From 86def6cb2b8d6d8c7f239795fa7af57c97a5890d Mon Sep 17 00:00:00 2001 From: Georg Brandl Date: Mon, 21 Jan 2008 20:36:10 +0000 Subject: Merged revisions 60151-60159,60161-60168,60170,60172-60173,60175 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r60151 | christian.heimes | 2008-01-21 14:11:15 +0100 (Mon, 21 Jan 2008) | 1 line A bunch of header files were not listed as dependencies for object files. Changes to files like Parser/parser.h weren't picked up by make. ........ r60152 | georg.brandl | 2008-01-21 15:16:46 +0100 (Mon, 21 Jan 2008) | 3 lines #1087741: make mmap.mmap the type of mmap objects, not a factory function. Allow it to be subclassed. ........ r60153 | georg.brandl | 2008-01-21 15:18:14 +0100 (Mon, 21 Jan 2008) | 2 lines mmap is an extension module. ........ r60154 | georg.brandl | 2008-01-21 17:28:13 +0100 (Mon, 21 Jan 2008) | 2 lines Fix example. ........ r60155 | georg.brandl | 2008-01-21 17:34:07 +0100 (Mon, 21 Jan 2008) | 2 lines #1555501: document plistlib and move it to the general library. ........ r60156 | georg.brandl | 2008-01-21 17:36:00 +0100 (Mon, 21 Jan 2008) | 2 lines Add a stub for bundlebuilder documentation. ........ r60157 | georg.brandl | 2008-01-21 17:46:58 +0100 (Mon, 21 Jan 2008) | 2 lines Removing bundlebuilder docs again -- it's not to be used anymore (see #779825). ........ r60158 | georg.brandl | 2008-01-21 17:51:51 +0100 (Mon, 21 Jan 2008) | 2 lines #997912: acknowledge nested scopes in tutorial. ........ r60159 | vinay.sajip | 2008-01-21 18:02:26 +0100 (Mon, 21 Jan 2008) | 1 line Fix: #1836: Off-by-one bug in TimedRotatingFileHandler rollover calculation. Patch thanks to Kathryn M. Kowalski. ........ r60161 | georg.brandl | 2008-01-21 18:13:03 +0100 (Mon, 21 Jan 2008) | 2 lines Adapt pydoc to new doc URLs. ........ r60162 | georg.brandl | 2008-01-21 18:17:00 +0100 (Mon, 21 Jan 2008) | 2 lines Fix old link. ........ r60163 | georg.brandl | 2008-01-21 18:22:06 +0100 (Mon, 21 Jan 2008) | 2 lines #1726198: replace while 1: fp.readline() with file iteration. ........ r60164 | georg.brandl | 2008-01-21 18:29:23 +0100 (Mon, 21 Jan 2008) | 2 lines Clarify $ behavior in re docstring. #1631394. ........ r60165 | vinay.sajip | 2008-01-21 18:39:22 +0100 (Mon, 21 Jan 2008) | 1 line Minor documentation change - hyperlink tidied up. ........ r60166 | georg.brandl | 2008-01-21 18:42:40 +0100 (Mon, 21 Jan 2008) | 2 lines #1530959: change distutils build dir for --with-pydebug python builds. ........ r60167 | vinay.sajip | 2008-01-21 19:16:05 +0100 (Mon, 21 Jan 2008) | 1 line Updated to include news on recent logging fixes and documentation changes. ........ r60168 | georg.brandl | 2008-01-21 19:35:49 +0100 (Mon, 21 Jan 2008) | 3 lines Issue #1882: when compiling code from a string, encoding cookies in the second line of code were not always recognized correctly. ........ r60170 | georg.brandl | 2008-01-21 19:36:51 +0100 (Mon, 21 Jan 2008) | 2 lines Add NEWS entry for #1882. ........ r60172 | georg.brandl | 2008-01-21 19:41:24 +0100 (Mon, 21 Jan 2008) | 2 lines Use original location of document, which has translations. ........ r60173 | walter.doerwald | 2008-01-21 21:18:04 +0100 (Mon, 21 Jan 2008) | 2 lines Follow PEP 8 in module docstring. ........ r60175 | georg.brandl | 2008-01-21 21:20:53 +0100 (Mon, 21 Jan 2008) | 2 lines Adapt to latest doctools refactoring. ........ --- Doc/bugs.rst | 2 +- Doc/conf.py | 15 +- Doc/extending/building.rst | 2 +- Doc/howto/regex.rst | 5 +- Doc/library/configparser.rst | 2 + Doc/library/fileformats.rst | 1 + Doc/library/logging.rst | 13 +- Doc/library/mmap.rst | 15 +- Doc/library/plistlib.rst | 124 ++++++++++ Doc/library/pydoc.rst | 2 +- Doc/tools/sphinxext/patchlevel.py | 68 ++++++ Doc/tutorial/controlflow.rst | 9 +- Lib/distutils/command/build.py | 6 + Lib/formatter.py | 5 +- Lib/keyword.py | 4 +- Lib/logging/handlers.py | 7 +- Lib/plat-mac/plistlib.py | 469 ------------------------------------- Lib/plistlib.py | 470 ++++++++++++++++++++++++++++++++++++++ Lib/pydoc.py | 13 +- Lib/re.py | 9 +- Lib/test/test_pep263.py | 8 + Lib/urlparse.py | 4 +- Makefile.pre.in | 35 ++- Modules/mmapmodule.c | 47 ++-- Parser/tokenizer.c | 15 +- Tools/pynche/ColorDB.py | 5 +- 26 files changed, 802 insertions(+), 553 deletions(-) create mode 100644 Doc/library/plistlib.rst create mode 100644 Doc/tools/sphinxext/patchlevel.py delete mode 100644 Lib/plat-mac/plistlib.py create mode 100644 Lib/plistlib.py diff --git a/Doc/bugs.rst b/Doc/bugs.rst index f8f75c2..8b8df81 100644 --- a/Doc/bugs.rst +++ b/Doc/bugs.rst @@ -49,7 +49,7 @@ taken on the bug. .. seealso:: - `How to Report Bugs Effectively `_ + `How to Report Bugs Effectively `_ Article which goes into some detail about how to create a useful bug report. This describes what kind of information is useful and why it is useful. diff --git a/Doc/conf.py b/Doc/conf.py index 5be5d1e..8359674 100644 --- a/Doc/conf.py +++ b/Doc/conf.py @@ -7,23 +7,27 @@ # The contents of this file are pickled, so don't put values in the namespace # that aren't pickleable (module imports are okay, they're removed automatically). +import sys, os, time +sys.path.append('tools/sphinxext') + # General configuration # --------------------- # General substitutions. project = 'Python' -copyright = '1990-2007, Python Software Foundation' +copyright = '1990-%s, Python Software Foundation' % time.strftime('%Y') # The default replacements for |version| and |release|. -# If '', Sphinx looks for the Include/patchlevel.h file in the current Python -# source tree and replaces the values accordingly. # # The short X.Y version. # version = '2.6' -version = '' # The full version, including alpha/beta/rc tags. # release = '2.6a0' -release = '' + +# We look for the Include/patchlevel.h file in the current Python source tree +# and replace the values accordingly. +import patchlevel +version, release = patchlevel.get_version_info() # There are two options for replacing |today|: either, you set today to some # non-false value, then it is used: @@ -119,7 +123,6 @@ latex_documents = [ 'What\'s New in Python', 'A. M. Kuchling', 'howto'), ] # Collect all HOWTOs individually -import os latex_documents.extend(('howto/' + fn, 'howto-' + fn[:-4] + '.tex', 'HOWTO', _stdauthor, 'howto') for fn in os.listdir('howto') diff --git a/Doc/extending/building.rst b/Doc/extending/building.rst index 5e1dec8..1c7b53f 100644 --- a/Doc/extending/building.rst +++ b/Doc/extending/building.rst @@ -80,7 +80,7 @@ example below. :: description = 'This is a demo package', author = 'Martin v. Loewis', author_email = 'martin@v.loewis.de', - url = 'http://www.python.org/doc/current/ext/building.html', + url = 'http://docs.python.org/extending/building', long_description = ''' This is really just a demo package. ''', diff --git a/Doc/howto/regex.rst b/Doc/howto/regex.rst index 6adecd7..d6c6b0a 100644 --- a/Doc/howto/regex.rst +++ b/Doc/howto/regex.rst @@ -335,9 +335,8 @@ Performing Matches Once you have an object representing a compiled regular expression, what do you do with it? :class:`RegexObject` instances have several methods and attributes. -Only the most significant ones will be covered here; consult `the Library -Reference `_ for a complete -listing. +Only the most significant ones will be covered here; consult the :mod:`re` docs +for a complete listing. +------------------+-----------------------------------------------+ | Method/Attribute | Purpose | diff --git a/Doc/library/configparser.rst b/Doc/library/configparser.rst index 979f351..28f2e59 100644 --- a/Doc/library/configparser.rst +++ b/Doc/library/configparser.rst @@ -420,3 +420,5 @@ The function ``opt_move`` below can be used to move options between sections:: # Create non-existent section config.add_section(section2) opt_move(config, section1, section2, option) + else: + config.remove_option(section1, option) diff --git a/Doc/library/fileformats.rst b/Doc/library/fileformats.rst index c0c2eed..d2f0639 100644 --- a/Doc/library/fileformats.rst +++ b/Doc/library/fileformats.rst @@ -16,3 +16,4 @@ that aren't markup languages or are related to e-mail. robotparser.rst netrc.rst xdrlib.rst + plistlib.rst diff --git a/Doc/library/logging.rst b/Doc/library/logging.rst index 923d9f2..ce574d0 100644 --- a/Doc/library/logging.rst +++ b/Doc/library/logging.rst @@ -1180,13 +1180,13 @@ also illustrates what dict-like behaviour is needed from an arbitrary "dict-like" object for use in the constructor:: import logging - + class ConnInfo: """ An example class which shows how an arbitrary class can be used as the 'extra' context information repository passed to a LoggerAdapter. """ - + def __getitem__(self, name): """ To allow this instance to look like a dict. @@ -1199,7 +1199,7 @@ also illustrates what dict-like behaviour is needed from an arbitrary else: result = self.__dict__.get(name, "?") return result - + def __iter__(self): """ To allow iteration over keys, which will be merged into @@ -1208,7 +1208,7 @@ also illustrates what dict-like behaviour is needed from an arbitrary keys = ["ip", "user"] keys.extend(self.__dict__.keys()) return keys.__iter__() - + if __name__ == "__main__": from random import choice levels = (logging.DEBUG, logging.INFO, logging.WARNING, logging.ERROR, logging.CRITICAL) @@ -2133,7 +2133,10 @@ LoggerAdapter Objects .. versionadded:: 2.6 :class:`LoggerAdapter` instances are used to conveniently pass contextual -information into logging calls. For a usage example , see context-info_. +information into logging calls. For a usage example , see the section on +`adding contextual information to your logging output`__. + +__ context-info_ .. class:: LoggerAdapter(logger, extra) diff --git a/Doc/library/mmap.rst b/Doc/library/mmap.rst index 37391d0..8ec9885 100644 --- a/Doc/library/mmap.rst +++ b/Doc/library/mmap.rst @@ -15,7 +15,7 @@ substring by assigning to a slice: ``obj[i1:i2] = '...'``. You can also read and write data starting at the current file position, and :meth:`seek` through the file to different positions. -A memory-mapped file is created by the :func:`mmap` function, which is different +A memory-mapped file is created by the :class:`mmap` constructor, which is different on Unix and on Windows. In either case you must provide a file descriptor for a file opened for update. If you wish to map an existing Python file object, use its :meth:`fileno` method to obtain the correct value for the *fileno* @@ -23,7 +23,7 @@ parameter. Otherwise, you can open the file using the :func:`os.open` function, which returns a file descriptor directly (the file still needs to be closed when done). -For both the Unix and Windows versions of the function, *access* may be +For both the Unix and Windows versions of the constructor, *access* may be specified as an optional keyword parameter. *access* accepts one of three values: :const:`ACCESS_READ`, :const:`ACCESS_WRITE`, or :const:`ACCESS_COPY` to specify readonly, write-through or copy-on-write memory respectively. *access* @@ -37,11 +37,10 @@ not update the underlying file. To map anonymous memory, -1 should be passed as the fileno along with the length. - -.. function:: mmap(fileno, length[, tagname[, access[, offset]]]) +.. class:: mmap(fileno, length[, tagname[, access[, offset]]]) **(Windows version)** Maps *length* bytes from the file specified by the file - handle *fileno*, and returns a mmap object. If *length* is larger than the + handle *fileno*, and creates a mmap object. If *length* is larger than the current size of the file, the file is extended to contain *length* bytes. If *length* is ``0``, the maximum length of the map is the current size of the file, except that if the file is empty Windows raises an exception (you cannot @@ -59,12 +58,12 @@ To map anonymous memory, -1 should be passed as the fileno along with the length *offset* must be a multiple of the ALLOCATIONGRANULARITY. -.. function:: mmap(fileno, length[, flags[, prot[, access[, offset]]]]) +.. class:: mmap(fileno, length[, flags[, prot[, access[, offset]]]]) :noindex: **(Unix version)** Maps *length* bytes from the file specified by the file descriptor *fileno*, and returns a mmap object. If *length* is ``0``, the - maximum length of the map will be the current size of the file when :func:`mmap` + maximum length of the map will be the current size of the file when :class:`mmap` is called. *flags* specifies the nature of the mapping. :const:`MAP_PRIVATE` creates a @@ -85,7 +84,7 @@ To map anonymous memory, -1 should be passed as the fileno along with the length be relative to the offset from the beginning of the file. *offset* defaults to 0. *offset* must be a multiple of the PAGESIZE or ALLOCATIONGRANULARITY. - This example shows a simple way of using :func:`mmap`:: + This example shows a simple way of using :class:`mmap`:: import mmap diff --git a/Doc/library/plistlib.rst b/Doc/library/plistlib.rst new file mode 100644 index 0000000..508f8e8 --- /dev/null +++ b/Doc/library/plistlib.rst @@ -0,0 +1,124 @@ +:mod:`plistlib` --- Generate and parse MacOS X ``.plist`` files +=============================================================== + +.. module:: plistlib + :synopsis: Generate and parse MacOS X plist files. +.. moduleauthor:: Jack Jansen +.. sectionauthor:: Georg Brandl +.. (harvested from docstrings in the original file) + +.. versionchanged:: 2.6 + This module was previously only available in the Mac-specific library, it is + now available for all platforms. + +.. index:: + pair: plist; file + single: property list + +This module provides an interface for reading and writing the "property list" +XML files used mainly by MacOS X. + +The property list (``.plist``) file format is a simple XML pickle supporting +basic object types, like dictionaries, lists, numbers and strings. Usually the +top level object is a dictionary. + +Values can be strings, integers, floats, booleans, tuples, lists, dictionaries +(but only with string keys), :class:`Data` or :class:`datetime.datetime` +objects. String values (including dictionary keys) may be unicode strings -- +they will be written out as UTF-8. + +The ```` plist type is supported through the :class:`Data` class. This is +a thin wrapper around a Python string. Use :class:`Data` if your strings +contain control characters. + +.. seealso:: + + `PList manual page ` + Apple's documentation of the file format. + + +This module defines the following functions: + +.. function:: readPlist(pathOrFile) + + Read a plist file. *pathOrFile* may either be a file name or a (readable) + file object. Return the unpacked root object (which usually is a + dictionary). + + The XML data is parsed using the Expat parser from :mod:`xml.parsers.expat` + -- see its documentation for possible exceptions on ill-formed XML. + Unknown elements will simply be ignored by the plist parser. + + +.. function:: writePlist(rootObject, pathOrFile) + + Write *rootObject* to a plist file. *pathOrFile* may either be a file name + or a (writable) file object. + + A :exc:`TypeError` will be raised if the object is of an unsupported type or + a container that contains objects of unsupported types. + + +.. function:: readPlistFromString(data) + + Read a plist from a string. Return the root object. + + +.. function:: writePlistToString(rootObject) + + Return *rootObject* as a plist-formatted string. + + + +.. function:: readPlistFromResource(path[, restype='plst'[, resid=0]]) + + Read a plist from the resource with type *restype* from the resource fork of + *path*. Availability: MacOS X. + + +.. function:: writePlistToResource(rootObject, path[, restype='plst'[, resid=0]]) + + Write *rootObject* as a resource with type *restype* to the resource fork of + *path*. Availability: MacOS X. + + +The following class is available: + +.. class:: Data(data) + + Return a "data" wrapper object around the string *data*. This is used in + functions converting from/to plists to represent the ```` type + available in plists. + + It has one attribute, :attr:`data`, that can be used to retrieve the Python + string stored in it. + + +Examples +-------- + +Generating a plist:: + + pl = dict( + aString="Doodah", + aList=["A", "B", 12, 32.1, [1, 2, 3]], + aFloat = 0.1, + anInt = 728, + aDict=dict( + anotherString="", + aUnicodeValue=u'M\xe4ssig, Ma\xdf', + aTrueValue=True, + aFalseValue=False, + ), + someData = Data(""), + someMoreData = Data("" * 10), + aDate = datetime.datetime.fromtimestamp(time.mktime(time.gmtime())), + ) + # unicode keys are possible, but a little awkward to use: + pl[u'\xc5benraa'] = "That was a unicode key." + writePlist(pl, fileName) + +Parsing a plist:: + + pl = readPlist(pathOrFile) + print pl["aKey"] diff --git a/Doc/library/pydoc.rst b/Doc/library/pydoc.rst index 4d74397..41ea1c6 100644 --- a/Doc/library/pydoc.rst +++ b/Doc/library/pydoc.rst @@ -57,7 +57,7 @@ documents precisely the version of the module you would get if you started the Python interpreter and typed ``import spam``. Module docs for core modules are assumed to reside in -http://www.python.org/doc/current/lib/. This can be overridden by setting the +http://docs.python.org/library/. This can be overridden by setting the :envvar:`PYTHONDOCS` environment variable to a different URL or to a local directory containing the Library Reference Manual pages. diff --git a/Doc/tools/sphinxext/patchlevel.py b/Doc/tools/sphinxext/patchlevel.py new file mode 100644 index 0000000..971ea61 --- /dev/null +++ b/Doc/tools/sphinxext/patchlevel.py @@ -0,0 +1,68 @@ +# -*- coding: utf-8 -*- +""" + patchlevel.py + ~~~~~~~~~~~~~ + + Extract version info from Include/patchlevel.h. + Adapted from Doc/tools/getversioninfo. + + :copyright: 2007-2008 by Georg Brandl. + :license: Python license. +""" + +import os +import re +import sys + +def get_header_version_info(srcdir): + patchlevel_h = os.path.join(srcdir, '..', 'Include', 'patchlevel.h') + + # This won't pick out all #defines, but it will pick up the ones we + # care about. + rx = re.compile(r'\s*#define\s+([a-zA-Z][a-zA-Z_0-9]*)\s+([a-zA-Z_0-9]+)') + + d = {} + f = open(patchlevel_h) + try: + for line in f: + m = rx.match(line) + if m is not None: + name, value = m.group(1, 2) + d[name] = value + finally: + f.close() + + release = version = '%s.%s' % (d['PY_MAJOR_VERSION'], d['PY_MINOR_VERSION']) + micro = int(d['PY_MICRO_VERSION']) + if micro != 0: + release += '.' + str(micro) + + level = d['PY_RELEASE_LEVEL'] + suffixes = { + 'PY_RELEASE_LEVEL_ALPHA': 'a', + 'PY_RELEASE_LEVEL_BETA': 'b', + 'PY_RELEASE_LEVEL_GAMMA': 'c', + } + if level != 'PY_RELEASE_LEVEL_FINAL': + release += suffixes[level] + str(int(d['PY_RELEASE_SERIAL'])) + return version, release + + +def get_sys_version_info(): + major, minor, micro, level, serial = sys.version_info + release = version = '%s.%s' % (major, minor) + if micro: + release += '.%s' % micro + if level != 'final': + release += '%s%s' % (level[0], serial) + return version, release + + +def get_version_info(): + try: + return get_header_version_info('.') + except (IOError, OSError): + version, release = get_sys_version_info() + print >>sys.stderr, 'Can\'t get version info from Include/patchlevel.h, ' \ + 'using version of this interpreter (%s).' % release + return version, release diff --git a/Doc/tutorial/controlflow.rst b/Doc/tutorial/controlflow.rst index 82a8977..3d011d1 100644 --- a/Doc/tutorial/controlflow.rst +++ b/Doc/tutorial/controlflow.rst @@ -235,10 +235,11 @@ it. The *execution* of a function introduces a new symbol table used for the local variables of the function. More precisely, all variable assignments in a function store the value in the local symbol table; whereas variable references -first look in the local symbol table, then in the global symbol table, and then -in the table of built-in names. Thus, global variables cannot be directly -assigned a value within a function (unless named in a :keyword:`global` -statement), although they may be referenced. +first look in the local symbol table, then in the local symbol tables of +enclosing functions, then in the global symbol table, and finally in the table +of built-in names. Thus, global variables cannot be directly assigned a value +within a function (unless named in a :keyword:`global` statement), although they +may be referenced. The actual parameters (arguments) to a function call are introduced in the local symbol table of the called function when it is called; thus, arguments are diff --git a/Lib/distutils/command/build.py b/Lib/distutils/command/build.py index 1f2ce06..4fe95b0 100644 --- a/Lib/distutils/command/build.py +++ b/Lib/distutils/command/build.py @@ -66,6 +66,12 @@ class build(Command): def finalize_options(self): plat_specifier = ".%s-%s" % (get_platform(), sys.version[0:3]) + # Make it so Python 2.x and Python 2.x with --with-pydebug don't + # share the same build directories. Doing so confuses the build + # process for C modules + if hasattr(sys, 'gettotalrefcount'): + plat_specifier += '-pydebug' + # 'build_purelib' and 'build_platlib' just default to 'lib' and # 'lib.' under the base build directory. We only use one of # them for a given distribution, though -- diff --git a/Lib/formatter.py b/Lib/formatter.py index 99b4740..bb8ad20 100644 --- a/Lib/formatter.py +++ b/Lib/formatter.py @@ -433,10 +433,7 @@ def test(file = None): fp = open(sys.argv[1]) else: fp = sys.stdin - while 1: - line = fp.readline() - if not line: - break + for line in fp: if line == '\n': f.end_paragraph(1) else: diff --git a/Lib/keyword.py b/Lib/keyword.py index 9c49cd2..a7abe2b 100755 --- a/Lib/keyword.py +++ b/Lib/keyword.py @@ -64,9 +64,7 @@ def main(): fp = open(iptfile) strprog = re.compile('"([^"]+)"') lines = [] - while 1: - line = fp.readline() - if not line: break + for line in fp: if '{1, "' in line: match = strprog.search(line) if match: diff --git a/Lib/logging/handlers.py b/Lib/logging/handlers.py index b53262e..08bebbd 100644 --- a/Lib/logging/handlers.py +++ b/Lib/logging/handlers.py @@ -226,13 +226,16 @@ class TimedRotatingFileHandler(BaseRotatingHandler): # Days to rollover is 6 - 5 + 3, or 4. In this case, it's the # number of days left in the current week (1) plus the number # of days in the next week until the rollover day (3). + # The calculations described in 2) and 3) above need to have a day added. + # This is because the above time calculation takes us to midnight on this + # day, i.e. the start of the next day. if when.startswith('W'): day = t[6] # 0 is Monday if day != self.dayOfWeek: if day < self.dayOfWeek: - daysToWait = self.dayOfWeek - day - 1 + daysToWait = self.dayOfWeek - day else: - daysToWait = 6 - day + self.dayOfWeek + daysToWait = 6 - day + self.dayOfWeek + 1 self.rolloverAt = self.rolloverAt + (daysToWait * (60 * 60 * 24)) #print "Will rollover at %d, %d seconds from now" % (self.rolloverAt, self.rolloverAt - currentTime) diff --git a/Lib/plat-mac/plistlib.py b/Lib/plat-mac/plistlib.py deleted file mode 100644 index db5eea1..0000000 --- a/Lib/plat-mac/plistlib.py +++ /dev/null @@ -1,469 +0,0 @@ -"""plistlib.py -- a tool to generate and parse MacOSX .plist files. - -The PropertList (.plist) file format is a simple XML pickle supporting -basic object types, like dictionaries, lists, numbers and strings. -Usually the top level object is a dictionary. - -To write out a plist file, use the writePlist(rootObject, pathOrFile) -function. 