[pypy-commit] pypy vendor/stdlib: add the 3.2.3 version of the stdlib in lib-python/3.2
RonnyPfannschmidt
noreply at buildbot.pypy.org
Sat Apr 14 11:26:33 CEST 2012
Author: Ronny Pfannschmidt <Ronny.Pfannschmidt at gmx.de>
Branch: vendor/stdlib
Changeset: r54357:359343b9ac0e
Date: 2012-04-14 11:24 +0200
http://bitbucket.org/pypy/pypy/changeset/359343b9ac0e/
Log: add the 3.2.3 version of the stdlib in lib-python/3.2
diff too long, truncating to 10000 out of 558051 lines
diff --git a/lib-python/3.2/__future__.py b/lib-python/3.2/__future__.py
new file mode 100644
--- /dev/null
+++ b/lib-python/3.2/__future__.py
@@ -0,0 +1,134 @@
+"""Record of phased-in incompatible language changes.
+
+Each line is of the form:
+
+ FeatureName = "_Feature(" OptionalRelease "," MandatoryRelease ","
+ CompilerFlag ")"
+
+where, normally, OptionalRelease < MandatoryRelease, and both are 5-tuples
+of the same form as sys.version_info:
+
+ (PY_MAJOR_VERSION, # the 2 in 2.1.0a3; an int
+ PY_MINOR_VERSION, # the 1; an int
+ PY_MICRO_VERSION, # the 0; an int
+ PY_RELEASE_LEVEL, # "alpha", "beta", "candidate" or "final"; string
+ PY_RELEASE_SERIAL # the 3; an int
+ )
+
+OptionalRelease records the first release in which
+
+ from __future__ import FeatureName
+
+was accepted.
+
+In the case of MandatoryReleases that have not yet occurred,
+MandatoryRelease predicts the release in which the feature will become part
+of the language.
+
+Else MandatoryRelease records when the feature became part of the language;
+in releases at or after that, modules no longer need
+
+ from __future__ import FeatureName
+
+to use the feature in question, but may continue to use such imports.
+
+MandatoryRelease may also be None, meaning that a planned feature got
+dropped.
+
+Instances of class _Feature have two corresponding methods,
+.getOptionalRelease() and .getMandatoryRelease().
+
+CompilerFlag is the (bitfield) flag that should be passed in the fourth
+argument to the builtin function compile() to enable the feature in
+dynamically compiled code. This flag is stored in the .compiler_flag
+attribute on _Future instances. These values must match the appropriate
+#defines of CO_xxx flags in Include/compile.h.
+
+No feature line is ever to be deleted from this file.
+"""
+
+all_feature_names = [
+ "nested_scopes",
+ "generators",
+ "division",
+ "absolute_import",
+ "with_statement",
+ "print_function",
+ "unicode_literals",
+ "barry_as_FLUFL",
+]
+
+__all__ = ["all_feature_names"] + all_feature_names
+
+# The CO_xxx symbols are defined here under the same names used by
+# compile.h, so that an editor search will find them here. However,
+# they're not exported in __all__, because they don't really belong to
+# this module.
+CO_NESTED = 0x0010 # nested_scopes
+CO_GENERATOR_ALLOWED = 0 # generators (obsolete, was 0x1000)
+CO_FUTURE_DIVISION = 0x2000 # division
+CO_FUTURE_ABSOLUTE_IMPORT = 0x4000 # perform absolute imports by default
+CO_FUTURE_WITH_STATEMENT = 0x8000 # with statement
+CO_FUTURE_PRINT_FUNCTION = 0x10000 # print function
+CO_FUTURE_UNICODE_LITERALS = 0x20000 # unicode string literals
+CO_FUTURE_BARRY_AS_BDFL = 0x40000
+
+class _Feature:
+ def __init__(self, optionalRelease, mandatoryRelease, compiler_flag):
+ self.optional = optionalRelease
+ self.mandatory = mandatoryRelease
+ self.compiler_flag = compiler_flag
+
+ def getOptionalRelease(self):
+ """Return first release in which this feature was recognized.
+
+ This is a 5-tuple, of the same form as sys.version_info.
+ """
+
+ return self.optional
+
+ def getMandatoryRelease(self):
+ """Return release in which this feature will become mandatory.
+
+ This is a 5-tuple, of the same form as sys.version_info, or, if
+ the feature was dropped, is None.
+ """
+
+ return self.mandatory
+
+ def __repr__(self):
+ return "_Feature" + repr((self.optional,
+ self.mandatory,
+ self.compiler_flag))
+
+nested_scopes = _Feature((2, 1, 0, "beta", 1),
+ (2, 2, 0, "alpha", 0),
+ CO_NESTED)
+
+generators = _Feature((2, 2, 0, "alpha", 1),
+ (2, 3, 0, "final", 0),
+ CO_GENERATOR_ALLOWED)
+
+division = _Feature((2, 2, 0, "alpha", 2),
+ (3, 0, 0, "alpha", 0),
+ CO_FUTURE_DIVISION)
+
+absolute_import = _Feature((2, 5, 0, "alpha", 1),
+ (2, 7, 0, "alpha", 0),
+ CO_FUTURE_ABSOLUTE_IMPORT)
+
+with_statement = _Feature((2, 5, 0, "alpha", 1),
+ (2, 6, 0, "alpha", 0),
+ CO_FUTURE_WITH_STATEMENT)
+
+print_function = _Feature((2, 6, 0, "alpha", 2),
+ (3, 0, 0, "alpha", 0),
+ CO_FUTURE_PRINT_FUNCTION)
+
+unicode_literals = _Feature((2, 6, 0, "alpha", 2),
+ (3, 0, 0, "alpha", 0),
+ CO_FUTURE_UNICODE_LITERALS)
+
+barry_as_FLUFL = _Feature((3, 1, 0, "alpha", 2),
+ (3, 9, 0, "alpha", 0),
+ CO_FUTURE_BARRY_AS_BDFL)
diff --git a/lib-python/3.2/__phello__.foo.py b/lib-python/3.2/__phello__.foo.py
new file mode 100644
--- /dev/null
+++ b/lib-python/3.2/__phello__.foo.py
@@ -0,0 +1,1 @@
+# This file exists as a helper for the test.test_frozen module.
diff --git a/lib-python/3.2/_abcoll.py b/lib-python/3.2/_abcoll.py
new file mode 100644
--- /dev/null
+++ b/lib-python/3.2/_abcoll.py
@@ -0,0 +1,623 @@
+# Copyright 2007 Google, Inc. All Rights Reserved.
+# Licensed to PSF under a Contributor Agreement.
+
+"""Abstract Base Classes (ABCs) for collections, according to PEP 3119.
+
+DON'T USE THIS MODULE DIRECTLY! The classes here should be imported
+via collections; they are defined here only to alleviate certain
+bootstrapping issues. Unit tests are in test_collections.
+"""
+
+from abc import ABCMeta, abstractmethod
+import sys
+
+__all__ = ["Hashable", "Iterable", "Iterator",
+ "Sized", "Container", "Callable",
+ "Set", "MutableSet",
+ "Mapping", "MutableMapping",
+ "MappingView", "KeysView", "ItemsView", "ValuesView",
+ "Sequence", "MutableSequence",
+ "ByteString",
+ ]
+
+
+### collection related types which are not exposed through builtin ###
+## iterators ##
+bytes_iterator = type(iter(b''))
+bytearray_iterator = type(iter(bytearray()))
+#callable_iterator = ???
+dict_keyiterator = type(iter({}.keys()))
+dict_valueiterator = type(iter({}.values()))
+dict_itemiterator = type(iter({}.items()))
+list_iterator = type(iter([]))
+list_reverseiterator = type(iter(reversed([])))
+range_iterator = type(iter(range(0)))
+set_iterator = type(iter(set()))
+str_iterator = type(iter(""))
+tuple_iterator = type(iter(()))
+zip_iterator = type(iter(zip()))
+## views ##
+dict_keys = type({}.keys())
+dict_values = type({}.values())
+dict_items = type({}.items())
+## misc ##
+dict_proxy = type(type.__dict__)
+
+
+### ONE-TRICK PONIES ###
+
+class Hashable(metaclass=ABCMeta):
+
+ @abstractmethod
+ def __hash__(self):
+ return 0
+
+ @classmethod
+ def __subclasshook__(cls, C):
+ if cls is Hashable:
+ for B in C.__mro__:
+ if "__hash__" in B.__dict__:
+ if B.__dict__["__hash__"]:
+ return True
+ break
+ return NotImplemented
+
+
+class Iterable(metaclass=ABCMeta):
+
+ @abstractmethod
+ def __iter__(self):
+ while False:
+ yield None
+
+ @classmethod
+ def __subclasshook__(cls, C):
+ if cls is Iterable:
+ if any("__iter__" in B.__dict__ for B in C.__mro__):
+ return True
+ return NotImplemented
+
+
+class Iterator(Iterable):
+
+ @abstractmethod
+ def __next__(self):
+ raise StopIteration
+
+ def __iter__(self):
+ return self
+
+ @classmethod
+ def __subclasshook__(cls, C):
+ if cls is Iterator:
+ if (any("__next__" in B.__dict__ for B in C.__mro__) and
+ any("__iter__" in B.__dict__ for B in C.__mro__)):
+ return True
+ return NotImplemented
+
+Iterator.register(bytes_iterator)
+Iterator.register(bytearray_iterator)
+#Iterator.register(callable_iterator)
+Iterator.register(dict_keyiterator)
+Iterator.register(dict_valueiterator)
+Iterator.register(dict_itemiterator)
+Iterator.register(list_iterator)
+Iterator.register(list_reverseiterator)
+Iterator.register(range_iterator)
+Iterator.register(set_iterator)
+Iterator.register(str_iterator)
+Iterator.register(tuple_iterator)
+Iterator.register(zip_iterator)
+
+class Sized(metaclass=ABCMeta):
+
+ @abstractmethod
+ def __len__(self):
+ return 0
+
+ @classmethod
+ def __subclasshook__(cls, C):
+ if cls is Sized:
+ if any("__len__" in B.__dict__ for B in C.__mro__):
+ return True
+ return NotImplemented
+
+
+class Container(metaclass=ABCMeta):
+
+ @abstractmethod
+ def __contains__(self, x):
+ return False
+
+ @classmethod
+ def __subclasshook__(cls, C):
+ if cls is Container:
+ if any("__contains__" in B.__dict__ for B in C.__mro__):
+ return True
+ return NotImplemented
+
+
+class Callable(metaclass=ABCMeta):
+
+ @abstractmethod
+ def __call__(self, *args, **kwds):
+ return False
+
+ @classmethod
+ def __subclasshook__(cls, C):
+ if cls is Callable:
+ if any("__call__" in B.__dict__ for B in C.__mro__):
+ return True
+ return NotImplemented
+
+
+### SETS ###
+
+
+class Set(Sized, Iterable, Container):
+
+ """A set is a finite, iterable container.
+
+ This class provides concrete generic implementations of all
+ methods except for __contains__, __iter__ and __len__.
+
+ To override the comparisons (presumably for speed, as the
+ semantics are fixed), all you have to do is redefine __le__ and
+ then the other operations will automatically follow suit.
+ """
+
+ def __le__(self, other):
+ if not isinstance(other, Set):
+ return NotImplemented
+ if len(self) > len(other):
+ return False
+ for elem in self:
+ if elem not in other:
+ return False
+ return True
+
+ def __lt__(self, other):
+ if not isinstance(other, Set):
+ return NotImplemented
+ return len(self) < len(other) and self.__le__(other)
+
+ def __gt__(self, other):
+ if not isinstance(other, Set):
+ return NotImplemented
+ return other < self
+
+ def __ge__(self, other):
+ if not isinstance(other, Set):
+ return NotImplemented
+ return other <= self
+
+ def __eq__(self, other):
+ if not isinstance(other, Set):
+ return NotImplemented
+ return len(self) == len(other) and self.__le__(other)
+
+ def __ne__(self, other):
+ return not (self == other)
+
+ @classmethod
+ def _from_iterable(cls, it):
+ '''Construct an instance of the class from any iterable input.
+
+ Must override this method if the class constructor signature
+ does not accept an iterable for an input.
+ '''
+ return cls(it)
+
+ def __and__(self, other):
+ if not isinstance(other, Iterable):
+ return NotImplemented
+ return self._from_iterable(value for value in other if value in self)
+
+ def isdisjoint(self, other):
+ for value in other:
+ if value in self:
+ return False
+ return True
+
+ def __or__(self, other):
+ if not isinstance(other, Iterable):
+ return NotImplemented
+ chain = (e for s in (self, other) for e in s)
+ return self._from_iterable(chain)
+
+ def __sub__(self, other):
+ if not isinstance(other, Set):
+ if not isinstance(other, Iterable):
+ return NotImplemented
+ other = self._from_iterable(other)
+ return self._from_iterable(value for value in self
+ if value not in other)
+
+ def __xor__(self, other):
+ if not isinstance(other, Set):
+ if not isinstance(other, Iterable):
+ return NotImplemented
+ other = self._from_iterable(other)
+ return (self - other) | (other - self)
+
+ def _hash(self):
+ """Compute the hash value of a set.
+
+ Note that we don't define __hash__: not all sets are hashable.
+ But if you define a hashable set type, its __hash__ should
+ call this function.
+
+ This must be compatible __eq__.
+
+ All sets ought to compare equal if they contain the same
+ elements, regardless of how they are implemented, and
+ regardless of the order of the elements; so there's not much
+ freedom for __eq__ or __hash__. We match the algorithm used
+ by the built-in frozenset type.
+ """
+ MAX = sys.maxsize
+ MASK = 2 * MAX + 1
+ n = len(self)
+ h = 1927868237 * (n + 1)
+ h &= MASK
+ for x in self:
+ hx = hash(x)
+ h ^= (hx ^ (hx << 16) ^ 89869747) * 3644798167
+ h &= MASK
+ h = h * 69069 + 907133923
+ h &= MASK
+ if h > MAX:
+ h -= MASK + 1
+ if h == -1:
+ h = 590923713
+ return h
+
+Set.register(frozenset)
+
+
+class MutableSet(Set):
+
+ @abstractmethod
+ def add(self, value):
+ """Add an element."""
+ raise NotImplementedError
+
+ @abstractmethod
+ def discard(self, value):
+ """Remove an element. Do not raise an exception if absent."""
+ raise NotImplementedError
+
+ def remove(self, value):
+ """Remove an element. If not a member, raise a KeyError."""
+ if value not in self:
+ raise KeyError(value)
+ self.discard(value)
+
+ def pop(self):
+ """Return the popped value. Raise KeyError if empty."""
+ it = iter(self)
+ try:
+ value = next(it)
+ except StopIteration:
+ raise KeyError
+ self.discard(value)
+ return value
+
+ def clear(self):
+ """This is slow (creates N new iterators!) but effective."""
+ try:
+ while True:
+ self.pop()
+ except KeyError:
+ pass
+
+ def __ior__(self, it):
+ for value in it:
+ self.add(value)
+ return self
+
+ def __iand__(self, it):
+ for value in (self - it):
+ self.discard(value)
+ return self
+
+ def __ixor__(self, it):
+ if it is self:
+ self.clear()
+ else:
+ if not isinstance(it, Set):
+ it = self._from_iterable(it)
+ for value in it:
+ if value in self:
+ self.discard(value)
+ else:
+ self.add(value)
+ return self
+
+ def __isub__(self, it):
+ if it is self:
+ self.clear()
+ else:
+ for value in it:
+ self.discard(value)
+ return self
+
+MutableSet.register(set)
+
+
+### MAPPINGS ###
+
+
+class Mapping(Sized, Iterable, Container):
+
+ @abstractmethod
+ def __getitem__(self, key):
+ raise KeyError
+
+ def get(self, key, default=None):
+ try:
+ return self[key]
+ except KeyError:
+ return default
+
+ def __contains__(self, key):
+ try:
+ self[key]
+ except KeyError:
+ return False
+ else:
+ return True
+
+ def keys(self):
+ return KeysView(self)
+
+ def items(self):
+ return ItemsView(self)
+
+ def values(self):
+ return ValuesView(self)
+
+ def __eq__(self, other):
+ if not isinstance(other, Mapping):
+ return NotImplemented
+ return dict(self.items()) == dict(other.items())
+
+ def __ne__(self, other):
+ return not (self == other)
+
+
+class MappingView(Sized):
+
+ def __init__(self, mapping):
+ self._mapping = mapping
+
+ def __len__(self):
+ return len(self._mapping)
+
+ def __repr__(self):
+ return '{0.__class__.__name__}({0._mapping!r})'.format(self)
+
+
+class KeysView(MappingView, Set):
+
+ @classmethod
+ def _from_iterable(self, it):
+ return set(it)
+
+ def __contains__(self, key):
+ return key in self._mapping
+
+ def __iter__(self):
+ for key in self._mapping:
+ yield key
+
+KeysView.register(dict_keys)
+
+
+class ItemsView(MappingView, Set):
+
+ @classmethod
+ def _from_iterable(self, it):
+ return set(it)
+
+ def __contains__(self, item):
+ key, value = item
+ try:
+ v = self._mapping[key]
+ except KeyError:
+ return False
+ else:
+ return v == value
+
+ def __iter__(self):
+ for key in self._mapping:
+ yield (key, self._mapping[key])
+
+ItemsView.register(dict_items)
+
+
+class ValuesView(MappingView):
+
+ def __contains__(self, value):
+ for key in self._mapping:
+ if value == self._mapping[key]:
+ return True
+ return False
+
+ def __iter__(self):
+ for key in self._mapping:
+ yield self._mapping[key]
+
+ValuesView.register(dict_values)
+
+
+class MutableMapping(Mapping):
+
+ @abstractmethod
+ def __setitem__(self, key, value):
+ raise KeyError
+
+ @abstractmethod
+ def __delitem__(self, key):
+ raise KeyError
+
+ __marker = object()
+
+ def pop(self, key, default=__marker):
+ try:
+ value = self[key]
+ except KeyError:
+ if default is self.__marker:
+ raise
+ return default
+ else:
+ del self[key]
+ return value
+
+ def popitem(self):
+ try:
+ key = next(iter(self))
+ except StopIteration:
+ raise KeyError
+ value = self[key]
+ del self[key]
+ return key, value
+
+ def clear(self):
+ try:
+ while True:
+ self.popitem()
+ except KeyError:
+ pass
+
+ def update(*args, **kwds):
+ if len(args) > 2:
+ raise TypeError("update() takes at most 2 positional "
+ "arguments ({} given)".format(len(args)))
+ elif not args:
+ raise TypeError("update() takes at least 1 argument (0 given)")
+ self = args[0]
+ other = args[1] if len(args) >= 2 else ()
+
+ if isinstance(other, Mapping):
+ for key in other:
+ self[key] = other[key]
+ elif hasattr(other, "keys"):
+ for key in other.keys():
+ self[key] = other[key]
+ else:
+ for key, value in other:
+ self[key] = value
+ for key, value in kwds.items():
+ self[key] = value
+
+ def setdefault(self, key, default=None):
+ try:
+ return self[key]
+ except KeyError:
+ self[key] = default
+ return default
+
+MutableMapping.register(dict)
+
+
+### SEQUENCES ###
+
+
+class Sequence(Sized, Iterable, Container):
+
+ """All the operations on a read-only sequence.
+
+ Concrete subclasses must override __new__ or __init__,
+ __getitem__, and __len__.
+ """
+
+ @abstractmethod
+ def __getitem__(self, index):
+ raise IndexError
+
+ def __iter__(self):
+ i = 0
+ try:
+ while True:
+ v = self[i]
+ yield v
+ i += 1
+ except IndexError:
+ return
+
+ def __contains__(self, value):
+ for v in self:
+ if v == value:
+ return True
+ return False
+
+ def __reversed__(self):
+ for i in reversed(range(len(self))):
+ yield self[i]
+
+ def index(self, value):
+ for i, v in enumerate(self):
+ if v == value:
+ return i
+ raise ValueError
+
+ def count(self, value):
+ return sum(1 for v in self if v == value)
+
+Sequence.register(tuple)
+Sequence.register(str)
+Sequence.register(range)
+
+
+class ByteString(Sequence):
+
+ """This unifies bytes and bytearray.
+
+ XXX Should add all their methods.
+ """
+
+ByteString.register(bytes)
+ByteString.register(bytearray)
+
+
+class MutableSequence(Sequence):
+
+ @abstractmethod
+ def __setitem__(self, index, value):
+ raise IndexError
+
+ @abstractmethod
+ def __delitem__(self, index):
+ raise IndexError
+
+ @abstractmethod
+ def insert(self, index, value):
+ raise IndexError
+
+ def append(self, value):
+ self.insert(len(self), value)
+
+ def reverse(self):
+ n = len(self)
+ for i in range(n//2):
+ self[i], self[n-i-1] = self[n-i-1], self[i]
+
+ def extend(self, values):
+ for v in values:
+ self.append(v)
+
+ def pop(self, index=-1):
+ v = self[index]
+ del self[index]
+ return v
+
+ def remove(self, value):
+ del self[self.index(value)]
+
+ def __iadd__(self, values):
+ self.extend(values)
+ return self
+
+MutableSequence.register(list)
+MutableSequence.register(bytearray) # Multiply inheriting, see ByteString
diff --git a/lib-python/3.2/_compat_pickle.py b/lib-python/3.2/_compat_pickle.py
new file mode 100644
--- /dev/null
+++ b/lib-python/3.2/_compat_pickle.py
@@ -0,0 +1,81 @@
+# This module is used to map the old Python 2 names to the new names used in
+# Python 3 for the pickle module. This needed to make pickle streams
+# generated with Python 2 loadable by Python 3.
+
+# This is a copy of lib2to3.fixes.fix_imports.MAPPING. We cannot import
+# lib2to3 and use the mapping defined there, because lib2to3 uses pickle.
+# Thus, this could cause the module to be imported recursively.
+IMPORT_MAPPING = {
+ 'StringIO': 'io',
+ 'cStringIO': 'io',
+ 'cPickle': 'pickle',
+ '__builtin__' : 'builtins',
+ 'copy_reg': 'copyreg',
+ 'Queue': 'queue',
+ 'SocketServer': 'socketserver',
+ 'ConfigParser': 'configparser',
+ 'repr': 'reprlib',
+ 'FileDialog': 'tkinter.filedialog',
+ 'tkFileDialog': 'tkinter.filedialog',
+ 'SimpleDialog': 'tkinter.simpledialog',
+ 'tkSimpleDialog': 'tkinter.simpledialog',
+ 'tkColorChooser': 'tkinter.colorchooser',
+ 'tkCommonDialog': 'tkinter.commondialog',
+ 'Dialog': 'tkinter.dialog',
+ 'Tkdnd': 'tkinter.dnd',
+ 'tkFont': 'tkinter.font',
+ 'tkMessageBox': 'tkinter.messagebox',
+ 'ScrolledText': 'tkinter.scrolledtext',
+ 'Tkconstants': 'tkinter.constants',
+ 'Tix': 'tkinter.tix',
+ 'ttk': 'tkinter.ttk',
+ 'Tkinter': 'tkinter',
+ 'markupbase': '_markupbase',
+ '_winreg': 'winreg',
+ 'thread': '_thread',
+ 'dummy_thread': '_dummy_thread',
+ 'dbhash': 'dbm.bsd',
+ 'dumbdbm': 'dbm.dumb',
+ 'dbm': 'dbm.ndbm',
+ 'gdbm': 'dbm.gnu',
+ 'xmlrpclib': 'xmlrpc.client',
+ 'DocXMLRPCServer': 'xmlrpc.server',
+ 'SimpleXMLRPCServer': 'xmlrpc.server',
+ 'httplib': 'http.client',
+ 'htmlentitydefs' : 'html.entities',
+ 'HTMLParser' : 'html.parser',
+ 'Cookie': 'http.cookies',
+ 'cookielib': 'http.cookiejar',
+ 'BaseHTTPServer': 'http.server',
+ 'SimpleHTTPServer': 'http.server',
+ 'CGIHTTPServer': 'http.server',
+ 'test.test_support': 'test.support',
+ 'commands': 'subprocess',
+ 'UserString' : 'collections',
+ 'UserList' : 'collections',
+ 'urlparse' : 'urllib.parse',
+ 'robotparser' : 'urllib.robotparser',
+ 'whichdb': 'dbm',
+ 'anydbm': 'dbm'
+}
+
+
+# This contains rename rules that are easy to handle. We ignore the more
+# complex stuff (e.g. mapping the names in the urllib and types modules).
+# These rules should be run before import names are fixed.
+NAME_MAPPING = {
+ ('__builtin__', 'xrange'): ('builtins', 'range'),
+ ('__builtin__', 'reduce'): ('functools', 'reduce'),
+ ('__builtin__', 'intern'): ('sys', 'intern'),
+ ('__builtin__', 'unichr'): ('builtins', 'chr'),
+ ('__builtin__', 'basestring'): ('builtins', 'str'),
+ ('__builtin__', 'long'): ('builtins', 'int'),
+ ('itertools', 'izip'): ('builtins', 'zip'),
+ ('itertools', 'imap'): ('builtins', 'map'),
+ ('itertools', 'ifilter'): ('builtins', 'filter'),
+ ('itertools', 'ifilterfalse'): ('itertools', 'filterfalse'),
+}
+
+# Same, but for 3.x to 2.x
+REVERSE_IMPORT_MAPPING = dict((v, k) for (k, v) in IMPORT_MAPPING.items())
+REVERSE_NAME_MAPPING = dict((v, k) for (k, v) in NAME_MAPPING.items())
diff --git a/lib-python/3.2/_dummy_thread.py b/lib-python/3.2/_dummy_thread.py
new file mode 100644
--- /dev/null
+++ b/lib-python/3.2/_dummy_thread.py
@@ -0,0 +1,155 @@
+"""Drop-in replacement for the thread module.
+
+Meant to be used as a brain-dead substitute so that threaded code does
+not need to be rewritten for when the thread module is not present.
+
+Suggested usage is::
+
+ try:
+ import _thread
+ except ImportError:
+ import _dummy_thread as _thread
+
+"""
+# Exports only things specified by thread documentation;
+# skipping obsolete synonyms allocate(), start_new(), exit_thread().
+__all__ = ['error', 'start_new_thread', 'exit', 'get_ident', 'allocate_lock',
+ 'interrupt_main', 'LockType']
+
+# A dummy value
+TIMEOUT_MAX = 2**31
+
+# NOTE: this module can be imported early in the extension building process,
+# and so top level imports of other modules should be avoided. Instead, all
+# imports are done when needed on a function-by-function basis. Since threads
+# are disabled, the import lock should not be an issue anyway (??).
+
+class error(Exception):
+ """Dummy implementation of _thread.error."""
+
+ def __init__(self, *args):
+ self.args = args
+
+def start_new_thread(function, args, kwargs={}):
+ """Dummy implementation of _thread.start_new_thread().
+
+ Compatibility is maintained by making sure that ``args`` is a
+ tuple and ``kwargs`` is a dictionary. If an exception is raised
+ and it is SystemExit (which can be done by _thread.exit()) it is
+ caught and nothing is done; all other exceptions are printed out
+ by using traceback.print_exc().
+
+ If the executed function calls interrupt_main the KeyboardInterrupt will be
+ raised when the function returns.
+
+ """
+ if type(args) != type(tuple()):
+ raise TypeError("2nd arg must be a tuple")
+ if type(kwargs) != type(dict()):
+ raise TypeError("3rd arg must be a dict")
+ global _main
+ _main = False
+ try:
+ function(*args, **kwargs)
+ except SystemExit:
+ pass
+ except:
+ import traceback
+ traceback.print_exc()
+ _main = True
+ global _interrupt
+ if _interrupt:
+ _interrupt = False
+ raise KeyboardInterrupt
+
+def exit():
+ """Dummy implementation of _thread.exit()."""
+ raise SystemExit
+
+def get_ident():
+ """Dummy implementation of _thread.get_ident().
+
+ Since this module should only be used when _threadmodule is not
+ available, it is safe to assume that the current process is the
+ only thread. Thus a constant can be safely returned.
+ """
+ return -1
+
+def allocate_lock():
+ """Dummy implementation of _thread.allocate_lock()."""
+ return LockType()
+
+def stack_size(size=None):
+ """Dummy implementation of _thread.stack_size()."""
+ if size is not None:
+ raise error("setting thread stack size not supported")
+ return 0
+
+class LockType(object):
+ """Class implementing dummy implementation of _thread.LockType.
+
+ Compatibility is maintained by maintaining self.locked_status
+ which is a boolean that stores the state of the lock. Pickling of
+ the lock, though, should not be done since if the _thread module is
+ then used with an unpickled ``lock()`` from here problems could
+ occur from this class not having atomic methods.
+
+ """
+
+ def __init__(self):
+ self.locked_status = False
+
+ def acquire(self, waitflag=None, timeout=-1):
+ """Dummy implementation of acquire().
+
+ For blocking calls, self.locked_status is automatically set to
+ True and returned appropriately based on value of
+ ``waitflag``. If it is non-blocking, then the value is
+ actually checked and not set if it is already acquired. This
+ is all done so that threading.Condition's assert statements
+ aren't triggered and throw a little fit.
+
+ """
+ if waitflag is None or waitflag:
+ self.locked_status = True
+ return True
+ else:
+ if not self.locked_status:
+ self.locked_status = True
+ return True
+ else:
+ if timeout > 0:
+ import time
+ time.sleep(timeout)
+ return False
+
+ __enter__ = acquire
+
+ def __exit__(self, typ, val, tb):
+ self.release()
+
+ def release(self):
+ """Release the dummy lock."""
+ # XXX Perhaps shouldn't actually bother to test? Could lead
+ # to problems for complex, threaded code.
+ if not self.locked_status:
+ raise error
+ self.locked_status = False
+ return True
+
+ def locked(self):
+ return self.locked_status
+
+# Used to signal that interrupt_main was called in a "thread"
+_interrupt = False
+# True when not executing in a "thread"
+_main = True
+
+def interrupt_main():
+ """Set _interrupt flag to True to have start_new_thread raise
+ KeyboardInterrupt upon exiting."""
+ if _main:
+ raise KeyboardInterrupt
+ else:
+ global _interrupt
+ _interrupt = True
diff --git a/lib-python/3.2/_markupbase.py b/lib-python/3.2/_markupbase.py
new file mode 100644
--- /dev/null
+++ b/lib-python/3.2/_markupbase.py
@@ -0,0 +1,395 @@
+"""Shared support for scanning document type declarations in HTML and XHTML.
+
+This module is used as a foundation for the html.parser module. It has no
+documented public API and should not be used directly.
+
+"""
+
+import re
+
+_declname_match = re.compile(r'[a-zA-Z][-_.a-zA-Z0-9]*\s*').match
+_declstringlit_match = re.compile(r'(\'[^\']*\'|"[^"]*")\s*').match
+_commentclose = re.compile(r'--\s*>')
+_markedsectionclose = re.compile(r']\s*]\s*>')
+
+# An analysis of the MS-Word extensions is available at
+# http://www.planetpublish.com/xmlarena/xap/Thursday/WordtoXML.pdf
+
+_msmarkedsectionclose = re.compile(r']\s*>')
+
+del re
+
+
+class ParserBase:
+ """Parser base class which provides some common support methods used
+ by the SGML/HTML and XHTML parsers."""
+
+ def __init__(self):
+ if self.__class__ is ParserBase:
+ raise RuntimeError(
+ "_markupbase.ParserBase must be subclassed")
+
+ def error(self, message):
+ raise NotImplementedError(
+ "subclasses of ParserBase must override error()")
+
+ def reset(self):
+ self.lineno = 1
+ self.offset = 0
+
+ def getpos(self):
+ """Return current line number and offset."""
+ return self.lineno, self.offset
+
+ # Internal -- update line number and offset. This should be
+ # called for each piece of data exactly once, in order -- in other
+ # words the concatenation of all the input strings to this
+ # function should be exactly the entire input.
+ def updatepos(self, i, j):
+ if i >= j:
+ return j
+ rawdata = self.rawdata
+ nlines = rawdata.count("\n", i, j)
+ if nlines:
+ self.lineno = self.lineno + nlines
+ pos = rawdata.rindex("\n", i, j) # Should not fail
+ self.offset = j-(pos+1)
+ else:
+ self.offset = self.offset + j-i
+ return j
+
+ _decl_otherchars = ''
+
+ # Internal -- parse declaration (for use by subclasses).
+ def parse_declaration(self, i):
+ # This is some sort of declaration; in "HTML as
+ # deployed," this should only be the document type
+ # declaration ("<!DOCTYPE html...>").
+ # ISO 8879:1986, however, has more complex
+ # declaration syntax for elements in <!...>, including:
+ # --comment--
+ # [marked section]
+ # name in the following list: ENTITY, DOCTYPE, ELEMENT,
+ # ATTLIST, NOTATION, SHORTREF, USEMAP,
+ # LINKTYPE, LINK, IDLINK, USELINK, SYSTEM
+ rawdata = self.rawdata
+ j = i + 2
+ assert rawdata[i:j] == "<!", "unexpected call to parse_declaration"
+ if rawdata[j:j+1] == ">":
+ # the empty comment <!>
+ return j + 1
+ if rawdata[j:j+1] in ("-", ""):
+ # Start of comment followed by buffer boundary,
+ # or just a buffer boundary.
+ return -1
+ # A simple, practical version could look like: ((name|stringlit) S*) + '>'
+ n = len(rawdata)
+ if rawdata[j:j+2] == '--': #comment
+ # Locate --.*-- as the body of the comment
+ return self.parse_comment(i)
+ elif rawdata[j] == '[': #marked section
+ # Locate [statusWord [...arbitrary SGML...]] as the body of the marked section
+ # Where statusWord is one of TEMP, CDATA, IGNORE, INCLUDE, RCDATA
+ # Note that this is extended by Microsoft Office "Save as Web" function
+ # to include [if...] and [endif].
+ return self.parse_marked_section(i)
+ else: #all other declaration elements
+ decltype, j = self._scan_name(j, i)
+ if j < 0:
+ return j
+ if decltype == "doctype":
+ self._decl_otherchars = ''
+ while j < n:
+ c = rawdata[j]
+ if c == ">":
+ # end of declaration syntax
+ data = rawdata[i+2:j]
+ if decltype == "doctype":
+ self.handle_decl(data)
+ else:
+ # According to the HTML5 specs sections "8.2.4.44 Bogus
+ # comment state" and "8.2.4.45 Markup declaration open
+ # state", a comment token should be emitted.
+ # Calling unknown_decl provides more flexibility though.
+ self.unknown_decl(data)
+ return j + 1
+ if c in "\"'":
+ m = _declstringlit_match(rawdata, j)
+ if not m:
+ return -1 # incomplete
+ j = m.end()
+ elif c in "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ":
+ name, j = self._scan_name(j, i)
+ elif c in self._decl_otherchars:
+ j = j + 1
+ elif c == "[":
+ # this could be handled in a separate doctype parser
+ if decltype == "doctype":
+ j = self._parse_doctype_subset(j + 1, i)
+ elif decltype in {"attlist", "linktype", "link", "element"}:
+ # must tolerate []'d groups in a content model in an element declaration
+ # also in data attribute specifications of attlist declaration
+ # also link type declaration subsets in linktype declarations
+ # also link attribute specification lists in link declarations
+ self.error("unsupported '[' char in %s declaration" % decltype)
+ else:
+ self.error("unexpected '[' char in declaration")
+ else:
+ self.error(
+ "unexpected %r char in declaration" % rawdata[j])
+ if j < 0:
+ return j
+ return -1 # incomplete
+
+ # Internal -- parse a marked section
+ # Override this to handle MS-word extension syntax <![if word]>content<![endif]>
+ def parse_marked_section(self, i, report=1):
+ rawdata= self.rawdata
+ assert rawdata[i:i+3] == '<![', "unexpected call to parse_marked_section()"
+ sectName, j = self._scan_name( i+3, i )
+ if j < 0:
+ return j
+ if sectName in {"temp", "cdata", "ignore", "include", "rcdata"}:
+ # look for standard ]]> ending
+ match= _markedsectionclose.search(rawdata, i+3)
+ elif sectName in {"if", "else", "endif"}:
+ # look for MS Office ]> ending
+ match= _msmarkedsectionclose.search(rawdata, i+3)
+ else:
+ self.error('unknown status keyword %r in marked section' % rawdata[i+3:j])
+ if not match:
+ return -1
+ if report:
+ j = match.start(0)
+ self.unknown_decl(rawdata[i+3: j])
+ return match.end(0)
+
+ # Internal -- parse comment, return length or -1 if not terminated
+ def parse_comment(self, i, report=1):
+ rawdata = self.rawdata
+ if rawdata[i:i+4] != '<!--':
+ self.error('unexpected call to parse_comment()')
+ match = _commentclose.search(rawdata, i+4)
+ if not match:
+ return -1
+ if report:
+ j = match.start(0)
+ self.handle_comment(rawdata[i+4: j])
+ return match.end(0)
+
+ # Internal -- scan past the internal subset in a <!DOCTYPE declaration,
+ # returning the index just past any whitespace following the trailing ']'.
