0:
+ for value in test_values:
+ self.check_equal_hash(value, complex(value, zero))
+
+ def test_decimals(self):
+ # check that Decimal instances that have different representations
+ # but equal values give the same hash
+ zeros = ['0', '-0', '0.0', '-0.0e10', '000e-10']
+ for zero in zeros:
+ self.check_equal_hash(D(zero), D(0))
+
+ self.check_equal_hash(D('1.00'), D(1))
+ self.check_equal_hash(D('1.00000'), D(1))
+ self.check_equal_hash(D('-1.00'), D(-1))
+ self.check_equal_hash(D('-1.00000'), D(-1))
+ self.check_equal_hash(D('123e2'), D(12300))
+ self.check_equal_hash(D('1230e1'), D(12300))
+ self.check_equal_hash(D('12300'), D(12300))
+ self.check_equal_hash(D('12300.0'), D(12300))
+ self.check_equal_hash(D('12300.00'), D(12300))
+ self.check_equal_hash(D('12300.000'), D(12300))
+
+ def test_fractions(self):
+ # check special case for fractions where either the numerator
+ # or the denominator is a multiple of _PyHASH_MODULUS
+ self.assertEqual(hash(F(1, _PyHASH_MODULUS)), _PyHASH_INF)
+ self.assertEqual(hash(F(-1, 3*_PyHASH_MODULUS)), -_PyHASH_INF)
+ self.assertEqual(hash(F(7*_PyHASH_MODULUS, 1)), 0)
+ self.assertEqual(hash(F(-_PyHASH_MODULUS, 1)), 0)
+
+ def test_hash_normalization(self):
+ # Test for a bug encountered while changing long_hash.
+ #
+ # Given objects x and y, it should be possible for y's
+ # __hash__ method to return hash(x) in order to ensure that
+ # hash(x) == hash(y). But hash(x) is not exactly equal to the
+ # result of x.__hash__(): there's some internal normalization
+ # to make sure that the result fits in a C long, and is not
+ # equal to the invalid hash value -1. This internal
+ # normalization must therefore not change the result of
+ # hash(x) for any x.
+
+ class HalibutProxy:
+ def __hash__(self):
+ return hash('halibut')
+ def __eq__(self, other):
+ return other == 'halibut'
+
+ x = {'halibut', HalibutProxy()}
+ self.assertEqual(len(x), 1)
+
+
+def test_main():
+ run_unittest(HashTest)
+
+if __name__ == '__main__':
+ test_main()
diff --git a/Lib/test/test_sys.py b/Lib/test/test_sys.py
index 2caf09f..c056f9a 100644
--- a/Lib/test/test_sys.py
+++ b/Lib/test/test_sys.py
@@ -426,6 +426,23 @@ class SysModuleTest(unittest.TestCase):
self.assertEqual(type(sys.int_info.bits_per_digit), int)
self.assertEqual(type(sys.int_info.sizeof_digit), int)
self.assertIsInstance(sys.hexversion, int)
+
+ self.assertEqual(len(sys.hash_info), 5)
+ self.assertLess(sys.hash_info.modulus, 2**sys.hash_info.width)
+ # sys.hash_info.modulus should be a prime; we do a quick
+ # probable primality test (doesn't exclude the possibility of
+ # a Carmichael number)
+ for x in range(1, 100):
+ self.assertEqual(
+ pow(x, sys.hash_info.modulus-1, sys.hash_info.modulus),
+ 1,
+ "sys.hash_info.modulus {} is a non-prime".format(
+ sys.hash_info.modulus)
+ )
+ self.assertIsInstance(sys.hash_info.inf, int)
+ self.assertIsInstance(sys.hash_info.nan, int)
+ self.assertIsInstance(sys.hash_info.imag, int)
+
self.assertIsInstance(sys.maxsize, int)
self.assertIsInstance(sys.maxunicode, int)
self.assertIsInstance(sys.platform, str)
diff --git a/Misc/NEWS b/Misc/NEWS
index 498c4ab..36f374b 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -12,6 +12,11 @@ What's New in Python 3.2 Alpha 1?