'rootObject' is the top level object, 'pathOrFile' is a -filename or a (writable) file object. - -To parse a plist from a file, use the readPlist(pathOrFile) function, -with a file name or a (readable) file object as the only argument. It -returns the top level object (again, usually a dictionary). - -To work with plist data in bytes objects, you can use readPlistFromBytes() -and writePlistToBytes(). - -Values can be strings, integers, floats, booleans, tuples, lists, -dictionaries, Data or datetime.datetime objects. String values (including -dictionary keys) may be unicode strings -- they will be written out as -UTF-8. - -The plist type is supported through the Data class. This is a -thin wrapper around a Python bytes object. - -Generate Plist example: - - pl = dict( - aString="Doodah", - aList=["A", "B", 12, 32.1, [1, 2, 3]], - aFloat = 0.1, - anInt = 728, - aDict=dict( - anotherString="", - aUnicodeValue=u'M\xe4ssig, Ma\xdf', - aTrueValue=True, - aFalseValue=False, - ), - someData = Data(b""), - someMoreData = Data(b"" * 10), - aDate = datetime.datetime.fromtimestamp(time.mktime(time.gmtime())), - ) - # unicode keys are possible, but a little awkward to use: - pl[u'\xc5benraa'] = "That was a unicode key." - writePlist(pl, fileName) - -Parse Plist example: - - pl = readPlist(pathOrFile) - print pl["aKey"] -""" - - -__all__ = [ - "readPlist", "writePlist", "readPlistFromBytes", "writePlistToBytes", - "readPlistFromResource", "writePlistToResource", - "Plist", "Data", "Dict" -] -# Note: the Plist and Dict classes have been deprecated. - -import binascii -import datetime -from io import BytesIO -import re - - -def readPlist(pathOrFile): - """Read a .plist file. 'pathOrFile' may either be a file name or a - (readable) file object. Return the unpacked root object (which - usually is a dictionary). - """ - didOpen = False - if isinstance(pathOrFile, str): - pathOrFile = open(pathOrFile, 'rb') - didOpen = True - p = PlistParser() - rootObject = p.parse(pathOrFile) - if didOpen: - pathOrFile.close() - return rootObject - - -def writePlist(rootObject, pathOrFile): - """Write 'rootObject' to a .plist file. 'pathOrFile' may either be a - file name or a (writable) file object. - """ - didOpen = False - if isinstance(pathOrFile, str): - pathOrFile = open(pathOrFile, 'wb') - didOpen = True - writer = PlistWriter(pathOrFile) - writer.writeln("") - writer.writeValue(rootObject) - writer.writeln("") - if didOpen: - pathOrFile.close() - - -def readPlistFromBytes(data): - """Read a plist data from a bytes object. Return the root object. - """ - return readPlist(BytesIO(data)) - - -def writePlistToBytes(rootObject): - """Return 'rootObject' as a plist-formatted bytes object. - """ - f = BytesIO() - writePlist(rootObject, f) - return f.getvalue() - - -def readPlistFromResource(path, restype='plst', resid=0): - """Read plst resource from the resource fork of path. - """ - from Carbon.File import FSRef, FSGetResourceForkName - from Carbon.Files import fsRdPerm - from Carbon import Res - fsRef = FSRef(path) - resNum = Res.FSOpenResourceFile(fsRef, FSGetResourceForkName(), fsRdPerm) - Res.UseResFile(resNum) - plistData = Res.Get1Resource(restype, resid).data - Res.CloseResFile(resNum) - return readPlistFromString(plistData) - - -def writePlistToResource(rootObject, path, restype='plst', resid=0): - """Write 'rootObject' as a plst resource to the resource fork of path. - """ - from Carbon.File import FSRef, FSGetResourceForkName - from Carbon.Files import fsRdWrPerm - from Carbon import Res - plistData = writePlistToString(rootObject) - fsRef = FSRef(path) - resNum = Res.FSOpenResourceFile(fsRef, FSGetResourceForkName(), fsRdWrPerm) - Res.UseResFile(resNum) - try: - Res.Get1Resource(restype, resid).RemoveResource() - except Res.Error: - pass - res = Res.Resource(plistData) - res.AddResource(restype, resid, '') - res.WriteResource() - Res.CloseResFile(resNum) - - -class DumbXMLWriter: - def __init__(self, file, indentLevel=0, indent="\t"): - self.file = file - self.stack = [] - self.indentLevel = indentLevel - self.indent = indent - - def beginElement(self, element): - self.stack.append(element) - self.writeln("<%s>" % element) - self.indentLevel += 1 - - def endElement(self, element): - assert self.indentLevel > 0 - assert self.stack.pop() == element - self.indentLevel -= 1 - self.writeln("" % element) - - def simpleElement(self, element, value=None): - if value is not None: - value = _escape(value) - self.writeln("<%s>%s" % (element, value, element)) - else: - self.writeln("<%s/>" % element) - - def writeln(self, line): - if line: - # plist has fixed encoding of utf-8 - if isinstance(line, str): - line = line.encode('utf-8') - self.file.write(self.indentLevel * self.indent) - self.file.write(line) - self.file.write(b'\n') - - -# Contents should conform to a subset of ISO 8601 -# (in particular, YYYY '-' MM '-' DD 'T' HH ':' MM ':' SS 'Z'. Smaller units may be omitted with -# a loss of precision) -_dateParser = re.compile(r"(?P\d\d\d\d)(?:-(?P\d\d)(?:-(?P\d\d)(?:T(?P\d\d)(?::(?P\d\d)(?::(?P\d\d))?)?)?)?)?Z") - -def _dateFromString(s): - order = ('year', 'month', 'day', 'hour', 'minute', 'second') - gd = _dateParser.match(s).groupdict() - lst = [] - for key in order: - val = gd[key] - if val is None: - break - lst.append(int(val)) - return datetime.datetime(*lst) - -def _dateToString(d): - return '%04d-%02d-%02dT%02d:%02d:%02dZ' % ( - d.year, d.month, d.day, - d.hour, d.minute, d.second - ) - - -# Regex to find any control chars, except for \t \n and \r -_controlCharPat = re.compile( - r"[\x00\x01\x02\x03\x04\x05\x06\x07\x08\x0b\x0c\x0e\x0f" - r"\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f]") - -def _escape(text): - m = _controlCharPat.search(text) - if m is not None: - raise ValueError("strings can't contains control characters; " - "use plistlib.Data instead") - text = text.replace("\r\n", "\n") # convert DOS line endings - text = text.replace("\r", "\n") # convert Mac line endings - text = text.replace("&", "&") # escape '&' - text = text.replace("<", "<") # escape '<' - text = text.replace(">", ">") # escape '>' - return text - - -PLISTHEADER = b"""\ - - -""" - -class PlistWriter(DumbXMLWriter): - - def __init__(self, file, indentLevel=0, indent=b"\t", writeHeader=1): - if writeHeader: - file.write(PLISTHEADER) - DumbXMLWriter.