json模块
json模块是实现序列化和反序列化的，主要用户不同程序之间的数据交换，首先来看一下:
dumps()序列化
import json
'''json模块是实现序列化和反序列话功能的'''
users = ["alex","tom","wupeiqi","sb","耿长学"]
mes = json.dumps(users) #实例化，并打印
print(mes)
运行结果如下：
["alex", "tom", "wupeiqi", "sb", "\u803f\u957f\u5b66"]
从上面可以看出，dumps其实是生成一个序列化的实例，这个后面会和dump进行区分，而且汉字非英文转化成的是字节码。
loads()反序列化
import json
'''json模块是实现序列化和反序列话功能的'''
users = ["alex","tom","wupeiqi","sb","耿长学"]
mes = json.dumps(users) #实例化，并打印
print("序列化:",mes) data = json.loads(mes)
print("反序列化：",data)
运行结果如下：
序列化: ["alex", "tom", "wupeiqi", "sb", "\u803f\u957f\u5b66"]
反序列化： ['alex', 'tom', 'wupeiqi', 'sb', '耿长学']
上面dumps()和loads()序列化和反序列化是在程序之间交互，即没有通过文件，只是以json.dumps()序列化一个实例，然后接收之后json.loads()进行反序列化，依次实现程序之间的交互。那么如何在文件中交互呢？
文件中的交互：
import json
'''json模块是实现序列化和反序列话功能的'''
users = ["alex","tom","wupeiqi","sb","耿长学"]
mes = json.dumps(users) #实例化，并打印
'''把mes序列化实例写入文件'''
with open("users",'w+') as fw:
fw.write(mes)
上面代码中，我们把序列化的实例写入到文件中，使用json.dumps()生成实例，fw.write()写入文件，需要通过文件的write()写入。
文件反序列化：
import json
with open('users','r+') as fr:
mess = json.loads(fr.read())
print(mess)
运行结果如下：
['alex', 'tom', 'wupeiqi', 'sb', '耿长学']
上面文件反序列化过程中，首先要把文件中的内容读取出来，因为是使用write()写进去的，因此要read()出来，然后再进行反序列化，生成一个实例。
下面我们来看看load()和dump()实现序列化和反序列化：
dump()序列化
import json
users = {"alex":"sb","wupeiqi":,"耿长学":}
with open("users","w+") as fw:
json.dump(users,fw)
从上面可以看出，json.dump()是直接把实例化的信息序列化到指定文件中，不需要write()来写入，直接可以自己来写入，而dumps()只是序列化成一个实例，还需要自己write()到文件中。
load()反序列化
import json
with open('users','r+') as fr:
users = json.load(fr)
print(users) 运行结果如下：
{'alex': 'sb', '耿长学': , 'wupeiqi': }
load()反序列化不需要读取之后才反序列化，直接可以从文件反序列化，因为是dump()进去的。
总结：
从上面dumps()、loads()和dump()、load()序列化和反序列化可以看出，dumps()是序列化生成一个实例，loads()是读取写进去的实例，dumps()和loads()主要用于不同程序或者接口之间的数据交换传输，而dump()和load()更适合于文件级别之间的读取和写入，两者之间还是有侧重点的。
这个不是说两者功能一样，用法不同，其实设计的时候侧重方向就是不一样的。
json源代码
r"""JSON (JavaScript Object Notation) <http://json.org> is a subset of
JavaScript syntax (ECMA- 3rd edition) used as a lightweight data
interchange format. :mod:`json` exposes an API familiar to users of the standard library
:mod:`marshal` and :mod:`pickle` modules. It is derived from a
version of the externally maintained simplejson library. Encoding basic Python object hierarchies:: >>> import json
>>> json.dumps(['foo', {'bar': ('baz', None, 1.0, )}])
'["foo", {"bar": ["baz", null, 1.0, 2]}]'
>>> print(json.dumps("\"foo\bar"))
"\"foo\bar"
>>> print(json.dumps('\u1234'))
"\u1234"
>>> print(json.dumps('\\'))
"\\"
>>> print(json.dumps({"c": , "b": , "a": }, sort_keys=True))
{"a": , "b": , "c": }
>>> from io import StringIO
>>> io = StringIO()
>>> json.dump(['streaming API'], io)
>>> io.getvalue()
'["streaming API"]' Compact encoding:: >>> import json
>>> from collections import OrderedDict
>>> mydict = OrderedDict([('', ), ('', )])
>>> json.dumps([,,,mydict], separators=(',', ':'))
'[1,2,3,{"4":5,"6":7}]' Pretty printing:: >>> import json
>>> print(json.dumps({'': , '': }, sort_keys=True, indent=))
{
"": ,
"":
} Decoding JSON:: >>> import json
>>> obj = ['foo', {'bar': ['baz', None, 1.0, ]}]
>>> json.loads('["foo", {"bar":["baz", null, 1.0, 2]}]') == obj
True
>>> json.loads('"\\"foo\\bar"') == '"foo\x08ar'
True
>>> from io import StringIO
>>> io = StringIO('["streaming API"]')
>>> json.load(io)[] == 'streaming API'
True Specializing JSON object decoding:: >>> import json
>>> def as_complex(dct):
... if '__complex__' in dct:
... return complex(dct['real'], dct['imag'])
... return dct
...
>>> json.loads('{"__complex__": true, "real": 1, "imag": 2}',
... object_hook=as_complex)
(+2j)
>>> from decimal import Decimal
>>> json.loads('1.1', parse_float=Decimal) == Decimal('1.1')
True Specializing JSON object encoding:: >>> import json
>>> def encode_complex(obj):
... if isinstance(obj, complex):
... return [obj.real, obj.imag]
... raise TypeError(repr(o) + " is not JSON serializable")
...