Core and Builtins
-----------------
+- Issue #8188: Introduce a new scheme for computing hashes of numbers
+ (instances of int, float, complex, decimal.Decimal and
+ fractions.Fraction) that makes it easy to maintain the invariant
+ that hash(x) == hash(y) whenever x and y have equal value.
+
- Issue #8748: Fix two issues with comparisons between complex and integer
objects. (1) The comparison could incorrectly return True in some cases
(2**53+1 == complex(2**53) == 2**53), breaking transivity of equality.
diff --git a/Objects/complexobject.c b/Objects/complexobject.c
index 9e1e217..7594c88 100644
--- a/Objects/complexobject.c
+++ b/Objects/complexobject.c
@@ -403,12 +403,12 @@ complex_str(PyComplexObject *v)
static long
complex_hash(PyComplexObject *v)
{
- long hashreal, hashimag, combined;
- hashreal = _Py_HashDouble(v->cval.real);
- if (hashreal == -1)
+ unsigned long hashreal, hashimag, combined;
+ hashreal = (unsigned long)_Py_HashDouble(v->cval.real);
+ if (hashreal == (unsigned long)-1)
return -1;
- hashimag = _Py_HashDouble(v->cval.imag);
- if (hashimag == -1)
+ hashimag = (unsigned long)_Py_HashDouble(v->cval.imag);
+ if (hashimag == (unsigned long)-1)
return -1;
/* Note: if the imaginary part is 0, hashimag is 0 now,
* so the following returns hashreal unchanged. This is
@@ -416,10 +416,10 @@ complex_hash(PyComplexObject *v)
* compare equal must have the same hash value, so that
* hash(x + 0*j) must equal hash(x).
*/
- combined = hashreal + 1000003 * hashimag;
- if (combined == -1)
- combined = -2;
- return combined;
+ combined = hashreal + _PyHASH_IMAG * hashimag;
+ if (combined == (unsigned long)-1)
+ combined = (unsigned long)-2;
+ return (long)combined;
}
/* This macro may return! */
diff --git a/Objects/longobject.c b/Objects/longobject.c
index 850396b..564d1a0 100644
--- a/Objects/longobject.c
+++ b/Objects/longobject.c
@@ -2571,18 +2571,37 @@ long_hash(PyLongObject *v)
sign = -1;
i = -(i);
}
- /* The following loop produces a C unsigned long x such that x is
- congruent to the absolute value of v modulo ULONG_MAX. The
- resulting x is nonzero if and only if v is. */
while (--i >= 0) {
- /* Force a native long #-bits (32 or 64) circular shift */
- x = (x >> (8*SIZEOF_LONG-PyLong_SHIFT)) | (x << PyLong_SHIFT);
+ /* Here x is a quantity in the range [0, _PyHASH_MODULUS); we
+ want to compute x * 2**PyLong_SHIFT + v->ob_digit[i] modulo
+ _PyHASH_MODULUS.
+
+ The computation of x * 2**PyLong_SHIFT % _PyHASH_MODULUS
+ amounts to a rotation of the bits of x. To see this, write
+
+ x * 2**PyLong_SHIFT = y * 2**_PyHASH_BITS + z
+
+ where y = x >> (_PyHASH_BITS - PyLong_SHIFT) gives the top
+ PyLong_SHIFT bits of x (those that are shifted out of the
+ original _PyHASH_BITS bits, and z = (x << PyLong_SHIFT) &
+ _PyHASH_MODULUS gives the bottom _PyHASH_BITS - PyLong_SHIFT
+ bits of x, shifted up. Then since 2**_PyHASH_BITS is
+ congruent to 1 modulo _PyHASH_MODULUS, y*2**_PyHASH_BITS is
+ congruent to y modulo _PyHASH_MODULUS. So
+
+ x * 2**PyLong_SHIFT = y + z (mod _PyHASH_MODULUS).