__init__(self, file, indentLevel, indent) - - def writeValue(self, value): - if isinstance(value, str): - self.simpleElement("string", value) - elif isinstance(value, bool): - # must switch for bool before int, as bool is a - # subclass of int... - if value: - self.simpleElement("true") - else: - self.simpleElement("false") - elif isinstance(value, int): - self.simpleElement("integer", "%d" % value) - elif isinstance(value, float): - self.simpleElement("real", repr(value)) - elif isinstance(value, dict): - self.writeDict(value) - elif isinstance(value, Data): - self.writeData(value) - elif isinstance(value, datetime.datetime): - self.simpleElement("date", _dateToString(value)) - elif isinstance(value, (tuple, list)): - self.writeArray(value) - else: - raise TypeError("unsuported type: %s" % type(value)) - - def writeData(self, data): - self.beginElement("data") - self.indentLevel -= 1 - maxlinelength = 76 - len(self.indent.replace(b"\t", b" " * 8) * - self.indentLevel) - for line in data.asBase64(maxlinelength).split(b"\n"): - if line: - self.writeln(line) - self.indentLevel += 1 - self.endElement("data") - - def writeDict(self, d): - self.beginElement("dict") - items = sorted(d.items()) - for key, value in items: - if not isinstance(key, str): - raise TypeError("keys must be strings") - self.simpleElement("key", key) - self.writeValue(value) - self.endElement("dict") - - def writeArray(self, array): - self.beginElement("array") - for value in array: - self.writeValue(value) - self.endElement("array") - - -class _InternalDict(dict): - - # This class is needed while Dict is scheduled for deprecation: - # we only need to warn when a *user* instantiates Dict or when - # the "attribute notation for dict keys" is used. - - def __getattr__(self, attr): - try: - value = self[attr] - except KeyError: - raise AttributeError(attr) - from warnings import warn - warn("Attribute access from plist dicts is deprecated, use d[key] " - "notation instead", PendingDeprecationWarning) - return value - - def __setattr__(self, attr, value): - from warnings import warn - warn("Attribute access from plist dicts is deprecated, use d[key] " - "notation instead", PendingDeprecationWarning) - self[attr] = value - - def __delattr__(self, attr): - try: - del self[attr] - except KeyError: - raise AttributeError(attr) - from warnings import warn - warn("Attribute access from plist dicts is deprecated, use d[key] " - "notation instead", PendingDeprecationWarning) - -class Dict(_InternalDict): - - def __init__(self, **kwargs): - from warnings import warn - warn("The plistlib.Dict class is deprecated, use builtin dict instead", - PendingDeprecationWarning) - super().__init__(**kwargs) - - -class Plist(_InternalDict): - - """This class has been deprecated. Use readPlist() and writePlist() - functions instead, together with regular dict objects. - """ - - def __init__(self, **kwargs): - from warnings import warn - warn("The Plist class is deprecated, use the readPlist() and " - "writePlist() functions instead", PendingDeprecationWarning) - super().__init__(**kwargs) - - def fromFile(cls, pathOrFile): - """Deprecated. Use the readPlist() function instead.""" - rootObject = readPlist(pathOrFile) - plist = cls() - plist.update(rootObject) - return plist - fromFile = classmethod(fromFile) - - def write(self, pathOrFile): - """Deprecated. Use the writePlist() function instead.""" - writePlist(self, pathOrFile) - - -def _encodeBase64(s, maxlinelength=76): - # copied from base64.encodestring(), with added maxlinelength argument - maxbinsize = (maxlinelength//4)*3 - pieces = [] - for i in range(0, len(s), maxbinsize): - chunk = s[i : i + maxbinsize] - pieces.append(binascii.b2a_base64(chunk)) - return b''.join(pieces) - -class Data: - - """Wrapper for binary data.""" - - def __init__(self, data): - if not isinstance(data, bytes): - raise TypeError("data must be as bytes") - self.data = data - - @classmethod - def fromBase64(cls, data): - # base64.decodestring just calls binascii.a2b_base64; - # it seems overkill to use both base64 and binascii. - return cls(binascii.a2b_base64(data)) - - def asBase64(self, maxlinelength=76): - return _encodeBase64(self.data, maxlinelength) - - def __eq__(self, other): - if isinstance(other, self.__class__): - return self.data == other.data - elif isinstance(other, str): - return self.data == other - else: - return id(self) == id(other) - - def __repr__(self): - return "%s(%s)" % (self.__class__.__name__, repr(self.data)) - - -class PlistParser: - - def __init__(self): - self.stack = [] - self.currentKey = None - self.root = None - - def parse(self, fileobj): - from xml.parsers.expat import ParserCreate - parser = ParserCreate() - parser.StartElementHandler = self.handleBeginElement - parser.EndElementHandler = self.handleEndElement - parser.CharacterDataHandler = self.handleData - parser.ParseFile(fileobj) - return self.root - - def handleBeginElement(self, element, attrs): - self.data = [] - handler = getattr(self, "begin_" + element, None) - if handler is not None: - handler(attrs) - - def handleEndElement(self, element): - handler = getattr(self, "end_" + element, None) - if handler is not None: - handler() - - def handleData(self, data): - self.data.append(data) - - def addObject(self, value): - if self.currentKey is not None: - self.stack[-1][self.currentKey] = value - self.currentKey = None - elif not self.stack: - # this is the root object - self.root = value - else: - self.stack[-1].append(value) - - def getData(self): - data = ''.join(self.data) - self.data = [] - return data - - # element handlers - - def begin_dict(self, attrs): - d = _InternalDict() - self.addObject(d) - self.stack.append(d) - def end_dict(self): - self.stack.pop() - - def end_key(self): - self.currentKey = self.getData() - - def begin_array(self, attrs): - a = [] - self.addObject(a) - self.stack.append(a) - def end_array(self): - self.stack.pop() - - def end_true(self): - self.addObject(True) - def end_false(self): - self.addObject(False) - def end_integer(self): - self.addObject(int(self.getData())) - def end_real(self): - self.addObject(float(self.getData())) - def end_string(self): - self.addObject(self.getData()) - def end_data(self): - self.addObject(Data.fromBase64(self.getData().encode("utf-8"))) - def end_date(self): - self.addObject(_dateFromString(self.getData())) diff --git a/Lib/plistlib.py b/Lib/plistlib.py new file mode 100644 index 0000000..9cd1c8e --- /dev/null +++ b/Lib/plistlib.py @@ -0,0 +1,470 @@ +"""plistlib.py -- a tool to generate and parse MacOSX .plist files. + +The PropertyList (.plist) file format is a simple XML pickle supporting +basic object types, like dictionaries, lists, numbers and strings. +Usually the top level object is a dictionary. + +To write out a plist file, use the writePlist(rootObject, pathOrFile) +function. 'rootObject' is the top level object, 'pathOrFile' is a +filename or a (writable) file object. + +To parse a plist from a file, use the readPlist(pathOrFile) function, +with a file name or a (readable) file object as the only argument. It +returns the top level object (again, usually a dictionary). + +To work with plist data in strings, you can use readPlistFromString() +and writePlistToString(). + +Values can be strings, integers, floats, booleans, tuples, lists, +dictionaries, Data or datetime.datetime objects. String values (including +dictionary keys) may be unicode strings -- they will be written out as +UTF-8. + +The plist type is supported through the Data class. This is a +thin wrapper around a Python string. + +Generate Plist example: + + pl = dict( + aString="Doodah", + aList=["A", "B", 12, 32.1, [1, 2, 3]], + aFloat=0.1, + anInt=728, + aDict=dict( + anotherString="", + aUnicodeValue=u'M\xe4ssig, Ma\xdf', + aTrueValue=True, + aFalseValue=False, + ), + someData=Data(""), + someMoreData=Data("" * 10), + aDate=datetime.datetime.fromtimestamp(time.mktime(time.gmtime())), + ) + # unicode keys are possible, but a little awkward to use: + pl[u'\xc5benraa'] = "That was a unicode key." + writePlist(pl, fileName) + +Parse Plist example: + + pl = readPlist(pathOrFile) + print pl["aKey"] +""" + + +__all__ = [ + "readPlist", "writePlist", "readPlistFromString", "writePlistToString", + "readPlistFromResource", "writePlistToResource", + "Plist", "Data", "Dict" +] +# Note: the Plist and Dict classes have been deprecated. + +import binascii +import datetime +from io import StringIO +import re + + +def readPlist(pathOrFile): + """Read a .plist file. 