+ def _parse_doctype_subset(self, i, declstartpos):
+ rawdata = self.rawdata
+ n = len(rawdata)
+ j = i
+ while j < n:
+ c = rawdata[j]
+ if c == "<":
+ s = rawdata[j:j+2]
+ if s == "<":
+ # end of buffer; incomplete
+ return -1
+ if s != "<!":
+ self.updatepos(declstartpos, j + 1)
+ self.error("unexpected char in internal subset (in %r)" % s)
+ if (j + 2) == n:
+ # end of buffer; incomplete
+ return -1
+ if (j + 4) > n:
+ # end of buffer; incomplete
+ return -1
+ if rawdata[j:j+4] == "<!--":
+ j = self.parse_comment(j, report=0)
+ if j < 0:
+ return j
+ continue
+ name, j = self._scan_name(j + 2, declstartpos)
+ if j == -1:
+ return -1
+ if name not in {"attlist", "element", "entity", "notation"}:
+ self.updatepos(declstartpos, j + 2)
+ self.error(
+ "unknown declaration %r in internal subset" % name)
+ # handle the individual names
+ meth = getattr(self, "_parse_doctype_" + name)
+ j = meth(j, declstartpos)
+ if j < 0:
+ return j
+ elif c == "%":
+ # parameter entity reference
+ if (j + 1) == n:
+ # end of buffer; incomplete
+ return -1
+ s, j = self._scan_name(j + 1, declstartpos)
+ if j < 0:
+ return j
+ if rawdata[j] == ";":
+ j = j + 1
+ elif c == "]":
+ j = j + 1
+ while j < n and rawdata[j].isspace():
+ j = j + 1
+ if j < n:
+ if rawdata[j] == ">":
+ return j
+ self.updatepos(declstartpos, j)
+ self.error("unexpected char after internal subset")
+ else:
+ return -1
+ elif c.isspace():
+ j = j + 1
+ else:
+ self.updatepos(declstartpos, j)
+ self.error("unexpected char %r in internal subset" % c)
+ # end of buffer reached
+ return -1
+
+ # Internal -- scan past <!ELEMENT declarations
+ def _parse_doctype_element(self, i, declstartpos):
+ name, j = self._scan_name(i, declstartpos)
+ if j == -1:
+ return -1
+ # style content model; just skip until '>'
+ rawdata = self.rawdata
+ if '>' in rawdata[j:]:
+ return rawdata.find(">", j) + 1
+ return -1
+
+ # Internal -- scan past <!ATTLIST declarations
+ def _parse_doctype_attlist(self, i, declstartpos):
+ rawdata = self.rawdata
+ name, j = self._scan_name(i, declstartpos)
+ c = rawdata[j:j+1]
+ if c == "":
+ return -1
+ if c == ">":
+ return j + 1
+ while 1:
+ # scan a series of attribute descriptions; simplified:
+ # name type [value] [#constraint]
+ name, j = self._scan_name(j, declstartpos)
+ if j < 0:
+ return j
+ c = rawdata[j:j+1]
+ if c == "":
+ return -1
+ if c == "(":
+ # an enumerated type; look for ')'
+ if ")" in rawdata[j:]:
+ j = rawdata.find(")", j) + 1
+ else:
+ return -1
+ while rawdata[j:j+1].isspace():
+ j = j + 1
+ if not rawdata[j:]:
+ # end of buffer, incomplete
+ return -1
+ else:
+ name, j = self._scan_name(j, declstartpos)
+ c = rawdata[j:j+1]
+ if not c:
+ return -1
+ if c in "'\"":
+ m = _declstringlit_match(rawdata, j)
+ if m:
+ j = m.end()
+ else:
+ return -1
+ c = rawdata[j:j+1]
+ if not c:
+ return -1
+ if c == "#":
+ if rawdata[j:] == "#":
+ # end of buffer
+ return -1
+ name, j = self._scan_name(j + 1, declstartpos)
+ if j < 0:
+ return j
+ c = rawdata[j:j+1]
+ if not c:
+ return -1
+ if c == '>':
+ # all done
+ return j + 1
+
+ # Internal -- scan past <!NOTATION declarations
+ def _parse_doctype_notation(self, i, declstartpos):
+ name, j = self._scan_name(i, declstartpos)
+ if j < 0:
+ return j
+ rawdata = self.rawdata
+ while 1:
+ c = rawdata[j:j+1]
+ if not c:
+ # end of buffer; incomplete
+ return -1
+ if c == '>':
+ return j + 1
+ if c in "'\"":
+ m = _declstringlit_match(rawdata, j)
+ if not m:
+ return -1
+ j = m.end()
+ else:
+ name, j = self._scan_name(j, declstartpos)
+ if j < 0:
+ return j
+
+ # Internal -- scan past <!ENTITY declarations
+ def _parse_doctype_entity(self, i, declstartpos):
+ rawdata = self.rawdata
+ if rawdata[i:i+1] == "%":
+ j = i + 1
+ while 1:
+ c = rawdata[j:j+1]
+ if not c:
+ return -1
+ if c.isspace():
+ j = j + 1
+ else:
+ break
+ else:
+ j = i
+ name, j = self._scan_name(j, declstartpos)
+ if j < 0:
+ return j
+ while 1:
+ c = self.rawdata[j:j+1]
+ if not c:
+ return -1
+ if c in "'\"":
+ m = _declstringlit_match(rawdata, j)
+ if m:
+ j = m.end()
+ else:
+ return -1 # incomplete
+ elif c == ">":
+ return j + 1
+ else:
+ name, j = self._scan_name(j, declstartpos)
+ if j < 0:
+ return j
+
+ # Internal -- scan a name token and the new position and the token, or
+ # return -1 if we've reached the end of the buffer.
+ def _scan_name(self, i, declstartpos):
+ rawdata = self.rawdata
+ n = len(rawdata)
+ if i == n:
+ return None, -1
+ m = _declname_match(rawdata, i)
+ if m:
+ s = m.group()
+ name = s.strip()
+ if (i + len(s)) == n:
+ return None, -1 # end of buffer
+ return name.lower(), m.end()
+ else:
+ self.updatepos(declstartpos, i)
+ self.error("expected name token at %r"
+ % rawdata[declstartpos:declstartpos+20])
+
+ # To be overridden -- handlers for unknown objects
+ def unknown_decl(self, data):
+ pass
diff --git a/lib-python/3.2/_pyio.py b/lib-python/3.2/_pyio.py
new file mode 100644
--- /dev/null
+++ b/lib-python/3.2/_pyio.py
@@ -0,0 +1,2033 @@
+"""
+Python implementation of the io module.
+"""
+
+import os
+import abc
+import codecs
+import warnings
+import errno
+# Import _thread instead of threading to reduce startup cost
+try:
+ from _thread import allocate_lock as Lock
+except ImportError:
+ from _dummy_thread import allocate_lock as Lock
+
+import io
+from io import (__all__, SEEK_SET, SEEK_CUR, SEEK_END)
+from errno import EINTR
+
+# open() uses st_blksize whenever we can
+DEFAULT_BUFFER_SIZE = 8 * 1024 # bytes
+
+# NOTE: Base classes defined here are registered with the "official" ABCs
+# defined in io.py. We don't use real inheritance though, because we don't
+# want to inherit the C implementations.
+
+
+class BlockingIOError(IOError):
+
+ """Exception raised when I/O would block on a non-blocking I/O stream."""
+
+ def __init__(self, errno, strerror, characters_written=0):
+ super().__init__(errno, strerror)
+ if not isinstance(characters_written, int):
+ raise TypeError("characters_written must be a integer")
+ self.characters_written = characters_written
+
+
+def open(file, mode="r", buffering=-1, encoding=None, errors=None,
+ newline=None, closefd=True):
+
+ r"""Open file and return a stream. Raise IOError upon failure.
+
+ file is either a text or byte string giving the name (and the path
+ if the file isn't in the current working directory) of the file to
+ be opened or an integer file descriptor of the file to be
+ wrapped. (If a file descriptor is given, it is closed when the
+ returned I/O object is closed, unless closefd is set to False.)
+
+ mode is an optional string that specifies the mode in which the file
+ is opened. It defaults to 'r' which means open for reading in text
+ mode. Other common values are 'w' for writing (truncating the file if
+ it already exists), and 'a' for appending (which on some Unix systems,
+ means that all writes append to the end of the file regardless of the
+ current seek position). In text mode, if encoding is not specified the
+ encoding used is platform dependent. (For reading and writing raw
+ bytes use binary mode and leave encoding unspecified.) The available
+ modes are:
+
+ ========= ===============================================================
+ Character Meaning
+ --------- ---------------------------------------------------------------
+ 'r' open for reading (default)
+ 'w' open for writing, truncating the file first
+ 'a' open for writing, appending to the end of the file if it exists
+ 'b' binary mode
+ 't' text mode (default)
+ '+' open a disk file for updating (reading and writing)
+ 'U' universal newline mode (for backwards compatibility; unneeded
+ for new code)
+ ========= ===============================================================
+
+ The default mode is 'rt' (open for reading text). For binary random
+ access, the mode 'w+b' opens and truncates the file to 0 bytes, while
+ 'r+b' opens the file without truncation.
+
+ Python distinguishes between files opened in binary and text modes,
+ even when the underlying operating system doesn't. Files opened in
+ binary mode (appending 'b' to the mode argument) return contents as
+ bytes objects without any decoding. In text mode (the default, or when
+ 't' is appended to the mode argument), the contents of the file are
+ returned as strings, the bytes having been first decoded using a
+ platform-dependent encoding or using the specified encoding if given.
+
+ buffering is an optional integer used to set the buffering policy.
+ Pass 0 to switch buffering off (only allowed in binary mode), 1 to select
+ line buffering (only usable in text mode), and an integer > 1 to indicate
+ the size of a fixed-size chunk buffer. When no buffering argument is
+ given, the default buffering policy works as follows:
+
+ * Binary files are buffered in fixed-size chunks; the size of the buffer
+ is chosen using a heuristic trying to determine the underlying device's
+ "block size" and falling back on `io.DEFAULT_BUFFER_SIZE`.
+ On many systems, the buffer will typically be 4096 or 8192 bytes long.
+
+ * "Interactive" text files (files for which isatty() returns True)
+ use line buffering. Other text files use the policy described above
+ for binary files.
+
+ encoding is the str name of the encoding used to decode or encode the
+ file. This should only be used in text mode. The default encoding is
+ platform dependent, but any encoding supported by Python can be
+ passed. See the codecs module for the list of supported encodings.
+
+ errors is an optional string that specifies how encoding errors are to
+ be handled---this argument should not be used in binary mode. Pass
+ 'strict' to raise a ValueError exception if there is an encoding error
+ (the default of None has the same effect), or pass 'ignore' to ignore
+ errors. (Note that ignoring encoding errors can lead to data loss.)
+ See the documentation for codecs.register for a list of the permitted
+ encoding error strings.
+
+ newline is a string controlling how universal newlines works (it only
+ applies to text mode). It can be None, '', '\n', '\r', and '\r\n'. It works
+ as follows:
+
+ * On input, if newline is None, universal newlines mode is
+ enabled. Lines in the input can end in '\n', '\r', or '\r\n', and
+ these are translated into '\n' before being returned to the
+ caller. If it is '', universal newline mode is enabled, but line
+ endings are returned to the caller untranslated. If it has any of
+ the other legal values, input lines are only terminated by the given
+ string, and the line ending is returned to the caller untranslated.
+
+ * On output, if newline is None, any '\n' characters written are
+ translated to the system default line separator, os.linesep. If
+ newline is '', no translation takes place. If newline is any of the
+ other legal values, any '\n' characters written are translated to
+ the given string.
+
+ closedfd is a bool. If closefd is False, the underlying file descriptor will
+ be kept open when the file is closed. This does not work when a file name is
+ given and must be True in that case.
+
+ open() returns a file object whose type depends on the mode, and
+ through which the standard file operations such as reading and writing
+ are performed. When open() is used to open a file in a text mode ('w',
+ 'r', 'wt', 'rt', etc.), it returns a TextIOWrapper. When used to open
+ a file in a binary mode, the returned class varies: in read binary
+ mode, it returns a BufferedReader; in write binary and append binary
+ modes, it returns a BufferedWriter, and in read/write mode, it returns
+ a BufferedRandom.
+
+ It is also possible to use a string or bytearray as a file for both
+ reading and writing. For strings StringIO can be used like a file
+ opened in a text mode, and for bytes a BytesIO can be used like a file
+ opened in a binary mode.
+ """
+ if not isinstance(file, (str, bytes, int)):
+ raise TypeError("invalid file: %r" % file)
+ if not isinstance(mode, str):
+ raise TypeError("invalid mode: %r" % mode)
+ if not isinstance(buffering, int):
+ raise TypeError("invalid buffering: %r" % buffering)
+ if encoding is not None and not isinstance(encoding, str):
+ raise TypeError("invalid encoding: %r" % encoding)
+ if errors is not None and not isinstance(errors, str):
+ raise TypeError("invalid errors: %r" % errors)
+ modes = set(mode)
+ if modes - set("arwb+tU") or len(mode) > len(modes):
+ raise ValueError("invalid mode: %r" % mode)
+ reading = "r" in modes
+ writing = "w" in modes
+ appending = "a" in modes
+ updating = "+" in modes
+ text = "t" in modes
+ binary = "b" in modes
+ if "U" in modes:
+ if writing or appending:
+ raise ValueError("can't use U and writing mode at once")
+ reading = True
+ if text and binary:
+ raise ValueError("can't have text and binary mode at once")
+ if reading + writing + appending > 1:
+ raise ValueError("can't have read/write/append mode at once")
+ if not (reading or writing or appending):
+ raise ValueError("must have exactly one of read/write/append mode")
+ if binary and encoding is not None:
+ raise ValueError("binary mode doesn't take an encoding argument")
+ if binary and errors is not None:
+ raise ValueError("binary mode doesn't take an errors argument")
+ if binary and newline is not None:
+ raise ValueError("binary mode doesn't take a newline argument")
+ raw = FileIO(file,
+ (reading and "r" or "") +
+ (writing and "w" or "") +
+ (appending and "a" or "") +
+ (updating and "+" or ""),
+ closefd)
+ line_buffering = False
+ if buffering == 1 or buffering < 0 and raw.isatty():
+ buffering = -1
+ line_buffering = True
+ if buffering < 0:
+ buffering = DEFAULT_BUFFER_SIZE
+ try:
+ bs = os.fstat(raw.fileno()).st_blksize
+ except (os.error, AttributeError):
+ pass
+ else:
+ if bs > 1:
+ buffering = bs
+ if buffering < 0:
+ raise ValueError("invalid buffering size")
+ if buffering == 0:
+ if binary:
+ return raw
+ raise ValueError("can't have unbuffered text I/O")
+ if updating:
+ buffer = BufferedRandom(raw, buffering)
+ elif writing or appending:
+ buffer = BufferedWriter(raw, buffering)
+ elif reading:
+ buffer = BufferedReader(raw, buffering)
+ else:
+ raise ValueError("unknown mode: %r" % mode)
+ if binary:
+ return buffer
+ text = TextIOWrapper(buffer, encoding, errors, newline, line_buffering)
+ text.mode = mode
+ return text
+
+
+class DocDescriptor:
+ """Helper for builtins.open.__doc__
+ """
+ def __get__(self, obj, typ):
+ return (
+ "open(file, mode='r', buffering=-1, encoding=None, "
+ "errors=None, newline=None, closefd=True)\n\n" +
+ open.__doc__)
+
+class OpenWrapper:
+ """Wrapper for builtins.open
+
+ Trick so that open won't become a bound method when stored
+ as a class variable (as dbm.dumb does).
+
+ See initstdio() in Python/pythonrun.c.
+ """
+ __doc__ = DocDescriptor()
+
+ def __new__(cls, *args, **kwargs):
+ return open(*args, **kwargs)
+
+
+# In normal operation, both `UnsupportedOperation`s should be bound to the
+# same object.
+try:
+ UnsupportedOperation = io.UnsupportedOperation
+except AttributeError:
+ class UnsupportedOperation(ValueError, IOError):
+ pass
+
+
+class IOBase(metaclass=abc.ABCMeta):
+
+ """The abstract base class for all I/O classes, acting on streams of
+ bytes. There is no public constructor.
+
+ This class provides dummy implementations for many methods that
+ derived classes can override selectively; the default implementations
+ represent a file that cannot be read, written or seeked.
+
+ Even though IOBase does not declare read, readinto, or write because
+ their signatures will vary, implementations and clients should
+ consider those methods part of the interface. Also, implementations
+ may raise UnsupportedOperation when operations they do not support are
+ called.
+
+ The basic type used for binary data read from or written to a file is
+ bytes. bytearrays are accepted too, and in some cases (such as
+ readinto) needed. Text I/O classes work with str data.
+
+ Note that calling any method (even inquiries) on a closed stream is
+ undefined. Implementations may raise IOError in this case.
+
+ IOBase (and its subclasses) support the iterator protocol, meaning
+ that an IOBase object can be iterated over yielding the lines in a
+ stream.
+
+ IOBase also supports the :keyword:`with` statement. In this example,
+ fp is closed after the suite of the with statement is complete:
+
+ with open('spam.txt', 'r') as fp:
+ fp.write('Spam and eggs!')
+ """
+
+ ### Internal ###
+
+ def _unsupported(self, name):
+ """Internal: raise an IOError exception for unsupported operations."""
+ raise UnsupportedOperation("%s.%s() not supported" %
+ (self.__class__.__name__, name))
+
+ ### Positioning ###
+
+ def seek(self, pos, whence=0):
+ """Change stream position.
+
+ Change the stream position to byte offset offset. offset is
+ interpreted relative to the position indicated by whence. Values
+ for whence are ints:
+
+ * 0 -- start of stream (the default); offset should be zero or positive
+ * 1 -- current stream position; offset may be negative
+ * 2 -- end of stream; offset is usually negative
+
+ Return an int indicating the new absolute position.
+ """
+ self._unsupported("seek")
+
+ def tell(self):
+ """Return an int indicating the current stream position."""
+ return self.seek(0, 1)
+
+ def truncate(self, pos=None):
+ """Truncate file to size bytes.
+
+ Size defaults to the current IO position as reported by tell(). Return
+ the new size.
+ """
+ self._unsupported("truncate")
+
+ ### Flush and close ###
+
+ def flush(self):
+ """Flush write buffers, if applicable.
+
+ This is not implemented for read-only and non-blocking streams.
+ """
+ self._checkClosed()
+ # XXX Should this return the number of bytes written???
+
+ __closed = False
+
+ def close(self):
+ """Flush and close the IO object.
+
+ This method has no effect if the file is already closed.
+ """
+ if not self.__closed:
+ self.flush()
+ self.__closed = True
+
+ def __del__(self):
+ """Destructor. Calls close()."""
+ # The try/except block is in case this is called at program
+ # exit time, when it's possible that globals have already been
+ # deleted, and then the close() call might fail. Since
+ # there's nothing we can do about such failures and they annoy
+ # the end users, we suppress the traceback.
+ try:
+ self.close()
+ except:
+ pass
+
+ ### Inquiries ###
+
+ def seekable(self):
+ """Return a bool indicating whether object supports random access.
+
+ If False, seek(), tell() and truncate() will raise UnsupportedOperation.
+ This method may need to do a test seek().
+ """
+ return False
+
+ def _checkSeekable(self, msg=None):
+ """Internal: raise UnsupportedOperation if file is not seekable
+ """
+ if not self.seekable():
+ raise UnsupportedOperation("File or stream is not seekable."
+ if msg is None else msg)
+
+ def readable(self):
+ """Return a bool indicating whether object was opened for reading.
+
+ If False, read() will raise UnsupportedOperation.
+ """
+ return False
+
+ def _checkReadable(self, msg=None):
+ """Internal: raise UnsupportedOperation if file is not readable
+ """
+ if not self.readable():
+ raise UnsupportedOperation("File or stream is not readable."
+ if msg is None else msg)
+
+ def writable(self):
+ """Return a bool indicating whether object was opened for writing.
+
+ If False, write() and truncate() will raise UnsupportedOperation.
+ """
+ return False
+
+ def _checkWritable(self, msg=None):
+ """Internal: raise UnsupportedOperation if file is not writable
+ """
+ if not self.writable():
+ raise UnsupportedOperation("File or stream is not writable."
+ if msg is None else msg)
+
+ @property
+ def closed(self):
+ """closed: bool. True iff the file has been closed.
+
+ For backwards compatibility, this is a property, not a predicate.
+ """
+ return self.__closed
+
+ def _checkClosed(self, msg=None):
+ """Internal: raise an ValueError if file is closed
+ """
+ if self.closed:
+ raise ValueError("I/O operation on closed file."
+ if msg is None else msg)
+
+ ### Context manager ###
+
+ def __enter__(self): # That's a forward reference
+ """Context management protocol. Returns self (an instance of IOBase)."""
+ self._checkClosed()
+ return self
+
+ def __exit__(self, *args):
+ """Context management protocol. Calls close()"""
+ self.close()
+
+ ### Lower-level APIs ###
+
+ # XXX Should these be present even if unimplemented?
+
+ def fileno(self):
+ """Returns underlying file descriptor (an int) if one exists.
+
+ An IOError is raised if the IO object does not use a file descriptor.
+ """
+ self._unsupported("fileno")
+
+ def isatty(self):
+ """Return a bool indicating whether this is an 'interactive' stream.
+
+ Return False if it can't be determined.
+ """
+ self._checkClosed()
+ return False
+
+ ### Readline[s] and writelines ###
+
+ def readline(self, limit=-1):
+ r"""Read and return a line of bytes from the stream.
+
+ If limit is specified, at most limit bytes will be read.
+ Limit should be an int.
+
+ The line terminator is always b'\n' for binary files; for text
+ files, the newlines argument to open can be used to select the line
+ terminator(s) recognized.
+ """
+ # For backwards compatibility, a (slowish) readline().
+ if hasattr(self, "peek"):
+ def nreadahead():
+ readahead = self.peek(1)
+ if not readahead:
+ return 1
+ n = (readahead.find(b"\n") + 1) or len(readahead)
+ if limit >= 0:
+ n = min(n, limit)
+ return n
+ else:
+ def nreadahead():
+ return 1
+ if limit is None:
+ limit = -1
+ elif not isinstance(limit, int):
+ raise TypeError("limit must be an integer")
+ res = bytearray()
+ while limit < 0 or len(res) < limit:
+ b = self.read(nreadahead())
+ if not b:
+ break
+ res += b
+ if res.endswith(b"\n"):
+ break
+ return bytes(res)
+
+ def __iter__(self):
+ self._checkClosed()
+ return self
+
+ def __next__(self):
+ line = self.readline()
+ if not line:
+ raise StopIteration
+ return line
+
+ def readlines(self, hint=None):
+ """Return a list of lines from the stream.
+
+ hint can be specified to control the number of lines read: no more
+ lines will be read if the total size (in bytes/characters) of all
+ lines so far exceeds hint.
+ """
+ if hint is None or hint <= 0:
+ return list(self)
+ n = 0
+ lines = []
+ for line in self:
+ lines.append(line)
+ n += len(line)
+ if n >= hint:
+ break
+ return lines
+
+ def writelines(self, lines):
+ self._checkClosed()
+ for line in lines:
+ self.write(line)
+
+io.IOBase.register(IOBase)
+
+
+class RawIOBase(IOBase):
+
+ """Base class for raw binary I/O."""
+
+ # The read() method is implemented by calling readinto(); derived
+ # classes that want to support read() only need to implement
+ # readinto() as a primitive operation. In general, readinto() can be
+ # more efficient than read().
+
+ # (It would be tempting to also provide an implementation of
+ # readinto() in terms of read(), in case the latter is a more suitable
+ # primitive operation, but that would lead to nasty recursion in case
+ # a subclass doesn't implement either.)
+
+ def read(self, n=-1):
+ """Read and return up to n bytes, where n is an int.
+
+ Returns an empty bytes object on EOF, or None if the object is
+ set not to block and has no data to read.
+ """
+ if n is None:
+ n = -1
+ if n < 0:
+ return self.readall()
+ b = bytearray(n.__index__())
+ n = self.readinto(b)
+ if n is None:
+ return None
+ del b[n:]
+ return bytes(b)
+
+ def readall(self):
+ """Read until EOF, using multiple read() call."""
+ res = bytearray()
+ while True:
+ data = self.read(DEFAULT_BUFFER_SIZE)
+ if not data:
+ break
+ res += data
+ if res:
+ return bytes(res)
+ else:
+ # b'' or None
+ return data
+
+ def readinto(self, b):
+ """Read up to len(b) bytes into bytearray b.
+
+ Returns an int representing the number of bytes read (0 for EOF), or
+ None if the object is set not to block and has no data to read.
+ """
+ self._unsupported("readinto")
+
+ def write(self, b):
+ """Write the given buffer to the IO stream.
+
+ Returns the number of bytes written, which may be less than len(b).
+ """
+ self._unsupported("write")
+
+io.RawIOBase.register(RawIOBase)
+from _io import FileIO
+RawIOBase.register(FileIO)
+
+
+class BufferedIOBase(IOBase):
+
+ """Base class for buffered IO objects.
+
+ The main difference with RawIOBase is that the read() method
+ supports omitting the size argument, and does not have a default
+ implementation that defers to readinto().
+
+ In addition, read(), readinto() and write() may raise
+ BlockingIOError if the underlying raw stream is in non-blocking
+ mode and not ready; unlike their raw counterparts, they will never
+ return None.
+
+ A typical implementation should not inherit from a RawIOBase
+ implementation, but wrap one.
+ """
+
+ def read(self, n=None):
+ """Read and return up to n bytes, where n is an int.
+
+ If the argument is omitted, None, or negative, reads and
+ returns all data until EOF.
+
+ If the argument is positive, and the underlying raw stream is
+ not 'interactive', multiple raw reads may be issued to satisfy
+ the byte count (unless EOF is reached first). But for
+ interactive raw streams (XXX and for pipes?), at most one raw
+ read will be issued, and a short result does not imply that
+ EOF is imminent.
+
+ Returns an empty bytes array on EOF.
+
+ Raises BlockingIOError if the underlying raw stream has no
+ data at the moment.
+ """
+ self._unsupported("read")
+
+ def read1(self, n=None):
+ """Read up to n bytes with at most one read() system call,
+ where n is an int.
+ """
+ self._unsupported("read1")
+
+ def readinto(self, b):
+ """Read up to len(b) bytes into bytearray b.
+
+ Like read(), this may issue multiple reads to the underlying raw
+ stream, unless the latter is 'interactive'.
+
+ Returns an int representing the number of bytes read (0 for EOF).
+
+ Raises BlockingIOError if the underlying raw stream has no
+ data at the moment.
+ """
+ # XXX This ought to work with anything that supports the buffer API
+ data = self.read(len(b))
+ n = len(data)
+ try:
+ b[:n] = data
+ except TypeError as err:
+ import array
+ if not isinstance(b, array.array):
+ raise err
+ b[:n] = array.array('b', data)
+ return n
+
+ def write(self, b):
+ """Write the given bytes buffer to the IO stream.
+
+ Return the number of bytes written, which is never less than
+ len(b).
+
+ Raises BlockingIOError if the buffer is full and the
+ underlying raw stream cannot accept more data at the moment.
+ """
+ self._unsupported("write")
+
+ def detach(self):
+ """
+ Separate the underlying raw stream from the buffer and return it.
+
+ After the raw stream has been detached, the buffer is in an unusable
+ state.
+ """
+ self._unsupported("detach")
+
+io.BufferedIOBase.register(BufferedIOBase)
+
+
+class _BufferedIOMixin(BufferedIOBase):
+
+ """A mixin implementation of BufferedIOBase with an underlying raw stream.
+
+ This passes most requests on to the underlying raw stream. It
+ does *not* provide implementations of read(), readinto() or
+ write().
+ """
+
+ def __init__(self, raw):
+ self._raw = raw
+
+ ### Positioning ###
+
+ def seek(self, pos, whence=0):
+ new_position = self.raw.seek(pos, whence)
+ if new_position < 0:
+ raise IOError("seek() returned an invalid position")
+ return new_position
+
+ def tell(self):
+ pos = self.raw.tell()
+ if pos < 0:
+ raise IOError("tell() returned an invalid position")
+ return pos
+
+ def truncate(self, pos=None):
+ # Flush the stream. We're mixing buffered I/O with lower-level I/O,
+ # and a flush may be necessary to synch both views of the current
+ # file state.
+ self.flush()
+
+ if pos is None:
+ pos = self.tell()
+ # XXX: Should seek() be used, instead of passing the position
+ # XXX directly to truncate?
+ return self.raw.truncate(pos)
+
+ ### Flush and close ###
+
+ def flush(self):
+ if self.closed:
+ raise ValueError("flush of closed file")
+ self.raw.flush()
+
+ def close(self):
+ if self.raw is not None and not self.closed:
+ try:
+ # may raise BlockingIOError or BrokenPipeError etc
+ self.flush()
+ finally:
+ self.raw.close()
+
+ def detach(self):
+ if self.raw is None:
+ raise ValueError("raw stream already detached")
+ self.flush()
+ raw = self._raw
+ self._raw = None
+ return raw
+
+ ### Inquiries ###
+
+ def seekable(self):
+ return self.raw.seekable()
+
+ def readable(self):
+ return self.raw.readable()
+
+ def writable(self):
+ return self.raw.writable()
+
+ @property
+ def raw(self):
+ return self._raw
+
+ @property
+ def closed(self):
+ return self.raw.closed
+
+ @property
+ def name(self):
+ return self.raw.name
+
+ @property
+ def mode(self):
+ return self.raw.mode
+
+ def __getstate__(self):
+ raise TypeError("can not serialize a '{0}' object"
+ .format(self.__class__.__name__))
+
+ def __repr__(self):
+ clsname = self.__class__.__name__
+ try:
+ name = self.name
+ except AttributeError:
+ return "<_pyio.{0}>".format(clsname)
+ else:
+ return "<_pyio.{0} name={1!r}>".format(clsname, name)
+
+ ### Lower-level APIs ###
+
+ def fileno(self):
+ return self.raw.fileno()
+
+ def isatty(self):
+ return self.raw.isatty()
+
+
+class BytesIO(BufferedIOBase):
+
+ """Buffered I/O implementation using an in-memory bytes buffer."""
+
+ def __init__(self, initial_bytes=None):
+ buf = bytearray()
+ if initial_bytes is not None:
+ buf += initial_bytes
+ self._buffer = buf
+ self._pos = 0
+
+ def __getstate__(self):
+ if self.closed:
+ raise ValueError("__getstate__ on closed file")
+ return self.__dict__.copy()
+
+ def getvalue(self):
+ """Return the bytes value (contents) of the buffer
+ """
+ if self.closed:
+ raise ValueError("getvalue on closed file")
+ return bytes(self._buffer)
+
+ def getbuffer(self):
+ """Return a readable and writable view of the buffer.
+ """
+ return memoryview(self._buffer)
+
+ def read(self, n=None):
+ if self.closed:
+ raise ValueError("read from closed file")
+ if n is None:
+ n = -1
+ if n < 0:
+ n = len(self._buffer)
+ if len(self._buffer) <= self._pos:
+ return b""
+ newpos = min(len(self._buffer), self._pos + n)
+ b = self._buffer[self._pos : newpos]
+ self._pos = newpos
+ return bytes(b)
+
+ def read1(self, n):
+ """This is the same as read.
+ """
+ return self.read(n)
+
+ def write(self, b):
+ if self.closed:
+ raise ValueError("write to closed file")
+ if isinstance(b, str):
+ raise TypeError("can't write str to binary stream")
+ n = len(b)
+ if n == 0:
+ return 0
+ pos = self._pos
+ if pos > len(self._buffer):
+ # Inserts null bytes between the current end of the file
+ # and the new write position.
+ padding = b'\x00' * (pos - len(self._buffer))
+ self._buffer += padding
+ self._buffer[pos:pos + n] = b
+ self._pos += n
+ return n
+
+ def seek(self, pos, whence=0):
+ if self.closed:
+ raise ValueError("seek on closed file")
+ try:
+ pos.__index__
+ except AttributeError as err:
+ raise TypeError("an integer is required") from err
+ if whence == 0:
+ if pos < 0:
+ raise ValueError("negative seek position %r" % (pos,))
+ self._pos = pos
+ elif whence == 1:
+ self._pos = max(0, self._pos + pos)
+ elif whence == 2:
+ self._pos = max(0, len(self._buffer) + pos)
+ else:
+ raise ValueError("invalid whence value")
+ return self._pos
+
+ def tell(self):
+ if self.closed:
+ raise ValueError("tell on closed file")
+ return self._pos
+
+ def truncate(self, pos=None):
+ if self.closed:
+ raise ValueError("truncate on closed file")
+ if pos is None:
+ pos = self._pos
+ else:
+ try:
+ pos.__index__
+ except AttributeError as err:
+ raise TypeError("an integer is required") from err
+ if pos < 0:
+ raise ValueError("negative truncate position %r" % (pos,))
+ del self._buffer[pos:]
+ return pos
+
+ def readable(self):
+ return True
+
+ def writable(self):
+ return True
+
+ def seekable(self):
+ return True
+
+
+class BufferedReader(_BufferedIOMixin):
+
+ """BufferedReader(raw[, buffer_size])
+
+ A buffer for a readable, sequential BaseRawIO object.
+
+ The constructor creates a BufferedReader for the given readable raw
+ stream and buffer_size. If buffer_size is omitted, DEFAULT_BUFFER_SIZE
+ is used.
+ """
+
+ def __init__(self, raw, buffer_size=DEFAULT_BUFFER_SIZE):
+ """Create a new buffered reader using the given readable raw IO object.
+ """
+ if not raw.readable():
+ raise IOError('"raw" argument must be readable.')
+
+ _BufferedIOMixin.__init__(self, raw)
+ if buffer_size <= 0:
+ raise ValueError("invalid buffer size")
+ self.buffer_size = buffer_size
+ self._reset_read_buf()
+ self._read_lock = Lock()
+
+ def _reset_read_buf(self):
+ self._read_buf = b""
+ self._read_pos = 0
+
+ def read(self, n=None):
+ """Read n bytes.
+
+ Returns exactly n bytes of data unless the underlying raw IO
+ stream reaches EOF or if the call would block in non-blocking
+ mode. If n is negative, read until EOF or until read() would
+ block.
+ """
+ if n is not None and n < -1:
+ raise ValueError("invalid number of bytes to read")
+ with self._read_lock:
+ return self._read_unlocked(n)
+
+ def _read_unlocked(self, n=None):
+ nodata_val = b""
+ empty_values = (b"", None)
+ buf = self._read_buf
+ pos = self._read_pos
+
+ # Special case for when the number of bytes to read is unspecified.
+ if n is None or n == -1:
+ self._reset_read_buf()
+ chunks = [buf[pos:]] # Strip the consumed bytes.
+ current_size = 0
+ while True:
+ # Read until EOF or until read() would block.
+ try:
+ chunk = self.raw.read()
+ except IOError as e:
+ if e.errno != EINTR:
+ raise
+ continue
+ if chunk in empty_values:
+ nodata_val = chunk
+ break
+ current_size += len(chunk)
+ chunks.append(chunk)
+ return b"".join(chunks) or nodata_val
+
+ # The number of bytes to read is specified, return at most n bytes.
+ avail = len(buf) - pos # Length of the available buffered data.
+ if n <= avail:
+ # Fast path: the data to read is fully buffered.
+ self._read_pos += n
+ return buf[pos:pos+n]
+ # Slow path: read from the stream until enough bytes are read,
+ # or until an EOF occurs or until read() would block.
+ chunks = [buf[pos:]]
+ wanted = max(self.buffer_size, n)
+ while avail < n:
+ try:
+ chunk = self.raw.read(wanted)
+ except IOError as e:
+ if e.errno != EINTR:
+ raise
+ continue
+ if chunk in empty_values:
+ nodata_val = chunk
+ break
+ avail += len(chunk)
+ chunks.append(chunk)
+ # n is more then avail only when an EOF occurred or when
+ # read() would have blocked.
+ n = min(n, avail)
+ out = b"".join(chunks)
+ self._read_buf = out[n:] # Save the extra data in the buffer.
+ self._read_pos = 0
+ return out[:n] if out else nodata_val
+
+ def peek(self, n=0):
+ """Returns buffered bytes without advancing the position.
+
+ The argument indicates a desired minimal number of bytes; we
+ do at most one raw read to satisfy it. We never return more
+ than self.buffer_size.
+ """
+ with self._read_lock:
+ return self._peek_unlocked(n)
+
+ def _peek_unlocked(self, n=0):
+ want = min(n, self.buffer_size)
+ have = len(self._read_buf) - self._read_pos
+ if have < want or have <= 0:
+ to_read = self.buffer_size - have
+ while True:
+ try:
+ current = self.raw.read(to_read)
+ except IOError as e:
+ if e.errno != EINTR:
+ raise
+ continue
+ break
+ if current:
+ self._read_buf = self._read_buf[self._read_pos:] + current
+ self._read_pos = 0
+ return self._read_buf[self._read_pos:]
+
+ def read1(self, n):
+ """Reads up to n bytes, with at most one read() system call."""
+ # Returns up to n bytes. If at least one byte is buffered, we
+ # only return buffered bytes. Otherwise, we do one raw read.
+ if n < 0:
+ raise ValueError("number of bytes to read must be positive")
+ if n == 0:
+ return b""
+ with self._read_lock:
+ self._peek_unlocked(1)
+ return self._read_unlocked(
+ min(n, len(self._read_buf) - self._read_pos))
+
+ def tell(self):
+ return _BufferedIOMixin.tell(self) - len(self._read_buf) + self._read_pos
+
+ def seek(self, pos, whence=0):
+ if not (0 <= whence <= 2):
+ raise ValueError("invalid whence value")
+ with self._read_lock:
+ if whence == 1:
+ pos -= len(self._read_buf) - self._read_pos
+ pos = _BufferedIOMixin.seek(self, pos, whence)
+ self._reset_read_buf()
+ return pos
+
+class BufferedWriter(_BufferedIOMixin):
+
+ """A buffer for a writeable sequential RawIO object.
+
+ The constructor creates a BufferedWriter for the given writeable raw
+ stream. If the buffer_size is not given, it defaults to
+ DEFAULT_BUFFER_SIZE.
+ """
+
+ _warning_stack_offset = 2
+
+ def __init__(self, raw,
+ buffer_size=DEFAULT_BUFFER_SIZE, max_buffer_size=None):
+ if not raw.writable():
+ raise IOError('"raw" argument must be writable.')
+
+ _BufferedIOMixin.__init__(self, raw)
+ if buffer_size <= 0:
+ raise ValueError("invalid buffer size")
+ if max_buffer_size is not None:
+ warnings.warn("max_buffer_size is deprecated", DeprecationWarning,
+ self._warning_stack_offset)
+ self.buffer_size = buffer_size
+ self._write_buf = bytearray()
+ self._write_lock = Lock()
+
+ def write(self, b):
+ if self.closed:
+ raise ValueError("write to closed file")
+ if isinstance(b, str):
+ raise TypeError("can't write str to binary stream")
+ with self._write_lock:
+ # XXX we can implement some more tricks to try and avoid
+ # partial writes
+ if len(self._write_buf) > self.buffer_size:
+ # We're full, so let's pre-flush the buffer. (This may
+ # raise BlockingIOError with characters_written == 0.)
+ self._flush_unlocked()
+ before = len(self._write_buf)
+ self._write_buf.extend(b)
+ written = len(self._write_buf) - before
+ if len(self._write_buf) > self.buffer_size:
+ try:
+ self._flush_unlocked()
+ except BlockingIOError as e:
+ if len(self._write_buf) > self.buffer_size:
+ # We've hit the buffer_size. We have to accept a partial
+ # write and cut back our buffer.
+ overage = len(self._write_buf) - self.buffer_size
+ written -= overage
+ self._write_buf = self._write_buf[:self.buffer_size]
+ raise BlockingIOError(e.errno, e.strerror, written)
+ return written
+
+ def truncate(self, pos=None):
+ with self._write_lock:
+ self._flush_unlocked()
+ if pos is None:
+ pos = self.raw.tell()
+ return self.raw.truncate(pos)
+
+ def flush(self):
+ with self._write_lock:
+ self._flush_unlocked()
+
+ def _flush_unlocked(self):
+ if self.closed:
+ raise ValueError("flush of closed file")
+ while self._write_buf:
+ try:
+ n = self.raw.write(self._write_buf)
+ except BlockingIOError:
+ raise RuntimeError("self.raw should implement RawIOBase: it "
+ "should not raise BlockingIOError")
+ except IOError as e:
+ if e.errno != EINTR:
+ raise
+ continue
+ if n is None:
+ raise BlockingIOError(
+ errno.EAGAIN,
+ "write could not complete without blocking", 0)
+ if n > len(self._write_buf) or n < 0:
+ raise IOError("write() returned incorrect number of bytes")
+ del self._write_buf[:n]
+
+ def tell(self):
+ return _BufferedIOMixin.tell(self) + len(self._write_buf)
+
+ def seek(self, pos, whence=0):
+ if not (0 <= whence <= 2):
+ raise ValueError("invalid whence")
+ with self._write_lock:
+ self._flush_unlocked()
+ return _BufferedIOMixin.seek(self, pos, whence)
+
+
+class BufferedRWPair(BufferedIOBase):
+
+ """A buffered reader and writer object together.
+
+ A buffered reader object and buffered writer object put together to
+ form a sequential IO object that can read and write. This is typically
+ used with a socket or two-way pipe.
+
+ reader and writer are RawIOBase objects that are readable and
+ writeable respectively. If the buffer_size is omitted it defaults to
+ DEFAULT_BUFFER_SIZE.
+ """
+
+ # XXX The usefulness of this (compared to having two separate IO
+ # objects) is questionable.