>>> json.dumps( + 1j, default=encode_complex)
'[2.0, 1.0]'
>>> json.JSONEncoder(default=encode_complex).encode( + 1j)
'[2.0, 1.0]'
>>> ''.join(json.JSONEncoder(default=encode_complex).iterencode( + 1j))
'[2.0, 1.0]' Using json.tool from the shell to validate and pretty-print:: $ echo '{"json":"obj"}' | python -m json.tool
{
"json": "obj"
}
$ echo '{ 1.2:3.4}' | python -m json.tool
Expecting property name enclosed in double quotes: line column (char )
"""
__version__ = '2.0.9'
__all__ = [
'dump', 'dumps', 'load', 'loads',
'JSONDecoder', 'JSONDecodeError', 'JSONEncoder',
] __author__ = 'Bob Ippolito <bob@redivi.com>' from .decoder import JSONDecoder, JSONDecodeError
from .encoder import JSONEncoder _default_encoder = JSONEncoder(
skipkeys=False,
ensure_ascii=True,
check_circular=True,
allow_nan=True,
indent=None,
separators=None,
default=None,
) def dump(obj, fp, skipkeys=False, ensure_ascii=True, check_circular=True,
allow_nan=True, cls=None, indent=None, separators=None,
default=None, sort_keys=False, **kw):
"""Serialize ``obj`` as a JSON formatted stream to ``fp`` (a
``.write()``-supporting file-like object). If ``skipkeys`` is true then ``dict`` keys that are not basic types
(``str``, ``int``, ``float``, ``bool``, ``None``) will be skipped
instead of raising a ``TypeError``. If ``ensure_ascii`` is false, then the strings written to ``fp`` can
contain non-ASCII characters if they appear in strings contained in
``obj``. Otherwise, all such characters are escaped in JSON strings. If ``check_circular`` is false, then the circular reference check
for container types will be skipped and a circular reference will
result in an ``OverflowError`` (or worse). If ``allow_nan`` is false, then it will be a ``ValueError`` to
serialize out of range ``float`` values (``nan``, ``inf``, ``-inf``)
in strict compliance of the JSON specification, instead of using the
JavaScript equivalents (``NaN``, ``Infinity``, ``-Infinity``). If ``indent`` is a non-negative integer, then JSON array elements and
object members will be pretty-printed with that indent level. An indent
level of will only insert newlines. ``None`` is the most compact
representation. If specified, ``separators`` should be an ``(item_separator, key_separator)``
tuple. The default is ``(', ', ': ')`` if *indent* is ``None`` and
``(',', ': ')`` otherwise. To get the most compact JSON representation,
you should specify ``(',', ':')`` to eliminate whitespace. ``default(obj)`` is a function that should return a serializable version
of obj or raise TypeError. The default simply raises TypeError. If *sort_keys* is ``True`` (default: ``False``), then the output of
dictionaries will be sorted by key. To use a custom ``JSONEncoder`` subclass (e.g. one that overrides the
``.default()`` method to serialize additional types), specify it with
the ``cls`` kwarg; otherwise ``JSONEncoder`` is used. """
# cached encoder
if (not skipkeys and ensure_ascii and
check_circular and allow_nan and
cls is None and indent is None and separators is None and
default is None and not sort_keys and not kw):
iterable = _default_encoder.iterencode(obj)
else:
if cls is None:
cls = JSONEncoder
iterable = cls(skipkeys=skipkeys, ensure_ascii=ensure_ascii,
check_circular=check_circular, allow_nan=allow_nan, indent=indent,
separators=separators,
default=default, sort_keys=sort_keys, **kw).iterencode(obj)
# could accelerate with writelines in some versions of Python, at
# a debuggability cost
for chunk in iterable:
fp.write(chunk) def dumps(obj, skipkeys=False, ensure_ascii=True, check_circular=True,
allow_nan=True, cls=None, indent=None, separators=None,
default=None, sort_keys=False, **kw):
"""Serialize ``obj`` to a JSON formatted ``str``. If ``skipkeys`` is true then ``dict`` keys that are not basic types
(``str``, ``int``, ``float``, ``bool``, ``None``) will be skipped
instead of raising a ``TypeError``. If ``ensure_ascii`` is false, then the return value can contain non-ASCII
characters if they appear in strings contained in ``obj``. Otherwise, all
such characters are escaped in JSON strings. If ``check_circular`` is false, then the circular reference check
for container types will be skipped and a circular reference will
result in an ``OverflowError`` (or worse). If ``allow_nan`` is false, then it will be a ``ValueError`` to
serialize out of range ``float`` values (``nan``, ``inf``, ``-inf``) in
strict compliance of the JSON specification, instead of using the
JavaScript equivalents (``NaN``, ``Infinity``, ``-Infinity``). If ``indent`` is a non-negative integer, then JSON array elements and
object members will be pretty-printed with that indent level. An indent
level of will only insert newlines. ``None`` is the most compact
representation. If specified, ``separators`` should be an ``(item_separator, key_separator)``
tuple. The default is ``(', ', ': ')`` if *indent* is ``None`` and
``(',', ': ')`` otherwise. To get the most compact JSON representation,
you should specify ``(',', ':')`` to eliminate whitespace. ``default(obj)`` is a function that should return a serializable version
of obj or raise TypeError. The default simply raises TypeError. If *sort_keys* is ``True`` (default: ``False``), then the output of
dictionaries will be sorted by key. To use a custom ``JSONEncoder`` subclass (e.g. one that overrides the
``.default()`` method to serialize additional types), specify it with
the ``cls`` kwarg; otherwise ``JSONEncoder`` is used. """
# cached encoder
if (not skipkeys and ensure_ascii and
check_circular and allow_nan and
cls is None and indent is None and separators is None and
default is None and not sort_keys and not kw):
return _default_encoder.encode(obj)
if cls is None:
cls = JSONEncoder
return cls(
skipkeys=skipkeys, ensure_ascii=ensure_ascii,
check_circular=check_circular, allow_nan=allow_nan, indent=indent,
separators=separators, default=default, sort_keys=sort_keys,
**kw).encode(obj) _default_decoder = JSONDecoder(object_hook=None, object_pairs_hook=None) def load(fp, cls=None, object_hook=None, parse_float=None,
parse_int=None, parse_constant=None, object_pairs_hook=None, **kw):
"""Deserialize ``fp`` (a ``.read()``-supporting file-like object containing
a JSON document) to a Python object. ``object_hook`` is an optional function that will be called with the
result of any object literal decode (a ``dict``). The return value of
``object_hook`` will be used instead of the ``dict``. This feature
can be used to implement custom decoders (e.g. JSON-RPC class hinting). ``object_pairs_hook`` is an optional function that will be called with the
result of any object literal decoded with an ordered list of pairs. The
return value of ``object_pairs_hook`` will be used instead of the ``dict``.