'pathOrFile' may either be a file name or a + (readable) file object. Return the unpacked root object (which + usually is a dictionary). + """ + didOpen = 0 + if isinstance(pathOrFile, str): + pathOrFile = open(pathOrFile) + didOpen = 1 + p = PlistParser() + rootObject = p.parse(pathOrFile) + if didOpen: + pathOrFile.close() + return rootObject + + +def writePlist(rootObject, pathOrFile): + """Write 'rootObject' to a .plist file. 'pathOrFile' may either be a + file name or a (writable) file object. + """ + didOpen = 0 + if isinstance(pathOrFile, str): + pathOrFile = open(pathOrFile, "w") + didOpen = 1 + writer = PlistWriter(pathOrFile) + writer.writeln("") + writer.writeValue(rootObject) + writer.writeln("") + if didOpen: + pathOrFile.close() + + +def readPlistFromString(data): + """Read a plist data from a string. Return the root object. + """ + return readPlist(StringIO(data)) + + +def writePlistToString(rootObject): + """Return 'rootObject' as a plist-formatted string. + """ + f = StringIO() + writePlist(rootObject, f) + return f.getvalue() + + +def readPlistFromResource(path, restype='plst', resid=0): + """Read plst resource from the resource fork of path. + """ + from Carbon.File import FSRef, FSGetResourceForkName + from Carbon.Files import fsRdPerm + from Carbon import Res + fsRef = FSRef(path) + resNum = Res.FSOpenResourceFile(fsRef, FSGetResourceForkName(), fsRdPerm) + Res.UseResFile(resNum) + plistData = Res.Get1Resource(restype, resid).data + Res.CloseResFile(resNum) + return readPlistFromString(plistData) + + +def writePlistToResource(rootObject, path, restype='plst', resid=0): + """Write 'rootObject' as a plst resource to the resource fork of path. + """ + from Carbon.File import FSRef, FSGetResourceForkName + from Carbon.Files import fsRdWrPerm + from Carbon import Res + plistData = writePlistToString(rootObject) + fsRef = FSRef(path) + resNum = Res.FSOpenResourceFile(fsRef, FSGetResourceForkName(), fsRdWrPerm) + Res.UseResFile(resNum) + try: + Res.Get1Resource(restype, resid).RemoveResource() + except Res.Error: + pass + res = Res.Resource(plistData) + res.AddResource(restype, resid, '') + res.WriteResource() + Res.CloseResFile(resNum) + + +class DumbXMLWriter: + + def __init__(self, file, indentLevel=0, indent="\t"): + self.file = file + self.stack = [] + self.indentLevel = indentLevel + self.indent = indent + + def beginElement(self, element): + self.stack.append(element) + self.writeln("<%s>" % element) + self.indentLevel += 1 + + def endElement(self, element): + assert self.indentLevel > 0 + assert self.stack.pop() == element + self.indentLevel -= 1 + self.writeln("" % element) + + def simpleElement(self, element, value=None): + if value is not None: + value = _escapeAndEncode(value) + self.writeln("<%s>%s" % (element, value, element)) + else: + self.writeln("<%s/>" % element) + + def writeln(self, line): + if line: + self.file.write(self.indentLevel * self.indent + line + "\n") + else: + self.file.write("\n") + + +# Contents should conform to a subset of ISO 8601 +# (in particular, YYYY '-' MM '-' DD 'T' HH ':' MM ':' SS 'Z'. Smaller units may be omitted with +# a loss of precision) +_dateParser = re.compile(r"(?P\d\d\d\d)(?:-(?P\d\d)(?:-(?P\d\d)(?:T(?P\d\d)(?::(?P\d\d)(?::(?P\d\d))?)?)?)?)?Z") + +def _dateFromString(s): + order = ('year', 'month', 'day', 'hour', 'minute', 'second') + gd = _dateParser.match(s).groupdict() + lst = [] + for key in order: + val = gd[key] + if val is None: + break + lst.append(int(val)) + return datetime.datetime(*lst) + +def _dateToString(d): + return '%04d-%02d-%02dT%02d:%02d:%02dZ' % ( + d.year, d.month, d.day, + d.hour, d.minute, d.second + ) + + +# Regex to find any control chars, except for \t \n and \r +_controlCharPat = re.compile( + r"[\x00\x01\x02\x03\x04\x05\x06\x07\x08\x0b\x0c\x0e\x0f" + r"\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f]") + +def _escapeAndEncode(text): + m = _controlCharPat.search(text) + if m is not None: + raise ValueError("strings can't contains control characters; " + "use plistlib.Data instead") + text = text.replace("\r\n", "\n") # convert DOS line endings + text = text.replace("\r", "\n") # convert Mac line endings + text = text.replace("&", "&") # escape '&' + text = text.replace("<", "<") # escape '<' + text = text.replace(">", ">") # escape '>' + return text.encode("utf-8") # encode as UTF-8 + + +PLISTHEADER = """\ + + +""" + +class PlistWriter(DumbXMLWriter): + + def __init__(self, file, indentLevel=0, indent="\t", writeHeader=1): + if writeHeader: + file.write(PLISTHEADER) + DumbXMLWriter.__init__(self, file, indentLevel, indent) + + def writeValue(self, value): + if isinstance(value, str): + self.simpleElement("string", value) + elif isinstance(value, bool): + # must switch for bool before int, as bool is a + # subclass of int... + if value: + self.simpleElement("true") + else: + self.simpleElement("false") + elif isinstance(value, int): + self.simpleElement("integer", "%d" % value) + elif isinstance(value, float): + self.simpleElement("real", repr(value)) + elif isinstance(value, dict): + self.writeDict(value) + elif isinstance(value, Data): + self.writeData(value) + elif isinstance(value, datetime.datetime): + self.simpleElement("date", _dateToString(value)) + elif isinstance(value, (tuple, list)): + self.writeArray(value) + else: + raise TypeError("unsuported type: %s" % type(value)) + + def writeData(self, data): + self.beginElement("data") + self.indentLevel -= 1 + maxlinelength = 76 - len(self.indent.replace("\t", " " * 8) * + self.indentLevel) + for line in data.asBase64(maxlinelength).split("\n"): + if line: + self.writeln(line) + self.indentLevel += 1 + self.endElement("data") + + def writeDict(self, d): + self.beginElement("dict") + items = list(d.items()) + items.sort() + for key, value in items: + if not isinstance(key, str): + raise TypeError("keys must be strings") + self.simpleElement("key", key) + self.writeValue(value) + self.endElement("dict") + + def writeArray(self, array): + self.beginElement("array") + for value in array: + self.writeValue(value) + self.endElement("array") + + +class _InternalDict(dict): + + # This class is needed while Dict is scheduled for deprecation: + # we only need to warn when a *user* instantiates Dict or when + # the "attribute notation for dict keys" is used. + + def __getattr__(self, attr): + try: + value = self[attr] + except KeyError: + raise AttributeError(attr) + from warnings import warn + warn("Attribute access from plist dicts is deprecated, use d[key] " + "notation instead", PendingDeprecationWarning) + return value + + def __setattr__(self, attr, value): + from warnings import warn + warn("Attribute access from plist dicts is deprecated, use d[key] " + "notation instead", PendingDeprecationWarning) + self[attr] = value + + def __delattr__(self, attr): + try: + del self[attr] + except KeyError: + raise AttributeError(attr) + from warnings import warn + warn("Attribute access from plist dicts is deprecated, use d[key] " + "notation instead", PendingDeprecationWarning) + +class Dict(_InternalDict): + + def __init__(self, **kwargs): + from warnings import warn + warn("The plistlib.Dict class is deprecated, use builtin dict instead", + PendingDeprecationWarning) + super(Dict, self).__init__(**kwargs) + + +class Plist(_InternalDict): + + """This class has been deprecated. Use readPlist() and writePlist() + functions instead, together with regular dict objects. + """ + + def __init__(self, **kwargs): + from warnings import warn + warn("The Plist class is deprecated, use the readPlist() and " + "writePlist() functions instead", PendingDeprecationWarning) + super(Plist, self).