+
+ The right-hand side is just the result of rotating the
+ _PyHASH_BITS bits of x left by PyLong_SHIFT places; since
+ not all _PyHASH_BITS bits of x are 1s, the same is true
+ after rotation, so 0 <= y+z < _PyHASH_MODULUS and y + z is
+ the reduction of x*2**PyLong_SHIFT modulo
+ _PyHASH_MODULUS. */
+ x = ((x << PyLong_SHIFT) & _PyHASH_MODULUS) |
+ (x >> (_PyHASH_BITS - PyLong_SHIFT));
x += v->ob_digit[i];
- /* If the addition above overflowed we compensate by
- incrementing. This preserves the value modulo
- ULONG_MAX. */
- if (x < v->ob_digit[i])
- x++;
+ if (x >= _PyHASH_MODULUS)
+ x -= _PyHASH_MODULUS;
}
x = x * sign;
if (x == (unsigned long)-1)
diff --git a/Objects/object.c b/Objects/object.c
index 0802348..76d018f 100644
--- a/Objects/object.c
+++ b/Objects/object.c
@@ -647,63 +647,101 @@ PyObject_RichCompareBool(PyObject *v, PyObject *w, int op)
All the utility functions (_Py_Hash*()) return "-1" to signify an error.
*/
+/* For numeric types, the hash of a number x is based on the reduction
+ of x modulo the prime P = 2**_PyHASH_BITS - 1. It's designed so that
+ hash(x) == hash(y) whenever x and y are numerically equal, even if
+ x and y have different types.
+
+ A quick summary of the hashing strategy:
+
+ (1) First define the 'reduction of x modulo P' for any rational
+ number x; this is a standard extension of the usual notion of
+ reduction modulo P for integers. If x == p/q (written in lowest
+ terms), the reduction is interpreted as the reduction of p times
+ the inverse of the reduction of q, all modulo P; if q is exactly
+ divisible by P then define the reduction to be infinity. So we've
+ got a well-defined map
+
+ reduce : { rational numbers } -> { 0, 1, 2, ..., P-1, infinity }.
+
+ (2) Now for a rational number x, define hash(x) by:
+
+ reduce(x) if x >= 0
+ -reduce(-x) if x < 0
+
+ If the result of the reduction is infinity (this is impossible for
+ integers, floats and Decimals) then use the predefined hash value
+ _PyHASH_INF for x >= 0, or -_PyHASH_INF for x < 0, instead.
+ _PyHASH_INF, -_PyHASH_INF and _PyHASH_NAN are also used for the
+ hashes of float and Decimal infinities and nans.
+
+ A selling point for the above strategy is that it makes it possible
+ to compute hashes of decimal and binary floating-point numbers
+ efficiently, even if the exponent of the binary or decimal number
+ is large. The key point is that
+
+ reduce(x * y) == reduce(x) * reduce(y) (modulo _PyHASH_MODULUS)
+
+ provided that {reduce(x), reduce(y)} != {0, infinity}. The reduction of a
+ binary or decimal float is never infinity, since the denominator is a power
+ of 2 (for binary) or a divisor of a power of 10 (for decimal). So we have,
+ for nonnegative x,
+
+ reduce(x * 2**e) == reduce(x) * reduce(2**e) % _PyHASH_MODULUS
+
+ reduce(x * 10**e) == reduce(x) * reduce(10**e) % _PyHASH_MODULUS
+
+ and reduce(10**e) can be computed efficiently by the usual modular
+ exponentiation algorithm. For reduce(2**e) it's even better: since
+ P is of the form 2**n-1, reduce(2**e) is 2**(e mod n), and multiplication
+ by 2**(e mod n) modulo 2**n-1 just amounts to a rotation of bits.
+
+ */
+
long
_Py_HashDouble(double v)
{
- double intpart, fractpart;
- int expo;
- long hipart;
- long x; /* the final hash value */
- /* This is designed so that Python numbers of different types
- * that compare equal hash to the same value; otherwise comparisons
- * of mapping keys will turn out weird.