This feature can be used to implement custom decoders that rely on the
order that the key and value pairs are decoded (for example,
collections.OrderedDict will remember the order of insertion). If
``object_hook`` is also defined, the ``object_pairs_hook`` takes priority. To use a custom ``JSONDecoder`` subclass, specify it with the ``cls``
kwarg; otherwise ``JSONDecoder`` is used. """
return loads(fp.read(),
cls=cls, object_hook=object_hook,
parse_float=parse_float, parse_int=parse_int,
parse_constant=parse_constant, object_pairs_hook=object_pairs_hook, **kw) def loads(s, encoding=None, cls=None, object_hook=None, parse_float=None,
parse_int=None, parse_constant=None, object_pairs_hook=None, **kw):
"""Deserialize ``s`` (a ``str`` instance containing a JSON
document) to a Python object. ``object_hook`` is an optional function that will be called with the
result of any object literal decode (a ``dict``). The return value of
``object_hook`` will be used instead of the ``dict``. This feature
can be used to implement custom decoders (e.g. JSON-RPC class hinting). ``object_pairs_hook`` is an optional function that will be called with the
result of any object literal decoded with an ordered list of pairs. The
return value of ``object_pairs_hook`` will be used instead of the ``dict``.
This feature can be used to implement custom decoders that rely on the
order that the key and value pairs are decoded (for example,
collections.OrderedDict will remember the order of insertion). If
``object_hook`` is also defined, the ``object_pairs_hook`` takes priority. ``parse_float``, if specified, will be called with the string
of every JSON float to be decoded. By default this is equivalent to
float(num_str). This can be used to use another datatype or parser
for JSON floats (e.g. decimal.Decimal). ``parse_int``, if specified, will be called with the string
of every JSON int to be decoded. By default this is equivalent to
int(num_str). This can be used to use another datatype or parser
for JSON integers (e.g. float). ``parse_constant``, if specified, will be called with one of the
following strings: -Infinity, Infinity, NaN, null, true, false.
This can be used to raise an exception if invalid JSON numbers
are encountered. To use a custom ``JSONDecoder`` subclass, specify it with the ``cls``
kwarg; otherwise ``JSONDecoder`` is used. The ``encoding`` argument is ignored and deprecated. """
if not isinstance(s, str):
raise TypeError('the JSON object must be str, not {!r}'.format(
s.__class__.__name__))
if s.startswith(u'\ufeff'):
raise JSONDecodeError("Unexpected UTF-8 BOM (decode using utf-8-sig)",
s, )
if (cls is None and object_hook is None and
parse_int is None and parse_float is None and
parse_constant is None and object_pairs_hook is None and not kw):
return _default_decoder.decode(s)
if cls is None:
cls = JSONDecoder
if object_hook is not None:
kw['object_hook'] = object_hook
if object_pairs_hook is not None:
kw['object_pairs_hook'] = object_pairs_hook
if parse_float is not None:
kw['parse_float'] = parse_float
if parse_int is not None:
kw['parse_int'] = parse_int
if parse_constant is not None:
kw['parse_constant'] = parse_constant
return cls(**kw).decode(s)
pickle源代码
"""Create portable serialized representations of Python objects. See module copyreg for a mechanism for registering custom picklers.
See module pickletools source for extensive comments. Classes: Pickler
Unpickler Functions: dump(object, file)
dumps(object) -> string
load(file) -> object
loads(string) -> object Misc variables: __version__
format_version
compatible_formats """ from types import FunctionType
from copyreg import dispatch_table
from copyreg import _extension_registry, _inverted_registry, _extension_cache
from itertools import islice
import sys
from sys import maxsize
from struct import pack, unpack
import re
import io
import codecs
import _compat_pickle __all__ = ["PickleError", "PicklingError", "UnpicklingError", "Pickler",
"Unpickler", "dump", "dumps", "load", "loads"] # Shortcut for use in isinstance testing
bytes_types = (bytes, bytearray) # These are purely informational; no code uses these.
format_version = "4.0" # File format version we write
compatible_formats = ["1.0", # Original protocol
"1.1", # Protocol with INST added
"1.2", # Original protocol
"1.3", # Protocol with BINFLOAT added
"2.0", # Protocol
"3.0", # Protocol
"4.0", # Protocol
] # Old format versions we can read # This is the highest protocol number we know how to read.
HIGHEST_PROTOCOL = # The protocol we write by default. May be less than HIGHEST_PROTOCOL.
# We intentionally write a protocol that Python .x cannot read;
# there are too many issues with that.
DEFAULT_PROTOCOL = class PickleError(Exception):
"""A common base class for the other pickling exceptions."""
pass class PicklingError(PickleError):
"""This exception is raised when an unpicklable object is passed to the
dump() method. """
pass class UnpicklingError(PickleError):
"""This exception is raised when there is a problem unpickling an object,
such as a security violation. Note that other exceptions may also be raised during unpickling, including
(but not necessarily limited to) AttributeError, EOFError, ImportError,
and IndexError. """
pass # An instance of _Stop is raised by Unpickler.load_stop() in response to
# the STOP opcode, passing the object that is the result of unpickling.
class _Stop(Exception):
def __init__(self, value):
self.value = value # Jython has PyStringMap; it's a dict subclass with string keys
try:
from org.python.core import PyStringMap
except ImportError:
PyStringMap = None # Pickle opcodes. See pickletools.py for extensive docs. The listing