__init__(**kwargs) + + def fromFile(cls, pathOrFile): + """Deprecated. Use the readPlist() function instead.""" + rootObject = readPlist(pathOrFile) + plist = cls() + plist.update(rootObject) + return plist + fromFile = classmethod(fromFile) + + def write(self, pathOrFile): + """Deprecated. Use the writePlist() function instead.""" + writePlist(self, pathOrFile) + + +def _encodeBase64(s, maxlinelength=76): + # copied from base64.encodestring(), with added maxlinelength argument + maxbinsize = (maxlinelength//4)*3 + pieces = [] + for i in range(0, len(s), maxbinsize): + chunk = s[i : i + maxbinsize] + pieces.append(binascii.b2a_base64(chunk)) + return "".join(pieces) + +class Data: + + """Wrapper for binary data.""" + + def __init__(self, data): + self.data = data + + def fromBase64(cls, data): + # base64.decodestring just calls binascii.a2b_base64; + # it seems overkill to use both base64 and binascii. + return cls(binascii.a2b_base64(data)) + fromBase64 = classmethod(fromBase64) + + def asBase64(self, maxlinelength=76): + return _encodeBase64(self.data, maxlinelength) + + def __cmp__(self, other): + if isinstance(other, self.__class__): + return cmp(self.data, other.data) + elif isinstance(other, str): + return cmp(self.data, other) + else: + return cmp(id(self), id(other)) + + def __repr__(self): + return "%s(%s)" % (self.__class__.__name__, repr(self.data)) + + +class PlistParser: + + def __init__(self): + self.stack = [] + self.currentKey = None + self.root = None + + def parse(self, fileobj): + from xml.parsers.expat import ParserCreate + parser = ParserCreate() + parser.StartElementHandler = self.handleBeginElement + parser.EndElementHandler = self.handleEndElement + parser.CharacterDataHandler = self.handleData + parser.ParseFile(fileobj) + return self.root + + def handleBeginElement(self, element, attrs): + self.data = [] + handler = getattr(self, "begin_" + element, None) + if handler is not None: + handler(attrs) + + def handleEndElement(self, element): + handler = getattr(self, "end_" + element, None) + if handler is not None: + handler() + + def handleData(self, data): + self.data.append(data) + + def addObject(self, value): + if self.currentKey is not None: + self.stack[-1][self.currentKey] = value + self.currentKey = None + elif not self.stack: + # this is the root object + self.root = value + else: + self.stack[-1].append(value) + + def getData(self): + data = "".join(self.data) + try: + data = data.encode("ascii") + except UnicodeError: + pass + self.data = [] + return data + + # element handlers + + def begin_dict(self, attrs): + d = _InternalDict() + self.addObject(d) + self.stack.append(d) + def end_dict(self): + self.stack.pop() + + def end_key(self): + self.currentKey = self.getData() + + def begin_array(self, attrs): + a = [] + self.addObject(a) + self.stack.append(a) + def end_array(self): + self.stack.pop() + + def end_true(self): + self.addObject(True) + def end_false(self): + self.addObject(False) + def end_integer(self): + self.addObject(int(self.getData())) + def end_real(self): + self.addObject(float(self.getData())) + def end_string(self): + self.addObject(self.getData()) + def end_data(self): + self.addObject(Data.fromBase64(self.getData())) + def end_date(self): + self.addObject(_dateFromString(self.getData())) diff --git a/Lib/pydoc.py b/Lib/pydoc.py index 2a1e98f..d5fb91b 100755 --- a/Lib/pydoc.py +++ b/Lib/pydoc.py @@ -27,7 +27,7 @@ to a file named ".html". Module docs for core modules are assumed to be in - http://www.python.org/doc/current/lib/ + http://docs.python.org/library/ This can be overridden by setting the PYTHONDOCS environment variable to a different URL or to a local directory containing the Library @@ -341,7 +341,7 @@ class Doc: file = '(built-in)' docloc = os.environ.get("PYTHONDOCS", - "http://www.python.org/doc/current/lib") + "http://docs.python.org/library") basedir = os.path.join(sys.exec_prefix, "lib", "python"+sys.version[0:3]) if (isinstance(object, type(os)) and @@ -350,11 +350,10 @@ class Doc: 'thread', 'zipimport') or (file.startswith(basedir) and not file.startswith(os.path.join(basedir, 'site-packages'))))): - htmlfile = "module-%s.html" % object.__name__ if docloc.startswith("http://"): - docloc = "%s/%s" % (docloc.rstrip("/"), htmlfile) + docloc = "%s/%s" % (docloc.rstrip("/"), object.__name__) else: - docloc = os.path.join(docloc, htmlfile) + docloc = os.path.join(docloc, object.__name__ + ".html") else: docloc = None return docloc @@ -537,7 +536,7 @@ class HTMLDoc(Doc): url = 'http://www.rfc-editor.org/rfc/rfc%d.txt' % int(rfc) results.append('%s' % (url, escape(all))) elif pep: - url = 'http://www.python.org/peps/pep-%04d.html' % int(pep) + url = 'http://www.python.org/peps/pep-%04d' % int(pep) results.append('%s' % (url, escape(all))) elif text[end:end+1] == '(': results.append(self.namelink(name, methods, funcs, classes)) @@ -1729,7 +1728,7 @@ has the same effect as typing a particular string at the help> prompt. Welcome to Python %s! This is the online help utility. If this is your first time using Python, you should definitely check out -the tutorial on the Internet at http://www.python.org/doc/tut/. +the tutorial on the Internet at http://docs.python.org/tutorial/. Enter the name of any module, keyword, or topic to get help on writing Python programs and using Python modules. To quit this help utility and diff --git a/Lib/re.py b/Lib/re.py index 1e0c468..91b119c 100644 --- a/Lib/re.py +++ b/Lib/re.py @@ -29,7 +29,8 @@ concatenate ordinary characters, so last matches the string 'last'. The special characters are: "." Matches any character except a newline. "^" Matches the start of the string. - "$" Matches the end of the string. + "$" Matches the end of the string or just before the newline at + the end of the string. "*" Matches 0 or more (greedy) repetitions of the preceding RE. Greedy means that it will match as many repetitions as possible. "+" Matches 1 or more (greedy) repetitions of the preceding RE. @@ -83,8 +84,10 @@ This module exports the following functions: Some of the functions in this module takes flags as optional parameters: I IGNORECASE Perform case-insensitive matching. L LOCALE Make \w, \W, \b, \B, dependent on the current locale. - M MULTILINE "^" matches the beginning of lines as well as the string. - "$" matches the end of lines as well as the string. + M MULTILINE "^" matches the beginning of lines (after a newline) + as well as the string. + "$" matches the end of lines (before a newline) as well + as the end of the string. S DOTALL "." matches any character at all, including the newline. X VERBOSE Ignore whitespace and comments for nicer looking RE's. U UNICODE Make \w, \W, \b, \B, dependent on the Unicode locale. diff --git a/Lib/test/test_pep263.py b/Lib/test/test_pep263.py index dd13558..cacf1d6 100644 --- a/Lib/test/test_pep263.py +++ b/Lib/test/test_pep263.py @@ -16,6 +16,14 @@ class PEP263Test(unittest.TestCase): b'\\\xd0\x9f' ) + def test_compilestring(self): + # see #1882 + c = compile("\n# coding: utf-8\nu = '\xc3\xb3'\n", "dummy", "exec") + d = {} + exec(c, d) + self.assertEqual(d['u'], '\xf3') + + def test_main(): test_support.run_unittest(PEP263Test) diff --git a/Lib/urlparse.py b/Lib/urlparse.py index 0c05dfe..30de699 100644 --- a/Lib/urlparse.py +++ b/Lib/urlparse.py @@ -305,9 +305,7 @@ def test(): else: from io import StringIO fp = StringIO(test_input) - while 1: - line = fp.readline() - if not line: break + for line in fp: words = line.split() if not words: continue diff --git a/Makefile.pre.in b/Makefile.pre.in index