+
+ def __init__(self, reader, writer,
+ buffer_size=DEFAULT_BUFFER_SIZE, max_buffer_size=None):
+ """Constructor.
+
+ The arguments are two RawIO instances.
+ """
+ if max_buffer_size is not None:
+ warnings.warn("max_buffer_size is deprecated", DeprecationWarning, 2)
+
+ if not reader.readable():
+ raise IOError('"reader" argument must be readable.')
+
+ if not writer.writable():
+ raise IOError('"writer" argument must be writable.')
+
+ self.reader = BufferedReader(reader, buffer_size)
+ self.writer = BufferedWriter(writer, buffer_size)
+
+ def read(self, n=None):
+ if n is None:
+ n = -1
+ return self.reader.read(n)
+
+ def readinto(self, b):
+ return self.reader.readinto(b)
+
+ def write(self, b):
+ return self.writer.write(b)
+
+ def peek(self, n=0):
+ return self.reader.peek(n)
+
+ def read1(self, n):
+ return self.reader.read1(n)
+
+ def readable(self):
+ return self.reader.readable()
+
+ def writable(self):
+ return self.writer.writable()
+
+ def flush(self):
+ return self.writer.flush()
+
+ def close(self):
+ self.writer.close()
+ self.reader.close()
+
+ def isatty(self):
+ return self.reader.isatty() or self.writer.isatty()
+
+ @property
+ def closed(self):
+ return self.writer.closed
+
+
+class BufferedRandom(BufferedWriter, BufferedReader):
+
+ """A buffered interface to random access streams.
+
+ The constructor creates a reader and writer for a seekable stream,
+ raw, given in the first argument. If the buffer_size is omitted it
+ defaults to DEFAULT_BUFFER_SIZE.
+ """
+
+ _warning_stack_offset = 3
+
+ def __init__(self, raw,
+ buffer_size=DEFAULT_BUFFER_SIZE, max_buffer_size=None):
+ raw._checkSeekable()
+ BufferedReader.__init__(self, raw, buffer_size)
+ BufferedWriter.__init__(self, raw, buffer_size, max_buffer_size)
+
+ def seek(self, pos, whence=0):
+ if not (0 <= whence <= 2):
+ raise ValueError("invalid whence")
+ self.flush()
+ if self._read_buf:
+ # Undo read ahead.
+ with self._read_lock:
+ self.raw.seek(self._read_pos - len(self._read_buf), 1)
+ # First do the raw seek, then empty the read buffer, so that
+ # if the raw seek fails, we don't lose buffered data forever.
+ pos = self.raw.seek(pos, whence)
+ with self._read_lock:
+ self._reset_read_buf()
+ if pos < 0:
+ raise IOError("seek() returned invalid position")
+ return pos
+
+ def tell(self):
+ if self._write_buf:
+ return BufferedWriter.tell(self)
+ else:
+ return BufferedReader.tell(self)
+
+ def truncate(self, pos=None):
+ if pos is None:
+ pos = self.tell()
+ # Use seek to flush the read buffer.
+ return BufferedWriter.truncate(self, pos)
+
+ def read(self, n=None):
+ if n is None:
+ n = -1
+ self.flush()
+ return BufferedReader.read(self, n)
+
+ def readinto(self, b):
+ self.flush()
+ return BufferedReader.readinto(self, b)
+
+ def peek(self, n=0):
+ self.flush()
+ return BufferedReader.peek(self, n)
+
+ def read1(self, n):
+ self.flush()
+ return BufferedReader.read1(self, n)
+
+ def write(self, b):
+ if self._read_buf:
+ # Undo readahead
+ with self._read_lock:
+ self.raw.seek(self._read_pos - len(self._read_buf), 1)
+ self._reset_read_buf()
+ return BufferedWriter.write(self, b)
+
+
+class TextIOBase(IOBase):
+
+ """Base class for text I/O.
+
+ This class provides a character and line based interface to stream
+ I/O. There is no readinto method because Python's character strings
+ are immutable. There is no public constructor.
+ """
+
+ def read(self, n=-1):
+ """Read at most n characters from stream, where n is an int.
+
+ Read from underlying buffer until we have n characters or we hit EOF.
+ If n is negative or omitted, read until EOF.
+
+ Returns a string.
+ """
+ self._unsupported("read")
+
+ def write(self, s):
+ """Write string s to stream and returning an int."""
+ self._unsupported("write")
+
+ def truncate(self, pos=None):
+ """Truncate size to pos, where pos is an int."""
+ self._unsupported("truncate")
+
+ def readline(self):
+ """Read until newline or EOF.
+
+ Returns an empty string if EOF is hit immediately.
+ """
+ self._unsupported("readline")
+
+ def detach(self):
+ """
+ Separate the underlying buffer from the TextIOBase and return it.
+
+ After the underlying buffer has been detached, the TextIO is in an
+ unusable state.
+ """
+ self._unsupported("detach")
+
+ @property
+ def encoding(self):
+ """Subclasses should override."""
+ return None
+
+ @property
+ def newlines(self):
+ """Line endings translated so far.
+
+ Only line endings translated during reading are considered.
+
+ Subclasses should override.
+ """
+ return None
+
+ @property
+ def errors(self):
+ """Error setting of the decoder or encoder.
+
+ Subclasses should override."""
+ return None
+
+io.TextIOBase.register(TextIOBase)
+
+
+class IncrementalNewlineDecoder(codecs.IncrementalDecoder):
+ r"""Codec used when reading a file in universal newlines mode. It wraps
+ another incremental decoder, translating \r\n and \r into \n. It also
+ records the types of newlines encountered. When used with
+ translate=False, it ensures that the newline sequence is returned in
+ one piece.
+ """
+ def __init__(self, decoder, translate, errors='strict'):
+ codecs.IncrementalDecoder.__init__(self, errors=errors)
+ self.translate = translate
+ self.decoder = decoder
+ self.seennl = 0
+ self.pendingcr = False
+
+ def decode(self, input, final=False):
+ # decode input (with the eventual \r from a previous pass)
+ if self.decoder is None:
+ output = input
+ else:
+ output = self.decoder.decode(input, final=final)
+ if self.pendingcr and (output or final):
+ output = "\r" + output
+ self.pendingcr = False
+
+ # retain last \r even when not translating data:
+ # then readline() is sure to get \r\n in one pass
+ if output.endswith("\r") and not final:
+ output = output[:-1]
+ self.pendingcr = True
+
+ # Record which newlines are read
+ crlf = output.count('\r\n')
+ cr = output.count('\r') - crlf
+ lf = output.count('\n') - crlf
+ self.seennl |= (lf and self._LF) | (cr and self._CR) \
+ | (crlf and self._CRLF)
+
+ if self.translate:
+ if crlf:
+ output = output.replace("\r\n", "\n")
+ if cr:
+ output = output.replace("\r", "\n")
+
+ return output
+
+ def getstate(self):
+ if self.decoder is None:
+ buf = b""
+ flag = 0
+ else:
+ buf, flag = self.decoder.getstate()
+ flag <<= 1
+ if self.pendingcr:
+ flag |= 1
+ return buf, flag
+
+ def setstate(self, state):
+ buf, flag = state
+ self.pendingcr = bool(flag & 1)
+ if self.decoder is not None:
+ self.decoder.setstate((buf, flag >> 1))
+
+ def reset(self):
+ self.seennl = 0
+ self.pendingcr = False
+ if self.decoder is not None:
+ self.decoder.reset()
+
+ _LF = 1
+ _CR = 2
+ _CRLF = 4
+
+ @property
+ def newlines(self):
+ return (None,
+ "\n",
+ "\r",
+ ("\r", "\n"),
+ "\r\n",
+ ("\n", "\r\n"),
+ ("\r", "\r\n"),
+ ("\r", "\n", "\r\n")
+ )[self.seennl]
+
+
+class TextIOWrapper(TextIOBase):
+
+ r"""Character and line based layer over a BufferedIOBase object, buffer.
+
+ encoding gives the name of the encoding that the stream will be
+ decoded or encoded with. It defaults to locale.getpreferredencoding.
+
+ errors determines the strictness of encoding and decoding (see the
+ codecs.register) and defaults to "strict".
+
+ newline can be None, '', '\n', '\r', or '\r\n'. It controls the
+ handling of line endings. If it is None, universal newlines is
+ enabled. With this enabled, on input, the lines endings '\n', '\r',
+ or '\r\n' are translated to '\n' before being returned to the
+ caller. Conversely, on output, '\n' is translated to the system
+ default line separator, os.linesep. If newline is any other of its
+ legal values, that newline becomes the newline when the file is read
+ and it is returned untranslated. On output, '\n' is converted to the
+ newline.
+
+ If line_buffering is True, a call to flush is implied when a call to
+ write contains a newline character.
+ """
+
+ _CHUNK_SIZE = 2048
+
+ def __init__(self, buffer, encoding=None, errors=None, newline=None,
+ line_buffering=False, write_through=False):
+ if newline is not None and not isinstance(newline, str):
+ raise TypeError("illegal newline type: %r" % (type(newline),))
+ if newline not in (None, "", "\n", "\r", "\r\n"):
+ raise ValueError("illegal newline value: %r" % (newline,))
+ if encoding is None:
+ try:
+ encoding = os.device_encoding(buffer.fileno())
+ except (AttributeError, UnsupportedOperation):
+ pass
+ if encoding is None:
+ try:
+ import locale
+ except ImportError:
+ # Importing locale may fail if Python is being built
+ encoding = "ascii"
+ else:
+ encoding = locale.getpreferredencoding()
+
+ if not isinstance(encoding, str):
+ raise ValueError("invalid encoding: %r" % encoding)
+
+ if errors is None:
+ errors = "strict"
+ else:
+ if not isinstance(errors, str):
+ raise ValueError("invalid errors: %r" % errors)
+
+ self._buffer = buffer
+ self._line_buffering = line_buffering
+ self._encoding = encoding
+ self._errors = errors
+ self._readuniversal = not newline
+ self._readtranslate = newline is None
+ self._readnl = newline
+ self._writetranslate = newline != ''
+ self._writenl = newline or os.linesep
+ self._encoder = None
+ self._decoder = None
+ self._decoded_chars = '' # buffer for text returned from decoder
+ self._decoded_chars_used = 0 # offset into _decoded_chars for read()
+ self._snapshot = None # info for reconstructing decoder state
+ self._seekable = self._telling = self.buffer.seekable()
+ self._has_read1 = hasattr(self.buffer, 'read1')
+
+ if self._seekable and self.writable():
+ position = self.buffer.tell()
+ if position != 0:
+ try:
+ self._get_encoder().setstate(0)
+ except LookupError:
+ # Sometimes the encoder doesn't exist
+ pass
+
+ # self._snapshot is either None, or a tuple (dec_flags, next_input)
+ # where dec_flags is the second (integer) item of the decoder state
+ # and next_input is the chunk of input bytes that comes next after the
+ # snapshot point. We use this to reconstruct decoder states in tell().
+
+ # Naming convention:
+ # - "bytes_..." for integer variables that count input bytes
+ # - "chars_..." for integer variables that count decoded characters
+
+ def __repr__(self):
+ result = "<_pyio.TextIOWrapper"
+ try:
+ name = self.name
+ except AttributeError:
+ pass
+ else:
+ result += " name={0!r}".format(name)
+ try:
+ mode = self.mode
+ except AttributeError:
+ pass
+ else:
+ result += " mode={0!r}".format(mode)
+ return result + " encoding={0!r}>".format(self.encoding)
+
+ @property
+ def encoding(self):
+ return self._encoding
+
+ @property
+ def errors(self):
+ return self._errors
+
+ @property
+ def line_buffering(self):
+ return self._line_buffering
+
+ @property
+ def buffer(self):
+ return self._buffer
+
+ def seekable(self):
+ return self._seekable
+
+ def readable(self):
+ return self.buffer.readable()
+
+ def writable(self):
+ return self.buffer.writable()
+
+ def flush(self):
+ self.buffer.flush()
+ self._telling = self._seekable
+
+ def close(self):
+ if self.buffer is not None and not self.closed:
+ self.flush()
+ self.buffer.close()
+
+ @property
+ def closed(self):
+ return self.buffer.closed
+
+ @property
+ def name(self):
+ return self.buffer.name
+
+ def fileno(self):
+ return self.buffer.fileno()
+
+ def isatty(self):
+ return self.buffer.isatty()
+
+ def write(self, s):
+ 'Write data, where s is a str'
+ if self.closed:
+ raise ValueError("write to closed file")
+ if not isinstance(s, str):
+ raise TypeError("can't write %s to text stream" %
+ s.__class__.__name__)
+ length = len(s)
+ haslf = (self._writetranslate or self._line_buffering) and "\n" in s
+ if haslf and self._writetranslate and self._writenl != "\n":
+ s = s.replace("\n", self._writenl)
+ encoder = self._encoder or self._get_encoder()
+ # XXX What if we were just reading?
+ b = encoder.encode(s)
+ self.buffer.write(b)
+ if self._line_buffering and (haslf or "\r" in s):
+ self.flush()
+ self._snapshot = None
+ if self._decoder:
+ self._decoder.reset()
+ return length
+
+ def _get_encoder(self):
+ make_encoder = codecs.getincrementalencoder(self._encoding)
+ self._encoder = make_encoder(self._errors)
+ return self._encoder
+
+ def _get_decoder(self):
+ make_decoder = codecs.getincrementaldecoder(self._encoding)
+ decoder = make_decoder(self._errors)
+ if self._readuniversal:
+ decoder = IncrementalNewlineDecoder(decoder, self._readtranslate)
+ self._decoder = decoder
+ return decoder
+
+ # The following three methods implement an ADT for _decoded_chars.
+ # Text returned from the decoder is buffered here until the client
+ # requests it by calling our read() or readline() method.
+ def _set_decoded_chars(self, chars):
+ """Set the _decoded_chars buffer."""
+ self._decoded_chars = chars
+ self._decoded_chars_used = 0
+
+ def _get_decoded_chars(self, n=None):
+ """Advance into the _decoded_chars buffer."""
+ offset = self._decoded_chars_used
+ if n is None:
+ chars = self._decoded_chars[offset:]
+ else:
+ chars = self._decoded_chars[offset:offset + n]
+ self._decoded_chars_used += len(chars)
+ return chars
+
+ def _rewind_decoded_chars(self, n):
+ """Rewind the _decoded_chars buffer."""
+ if self._decoded_chars_used < n:
+ raise AssertionError("rewind decoded_chars out of bounds")
+ self._decoded_chars_used -= n
+
+ def _read_chunk(self):
+ """
+ Read and decode the next chunk of data from the BufferedReader.
+ """
+
+ # The return value is True unless EOF was reached. The decoded
+ # string is placed in self._decoded_chars (replacing its previous
+ # value). The entire input chunk is sent to the decoder, though
+ # some of it may remain buffered in the decoder, yet to be
+ # converted.
+
+ if self._decoder is None:
+ raise ValueError("no decoder")
+
+ if self._telling:
+ # To prepare for tell(), we need to snapshot a point in the
+ # file where the decoder's input buffer is empty.
+
+ dec_buffer, dec_flags = self._decoder.getstate()
+ # Given this, we know there was a valid snapshot point
+ # len(dec_buffer) bytes ago with decoder state (b'', dec_flags).
+
+ # Read a chunk, decode it, and put the result in self._decoded_chars.
+ if self._has_read1:
+ input_chunk = self.buffer.read1(self._CHUNK_SIZE)
+ else:
+ input_chunk = self.buffer.read(self._CHUNK_SIZE)
+ eof = not input_chunk
+ self._set_decoded_chars(self._decoder.decode(input_chunk, eof))
+
+ if self._telling:
+ # At the snapshot point, len(dec_buffer) bytes before the read,
+ # the next input to be decoded is dec_buffer + input_chunk.
+ self._snapshot = (dec_flags, dec_buffer + input_chunk)
+
+ return not eof
+
+ def _pack_cookie(self, position, dec_flags=0,
+ bytes_to_feed=0, need_eof=0, chars_to_skip=0):
+ # The meaning of a tell() cookie is: seek to position, set the
+ # decoder flags to dec_flags, read bytes_to_feed bytes, feed them
+ # into the decoder with need_eof as the EOF flag, then skip
+ # chars_to_skip characters of the decoded result. For most simple
+ # decoders, tell() will often just give a byte offset in the file.
+ return (position | (dec_flags<<64) | (bytes_to_feed<<128) |
+ (chars_to_skip<<192) | bool(need_eof)<<256)
+
+ def _unpack_cookie(self, bigint):
+ rest, position = divmod(bigint, 1<<64)
+ rest, dec_flags = divmod(rest, 1<<64)
+ rest, bytes_to_feed = divmod(rest, 1<<64)
+ need_eof, chars_to_skip = divmod(rest, 1<<64)
+ return position, dec_flags, bytes_to_feed, need_eof, chars_to_skip
+
+ def tell(self):
+ if not self._seekable:
+ raise UnsupportedOperation("underlying stream is not seekable")
+ if not self._telling:
+ raise IOError("telling position disabled by next() call")
+ self.flush()
+ position = self.buffer.tell()
+ decoder = self._decoder
+ if decoder is None or self._snapshot is None:
+ if self._decoded_chars:
+ # This should never happen.
+ raise AssertionError("pending decoded text")
+ return position
+
+ # Skip backward to the snapshot point (see _read_chunk).
+ dec_flags, next_input = self._snapshot
+ position -= len(next_input)
+
+ # How many decoded characters have been used up since the snapshot?
+ chars_to_skip = self._decoded_chars_used
+ if chars_to_skip == 0:
+ # We haven't moved from the snapshot point.
+ return self._pack_cookie(position, dec_flags)
+
+ # Starting from the snapshot position, we will walk the decoder
+ # forward until it gives us enough decoded characters.
+ saved_state = decoder.getstate()
+ try:
+ # Note our initial start point.
+ decoder.setstate((b'', dec_flags))
+ start_pos = position
+ start_flags, bytes_fed, chars_decoded = dec_flags, 0, 0
+ need_eof = 0
+
+ # Feed the decoder one byte at a time. As we go, note the
+ # nearest "safe start point" before the current location
+ # (a point where the decoder has nothing buffered, so seek()
+ # can safely start from there and advance to this location).
+ next_byte = bytearray(1)
+ for next_byte[0] in next_input:
+ bytes_fed += 1
+ chars_decoded += len(decoder.decode(next_byte))
+ dec_buffer, dec_flags = decoder.getstate()
+ if not dec_buffer and chars_decoded <= chars_to_skip:
+ # Decoder buffer is empty, so this is a safe start point.
+ start_pos += bytes_fed
+ chars_to_skip -= chars_decoded
+ start_flags, bytes_fed, chars_decoded = dec_flags, 0, 0
+ if chars_decoded >= chars_to_skip:
+ break
+ else:
+ # We didn't get enough decoded data; signal EOF to get more.
+ chars_decoded += len(decoder.decode(b'', final=True))
+ need_eof = 1
+ if chars_decoded < chars_to_skip:
+ raise IOError("can't reconstruct logical file position")
+
+ # The returned cookie corresponds to the last safe start point.
+ return self._pack_cookie(
+ start_pos, start_flags, bytes_fed, need_eof, chars_to_skip)
+ finally:
+ decoder.setstate(saved_state)
+
+ def truncate(self, pos=None):
+ self.flush()
+ if pos is None:
+ pos = self.tell()
+ return self.buffer.truncate(pos)
+
+ def detach(self):
+ if self.buffer is None:
+ raise ValueError("buffer is already detached")
+ self.flush()
+ buffer = self._buffer
+ self._buffer = None
+ return buffer
+
+ def seek(self, cookie, whence=0):
+ if self.closed:
+ raise ValueError("tell on closed file")
+ if not self._seekable:
+ raise UnsupportedOperation("underlying stream is not seekable")
+ if whence == 1: # seek relative to current position
+ if cookie != 0:
+ raise UnsupportedOperation("can't do nonzero cur-relative seeks")
+ # Seeking to the current position should attempt to
+ # sync the underlying buffer with the current position.
+ whence = 0
+ cookie = self.tell()
+ if whence == 2: # seek relative to end of file
+ if cookie != 0:
+ raise UnsupportedOperation("can't do nonzero end-relative seeks")
+ self.flush()
+ position = self.buffer.seek(0, 2)
+ self._set_decoded_chars('')
+ self._snapshot = None
+ if self._decoder:
+ self._decoder.reset()
+ return position
+ if whence != 0:
+ raise ValueError("invalid whence (%r, should be 0, 1 or 2)" %
+ (whence,))
+ if cookie < 0:
+ raise ValueError("negative seek position %r" % (cookie,))
+ self.flush()
+
+ # The strategy of seek() is to go back to the safe start point
+ # and replay the effect of read(chars_to_skip) from there.
+ start_pos, dec_flags, bytes_to_feed, need_eof, chars_to_skip = \
+ self._unpack_cookie(cookie)
+
+ # Seek back to the safe start point.
+ self.buffer.seek(start_pos)
+ self._set_decoded_chars('')
+ self._snapshot = None
+
+ # Restore the decoder to its state from the safe start point.
+ if cookie == 0 and self._decoder:
+ self._decoder.reset()
+ elif self._decoder or dec_flags or chars_to_skip:
+ self._decoder = self._decoder or self._get_decoder()
+ self._decoder.setstate((b'', dec_flags))
+ self._snapshot = (dec_flags, b'')
+
+ if chars_to_skip:
+ # Just like _read_chunk, feed the decoder and save a snapshot.
+ input_chunk = self.buffer.read(bytes_to_feed)
+ self._set_decoded_chars(
+ self._decoder.decode(input_chunk, need_eof))
+ self._snapshot = (dec_flags, input_chunk)
+
+ # Skip chars_to_skip of the decoded characters.
+ if len(self._decoded_chars) < chars_to_skip:
+ raise IOError("can't restore logical file position")
+ self._decoded_chars_used = chars_to_skip
+
+ # Finally, reset the encoder (merely useful for proper BOM handling)
+ try:
+ encoder = self._encoder or self._get_encoder()
+ except LookupError:
+ # Sometimes the encoder doesn't exist
+ pass
+ else:
+ if cookie != 0:
+ encoder.setstate(0)
+ else:
+ encoder.reset()
+ return cookie
+
+ def read(self, n=None):
+ self._checkReadable()
+ if n is None:
+ n = -1
+ decoder = self._decoder or self._get_decoder()
+ try:
+ n.__index__
+ except AttributeError as err:
+ raise TypeError("an integer is required") from err
+ if n < 0:
+ # Read everything.
+ result = (self._get_decoded_chars() +
+ decoder.decode(self.buffer.read(), final=True))
+ self._set_decoded_chars('')
+ self._snapshot = None
+ return result
+ else:
+ # Keep reading chunks until we have n characters to return.
+ eof = False
+ result = self._get_decoded_chars(n)
+ while len(result) < n and not eof:
+ eof = not self._read_chunk()
+ result += self._get_decoded_chars(n - len(result))
+ return result
+
+ def __next__(self):
+ self._telling = False
+ line = self.readline()
+ if not line:
+ self._snapshot = None
+ self._telling = self._seekable
+ raise StopIteration
+ return line
+
+ def readline(self, limit=None):
+ if self.closed:
+ raise ValueError("read from closed file")
+ if limit is None:
+ limit = -1
+ elif not isinstance(limit, int):
+ raise TypeError("limit must be an integer")
+
+ # Grab all the decoded text (we will rewind any extra bits later).
+ line = self._get_decoded_chars()
+
+ start = 0
+ # Make the decoder if it doesn't already exist.
+ if not self._decoder:
+ self._get_decoder()
+
+ pos = endpos = None
+ while True:
+ if self._readtranslate:
+ # Newlines are already translated, only search for \n
+ pos = line.find('\n', start)
+ if pos >= 0:
+ endpos = pos + 1
+ break
+ else:
+ start = len(line)
+
+ elif self._readuniversal:
+ # Universal newline search. Find any of \r, \r\n, \n
+ # The decoder ensures that \r\n are not split in two pieces
+
+ # In C we'd look for these in parallel of course.
+ nlpos = line.find("\n", start)
+ crpos = line.find("\r", start)
+ if crpos == -1:
+ if nlpos == -1:
+ # Nothing found
+ start = len(line)
+ else:
+ # Found \n
+ endpos = nlpos + 1
+ break
+ elif nlpos == -1:
+ # Found lone \r
+ endpos = crpos + 1
+ break
+ elif nlpos < crpos:
+ # Found \n
+ endpos = nlpos + 1
+ break
+ elif nlpos == crpos + 1:
+ # Found \r\n
+ endpos = crpos + 2
+ break
+ else:
+ # Found \r
+ endpos = crpos + 1
+ break
+ else:
+ # non-universal
+ pos = line.find(self._readnl)
+ if pos >= 0:
+ endpos = pos + len(self._readnl)
+ break
+
+ if limit >= 0 and len(line) >= limit:
+ endpos = limit # reached length limit
+ break
+
+ # No line ending seen yet - get more data'
+ while self._read_chunk():
+ if self._decoded_chars:
+ break
+ if self._decoded_chars:
+ line += self._get_decoded_chars()
+ else:
+ # end of file
+ self._set_decoded_chars('')
+ self._snapshot = None
+ return line
+
+ if limit >= 0 and endpos > limit:
+ endpos = limit # don't exceed limit
+
+ # Rewind _decoded_chars to just after the line ending we found.
+ self._rewind_decoded_chars(len(line) - endpos)
+ return line[:endpos]
+
+ @property
+ def newlines(self):
+ return self._decoder.newlines if self._decoder else None
+
+
+class StringIO(TextIOWrapper):
+ """Text I/O implementation using an in-memory buffer.
+
+ The initial_value argument sets the value of object. The newline
+ argument is like the one of TextIOWrapper's constructor.
+ """
+
+ def __init__(self, initial_value="", newline="\n"):
+ super(StringIO, self).__init__(BytesIO(),
+ encoding="utf-8",
+ errors="strict",
+ newline=newline)
+ # Issue #5645: make universal newlines semantics the same as in the
+ # C version, even under Windows.
+ if newline is None:
+ self._writetranslate = False
+ if initial_value is not None:
+ if not isinstance(initial_value, str):
+ raise TypeError("initial_value must be str or None, not {0}"
+ .format(type(initial_value).__name__))
+ initial_value = str(initial_value)
+ self.write(initial_value)
+ self.seek(0)
+
+ def getvalue(self):
+ self.flush()
+ return self.buffer.getvalue().decode(self._encoding, self._errors)
+
+ def __repr__(self):
+ # TextIOWrapper tells the encoding in its repr. In StringIO,
+ # that's a implementation detail.
+ return object.__repr__(self)
+
+ @property
+ def errors(self):
+ return None
+
+ @property
+ def encoding(self):
+ return None
+
+ def detach(self):
+ # This doesn't make sense on StringIO.
+ self._unsupported("detach")
diff --git a/lib-python/3.2/_strptime.py b/lib-python/3.2/_strptime.py
new file mode 100644
--- /dev/null
+++ b/lib-python/3.2/_strptime.py
@@ -0,0 +1,499 @@
+"""Strptime-related classes and functions.
+
+CLASSES:
+ LocaleTime -- Discovers and stores locale-specific time information
+ TimeRE -- Creates regexes for pattern matching a string of text containing
+ time information
+
+FUNCTIONS:
+ _getlang -- Figure out what language is being used for the locale
+ strptime -- Calculates the time struct represented by the passed-in string
+
+"""
+import time
+import locale
+import calendar
+from re import compile as re_compile
+from re import IGNORECASE, ASCII
+from re import escape as re_escape
+from datetime import (date as datetime_date,
+ timedelta as datetime_timedelta,
+ timezone as datetime_timezone)
+try:
+ from _thread import allocate_lock as _thread_allocate_lock
+except:
+ from _dummy_thread import allocate_lock as _thread_allocate_lock
+
+__all__ = []
+
+def _getlang():
+ # Figure out what the current language is set to.
+ return locale.getlocale(locale.LC_TIME)
+
+class LocaleTime(object):
+ """Stores and handles locale-specific information related to time.
+
+ ATTRIBUTES:
+ f_weekday -- full weekday names (7-item list)
+ a_weekday -- abbreviated weekday names (7-item list)
+ f_month -- full month names (13-item list; dummy value in [0], which
+ is added by code)
+ a_month -- abbreviated month names (13-item list, dummy value in
+ [0], which is added by code)
+ am_pm -- AM/PM representation (2-item list)
+ LC_date_time -- format string for date/time representation (string)
+ LC_date -- format string for date representation (string)
+ LC_time -- format string for time representation (string)
+ timezone -- daylight- and non-daylight-savings timezone representation
+ (2-item list of sets)
+ lang -- Language used by instance (2-item tuple)
+ """
+
+ def __init__(self):
+ """Set all attributes.
+
+ Order of methods called matters for dependency reasons.
+
+ The locale language is set at the offset and then checked again before
+ exiting. This is to make sure that the attributes were not set with a
+ mix of information from more than one locale. This would most likely
+ happen when using threads where one thread calls a locale-dependent
+ function while another thread changes the locale while the function in
+ the other thread is still running. Proper coding would call for
+ locks to prevent changing the locale while locale-dependent code is
+ running. The check here is done in case someone does not think about
+ doing this.
+
+ Only other possible issue is if someone changed the timezone and did
+ not call tz.tzset . That is an issue for the programmer, though,
+ since changing the timezone is worthless without that call.
+
+ """
+ self.lang = _getlang()
+ self.__calc_weekday()
+ self.__calc_month()
+ self.__calc_am_pm()
+ self.__calc_timezone()
+ self.__calc_date_time()
+ if _getlang() != self.lang:
+ raise ValueError("locale changed during initialization")
+
+ def __pad(self, seq, front):
+ # Add '' to seq to either the front (is True), else the back.
+ seq = list(seq)
+ if front:
+ seq.insert(0, '')
+ else:
+ seq.append('')
+ return seq
+
+ def __calc_weekday(self):
+ # Set self.a_weekday and self.f_weekday using the calendar
+ # module.
+ a_weekday = [calendar.day_abbr[i].lower() for i in range(7)]
+ f_weekday = [calendar.day_name[i].lower() for i in range(7)]
+ self.a_weekday = a_weekday
+ self.f_weekday = f_weekday
+
+ def __calc_month(self):
+ # Set self.f_month and self.a_month using the calendar module.
+ a_month = [calendar.month_abbr[i].lower() for i in range(13)]
+ f_month = [calendar.month_name[i].lower() for i in range(13)]
+ self.a_month = a_month
+ self.f_month = f_month
+
+ def __calc_am_pm(self):
+ # Set self.am_pm by using time.strftime().
+
+ # The magic date (1999,3,17,hour,44,55,2,76,0) is not really that
+ # magical; just happened to have used it everywhere else where a
+ # static date was needed.
+ am_pm = []
+ for hour in (1, 22):
+ time_tuple = time.struct_time((1999,3,17,hour,44,55,2,76,0))
+ am_pm.append(time.strftime("%p", time_tuple).lower())
+ self.am_pm = am_pm
+
+ def __calc_date_time(self):
+ # Set self.date_time, self.date, & self.time by using
+ # time.strftime().
+
+ # Use (1999,3,17,22,44,55,2,76,0) for magic date because the amount of
+ # overloaded numbers is minimized. The order in which searches for
+ # values within the format string is very important; it eliminates
+ # possible ambiguity for what something represents.
+ time_tuple = time.struct_time((1999,3,17,22,44,55,2,76,0))
+ date_time = [None, None, None]
+ date_time[0] = time.strftime("%c", time_tuple).lower()
+ date_time[1] = time.strftime("%x", time_tuple).lower()
+ date_time[2] = time.strftime("%X", time_tuple).lower()
+ replacement_pairs = [('%', '%%'), (self.f_weekday[2], '%A'),
+ (self.f_month[3], '%B'), (self.a_weekday[2], '%a'),
+ (self.a_month[3], '%b'), (self.am_pm[1], '%p'),
+ ('1999', '%Y'), ('99', '%y'), ('22', '%H'),
+ ('44', '%M'), ('55', '%S'), ('76', '%j'),
+ ('17', '%d'), ('03', '%m'), ('3', '%m'),
+ # '3' needed for when no leading zero.
+ ('2', '%w'), ('10', '%I')]
+ replacement_pairs.extend([(tz, "%Z") for tz_values in self.timezone
+ for tz in tz_values])
+ for offset,directive in ((0,'%c'), (1,'%x'), (2,'%X')):
+ current_format = date_time[offset]
+ for old, new in replacement_pairs:
+ # Must deal with possible lack of locale info
+ # manifesting itself as the empty string (e.g., Swedish's
+ # lack of AM/PM info) or a platform returning a tuple of empty
+ # strings (e.g., MacOS 9 having timezone as ('','')).
+ if old:
+ current_format = current_format.replace(old, new)
+ # If %W is used, then Sunday, 2005-01-03 will fall on week 0 since
+ # 2005-01-03 occurs before the first Monday of the year. Otherwise
+ # %U is used.
+ time_tuple = time.struct_time((1999,1,3,1,1,1,6,3,0))
+ if '00' in time.strftime(directive, time_tuple):
+ U_W = '%W'
+ else:
+ U_W = '%U'
+ date_time[offset] = current_format.replace('11', U_W)
+ self.LC_date_time = date_time[0]
+ self.LC_date = date_time[1]
+ self.LC_time = date_time[2]
+
+ def __calc_timezone(self):
+ # Set self.timezone by using time.tzname.
+ # Do not worry about possibility of time.tzname[0] == timetzname[1]
+ # and time.daylight; handle that in strptime .
+ try:
+ time.tzset()
+ except AttributeError:
+ pass
+ no_saving = frozenset(["utc", "gmt", time.tzname[0].lower()])
+ if time.daylight:
+ has_saving = frozenset([time.tzname[1].lower()])
+ else:
+ has_saving = frozenset()
+ self.timezone = (no_saving, has_saving)
+
+
+class TimeRE(dict):
+ """Handle conversion from format directives to regexes."""
+
+ def __init__(self, locale_time=None):
+ """Create keys/values.
+
+ Order of execution is important for dependency reasons.
+
+ """
+ if locale_time:
+ self.locale_time = locale_time
+ else:
+ self.locale_time = LocaleTime()
+ base = super()
+ base.__init__({
+ # The " \d" part of the regex is to make %c from ANSI C work
+ 'd': r"(?P<d>3[0-1]|[1-2]\d|0[1-9]|[1-9]| [1-9])",
+ 'f': r"(?P<f>[0-9]{1,6})",
+ 'H': r"(?P<H>2[0-3]|[0-1]\d|\d)",
+ 'I': r"(?P<I>1[0-2]|0[1-9]|[1-9])",
+ 'j': r"(?P<j>36[0-6]|3[0-5]\d|[1-2]\d\d|0[1-9]\d|00[1-9]|[1-9]\d|0[1-9]|[1-9])",
+ 'm': r"(?P<m>1[0-2]|0[1-9]|[1-9])",
+ 'M': r"(?P<M>[0-5]\d|\d)",
+ 'S': r"(?P<S>6[0-1]|[0-5]\d|\d)",
+ 'U': r"(?P<U>5[0-3]|[0-4]\d|\d)",
+ 'w': r"(?P<w>[0-6])",
+ # W is set below by using 'U'
+ 'y': r"(?P<y>\d\d)",
+ #XXX: Does 'Y' need to worry about having less or more than
+ # 4 digits?
+ 'Y': r"(?P<Y>\d\d\d\d)",
+ 'z': r"(?P<z>[+-]\d\d[0-5]\d)",
+ 'A': self.__seqToRE(self.locale_time.f_weekday, 'A'),
+ 'a': self.__seqToRE(self.locale_time.a_weekday, 'a'),
+ 'B': self.__seqToRE(self.locale_time.f_month[1:], 'B'),
+ 'b': self.__seqToRE(self.locale_time.a_month[1:], 'b'),
+ 'p': self.__seqToRE(self.locale_time.am_pm, 'p'),
+ 'Z': self.__seqToRE((tz for tz_names in self.locale_time.timezone
+ for tz in tz_names),
+ 'Z'),
+ '%': '%'})
+ base.__setitem__('W', base.__getitem__('U').replace('U', 'W'))
+ base.__setitem__('c', self.pattern(self.locale_time.LC_date_time))
+ base.__setitem__('x', self.pattern(self.locale_time.LC_date))
+ base.__setitem__('X', self.pattern(self.locale_time.LC_time))
+
+ def __seqToRE(self, to_convert, directive):
+ """Convert a list to a regex string for matching a directive.
+
+ Want possible matching values to be from longest to shortest. This
+ prevents the possibility of a match occuring for a value that also
+ a substring of a larger value that should have matched (e.g., 'abc'
+ matching when 'abcdef' should have been the match).
+
+ """
+ to_convert = sorted(to_convert, key=len, reverse=True)
+ for value in to_convert:
+ if value != '':
+ break
+ else:
+ return ''
+ regex = '|'.join(re_escape(stuff) for stuff in to_convert)
+ regex = '(?P<%s>%s' % (directive, regex)
+ return '%s)' % regex
+
+ def pattern(self, format):
+ """Return regex pattern for the format string.
+
+ Need to make sure that any characters that might be interpreted as
+ regex syntax are escaped.
+
+ """
+ processed_format = ''
+ # The sub() call escapes all characters that might be misconstrued
+ # as regex syntax. Cannot use re.escape since we have to deal with
+ # format directives (%m, etc.).
+ regex_chars = re_compile(r"([\\.^$*+?\(\){}\[\]|])")
+ format = regex_chars.sub(r"\\\1", format)
+ whitespace_replacement = re_compile('\s+')
+ format = whitespace_replacement.sub('\s+', format)
+ while '%' in format:
+ directive_index = format.index('%')+1
+ processed_format = "%s%s%s" % (processed_format,
+ format[:directive_index-1],
+ self[format[directive_index]])
+ format = format[directive_index+1:]
+ return "%s%s" % (processed_format, format)
+
+ def compile(self, format):
+ """Return a compiled re object for the format string."""
+ return re_compile(self.pattern(format), IGNORECASE)
+
+_cache_lock = _thread_allocate_lock()
+# DO NOT modify _TimeRE_cache or _regex_cache without acquiring the cache lock
+# first!
+_TimeRE_cache = TimeRE()
+_CACHE_MAX_SIZE = 5 # Max number of regexes stored in _regex_cache
+_regex_cache = {}
+
+def _calc_julian_from_U_or_W(year, week_of_year, day_of_week, week_starts_Mon):
+ """Calculate the Julian day based on the year, week of the year, and day of
+ the week, with week_start_day representing whether the week of the year
+ assumes the week starts on Sunday or Monday (6 or 0)."""
+ first_weekday = datetime_date(year, 1, 1).weekday()
+ # If we are dealing with the %U directive (week starts on Sunday), it's
+ # easier to just shift the view to Sunday being the first day of the
+ # week.
+ if not week_starts_Mon:
+ first_weekday = (first_weekday + 1) % 7
+ day_of_week = (day_of_week + 1) % 7
+ # Need to watch out for a week 0 (when the first day of the year is not
+ # the same as that specified by %U or %W).
+ week_0_length = (7 - first_weekday) % 7
+ if week_of_year == 0:
+ return 1 + day_of_week - first_weekday
+ else:
+ days_to_week = week_0_length + (7 * (week_of_year - 1))
+ return 1 + days_to_week + day_of_week
+
+
+def _strptime(data_string, format="%a %b %d %H:%M:%S %Y"):
+ """Return a 2-tuple consisting of a time struct and an int containing
+ the number of microseconds based on the input string and the
+ format string."""