# here is in kind-of alphabetical order of -character pickle code.
# pickletools groups them by purpose. MARK = b'(' # push special markobject on stack
STOP = b'.' # every pickle ends with STOP
POP = b'' # discard topmost stack item
POP_MARK = b'' # discard stack top through topmost markobject
DUP = b'' # duplicate top stack item
FLOAT = b'F' # push float object; decimal string argument
INT = b'I' # push integer or bool; decimal string argument
BININT = b'J' # push four-byte signed int
BININT1 = b'K' # push -byte unsigned int
LONG = b'L' # push long; decimal string argument
BININT2 = b'M' # push -byte unsigned int
NONE = b'N' # push None
PERSID = b'P' # push persistent object; id is taken from string arg
BINPERSID = b'Q' # " " " ; " " " " stack
REDUCE = b'R' # apply callable to argtuple, both on stack
STRING = b'S' # push string; NL-terminated string argument
BINSTRING = b'T' # push string; counted binary string argument
SHORT_BINSTRING= b'U' # " " ; " " " " < bytes
UNICODE = b'V' # push Unicode string; raw-unicode-escaped'd argument
BINUNICODE = b'X' # " " " ; counted UTF-8 string argument
APPEND = b'a' # append stack top to list below it
BUILD = b'b' # call __setstate__ or __dict__.update()
GLOBAL = b'c' # push self.find_class(modname, name); string args
DICT = b'd' # build a dict from stack items
EMPTY_DICT = b'}' # push empty dict
APPENDS = b'e' # extend list on stack by topmost stack slice
GET = b'g' # push item from memo on stack; index is string arg
BINGET = b'h' # " " " " " " ; " " -byte arg
INST = b'i' # build & push class instance
LONG_BINGET = b'j' # push item from memo on stack; index is -byte arg
LIST = b'l' # build list from topmost stack items
EMPTY_LIST = b']' # push empty list
OBJ = b'o' # build & push class instance
PUT = b'p' # store stack top in memo; index is string arg
BINPUT = b'q' # " " " " " ; " " 1-byte arg
LONG_BINPUT = b'r' # " " " " " ; " " 4-byte arg
SETITEM = b's' # add key+value pair to dict
TUPLE = b't' # build tuple from topmost stack items
EMPTY_TUPLE = b')' # push empty tuple
SETITEMS = b'u' # modify dict by adding topmost key+value pairs
BINFLOAT = b'G' # push float; arg is -byte float encoding TRUE = b'I01\n' # not an opcode; see INT docs in pickletools.py
FALSE = b'I00\n' # not an opcode; see INT docs in pickletools.py # Protocol PROTO = b'\x80' # identify pickle protocol
NEWOBJ = b'\x81' # build object by applying cls.__new__ to argtuple
EXT1 = b'\x82' # push object from extension registry; -byte index
EXT2 = b'\x83' # ditto, but -byte index
EXT4 = b'\x84' # ditto, but -byte index
TUPLE1 = b'\x85' # build -tuple from stack top
TUPLE2 = b'\x86' # build -tuple from two topmost stack items
TUPLE3 = b'\x87' # build -tuple from three topmost stack items
NEWTRUE = b'\x88' # push True
NEWFALSE = b'\x89' # push False
LONG1 = b'\x8a' # push long from < bytes
LONG4 = b'\x8b' # push really big long _tuplesize2code = [EMPTY_TUPLE, TUPLE1, TUPLE2, TUPLE3] # Protocol (Python .x) BINBYTES = b'B' # push bytes; counted binary string argument
SHORT_BINBYTES = b'C' # " " ; " " " " < bytes # Protocol
SHORT_BINUNICODE = b'\x8c' # push short string; UTF- length < bytes
BINUNICODE8 = b'\x8d' # push very long string
BINBYTES8 = b'\x8e' # push very long bytes string
EMPTY_SET = b'\x8f' # push empty set on the stack
ADDITEMS = b'\x90' # modify set by adding topmost stack items
FROZENSET = b'\x91' # build frozenset from topmost stack items
NEWOBJ_EX = b'\x92' # like NEWOBJ but work with keyword only arguments
STACK_GLOBAL = b'\x93' # same as GLOBAL but using names on the stacks
MEMOIZE = b'\x94' # store top of the stack in memo
FRAME = b'\x95' # indicate the beginning of a new frame __all__.extend([x for x in dir() if re.match("[A-Z][A-Z0-9_]+$", x)]) class _Framer: _FRAME_SIZE_TARGET = * def __init__(self, file_write):
self.file_write = file_write
self.current_frame = None def start_framing(self):
self.current_frame = io.BytesIO() def end_framing(self):
if self.current_frame and self.current_frame.tell() > :
self.commit_frame(force=True)
self.current_frame = None def commit_frame(self, force=False):
if self.current_frame:
f = self.current_frame
if f.tell() >= self._FRAME_SIZE_TARGET or force:
with f.getbuffer() as data:
n = len(data)
write = self.file_write
write(FRAME)
write(pack("<Q", n))
write(data)
f.seek()
f.truncate() def write(self, data):
if self.current_frame:
return self.current_frame.write(data)
else:
return self.file_write(data) class _Unframer: def __init__(self, file_read, file_readline, file_tell=None):
self.file_read = file_read
self.file_readline = file_readline
self.current_frame = None def read(self, n):
if self.current_frame:
data = self.current_frame.read(n)
if not data and n != :
self.current_frame = None
return self.file_read(n)
if len(data) < n:
raise UnpicklingError(
"pickle exhausted before end of frame")
return data
else:
return self.file_read(n) def readline(self):
if self.current_frame:
data = self.current_frame.readline()
if not data:
self.current_frame = None
return self.file_readline()
if data[-] != b'\n'[]:
raise UnpicklingError(
"pickle exhausted before end of frame")
return data
else:
return self.file_readline() def load_frame(self, frame_size):
if self.current_frame and self.current_frame.read() != b'':
raise UnpicklingError(
"beginning of a new frame before end of current frame")
self.current_frame = io.BytesIO(self.file_read(frame_size)) # Tools used for pickling. def _getattribute(obj, name):
for subpath in name.split('.'):
if subpath == '<locals>':
raise AttributeError("Can't get local attribute {!r} on {!r}"
.format(name, obj))
try:
parent = obj
obj = getattr(obj, subpath)
except AttributeError:
raise AttributeError("Can't get attribute {!r} on {!r}"
.format(name, obj))
return obj, parent def whichmodule(obj, name):
"""Find the module an object belong to."""
module_name = getattr(obj, '__module__', None)
if module_name is not None:
return module_name
# Protect the iteration by using a list copy of sys.modules against dynamic
# modules that trigger imports of other modules upon calls to getattr.
for module_name, module in list(sys.modules.items()):
if module_name == '__main__' or module is None:
continue
try:
if _getattribute(module, name)[] is obj:
return module_name
except AttributeError:
pass
return '__main__' def encode_long(x):
r"""Encode a long to a two's complement little-endian binary string.
Note that is a special case, returning an empty string, to save a
byte in the LONG1 pickling context. >>> encode_long()
b''
>>> encode_long()
b'\xff\x00'
>>> encode_long()
b'\xff\x7f'
>>> encode_long(-)
b'\x00\xff'
>>> encode_long(-)
b'\x00\x80'
>>> encode_long(-)
b'\x80'
>>> encode_long()
b'\x7f'
>>>
"""
if x == :
return b''
nbytes = (x.bit_length() >> ) +
result = x.to_bytes(nbytes, byteorder='little', signed=True)
if x < and nbytes > :
if result[-] == 0xff and (result[-] & 0x80) != :
result = result[:-]
return result def decode_long(data):
r"""Decode a long from a two's complement little-endian binary string. >>> decode_long(b'') >>> decode_long(b"\xff\x00") >>> decode_long(b"\xff\x7f") >>> decode_long(b"\x00\xff")
-
>>> decode_long(b"\x00\x80")
-
>>> decode_long(b"\x80")
-
>>> decode_long(b"\x7f") """
return int.from_bytes(data, byteorder='little', signed=True) # Pickling machinery class _Pickler: def __init__(self, file, protocol=None, *, fix_imports=True):
"""This takes a binary file for writing a pickle data stream. The optional *protocol* argument tells the pickler to use the
given protocol; supported protocols are , , , and . The
default protocol is ; a backward-incompatible protocol designed
for Python . Specifying a negative protocol version selects the highest
protocol version supported. The higher the protocol used, the
more recent the version of Python needed to read the pickle
produced. The *file* argument must have a write() method that accepts a
single bytes argument. It can thus be a file object opened for
binary writing, an io.BytesIO instance, or any other custom
object that meets this interface. If *fix_imports* is True and *protocol* is less than , pickle
will try to map the new Python names to the old module names
used in Python , so that the pickle data stream is readable
with Python .