d762185..406478c 100644 --- a/Makefile.pre.in +++ b/Makefile.pre.in @@ -223,6 +223,10 @@ PGOBJS= \ Parser/printgrammar.o \ Parser/pgenmain.o +PARSER_HEADERS= \ + Parser/parser.h \ + Parser/tokenizer.h + PGENOBJS= $(PGENMAIN) $(POBJS) $(PGOBJS) ########################################################################## @@ -542,13 +546,16 @@ Python/formatter_unicode.o: $(srcdir)/Python/formatter_unicode.c \ # Header files PYTHON_HEADERS= \ - Include/Python.h \ Include/Python-ast.h \ - Include/asdl.h \ + Include/Python.h \ Include/abstract.h \ + Include/asdl.h \ + Include/ast.h \ + Include/bitset.h \ Include/boolobject.h \ Include/bytes_methods.h \ Include/bytesobject.h \ + Include/cellobject.h \ Include/ceval.h \ Include/classobject.h \ Include/cobject.h \ @@ -559,48 +566,62 @@ PYTHON_HEADERS= \ Include/descrobject.h \ Include/dictobject.h \ Include/enumobject.h \ - Include/genobject.h \ + Include/errcode.h \ + Include/eval.h \ Include/fileobject.h \ Include/floatobject.h \ Include/formatter_unicode.h \ + Include/frameobject.h \ Include/funcobject.h \ + Include/genobject.h \ Include/import.h \ Include/intrcheck.h \ Include/iterobject.h \ Include/listobject.h \ Include/longintrepr.h \ Include/longobject.h \ + Include/marshal.h \ Include/memoryobject.h \ + Include/metagrammar.h \ Include/methodobject.h \ Include/modsupport.h \ Include/moduleobject.h \ + Include/node.h \ Include/object.h \ Include/objimpl.h \ + Include/opcode.h \ + Include/osdefs.h \ Include/parsetok.h \ Include/patchlevel.h \ + Include/pgen.h \ + Include/pgenheaders.h \ Include/pyarena.h \ Include/pydebug.h \ Include/pyerrors.h \ Include/pyfpe.h \ + Include/pygetopt.h \ Include/pymem.h \ Include/pyport.h \ Include/pystate.h \ - Include/pystrtod.h \ Include/pystrcmp.h \ + Include/pystrtod.h \ Include/pythonrun.h \ + Include/pythread.h \ Include/rangeobject.h \ - Include/setobject.h \ + Include/setobject.h \ Include/sliceobject.h \ Include/stringobject.h \ - Include/structseq.h \ Include/structmember.h \ + Include/structseq.h \ Include/symtable.h \ Include/sysmodule.h \ Include/traceback.h \ Include/tupleobject.h \ + Include/ucnhash.h \ Include/unicodeobject.h \ Include/weakrefobject.h \ - pyconfig.h + pyconfig.h \ + $(PARSER_HEADERS) $(LIBRARY_OBJS) $(MODOBJS) Modules/python.o: $(PYTHON_HEADERS) diff --git a/Modules/mmapmodule.c b/Modules/mmapmodule.c index e06cefb..ac39a23 100644 --- a/Modules/mmapmodule.c +++ b/Modules/mmapmodule.c @@ -895,6 +895,9 @@ static PyBufferProcs mmap_as_buffer = { (releasebufferproc)mmap_buffer_releasebuf, }; +static PyObject * +new_mmap_object(PyTypeObject *type, PyObject *args, PyObject *kwdict); + PyDoc_STRVAR(mmap_doc, "Windows: mmap(fileno, length[, tagname[, access[, offset]]])\n\ \n\ @@ -920,7 +923,7 @@ To map anonymous memory, pass -1 as the fileno (both versions)."); static PyTypeObject mmap_object_type = { - PyVarObject_HEAD_INIT(0, 0) /* patched in module init */ + PyVarObject_HEAD_INIT(NULL, 0) "mmap.mmap", /* tp_name */ sizeof(mmap_object), /* tp_size */ 0, /* tp_itemsize */ @@ -940,16 +943,26 @@ static PyTypeObject mmap_object_type = { PyObject_GenericGetAttr, /*tp_getattro*/ 0, /*tp_setattro*/ &mmap_as_buffer, /*tp_as_buffer*/ - Py_TPFLAGS_DEFAULT, /*tp_flags*/ + Py_TPFLAGS_DEFAULT | Py_TPFLAGS_BASETYPE, /*tp_flags*/ mmap_doc, /*tp_doc*/ 0, /* tp_traverse */ 0, /* tp_clear */ 0, /* tp_richcompare */ 0, /* tp_weaklistoffset */ - 0, /* tp_iter */ - 0, /* tp_iternext */ + 0, /* tp_iter */ + 0, /* tp_iternext */ mmap_object_methods, /* tp_methods */ - + 0, /* tp_members */ + 0, /* tp_getset */ + 0, /* tp_base */ + 0, /* tp_dict */ + 0, /* tp_descr_get */ + 0, /* tp_descr_set */ + 0, /* tp_dictoffset */ + 0, /* tp_init */ + PyType_GenericAlloc, /* tp_alloc */ + new_mmap_object, /* tp_new */ + PyObject_Del, /* tp_free */ }; @@ -981,7 +994,7 @@ _GetMapSize(PyObject *o, const char* param) #ifdef UNIX static PyObject * -new_mmap_object(PyObject *self, PyObject *args, PyObject *kwdict) +new_mmap_object(PyTypeObject *type, PyObject *args, PyObject *kwdict) { #ifdef HAVE_FSTAT struct stat st; @@ -1049,7 +1062,7 @@ new_mmap_object(PyObject *self, PyObject *args, PyObject *kwdict) } } #endif - m_obj = PyObject_New(mmap_object, &mmap_object_type); + m_obj = (mmap_object *)type->tp_alloc(type, 0); if (m_obj == NULL) {return NULL;} m_obj->data = NULL; m_obj->size = (size_t) map_size; @@ -1104,7 +1117,7 @@ new_mmap_object(PyObject *self, PyObject *args, PyObject *kwdict) #ifdef MS_WINDOWS static PyObject * -new_mmap_object(PyObject *self, PyObject *args, PyObject *kwdict) +new_mmap_object(PyTypeObject *type, PyObject *args, PyObject *kwdict) { mmap_object *m_obj; PyObject *map_size_obj = NULL, *offset_obj = NULL; @@ -1173,7 +1186,7 @@ new_mmap_object(PyObject *self, PyObject *args, PyObject *kwdict) lseek(fileno, 0, SEEK_SET); } - m_obj = PyObject_New(mmap_object, &mmap_object_type); + m_obj = (mmap_object *)type->tp_alloc(type, 0); if (m_obj == NULL) return NULL; /* Set every field to an invalid marker, so we can safely @@ -1288,13 +1301,6 @@ new_mmap_object(PyObject *self, PyObject *args, PyObject *kwdict) } #endif /* MS_WINDOWS */ -/* List of functions exported by this module */ -static struct PyMethodDef mmap_functions[] = { - {"mmap", (PyCFunction) new_mmap_object, - METH_VARARGS|METH_KEYWORDS, mmap_doc}, - {NULL, NULL} /* Sentinel */ -}; - static void setint(PyObject *d, const char *name, long value) { @@ -1305,14 +1311,14 @@ setint(PyObject *d, const char *name, long value) } PyMODINIT_FUNC - initmmap(void) +initmmap(void) { PyObject *dict, *module; - /* Patch the object type */ - Py_TYPE(&mmap_object_type) = &PyType_Type; + if (PyType_Ready(&mmap_object_type) < 0) + return; - module = Py_InitModule("mmap", mmap_functions); + module = Py_InitModule("mmap", NULL); if (module == NULL) return; dict = PyModule_GetDict(module); @@ -1320,6 +1326,7 @@ PyMODINIT_FUNC return; mmap_module_error = PyExc_EnvironmentError; PyDict_SetItemString(dict, "error", mmap_module_error); + PyDict_SetItemString(dict, "mmap", (PyObject*) &mmap_object_type); #ifdef PROT_EXEC setint(dict, "PROT_EXEC", PROT_EXEC); #endif diff --git a/Parser/tokenizer.c b/Parser/tokenizer.c index 3733f49..36ea466 100644 --- a/Parser/tokenizer.c +++ b/Parser/tokenizer.c @@ -640,6 +640,7 @@ decode_str(const char *str, struct tok_state *tok) { PyObject* utf8 = NULL; const char *s; + char *newl[2] = {NULL, NULL}; int lineno = 0; tok->enc = NULL; tok->str = str; @@ -656,13 +657,23 @@ decode_str(const char *str, struct tok_state *tok) for (s = str;; s++) { if (*s == '\0') break; else if (*s == '\n') { + newl[lineno] = s; lineno++; if (lineno == 2) break; } } tok->enc = NULL; - if (!check_coding_spec(str, s - str, tok, buf_setreadl)) - return error_ret(tok); + /* need to check line 1 and 2 separately since check_coding_spec + assumes a single line as input */ + if (newl[0]) { + if (!check_coding_spec(str, newl[0] - str, tok, buf_setreadl)) + return error_ret(tok); + if (tok->enc == NULL && newl[1]) { + if (!check_coding_spec(newl[0]+1, newl[1] - newl[0], + tok, buf_setreadl)) + return error_ret(tok); + } + } if (tok->enc != NULL) { assert(utf8 == NULL); utf8 = translate_into_utf8(str, tok->enc); diff --git a/Tools/pynche/ColorDB.py b/Tools/pynche/ColorDB.py index 2e7a1b5..3b978fb 100644 --- a/Tools/pynche/ColorDB.py +++ b/Tools/pynche/ColorDB.py @@ -50,10 +50,7 @@ class ColorDB: self.__byname = {} # all unique names (non-aliases). built-on demand self.__allnames = None - while 1: - line = fp.readline() - if not line: - break + for line in fp: # get this compiled regular expression from derived class mo = self._re.match(line) if not mo: -- cgit v0.12