+
+ for index, arg in enumerate([data_string, format]):
+ if not isinstance(arg, str):
+ msg = "strptime() argument {} must be str, not {}"
+ raise TypeError(msg.format(index, type(arg)))
+
+ global _TimeRE_cache, _regex_cache
+ with _cache_lock:
+
+ if _getlang() != _TimeRE_cache.locale_time.lang:
+ _TimeRE_cache = TimeRE()
+ _regex_cache.clear()
+ if len(_regex_cache) > _CACHE_MAX_SIZE:
+ _regex_cache.clear()
+ locale_time = _TimeRE_cache.locale_time
+ format_regex = _regex_cache.get(format)
+ if not format_regex:
+ try:
+ format_regex = _TimeRE_cache.compile(format)
+ # KeyError raised when a bad format is found; can be specified as
+ # \\, in which case it was a stray % but with a space after it
+ except KeyError as err:
+ bad_directive = err.args[0]
+ if bad_directive == "\\":
+ bad_directive = "%"
+ del err
+ raise ValueError("'%s' is a bad directive in format '%s'" %
+ (bad_directive, format))
+ # IndexError only occurs when the format string is "%"
+ except IndexError:
+ raise ValueError("stray %% in format '%s'" % format)
+ _regex_cache[format] = format_regex
+ found = format_regex.match(data_string)
+ if not found:
+ raise ValueError("time data %r does not match format %r" %
+ (data_string, format))
+ if len(data_string) != found.end():
+ raise ValueError("unconverted data remains: %s" %
+ data_string[found.end():])
+
+ year = 1900
+ month = day = 1
+ hour = minute = second = fraction = 0
+ tz = -1
+ tzoffset = None
+ # Default to -1 to signify that values not known; not critical to have,
+ # though
+ week_of_year = -1
+ week_of_year_start = -1
+ # weekday and julian defaulted to -1 so as to signal need to calculate
+ # values
+ weekday = julian = -1
+ found_dict = found.groupdict()
+ for group_key in found_dict.keys():
+ # Directives not explicitly handled below:
+ # c, x, X
+ # handled by making out of other directives
+ # U, W
+ # worthless without day of the week
+ if group_key == 'y':
+ year = int(found_dict['y'])
+ # Open Group specification for strptime() states that a %y
+ #value in the range of [00, 68] is in the century 2000, while
+ #[69,99] is in the century 1900
+ if year <= 68:
+ year += 2000
+ else:
+ year += 1900
+ elif group_key == 'Y':
+ year = int(found_dict['Y'])
+ elif group_key == 'm':
+ month = int(found_dict['m'])
+ elif group_key == 'B':
+ month = locale_time.f_month.index(found_dict['B'].lower())
+ elif group_key == 'b':
+ month = locale_time.a_month.index(found_dict['b'].lower())
+ elif group_key == 'd':
+ day = int(found_dict['d'])
+ elif group_key == 'H':
+ hour = int(found_dict['H'])
+ elif group_key == 'I':
+ hour = int(found_dict['I'])
+ ampm = found_dict.get('p', '').lower()
+ # If there was no AM/PM indicator, we'll treat this like AM
+ if ampm in ('', locale_time.am_pm[0]):
+ # We're in AM so the hour is correct unless we're
+ # looking at 12 midnight.
+ # 12 midnight == 12 AM == hour 0
+ if hour == 12:
+ hour = 0
+ elif ampm == locale_time.am_pm[1]:
+ # We're in PM so we need to add 12 to the hour unless
+ # we're looking at 12 noon.
+ # 12 noon == 12 PM == hour 12
+ if hour != 12:
+ hour += 12
+ elif group_key == 'M':
+ minute = int(found_dict['M'])
+ elif group_key == 'S':
+ second = int(found_dict['S'])
+ elif group_key == 'f':
+ s = found_dict['f']
+ # Pad to always return microseconds.
+ s += "0" * (6 - len(s))
+ fraction = int(s)
+ elif group_key == 'A':
+ weekday = locale_time.f_weekday.index(found_dict['A'].lower())
+ elif group_key == 'a':
+ weekday = locale_time.a_weekday.index(found_dict['a'].lower())
+ elif group_key == 'w':
+ weekday = int(found_dict['w'])
+ if weekday == 0:
+ weekday = 6
+ else:
+ weekday -= 1
+ elif group_key == 'j':
+ julian = int(found_dict['j'])
+ elif group_key in ('U', 'W'):
+ week_of_year = int(found_dict[group_key])
+ if group_key == 'U':
+ # U starts week on Sunday.
+ week_of_year_start = 6
+ else:
+ # W starts week on Monday.
+ week_of_year_start = 0
+ elif group_key == 'z':
+ z = found_dict['z']
+ tzoffset = int(z[1:3]) * 60 + int(z[3:5])
+ if z.startswith("-"):
+ tzoffset = -tzoffset
+ elif group_key == 'Z':
+ # Since -1 is default value only need to worry about setting tz if
+ # it can be something other than -1.
+ found_zone = found_dict['Z'].lower()
+ for value, tz_values in enumerate(locale_time.timezone):
+ if found_zone in tz_values:
+ # Deal with bad locale setup where timezone names are the
+ # same and yet time.daylight is true; too ambiguous to
+ # be able to tell what timezone has daylight savings
+ if (time.tzname[0] == time.tzname[1] and
+ time.daylight and found_zone not in ("utc", "gmt")):
+ break
+ else:
+ tz = value
+ break
+ # If we know the week of the year and what day of that week, we can figure
+ # out the Julian day of the year.
+ if julian == -1 and week_of_year != -1 and weekday != -1:
+ week_starts_Mon = True if week_of_year_start == 0 else False
+ julian = _calc_julian_from_U_or_W(year, week_of_year, weekday,
+ week_starts_Mon)
+ # Cannot pre-calculate datetime_date() since can change in Julian
+ # calculation and thus could have different value for the day of the week
+ # calculation.
+ if julian == -1:
+ # Need to add 1 to result since first day of the year is 1, not 0.
+ julian = datetime_date(year, month, day).toordinal() - \
+ datetime_date(year, 1, 1).toordinal() + 1
+ else: # Assume that if they bothered to include Julian day it will
+ # be accurate.
+ datetime_result = datetime_date.fromordinal((julian - 1) + datetime_date(year, 1, 1).toordinal())
+ year = datetime_result.year
+ month = datetime_result.month
+ day = datetime_result.day
+ if weekday == -1:
+ weekday = datetime_date(year, month, day).weekday()
+ # Add timezone info
+ tzname = found_dict.get("Z")
+ if tzoffset is not None:
+ gmtoff = tzoffset * 60
+ else:
+ gmtoff = None
+
+ return (year, month, day,
+ hour, minute, second,
+ weekday, julian, tz, gmtoff, tzname), fraction
+
+def _strptime_time(data_string, format="%a %b %d %H:%M:%S %Y"):
+ """Return a time struct based on the input string and the
+ format string."""
+ tt = _strptime(data_string, format)[0]
+ return time.struct_time(tt[:9])
+
+def _strptime_datetime(cls, data_string, format="%a %b %d %H:%M:%S %Y"):
+ """Return a class cls instance based on the input string and the
+ format string."""
+ tt, fraction = _strptime(data_string, format)
+ gmtoff, tzname = tt[-2:]
+ args = tt[:6] + (fraction,)
+ if gmtoff is not None:
+ tzdelta = datetime_timedelta(seconds=gmtoff)
+ if tzname:
+ tz = datetime_timezone(tzdelta, tzname)
+ else:
+ tz = datetime_timezone(tzdelta)
+ args += (tz,)
+
+ return cls(*args)
diff --git a/lib-python/3.2/_threading_local.py b/lib-python/3.2/_threading_local.py
new file mode 100644
--- /dev/null
+++ b/lib-python/3.2/_threading_local.py
@@ -0,0 +1,246 @@
+"""Thread-local objects.
+
+(Note that this module provides a Python version of the threading.local
+ class. Depending on the version of Python you're using, there may be a
+ faster one available. You should always import the `local` class from
+ `threading`.)
+
+Thread-local objects support the management of thread-local data.
+If you have data that you want to be local to a thread, simply create
+a thread-local object and use its attributes:
+
+ >>> mydata = local()
+ >>> mydata.number = 42
+ >>> mydata.number
+ 42
+
+You can also access the local-object's dictionary:
+
+ >>> mydata.__dict__
+ {'number': 42}
+ >>> mydata.__dict__.setdefault('widgets', [])
+ []
+ >>> mydata.widgets
+ []
+
+What's important about thread-local objects is that their data are
+local to a thread. If we access the data in a different thread:
+
+ >>> log = []
+ >>> def f():
+ ... items = sorted(mydata.__dict__.items())
+ ... log.append(items)
+ ... mydata.number = 11
+ ... log.append(mydata.number)
+
+ >>> import threading
+ >>> thread = threading.Thread(target=f)
+ >>> thread.start()
+ >>> thread.join()
+ >>> log
+ [[], 11]
+
+we get different data. Furthermore, changes made in the other thread
+don't affect data seen in this thread:
+
+ >>> mydata.number
+ 42
+
+Of course, values you get from a local object, including a __dict__
+attribute, are for whatever thread was current at the time the
+attribute was read. For that reason, you generally don't want to save
+these values across threads, as they apply only to the thread they
+came from.
+
+You can create custom local objects by subclassing the local class:
+
+ >>> class MyLocal(local):
+ ... number = 2
+ ... initialized = False
+ ... def __init__(self, **kw):
+ ... if self.initialized:
+ ... raise SystemError('__init__ called too many times')
+ ... self.initialized = True
+ ... self.__dict__.update(kw)
+ ... def squared(self):
+ ... return self.number ** 2
+
+This can be useful to support default values, methods and
+initialization. Note that if you define an __init__ method, it will be
+called each time the local object is used in a separate thread. This
+is necessary to initialize each thread's dictionary.
+
+Now if we create a local object:
+
+ >>> mydata = MyLocal(color='red')
+
+Now we have a default number:
+
+ >>> mydata.number
+ 2
+
+an initial color:
+
+ >>> mydata.color
+ 'red'
+ >>> del mydata.color
+
+And a method that operates on the data:
+
+ >>> mydata.squared()
+ 4
+
+As before, we can access the data in a separate thread:
+
+ >>> log = []
+ >>> thread = threading.Thread(target=f)
+ >>> thread.start()
+ >>> thread.join()
+ >>> log
+ [[('color', 'red'), ('initialized', True)], 11]
+
+without affecting this thread's data:
+
+ >>> mydata.number
+ 2
+ >>> mydata.color
+ Traceback (most recent call last):
+ ...
+ AttributeError: 'MyLocal' object has no attribute 'color'
+
+Note that subclasses can define slots, but they are not thread
+local. They are shared across threads:
+
+ >>> class MyLocal(local):
+ ... __slots__ = 'number'
+
+ >>> mydata = MyLocal()
+ >>> mydata.number = 42
+ >>> mydata.color = 'red'
+
+So, the separate thread:
+
+ >>> thread = threading.Thread(target=f)
+ >>> thread.start()
+ >>> thread.join()
+
+affects what we see:
+
+ >>> mydata.number
+ 11
+
+>>> del mydata
+"""
+
+from weakref import ref
+from contextlib import contextmanager
+
+__all__ = ["local"]
+
+# We need to use objects from the threading module, but the threading
+# module may also want to use our `local` class, if support for locals
+# isn't compiled in to the `thread` module. This creates potential problems
+# with circular imports. For that reason, we don't import `threading`
+# until the bottom of this file (a hack sufficient to worm around the
+# potential problems). Note that all platforms on CPython do have support
+# for locals in the `thread` module, and there is no circular import problem
+# then, so problems introduced by fiddling the order of imports here won't
+# manifest.
+
+class _localimpl:
+ """A class managing thread-local dicts"""
+ __slots__ = 'key', 'dicts', 'localargs', 'locallock', '__weakref__'
+
+ def __init__(self):
+ # The key used in the Thread objects' attribute dicts.
+ # We keep it a string for speed but make it unlikely to clash with
+ # a "real" attribute.
+ self.key = '_threading_local._localimpl.' + str(id(self))
+ # { id(Thread) -> (ref(Thread), thread-local dict) }
+ self.dicts = {}
+
+ def get_dict(self):
+ """Return the dict for the current thread. Raises KeyError if none
+ defined."""
+ thread = current_thread()
+ return self.dicts[id(thread)][1]
+
+ def create_dict(self):
+ """Create a new dict for the current thread, and return it."""
+ localdict = {}
+ key = self.key
+ thread = current_thread()
+ idt = id(thread)
+ def local_deleted(_, key=key):
+ # When the localimpl is deleted, remove the thread attribute.
+ thread = wrthread()
+ if thread is not None:
+ del thread.__dict__[key]
+ def thread_deleted(_, idt=idt):
+ # When the thread is deleted, remove the local dict.
+ # Note that this is suboptimal if the thread object gets
+ # caught in a reference loop. We would like to be called
+ # as soon as the OS-level thread ends instead.
+ local = wrlocal()
+ if local is not None:
+ dct = local.dicts.pop(idt)
+ wrlocal = ref(self, local_deleted)
+ wrthread = ref(thread, thread_deleted)
+ thread.__dict__[key] = wrlocal
+ self.dicts[idt] = wrthread, localdict
+ return localdict
+
+
+ at contextmanager
+def _patch(self):
+ impl = object.__getattribute__(self, '_local__impl')
+ try:
+ dct = impl.get_dict()
+ except KeyError:
+ dct = impl.create_dict()
+ args, kw = impl.localargs
+ self.__init__(*args, **kw)
+ with impl.locallock:
+ object.__setattr__(self, '__dict__', dct)
+ yield
+
+
+class local:
+ __slots__ = '_local__impl', '__dict__'
+
+ def __new__(cls, *args, **kw):
+ if (args or kw) and (cls.__init__ is object.__init__):
+ raise TypeError("Initialization arguments are not supported")
+ self = object.__new__(cls)
+ impl = _localimpl()
+ impl.localargs = (args, kw)
+ impl.locallock = RLock()
+ object.__setattr__(self, '_local__impl', impl)
+ # We need to create the thread dict in anticipation of
+ # __init__ being called, to make sure we don't call it
+ # again ourselves.
+ impl.create_dict()
+ return self
+
+ def __getattribute__(self, name):
+ with _patch(self):
+ return object.__getattribute__(self, name)
+
+ def __setattr__(self, name, value):
+ if name == '__dict__':
+ raise AttributeError(
+ "%r object attribute '__dict__' is read-only"
+ % self.__class__.__name__)
+ with _patch(self):
+ return object.__setattr__(self, name, value)
+
+ def __delattr__(self, name):
+ if name == '__dict__':
+ raise AttributeError(
+ "%r object attribute '__dict__' is read-only"
+ % self.__class__.__name__)
+ with _patch(self):
+ return object.__delattr__(self, name)
+
+
+from threading import current_thread, RLock
diff --git a/lib-python/3.2/_weakrefset.py b/lib-python/3.2/_weakrefset.py
new file mode 100644
--- /dev/null
+++ b/lib-python/3.2/_weakrefset.py
@@ -0,0 +1,214 @@
+# Access WeakSet through the weakref module.
+# This code is separated-out because it is needed
+# by abc.py to load everything else at startup.
+
+from _weakref import ref
+
+__all__ = ['WeakSet']
+
+
+class _IterationGuard:
+ # This context manager registers itself in the current iterators of the
+ # weak container, such as to delay all removals until the context manager
+ # exits.
+ # This technique should be relatively thread-safe (since sets are).
+
+ def __init__(self, weakcontainer):
+ # Don't create cycles
+ self.weakcontainer = ref(weakcontainer)
+
+ def __enter__(self):
+ w = self.weakcontainer()
+ if w is not None:
+ w._iterating.add(self)
+ return self
+
+ def __exit__(self, e, t, b):
+ w = self.weakcontainer()
+ if w is not None:
+ s = w._iterating
+ s.remove(self)
+ if not s:
+ w._commit_removals()
+
+
+class WeakSet:
+ def __init__(self, data=None):
+ self.data = set()
+ def _remove(item, selfref=ref(self)):
+ self = selfref()
+ if self is not None:
+ if self._iterating:
+ self._pending_removals.append(item)
+ else:
+ self.data.discard(item)
+ self._remove = _remove
+ # A list of keys to be removed
+ self._pending_removals = []
+ self._iterating = set()
+ if data is not None:
+ self.update(data)
+
+ def _commit_removals(self):
+ l = self._pending_removals
+ discard = self.data.discard
+ while l:
+ discard(l.pop())
+
+ def __iter__(self):
+ with _IterationGuard(self):
+ for itemref in self.data:
+ item = itemref()
+ if item is not None:
+ yield item
+
+ def __len__(self):
+ return sum(x() is not None for x in self.data)
+
+ def __contains__(self, item):
+ try:
+ wr = ref(item)
+ except TypeError:
+ return False
+ return wr in self.data
+
+ def __reduce__(self):
+ return (self.__class__, (list(self),),
+ getattr(self, '__dict__', None))
+
+ def add(self, item):
+ if self._pending_removals:
+ self._commit_removals()
+ self.data.add(ref(item, self._remove))
+
+ def clear(self):
+ if self._pending_removals:
+ self._commit_removals()
+ self.data.clear()
+
+ def copy(self):
+ return self.__class__(self)
+
+ def pop(self):
+ if self._pending_removals:
+ self._commit_removals()
+ while True:
+ try:
+ itemref = self.data.pop()
+ except KeyError:
+ raise KeyError('pop from empty WeakSet')
+ item = itemref()
+ if item is not None:
+ return item
+
+ def remove(self, item):
+ if self._pending_removals:
+ self._commit_removals()
+ self.data.remove(ref(item))
+
+ def discard(self, item):
+ if self._pending_removals:
+ self._commit_removals()
+ self.data.discard(ref(item))
+
+ def update(self, other):
+ if self._pending_removals:
+ self._commit_removals()
+ if isinstance(other, self.__class__):
+ self.data.update(other.data)
+ else:
+ for element in other:
+ self.add(element)
+
+ def __ior__(self, other):
+ self.update(other)
+ return self
+
+ # Helper functions for simple delegating methods.
+ def _apply(self, other, method):
+ if not isinstance(other, self.__class__):
+ other = self.__class__(other)
+ newdata = method(other.data)
+ newset = self.__class__()
+ newset.data = newdata
+ return newset
+
+ def difference(self, other):
+ return self._apply(other, self.data.difference)
+ __sub__ = difference
+
+ def difference_update(self, other):
+ if self._pending_removals:
+ self._commit_removals()
+ if self is other:
+ self.data.clear()
+ else:
+ self.data.difference_update(ref(item) for item in other)
+ def __isub__(self, other):
+ if self._pending_removals:
+ self._commit_removals()
+ if self is other:
+ self.data.clear()
+ else:
+ self.data.difference_update(ref(item) for item in other)
+ return self
+
+ def intersection(self, other):
+ return self._apply(other, self.data.intersection)
+ __and__ = intersection
+
+ def intersection_update(self, other):
+ if self._pending_removals:
+ self._commit_removals()
+ self.data.intersection_update(ref(item) for item in other)
+ def __iand__(self, other):
+ if self._pending_removals:
+ self._commit_removals()
+ self.data.intersection_update(ref(item) for item in other)
+ return self
+
+ def issubset(self, other):
+ return self.data.issubset(ref(item) for item in other)
+ __lt__ = issubset
+
+ def __le__(self, other):
+ return self.data <= set(ref(item) for item in other)
+
+ def issuperset(self, other):
+ return self.data.issuperset(ref(item) for item in other)
+ __gt__ = issuperset
+
+ def __ge__(self, other):
+ return self.data >= set(ref(item) for item in other)
+
+ def __eq__(self, other):
+ if not isinstance(other, self.__class__):
+ return NotImplemented
+ return self.data == set(ref(item) for item in other)
+
+ def symmetric_difference(self, other):
+ return self._apply(other, self.data.symmetric_difference)
+ __xor__ = symmetric_difference
+
+ def symmetric_difference_update(self, other):
+ if self._pending_removals:
+ self._commit_removals()
+ if self is other:
+ self.data.clear()
+ else:
+ self.data.symmetric_difference_update(ref(item) for item in other)
+ def __ixor__(self, other):
+ if self._pending_removals:
+ self._commit_removals()
+ if self is other:
+ self.data.clear()
+ else:
+ self.data.symmetric_difference_update(ref(item) for item in other)
+ return self
+
+ def union(self, other):
+ return self._apply(other, self.data.union)
+ __or__ = union
+
+ def isdisjoint(self, other):
+ return len(self.intersection(other)) == 0
diff --git a/lib-python/3.2/abc.py b/lib-python/3.2/abc.py
new file mode 100644
--- /dev/null
+++ b/lib-python/3.2/abc.py
@@ -0,0 +1,211 @@
+# Copyright 2007 Google, Inc. All Rights Reserved.
+# Licensed to PSF under a Contributor Agreement.
+
+"""Abstract Base Classes (ABCs) according to PEP 3119."""
+
+from _weakrefset import WeakSet
+
+def abstractmethod(funcobj):
+ """A decorator indicating abstract methods.
+
+ Requires that the metaclass is ABCMeta or derived from it. A
+ class that has a metaclass derived from ABCMeta cannot be
+ instantiated unless all of its abstract methods are overridden.
+ The abstract methods can be called using any of the normal
+ 'super' call mechanisms.
+
+ Usage:
+
+ class C(metaclass=ABCMeta):
+ @abstractmethod
+ def my_abstract_method(self, ...):
+ ...
+ """
+ funcobj.__isabstractmethod__ = True
+ return funcobj
+
+
+class abstractclassmethod(classmethod):
+ """A decorator indicating abstract classmethods.
+
+ Similar to abstractmethod.
+
+ Usage:
+
+ class C(metaclass=ABCMeta):
+ @abstractclassmethod
+ def my_abstract_classmethod(cls, ...):
+ ...
+ """
+
+ __isabstractmethod__ = True
+
+ def __init__(self, callable):
+ callable.__isabstractmethod__ = True
+ super().__init__(callable)
+
+
+class abstractstaticmethod(staticmethod):
+ """A decorator indicating abstract staticmethods.
+
+ Similar to abstractmethod.
+
+ Usage:
+
+ class C(metaclass=ABCMeta):
+ @abstractstaticmethod
+ def my_abstract_staticmethod(...):
+ ...
+ """
+
+ __isabstractmethod__ = True
+
+ def __init__(self, callable):
+ callable.__isabstractmethod__ = True
+ super().__init__(callable)
+
+
+class abstractproperty(property):
+ """A decorator indicating abstract properties.
+
+ Requires that the metaclass is ABCMeta or derived from it. A
+ class that has a metaclass derived from ABCMeta cannot be
+ instantiated unless all of its abstract properties are overridden.
+ The abstract properties can be called using any of the normal
+ 'super' call mechanisms.
+
+ Usage:
+
+ class C(metaclass=ABCMeta):
+ @abstractproperty
+ def my_abstract_property(self):
+ ...
+
+ This defines a read-only property; you can also define a read-write
+ abstract property using the 'long' form of property declaration:
+
+ class C(metaclass=ABCMeta):
+ def getx(self): ...
+ def setx(self, value): ...
+ x = abstractproperty(getx, setx)
+ """
+ __isabstractmethod__ = True
+
+
+class ABCMeta(type):
+
+ """Metaclass for defining Abstract Base Classes (ABCs).
+
+ Use this metaclass to create an ABC. An ABC can be subclassed
+ directly, and then acts as a mix-in class. You can also register
+ unrelated concrete classes (even built-in classes) and unrelated
+ ABCs as 'virtual subclasses' -- these and their descendants will
+ be considered subclasses of the registering ABC by the built-in
+ issubclass() function, but the registering ABC won't show up in
+ their MRO (Method Resolution Order) nor will method
+ implementations defined by the registering ABC be callable (not
+ even via super()).
+
+ """
+
+ # A global counter that is incremented each time a class is
+ # registered as a virtual subclass of anything. It forces the
+ # negative cache to be cleared before its next use.
+ _abc_invalidation_counter = 0
+
+ def __new__(mcls, name, bases, namespace):
+ cls = super().__new__(mcls, name, bases, namespace)
+ # Compute set of abstract method names
+ abstracts = {name
+ for name, value in namespace.items()
+ if getattr(value, "__isabstractmethod__", False)}
+ for base in bases:
+ for name in getattr(base, "__abstractmethods__", set()):
+ value = getattr(cls, name, None)
+ if getattr(value, "__isabstractmethod__", False):
+ abstracts.add(name)
+ cls.__abstractmethods__ = frozenset(abstracts)
+ # Set up inheritance registry
+ cls._abc_registry = WeakSet()
+ cls._abc_cache = WeakSet()
+ cls._abc_negative_cache = WeakSet()
+ cls._abc_negative_cache_version = ABCMeta._abc_invalidation_counter
+ return cls
+
+ def register(cls, subclass):
+ """Register a virtual subclass of an ABC."""
+ if not isinstance(subclass, type):
+ raise TypeError("Can only register classes")
+ if issubclass(subclass, cls):
+ return # Already a subclass
+ # Subtle: test for cycles *after* testing for "already a subclass";
+ # this means we allow X.register(X) and interpret it as a no-op.
+ if issubclass(cls, subclass):
+ # This would create a cycle, which is bad for the algorithm below
+ raise RuntimeError("Refusing to create an inheritance cycle")
+ cls._abc_registry.add(subclass)
+ ABCMeta._abc_invalidation_counter += 1 # Invalidate negative cache
+
+ def _dump_registry(cls, file=None):
+ """Debug helper to print the ABC registry."""
+ print("Class: %s.%s" % (cls.__module__, cls.__name__), file=file)
+ print("Inv.counter: %s" % ABCMeta._abc_invalidation_counter, file=file)
+ for name in sorted(cls.__dict__.keys()):
+ if name.startswith("_abc_"):
+ value = getattr(cls, name)
+ print("%s: %r" % (name, value), file=file)
+
+ def __instancecheck__(cls, instance):
+ """Override for isinstance(instance, cls)."""
+ # Inline the cache checking
+ subclass = instance.__class__
+ if subclass in cls._abc_cache:
+ return True
+ subtype = type(instance)
+ if subtype is subclass:
+ if (cls._abc_negative_cache_version ==
+ ABCMeta._abc_invalidation_counter and
+ subclass in cls._abc_negative_cache):
+ return False
+ # Fall back to the subclass check.
+ return cls.__subclasscheck__(subclass)
+ return any(cls.__subclasscheck__(c) for c in {subclass, subtype})
+
+ def __subclasscheck__(cls, subclass):
+ """Override for issubclass(subclass, cls)."""
+ # Check cache
+ if subclass in cls._abc_cache:
+ return True
+ # Check negative cache; may have to invalidate
+ if cls._abc_negative_cache_version < ABCMeta._abc_invalidation_counter:
+ # Invalidate the negative cache
+ cls._abc_negative_cache = WeakSet()
+ cls._abc_negative_cache_version = ABCMeta._abc_invalidation_counter
+ elif subclass in cls._abc_negative_cache:
+ return False
+ # Check the subclass hook
+ ok = cls.__subclasshook__(subclass)
+ if ok is not NotImplemented:
+ assert isinstance(ok, bool)
+ if ok:
+ cls._abc_cache.add(subclass)
+ else:
+ cls._abc_negative_cache.add(subclass)
+ return ok
+ # Check if it's a direct subclass
+ if cls in getattr(subclass, '__mro__', ()):
+ cls._abc_cache.add(subclass)
+ return True
+ # Check if it's a subclass of a registered class (recursive)
+ for rcls in cls._abc_registry:
+ if issubclass(subclass, rcls):
+ cls._abc_cache.add(subclass)
+ return True
+ # Check if it's a subclass of a subclass (recursive)
+ for scls in cls.__subclasses__():
+ if issubclass(subclass, scls):
+ cls._abc_cache.add(subclass)
+ return True
+ # No dice; update negative cache
+ cls._abc_negative_cache.add(subclass)
+ return False
diff --git a/lib-python/3.2/aifc.py b/lib-python/3.2/aifc.py
new file mode 100644
--- /dev/null
+++ b/lib-python/3.2/aifc.py
@@ -0,0 +1,891 @@
+"""Stuff to parse AIFF-C and AIFF files.
+
+Unless explicitly stated otherwise, the description below is true
+both for AIFF-C files and AIFF files.
+
+An AIFF-C file has the following structure.
+
+ +-----------------+
+ | FORM |
+ +-----------------+
+ | <size> |
+ +----+------------+
+ | | AIFC |
+ | +------------+
+ | | <chunks> |
+ | | . |
+ | | . |
+ | | . |
+ +----+------------+
+
+An AIFF file has the string "AIFF" instead of "AIFC".
+
+A chunk consists of an identifier (4 bytes) followed by a size (4 bytes,
+big endian order), followed by the data. The size field does not include
+the size of the 8 byte header.
+
+The following chunk types are recognized.
+
+ FVER
+ <version number of AIFF-C defining document> (AIFF-C only).
+ MARK
+ <# of markers> (2 bytes)
+ list of markers:
+ <marker ID> (2 bytes, must be > 0)
+ <position> (4 bytes)
+ <marker name> ("pstring")
+ COMM
+ <# of channels> (2 bytes)
+ <# of sound frames> (4 bytes)
+ <size of the samples> (2 bytes)
+ <sampling frequency> (10 bytes, IEEE 80-bit extended
+ floating point)
+ in AIFF-C files only:
+ <compression type> (4 bytes)
+ <human-readable version of compression type> ("pstring")
+ SSND
+ <offset> (4 bytes, not used by this program)
+ <blocksize> (4 bytes, not used by this program)
+ <sound data>
+
+A pstring consists of 1 byte length, a string of characters, and 0 or 1
+byte pad to make the total length even.
+
+Usage.
+
+Reading AIFF files:
+ f = aifc.open(file, 'r')
+where file is either the name of a file or an open file pointer.
+The open file pointer must have methods read(), seek(), and close().
+In some types of audio files, if the setpos() method is not used,
+the seek() method is not necessary.
+
+This returns an instance of a class with the following public methods:
+ getnchannels() -- returns number of audio channels (1 for
+ mono, 2 for stereo)
+ getsampwidth() -- returns sample width in bytes
+ getframerate() -- returns sampling frequency
+ getnframes() -- returns number of audio frames
+ getcomptype() -- returns compression type ('NONE' for AIFF files)
+ getcompname() -- returns human-readable version of
+ compression type ('not compressed' for AIFF files)
+ getparams() -- returns a tuple consisting of all of the
+ above in the above order
+ getmarkers() -- get the list of marks in the audio file or None
+ if there are no marks
+ getmark(id) -- get mark with the specified id (raises an error
+ if the mark does not exist)
+ readframes(n) -- returns at most n frames of audio
+ rewind() -- rewind to the beginning of the audio stream
+ setpos(pos) -- seek to the specified position
+ tell() -- return the current position
+ close() -- close the instance (make it unusable)
+The position returned by tell(), the position given to setpos() and
+the position of marks are all compatible and have nothing to do with
+the actual position in the file.
+The close() method is called automatically when the class instance
+is destroyed.
+
+Writing AIFF files:
+ f = aifc.open(file, 'w')
+where file is either the name of a file or an open file pointer.
+The open file pointer must have methods write(), tell(), seek(), and
+close().
+
+This returns an instance of a class with the following public methods:
+ aiff() -- create an AIFF file (AIFF-C default)
+ aifc() -- create an AIFF-C file
+ setnchannels(n) -- set the number of channels
+ setsampwidth(n) -- set the sample width
+ setframerate(n) -- set the frame rate
+ setnframes(n) -- set the number of frames
+ setcomptype(type, name)
+ -- set the compression type and the
+ human-readable compression type
+ setparams(tuple)
+ -- set all parameters at once
+ setmark(id, pos, name)
+ -- add specified mark to the list of marks
+ tell() -- return current position in output file (useful
+ in combination with setmark())
+ writeframesraw(data)
+ -- write audio frames without pathing up the
+ file header
+ writeframes(data)
+ -- write audio frames and patch up the file header
+ close() -- patch up the file header and close the
+ output file
+You should set the parameters before the first writeframesraw or
+writeframes. The total number of frames does not need to be set,
+but when it is set to the correct value, the header does not have to
+be patched up.
+It is best to first set all parameters, perhaps possibly the
+compression type, and then write audio frames using writeframesraw.
+When all frames have been written, either call writeframes('') or
+close() to patch up the sizes in the header.
+Marks can be added anytime. If there are any marks, ypu must call
+close() after all frames have been written.
+The close() method is called automatically when the class instance
+is destroyed.
+
+When a file is opened with the extension '.aiff', an AIFF file is
+written, otherwise an AIFF-C file is written. This default can be
+changed by calling aiff() or aifc() before the first writeframes or
+writeframesraw.
+"""
+
+import struct
+import builtins
+
+__all__ = ["Error", "open", "openfp"]
+
+class Error(Exception):
+ pass
+
+_AIFC_version = 0xA2805140 # Version 1 of AIFF-C
+
+def _read_long(file):
+ try:
+ return struct.unpack('>l', file.read(4))[0]
+ except struct.error:
+ raise EOFError
+
+def _read_ulong(file):
+ try:
+ return struct.unpack('>L', file.read(4))[0]
+ except struct.error:
+ raise EOFError
+
+def _read_short(file):
+ try:
+ return struct.unpack('>h', file.read(2))[0]
+ except struct.error:
+ raise EOFError
+
+def _read_ushort(file):
+ try:
+ return struct.unpack('>H', file.read(2))[0]
+ except struct.error:
+ raise EOFError
+
+def _read_string(file):
+ length = ord(file.read(1))
+ if length == 0:
+ data = b''
+ else:
+ data = file.read(length)
+ if length & 1 == 0:
+ dummy = file.read(1)
+ return data
+
+_HUGE_VAL = 1.79769313486231e+308 # See <limits.h>
+
+def _read_float(f): # 10 bytes
+ expon = _read_short(f) # 2 bytes
+ sign = 1
+ if expon < 0:
+ sign = -1
+ expon = expon + 0x8000
+ himant = _read_ulong(f) # 4 bytes
+ lomant = _read_ulong(f) # 4 bytes
+ if expon == himant == lomant == 0:
+ f = 0.0
+ elif expon == 0x7FFF:
+ f = _HUGE_VAL
+ else:
+ expon = expon - 16383
+ f = (himant * 0x100000000 + lomant) * pow(2.0, expon - 63)
+ return sign * f
+
+def _write_short(f, x):
+ f.write(struct.pack('>h', x))
+
+def _write_ushort(f, x):
+ f.write(struct.pack('>H', x))
+
+def _write_long(f, x):
+ f.write(struct.pack('>l', x))
+
+def _write_ulong(f, x):
+ f.write(struct.pack('>L', x))
+
+def _write_string(f, s):
+ if len(s) > 255:
+ raise ValueError("string exceeds maximum pstring length")
+ f.write(struct.pack('B', len(s)))
+ f.write(s)
+ if len(s) & 1 == 0:
+ f.write(b'\x00')
+
+def _write_float(f, x):
+ import math
+ if x < 0:
+ sign = 0x8000
+ x = x * -1
+ else:
+ sign = 0
+ if x == 0:
+ expon = 0
+ himant = 0
+ lomant = 0
+ else:
+ fmant, expon = math.frexp(x)
+ if expon > 16384 or fmant >= 1 or fmant != fmant: # Infinity or NaN
+ expon = sign|0x7FFF
+ himant = 0
+ lomant = 0
+ else: # Finite
+ expon = expon + 16382
+ if expon < 0: # denormalized
+ fmant = math.ldexp(fmant, expon)
+ expon = 0
+ expon = expon | sign
+ fmant = math.ldexp(fmant, 32)
+ fsmant = math.floor(fmant)
+ himant = int(fsmant)
+ fmant = math.ldexp(fmant - fsmant, 32)
+ fsmant = math.floor(fmant)
+ lomant = int(fsmant)
+ _write_ushort(f, expon)
+ _write_ulong(f, himant)
+ _write_ulong(f, lomant)
+
+from chunk import Chunk
+
+class Aifc_read:
+ # Variables used in this class:
+ #
+ # These variables are available to the user though appropriate
+ # methods of this class:
+ # _file -- the open file with methods read(), close(), and seek()
+ # set through the __init__() method
+ # _nchannels -- the number of audio channels
+ # available through the getnchannels() method
+ # _nframes -- the number of audio frames
+ # available through the getnframes() method
+ # _sampwidth -- the number of bytes per audio sample
+ # available through the getsampwidth() method
+ # _framerate -- the sampling frequency
+ # available through the getframerate() method
+ # _comptype -- the AIFF-C compression type ('NONE' if AIFF)
+ # available through the getcomptype() method
+ # _compname -- the human-readable AIFF-C compression type
+ # available through the getcomptype() method
+ # _markers -- the marks in the audio file
+ # available through the getmarkers() and getmark()
+ # methods
+ # _soundpos -- the position in the audio stream
+ # available through the tell() method, set through the
+ # setpos() method
+ #
+ # These variables are used internally only:
+ # _version -- the AIFF-C version number
+ # _decomp -- the decompressor from builtin module cl
+ # _comm_chunk_read -- 1 iff the COMM chunk has been read
+ # _aifc -- 1 iff reading an AIFF-C file
+ # _ssnd_seek_needed -- 1 iff positioned correctly in audio
+ # file for readframes()
+ # _ssnd_chunk -- instantiation of a chunk class for the SSND chunk
+ # _framesize -- size of one frame in the file
+
+ def initfp(self, file):
+ self._version = 0
+ self._convert = None
+ self._markers = []
+ self._soundpos = 0
+ self._file = file
+ chunk = Chunk(file)
+ if chunk.getname() != b'FORM':
+ raise Error('file does not start with FORM id')
+ formdata = chunk.read(4)
+ if formdata == b'AIFF':
+ self._aifc = 0
+ elif formdata == b'AIFC':
+ self._aifc = 1
+ else:
+ raise Error('not an AIFF or AIFF-C file')
+ self._comm_chunk_read = 0
+ while 1:
+ self._ssnd_seek_needed = 1
+ try:
+ chunk = Chunk(self._file)
+ except EOFError:
+ break
+ chunkname = chunk.getname()
+ if chunkname == b'COMM':
+ self._read_comm_chunk(chunk)
+ self._comm_chunk_read = 1
+ elif chunkname == b'SSND':
+ self._ssnd_chunk = chunk
+ dummy = chunk.read(8)
+ self._ssnd_seek_needed = 0
+ elif chunkname == b'FVER':
+ self._version = _read_ulong(chunk)
+ elif chunkname == b'MARK':
+ self._readmark(chunk)
+ chunk.skip()
+ if not self._comm_chunk_read or not self._ssnd_chunk:
+ raise Error('COMM chunk and/or SSND chunk missing')
+
+ def __init__(self, f):
+ if isinstance(f, str):
+ f = builtins.open(f, 'rb')
+ # else, assume it is an open file object already
+ self.initfp(f)
+
+ #
+ # User visible methods.