"""
if protocol is None:
protocol = DEFAULT_PROTOCOL
if protocol < :
protocol = HIGHEST_PROTOCOL
elif not <= protocol <= HIGHEST_PROTOCOL:
raise ValueError("pickle protocol must be <= %d" % HIGHEST_PROTOCOL)
try:
self._file_write = file.write
except AttributeError:
raise TypeError("file must have a 'write' attribute")
self.framer = _Framer(self._file_write)
self.write = self.framer.write
self.memo = {}
self.proto = int(protocol)
self.bin = protocol >=
self.fast =
self.fix_imports = fix_imports and protocol < def clear_memo(self):
"""Clears the pickler's "memo". The memo is the data structure that remembers which objects the
pickler has already seen, so that shared or recursive objects
are pickled by reference and not by value. This method is
useful when re-using picklers.
"""
self.memo.clear() def dump(self, obj):
"""Write a pickled representation of obj to the open file."""
# Check whether Pickler was initialized correctly. This is
# only needed to mimic the behavior of _pickle.Pickler.dump().
if not hasattr(self, "_file_write"):
raise PicklingError("Pickler.__init__() was not called by "
"%s.__init__()" % (self.__class__.__name__,))
if self.proto >= :
self.write(PROTO + pack("<B", self.proto))
if self.proto >= :
self.framer.start_framing()
self.save(obj)
self.write(STOP)
self.framer.end_framing() def memoize(self, obj):
"""Store an object in the memo.""" # The Pickler memo is a dictionary mapping object ids to -tuples
# that contain the Unpickler memo key and the object being memoized.
# The memo key is written to the pickle and will become
# the key in the Unpickler's memo. The object is stored in the
# Pickler memo so that transient objects are kept alive during
# pickling. # The use of the Unpickler memo length as the memo key is just a
# convention. The only requirement is that the memo values be unique.
# But there appears no advantage to any other scheme, and this
# scheme allows the Unpickler memo to be implemented as a plain (but
# growable) array, indexed by memo key.
if self.fast:
return
assert id(obj) not in self.memo
idx = len(self.memo)
self.write(self.put(idx))
self.memo[id(obj)] = idx, obj # Return a PUT (BINPUT, LONG_BINPUT) opcode string, with argument i.
def put(self, idx):
if self.proto >= :
return MEMOIZE
elif self.bin:
if idx < :
return BINPUT + pack("<B", idx)
else:
return LONG_BINPUT + pack("<I", idx)
else:
return PUT + repr(idx).encode("ascii") + b'\n' # Return a GET (BINGET, LONG_BINGET) opcode string, with argument i.
def get(self, i):
if self.bin:
if i < :
return BINGET + pack("<B", i)
else:
return LONG_BINGET + pack("<I", i) return GET + repr(i).encode("ascii") + b'\n' def save(self, obj, save_persistent_id=True):
self.framer.commit_frame() # Check for persistent id (defined by a subclass)
pid = self.persistent_id(obj)
if pid is not None and save_persistent_id:
self.save_pers(pid)
return # Check the memo
x = self.memo.get(id(obj))
if x is not None:
self.write(self.get(x[]))
return # Check the type dispatch table
t = type(obj)
f = self.dispatch.get(t)
if f is not None:
f(self, obj) # Call unbound method with explicit self
return # Check private dispatch table if any, or else copyreg.dispatch_table
reduce = getattr(self, 'dispatch_table', dispatch_table).get(t)
if reduce is not None:
rv = reduce(obj)
else:
# Check for a class with a custom metaclass; treat as regular class
try:
issc = issubclass(t, type)
except TypeError: # t is not a class (old Boost; see SF #)
issc = False
if issc:
self.save_global(obj)
return # Check for a __reduce_ex__ method, fall back to __reduce__
reduce = getattr(obj, "__reduce_ex__", None)
if reduce is not None:
rv = reduce(self.proto)
else:
reduce = getattr(obj, "__reduce__", None)
if reduce is not None:
rv = reduce()
else:
raise PicklingError("Can't pickle %r object: %r" %
(t.__name__, obj)) # Check for string returned by reduce(), meaning "save as global"
if isinstance(rv, str):
self.save_global(obj, rv)
return # Assert that reduce() returned a tuple
if not isinstance(rv, tuple):
raise PicklingError("%s must return string or tuple" % reduce) # Assert that it returned an appropriately sized tuple
l = len(rv)
if not ( <= l <= ):
raise PicklingError("Tuple returned by %s must have "
"two to five elements" % reduce) # Save the reduce() output and finally memoize the object
self.save_reduce(obj=obj, *rv) def persistent_id(self, obj):
# This exists so a subclass can override it
return None def save_pers(self, pid):
# Save a persistent id reference
if self.bin:
self.save(pid, save_persistent_id=False)
self.write(BINPERSID)
else:
self.write(PERSID + str(pid).encode("ascii") + b'\n') def save_reduce(self, func, args, state=None, listitems=None,
dictitems=None, obj=None):
# This API is called by some subclasses if not isinstance(args, tuple):
raise PicklingError("args from save_reduce() must be a tuple")
if not callable(func):
raise PicklingError("func from save_reduce() must be callable") save = self.save
write = self.write func_name = getattr(func, "__name__", "")
if self.proto >= and func_name == "__newobj_ex__":
cls, args, kwargs = args
if not hasattr(cls, "__new__"):
raise PicklingError("args[0] from {} args has no __new__"
.format(func_name))
if obj is not None and cls is not obj.__class__:
raise PicklingError("args[0] from {} args has the wrong class"
.format(func_name))
save(cls)
save(args)
save(kwargs)
write(NEWOBJ_EX)
elif self.proto >= and func_name == "__newobj__":