- */
+ int e, sign;
+ double m;
+ unsigned long x, y;
if (!Py_IS_FINITE(v)) {
if (Py_IS_INFINITY(v))
- return v < 0 ? -271828 : 314159;
+ return v > 0 ? _PyHASH_INF : -_PyHASH_INF;
else
- return 0;
+ return _PyHASH_NAN;
}
- fractpart = modf(v, &intpart);
- if (fractpart == 0.0) {
- /* This must return the same hash as an equal int or long. */
- if (intpart > LONG_MAX/2 || -intpart > LONG_MAX/2) {
- /* Convert to long and use its hash. */
- PyObject *plong; /* converted to Python long */
- plong = PyLong_FromDouble(v);
- if (plong == NULL)
- return -1;
- x = PyObject_Hash(plong);
- Py_DECREF(plong);
- return x;
- }
- /* Fits in a C long == a Python int, so is its own hash. */
- x = (long)intpart;
- if (x == -1)
- x = -2;
- return x;
- }
- /* The fractional part is non-zero, so we don't have to worry about
- * making this match the hash of some other type.
- * Use frexp to get at the bits in the double.
- * Since the VAX D double format has 56 mantissa bits, which is the
- * most of any double format in use, each of these parts may have as
- * many as (but no more than) 56 significant bits.
- * So, assuming sizeof(long) >= 4, each part can be broken into two
- * longs; frexp and multiplication are used to do that.
- * Also, since the Cray double format has 15 exponent bits, which is
- * the most of any double format in use, shifting the exponent field
- * left by 15 won't overflow a long (again assuming sizeof(long) >= 4).
- */
- v = frexp(v, &expo);
- v *= 2147483648.0; /* 2**31 */
- hipart = (long)v; /* take the top 32 bits */
- v = (v - (double)hipart) * 2147483648.0; /* get the next 32 bits */
- x = hipart + (long)v + (expo << 15);
- if (x == -1)
- x = -2;
- return x;
+
+ m = frexp(v, &e);
+
+ sign = 1;
+ if (m < 0) {
+ sign = -1;
+ m = -m;
+ }
+
+ /* process 28 bits at a time; this should work well both for binary
+ and hexadecimal floating point. */
+ x = 0;
+ while (m) {
+ x = ((x << 28) & _PyHASH_MODULUS) | x >> (_PyHASH_BITS - 28);
+ m *= 268435456.0; /* 2**28 */
+ e -= 28;
+ y = (unsigned long)m; /* pull out integer part */
+ m -= y;
+ x += y;
+ if (x >= _PyHASH_MODULUS)
+ x -= _PyHASH_MODULUS;
+ }
+
+ /* adjust for the exponent; first reduce it modulo _PyHASH_BITS */
+ e = e >= 0 ? e % _PyHASH_BITS : _PyHASH_BITS-1-((-1-e) % _PyHASH_BITS);
+ x = ((x << e) & _PyHASH_MODULUS) | x >> (_PyHASH_BITS - e);
+
+ x = x * sign;
+ if (x == (unsigned long)-1)
+ x = (unsigned long)-2;
+ return (long)x;
}
long
diff --git a/Objects/typeobject.c b/Objects/typeobject.c
index 369bac6..adfb0ec 100644
--- a/Objects/typeobject.c
+++ b/Objects/typeobject.c
@@ -4921,6 +4921,7 @@ slot_tp_hash(PyObject *self)
PyObject *func, *res;
static PyObject *hash_str;
long h;
+ int overflow;
func = lookup_method(self, "__hash__", &hash_str);
@@ -4937,14 +4938,27 @@ slot_tp_hash(PyObject *self)
Py_DECREF(func);
if (res == NULL)
return -1;
- if (PyLong_Check(res))
+
+ if (!PyLong_Check(res)) {
+ PyErr_SetString(PyExc_TypeError,