+ #
+ def getfp(self):
+ return self._file
+
+ def rewind(self):
+ self._ssnd_seek_needed = 1
+ self._soundpos = 0
+
+ def close(self):
+ self._file.close()
+
+ def tell(self):
+ return self._soundpos
+
+ def getnchannels(self):
+ return self._nchannels
+
+ def getnframes(self):
+ return self._nframes
+
+ def getsampwidth(self):
+ return self._sampwidth
+
+ def getframerate(self):
+ return self._framerate
+
+ def getcomptype(self):
+ return self._comptype
+
+ def getcompname(self):
+ return self._compname
+
+## def getversion(self):
+## return self._version
+
+ def getparams(self):
+ return self.getnchannels(), self.getsampwidth(), \
+ self.getframerate(), self.getnframes(), \
+ self.getcomptype(), self.getcompname()
+
+ def getmarkers(self):
+ if len(self._markers) == 0:
+ return None
+ return self._markers
+
+ def getmark(self, id):
+ for marker in self._markers:
+ if id == marker[0]:
+ return marker
+ raise Error('marker {0!r} does not exist'.format(id))
+
+ def setpos(self, pos):
+ if pos < 0 or pos > self._nframes:
+ raise Error('position not in range')
+ self._soundpos = pos
+ self._ssnd_seek_needed = 1
+
+ def readframes(self, nframes):
+ if self._ssnd_seek_needed:
+ self._ssnd_chunk.seek(0)
+ dummy = self._ssnd_chunk.read(8)
+ pos = self._soundpos * self._framesize
+ if pos:
+ self._ssnd_chunk.seek(pos + 8)
+ self._ssnd_seek_needed = 0
+ if nframes == 0:
+ return b''
+ data = self._ssnd_chunk.read(nframes * self._framesize)
+ if self._convert and data:
+ data = self._convert(data)
+ self._soundpos = self._soundpos + len(data) // (self._nchannels
+ * self._sampwidth)
+ return data
+
+ #
+ # Internal methods.
+ #
+
+ def _alaw2lin(self, data):
+ import audioop
+ return audioop.alaw2lin(data, 2)
+
+ def _ulaw2lin(self, data):
+ import audioop
+ return audioop.ulaw2lin(data, 2)
+
+ def _adpcm2lin(self, data):
+ import audioop
+ if not hasattr(self, '_adpcmstate'):
+ # first time
+ self._adpcmstate = None
+ data, self._adpcmstate = audioop.adpcm2lin(data, 2, self._adpcmstate)
+ return data
+
+ def _read_comm_chunk(self, chunk):
+ self._nchannels = _read_short(chunk)
+ self._nframes = _read_long(chunk)
+ self._sampwidth = (_read_short(chunk) + 7) // 8
+ self._framerate = int(_read_float(chunk))
+ self._framesize = self._nchannels * self._sampwidth
+ if self._aifc:
+ #DEBUG: SGI's soundeditor produces a bad size :-(
+ kludge = 0
+ if chunk.chunksize == 18:
+ kludge = 1
+ print('Warning: bad COMM chunk size')
+ chunk.chunksize = 23
+ #DEBUG end
+ self._comptype = chunk.read(4)
+ #DEBUG start
+ if kludge:
+ length = ord(chunk.file.read(1))
+ if length & 1 == 0:
+ length = length + 1
+ chunk.chunksize = chunk.chunksize + length
+ chunk.file.seek(-1, 1)
+ #DEBUG end
+ self._compname = _read_string(chunk)
+ if self._comptype != b'NONE':
+ if self._comptype == b'G722':
+ self._convert = self._adpcm2lin
+ self._framesize = self._framesize // 4
+ elif self._comptype in (b'ulaw', b'ULAW'):
+ self._convert = self._ulaw2lin
+ self._framesize = self._framesize // 2
+ elif self._comptype in (b'alaw', b'ALAW'):
+ self._convert = self._alaw2lin
+ self._framesize = self._framesize // 2
+ else:
+ raise Error('unsupported compression type')
+ else:
+ self._comptype = b'NONE'
+ self._compname = b'not compressed'
+
+ def _readmark(self, chunk):
+ nmarkers = _read_short(chunk)
+ # Some files appear to contain invalid counts.
+ # Cope with this by testing for EOF.
+ try:
+ for i in range(nmarkers):
+ id = _read_short(chunk)
+ pos = _read_long(chunk)
+ name = _read_string(chunk)
+ if pos or name:
+ # some files appear to have
+ # dummy markers consisting of
+ # a position 0 and name ''
+ self._markers.append((id, pos, name))
+ except EOFError:
+ print('Warning: MARK chunk contains only', end=' ')
+ print(len(self._markers), end=' ')
+ if len(self._markers) == 1: print('marker', end=' ')
+ else: print('markers', end=' ')
+ print('instead of', nmarkers)
+
+class Aifc_write:
+ # Variables used in this class:
+ #
+ # These variables are user settable through appropriate methods
+ # of this class:
+ # _file -- the open file with methods write(), close(), tell(), seek()
+ # set through the __init__() method
+ # _comptype -- the AIFF-C compression type ('NONE' in AIFF)
+ # set through the setcomptype() or setparams() method
+ # _compname -- the human-readable AIFF-C compression type
+ # set through the setcomptype() or setparams() method
+ # _nchannels -- the number of audio channels
+ # set through the setnchannels() or setparams() method
+ # _sampwidth -- the number of bytes per audio sample
+ # set through the setsampwidth() or setparams() method
+ # _framerate -- the sampling frequency
+ # set through the setframerate() or setparams() method
+ # _nframes -- the number of audio frames written to the header
+ # set through the setnframes() or setparams() method
+ # _aifc -- whether we're writing an AIFF-C file or an AIFF file
+ # set through the aifc() method, reset through the
+ # aiff() method
+ #
+ # These variables are used internally only:
+ # _version -- the AIFF-C version number
+ # _comp -- the compressor from builtin module cl
+ # _nframeswritten -- the number of audio frames actually written
+ # _datalength -- the size of the audio samples written to the header
+ # _datawritten -- the size of the audio samples actually written
+
+ def __init__(self, f):
+ if isinstance(f, str):
+ filename = f
+ f = builtins.open(f, 'wb')
+ else:
+ # else, assume it is an open file object already
+ filename = '???'
+ self.initfp(f)
+ if filename[-5:] == '.aiff':
+ self._aifc = 0
+ else:
+ self._aifc = 1
+
+ def initfp(self, file):
+ self._file = file
+ self._version = _AIFC_version
+ self._comptype = b'NONE'
+ self._compname = b'not compressed'
+ self._convert = None
+ self._nchannels = 0
+ self._sampwidth = 0
+ self._framerate = 0
+ self._nframes = 0
+ self._nframeswritten = 0
+ self._datawritten = 0
+ self._datalength = 0
+ self._markers = []
+ self._marklength = 0
+ self._aifc = 1 # AIFF-C is default
+
+ def __del__(self):
+ self.close()
+
+ #
+ # User visible methods.
+ #
+ def aiff(self):
+ if self._nframeswritten:
+ raise Error('cannot change parameters after starting to write')
+ self._aifc = 0
+
+ def aifc(self):
+ if self._nframeswritten:
+ raise Error('cannot change parameters after starting to write')
+ self._aifc = 1
+
+ def setnchannels(self, nchannels):
+ if self._nframeswritten:
+ raise Error('cannot change parameters after starting to write')
+ if nchannels < 1:
+ raise Error('bad # of channels')
+ self._nchannels = nchannels
+
+ def getnchannels(self):
+ if not self._nchannels:
+ raise Error('number of channels not set')
+ return self._nchannels
+
+ def setsampwidth(self, sampwidth):
+ if self._nframeswritten:
+ raise Error('cannot change parameters after starting to write')
+ if sampwidth < 1 or sampwidth > 4:
+ raise Error('bad sample width')
+ self._sampwidth = sampwidth
+
+ def getsampwidth(self):
+ if not self._sampwidth:
+ raise Error('sample width not set')
+ return self._sampwidth
+
+ def setframerate(self, framerate):
+ if self._nframeswritten:
+ raise Error('cannot change parameters after starting to write')
+ if framerate <= 0:
+ raise Error('bad frame rate')
+ self._framerate = framerate
+
+ def getframerate(self):
+ if not self._framerate:
+ raise Error('frame rate not set')
+ return self._framerate
+
+ def setnframes(self, nframes):
+ if self._nframeswritten:
+ raise Error('cannot change parameters after starting to write')
+ self._nframes = nframes
+
+ def getnframes(self):
+ return self._nframeswritten
+
+ def setcomptype(self, comptype, compname):
+ if self._nframeswritten:
+ raise Error('cannot change parameters after starting to write')
+ if comptype not in (b'NONE', b'ulaw', b'ULAW',
+ b'alaw', b'ALAW', b'G722'):
+ raise Error('unsupported compression type')
+ self._comptype = comptype
+ self._compname = compname
+
+ def getcomptype(self):
+ return self._comptype
+
+ def getcompname(self):
+ return self._compname
+
+## def setversion(self, version):
+## if self._nframeswritten:
+## raise Error, 'cannot change parameters after starting to write'
+## self._version = version
+
+ def setparams(self, params):
+ nchannels, sampwidth, framerate, nframes, comptype, compname = params
+ if self._nframeswritten:
+ raise Error('cannot change parameters after starting to write')
+ if comptype not in (b'NONE', b'ulaw', b'ULAW',
+ b'alaw', b'ALAW', b'G722'):
+ raise Error('unsupported compression type')
+ self.setnchannels(nchannels)
+ self.setsampwidth(sampwidth)
+ self.setframerate(framerate)
+ self.setnframes(nframes)
+ self.setcomptype(comptype, compname)
+
+ def getparams(self):
+ if not self._nchannels or not self._sampwidth or not self._framerate:
+ raise Error('not all parameters set')
+ return self._nchannels, self._sampwidth, self._framerate, \
+ self._nframes, self._comptype, self._compname
+
+ def setmark(self, id, pos, name):
+ if id <= 0:
+ raise Error('marker ID must be > 0')
+ if pos < 0:
+ raise Error('marker position must be >= 0')
+ if not isinstance(name, bytes):
+ raise Error('marker name must be bytes')
+ for i in range(len(self._markers)):
+ if id == self._markers[i][0]:
+ self._markers[i] = id, pos, name
+ return
+ self._markers.append((id, pos, name))
+
+ def getmark(self, id):
+ for marker in self._markers:
+ if id == marker[0]:
+ return marker
+ raise Error('marker {0!r} does not exist'.format(id))
+
+ def getmarkers(self):
+ if len(self._markers) == 0:
+ return None
+ return self._markers
+
+ def tell(self):
+ return self._nframeswritten
+
+ def writeframesraw(self, data):
+ self._ensure_header_written(len(data))
+ nframes = len(data) // (self._sampwidth * self._nchannels)
+ if self._convert:
+ data = self._convert(data)
+ self._file.write(data)
+ self._nframeswritten = self._nframeswritten + nframes
+ self._datawritten = self._datawritten + len(data)
+
+ def writeframes(self, data):
+ self.writeframesraw(data)
+ if self._nframeswritten != self._nframes or \
+ self._datalength != self._datawritten:
+ self._patchheader()
+
+ def close(self):
+ if self._file:
+ self._ensure_header_written(0)
+ if self._datawritten & 1:
+ # quick pad to even size
+ self._file.write(b'\x00')
+ self._datawritten = self._datawritten + 1
+ self._writemarkers()
+ if self._nframeswritten != self._nframes or \
+ self._datalength != self._datawritten or \
+ self._marklength:
+ self._patchheader()
+ # Prevent ref cycles
+ self._convert = None
+ self._file.close()
+ self._file = None
+
+ #
+ # Internal methods.
+ #
+
+ def _lin2alaw(self, data):
+ import audioop
+ return audioop.lin2alaw(data, 2)
+
+ def _lin2ulaw(self, data):
+ import audioop
+ return audioop.lin2ulaw(data, 2)
+
+ def _lin2adpcm(self, data):
+ import audioop
+ if not hasattr(self, '_adpcmstate'):
+ self._adpcmstate = None
+ data, self._adpcmstate = audioop.lin2adpcm(data, 2, self._adpcmstate)
+ return data
+
+ def _ensure_header_written(self, datasize):
+ if not self._nframeswritten:
+ if self._comptype in (b'ULAW', b'ulaw', b'ALAW', b'alaw', b'G722'):
+ if not self._sampwidth:
+ self._sampwidth = 2
+ if self._sampwidth != 2:
+ raise Error('sample width must be 2 when compressing '
+ 'with ulaw/ULAW, alaw/ALAW or G7.22 (ADPCM)')
+ if not self._nchannels:
+ raise Error('# channels not specified')
+ if not self._sampwidth:
+ raise Error('sample width not specified')
+ if not self._framerate:
+ raise Error('sampling rate not specified')
+ self._write_header(datasize)
+
+ def _init_compression(self):
+ if self._comptype == b'G722':
+ self._convert = self._lin2adpcm
+ elif self._comptype in (b'ulaw', b'ULAW'):
+ self._convert = self._lin2ulaw
+ elif self._comptype in (b'alaw', b'ALAW'):
+ self._convert = self._lin2alaw
+
+ def _write_header(self, initlength):
+ if self._aifc and self._comptype != b'NONE':
+ self._init_compression()
+ self._file.write(b'FORM')
+ if not self._nframes:
+ self._nframes = initlength // (self._nchannels * self._sampwidth)
+ self._datalength = self._nframes * self._nchannels * self._sampwidth
+ if self._datalength & 1:
+ self._datalength = self._datalength + 1
+ if self._aifc:
+ if self._comptype in (b'ulaw', b'ULAW', b'alaw', b'ALAW'):
+ self._datalength = self._datalength // 2
+ if self._datalength & 1:
+ self._datalength = self._datalength + 1
+ elif self._comptype == b'G722':
+ self._datalength = (self._datalength + 3) // 4
+ if self._datalength & 1:
+ self._datalength = self._datalength + 1
+ self._form_length_pos = self._file.tell()
+ commlength = self._write_form_length(self._datalength)
+ if self._aifc:
+ self._file.write(b'AIFC')
+ self._file.write(b'FVER')
+ _write_ulong(self._file, 4)
+ _write_ulong(self._file, self._version)
+ else:
+ self._file.write(b'AIFF')
+ self._file.write(b'COMM')
+ _write_ulong(self._file, commlength)
+ _write_short(self._file, self._nchannels)
+ self._nframes_pos = self._file.tell()
+ _write_ulong(self._file, self._nframes)
+ _write_short(self._file, self._sampwidth * 8)
+ _write_float(self._file, self._framerate)
+ if self._aifc:
+ self._file.write(self._comptype)
+ _write_string(self._file, self._compname)
+ self._file.write(b'SSND')
+ self._ssnd_length_pos = self._file.tell()
+ _write_ulong(self._file, self._datalength + 8)
+ _write_ulong(self._file, 0)
+ _write_ulong(self._file, 0)
+
+ def _write_form_length(self, datalength):
+ if self._aifc:
+ commlength = 18 + 5 + len(self._compname)
+ if commlength & 1:
+ commlength = commlength + 1
+ verslength = 12
+ else:
+ commlength = 18
+ verslength = 0
+ _write_ulong(self._file, 4 + verslength + self._marklength + \
+ 8 + commlength + 16 + datalength)
+ return commlength
+
+ def _patchheader(self):
+ curpos = self._file.tell()
+ if self._datawritten & 1:
+ datalength = self._datawritten + 1
+ self._file.write(b'\x00')
+ else:
+ datalength = self._datawritten
+ if datalength == self._datalength and \
+ self._nframes == self._nframeswritten and \
+ self._marklength == 0:
+ self._file.seek(curpos, 0)
+ return
+ self._file.seek(self._form_length_pos, 0)
+ dummy = self._write_form_length(datalength)
+ self._file.seek(self._nframes_pos, 0)
+ _write_ulong(self._file, self._nframeswritten)
+ self._file.seek(self._ssnd_length_pos, 0)
+ _write_ulong(self._file, datalength + 8)
+ self._file.seek(curpos, 0)
+ self._nframes = self._nframeswritten
+ self._datalength = datalength
+
+ def _writemarkers(self):
+ if len(self._markers) == 0:
+ return
+ self._file.write(b'MARK')
+ length = 2
+ for marker in self._markers:
+ id, pos, name = marker
+ length = length + len(name) + 1 + 6
+ if len(name) & 1 == 0:
+ length = length + 1
+ _write_ulong(self._file, length)
+ self._marklength = length + 8
+ _write_short(self._file, len(self._markers))
+ for marker in self._markers:
+ id, pos, name = marker
+ _write_short(self._file, id)
+ _write_ulong(self._file, pos)
+ _write_string(self._file, name)
+
+def open(f, mode=None):
+ if mode is None:
+ if hasattr(f, 'mode'):
+ mode = f.mode
+ else:
+ mode = 'rb'
+ if mode in ('r', 'rb'):
+ return Aifc_read(f)
+ elif mode in ('w', 'wb'):
+ return Aifc_write(f)
+ else:
+ raise Error("mode must be 'r', 'rb', 'w', or 'wb'")
+
+openfp = open # B/W compatibility
+
+if __name__ == '__main__':
+ import sys
+ if not sys.argv[1:]:
+ sys.argv.append('/usr/demos/data/audio/bach.aiff')
+ fn = sys.argv[1]
+ f = open(fn, 'r')
+ print("Reading", fn)
+ print("nchannels =", f.getnchannels())
+ print("nframes =", f.getnframes())
+ print("sampwidth =", f.getsampwidth())
+ print("framerate =", f.getframerate())
+ print("comptype =", f.getcomptype())
+ print("compname =", f.getcompname())
+ if sys.argv[2:]:
+ gn = sys.argv[2]
+ print("Writing", gn)
+ g = open(gn, 'w')
+ g.setparams(f.getparams())
+ while 1:
+ data = f.readframes(1024)
+ if not data:
+ break
+ g.writeframes(data)
+ g.close()
+ f.close()
+ print("Done.")
diff --git a/lib-python/3.2/antigravity.py b/lib-python/3.2/antigravity.py
new file mode 100644
--- /dev/null
+++ b/lib-python/3.2/antigravity.py
@@ -0,0 +1,17 @@
+
+import webbrowser
+import hashlib
+
+webbrowser.open("http://xkcd.com/353/")
+
+def geohash(latitude, longitude, datedow):
+ '''Compute geohash() using the Munroe algorithm.
+
+ >>> geohash(37.421542, -122.085589, b'2005-05-26-10458.68')
+ 37.857713 -122.544543
+
+ '''
+ # http://xkcd.com/426/
+ h = hashlib.md5(datedow).hexdigest()
+ p, q = [('%f' % float.fromhex('0.' + x)) for x in (h[:16], h[16:32])]
+ print('%d%s %d%s' % (latitude, p[1:], longitude, q[1:]))
diff --git a/lib-python/3.2/argparse.py b/lib-python/3.2/argparse.py
new file mode 100644
--- /dev/null
+++ b/lib-python/3.2/argparse.py
@@ -0,0 +1,2362 @@
+# Author: Steven J. Bethard <steven.bethard at gmail.com>.
+
+"""Command-line parsing library
+
+This module is an optparse-inspired command-line parsing library that:
+
+ - handles both optional and positional arguments
+ - produces highly informative usage messages
+ - supports parsers that dispatch to sub-parsers
+
+The following is a simple usage example that sums integers from the
+command-line and writes the result to a file::
+
+ parser = argparse.ArgumentParser(
+ description='sum the integers at the command line')
+ parser.add_argument(
+ 'integers', metavar='int', nargs='+', type=int,
+ help='an integer to be summed')
+ parser.add_argument(
+ '--log', default=sys.stdout, type=argparse.FileType('w'),
+ help='the file where the sum should be written')
+ args = parser.parse_args()
+ args.log.write('%s' % sum(args.integers))
+ args.log.close()
+
+The module contains the following public classes:
+
+ - ArgumentParser -- The main entry point for command-line parsing. As the
+ example above shows, the add_argument() method is used to populate
+ the parser with actions for optional and positional arguments. Then
+ the parse_args() method is invoked to convert the args at the
+ command-line into an object with attributes.
+
+ - ArgumentError -- The exception raised by ArgumentParser objects when
+ there are errors with the parser's actions. Errors raised while
+ parsing the command-line are caught by ArgumentParser and emitted
+ as command-line messages.
+
+ - FileType -- A factory for defining types of files to be created. As the
+ example above shows, instances of FileType are typically passed as
+ the type= argument of add_argument() calls.
+
+ - Action -- The base class for parser actions. Typically actions are
+ selected by passing strings like 'store_true' or 'append_const' to
+ the action= argument of add_argument(). However, for greater
+ customization of ArgumentParser actions, subclasses of Action may
+ be defined and passed as the action= argument.
+
+ - HelpFormatter, RawDescriptionHelpFormatter, RawTextHelpFormatter,
+ ArgumentDefaultsHelpFormatter -- Formatter classes which
+ may be passed as the formatter_class= argument to the
+ ArgumentParser constructor. HelpFormatter is the default,
+ RawDescriptionHelpFormatter and RawTextHelpFormatter tell the parser
+ not to change the formatting for help text, and
+ ArgumentDefaultsHelpFormatter adds information about argument defaults
+ to the help.
+
+All other classes in this module are considered implementation details.
+(Also note that HelpFormatter and RawDescriptionHelpFormatter are only
+considered public as object names -- the API of the formatter objects is
+still considered an implementation detail.)
+"""
+
+__version__ = '1.1'
+__all__ = [
+ 'ArgumentParser',
+ 'ArgumentError',
+ 'ArgumentTypeError',
+ 'FileType',
+ 'HelpFormatter',
+ 'ArgumentDefaultsHelpFormatter',
+ 'RawDescriptionHelpFormatter',
+ 'RawTextHelpFormatter',
+ 'Namespace',
+ 'Action',
+ 'ONE_OR_MORE',
+ 'OPTIONAL',
+ 'PARSER',
+ 'REMAINDER',
+ 'SUPPRESS',
+ 'ZERO_OR_MORE',
+]
+
+
+import collections as _collections
+import copy as _copy
+import os as _os
+import re as _re
+import sys as _sys
+import textwrap as _textwrap
+
+from gettext import gettext as _, ngettext
+
+
+SUPPRESS = '==SUPPRESS=='
+
+OPTIONAL = '?'
+ZERO_OR_MORE = '*'
+ONE_OR_MORE = '+'
+PARSER = 'A...'
+REMAINDER = '...'
+_UNRECOGNIZED_ARGS_ATTR = '_unrecognized_args'
+
+# =============================
+# Utility functions and classes
+# =============================
+
+class _AttributeHolder(object):
+ """Abstract base class that provides __repr__.
+
+ The __repr__ method returns a string in the format::
+ ClassName(attr=name, attr=name, ...)
+ The attributes are determined either by a class-level attribute,
+ '_kwarg_names', or by inspecting the instance __dict__.
+ """
+
+ def __repr__(self):
+ type_name = type(self).__name__
+ arg_strings = []
+ for arg in self._get_args():
+ arg_strings.append(repr(arg))
+ for name, value in self._get_kwargs():
+ arg_strings.append('%s=%r' % (name, value))
+ return '%s(%s)' % (type_name, ', '.join(arg_strings))
+
+ def _get_kwargs(self):
+ return sorted(self.__dict__.items())
+
+ def _get_args(self):
+ return []
+
+
+def _ensure_value(namespace, name, value):
+ if getattr(namespace, name, None) is None:
+ setattr(namespace, name, value)
+ return getattr(namespace, name)
+
+
+# ===============
+# Formatting Help
+# ===============
+
+class HelpFormatter(object):
+ """Formatter for generating usage messages and argument help strings.
+
+ Only the name of this class is considered a public API. All the methods
+ provided by the class are considered an implementation detail.
+ """
+
+ def __init__(self,
+ prog,
+ indent_increment=2,
+ max_help_position=24,
+ width=None):
+
+ # default setting for width
+ if width is None:
+ try:
+ width = int(_os.environ['COLUMNS'])
+ except (KeyError, ValueError):
+ width = 80
+ width -= 2
+
+ self._prog = prog
+ self._indent_increment = indent_increment
+ self._max_help_position = max_help_position
+ self._width = width
+
+ self._current_indent = 0
+ self._level = 0
+ self._action_max_length = 0
+
+ self._root_section = self._Section(self, None)
+ self._current_section = self._root_section
+
+ self._whitespace_matcher = _re.compile(r'\s+')
+ self._long_break_matcher = _re.compile(r'\n\n\n+')
+
+ # ===============================
+ # Section and indentation methods
+ # ===============================
+ def _indent(self):
+ self._current_indent += self._indent_increment
+ self._level += 1
+
+ def _dedent(self):
+ self._current_indent -= self._indent_increment
+ assert self._current_indent >= 0, 'Indent decreased below 0.'
+ self._level -= 1
+
+ class _Section(object):
+
+ def __init__(self, formatter, parent, heading=None):
+ self.formatter = formatter
+ self.parent = parent
+ self.heading = heading
+ self.items = []
+
+ def format_help(self):
+ # format the indented section
+ if self.parent is not None:
+ self.formatter._indent()
+ join = self.formatter._join_parts
+ for func, args in self.items:
+ func(*args)
+ item_help = join([func(*args) for func, args in self.items])
+ if self.parent is not None:
+ self.formatter._dedent()
+
+ # return nothing if the section was empty
+ if not item_help:
+ return ''
+
+ # add the heading if the section was non-empty
+ if self.heading is not SUPPRESS and self.heading is not None:
+ current_indent = self.formatter._current_indent
+ heading = '%*s%s:\n' % (current_indent, '', self.heading)
+ else:
+ heading = ''
+
+ # join the section-initial newline, the heading and the help
+ return join(['\n', heading, item_help, '\n'])
+
+ def _add_item(self, func, args):
+ self._current_section.items.append((func, args))
+
+ # ========================
+ # Message building methods
+ # ========================
+ def start_section(self, heading):
+ self._indent()
+ section = self._Section(self, self._current_section, heading)
+ self._add_item(section.format_help, [])
+ self._current_section = section
+
+ def end_section(self):
+ self._current_section = self._current_section.parent
+ self._dedent()
+
+ def add_text(self, text):
+ if text is not SUPPRESS and text is not None:
+ self._add_item(self._format_text, [text])
+
+ def add_usage(self, usage, actions, groups, prefix=None):
+ if usage is not SUPPRESS:
+ args = usage, actions, groups, prefix
+ self._add_item(self._format_usage, args)
+
+ def add_argument(self, action):
+ if action.help is not SUPPRESS:
+
+ # find all invocations
+ get_invocation = self._format_action_invocation
+ invocations = [get_invocation(action)]
+ for subaction in self._iter_indented_subactions(action):
+ invocations.append(get_invocation(subaction))
+
+ # update the maximum item length
+ invocation_length = max([len(s) for s in invocations])
+ action_length = invocation_length + self._current_indent
+ self._action_max_length = max(self._action_max_length,
+ action_length)
+
+ # add the item to the list
+ self._add_item(self._format_action, [action])
+
+ def add_arguments(self, actions):
+ for action in actions:
+ self.add_argument(action)
+
+ # =======================
+ # Help-formatting methods
+ # =======================
+ def format_help(self):
+ help = self._root_section.format_help()
+ if help:
+ help = self._long_break_matcher.sub('\n\n', help)
+ help = help.strip('\n') + '\n'
+ return help
+
+ def _join_parts(self, part_strings):
+ return ''.join([part
+ for part in part_strings
+ if part and part is not SUPPRESS])
+
+ def _format_usage(self, usage, actions, groups, prefix):
+ if prefix is None:
+ prefix = _('usage: ')
+
+ # if usage is specified, use that
+ if usage is not None:
+ usage = usage % dict(prog=self._prog)
+
+ # if no optionals or positionals are available, usage is just prog
+ elif usage is None and not actions:
+ usage = '%(prog)s' % dict(prog=self._prog)
+
+ # if optionals and positionals are available, calculate usage
+ elif usage is None:
+ prog = '%(prog)s' % dict(prog=self._prog)
+
+ # split optionals from positionals
+ optionals = []
+ positionals = []
+ for action in actions:
+ if action.option_strings:
+ optionals.append(action)
+ else:
+ positionals.append(action)
+
+ # build full usage string
+ format = self._format_actions_usage
+ action_usage = format(optionals + positionals, groups)
+ usage = ' '.join([s for s in [prog, action_usage] if s])
+
+ # wrap the usage parts if it's too long
+ text_width = self._width - self._current_indent
+ if len(prefix) + len(usage) > text_width:
+
+ # break usage into wrappable parts
+ part_regexp = r'\(.*?\)+|\[.*?\]+|\S+'
+ opt_usage = format(optionals, groups)
+ pos_usage = format(positionals, groups)
+ opt_parts = _re.findall(part_regexp, opt_usage)
+ pos_parts = _re.findall(part_regexp, pos_usage)
+ assert ' '.join(opt_parts) == opt_usage
+ assert ' '.join(pos_parts) == pos_usage
+
+ # helper for wrapping lines
+ def get_lines(parts, indent, prefix=None):
+ lines = []
+ line = []
+ if prefix is not None:
+ line_len = len(prefix) - 1
+ else:
+ line_len = len(indent) - 1
+ for part in parts:
+ if line_len + 1 + len(part) > text_width:
+ lines.append(indent + ' '.join(line))
+ line = []
+ line_len = len(indent) - 1
+ line.append(part)
+ line_len += len(part) + 1
+ if line:
+ lines.append(indent + ' '.join(line))
+ if prefix is not None:
+ lines[0] = lines[0][len(indent):]
+ return lines
+
+ # if prog is short, follow it with optionals or positionals
+ if len(prefix) + len(prog) <= 0.75 * text_width:
+ indent = ' ' * (len(prefix) + len(prog) + 1)
+ if opt_parts:
+ lines = get_lines([prog] + opt_parts, indent, prefix)
+ lines.extend(get_lines(pos_parts, indent))
+ elif pos_parts:
+ lines = get_lines([prog] + pos_parts, indent, prefix)
+ else:
+ lines = [prog]
+
+ # if prog is long, put it on its own line
+ else:
+ indent = ' ' * len(prefix)
+ parts = opt_parts + pos_parts
+ lines = get_lines(parts, indent)
+ if len(lines) > 1:
+ lines = []
+ lines.extend(get_lines(opt_parts, indent))
+ lines.extend(get_lines(pos_parts, indent))
+ lines = [prog] + lines
+
+ # join lines into usage
+ usage = '\n'.join(lines)
+
+ # prefix with 'usage:'
+ return '%s%s\n\n' % (prefix, usage)
+
+ def _format_actions_usage(self, actions, groups):
+ # find group indices and identify actions in groups
+ group_actions = set()
+ inserts = {}
+ for group in groups:
+ try:
+ start = actions.index(group._group_actions[0])
+ except ValueError:
+ continue
+ else:
+ end = start + len(group._group_actions)
+ if actions[start:end] == group._group_actions:
+ for action in group._group_actions:
+ group_actions.add(action)
+ if not group.required:
+ if start in inserts:
+ inserts[start] += ' ['
+ else:
+ inserts[start] = '['
+ inserts[end] = ']'
+ else:
+ if start in inserts:
+ inserts[start] += ' ('
+ else:
+ inserts[start] = '('
+ inserts[end] = ')'
+ for i in range(start + 1, end):
+ inserts[i] = '|'
+
+ # collect all actions format strings
+ parts = []
+ for i, action in enumerate(actions):
+
+ # suppressed arguments are marked with None
+ # remove | separators for suppressed arguments
+ if action.help is SUPPRESS:
+ parts.append(None)
+ if inserts.get(i) == '|':
+ inserts.pop(i)
+ elif inserts.get(i + 1) == '|':
+ inserts.pop(i + 1)
+
+ # produce all arg strings
+ elif not action.option_strings:
+ part = self._format_args(action, action.dest)
+
+ # if it's in a group, strip the outer []
+ if action in group_actions:
+ if part[0] == '[' and part[-1] == ']':
+ part = part[1:-1]
+
+ # add the action string to the list
+ parts.append(part)
+
+ # produce the first way to invoke the option in brackets
+ else:
+ option_string = action.option_strings[0]
+
+ # if the Optional doesn't take a value, format is:
+ # -s or --long
+ if action.nargs == 0:
+ part = '%s' % option_string
+
+ # if the Optional takes a value, format is:
+ # -s ARGS or --long ARGS
+ else:
+ default = action.dest.upper()
+ args_string = self._format_args(action, default)
+ part = '%s %s' % (option_string, args_string)
+
+ # make it look optional if it's not required or in a group
+ if not action.required and action not in group_actions:
+ part = '[%s]' % part
+
+ # add the action string to the list
+ parts.append(part)
+
+ # insert things at the necessary indices
+ for i in sorted(inserts, reverse=True):
+ parts[i:i] = [inserts[i]]
+
+ # join all the action items with spaces
+ text = ' '.join([item for item in parts if item is not None])
+
+ # clean up separators for mutually exclusive groups
+ open = r'[\[(]'
+ close = r'[\])]'
+ text = _re.sub(r'(%s) ' % open, r'\1', text)
+ text = _re.sub(r' (%s)' % close, r'\1', text)
+ text = _re.sub(r'%s *%s' % (open, close), r'', text)
+ text = _re.sub(r'\(([^|]*)\)', r'\1', text)
+ text = text.strip()
+
+ # return the text
+ return text
+
+ def _format_text(self, text):
+ if '%(prog)' in text:
+ text = text % dict(prog=self._prog)
+ text_width = self._width - self._current_indent
+ indent = ' ' * self._current_indent
+ return self._fill_text(text, text_width, indent) + '\n\n'
+
+ def _format_action(self, action):
+ # determine the required width and the entry label
+ help_position = min(self._action_max_length + 2,
+ self._max_help_position)
+ help_width = self._width - help_position
+ action_width = help_position - self._current_indent - 2
+ action_header = self._format_action_invocation(action)
+
+ # ho nelp; start on same line and add a final newline
+ if not action.help:
+ tup = self._current_indent, '', action_header
+ action_header = '%*s%s\n' % tup
+
+ # short action name; start on the same line and pad two spaces
+ elif len(action_header) <= action_width:
+ tup = self._current_indent, '', action_width, action_header
+ action_header = '%*s%-*s ' % tup
+ indent_first = 0
+
+ # long action name; start on the next line
+ else:
+ tup = self._current_indent, '', action_header
+ action_header = '%*s%s\n' % tup
+ indent_first = help_position
+
+ # collect the pieces of the action help
+ parts = [action_header]
+
+ # if there was help for the action, add lines of help text
+ if action.help:
+ help_text = self._expand_help(action)
+ help_lines = self._split_lines(help_text, help_width)
+ parts.append('%*s%s\n' % (indent_first, '', help_lines[0]))
+ for line in help_lines[1:]:
+ parts.append('%*s%s\n' % (help_position, '', line))
+
+ # or add a newline if the description doesn't end with one
+ elif not action_header.endswith('\n'):
+ parts.append('\n')
+
+ # if there are any sub-actions, add their help as well
+ for subaction in self._iter_indented_subactions(action):
+ parts.append(self._format_action(subaction))
+
+ # return a single string
+ return self._join_parts(parts)
+
+ def _format_action_invocation(self, action):
+ if not action.option_strings:
+ metavar, = self._metavar_formatter(action, action.dest)(1)
+ return metavar
+
+ else:
+ parts = []
+
+ # if the Optional doesn't take a value, format is:
+ # -s, --long
+ if action.nargs == 0:
+ parts.extend(action.option_strings)
+
+ # if the Optional takes a value, format is:
+ # -s ARGS, --long ARGS
+ else:
+ default = action.dest.upper()
+ args_string = self._format_args(action, default)
+ for option_string in action.option_strings:
+ parts.append('%s %s' % (option_string, args_string))
+
+ return ', '.join(parts)
+
+ def _metavar_formatter(self, action, default_metavar):
+ if action.metavar is not None:
+ result = action.metavar
+ elif action.choices is not None:
+ choice_strs = [str(choice) for choice in action.choices]
+ result = '{%s}' % ','.join(choice_strs)
+ else:
+ result = default_metavar
+
+ def format(tuple_size):
+ if isinstance(result, tuple):
+ return result
+ else:
+ return (result, ) * tuple_size
+ return format
+
+ def _format_args(self, action, default_metavar):
+ get_metavar = self._metavar_formatter(action, default_metavar)
+ if action.nargs is None:
+ result = '%s' % get_metavar(1)
+ elif action.nargs == OPTIONAL:
+ result = '[%s]' % get_metavar(1)
+ elif action.nargs == ZERO_OR_MORE:
+ result = '[%s [%s ...]]' % get_metavar(2)
+ elif action.nargs == ONE_OR_MORE:
+ result = '%s [%s ...]' % get_metavar(2)
+ elif action.nargs == REMAINDER:
+ result = '...'
+ elif action.nargs == PARSER:
+ result = '%s ...' % get_metavar(1)
+ else:
+ formats = ['%s' for _ in range(action.nargs)]
+ result = ' '.join(formats) % get_metavar(action.nargs)
+ return result
+
+ def _expand_help(self, action):
+ params = dict(vars(action), prog=self._prog)
+ for name in list(params):
+ if params[name] is SUPPRESS:
+ del params[name]
+ for name in list(params):
+ if hasattr(params[name], '__name__'):
+ params[name] = params[name].__name__
+ if params.get('choices') is not None:
+ choices_str = ', '.join([str(c) for c in params['choices']])
+ params['choices'] = choices_str
+ return self._get_help_string(action) % params
+
+ def _iter_indented_subactions(self, action):
+ try:
+ get_subactions = action._get_subactions
+ except AttributeError:
+ pass
+ else:
+ self._indent()
+ for subaction in get_subactions():
+ yield subaction
+ self._dedent()
+
+ def _split_lines(self, text, width):
+ text = self._whitespace_matcher.sub(' ', text).strip()
+ return _textwrap.wrap(text, width)
+
+ def _fill_text(self, text, width, indent):
+ text = self._whitespace_matcher.sub(' ', text).strip()
+ return _textwrap.fill(text, width, initial_indent=indent,
+ subsequent_indent=indent)
+
+ def _get_help_string(self, action):
+ return action.help
+
+
+class RawDescriptionHelpFormatter(HelpFormatter):
+ """Help message formatter which retains any formatting in descriptions.
+
+ Only the name of this class is considered a public API. All the methods
+ provided by the class are considered an implementation detail.
+ """
+
+ def _fill_text(self, text, width, indent):
+ return ''.join([indent + line for line in text.splitlines(True)])
+
+
+class RawTextHelpFormatter(RawDescriptionHelpFormatter):
+ """Help message formatter which retains formatting of all help text.
+
+ Only the name of this class is considered a public API. All the methods
+ provided by the class are considered an implementation detail.
+ """
+
+ def _split_lines(self, text, width):
+ return text.splitlines()
+
+
+class ArgumentDefaultsHelpFormatter(HelpFormatter):
+ """Help message formatter which adds default values to argument help.
+
+ Only the name of this class is considered a public API. All the methods
+ provided by the class are considered an implementation detail.
+ """
+
+ def _get_help_string(self, action):
+ help = action.help
+ if '%(default)' not in action.help:
+ if action.default is not SUPPRESS:
+ defaulting_nargs = [OPTIONAL, ZERO_OR_MORE]
+ if action.option_strings or action.nargs in defaulting_nargs:
+ help += ' (default: %(default)s)'
+ return help
+
+
+# =====================
+# Options and Arguments
+# =====================
+
+def _get_action_name(argument):
+ if argument is None:
+ return None
+ elif argument.option_strings:
+ return '/'.join(argument.option_strings)
+ elif argument.metavar not in (None, SUPPRESS):
+ return argument.metavar
+ elif argument.dest not in (None, SUPPRESS):
+ return argument.dest
+ else:
+ return None
+
+
+class ArgumentError(Exception):
+ """An error from creating or using an argument (optional or positional).