# A __reduce__ implementation can direct protocol or newer to
# use the more efficient NEWOBJ opcode, while still
# allowing protocol and to work normally. For this to
# work, the function returned by __reduce__ should be
# called __newobj__, and its first argument should be a
# class. The implementation for __newobj__
# should be as follows, although pickle has no way to
# verify this:
#
# def __newobj__(cls, *args):
# return cls.__new__(cls, *args)
#
# Protocols and will pickle a reference to __newobj__,
# while protocol (and above) will pickle a reference to
# cls, the remaining args tuple, and the NEWOBJ code,
# which calls cls.__new__(cls, *args) at unpickling time
# (see load_newobj below). If __reduce__ returns a
# three-tuple, the state from the third tuple item will be
# pickled regardless of the protocol, calling __setstate__
# at unpickling time (see load_build below).
#
# Note that no standard __newobj__ implementation exists;
# you have to provide your own. This is to enforce
# compatibility with Python 2.2 (pickles written using
# protocol or in Python 2.3 should be unpicklable by
# Python 2.2).
cls = args[]
if not hasattr(cls, "__new__"):
raise PicklingError(
"args[0] from __newobj__ args has no __new__")
if obj is not None and cls is not obj.__class__:
raise PicklingError(
"args[0] from __newobj__ args has the wrong class")
args = args[:]
save(cls)
save(args)
write(NEWOBJ)
else:
save(func)
save(args)
write(REDUCE) if obj is not None:
# If the object is already in the memo, this means it is
# recursive. In this case, throw away everything we put on the
# stack, and fetch the object back from the memo.
if id(obj) in self.memo:
write(POP + self.get(self.memo[id(obj)][]))
else:
self.memoize(obj) # More new special cases (that work with older protocols as
# well): when __reduce__ returns a tuple with or items,
# the 4th and 5th item should be iterators that provide list
# items and dict items (as (key, value) tuples), or None. if listitems is not None:
self._batch_appends(listitems) if dictitems is not None:
self._batch_setitems(dictitems) if state is not None:
save(state)
write(BUILD) # Methods below this point are dispatched through the dispatch table dispatch = {} def save_none(self, obj):
self.write(NONE)
dispatch[type(None)] = save_none def save_bool(self, obj):
if self.proto >= :
self.write(NEWTRUE if obj else NEWFALSE)
else:
self.write(TRUE if obj else FALSE)
dispatch[bool] = save_bool def save_long(self, obj):
if self.bin:
# If the int is small enough to fit in a signed -byte 's-comp
# format, we can store it more efficiently than the general
# case.
# First one- and two-byte unsigned ints:
if obj >= :
if obj <= 0xff:
self.write(BININT1 + pack("<B", obj))
return
if obj <= 0xffff:
self.write(BININT2 + pack("<H", obj))
return
# Next check for -byte signed ints:
if -0x80000000 <= obj <= 0x7fffffff:
self.write(BININT + pack("<i", obj))
return
if self.proto >= :
encoded = encode_long(obj)
n = len(encoded)
if n < :
self.write(LONG1 + pack("<B", n) + encoded)
else:
self.write(LONG4 + pack("<i", n) + encoded)
return
self.write(LONG + repr(obj).encode("ascii") + b'L\n')
dispatch[int] = save_long def save_float(self, obj):
if self.bin:
self.write(BINFLOAT + pack('>d', obj))
else:
self.write(FLOAT + repr(obj).encode("ascii") + b'\n')
dispatch[float] = save_float def save_bytes(self, obj):
if self.proto < :
if not obj: # bytes object is empty
self.save_reduce(bytes, (), obj=obj)
else:
self.save_reduce(codecs.encode,
(str(obj, 'latin1'), 'latin1'), obj=obj)
return
n = len(obj)
if n <= 0xff:
self.write(SHORT_BINBYTES + pack("<B", n) + obj)
elif n > 0xffffffff and self.proto >= :
self.write(BINBYTES8 + pack("<Q", n) + obj)
else:
self.write(BINBYTES + pack("<I", n) + obj)
self.memoize(obj)
dispatch[bytes] = save_bytes def save_str(self, obj):
if self.bin:
encoded = obj.encode('utf-8', 'surrogatepass')
n = len(encoded)
if n <= 0xff and self.proto >= :
self.write(SHORT_BINUNICODE + pack("<B", n) + encoded)
elif n > 0xffffffff and self.proto >= :
self.write(BINUNICODE8 + pack("<Q", n) + encoded)
else:
self.write(BINUNICODE + pack("<I", n) + encoded)
else:
obj = obj.replace("\\", "\\u005c")
obj = obj.replace("\n", "\\u000a")
self.write(UNICODE + obj.encode('raw-unicode-escape') +
b'\n')
self.memoize(obj)
dispatch[str] = save_str def save_tuple(self, obj):
if not obj: # tuple is empty
if self.bin:
self.write(EMPTY_TUPLE)
else:
self.write(MARK + TUPLE)
return n = len(obj)
save = self.save
memo = self.memo
if n <= and self.proto >= :
for element in obj:
save(element)
# Subtle. Same as in the big comment below.
if id(obj) in memo:
get = self.get(memo[id(obj)][])
self.write(POP * n + get)
else:
self.write(_tuplesize2code[n])
self.memoize(obj)
return # proto or proto and tuple isn't empty, or proto > 1 and tuple
# has more than elements.
write = self.write
write(MARK)
for element in obj:
save(element) if id(obj) in memo:
# Subtle. d was not in memo when we entered save_tuple(), so
# the process of saving the tuple's elements must have saved
# the tuple itself: the tuple is recursive. The proper action
# now is to throw away everything we put on the stack, and
# simply GET the tuple (it's already constructed). This check
# could have been done in the "for element" loop instead, but
# recursive tuples are a rare thing.
get = self.get(memo[id(obj)][])
if self.bin:
write(POP_MARK + get)
else: # proto -- POP_MARK not available
write(POP * (n+) + get)
return # No recursion.