+ "__hash__ method should return an integer");
+ return -1;
+ }
+ /* Transform the PyLong `res` to a C long `h`. For an existing
+ hashable Python object x, hash(x) will always lie within the range
+ of a C long. Therefore our transformation must preserve values
+ that already lie within this range, to ensure that if x.__hash__()
+ returns hash(y) then hash(x) == hash(y). */
+ h = PyLong_AsLongAndOverflow(res, &overflow);
+ if (overflow)
+ /* res was not within the range of a C long, so we're free to
+ use any sufficiently bit-mixing transformation;
+ long.__hash__ will do nicely. */
h = PyLong_Type.tp_hash(res);
- else
- h = PyLong_AsLong(res);
Py_DECREF(res);
- if (h == -1 && !PyErr_Occurred())
- h = -2;
- return h;
+ if (h == -1 && !PyErr_Occurred())
+ h = -2;
+ return h;
}
static PyObject *
diff --git a/Python/sysmodule.c b/Python/sysmodule.c
index 77b120f..4c87d54 100644
--- a/Python/sysmodule.c
+++ b/Python/sysmodule.c
@@ -570,6 +570,57 @@ sys_setrecursionlimit(PyObject *self, PyObject *args)
return Py_None;
}
+static PyTypeObject Hash_InfoType;
+
+PyDoc_STRVAR(hash_info_doc,
+"hash_info\n\
+\n\
+A struct sequence providing parameters used for computing\n\
+numeric hashes. The attributes are read only.");
+
+static PyStructSequence_Field hash_info_fields[] = {
+ {"width", "width of the type used for hashing, in bits"},
+ {"modulus", "prime number giving the modulus on which the hash "
+ "function is based"},
+ {"inf", "value to be used for hash of a positive infinity"},
+ {"nan", "value to be used for hash of a nan"},
+ {"imag", "multiplier used for the imaginary part of a complex number"},
+ {NULL, NULL}
+};
+
+static PyStructSequence_Desc hash_info_desc = {
+ "sys.hash_info",
+ hash_info_doc,
+ hash_info_fields,
+ 5,
+};
+
+PyObject *
+get_hash_info(void)
+{
+ PyObject *hash_info;
+ int field = 0;
+ hash_info = PyStructSequence_New(&Hash_InfoType);
+ if (hash_info == NULL)
+ return NULL;
+ PyStructSequence_SET_ITEM(hash_info, field++,
+ PyLong_FromLong(8*sizeof(long)));
+ PyStructSequence_SET_ITEM(hash_info, field++,
+ PyLong_FromLong(_PyHASH_MODULUS));
+ PyStructSequence_SET_ITEM(hash_info, field++,
+ PyLong_FromLong(_PyHASH_INF));
+ PyStructSequence_SET_ITEM(hash_info, field++,
+ PyLong_FromLong(_PyHASH_NAN));
+ PyStructSequence_SET_ITEM(hash_info, field++,
+ PyLong_FromLong(_PyHASH_IMAG));
+ if (PyErr_Occurred()) {
+ Py_CLEAR(hash_info);
+ return NULL;
+ }
+ return hash_info;
+}
+
+
PyDoc_STRVAR(setrecursionlimit_doc,
"setrecursionlimit(n)\n\
\n\
@@ -1482,6 +1533,11 @@ _PySys_Init(void)
PyFloat_GetInfo());
SET_SYS_FROM_STRING("int_info",
PyLong_GetInfo());
+ /* initialize hash_info */
+ if (Hash_InfoType.tp_name == 0)
+ PyStructSequence_InitType(&Hash_InfoType, &hash_info_desc);
+ SET_SYS_FROM_STRING("hash_info",
+ get_hash_info());
SET_SYS_FROM_STRING("maxunicode",
PyLong_FromLong(PyUnicode_GetMax()));
SET_SYS_FROM_STRING("builtin_module_names",
generated by cgit v0.12 at 2024-10-19 22:17:25 (GMT)