+
+ The string value of this exception is the message, augmented with
+ information about the argument that caused it.
+ """
+
+ def __init__(self, argument, message):
+ self.argument_name = _get_action_name(argument)
+ self.message = message
+
+ def __str__(self):
+ if self.argument_name is None:
+ format = '%(message)s'
+ else:
+ format = 'argument %(argument_name)s: %(message)s'
+ return format % dict(message=self.message,
+ argument_name=self.argument_name)
+
+
+class ArgumentTypeError(Exception):
+ """An error from trying to convert a command line string to a type."""
+ pass
+
+
+# ==============
+# Action classes
+# ==============
+
+class Action(_AttributeHolder):
+ """Information about how to convert command line strings to Python objects.
+
+ Action objects are used by an ArgumentParser to represent the information
+ needed to parse a single argument from one or more strings from the
+ command line. The keyword arguments to the Action constructor are also
+ all attributes of Action instances.
+
+ Keyword Arguments:
+
+ - option_strings -- A list of command-line option strings which
+ should be associated with this action.
+
+ - dest -- The name of the attribute to hold the created object(s)
+
+ - nargs -- The number of command-line arguments that should be
+ consumed. By default, one argument will be consumed and a single
+ value will be produced. Other values include:
+ - N (an integer) consumes N arguments (and produces a list)
+ - '?' consumes zero or one arguments
+ - '*' consumes zero or more arguments (and produces a list)
+ - '+' consumes one or more arguments (and produces a list)
+ Note that the difference between the default and nargs=1 is that
+ with the default, a single value will be produced, while with
+ nargs=1, a list containing a single value will be produced.
+
+ - const -- The value to be produced if the option is specified and the
+ option uses an action that takes no values.
+
+ - default -- The value to be produced if the option is not specified.
+
+ - type -- The type which the command-line arguments should be converted
+ to, should be one of 'string', 'int', 'float', 'complex' or a
+ callable object that accepts a single string argument. If None,
+ 'string' is assumed.
+
+ - choices -- A container of values that should be allowed. If not None,
+ after a command-line argument has been converted to the appropriate
+ type, an exception will be raised if it is not a member of this
+ collection.
+
+ - required -- True if the action must always be specified at the
+ command line. This is only meaningful for optional command-line
+ arguments.
+
+ - help -- The help string describing the argument.
+
+ - metavar -- The name to be used for the option's argument with the
+ help string. If None, the 'dest' value will be used as the name.
+ """
+
+ def __init__(self,
+ option_strings,
+ dest,
+ nargs=None,
+ const=None,
+ default=None,
+ type=None,
+ choices=None,
+ required=False,
+ help=None,
+ metavar=None):
+ self.option_strings = option_strings
+ self.dest = dest
+ self.nargs = nargs
+ self.const = const
+ self.default = default
+ self.type = type
+ self.choices = choices
+ self.required = required
+ self.help = help
+ self.metavar = metavar
+
+ def _get_kwargs(self):
+ names = [
+ 'option_strings',
+ 'dest',
+ 'nargs',
+ 'const',
+ 'default',
+ 'type',
+ 'choices',
+ 'help',
+ 'metavar',
+ ]
+ return [(name, getattr(self, name)) for name in names]
+
+ def __call__(self, parser, namespace, values, option_string=None):
+ raise NotImplementedError(_('.__call__() not defined'))
+
+
+class _StoreAction(Action):
+
+ def __init__(self,
+ option_strings,
+ dest,
+ nargs=None,
+ const=None,
+ default=None,
+ type=None,
+ choices=None,
+ required=False,
+ help=None,
+ metavar=None):
+ if nargs == 0:
+ raise ValueError('nargs for store actions must be > 0; if you '
+ 'have nothing to store, actions such as store '
+ 'true or store const may be more appropriate')
+ if const is not None and nargs != OPTIONAL:
+ raise ValueError('nargs must be %r to supply const' % OPTIONAL)
+ super(_StoreAction, self).__init__(
+ option_strings=option_strings,
+ dest=dest,
+ nargs=nargs,
+ const=const,
+ default=default,
+ type=type,
+ choices=choices,
+ required=required,
+ help=help,
+ metavar=metavar)
+
+ def __call__(self, parser, namespace, values, option_string=None):
+ setattr(namespace, self.dest, values)
+
+
+class _StoreConstAction(Action):
+
+ def __init__(self,
+ option_strings,
+ dest,
+ const,
+ default=None,
+ required=False,
+ help=None,
+ metavar=None):
+ super(_StoreConstAction, self).__init__(
+ option_strings=option_strings,
+ dest=dest,
+ nargs=0,
+ const=const,
+ default=default,
+ required=required,
+ help=help)
+
+ def __call__(self, parser, namespace, values, option_string=None):
+ setattr(namespace, self.dest, self.const)
+
+
+class _StoreTrueAction(_StoreConstAction):
+
+ def __init__(self,
+ option_strings,
+ dest,
+ default=False,
+ required=False,
+ help=None):
+ super(_StoreTrueAction, self).__init__(
+ option_strings=option_strings,
+ dest=dest,
+ const=True,
+ default=default,
+ required=required,
+ help=help)
+
+
+class _StoreFalseAction(_StoreConstAction):
+
+ def __init__(self,
+ option_strings,
+ dest,
+ default=True,
+ required=False,
+ help=None):
+ super(_StoreFalseAction, self).__init__(
+ option_strings=option_strings,
+ dest=dest,
+ const=False,
+ default=default,
+ required=required,
+ help=help)
+
+
+class _AppendAction(Action):
+
+ def __init__(self,
+ option_strings,
+ dest,
+ nargs=None,
+ const=None,
+ default=None,
+ type=None,
+ choices=None,
+ required=False,
+ help=None,
+ metavar=None):
+ if nargs == 0:
+ raise ValueError('nargs for append actions must be > 0; if arg '
+ 'strings are not supplying the value to append, '
+ 'the append const action may be more appropriate')
+ if const is not None and nargs != OPTIONAL:
+ raise ValueError('nargs must be %r to supply const' % OPTIONAL)
+ super(_AppendAction, self).__init__(
+ option_strings=option_strings,
+ dest=dest,
+ nargs=nargs,
+ const=const,
+ default=default,
+ type=type,
+ choices=choices,
+ required=required,
+ help=help,
+ metavar=metavar)
+
+ def __call__(self, parser, namespace, values, option_string=None):
+ items = _copy.copy(_ensure_value(namespace, self.dest, []))
+ items.append(values)
+ setattr(namespace, self.dest, items)
+
+
+class _AppendConstAction(Action):
+
+ def __init__(self,
+ option_strings,
+ dest,
+ const,
+ default=None,
+ required=False,
+ help=None,
+ metavar=None):
+ super(_AppendConstAction, self).__init__(
+ option_strings=option_strings,
+ dest=dest,
+ nargs=0,
+ const=const,
+ default=default,
+ required=required,
+ help=help,
+ metavar=metavar)
+
+ def __call__(self, parser, namespace, values, option_string=None):
+ items = _copy.copy(_ensure_value(namespace, self.dest, []))
+ items.append(self.const)
+ setattr(namespace, self.dest, items)
+
+
+class _CountAction(Action):
+
+ def __init__(self,
+ option_strings,
+ dest,
+ default=None,
+ required=False,
+ help=None):
+ super(_CountAction, self).__init__(
+ option_strings=option_strings,
+ dest=dest,
+ nargs=0,
+ default=default,
+ required=required,
+ help=help)
+
+ def __call__(self, parser, namespace, values, option_string=None):
+ new_count = _ensure_value(namespace, self.dest, 0) + 1
+ setattr(namespace, self.dest, new_count)
+
+
+class _HelpAction(Action):
+
+ def __init__(self,
+ option_strings,
+ dest=SUPPRESS,
+ default=SUPPRESS,
+ help=None):
+ super(_HelpAction, self).__init__(
+ option_strings=option_strings,
+ dest=dest,
+ default=default,
+ nargs=0,
+ help=help)
+
+ def __call__(self, parser, namespace, values, option_string=None):
+ parser.print_help()
+ parser.exit()
+
+
+class _VersionAction(Action):
+
+ def __init__(self,
+ option_strings,
+ version=None,
+ dest=SUPPRESS,
+ default=SUPPRESS,
+ help="show program's version number and exit"):
+ super(_VersionAction, self).__init__(
+ option_strings=option_strings,
+ dest=dest,
+ default=default,
+ nargs=0,
+ help=help)
+ self.version = version
+
+ def __call__(self, parser, namespace, values, option_string=None):
+ version = self.version
+ if version is None:
+ version = parser.version
+ formatter = parser._get_formatter()
+ formatter.add_text(version)
+ parser.exit(message=formatter.format_help())
+
+
+class _SubParsersAction(Action):
+
+ class _ChoicesPseudoAction(Action):
+
+ def __init__(self, name, aliases, help):
+ metavar = dest = name
+ if aliases:
+ metavar += ' (%s)' % ', '.join(aliases)
+ sup = super(_SubParsersAction._ChoicesPseudoAction, self)
+ sup.__init__(option_strings=[], dest=dest, help=help,
+ metavar=metavar)
+
+ def __init__(self,
+ option_strings,
+ prog,
+ parser_class,
+ dest=SUPPRESS,
+ help=None,
+ metavar=None):
+
+ self._prog_prefix = prog
+ self._parser_class = parser_class
+ self._name_parser_map = _collections.OrderedDict()
+ self._choices_actions = []
+
+ super(_SubParsersAction, self).__init__(
+ option_strings=option_strings,
+ dest=dest,
+ nargs=PARSER,
+ choices=self._name_parser_map,
+ help=help,
+ metavar=metavar)
+
+ def add_parser(self, name, **kwargs):
+ # set prog from the existing prefix
+ if kwargs.get('prog') is None:
+ kwargs['prog'] = '%s %s' % (self._prog_prefix, name)
+
+ aliases = kwargs.pop('aliases', ())
+
+ # create a pseudo-action to hold the choice help
+ if 'help' in kwargs:
+ help = kwargs.pop('help')
+ choice_action = self._ChoicesPseudoAction(name, aliases, help)
+ self._choices_actions.append(choice_action)
+
+ # create the parser and add it to the map
+ parser = self._parser_class(**kwargs)
+ self._name_parser_map[name] = parser
+
+ # make parser available under aliases also
+ for alias in aliases:
+ self._name_parser_map[alias] = parser
+
+ return parser
+
+ def _get_subactions(self):
+ return self._choices_actions
+
+ def __call__(self, parser, namespace, values, option_string=None):
+ parser_name = values[0]
+ arg_strings = values[1:]
+
+ # set the parser name if requested
+ if self.dest is not SUPPRESS:
+ setattr(namespace, self.dest, parser_name)
+
+ # select the parser
+ try:
+ parser = self._name_parser_map[parser_name]
+ except KeyError:
+ args = {'parser_name': parser_name,
+ 'choices': ', '.join(self._name_parser_map)}
+ msg = _('unknown parser %(parser_name)r (choices: %(choices)s)') % args
+ raise ArgumentError(self, msg)
+
+ # parse all the remaining options into the namespace
+ # store any unrecognized options on the object, so that the top
+ # level parser can decide what to do with them
+ namespace, arg_strings = parser.parse_known_args(arg_strings, namespace)
+ if arg_strings:
+ vars(namespace).setdefault(_UNRECOGNIZED_ARGS_ATTR, [])
+ getattr(namespace, _UNRECOGNIZED_ARGS_ATTR).extend(arg_strings)
+
+
+# ==============
+# Type classes
+# ==============
+
+class FileType(object):
+ """Factory for creating file object types
+
+ Instances of FileType are typically passed as type= arguments to the
+ ArgumentParser add_argument() method.
+
+ Keyword Arguments:
+ - mode -- A string indicating how the file is to be opened. Accepts the
+ same values as the builtin open() function.
+ - bufsize -- The file's desired buffer size. Accepts the same values as
+ the builtin open() function.
+ """
+
+ def __init__(self, mode='r', bufsize=-1):
+ self._mode = mode
+ self._bufsize = bufsize
+
+ def __call__(self, string):
+ # the special argument "-" means sys.std{in,out}
+ if string == '-':
+ if 'r' in self._mode:
+ return _sys.stdin
+ elif 'w' in self._mode:
+ return _sys.stdout
+ else:
+ msg = _('argument "-" with mode %r') % self._mode
+ raise ValueError(msg)
+
+ # all other arguments are used as file names
+ try:
+ return open(string, self._mode, self._bufsize)
+ except IOError as e:
+ message = _("can't open '%s': %s")
+ raise ArgumentTypeError(message % (string, e))
+
+ def __repr__(self):
+ args = self._mode, self._bufsize
+ args_str = ', '.join(repr(arg) for arg in args if arg != -1)
+ return '%s(%s)' % (type(self).__name__, args_str)
+
+# ===========================
+# Optional and Positional Parsing
+# ===========================
+
+class Namespace(_AttributeHolder):
+ """Simple object for storing attributes.
+
+ Implements equality by attribute names and values, and provides a simple
+ string representation.
+ """
+
+ def __init__(self, **kwargs):
+ for name in kwargs:
+ setattr(self, name, kwargs[name])
+
+ def __eq__(self, other):
+ return vars(self) == vars(other)
+
+ def __ne__(self, other):
+ return not (self == other)
+
+ def __contains__(self, key):
+ return key in self.__dict__
+
+
+class _ActionsContainer(object):
+
+ def __init__(self,
+ description,
+ prefix_chars,
+ argument_default,
+ conflict_handler):
+ super(_ActionsContainer, self).__init__()
+
+ self.description = description
+ self.argument_default = argument_default
+ self.prefix_chars = prefix_chars
+ self.conflict_handler = conflict_handler
+
+ # set up registries
+ self._registries = {}
+
+ # register actions
+ self.register('action', None, _StoreAction)
+ self.register('action', 'store', _StoreAction)
+ self.register('action', 'store_const', _StoreConstAction)
+ self.register('action', 'store_true', _StoreTrueAction)
+ self.register('action', 'store_false', _StoreFalseAction)
+ self.register('action', 'append', _AppendAction)
+ self.register('action', 'append_const', _AppendConstAction)
+ self.register('action', 'count', _CountAction)
+ self.register('action', 'help', _HelpAction)
+ self.register('action', 'version', _VersionAction)
+ self.register('action', 'parsers', _SubParsersAction)
+
+ # raise an exception if the conflict handler is invalid
+ self._get_handler()
+
+ # action storage
+ self._actions = []
+ self._option_string_actions = {}
+
+ # groups
+ self._action_groups = []
+ self._mutually_exclusive_groups = []
+
+ # defaults storage
+ self._defaults = {}
+
+ # determines whether an "option" looks like a negative number
+ self._negative_number_matcher = _re.compile(r'^-\d+$|^-\d*\.\d+$')
+
+ # whether or not there are any optionals that look like negative
+ # numbers -- uses a list so it can be shared and edited
+ self._has_negative_number_optionals = []
+
+ # ====================
+ # Registration methods
+ # ====================
+ def register(self, registry_name, value, object):
+ registry = self._registries.setdefault(registry_name, {})
+ registry[value] = object
+
+ def _registry_get(self, registry_name, value, default=None):
+ return self._registries[registry_name].get(value, default)
+
+ # ==================================
+ # Namespace default accessor methods
+ # ==================================
+ def set_defaults(self, **kwargs):
+ self._defaults.update(kwargs)
+
+ # if these defaults match any existing arguments, replace
+ # the previous default on the object with the new one
+ for action in self._actions:
+ if action.dest in kwargs:
+ action.default = kwargs[action.dest]
+
+ def get_default(self, dest):
+ for action in self._actions:
+ if action.dest == dest and action.default is not None:
+ return action.default
+ return self._defaults.get(dest, None)
+
+
+ # =======================
+ # Adding argument actions
+ # =======================
+ def add_argument(self, *args, **kwargs):
+ """
+ add_argument(dest, ..., name=value, ...)
+ add_argument(option_string, option_string, ..., name=value, ...)
+ """
+
+ # if no positional args are supplied or only one is supplied and
+ # it doesn't look like an option string, parse a positional
+ # argument
+ chars = self.prefix_chars
+ if not args or len(args) == 1 and args[0][0] not in chars:
+ if args and 'dest' in kwargs:
+ raise ValueError('dest supplied twice for positional argument')
+ kwargs = self._get_positional_kwargs(*args, **kwargs)
+
+ # otherwise, we're adding an optional argument
+ else:
+ kwargs = self._get_optional_kwargs(*args, **kwargs)
+
+ # if no default was supplied, use the parser-level default
+ if 'default' not in kwargs:
+ dest = kwargs['dest']
+ if dest in self._defaults:
+ kwargs['default'] = self._defaults[dest]
+ elif self.argument_default is not None:
+ kwargs['default'] = self.argument_default
+
+ # create the action object, and add it to the parser
+ action_class = self._pop_action_class(kwargs)
+ if not callable(action_class):
+ raise ValueError('unknown action "%s"' % (action_class,))
+ action = action_class(**kwargs)
+
+ # raise an error if the action type is not callable
+ type_func = self._registry_get('type', action.type, action.type)
+ if not callable(type_func):
+ raise ValueError('%r is not callable' % (type_func,))
+
+ # raise an error if the metavar does not match the type
+ if hasattr(self, "_get_formatter"):
+ try:
+ self._get_formatter()._format_args(action, None)
+ except TypeError:
+ raise ValueError("length of metavar tuple does not match nargs")
+
+ return self._add_action(action)
+
+ def add_argument_group(self, *args, **kwargs):
+ group = _ArgumentGroup(self, *args, **kwargs)
+ self._action_groups.append(group)
+ return group
+
+ def add_mutually_exclusive_group(self, **kwargs):
+ group = _MutuallyExclusiveGroup(self, **kwargs)
+ self._mutually_exclusive_groups.append(group)
+ return group
+
+ def _add_action(self, action):
+ # resolve any conflicts
+ self._check_conflict(action)
+
+ # add to actions list
+ self._actions.append(action)
+ action.container = self
+
+ # index the action by any option strings it has
+ for option_string in action.option_strings:
+ self._option_string_actions[option_string] = action
+
+ # set the flag if any option strings look like negative numbers
+ for option_string in action.option_strings:
+ if self._negative_number_matcher.match(option_string):
+ if not self._has_negative_number_optionals:
+ self._has_negative_number_optionals.append(True)
+
+ # return the created action
+ return action
+
+ def _remove_action(self, action):
+ self._actions.remove(action)
+
+ def _add_container_actions(self, container):
+ # collect groups by titles
+ title_group_map = {}
+ for group in self._action_groups:
+ if group.title in title_group_map:
+ msg = _('cannot merge actions - two groups are named %r')
+ raise ValueError(msg % (group.title))
+ title_group_map[group.title] = group
+
+ # map each action to its group
+ group_map = {}
+ for group in container._action_groups:
+
+ # if a group with the title exists, use that, otherwise
+ # create a new group matching the container's group
+ if group.title not in title_group_map:
+ title_group_map[group.title] = self.add_argument_group(
+ title=group.title,
+ description=group.description,
+ conflict_handler=group.conflict_handler)
+
+ # map the actions to their new group
+ for action in group._group_actions:
+ group_map[action] = title_group_map[group.title]
+
+ # add container's mutually exclusive groups
+ # NOTE: if add_mutually_exclusive_group ever gains title= and
+ # description= then this code will need to be expanded as above
+ for group in container._mutually_exclusive_groups:
+ mutex_group = self.add_mutually_exclusive_group(
+ required=group.required)
+
+ # map the actions to their new mutex group
+ for action in group._group_actions:
+ group_map[action] = mutex_group
+
+ # add all actions to this container or their group
+ for action in container._actions:
+ group_map.get(action, self)._add_action(action)
+
+ def _get_positional_kwargs(self, dest, **kwargs):
+ # make sure required is not specified
+ if 'required' in kwargs:
+ msg = _("'required' is an invalid argument for positionals")
+ raise TypeError(msg)
+
+ # mark positional arguments as required if at least one is
+ # always required
+ if kwargs.get('nargs') not in [OPTIONAL, ZERO_OR_MORE]:
+ kwargs['required'] = True
+ if kwargs.get('nargs') == ZERO_OR_MORE and 'default' not in kwargs:
+ kwargs['required'] = True
+
+ # return the keyword arguments with no option strings
+ return dict(kwargs, dest=dest, option_strings=[])
+
+ def _get_optional_kwargs(self, *args, **kwargs):
+ # determine short and long option strings
+ option_strings = []
+ long_option_strings = []
+ for option_string in args:
+ # error on strings that don't start with an appropriate prefix
+ if not option_string[0] in self.prefix_chars:
+ args = {'option': option_string,
+ 'prefix_chars': self.prefix_chars}
+ msg = _('invalid option string %(option)r: '
+ 'must start with a character %(prefix_chars)r')
+ raise ValueError(msg % args)
+
+ # strings starting with two prefix characters are long options
+ option_strings.append(option_string)
+ if option_string[0] in self.prefix_chars:
+ if len(option_string) > 1:
+ if option_string[1] in self.prefix_chars:
+ long_option_strings.append(option_string)
+
+ # infer destination, '--foo-bar' -> 'foo_bar' and '-x' -> 'x'
+ dest = kwargs.pop('dest', None)
+ if dest is None:
+ if long_option_strings:
+ dest_option_string = long_option_strings[0]
+ else:
+ dest_option_string = option_strings[0]
+ dest = dest_option_string.lstrip(self.prefix_chars)
+ if not dest:
+ msg = _('dest= is required for options like %r')
+ raise ValueError(msg % option_string)
+ dest = dest.replace('-', '_')
+
+ # return the updated keyword arguments
+ return dict(kwargs, dest=dest, option_strings=option_strings)
+
+ def _pop_action_class(self, kwargs, default=None):
+ action = kwargs.pop('action', default)
+ return self._registry_get('action', action, action)
+
+ def _get_handler(self):
+ # determine function from conflict handler string
+ handler_func_name = '_handle_conflict_%s' % self.conflict_handler
+ try:
+ return getattr(self, handler_func_name)
+ except AttributeError:
+ msg = _('invalid conflict_resolution value: %r')
+ raise ValueError(msg % self.conflict_handler)
+
+ def _check_conflict(self, action):
+
+ # find all options that conflict with this option
+ confl_optionals = []
+ for option_string in action.option_strings:
+ if option_string in self._option_string_actions:
+ confl_optional = self._option_string_actions[option_string]
+ confl_optionals.append((option_string, confl_optional))
+
+ # resolve any conflicts
+ if confl_optionals:
+ conflict_handler = self._get_handler()
+ conflict_handler(action, confl_optionals)
+
+ def _handle_conflict_error(self, action, conflicting_actions):
+ message = ngettext('conflicting option string: %s',
+ 'conflicting option strings: %s',
+ len(conflicting_actions))
+ conflict_string = ', '.join([option_string
+ for option_string, action
+ in conflicting_actions])
+ raise ArgumentError(action, message % conflict_string)
+
+ def _handle_conflict_resolve(self, action, conflicting_actions):
+
+ # remove all conflicting options
+ for option_string, action in conflicting_actions:
+
+ # remove the conflicting option
+ action.option_strings.remove(option_string)
+ self._option_string_actions.pop(option_string, None)
+
+ # if the option now has no option string, remove it from the
+ # container holding it
+ if not action.option_strings:
+ action.container._remove_action(action)
+
+
+class _ArgumentGroup(_ActionsContainer):
+
+ def __init__(self, container, title=None, description=None, **kwargs):
+ # add any missing keyword arguments by checking the container
+ update = kwargs.setdefault
+ update('conflict_handler', container.conflict_handler)
+ update('prefix_chars', container.prefix_chars)
+ update('argument_default', container.argument_default)
+ super_init = super(_ArgumentGroup, self).__init__
+ super_init(description=description, **kwargs)
+
+ # group attributes
+ self.title = title
+ self._group_actions = []
+
+ # share most attributes with the container
+ self._registries = container._registries
+ self._actions = container._actions
+ self._option_string_actions = container._option_string_actions
+ self._defaults = container._defaults
+ self._has_negative_number_optionals = \
+ container._has_negative_number_optionals
+ self._mutually_exclusive_groups = container._mutually_exclusive_groups
+
+ def _add_action(self, action):
+ action = super(_ArgumentGroup, self)._add_action(action)
+ self._group_actions.append(action)
+ return action
+
+ def _remove_action(self, action):
+ super(_ArgumentGroup, self)._remove_action(action)
+ self._group_actions.remove(action)
+
+
+class _MutuallyExclusiveGroup(_ArgumentGroup):
+
+ def __init__(self, container, required=False):
+ super(_MutuallyExclusiveGroup, self).__init__(container)
+ self.required = required
+ self._container = container
+
+ def _add_action(self, action):
+ if action.required:
+ msg = _('mutually exclusive arguments must be optional')
+ raise ValueError(msg)
+ action = self._container._add_action(action)
+ self._group_actions.append(action)
+ return action
+
+ def _remove_action(self, action):
+ self._container._remove_action(action)
+ self._group_actions.remove(action)
+
+
+class ArgumentParser(_AttributeHolder, _ActionsContainer):
+ """Object for parsing command line strings into Python objects.
+
+ Keyword Arguments:
+ - prog -- The name of the program (default: sys.argv[0])
+ - usage -- A usage message (default: auto-generated from arguments)
+ - description -- A description of what the program does
+ - epilog -- Text following the argument descriptions
+ - parents -- Parsers whose arguments should be copied into this one
+ - formatter_class -- HelpFormatter class for printing help messages
+ - prefix_chars -- Characters that prefix optional arguments
+ - fromfile_prefix_chars -- Characters that prefix files containing
+ additional arguments
+ - argument_default -- The default value for all arguments
+ - conflict_handler -- String indicating how to handle conflicts
+ - add_help -- Add a -h/-help option
+ """
+
+ def __init__(self,
+ prog=None,
+ usage=None,
+ description=None,
+ epilog=None,
+ version=None,
+ parents=[],
+ formatter_class=HelpFormatter,
+ prefix_chars='-',
+ fromfile_prefix_chars=None,
+ argument_default=None,
+ conflict_handler='error',
+ add_help=True):
+
+ if version is not None:
+ import warnings
+ warnings.warn(
+ """The "version" argument to ArgumentParser is deprecated. """
+ """Please use """
+ """"add_argument(..., action='version', version="N", ...)" """
+ """instead""", DeprecationWarning)
+
+ superinit = super(ArgumentParser, self).__init__
+ superinit(description=description,
+ prefix_chars=prefix_chars,
+ argument_default=argument_default,
+ conflict_handler=conflict_handler)
+
+ # default setting for prog
+ if prog is None:
+ prog = _os.path.basename(_sys.argv[0])
+
+ self.prog = prog
+ self.usage = usage
+ self.epilog = epilog
+ self.version = version
+ self.formatter_class = formatter_class
+ self.fromfile_prefix_chars = fromfile_prefix_chars
+ self.add_help = add_help
+
+ add_group = self.add_argument_group
+ self._positionals = add_group(_('positional arguments'))
+ self._optionals = add_group(_('optional arguments'))
+ self._subparsers = None
+
+ # register types
+ def identity(string):
+ return string
+ self.register('type', None, identity)
+
+ # add help and version arguments if necessary
+ # (using explicit default to override global argument_default)
+ default_prefix = '-' if '-' in prefix_chars else prefix_chars[0]
+ if self.add_help:
+ self.add_argument(
+ default_prefix+'h', default_prefix*2+'help',
+ action='help', default=SUPPRESS,
+ help=_('show this help message and exit'))
+ if self.version:
+ self.add_argument(
+ default_prefix+'v', default_prefix*2+'version',
+ action='version', default=SUPPRESS,
+ version=self.version,
+ help=_("show program's version number and exit"))
+
+ # add parent arguments and defaults
+ for parent in parents:
+ self._add_container_actions(parent)
+ try:
+ defaults = parent._defaults
+ except AttributeError:
+ pass
+ else:
+ self._defaults.update(defaults)
+
+ # =======================
+ # Pretty __repr__ methods
+ # =======================
+ def _get_kwargs(self):
+ names = [
+ 'prog',
+ 'usage',
+ 'description',
+ 'version',
+ 'formatter_class',
+ 'conflict_handler',
+ 'add_help',
+ ]
+ return [(name, getattr(self, name)) for name in names]
+
+ # ==================================
+ # Optional/Positional adding methods
+ # ==================================
+ def add_subparsers(self, **kwargs):
+ if self._subparsers is not None:
+ self.error(_('cannot have multiple subparser arguments'))
+
+ # add the parser class to the arguments if it's not present
+ kwargs.setdefault('parser_class', type(self))
+
+ if 'title' in kwargs or 'description' in kwargs:
+ title = _(kwargs.pop('title', 'subcommands'))
+ description = _(kwargs.pop('description', None))
+ self._subparsers = self.add_argument_group(title, description)
+ else:
+ self._subparsers = self._positionals
+
+ # prog defaults to the usage message of this parser, skipping
+ # optional arguments and with no "usage:" prefix
+ if kwargs.get('prog') is None:
+ formatter = self._get_formatter()
+ positionals = self._get_positional_actions()
+ groups = self._mutually_exclusive_groups
+ formatter.add_usage(self.usage, positionals, groups, '')
+ kwargs['prog'] = formatter.format_help().strip()
+
+ # create the parsers action and add it to the positionals list
+ parsers_class = self._pop_action_class(kwargs, 'parsers')
+ action = parsers_class(option_strings=[], **kwargs)
+ self._subparsers._add_action(action)
+
+ # return the created parsers action
+ return action
+
+ def _add_action(self, action):
+ if action.option_strings:
+ self._optionals._add_action(action)
+ else:
+ self._positionals._add_action(action)
+ return action
+
+ def _get_optional_actions(self):
+ return [action
+ for action in self._actions
+ if action.option_strings]
+
+ def _get_positional_actions(self):
+ return [action
+ for action in self._actions
+ if not action.option_strings]
+
+ # =====================================
+ # Command line argument parsing methods
+ # =====================================
+ def parse_args(self, args=None, namespace=None):
+ args, argv = self.parse_known_args(args, namespace)
+ if argv:
+ msg = _('unrecognized arguments: %s')
+ self.error(msg % ' '.join(argv))
+ return args
+
+ def parse_known_args(self, args=None, namespace=None):
+ # args default to the system args
+ if args is None:
+ args = _sys.argv[1:]
+
+ # default Namespace built from parser defaults
+ if namespace is None:
+ namespace = Namespace()
+
+ # add any action defaults that aren't present
+ for action in self._actions:
+ if action.dest is not SUPPRESS:
+ if not hasattr(namespace, action.dest):
+ if action.default is not SUPPRESS:
+ default = action.default
+ if isinstance(action.default, str):
+ default = self._get_value(action, default)
+ setattr(namespace, action.dest, default)
+
+ # add any parser defaults that aren't present
+ for dest in self._defaults:
+ if not hasattr(namespace, dest):
+ setattr(namespace, dest, self._defaults[dest])
+
+ # parse the arguments and exit if there are any errors
+ try:
+ namespace, args = self._parse_known_args(args, namespace)
+ if hasattr(namespace, _UNRECOGNIZED_ARGS_ATTR):
+ args.extend(getattr(namespace, _UNRECOGNIZED_ARGS_ATTR))
+ delattr(namespace, _UNRECOGNIZED_ARGS_ATTR)
+ return namespace, args
+ except ArgumentError:
+ err = _sys.exc_info()[1]
+ self.error(str(err))
+
+ def _parse_known_args(self, arg_strings, namespace):
+ # replace arg strings that are file references
+ if self.fromfile_prefix_chars is not None:
+ arg_strings = self._read_args_from_files(arg_strings)
+
+ # map all mutually exclusive arguments to the other arguments
+ # they can't occur with
+ action_conflicts = {}
+ for mutex_group in self._mutually_exclusive_groups:
+ group_actions = mutex_group._group_actions
+ for i, mutex_action in enumerate(mutex_group._group_actions):
+ conflicts = action_conflicts.setdefault(mutex_action, [])
+ conflicts.extend(group_actions[:i])
+ conflicts.extend(group_actions[i + 1:])
+
+ # find all option indices, and determine the arg_string_pattern
+ # which has an 'O' if there is an option at an index,
+ # an 'A' if there is an argument, or a '-' if there is a '--'
+ option_string_indices = {}
+ arg_string_pattern_parts = []
+ arg_strings_iter = iter(arg_strings)
+ for i, arg_string in enumerate(arg_strings_iter):
+
+ # all args after -- are non-options
+ if arg_string == '--':
+ arg_string_pattern_parts.append('-')
+ for arg_string in arg_strings_iter:
+ arg_string_pattern_parts.append('A')
+
+ # otherwise, add the arg to the arg strings
+ # and note the index if it was an option
+ else:
+ option_tuple = self._parse_optional(arg_string)
+ if option_tuple is None:
+ pattern = 'A'
+ else:
+ option_string_indices[i] = option_tuple
+ pattern = 'O'
+ arg_string_pattern_parts.append(pattern)
+
+ # join the pieces together to form the pattern
+ arg_strings_pattern = ''.join(arg_string_pattern_parts)
+
+ # converts arg strings to the appropriate and then takes the action
+ seen_actions = set()
+ seen_non_default_actions = set()
+
+ def take_action(action, argument_strings, option_string=None):
+ seen_actions.add(action)
+ argument_values = self._get_values(action, argument_strings)
+
+ # error if this argument is not allowed with other previously
+ # seen arguments, assuming that actions that use the default
+ # value don't really count as "present"
+ if argument_values is not action.default:
+ seen_non_default_actions.add(action)
+ for conflict_action in action_conflicts.get(action, []):
+ if conflict_action in seen_non_default_actions:
+ msg = _('not allowed with argument %s')
+ action_name = _get_action_name(conflict_action)
+ raise ArgumentError(action, msg % action_name)
+
+ # take the action if we didn't receive a SUPPRESS value
+ # (e.g. from a default)
+ if argument_values is not SUPPRESS:
+ action(self, namespace, argument_values, option_string)
+
+ # function to convert arg_strings into an optional action
+ def consume_optional(start_index):
+
+ # get the optional identified at this index
+ option_tuple = option_string_indices[start_index]
+ action, option_string, explicit_arg = option_tuple
+
+ # identify additional optionals in the same arg string
+ # (e.g. -xyz is the same as -x -y -z if no args are required)
+ match_argument = self._match_argument
+ action_tuples = []
+ while True:
+
+ # if we found no optional action, skip it
+ if action is None:
+ extras.append(arg_strings[start_index])
+ return start_index + 1
+
+ # if there is an explicit argument, try to match the
+ # optional's string arguments to only this
+ if explicit_arg is not None:
+ arg_count = match_argument(action, 'A')
+
+ # if the action is a single-dash option and takes no
+ # arguments, try to parse more single-dash options out
+ # of the tail of the option string
+ chars = self.prefix_chars
+ if arg_count == 0 and option_string[1] not in chars:
+ action_tuples.append((action, [], option_string))
+ char = option_string[0]
+ option_string = char + explicit_arg[0]
+ new_explicit_arg = explicit_arg[1:] or None
+ optionals_map = self._option_string_actions
+ if option_string in optionals_map:
+ action = optionals_map[option_string]
+ explicit_arg = new_explicit_arg
+ else:
+ msg = _('ignored explicit argument %r')
+ raise ArgumentError(action, msg % explicit_arg)
+
+ # if the action expect exactly one argument, we've
+ # successfully matched the option; exit the loop
+ elif arg_count == 1:
+ stop = start_index + 1
+ args = [explicit_arg]
+ action_tuples.append((action, args, option_string))
+ break
+
+ # error if a double-dash option did not use the
+ # explicit argument
+ else:
+ msg = _('ignored explicit argument %r')
+ raise ArgumentError(action, msg % explicit_arg)
+
+ # if there is no explicit argument, try to match the
+ # optional's string arguments with the following strings
+ # if successful, exit the loop
+ else:
+ start = start_index + 1
+ selected_patterns = arg_strings_pattern[start:]
+ arg_count = match_argument(action, selected_patterns)
+ stop = start + arg_count
+ args = arg_strings[start:stop]
+ action_tuples.append((action, args, option_string))
+ break
+
+ # add the Optional to the list and return the index at which
+ # the Optional's string args stopped
+ assert action_tuples
+ for action, args, option_string in action_tuples:
+ take_action(action, args, option_string)
+ return stop
+
+ # the list of Positionals left to be parsed; this is modified
+ # by consume_positionals()
+ positionals = self._get_positional_actions()
+
+ # function to convert arg_strings into positional actions
+ def consume_positionals(start_index):
+ # match as many Positionals as possible
+ match_partial = self._match_arguments_partial
+ selected_pattern = arg_strings_pattern[start_index:]
+ arg_counts = match_partial(positionals, selected_pattern)
+
+ # slice off the appropriate arg strings for each Positional
+ # and add the Positional and its args to the list
+ for action, arg_count in zip(positionals, arg_counts):
+ args = arg_strings[start_index: start_index + arg_count]
+ start_index += arg_count
+ take_action(action, args)
+
+ # slice off the Positionals that we just parsed and return the
+ # index at which the Positionals' string args stopped
+ positionals[:] = positionals[len(arg_counts):]
+ return start_index
+
+ # consume Positionals and Optionals alternately, until we have
+ # passed the last option string
+ extras = []
+ start_index = 0
+ if option_string_indices:
+ max_option_string_index = max(option_string_indices)
+ else:
+ max_option_string_index = -1
+ while start_index <= max_option_string_index:
+
+ # consume any Positionals preceding the next option
+ next_option_string_index = min([
+ index
+ for index in option_string_indices
+ if index >= start_index])
+ if start_index != next_option_string_index:
+ positionals_end_index = consume_positionals(start_index)
+
+ # only try to parse the next optional if we didn't consume
+ # the option string during the positionals parsing
+ if positionals_end_index > start_index:
+ start_index = positionals_end_index
+ continue
+ else:
+ start_index = positionals_end_index
+
+ # if we consumed all the positionals we could and we're not
+ # at the index of an option string, there were extra arguments
+ if start_index not in option_string_indices:
+ strings = arg_strings[start_index:next_option_string_index]
+ extras.extend(strings)
+ start_index = next_option_string_index
+
+ # consume the next optional and any arguments for it
+ start_index = consume_optional(start_index)
+
+ # consume any positionals following the last Optional
+ stop_index = consume_positionals(start_index)
+
+ # if we didn't consume all the argument strings, there were extras
+ extras.extend(arg_strings[stop_index:])
+
+ # if we didn't use all the Positional objects, there were too few
+ # arg strings supplied.