write(TUPLE)
self.memoize(obj) dispatch[tuple] = save_tuple def save_list(self, obj):
if self.bin:
self.write(EMPTY_LIST)
else: # proto -- can't use EMPTY_LIST
self.write(MARK + LIST) self.memoize(obj)
self._batch_appends(obj) dispatch[list] = save_list _BATCHSIZE = def _batch_appends(self, items):
# Helper to batch up APPENDS sequences
save = self.save
write = self.write if not self.bin:
for x in items:
save(x)
write(APPEND)
return it = iter(items)
while True:
tmp = list(islice(it, self._BATCHSIZE))
n = len(tmp)
if n > :
write(MARK)
for x in tmp:
save(x)
write(APPENDS)
elif n:
save(tmp[])
write(APPEND)
# else tmp is empty, and we're done
if n < self._BATCHSIZE:
return def save_dict(self, obj):
if self.bin:
self.write(EMPTY_DICT)
else: # proto -- can't use EMPTY_DICT
self.write(MARK + DICT) self.memoize(obj)
self._batch_setitems(obj.items()) dispatch[dict] = save_dict
if PyStringMap is not None:
dispatch[PyStringMap] = save_dict def _batch_setitems(self, items):
# Helper to batch up SETITEMS sequences; proto >= only
save = self.save
write = self.write if not self.bin:
for k, v in items:
save(k)
save(v)
write(SETITEM)
return it = iter(items)
while True:
tmp = list(islice(it, self._BATCHSIZE))
n = len(tmp)
if n > :
write(MARK)
for k, v in tmp:
save(k)
save(v)
write(SETITEMS)
elif n:
k, v = tmp[]
save(k)
save(v)
write(SETITEM)
# else tmp is empty, and we're done
if n < self._BATCHSIZE:
return def save_set(self, obj):
save = self.save
write = self.write if self.proto < :
self.save_reduce(set, (list(obj),), obj=obj)
return write(EMPTY_SET)
self.memoize(obj) it = iter(obj)
while True:
batch = list(islice(it, self._BATCHSIZE))
n = len(batch)
if n > :
write(MARK)
for item in batch:
save(item)
write(ADDITEMS)
if n < self._BATCHSIZE:
return
dispatch[set] = save_set def save_frozenset(self, obj):
save = self.save
write = self.write if self.proto < :
self.save_reduce(frozenset, (list(obj),), obj=obj)
return write(MARK)
for item in obj:
save(item) if id(obj) in self.memo:
# If the object is already in the memo, this means it is
# recursive. In this case, throw away everything we put on the
# stack, and fetch the object back from the memo.
write(POP_MARK + self.get(self.memo[id(obj)][]))
return write(FROZENSET)
self.memoize(obj)
dispatch[frozenset] = save_frozenset def save_global(self, obj, name=None):
write = self.write
memo = self.memo if name is None:
name = getattr(obj, '__qualname__', None)
if name is None:
name = obj.__name__ module_name = whichmodule(obj, name)
try:
__import__(module_name, level=)
module = sys.modules[module_name]
obj2, parent = _getattribute(module, name)
except (ImportError, KeyError, AttributeError):
raise PicklingError(
"Can't pickle %r: it's not found as %s.%s" %
(obj, module_name, name))
else:
if obj2 is not obj:
raise PicklingError(
"Can't pickle %r: it's not the same object as %s.%s" %
(obj, module_name, name)) if self.proto >= :
code = _extension_registry.get((module_name, name))
if code:
assert code >
if code <= 0xff:
write(EXT1 + pack("<B", code))
elif code <= 0xffff:
write(EXT2 + pack("<H", code))
else:
write(EXT4 + pack("<i", code))
return
lastname = name.rpartition('.')[]
if parent is module:
name = lastname
# Non-ASCII identifiers are supported only with protocols >= .
if self.proto >= :
self.save(module_name)
self.save(name)
write(STACK_GLOBAL)
elif parent is not module:
self.save_reduce(getattr, (parent, lastname))
elif self.proto >= :
write(GLOBAL + bytes(module_name, "utf-8") + b'\n' +
bytes(name, "utf-8") + b'\n')
else:
if self.fix_imports:
r_name_mapping = _compat_pickle.REVERSE_NAME_MAPPING
r_import_mapping = _compat_pickle.REVERSE_IMPORT_MAPPING
if (module_name, name) in r_name_mapping:
module_name, name = r_name_mapping[(module_name, name)]
elif module_name in r_import_mapping:
module_name = r_import_mapping[module_name]
try:
write(GLOBAL + bytes(module_name, "ascii") + b'\n' +
bytes(name, "ascii") + b'\n')
except UnicodeEncodeError:
raise PicklingError(
"can't pickle global identifier '%s.%s' using "
"pickle protocol %i" % (module, name, self.proto)) self.memoize(obj) def save_type(self, obj):
if obj is type(None):
return self.save_reduce(type, (None,), obj=obj)
elif obj is type(NotImplemented):
return self.save_reduce(type, (NotImplemented,), obj=obj)
elif obj is type(...):
return self.save_reduce(type, (...,), obj=obj)
return self.save_global(obj) dispatch[FunctionType] = save_global
dispatch[type] = save_type # Unpickling machinery class _Unpickler: def __init__(self, file, *, fix_imports=True,
encoding="ASCII", errors="strict"):
"""This takes a binary file for reading a pickle data stream. The protocol version of the pickle is detected automatically, so
no proto argument is needed. The argument *file* must have two methods, a read() method that
takes an integer argument, and a readline() method that requires
no arguments. Both methods should return bytes. Thus *file*
can be a binary file object opened for reading, an io.BytesIO
object, or any other custom object that meets this interface. The file-like object must have two methods, a read() method
that takes an integer argument, and a readline() method that
requires no arguments. Both methods should return bytes.
Thus file-like object can be a binary file object opened for
reading, a BytesIO object, or any other custom object that
meets this interface. Optional keyword arguments are *fix_imports*, *encoding* and
*errors*, which are used to control compatibility support for
pickle stream generated by Python . If *fix_imports* is True,
pickle will try to map the old Python names to the new names
used in Python . The *encoding* and *errors* tell pickle how
to decode -bit string instances pickled by Python ; these
default to 'ASCII' and 'strict', respectively. *encoding* can be
'bytes' to read theses -bit string instances as bytes objects.
"""
self._file_readline = file.readline
self._file_read = file.read
self.memo = {}
self.encoding = encoding
self.errors = errors
self.proto =
self.fix_imports = fix_imports def load(self):
"""Read a pickled object representation from the open file. Return the reconstituted object hierarchy specified in the file.
"""
# Check whether Unpickler was initialized correctly. This is
# only needed to mimic the behavior of _pickle.Unpickler.dump().
if not hasattr(self, "_file_read"):
raise UnpicklingError("Unpickler.__init__() was not called by "
"%s.__init__()" % (self.__class__.__name__,))
self._unframer = _Unframer(self._file_read, self._file_readline)
self.read = self._unframer.read
self.readline = self._unframer.readline
self.mark = object() # any new unique object
self.stack = []
self.append = self.stack.append
self.proto =
read = self.read
dispatch = self.dispatch
try:
while True:
key = read()
if not key:
raise EOFError
assert isinstance(key, bytes_types)
dispatch[key[]](self)
except _Stop as stopinst:
return stopinst.value # Return largest index k such that self.stack[k] is self.mark.