+ if positionals:
+ self.error(_('too few arguments'))
+
+ # make sure all required actions were present
+ for action in self._actions:
+ if action.required:
+ if action not in seen_actions:
+ name = _get_action_name(action)
+ self.error(_('argument %s is required') % name)
+
+ # make sure all required groups had one option present
+ for group in self._mutually_exclusive_groups:
+ if group.required:
+ for action in group._group_actions:
+ if action in seen_non_default_actions:
+ break
+
+ # if no actions were used, report the error
+ else:
+ names = [_get_action_name(action)
+ for action in group._group_actions
+ if action.help is not SUPPRESS]
+ msg = _('one of the arguments %s is required')
+ self.error(msg % ' '.join(names))
+
+ # return the updated namespace and the extra arguments
+ return namespace, extras
+
+ def _read_args_from_files(self, arg_strings):
+ # expand arguments referencing files
+ new_arg_strings = []
+ for arg_string in arg_strings:
+
+ # for regular arguments, just add them back into the list
+ if arg_string[0] not in self.fromfile_prefix_chars:
+ new_arg_strings.append(arg_string)
+
+ # replace arguments referencing files with the file content
+ else:
+ try:
+ args_file = open(arg_string[1:])
+ try:
+ arg_strings = []
+ for arg_line in args_file.read().splitlines():
+ for arg in self.convert_arg_line_to_args(arg_line):
+ arg_strings.append(arg)
+ arg_strings = self._read_args_from_files(arg_strings)
+ new_arg_strings.extend(arg_strings)
+ finally:
+ args_file.close()
+ except IOError:
+ err = _sys.exc_info()[1]
+ self.error(str(err))
+
+ # return the modified argument list
+ return new_arg_strings
+
+ def convert_arg_line_to_args(self, arg_line):
+ return [arg_line]
+
+ def _match_argument(self, action, arg_strings_pattern):
+ # match the pattern for this action to the arg strings
+ nargs_pattern = self._get_nargs_pattern(action)
+ match = _re.match(nargs_pattern, arg_strings_pattern)
+
+ # raise an exception if we weren't able to find a match
+ if match is None:
+ nargs_errors = {
+ None: _('expected one argument'),
+ OPTIONAL: _('expected at most one argument'),
+ ONE_OR_MORE: _('expected at least one argument'),
+ }
+ default = ngettext('expected %s argument',
+ 'expected %s arguments',
+ action.nargs) % action.nargs
+ msg = nargs_errors.get(action.nargs, default)
+ raise ArgumentError(action, msg)
+
+ # return the number of arguments matched
+ return len(match.group(1))
+
+ def _match_arguments_partial(self, actions, arg_strings_pattern):
+ # progressively shorten the actions list by slicing off the
+ # final actions until we find a match
+ result = []
+ for i in range(len(actions), 0, -1):
+ actions_slice = actions[:i]
+ pattern = ''.join([self._get_nargs_pattern(action)
+ for action in actions_slice])
+ match = _re.match(pattern, arg_strings_pattern)
+ if match is not None:
+ result.extend([len(string) for string in match.groups()])
+ break
+
+ # return the list of arg string counts
+ return result
+
+ def _parse_optional(self, arg_string):
+ # if it's an empty string, it was meant to be a positional
+ if not arg_string:
+ return None
+
+ # if it doesn't start with a prefix, it was meant to be positional
+ if not arg_string[0] in self.prefix_chars:
+ return None
+
+ # if the option string is present in the parser, return the action
+ if arg_string in self._option_string_actions:
+ action = self._option_string_actions[arg_string]
+ return action, arg_string, None
+
+ # if it's just a single character, it was meant to be positional
+ if len(arg_string) == 1:
+ return None
+
+ # if the option string before the "=" is present, return the action
+ if '=' in arg_string:
+ option_string, explicit_arg = arg_string.split('=', 1)
+ if option_string in self._option_string_actions:
+ action = self._option_string_actions[option_string]
+ return action, option_string, explicit_arg
+
+ # search through all possible prefixes of the option string
+ # and all actions in the parser for possible interpretations
+ option_tuples = self._get_option_tuples(arg_string)
+
+ # if multiple actions match, the option string was ambiguous
+ if len(option_tuples) > 1:
+ options = ', '.join([option_string
+ for action, option_string, explicit_arg in option_tuples])
+ args = {'option': arg_string, 'matches': options}
+ msg = _('ambiguous option: %(option)s could match %(matches)s')
+ self.error(msg % args)
+
+ # if exactly one action matched, this segmentation is good,
+ # so return the parsed action
+ elif len(option_tuples) == 1:
+ option_tuple, = option_tuples
+ return option_tuple
+
+ # if it was not found as an option, but it looks like a negative
+ # number, it was meant to be positional
+ # unless there are negative-number-like options
+ if self._negative_number_matcher.match(arg_string):
+ if not self._has_negative_number_optionals:
+ return None
+
+ # if it contains a space, it was meant to be a positional
+ if ' ' in arg_string:
+ return None
+
+ # it was meant to be an optional but there is no such option
+ # in this parser (though it might be a valid option in a subparser)
+ return None, arg_string, None
+
+ def _get_option_tuples(self, option_string):
+ result = []
+
+ # option strings starting with two prefix characters are only
+ # split at the '='
+ chars = self.prefix_chars
+ if option_string[0] in chars and option_string[1] in chars:
+ if '=' in option_string:
+ option_prefix, explicit_arg = option_string.split('=', 1)
+ else:
+ option_prefix = option_string
+ explicit_arg = None
+ for option_string in self._option_string_actions:
+ if option_string.startswith(option_prefix):
+ action = self._option_string_actions[option_string]
+ tup = action, option_string, explicit_arg
+ result.append(tup)
+
+ # single character options can be concatenated with their arguments
+ # but multiple character options always have to have their argument
+ # separate
+ elif option_string[0] in chars and option_string[1] not in chars:
+ option_prefix = option_string
+ explicit_arg = None
+ short_option_prefix = option_string[:2]
+ short_explicit_arg = option_string[2:]
+
+ for option_string in self._option_string_actions:
+ if option_string == short_option_prefix:
+ action = self._option_string_actions[option_string]
+ tup = action, option_string, short_explicit_arg
+ result.append(tup)
+ elif option_string.startswith(option_prefix):
+ action = self._option_string_actions[option_string]
+ tup = action, option_string, explicit_arg
+ result.append(tup)
+
+ # shouldn't ever get here
+ else:
+ self.error(_('unexpected option string: %s') % option_string)
+
+ # return the collected option tuples
+ return result
+
+ def _get_nargs_pattern(self, action):
+ # in all examples below, we have to allow for '--' args
+ # which are represented as '-' in the pattern
+ nargs = action.nargs
+
+ # the default (None) is assumed to be a single argument
+ if nargs is None:
+ nargs_pattern = '(-*A-*)'
+
+ # allow zero or one arguments
+ elif nargs == OPTIONAL:
+ nargs_pattern = '(-*A?-*)'
+
+ # allow zero or more arguments
+ elif nargs == ZERO_OR_MORE:
+ nargs_pattern = '(-*[A-]*)'
+
+ # allow one or more arguments
+ elif nargs == ONE_OR_MORE:
+ nargs_pattern = '(-*A[A-]*)'
+
+ # allow any number of options or arguments
+ elif nargs == REMAINDER:
+ nargs_pattern = '([-AO]*)'
+
+ # allow one argument followed by any number of options or arguments
+ elif nargs == PARSER:
+ nargs_pattern = '(-*A[-AO]*)'
+
+ # all others should be integers
+ else:
+ nargs_pattern = '(-*%s-*)' % '-*'.join('A' * nargs)
+
+ # if this is an optional action, -- is not allowed
+ if action.option_strings:
+ nargs_pattern = nargs_pattern.replace('-*', '')
+ nargs_pattern = nargs_pattern.replace('-', '')
+
+ # return the pattern
+ return nargs_pattern
+
+ # ========================
+ # Value conversion methods
+ # ========================
+ def _get_values(self, action, arg_strings):
+ # for everything but PARSER args, strip out '--'
+ if action.nargs not in [PARSER, REMAINDER]:
+ arg_strings = [s for s in arg_strings if s != '--']
+
+ # optional argument produces a default when not present
+ if not arg_strings and action.nargs == OPTIONAL:
+ if action.option_strings:
+ value = action.const
+ else:
+ value = action.default
+ if isinstance(value, str):
+ value = self._get_value(action, value)
+ self._check_value(action, value)
+
+ # when nargs='*' on a positional, if there were no command-line
+ # args, use the default if it is anything other than None
+ elif (not arg_strings and action.nargs == ZERO_OR_MORE and
+ not action.option_strings):
+ if action.default is not None:
+ value = action.default
+ else:
+ value = arg_strings
+ self._check_value(action, value)
+
+ # single argument or optional argument produces a single value
+ elif len(arg_strings) == 1 and action.nargs in [None, OPTIONAL]:
+ arg_string, = arg_strings
+ value = self._get_value(action, arg_string)
+ self._check_value(action, value)
+
+ # REMAINDER arguments convert all values, checking none
+ elif action.nargs == REMAINDER:
+ value = [self._get_value(action, v) for v in arg_strings]
+
+ # PARSER arguments convert all values, but check only the first
+ elif action.nargs == PARSER:
+ value = [self._get_value(action, v) for v in arg_strings]
+ self._check_value(action, value[0])
+
+ # all other types of nargs produce a list
+ else:
+ value = [self._get_value(action, v) for v in arg_strings]
+ for v in value:
+ self._check_value(action, v)
+
+ # return the converted value
+ return value
+
+ def _get_value(self, action, arg_string):
+ type_func = self._registry_get('type', action.type, action.type)
+ if not callable(type_func):
+ msg = _('%r is not callable')
+ raise ArgumentError(action, msg % type_func)
+
+ # convert the value to the appropriate type
+ try:
+ result = type_func(arg_string)
+
+ # ArgumentTypeErrors indicate errors
+ except ArgumentTypeError:
+ name = getattr(action.type, '__name__', repr(action.type))
+ msg = str(_sys.exc_info()[1])
+ raise ArgumentError(action, msg)
+
+ # TypeErrors or ValueErrors also indicate errors
+ except (TypeError, ValueError):
+ name = getattr(action.type, '__name__', repr(action.type))
+ args = {'type': name, 'value': arg_string}
+ msg = _('invalid %(type)s value: %(value)r')
+ raise ArgumentError(action, msg % args)
+
+ # return the converted value
+ return result
+
+ def _check_value(self, action, value):
+ # converted value must be one of the choices (if specified)
+ if action.choices is not None and value not in action.choices:
+ args = {'value': value,
+ 'choices': ', '.join(map(repr, action.choices))}
+ msg = _('invalid choice: %(value)r (choose from %(choices)s)')
+ raise ArgumentError(action, msg % args)
+
+ # =======================
+ # Help-formatting methods
+ # =======================
+ def format_usage(self):
+ formatter = self._get_formatter()
+ formatter.add_usage(self.usage, self._actions,
+ self._mutually_exclusive_groups)
+ return formatter.format_help()
+
+ def format_help(self):
+ formatter = self._get_formatter()
+
+ # usage
+ formatter.add_usage(self.usage, self._actions,
+ self._mutually_exclusive_groups)
+
+ # description
+ formatter.add_text(self.description)
+
+ # positionals, optionals and user-defined groups
+ for action_group in self._action_groups:
+ formatter.start_section(action_group.title)
+ formatter.add_text(action_group.description)
+ formatter.add_arguments(action_group._group_actions)
+ formatter.end_section()
+
+ # epilog
+ formatter.add_text(self.epilog)
+
+ # determine help from format above
+ return formatter.format_help()
+
+ def format_version(self):
+ import warnings
+ warnings.warn(
+ 'The format_version method is deprecated -- the "version" '
+ 'argument to ArgumentParser is no longer supported.',
+ DeprecationWarning)
+ formatter = self._get_formatter()
+ formatter.add_text(self.version)
+ return formatter.format_help()
+
+ def _get_formatter(self):
+ return self.formatter_class(prog=self.prog)
+
+ # =====================
+ # Help-printing methods
+ # =====================
+ def print_usage(self, file=None):
+ if file is None:
+ file = _sys.stdout
+ self._print_message(self.format_usage(), file)
+
+ def print_help(self, file=None):
+ if file is None:
+ file = _sys.stdout
+ self._print_message(self.format_help(), file)
+
+ def print_version(self, file=None):
+ import warnings
+ warnings.warn(
+ 'The print_version method is deprecated -- the "version" '
+ 'argument to ArgumentParser is no longer supported.',
+ DeprecationWarning)
+ self._print_message(self.format_version(), file)
+
+ def _print_message(self, message, file=None):
+ if message:
+ if file is None:
+ file = _sys.stderr
+ file.write(message)
+
+ # ===============
+ # Exiting methods
+ # ===============
+ def exit(self, status=0, message=None):
+ if message:
+ self._print_message(message, _sys.stderr)
+ _sys.exit(status)
+
+ def error(self, message):
+ """error(message: string)
+
+ Prints a usage message incorporating the message to stderr and
+ exits.
+
+ If you override this in a subclass, it should not return -- it
+ should either exit or raise an exception.
+ """
+ self.print_usage(_sys.stderr)
+ args = {'prog': self.prog, 'message': message}
+ self.exit(2, _('%(prog)s: error: %(message)s\n') % args)
diff --git a/lib-python/3.2/ast.py b/lib-python/3.2/ast.py
new file mode 100644
--- /dev/null
+++ b/lib-python/3.2/ast.py
@@ -0,0 +1,318 @@
+"""
+ ast
+ ~~~
+
+ The `ast` module helps Python applications to process trees of the Python
+ abstract syntax grammar. The abstract syntax itself might change with
+ each Python release; this module helps to find out programmatically what
+ the current grammar looks like and allows modifications of it.
+
+ An abstract syntax tree can be generated by passing `ast.PyCF_ONLY_AST` as
+ a flag to the `compile()` builtin function or by using the `parse()`
+ function from this module. The result will be a tree of objects whose
+ classes all inherit from `ast.AST`.
+
+ A modified abstract syntax tree can be compiled into a Python code object
+ using the built-in `compile()` function.
+
+ Additionally various helper functions are provided that make working with
+ the trees simpler. The main intention of the helper functions and this
+ module in general is to provide an easy to use interface for libraries
+ that work tightly with the python syntax (template engines for example).
+
+
+ :copyright: Copyright 2008 by Armin Ronacher.
+ :license: Python License.
+"""
+from _ast import *
+from _ast import __version__
+
+
+def parse(source, filename='<unknown>', mode='exec'):
+ """
+ Parse the source into an AST node.
+ Equivalent to compile(source, filename, mode, PyCF_ONLY_AST).
+ """
+ return compile(source, filename, mode, PyCF_ONLY_AST)
+
+
+def literal_eval(node_or_string):
+ """
+ Safely evaluate an expression node or a string containing a Python
+ expression. The string or node provided may only consist of the following
+ Python literal structures: strings, bytes, numbers, tuples, lists, dicts,
+ sets, booleans, and None.
+ """
+ _safe_names = {'None': None, 'True': True, 'False': False}
+ if isinstance(node_or_string, str):
+ node_or_string = parse(node_or_string, mode='eval')
+ if isinstance(node_or_string, Expression):
+ node_or_string = node_or_string.body
+ def _convert(node):
+ if isinstance(node, (Str, Bytes)):
+ return node.s
+ elif isinstance(node, Num):
+ return node.n
+ elif isinstance(node, Tuple):
+ return tuple(map(_convert, node.elts))
+ elif isinstance(node, List):
+ return list(map(_convert, node.elts))
+ elif isinstance(node, Set):
+ return set(map(_convert, node.elts))
+ elif isinstance(node, Dict):
+ return dict((_convert(k), _convert(v)) for k, v
+ in zip(node.keys, node.values))
+ elif isinstance(node, Name):
+ if node.id in _safe_names:
+ return _safe_names[node.id]
+ elif isinstance(node, UnaryOp) and \
+ isinstance(node.op, (UAdd, USub)) and \
+ isinstance(node.operand, (Num, UnaryOp, BinOp)):
+ operand = _convert(node.operand)
+ if isinstance(node.op, UAdd):
+ return + operand
+ else:
+ return - operand
+ elif isinstance(node, BinOp) and \
+ isinstance(node.op, (Add, Sub)) and \
+ isinstance(node.right, (Num, UnaryOp, BinOp)) and \
+ isinstance(node.left, (Num, UnaryOp, BinOp)):
+ left = _convert(node.left)
+ right = _convert(node.right)
+ if isinstance(node.op, Add):
+ return left + right
+ else:
+ return left - right
+ raise ValueError('malformed node or string: ' + repr(node))
+ return _convert(node_or_string)
+
+
+def dump(node, annotate_fields=True, include_attributes=False):
+ """
+ Return a formatted dump of the tree in *node*. This is mainly useful for
+ debugging purposes. The returned string will show the names and the values
+ for fields. This makes the code impossible to evaluate, so if evaluation is
+ wanted *annotate_fields* must be set to False. Attributes such as line
+ numbers and column offsets are not dumped by default. If this is wanted,
+ *include_attributes* can be set to True.
+ """
+ def _format(node):
+ if isinstance(node, AST):
+ fields = [(a, _format(b)) for a, b in iter_fields(node)]
+ rv = '%s(%s' % (node.__class__.__name__, ', '.join(
+ ('%s=%s' % field for field in fields)
+ if annotate_fields else
+ (b for a, b in fields)
+ ))
+ if include_attributes and node._attributes:
+ rv += fields and ', ' or ' '
+ rv += ', '.join('%s=%s' % (a, _format(getattr(node, a)))
+ for a in node._attributes)
+ return rv + ')'
+ elif isinstance(node, list):
+ return '[%s]' % ', '.join(_format(x) for x in node)
+ return repr(node)
+ if not isinstance(node, AST):
+ raise TypeError('expected AST, got %r' % node.__class__.__name__)
+ return _format(node)
+
+
+def copy_location(new_node, old_node):
+ """
+ Copy source location (`lineno` and `col_offset` attributes) from
+ *old_node* to *new_node* if possible, and return *new_node*.
+ """
+ for attr in 'lineno', 'col_offset':
+ if attr in old_node._attributes and attr in new_node._attributes \
+ and hasattr(old_node, attr):
+ setattr(new_node, attr, getattr(old_node, attr))
+ return new_node
+
+
+def fix_missing_locations(node):
+ """
+ When you compile a node tree with compile(), the compiler expects lineno and
+ col_offset attributes for every node that supports them. This is rather
+ tedious to fill in for generated nodes, so this helper adds these attributes
+ recursively where not already set, by setting them to the values of the
+ parent node. It works recursively starting at *node*.
+ """
+ def _fix(node, lineno, col_offset):
+ if 'lineno' in node._attributes:
+ if not hasattr(node, 'lineno'):
+ node.lineno = lineno
+ else:
+ lineno = node.lineno
+ if 'col_offset' in node._attributes:
+ if not hasattr(node, 'col_offset'):
+ node.col_offset = col_offset
+ else:
+ col_offset = node.col_offset
+ for child in iter_child_nodes(node):
+ _fix(child, lineno, col_offset)
+ _fix(node, 1, 0)
+ return node
+
+
+def increment_lineno(node, n=1):
+ """
+ Increment the line number of each node in the tree starting at *node* by *n*.
+ This is useful to "move code" to a different location in a file.
+ """
+ for child in walk(node):
+ if 'lineno' in child._attributes:
+ child.lineno = getattr(child, 'lineno', 0) + n
+ return node
+
+
+def iter_fields(node):
+ """
+ Yield a tuple of ``(fieldname, value)`` for each field in ``node._fields``
+ that is present on *node*.
+ """
+ for field in node._fields:
+ try:
+ yield field, getattr(node, field)
+ except AttributeError:
+ pass
+
+
+def iter_child_nodes(node):
+ """
+ Yield all direct child nodes of *node*, that is, all fields that are nodes
+ and all items of fields that are lists of nodes.
+ """
+ for name, field in iter_fields(node):
+ if isinstance(field, AST):
+ yield field
+ elif isinstance(field, list):
+ for item in field:
+ if isinstance(item, AST):
+ yield item
+
+
+def get_docstring(node, clean=True):
+ """
+ Return the docstring for the given node or None if no docstring can
+ be found. If the node provided does not have docstrings a TypeError
+ will be raised.
+ """
+ if not isinstance(node, (FunctionDef, ClassDef, Module)):
+ raise TypeError("%r can't have docstrings" % node.__class__.__name__)
+ if node.body and isinstance(node.body[0], Expr) and \
+ isinstance(node.body[0].value, Str):
+ if clean:
+ import inspect
+ return inspect.cleandoc(node.body[0].value.s)
+ return node.body[0].value.s
+
+
+def walk(node):
+ """
+ Recursively yield all descendant nodes in the tree starting at *node*
+ (including *node* itself), in no specified order. This is useful if you
+ only want to modify nodes in place and don't care about the context.
+ """
+ from collections import deque
+ todo = deque([node])
+ while todo:
+ node = todo.popleft()
+ todo.extend(iter_child_nodes(node))
+ yield node
+
+
+class NodeVisitor(object):
+ """
+ A node visitor base class that walks the abstract syntax tree and calls a
+ visitor function for every node found. This function may return a value
+ which is forwarded by the `visit` method.
+
+ This class is meant to be subclassed, with the subclass adding visitor
+ methods.
+
+ Per default the visitor functions for the nodes are ``'visit_'`` +
+ class name of the node. So a `TryFinally` node visit function would
+ be `visit_TryFinally`. This behavior can be changed by overriding
+ the `visit` method. If no visitor function exists for a node
+ (return value `None`) the `generic_visit` visitor is used instead.
+
+ Don't use the `NodeVisitor` if you want to apply changes to nodes during
+ traversing. For this a special visitor exists (`NodeTransformer`) that
+ allows modifications.
+ """
+
+ def visit(self, node):
+ """Visit a node."""
+ method = 'visit_' + node.__class__.__name__
+ visitor = getattr(self, method, self.generic_visit)
+ return visitor(node)
+
+ def generic_visit(self, node):
+ """Called if no explicit visitor function exists for a node."""
+ for field, value in iter_fields(node):
+ if isinstance(value, list):
+ for item in value:
+ if isinstance(item, AST):
+ self.visit(item)
+ elif isinstance(value, AST):
+ self.visit(value)
+
+
+class NodeTransformer(NodeVisitor):
+ """
+ A :class:`NodeVisitor` subclass that walks the abstract syntax tree and
+ allows modification of nodes.
+
+ The `NodeTransformer` will walk the AST and use the return value of the
+ visitor methods to replace or remove the old node. If the return value of
+ the visitor method is ``None``, the node will be removed from its location,
+ otherwise it is replaced with the return value. The return value may be the
+ original node in which case no replacement takes place.
+
+ Here is an example transformer that rewrites all occurrences of name lookups
+ (``foo``) to ``data['foo']``::
+
+ class RewriteName(NodeTransformer):
+
+ def visit_Name(self, node):
+ return copy_location(Subscript(
+ value=Name(id='data', ctx=Load()),
+ slice=Index(value=Str(s=node.id)),
+ ctx=node.ctx
+ ), node)
+
+ Keep in mind that if the node you're operating on has child nodes you must
+ either transform the child nodes yourself or call the :meth:`generic_visit`
+ method for the node first.
+
+ For nodes that were part of a collection of statements (that applies to all
+ statement nodes), the visitor may also return a list of nodes rather than
+ just a single node.
+
+ Usually you use the transformer like this::
+
+ node = YourTransformer().visit(node)
+ """
+
+ def generic_visit(self, node):
+ for field, old_value in iter_fields(node):
+ old_value = getattr(node, field, None)
+ if isinstance(old_value, list):
+ new_values = []
+ for value in old_value:
+ if isinstance(value, AST):
+ value = self.visit(value)
+ if value is None:
+ continue
+ elif not isinstance(value, AST):
+ new_values.extend(value)
+ continue
+ new_values.append(value)
+ old_value[:] = new_values
+ elif isinstance(old_value, AST):
+ new_node = self.visit(old_value)
+ if new_node is None:
+ delattr(node, field)
+ else:
+ setattr(node, field, new_node)
+ return node
diff --git a/lib-python/3.2/asynchat.py b/lib-python/3.2/asynchat.py
new file mode 100644
--- /dev/null
+++ b/lib-python/3.2/asynchat.py
@@ -0,0 +1,336 @@
+# -*- Mode: Python; tab-width: 4 -*-
+# Id: asynchat.py,v 2.26 2000/09/07 22:29:26 rushing Exp
+# Author: Sam Rushing <rushing at nightmare.com>
+
+# ======================================================================
+# Copyright 1996 by Sam Rushing
+#
+# All Rights Reserved
+#
+# Permission to use, copy, modify, and distribute this software and
+# its documentation for any purpose and without fee is hereby
+# granted, provided that the above copyright notice appear in all
+# copies and that both that copyright notice and this permission
+# notice appear in supporting documentation, and that the name of Sam
+# Rushing not be used in advertising or publicity pertaining to
+# distribution of the software without specific, written prior
+# permission.
+#
+# SAM RUSHING DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
+# INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN
+# NO EVENT SHALL SAM RUSHING BE LIABLE FOR ANY SPECIAL, INDIRECT OR
+# CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
+# OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT,
+# NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
+# CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+# ======================================================================
+
+r"""A class supporting chat-style (command/response) protocols.
+
+This class adds support for 'chat' style protocols - where one side
+sends a 'command', and the other sends a response (examples would be
+the common internet protocols - smtp, nntp, ftp, etc..).
+
+The handle_read() method looks at the input stream for the current
+'terminator' (usually '\r\n' for single-line responses, '\r\n.\r\n'
+for multi-line output), calling self.found_terminator() on its
+receipt.
+
+for example:
+Say you build an async nntp client using this class. At the start
+of the connection, you'll have self.terminator set to '\r\n', in
+order to process the single-line greeting. Just before issuing a
+'LIST' command you'll set it to '\r\n.\r\n'. The output of the LIST
+command will be accumulated (using your own 'collect_incoming_data'
+method) up to the terminator, and then control will be returned to
+you - by calling your self.found_terminator() method.
+"""
+import socket
+import asyncore
+from collections import deque
+
+def buffer(obj, start=None, stop=None):
+ # if memoryview objects gain slicing semantics,
+ # this function will change for the better
+ # memoryview used for the TypeError
+ memoryview(obj)
+ if start == None:
+ start = 0
+ if stop == None:
+ stop = len(obj)
+ x = obj[start:stop]
+ ## print("buffer type is: %s"%(type(x),))
+ return x
+
+class async_chat (asyncore.dispatcher):
+ """This is an abstract class. You must derive from this class, and add
+ the two methods collect_incoming_data() and found_terminator()"""
+
+ # these are overridable defaults
+
+ ac_in_buffer_size = 4096
+ ac_out_buffer_size = 4096
+
+ # we don't want to enable the use of encoding by default, because that is a
+ # sign of an application bug that we don't want to pass silently
+
+ use_encoding = 0
+ encoding = 'latin1'
+
+ def __init__ (self, sock=None, map=None):
+ # for string terminator matching
+ self.ac_in_buffer = b''
+
+ # we use a list here rather than cStringIO for a few reasons...
+ # del lst[:] is faster than sio.truncate(0)
+ # lst = [] is faster than sio.truncate(0)
+ # cStringIO will be gaining unicode support in py3k, which
+ # will negatively affect the performance of bytes compared to
+ # a ''.join() equivalent
+ self.incoming = []
+
+ # we toss the use of the "simple producer" and replace it with
+ # a pure deque, which the original fifo was a wrapping of
+ self.producer_fifo = deque()
+ asyncore.dispatcher.__init__ (self, sock, map)
+
+ def collect_incoming_data(self, data):
+ raise NotImplementedError("must be implemented in subclass")
+
+ def _collect_incoming_data(self, data):
+ self.incoming.append(data)
+
+ def _get_data(self):
+ d = b''.join(self.incoming)
+ del self.incoming[:]
+ return d
+
+ def found_terminator(self):
+ raise NotImplementedError("must be implemented in subclass")
+
+ def set_terminator (self, term):
+ "Set the input delimiter. Can be a fixed string of any length, an integer, or None"
+ if isinstance(term, str) and self.use_encoding:
+ term = bytes(term, self.encoding)
+ self.terminator = term
+
+ def get_terminator (self):
+ return self.terminator
+
+ # grab some more data from the socket,
+ # throw it to the collector method,
+ # check for the terminator,
+ # if found, transition to the next state.
+
+ def handle_read (self):
+
+ try:
+ data = self.recv (self.ac_in_buffer_size)
+ except socket.error as why:
+ self.handle_error()
+ return
+
+ if isinstance(data, str) and self.use_encoding:
+ data = bytes(str, self.encoding)
+ self.ac_in_buffer = self.ac_in_buffer + data
+
+ # Continue to search for self.terminator in self.ac_in_buffer,
+ # while calling self.collect_incoming_data. The while loop
+ # is necessary because we might read several data+terminator
+ # combos with a single recv(4096).
+
+ while self.ac_in_buffer:
+ lb = len(self.ac_in_buffer)
+ terminator = self.get_terminator()
+ if not terminator:
+ # no terminator, collect it all
+ self.collect_incoming_data (self.ac_in_buffer)
+ self.ac_in_buffer = b''
+ elif isinstance(terminator, int):
+ # numeric terminator
+ n = terminator
+ if lb < n:
+ self.collect_incoming_data (self.ac_in_buffer)
+ self.ac_in_buffer = b''
+ self.terminator = self.terminator - lb
+ else:
+ self.collect_incoming_data (self.ac_in_buffer[:n])
+ self.ac_in_buffer = self.ac_in_buffer[n:]
+ self.terminator = 0
+ self.found_terminator()
+ else:
+ # 3 cases:
+ # 1) end of buffer matches terminator exactly:
+ # collect data, transition
+ # 2) end of buffer matches some prefix:
+ # collect data to the prefix
+ # 3) end of buffer does not match any prefix:
+ # collect data
+ terminator_len = len(terminator)
+ index = self.ac_in_buffer.find(terminator)
+ if index != -1:
+ # we found the terminator
+ if index > 0:
+ # don't bother reporting the empty string (source of subtle bugs)
+ self.collect_incoming_data (self.ac_in_buffer[:index])
+ self.ac_in_buffer = self.ac_in_buffer[index+terminator_len:]
+ # This does the Right Thing if the terminator is changed here.
+ self.found_terminator()
+ else:
+ # check for a prefix of the terminator
+ index = find_prefix_at_end (self.ac_in_buffer, terminator)
+ if index:
+ if index != lb:
+ # we found a prefix, collect up to the prefix
+ self.collect_incoming_data (self.ac_in_buffer[:-index])
+ self.ac_in_buffer = self.ac_in_buffer[-index:]
+ break
+ else:
+ # no prefix, collect it all
+ self.collect_incoming_data (self.ac_in_buffer)
+ self.ac_in_buffer = b''
+
+ def handle_write (self):
+ self.initiate_send()
+
+ def handle_close (self):
+ self.close()
+
+ def push (self, data):
+ sabs = self.ac_out_buffer_size
+ if len(data) > sabs:
+ for i in range(0, len(data), sabs):
+ self.producer_fifo.append(data[i:i+sabs])
+ else:
+ self.producer_fifo.append(data)
+ self.initiate_send()
+
+ def push_with_producer (self, producer):
+ self.producer_fifo.append(producer)
+ self.initiate_send()
+
+ def readable (self):
+ "predicate for inclusion in the readable for select()"
+ # cannot use the old predicate, it violates the claim of the
+ # set_terminator method.
+
+ # return (len(self.ac_in_buffer) <= self.ac_in_buffer_size)
+ return 1
+
+ def writable (self):
+ "predicate for inclusion in the writable for select()"
+ return self.producer_fifo or (not self.connected)
+
+ def close_when_done (self):
+ "automatically close this channel once the outgoing queue is empty"
+ self.producer_fifo.append(None)
+
+ def initiate_send(self):
+ while self.producer_fifo and self.connected:
+ first = self.producer_fifo[0]
+ # handle empty string/buffer or None entry
+ if not first:
+ del self.producer_fifo[0]
+ if first is None:
+ ## print("first is None")
+ self.handle_close()
+ return
+ ## print("first is not None")
+
+ # handle classic producer behavior
+ obs = self.ac_out_buffer_size
+ try:
+ data = buffer(first, 0, obs)
+ except TypeError:
+ data = first.more()
+ if data:
+ self.producer_fifo.appendleft(data)
+ else:
+ del self.producer_fifo[0]
+ continue
+
+ if isinstance(data, str) and self.use_encoding:
+ data = bytes(data, self.encoding)
+
+ # send the data
+ try:
+ num_sent = self.send(data)
+ except socket.error:
+ self.handle_error()
+ return
+
+ if num_sent:
+ if num_sent < len(data) or obs < len(first):
+ self.producer_fifo[0] = first[num_sent:]
+ else:
+ del self.producer_fifo[0]
+ # we tried to send some actual data
+ return
+
+ def discard_buffers (self):
+ # Emergencies only!
+ self.ac_in_buffer = b''
+ del self.incoming[:]
+ self.producer_fifo.clear()
+
+class simple_producer:
+
+ def __init__ (self, data, buffer_size=512):
+ self.data = data
+ self.buffer_size = buffer_size
+
+ def more (self):
+ if len (self.data) > self.buffer_size:
+ result = self.data[:self.buffer_size]
+ self.data = self.data[self.buffer_size:]
+ return result
+ else:
+ result = self.data
+ self.data = b''
+ return result
+
+class fifo:
+ def __init__ (self, list=None):
+ if not list:
+ self.list = deque()
+ else:
+ self.list = deque(list)
+
+ def __len__ (self):
+ return len(self.list)
+
+ def is_empty (self):
+ return not self.list
+
+ def first (self):
+ return self.list[0]
+
+ def push (self, data):
+ self.list.append(data)
+
+ def pop (self):
+ if self.list:
+ return (1, self.list.popleft())
+ else:
+ return (0, None)
+
+# Given 'haystack', see if any prefix of 'needle' is at its end. This
+# assumes an exact match has already been checked. Return the number of
+# characters matched.
+# for example:
+# f_p_a_e ("qwerty\r", "\r\n") => 1
+# f_p_a_e ("qwertydkjf", "\r\n") => 0
+# f_p_a_e ("qwerty\r\n", "\r\n") => <undefined>
+
+# this could maybe be made faster with a computed regex?
+# [answer: no; circa Python-2.0, Jan 2001]
+# new python: 28961/s
+# old python: 18307/s
+# re: 12820/s
+# regex: 14035/s
+
+def find_prefix_at_end (haystack, needle):
+ l = len(needle) - 1
+ while l and not haystack.endswith(needle[:l]):
+ l -= 1
+ return l
diff --git a/lib-python/3.2/asyncore.py b/lib-python/3.2/asyncore.py
new file mode 100644
--- /dev/null
+++ b/lib-python/3.2/asyncore.py
@@ -0,0 +1,663 @@
+# -*- Mode: Python -*-
+# Id: asyncore.py,v 2.51 2000/09/07 22:29:26 rushing Exp
+# Author: Sam Rushing <rushing at nightmare.com>
+
+# ======================================================================
+# Copyright 1996 by Sam Rushing
+#
+# All Rights Reserved
+#
+# Permission to use, copy, modify, and distribute this software and
+# its documentation for any purpose and without fee is hereby
+# granted, provided that the above copyright notice appear in all
+# copies and that both that copyright notice and this permission
+# notice appear in supporting documentation, and that the name of Sam
+# Rushing not be used in advertising or publicity pertaining to
+# distribution of the software without specific, written prior
+# permission.
+#
+# SAM RUSHING DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
+# INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN
+# NO EVENT SHALL SAM RUSHING BE LIABLE FOR ANY SPECIAL, INDIRECT OR
+# CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
+# OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT,
+# NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
+# CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+# ======================================================================
+
+"""Basic infrastructure for asynchronous socket service clients and servers.
+
+There are only two ways to have a program on a single processor do "more
+than one thing at a time". Multi-threaded programming is the simplest and
+most popular way to do it, but there is another very different technique,
+that lets you have nearly all the advantages of multi-threading, without
+actually using multiple threads. it's really only practical if your program
+is largely I/O bound. If your program is CPU bound, then pre-emptive
+scheduled threads are probably what you really need. Network servers are
+rarely CPU-bound, however.
+
+If your operating system supports the select() system call in its I/O
+library (and nearly all do), then you can use it to juggle multiple
+communication channels at once; doing other work while your I/O is taking
+place in the "background." Although this strategy can seem strange and
+complex, especially at first, it is in many ways easier to understand and
+control than multi-threaded programming. The module documented here solves
+many of the difficult problems for you, making the task of building
+sophisticated high-performance network servers and clients a snap.
+"""
+
+import select
+import socket
+import sys
+import time
+import warnings
+
+import os
+from errno import EALREADY, EINPROGRESS, EWOULDBLOCK, ECONNRESET, EINVAL, \
+ ENOTCONN, ESHUTDOWN, EINTR, EISCONN, EBADF, ECONNABORTED, EPIPE, EAGAIN, \
+ errorcode
+
+_DISCONNECTED = frozenset((ECONNRESET, ENOTCONN, ESHUTDOWN, ECONNABORTED, EPIPE,
+ EBADF))
+
+try:
+ socket_map
+except NameError:
+ socket_map = {}
+
+def _strerror(err):
+ try:
+ return os.strerror(err)
+ except (ValueError, OverflowError, NameError):
+ if err in errorcode:
+ return errorcode[err]
+ return "Unknown error %s" %err
+
+class ExitNow(Exception):
+ pass
+
+_reraised_exceptions = (ExitNow, KeyboardInterrupt, SystemExit)
+
+def read(obj):
+ try:
+ obj.handle_read_event()
+ except _reraised_exceptions:
+ raise
+ except:
+ obj.handle_error()
+
+def write(obj):
+ try:
+ obj.handle_write_event()
+ except _reraised_exceptions:
+ raise
+ except:
+ obj.handle_error()
+
+def _exception(obj):
+ try:
+ obj.handle_expt_event()
+ except _reraised_exceptions:
+ raise
+ except:
+ obj.handle_error()
+
+def readwrite(obj, flags):
+ try:
+ if flags & select.POLLIN:
+ obj.handle_read_event()
+ if flags & select.POLLOUT:
+ obj.handle_write_event()
+ if flags & select.POLLPRI:
+ obj.handle_expt_event()
+ if flags & (select.POLLHUP | select.POLLERR | select.POLLNVAL):
+ obj.handle_close()
+ except socket.error as e:
+ if e.args[0] not in _DISCONNECTED:
+ obj.handle_error()
+ else:
+ obj.handle_close()
+ except _reraised_exceptions:
+ raise
+ except:
+ obj.handle_error()
+
+def poll(timeout=0.0, map=None):
+ if map is None:
+ map = socket_map
+ if map:
+ r = []; w = []; e = []
+ for fd, obj in list(map.items()):
+ is_r = obj.readable()
+ is_w = obj.writable()
+ if is_r:
+ r.append(fd)
+ # accepting sockets should not be writable
+ if is_w and not obj.accepting:
+ w.append(fd)
+ if is_r or is_w:
+ e.append(fd)
+ if [] == r == w == e:
+ time.sleep(timeout)
+ return
+
+ try:
+ r, w, e = select.select(r, w, e, timeout)
+ except select.error as err:
+ if err.args[0] != EINTR:
+ raise
+ else:
+ return
+
+ for fd in r:
+ obj = map.get(fd)
+ if obj is None:
+ continue
+ read(obj)
+
+ for fd in w:
+ obj = map.get(fd)
+ if obj is None:
+ continue
+ write(obj)
+
+ for fd in e:
+ obj = map.get(fd)
+ if obj is None:
+ continue
+ _exception(obj)
+
+def poll2(timeout=0.0, map=None):
+ # Use the poll() support added to the select module in Python 2.0
+ if map is None:
+ map = socket_map
+ if timeout is not None:
+ # timeout is in milliseconds
+ timeout = int(timeout*1000)
+ pollster = select.poll()
+ if map:
+ for fd, obj in list(map.items()):
+ flags = 0
+ if obj.readable():
+ flags |= select.POLLIN | select.POLLPRI
+ # accepting sockets should not be writable
+ if obj.writable() and not obj.accepting:
+ flags |= select.POLLOUT
+ if flags:
+ # Only check for exceptions if object was either readable
+ # or writable.
+ flags |= select.POLLERR | select.POLLHUP | select.POLLNVAL
+ pollster.register(fd, flags)
+ try:
+ r = pollster.poll(timeout)
+ except select.error as err:
+ if err.args[0] != EINTR:
+ raise
+ r = []
+ for fd, flags in r:
+ obj = map.get(fd)
+ if obj is None:
+ continue
+ readwrite(obj, flags)
+
+poll3 = poll2 # Alias for backward compatibility
+
+def loop(timeout=30.0, use_poll=False, map=None, count=None):
+ if map is None:
+ map = socket_map
+
+ if use_poll and hasattr(select, 'poll'):
+ poll_fun = poll2
+ else:
+ poll_fun = poll
+
+ if count is None:
+ while map:
+ poll_fun(timeout, map)
+
+ else:
+ while map and count > 0:
+ poll_fun(timeout, map)
+ count = count - 1
+
+class dispatcher:
+
+ debug = False
+ connected = False
+ accepting = False
+ closing = False
+ addr = None
+ ignore_log_types = frozenset(['warning'])
+
+ def __init__(self, sock=None, map=None):
+ if map is None:
+ self._map = socket_map
+ else:
+ self._map = map
+
+ self._fileno = None
+
+ if sock:
+ # Set to nonblocking just to make sure for cases where we
+ # get a socket from a blocking source.
+ sock.setblocking(0)
+ self.set_socket(sock, map)
+ self.connected = True
+ # The constructor no longer requires that the socket
+ # passed be connected.
+ try:
+ self.addr = sock.getpeername()
+ except socket.error as err:
+ if err.args[0] == ENOTCONN:
+ # To handle the case where we got an unconnected
+ # socket.
+ self.connected = False
+ else:
+ # The socket is broken in some unknown way, alert
+ # the user and remove it from the map (to prevent
+ # polling of broken sockets).
+ self.del_channel(map)
+ raise
+ else:
+ self.socket = None
+
+ def __repr__(self):
+ status = [self.__class__.__module__+"."+self.__class__.__name__]
+ if self.accepting and self.addr:
+ status.append('listening')
+ elif self.connected:
+ status.append('connected')
+ if self.addr is not None:
+ try:
+ status.append('%s:%d' % self.addr)
+ except TypeError:
+ status.append(repr(self.addr))
+ return '<%s at %#x>' % (' '.join(status), id(self))
+
+ __str__ = __repr__
+
+ def add_channel(self, map=None):
+ #self.log_info('adding channel %s' % self)
+ if map is None:
+ map = self._map
+ map[self._fileno] = self
+
+ def del_channel(self, map=None):
+ fd = self._fileno
+ if map is None:
+ map = self._map
+ if fd in map:
+ #self.log_info('closing channel %d:%s' % (fd, self))
+ del map[fd]
+ self._fileno = None
+
+ def create_socket(self, family, type):
+ self.family_and_type = family, type
+ sock = socket.socket(family, type)
+ sock.setblocking(0)
+ self.set_socket(sock)
+
+ def set_socket(self, sock, map=None):
+ self.socket = sock
+## self.__dict__['socket'] = sock
+ self._fileno = sock.fileno()
+ self.add_channel(map)
+
+ def set_reuse_addr(self):
+ # try to re-use a server port if possible
+ try:
+ self.socket.setsockopt(
+ socket.SOL_SOCKET, socket.SO_REUSEADDR,
+ self.socket.getsockopt(socket.SOL_SOCKET,
+ socket.SO_REUSEADDR) | 1
+ )
+ except socket.error:
+ pass
+
+ # ==================================================
+ # predicates for select()
+ # these are used as filters for the lists of sockets
+ # to pass to select().
+ # ==================================================
+
+ def readable(self):
+ return True
+
+ def writable(self):
+ return True
+
+ # ==================================================
+ # socket object methods.
+ # ==================================================
+
+ def listen(self, num):
+ self.accepting = True
+ if os.name == 'nt' and num > 5:
+ num = 5
+ return self.socket.listen(num)
+
+ def bind(self, addr):
+ self.addr = addr
+ return self.socket.bind(addr)
+
+ def connect(self, address):
+ self.connected = False
+ err = self.socket.connect_ex(address)
+ if err in (EINPROGRESS, EALREADY, EWOULDBLOCK) \
+ or err == EINVAL and os.name in ('nt', 'ce'):
+ return
+ if err in (0, EISCONN):
+ self.addr = address
+ self.handle_connect_event()
+ else:
+ raise socket.error(err, errorcode[err])
+
+ def accept(self):
+ # XXX can return either an address pair or None
+ try:
+ conn, addr = self.socket.accept()
+ except TypeError:
+ return None
+ except socket.error as why:
+ if why.args[0] in (EWOULDBLOCK, ECONNABORTED, EAGAIN):
+ return None
+ else:
+ raise
+ else:
+ return conn, addr
+
+ def send(self, data):
+ try:
+ result = self.socket.send(data)
+ return result
+ except socket.error as why:
+ if why.args[0] == EWOULDBLOCK:
+ return 0
+ elif why.args[0] in _DISCONNECTED:
+ self.handle_close()
+ return 0
+ else:
+ raise
+
+ def recv(self, buffer_size):
+ try:
+ data = self.socket.recv(buffer_size)
+ if not data:
+ # a closed connection is indicated by signaling
+ # a read condition, and having recv() return 0.
+ self.handle_close()
+ return b''
+ else:
+ return data
+ except socket.error as why:
+ # winsock sometimes throws ENOTCONN
+ if why.args[0] in _DISCONNECTED:
+ self.handle_close()
+ return b''
+ else:
+ raise
+
+ def close(self):
+ self.connected = False
+ self.accepting = False
+ self.del_channel()
+ try:
+ self.socket.close()
+ except socket.error as why:
+ if why.args[0] not in (ENOTCONN, EBADF):
+ raise
+
+ # cheap inheritance, used to pass all other attribute
+ # references to the underlying socket object.
+ def __getattr__(self, attr):
+ try:
+ retattr = getattr(self.socket, attr)
+ except AttributeError:
+ raise AttributeError("%s instance has no attribute '%s'"
+ %(self.__class__.__name__, attr))
+ else:
+ msg = "%(me)s.%(attr)s is deprecated; use %(me)s.socket.%(attr)s " \
+ "instead" % {'me' : self.__class__.__name__, 'attr' : attr}
+ warnings.warn(msg, DeprecationWarning, stacklevel=2)
+ return retattr
+
+ # log and log_info may be overridden to provide more sophisticated
+ # logging and warning methods. In general, log is for 'hit' logging
+ # and 'log_info' is for informational, warning and error logging.
+
+ def log(self, message):
+ sys.stderr.write('log: %s\n' % str(message))
+
+ def log_info(self, message, type='info'):
+ if type not in self.ignore_log_types:
+ print('%s: %s' % (type, message))
+
+ def handle_read_event(self):
+ if self.accepting:
+ # accepting sockets are never connected, they "spawn" new
+ # sockets that are connected
+ self.handle_accept()
+ elif not self.connected:
+ self.handle_connect_event()
+ self.handle_read()
+ else:
+ self.handle_read()
+
+ def handle_connect_event(self):
+ err = self.socket.getsockopt(socket.SOL_SOCKET, socket.SO_ERROR)
+ if err != 0:
+ raise socket.error(err, _strerror(err))
+ self.handle_connect()
+ self.connected = True
+
+ def handle_write_event(self):
+ if self.accepting:
+ # Accepting sockets shouldn't get a write event.
+ # We will pretend it didn't happen.
+ return
+
+ if not self.connected:
+ #check for errors
+ err = self.socket.getsockopt(socket.SOL_SOCKET, socket.SO_ERROR)
+ if err != 0:
+ raise socket.error(err, _strerror(err))
+
+ self.handle_connect_event()
+ self.handle_write()
+
+ def handle_expt_event(self):
+ # handle_expt_event() is called if there might be an error on the
+ # socket, or if there is OOB data
+ # check for the error condition first
+ err = self.socket.getsockopt(socket.SOL_SOCKET, socket.SO_ERROR)
+ if err != 0:
+ # we can get here when select.select() says that there is an
+ # exceptional condition on the socket
+ # since there is an error, we'll go ahead and close the socket
+ # like we would in a subclassed handle_read() that received no
+ # data
+ self.handle_close()
+ else:
+ self.handle_expt()
+
+ def handle_error(self):
+ nil, t, v, tbinfo = compact_traceback()
+
+ # sometimes a user repr method will crash.
+ try:
+ self_repr = repr(self)
+ except:
+ self_repr = '<__repr__(self) failed for object at %0x>' % id(self)
+
+ self.log_info(
+ 'uncaptured python exception, closing channel %s (%s:%s %s)' % (
+ self_repr,
+ t,
+ v,
+ tbinfo
+ ),
+ 'error'
+ )
+ self.handle_close()
+
+ def handle_expt(self):
+ self.log_info('unhandled incoming priority event', 'warning')
+
+ def handle_read(self):
+ self.log_info('unhandled read event', 'warning')
+
+ def handle_write(self):
+ self.log_info('unhandled write event', 'warning')
+
+ def handle_connect(self):
+ self.log_info('unhandled connect event', 'warning')
+
+ def handle_accept(self):
+ pair = self.accept()
+ if pair is not None:
+ self.handle_accepted(*pair)
+
+ def handle_accepted(self, sock, addr):
+ sock.close()
+ self.log_info('unhandled accepted event', 'warning')
+
+ def handle_close(self):
+ self.log_info('unhandled close event', 'warning')
+ self.close()
+
+# ---------------------------------------------------------------------------
+# adds simple buffered output capability, useful for simple clients.
+# [for more sophisticated usage use asynchat.async_chat]
+# ---------------------------------------------------------------------------
+
+class dispatcher_with_send(dispatcher):
+
+ def __init__(self, sock=None, map=None):
+ dispatcher.__init__(self, sock, map)
+ self.out_buffer = b''
+
+ def initiate_send(self):
+ num_sent = 0
+ num_sent = dispatcher.send(self, self.out_buffer[:512])
+ self.out_buffer = self.out_buffer[num_sent:]
+
+ def handle_write(self):
+ self.initiate_send()
+
+ def writable(self):
+ return (not self.connected) or len(self.out_buffer)
+
+ def send(self, data):
+ if self.debug:
+ self.log_info('sending %s' % repr(data))
+ self.out_buffer = self.out_buffer + data
+ self.initiate_send()
+
+# ---------------------------------------------------------------------------
+# used for debugging.
+# ---------------------------------------------------------------------------
+
+def compact_traceback():
+ t, v, tb = sys.exc_info()
+ tbinfo = []
+ if not tb: # Must have a traceback
+ raise AssertionError("traceback does not exist")
+ while tb:
+ tbinfo.append((
+ tb.tb_frame.f_code.co_filename,
+ tb.tb_frame.f_code.co_name,
+ str(tb.tb_lineno)
+ ))
+ tb = tb.tb_next
+
+ # just to be safe
+ del tb
+
+ file, function, line = tbinfo[-1]
+ info = ' '.join(['[%s|%s|%s]' % x for x in tbinfo])
+ return (file, function, line), t, v, info
+
+def close_all(map=None, ignore_all=False):
+ if map is None:
+ map = socket_map
+ for x in list(map.values()):
+ try:
+ x.close()
+ except OSError as x:
+ if x.args[0] == EBADF:
+ pass
+ elif not ignore_all:
+ raise
+ except _reraised_exceptions:
+ raise
+ except:
+ if not ignore_all:
+ raise
+ map.clear()
+
+# Asynchronous File I/O:
+#
+# After a little research (reading man pages on various unixen, and
+# digging through the linux kernel), I've determined that select()
+# isn't meant for doing asynchronous file i/o.
+# Heartening, though - reading linux/mm/filemap.c shows that linux
+# supports asynchronous read-ahead. So _MOST_ of the time, the data
+# will be sitting in memory for us already when we go to read it.
+#
+# What other OS's (besides NT) support async file i/o? [VMS?]
+#
+# Regardless, this is useful for pipes, and stdin/stdout...
+
+if os.name == 'posix':
+ import fcntl
+
+ class file_wrapper:
+ # Here we override just enough to make a file
+ # look like a socket for the purposes of asyncore.
+ # The passed fd is automatically os.dup()'d
+
+ def __init__(self, fd):
+ self.fd = os.dup(fd)
+
+ def recv(self, *args):
+ return os.read(self.fd, *args)
+
+ def send(self, *args):
+ return os.write(self.fd, *args)
+
+ def getsockopt(self, level, optname, buflen=None):
+ if (level == socket.SOL_SOCKET and
+ optname == socket.SO_ERROR and
+ not buflen):
+ return 0
+ raise NotImplementedError("Only asyncore specific behaviour "
+ "implemented.")
+
+ read = recv
+ write = send
+
+ def close(self):
+ os.close(self.fd)
+
+ def fileno(self):
+ return self.fd
+
+ class file_dispatcher(dispatcher):
+
+ def __init__(self, fd, map=None):
+ dispatcher.__init__(self, None, map)
+ self.connected = True
+ try:
+ fd = fd.fileno()
+ except AttributeError:
+ pass
+ self.set_file(fd)
+ # set it to non-blocking mode
+ flags = fcntl.fcntl(fd, fcntl.F_GETFL, 0)
+ flags = flags | os.O_NONBLOCK
+ fcntl.fcntl(fd, fcntl.F_SETFL, flags)
+
+ def set_file(self, fd):
+ self.socket = file_wrapper(fd)
+ self._fileno = self.socket.fileno()
+ self.add_channel()
diff --git a/lib-python/3.2/base64.py b/lib-python/3.2/base64.py
new file mode 100755
--- /dev/null
+++ b/lib-python/3.2/base64.py
@@ -0,0 +1,408 @@
+#! /usr/bin/env python3
+
+"""RFC 3548: Base16, Base32, Base64 Data Encodings"""
+
+# Modified 04-Oct-1995 by Jack Jansen to use binascii module
+# Modified 30-Dec-2003 by Barry Warsaw to add full RFC 3548 support
+# Modified 22-May-2007 by Guido van Rossum to use bytes everywhere
+
+import re
+import struct
+import binascii
+
+
+__all__ = [
+ # Legacy interface exports traditional RFC 1521 Base64 encodings
+ 'encode', 'decode', 'encodebytes', 'decodebytes',
+ # Generalized interface for other encodings
+ 'b64encode', 'b64decode', 'b32encode', 'b32decode',
+ 'b16encode', 'b16decode',
+ # Standard Base64 encoding
+ 'standard_b64encode', 'standard_b64decode',
+ # Some common Base64 alternatives. As referenced by RFC 3458, see thread
+ # starting at:
+ #
+ # http://zgp.org/pipermail/p2p-hackers/2001-September/000316.html
+ 'urlsafe_b64encode', 'urlsafe_b64decode',
+ ]
+
+
+bytes_types = (bytes, bytearray) # Types acceptable as binary data
+
+
+def _translate(s, altchars):
+ if not isinstance(s, bytes_types):
+ raise TypeError("expected bytes, not %s" % s.__class__.__name__)
+ translation = bytearray(range(256))
+ for k, v in altchars.items():
+ translation[ord(k)] = v[0]
+ return s.translate(translation)
+
+
+
+# Base64 encoding/decoding uses binascii
+
+def b64encode(s, altchars=None):
+ """Encode a byte string using Base64.
+
+ s is the byte string to encode. Optional altchars must be a byte
+ string of length 2 which specifies an alternative alphabet for the
+ '+' and '/' characters. This allows an application to
+ e.g. generate url or filesystem safe Base64 strings.
+
+ The encoded byte string is returned.
+ """
+ if not isinstance(s, bytes_types):
+ raise TypeError("expected bytes, not %s" % s.__class__.__name__)
+ # Strip off the trailing newline
+ encoded = binascii.b2a_base64(s)[:-1]
+ if altchars is not None:
+ if not isinstance(altchars, bytes_types):
+ raise TypeError("expected bytes, not %s"
+ % altchars.__class__.__name__)
+ assert len(altchars) == 2, repr(altchars)
+ return _translate(encoded, {'+': altchars[0:1], '/': altchars[1:2]})
+ return encoded
+
+
+def b64decode(s, altchars=None, validate=False):
+ """Decode a Base64 encoded byte string.
+
+ s is the byte string to decode. Optional altchars must be a
+ string of length 2 which specifies the alternative alphabet used
+ instead of the '+' and '/' characters.
+
+ The decoded string is returned. A binascii.Error is raised if s is
+ incorrectly padded.
+
+ If validate is False (the default), non-base64-alphabet characters are
+ discarded prior to the padding check. If validate is True,
+ non-base64-alphabet characters in the input result in a binascii.Error.
+ """
+ if not isinstance(s, bytes_types):
+ raise TypeError("expected bytes, not %s" % s.__class__.__name__)
+ if altchars is not None:
+ if not isinstance(altchars, bytes_types):
+ raise TypeError("expected bytes, not %s"
+ % altchars.__class__.__name__)
+ assert len(altchars) == 2, repr(altchars)
+ s = _translate(s, {chr(altchars[0]): b'+', chr(altchars[1]): b'/'})
+ if validate and not re.match(b'^[A-Za-z0-9+/]*={0,2}$', s):
+ raise binascii.Error('Non-base64 digit found')
+ return binascii.a2b_base64(s)
+
+
+def standard_b64encode(s):
+ """Encode a byte string using the standard Base64 alphabet.
+
+ s is the byte string to encode. The encoded byte string is returned.
+ """
+ return b64encode(s)
+
+def standard_b64decode(s):
+ """Decode a byte string encoded with the standard Base64 alphabet.
+
+ s is the byte string to decode. The decoded byte string is
+ returned. binascii.Error is raised if the input is incorrectly
+ padded or if there are non-alphabet characters present in the
+ input.
+ """
+ return b64decode(s)
+
+def urlsafe_b64encode(s):
+ """Encode a byte string using a url-safe Base64 alphabet.
+
+ s is the byte string to encode. The encoded byte string is
+ returned. The alphabet uses '-' instead of '+' and '_' instead of
+ '/'.
+ """
+ return b64encode(s, b'-_')
+
+def urlsafe_b64decode(s):
+ """Decode a byte string encoded with the standard Base64 alphabet.
+
+ s is the byte string to decode. The decoded byte string is
+ returned. binascii.Error is raised if the input is incorrectly
+ padded or if there are non-alphabet characters present in the
+ input.
+
+ The alphabet uses '-' instead of '+' and '_' instead of '/'.
+ """
+ return b64decode(s, b'-_')
+
+
+
+# Base32 encoding/decoding must be done in Python
+_b32alphabet = {
+ 0: b'A', 9: b'J', 18: b'S', 27: b'3',
+ 1: b'B', 10: b'K', 19: b'T', 28: b'4',
+ 2: b'C', 11: b'L', 20: b'U', 29: b'5',
+ 3: b'D', 12: b'M', 21: b'V', 30: b'6',
+ 4: b'E', 13: b'N', 22: b'W', 31: b'7',
+ 5: b'F', 14: b'O', 23: b'X',
+ 6: b'G', 15: b'P', 24: b'Y',
+ 7: b'H', 16: b'Q', 25: b'Z',
+ 8: b'I', 17: b'R', 26: b'2',
+ }
+
+_b32tab = [v[0] for k, v in sorted(_b32alphabet.items())]
+_b32rev = dict([(v[0], k) for k, v in _b32alphabet.items()])
+
+
+def b32encode(s):
+ """Encode a byte string using Base32.
+
+ s is the byte string to encode. The encoded byte string is returned.
+ """
+ if not isinstance(s, bytes_types):
+ raise TypeError("expected bytes, not %s" % s.__class__.__name__)
+ quanta, leftover = divmod(len(s), 5)
+ # Pad the last quantum with zero bits if necessary
+ if leftover:
+ s = s + bytes(5 - leftover) # Don't use += !
+ quanta += 1
+ encoded = bytes()
+ for i in range(quanta):
+ # c1 and c2 are 16 bits wide, c3 is 8 bits wide. The intent of this
+ # code is to process the 40 bits in units of 5 bits. So we take the 1
+ # leftover bit of c1 and tack it onto c2. Then we take the 2 leftover
+ # bits of c2 and tack them onto c3. The shifts and masks are intended
+ # to give us values of exactly 5 bits in width.
+ c1, c2, c3 = struct.unpack('!HHB', s[i*5:(i+1)*5])
+ c2 += (c1 & 1) << 16 # 17 bits wide
+ c3 += (c2 & 3) << 8 # 10 bits wide
+ encoded += bytes([_b32tab[c1 >> 11], # bits 1 - 5
+ _b32tab[(c1 >> 6) & 0x1f], # bits 6 - 10
+ _b32tab[(c1 >> 1) & 0x1f], # bits 11 - 15
+ _b32tab[c2 >> 12], # bits 16 - 20 (1 - 5)
+ _b32tab[(c2 >> 7) & 0x1f], # bits 21 - 25 (6 - 10)
+ _b32tab[(c2 >> 2) & 0x1f], # bits 26 - 30 (11 - 15)
+ _b32tab[c3 >> 5], # bits 31 - 35 (1 - 5)
+ _b32tab[c3 & 0x1f], # bits 36 - 40 (1 - 5)
+ ])
+ # Adjust for any leftover partial quanta
+ if leftover == 1:
+ return encoded[:-6] + b'======'
+ elif leftover == 2:
+ return encoded[:-4] + b'===='
+ elif leftover == 3:
+ return encoded[:-3] + b'==='
+ elif leftover == 4:
+ return encoded[:-1] + b'='
+ return encoded
+
+
+def b32decode(s, casefold=False, map01=None):
+ """Decode a Base32 encoded byte string.
+
+ s is the byte string to decode. Optional casefold is a flag
+ specifying whether a lowercase alphabet is acceptable as input.
+ For security purposes, the default is False.
+
+ RFC 3548 allows for optional mapping of the digit 0 (zero) to the
+ letter O (oh), and for optional mapping of the digit 1 (one) to
+ either the letter I (eye) or letter L (el). The optional argument
+ map01 when not None, specifies which letter the digit 1 should be
+ mapped to (when map01 is not None, the digit 0 is always mapped to
+ the letter O). For security purposes the default is None, so that
+ 0 and 1 are not allowed in the input.
+
+ The decoded byte string is returned. binascii.Error is raised if
+ the input is incorrectly padded or if there are non-alphabet
+ characters present in the input.
+ """
+ if not isinstance(s, bytes_types):
+ raise TypeError("expected bytes, not %s" % s.__class__.__name__)
+ quanta, leftover = divmod(len(s), 8)
+ if leftover:
+ raise binascii.Error('Incorrect padding')
+ # Handle section 2.4 zero and one mapping. The flag map01 will be either
+ # False, or the character to map the digit 1 (one) to. It should be
+ # either L (el) or I (eye).
+ if map01 is not None:
+ if not isinstance(map01, bytes_types):
+ raise TypeError("expected bytes, not %s" % map01.__class__.__name__)
+ assert len(map01) == 1, repr(map01)
+ s = _translate(s, {b'0': b'O', b'1': map01})
+ if casefold:
+ s = s.upper()
+ # Strip off pad characters from the right. We need to count the pad
+ # characters because this will tell us how many null bytes to remove from
+ # the end of the decoded string.
+ padchars = 0
+ mo = re.search(b'(?P<pad>[=]*)$', s)
+ if mo:
+ padchars = len(mo.group('pad'))
+ if padchars > 0:
+ s = s[:-padchars]
+ # Now decode the full quanta
+ parts = []
+ acc = 0
+ shift = 35
+ for c in s:
+ val = _b32rev.get(c)
+ if val is None:
+ raise TypeError('Non-base32 digit found')
+ acc += _b32rev[c] << shift
+ shift -= 5
+ if shift < 0:
+ parts.append(binascii.unhexlify(bytes('%010x' % acc, "ascii")))
+ acc = 0
+ shift = 35
+ # Process the last, partial quanta
+ last = binascii.unhexlify(bytes('%010x' % acc, "ascii"))
+ if padchars == 0:
+ last = b'' # No characters
+ elif padchars == 1:
+ last = last[:-1]
+ elif padchars == 3:
+ last = last[:-2]
+ elif padchars == 4:
+ last = last[:-3]
+ elif padchars == 6:
+ last = last[:-4]
+ else:
+ raise binascii.Error('Incorrect padding')
+ parts.append(last)
+ return b''.join(parts)
+
+
+
+# RFC 3548, Base 16 Alphabet specifies uppercase, but hexlify() returns
+# lowercase. The RFC also recommends against accepting input case
+# insensitively.
+def b16encode(s):
+ """Encode a byte string using Base16.
+
+ s is the byte string to encode. The encoded byte string is returned.
+ """
+ if not isinstance(s, bytes_types):
+ raise TypeError("expected bytes, not %s" % s.__class__.__name__)
+ return binascii.hexlify(s).upper()
+
+
+def b16decode(s, casefold=False):
+ """Decode a Base16 encoded byte string.
+
+ s is the byte string to decode. Optional casefold is a flag
+ specifying whether a lowercase alphabet is acceptable as input.
+ For security purposes, the default is False.
+
+ The decoded byte string is returned. binascii.Error is raised if
+ s were incorrectly padded or if there are non-alphabet characters
+ present in the string.
+ """
+ if not isinstance(s, bytes_types):
+ raise TypeError("expected bytes, not %s" % s.__class__.__name__)
+ if casefold:
+ s = s.upper()
+ if re.search(b'[^0-9A-F]', s):
+ raise binascii.Error('Non-base16 digit found')
+ return binascii.unhexlify(s)
+
+
+
+# Legacy interface. This code could be cleaned up since I don't believe
+# binascii has any line length limitations. It just doesn't seem worth it
+# though. The files should be opened in binary mode.
+
+MAXLINESIZE = 76 # Excluding the CRLF
+MAXBINSIZE = (MAXLINESIZE//4)*3
+
+def encode(input, output):
+ """Encode a file; input and output are binary files."""
+ while True:
+ s = input.read(MAXBINSIZE)
+ if not s:
+ break
+ while len(s) < MAXBINSIZE:
+ ns = input.read(MAXBINSIZE-len(s))
+ if not ns:
+ break
+ s += ns
+ line = binascii.b2a_base64(s)
+ output.write(line)
+
+
+def decode(input, output):
+ """Decode a file; input and output are binary files."""
+ while True:
+ line = input.readline()
+ if not line:
+ break
+ s = binascii.a2b_base64(line)
+ output.write(s)
+
+
+def encodebytes(s):
+ """Encode a bytestring into a bytestring containing multiple lines
+ of base-64 data."""
+ if not isinstance(s, bytes_types):
+ raise TypeError("expected bytes, not %s" % s.__class__.__name__)
+ pieces = []
+ for i in range(0, len(s), MAXBINSIZE):
+ chunk = s[i : i + MAXBINSIZE]
+ pieces.append(binascii.b2a_base64(chunk))
+ return b"".join(pieces)
+
+def encodestring(s):
+ """Legacy alias of encodebytes()."""
+ import warnings
+ warnings.warn("encodestring() is a deprecated alias, use encodebytes()",
+ DeprecationWarning, 2)
+ return encodebytes(s)
+
+
+def decodebytes(s):
+ """Decode a bytestring of base-64 data into a bytestring."""
+ if not isinstance(s, bytes_types):
+ raise TypeError("expected bytes, not %s" % s.__class__.__name__)
+ return binascii.a2b_base64(s)
+
+def decodestring(s):
+ """Legacy alias of decodebytes()."""
+ import warnings
+ warnings.warn("decodestring() is a deprecated alias, use decodebytes()",
+ DeprecationWarning, 2)
+ return decodebytes(s)
+
+
+# Usable as a script...
+def main():
+ """Small main program"""
+ import sys, getopt
+ try:
+ opts, args = getopt.getopt(sys.argv[1:], 'deut')
+ except getopt.error as msg:
+ sys.stdout = sys.stderr
+ print(msg)
+ print("""usage: %s [-d|-e|-u|-t] [file|-]
+ -d, -u: decode
+ -e: encode (default)
+ -t: encode and decode string 'Aladdin:open sesame'"""%sys.argv[0])
+ sys.exit(2)
+ func = encode
+ for o, a in opts:
+ if o == '-e': func = encode
+ if o == '-d': func = decode
+ if o == '-u': func = decode
+ if o == '-t': test(); return
+ if args and args[0] != '-':
+ with open(args[0], 'rb') as f:
+ func(f, sys.stdout.buffer)
+ else:
+ func(sys.stdin.buffer, sys.stdout.buffer)
+
+
+def test():
+ s0 = b"Aladdin:open sesame"
+ print(repr(s0))
+ s1 = encodebytes(s0)
+ print(repr(s1))
+ s2 = decodebytes(s1)
+ print(repr(s2))
+ assert s0 == s2
+
+
+if __name__ == '__main__':
+ main()
diff --git a/lib-python/3.2/bdb.py b/lib-python/3.2/bdb.py
new file mode 100644
--- /dev/null
+++ b/lib-python/3.2/bdb.py
@@ -0,0 +1,634 @@
+"""Debugger basics"""
+
+import fnmatch
+import sys
+import os
+
+__all__ = ["BdbQuit", "Bdb", "Breakpoint"]
+
+class BdbQuit(Exception):
+ """Exception to give up completely."""
+
+
+class Bdb:
+ """Generic Python debugger base class.
+
+ This class takes care of details of the trace facility;
+ a derived class should implement user interaction.
+ The standard debugger class (pdb.Pdb) is an example.
+ """
+
+ def __init__(self, skip=None):
+ self.skip = set(skip) if skip else None
+ self.breaks = {}
+ self.fncache = {}
+
+ def canonic(self, filename):
+ if filename == "<" + filename[1:-1] + ">":
+ return filename
+ canonic = self.fncache.get(filename)
+ if not canonic:
+ canonic = os.path.abspath(filename)
+ canonic = os.path.normcase(canonic)
+ self.fncache[filename] = canonic
+ return canonic
+
+ def reset(self):
+ import linecache
+ linecache.checkcache()
+ self.botframe = None
+ self._set_stopinfo(None, None)
+
+ def trace_dispatch(self, frame, event, arg):
+ if self.quitting:
+ return # None
+ if event == 'line':
+ return self.dispatch_line(frame)
+ if event == 'call':
+ return self.dispatch_call(frame, arg)
+ if event == 'return':
+ return self.dispatch_return(frame, arg)
+ if event == 'exception':
+ return self.dispatch_exception(frame, arg)
+ if event == 'c_call':
+ return self.trace_dispatch
+ if event == 'c_exception':
+ return self.trace_dispatch
+ if event == 'c_return':
+ return self.trace_dispatch
+ print('bdb.Bdb.dispatch: unknown debugging event:', repr(event))
+ return self.trace_dispatch
+
+ def dispatch_line(self, frame):
+ if self.stop_here(frame) or self.break_here(frame):
+ self.user_line(frame)
+ if self.quitting: raise BdbQuit
+ return self.trace_dispatch
+
+ def dispatch_call(self, frame, arg):
+ # XXX 'arg' is no longer used
+ if self.botframe is None:
+ # First call of dispatch since reset()
+ self.botframe = frame.f_back # (CT) Note that this may also be None!
+ return self.trace_dispatch
+ if not (self.stop_here(frame) or self.break_anywhere(frame)):
+ # No need to trace this function
+ return # None
+ self.user_call(frame, arg)
+ if self.quitting: raise BdbQuit
+ return self.trace_dispatch
+
+ def dispatch_return(self, frame, arg):
+ if self.stop_here(frame) or frame == self.returnframe:
+ self.user_return(frame, arg)
+ if self.quitting: raise BdbQuit
+ return self.trace_dispatch
+
+ def dispatch_exception(self, frame, arg):
+ if self.stop_here(frame):
+ self.user_exception(frame, arg)
+ if self.quitting: raise BdbQuit
+ return self.trace_dispatch
+
+ # Normally derived classes don't override the following
+ # methods, but they may if they want to redefine the
+ # definition of stopping and breakpoints.
+
+ def is_skipped_module(self, module_name):
+ for pattern in self.skip:
+ if fnmatch.fnmatch(module_name, pattern):
+ return True
+ return False
+
+ def stop_here(self, frame):
+ # (CT) stopframe may now also be None, see dispatch_call.
+ # (CT) the former test for None is therefore removed from here.
+ if self.skip and \
+ self.is_skipped_module(frame.f_globals.get('__name__')):
+ return False
+ if frame is self.stopframe:
+ if self.stoplineno == -1:
+ return False
+ return frame.f_lineno >= self.stoplineno
+ while frame is not None and frame is not self.stopframe:
+ if frame is self.botframe:
+ return True
+ frame = frame.f_back
+ return False
+
+ def break_here(self, frame):
+ filename = self.canonic(frame.f_code.co_filename)
+ if filename not in self.breaks:
+ return False
+ lineno = frame.f_lineno
+ if lineno not in self.breaks[filename]:
+ # The line itself has no breakpoint, but maybe the line is the
+ # first line of a function with breakpoint set by function name.
+ lineno = frame.f_code.co_firstlineno
+ if lineno not in self.breaks[filename]:
+ return False
+
+ # flag says ok to delete temp. bp
+ (bp, flag) = effective(filename, lineno, frame)
+ if bp:
+ self.currentbp = bp.number
+ if (flag and bp.temporary):
+ self.do_clear(str(bp.number))
+ return True
+ else:
+ return False
+
+ def do_clear(self, arg):
+ raise NotImplementedError("subclass of bdb must implement do_clear()")
+
+ def break_anywhere(self, frame):
+ return self.canonic(frame.f_code.co_filename) in self.breaks
+
+ # Derived classes should override the user_* methods
+ # to gain control.
+
+ def user_call(self, frame, argument_list):
+ """This method is called when there is the remote possibility
+ that we ever need to stop in this function."""
+ pass
+
+ def user_line(self, frame):
+ """This method is called when we stop or break at this line."""
+ pass
+
+ def user_return(self, frame, return_value):
+ """This method is called when a return trap is set here."""
+ pass
+
+ def user_exception(self, frame, exc_info):
+ """This method is called if an exception occurs,
+ but only if we are to stop at or just below this level."""
+ pass
+
+ def _set_stopinfo(self, stopframe, returnframe, stoplineno=0):
+ self.stopframe = stopframe
+ self.returnframe = returnframe
+ self.quitting = False
+ # stoplineno >= 0 means: stop at line >= the stoplineno
+ # stoplineno -1 means: don't stop at all
+ self.stoplineno = stoplineno
+
+ # Derived classes and clients can call the following methods
+ # to affect the stepping state.
+
+ def set_until(self, frame, lineno=None):
+ """Stop when the line with the line no greater than the current one is
+ reached or when returning from current frame"""
+ # the name "until" is borrowed from gdb
+ if lineno is None:
+ lineno = frame.f_lineno + 1
+ self._set_stopinfo(frame, frame, lineno)
+
+ def set_step(self):
+ """Stop after one line of code."""
+ self._set_stopinfo(None, None)
+
+ def set_next(self, frame):
+ """Stop on the next line in or below the given frame."""
+ self._set_stopinfo(frame, None)
+
+ def set_return(self, frame):
+ """Stop when returning from the given frame."""
+ self._set_stopinfo(frame.f_back, frame)
+
+ def set_trace(self, frame=None):
+ """Start debugging from `frame`.
+
+ If frame is not specified, debugging starts from caller's frame.
+ """
+ if frame is None:
+ frame = sys._getframe().f_back
+ self.reset()
+ while frame:
+ frame.f_trace = self.trace_dispatch
+ self.botframe = frame
+ frame = frame.f_back
+ self.set_step()
+ sys.settrace(self.trace_dispatch)
+
+ def set_continue(self):
+ # Don't stop except at breakpoints or when finished
+ self._set_stopinfo(self.botframe, None, -1)
+ if not self.breaks:
+ # no breakpoints; run without debugger overhead
+ sys.settrace(None)
+ frame = sys._getframe().f_back
+ while frame and frame is not self.botframe:
+ del frame.f_trace
+ frame = frame.f_back
+
+ def set_quit(self):
+ self.stopframe = self.botframe
+ self.returnframe = None
+ self.quitting = True
+ sys.settrace(None)
+
+ # Derived classes and clients can call the following methods
+ # to manipulate breakpoints. These methods return an
+ # error message is something went wrong, None if all is well.
+ # Set_break prints out the breakpoint line and file:lineno.
+ # Call self.get_*break*() to see the breakpoints or better
+ # for bp in Breakpoint.bpbynumber: if bp: bp.bpprint().
+
+ def set_break(self, filename, lineno, temporary=False, cond=None,
+ funcname=None):
+ filename = self.canonic(filename)
+ import linecache # Import as late as possible
+ line = linecache.getline(filename, lineno)
+ if not line:
+ return 'Line %s:%d does not exist' % (filename, lineno)
+ list = self.breaks.setdefault(filename, [])
+ if lineno not in list:
+ list.append(lineno)
+ bp = Breakpoint(filename, lineno, temporary, cond, funcname)
+
+ def _prune_breaks(self, filename, lineno):
+ if (filename, lineno) not in Breakpoint.bplist:
+ self.breaks[filename].remove(lineno)
+ if not self.breaks[filename]:
+ del self.breaks[filename]
+
+ def clear_break(self, filename, lineno):
+ filename = self.canonic(filename)
+ if filename not in self.breaks:
+ return 'There are no breakpoints in %s' % filename
+ if lineno not in self.breaks[filename]:
+ return 'There is no breakpoint at %s:%d' % (filename, lineno)
+ # If there's only one bp in the list for that file,line
+ # pair, then remove the breaks entry
+ for bp in Breakpoint.bplist[filename, lineno][:]:
+ bp.deleteMe()
+ self._prune_breaks(filename, lineno)
+
+ def clear_bpbynumber(self, arg):
+ try:
+ bp = self.get_bpbynumber(arg)
+ except ValueError as err:
+ return str(err)
+ bp.deleteMe()
+ self._prune_breaks(bp.file, bp.line)
+
+ def clear_all_file_breaks(self, filename):
+ filename = self.canonic(filename)
+ if filename not in self.breaks:
+ return 'There are no breakpoints in %s' % filename
+ for line in self.breaks[filename]:
+ blist = Breakpoint.bplist[filename, line]
+ for bp in blist:
+ bp.deleteMe()
+ del self.breaks[filename]
+
+ def clear_all_breaks(self):
+ if not self.breaks:
+ return 'There are no breakpoints'
+ for bp in Breakpoint.bpbynumber:
+ if bp:
+ bp.deleteMe()
+ self.breaks = {}
+
+ def get_bpbynumber(self, arg):
+ if not arg:
+ raise ValueError('Breakpoint number expected')
+ try:
+ number = int(arg)
+ except ValueError:
+ raise ValueError('Non-numeric breakpoint number %s' % arg)
+ try:
+ bp = Breakpoint.bpbynumber[number]
+ except IndexError:
+ raise ValueError('Breakpoint number %d out of range' % number)
+ if bp is None:
+ raise ValueError('Breakpoint %d already deleted' % number)
+ return bp
+
+ def get_break(self, filename, lineno):
+ filename = self.canonic(filename)
+ return filename in self.breaks and \
+ lineno in self.breaks[filename]
+
+ def get_breaks(self, filename, lineno):
+ filename = self.canonic(filename)
+ return filename in self.breaks and \
+ lineno in self.breaks[filename] and \
+ Breakpoint.bplist[filename, lineno] or []
More information about the pypy-commit
mailing list