# If the stack doesn't contain a mark, eventually raises IndexError.
# This could be sped by maintaining another stack, of indices at which
# the mark appears. For that matter, the latter stack would suffice,
# and we wouldn't need to push mark objects on self.stack at all.
# Doing so is probably a good thing, though, since if the pickle is
# corrupt (or hostile) we may get a clue from finding self.mark embedded
# in unpickled objects.
def marker(self):
stack = self.stack
mark = self.mark
k = len(stack)-
while stack[k] is not mark: k = k-
return k def persistent_load(self, pid):
raise UnpicklingError("unsupported persistent id encountered") dispatch = {} def load_proto(self):
proto = self.read()[]
if not <= proto <= HIGHEST_PROTOCOL:
raise ValueError("unsupported pickle protocol: %d" % proto)
self.proto = proto
dispatch[PROTO[]] = load_proto def load_frame(self):
frame_size, = unpack('<Q', self.read())
if frame_size > sys.maxsize:
raise ValueError("frame size > sys.maxsize: %d" % frame_size)
self._unframer.load_frame(frame_size)
dispatch[FRAME[]] = load_frame def load_persid(self):
pid = self.readline()[:-].decode("ascii")
self.append(self.persistent_load(pid))
dispatch[PERSID[]] = load_persid def load_binpersid(self):
pid = self.stack.pop()
self.append(self.persistent_load(pid))
dispatch[BINPERSID[]] = load_binpersid def load_none(self):
self.append(None)
dispatch[NONE[]] = load_none def load_false(self):
self.append(False)
dispatch[NEWFALSE[]] = load_false def load_true(self):
self.append(True)
dispatch[NEWTRUE[]] = load_true def load_int(self):
data = self.readline()
if data == FALSE[:]:
val = False
elif data == TRUE[:]:
val = True
else:
val = int(data, )
self.append(val)
dispatch[INT[]] = load_int def load_binint(self):
self.append(unpack('<i', self.read())[])
dispatch[BININT[]] = load_binint def load_binint1(self):
self.append(self.read()[])
dispatch[BININT1[]] = load_binint1 def load_binint2(self):
self.append(unpack('<H', self.read())[])
dispatch[BININT2[]] = load_binint2 def load_long(self):
val = self.readline()[:-]
if val and val[-] == b'L'[]:
val = val[:-]
self.append(int(val, ))
dispatch[LONG[]] = load_long def load_long1(self):
n = self.read()[]
data = self.read(n)
self.append(decode_long(data))
dispatch[LONG1[]] = load_long1 def load_long4(self):
n, = unpack('<i', self.read())
if n < :
# Corrupt or hostile pickle -- we never write one like this
raise UnpicklingError("LONG pickle has negative byte count")
data = self.read(n)
self.append(decode_long(data))
dispatch[LONG4[]] = load_long4 def load_float(self):
self.append(float(self.readline()[:-]))
dispatch[FLOAT[]] = load_float def load_binfloat(self):
self.append(unpack('>d', self.read())[])
dispatch[BINFLOAT[]] = load_binfloat def _decode_string(self, value):
# Used to allow strings from Python to be decoded either as
# bytes or Unicode strings. This should be used only with the
# STRING, BINSTRING and SHORT_BINSTRING opcodes.
if self.encoding == "bytes":
return value
else:
return value.decode(self.encoding, self.errors) def load_string(self):
data = self.readline()[:-]
# Strip outermost quotes
if len(data) >= and data[] == data[-] and data[] in b'"\'':
data = data[:-]
else:
raise UnpicklingError("the STRING opcode argument must be quoted")
self.append(self._decode_string(codecs.escape_decode(data)[]))
dispatch[STRING[]] = load_string def load_binstring(self):
# Deprecated BINSTRING uses signed -bit length
len, = unpack('<i', self.read())
if len < :
raise UnpicklingError("BINSTRING pickle has negative byte count")
data = self.read(len)
self.append(self._decode_string(data))
dispatch[BINSTRING[]] = load_binstring def load_binbytes(self):
len, = unpack('<I', self.read())
if len > maxsize:
raise UnpicklingError("BINBYTES exceeds system's maximum size "
"of %d bytes" % maxsize)
self.append(self.read(len))
dispatch[BINBYTES[]] = load_binbytes def load_unicode(self):
self.append(str(self.readline()[:-], 'raw-unicode-escape'))
dispatch[UNICODE[]] = load_unicode def load_binunicode(self):
len, = unpack('<I', self.read())
if len > maxsize:
raise UnpicklingError("BINUNICODE exceeds system's maximum size "
"of %d bytes" % maxsize)
self.append(str(self.read(len), 'utf-8', 'surrogatepass'))
dispatch[BINUNICODE[]] = load_binunicode def load_binunicode8(self):
len, = unpack('<Q', self.read())
if len > maxsize:
raise UnpicklingError("BINUNICODE8 exceeds system's maximum size "
"of %d bytes" % maxsize)
self.append(str(self.read(len), 'utf-8', 'surrogatepass'))
dispatch[BINUNICODE8[]] = load_binunicode8 def load_binbytes8(self):
len, = unpack('<Q', self.read())
if len > maxsize:
raise UnpicklingError("BINBYTES8 exceeds system's maximum size "
"of %d bytes" % maxsize)
self.append(self.read(len))
dispatch[BINBYTES8[]] = load_binbytes8 def load_short_binstring(self):
len = self.read()[]
data = self.read(len)
self.append(self._decode_string(data))
dispatch[SHORT_BINSTRING[]] = load_short_binstring def load_short_binbytes(self):
len = self.read()[]
self.append(self.read(len))
dispatch[SHORT_BINBYTES[]] = load_short_binbytes def load_short_binunicode(self):
len = self.read()[]
self.append(str(self.read(len), 'utf-8', 'surrogatepass'))
dispatch[SHORT_BINUNICODE[]] = load_short_binunicode def load_tuple(self):
k = self.marker()
self.stack[k:] = [tuple(self.stack[k+:])]
dispatch[TUPLE[]] = load_tuple def load_empty_tuple(self):
self.append(())
dispatch[EMPTY_TUPLE[]] = load_empty_tuple def load_tuple1(self):
self.stack[-] = (self.stack[-],)
dispatch[TUPLE1[]] = load_tuple1 def load_tuple2(self):
self.stack[-:] = [(self.stack[-], self.stack[-])]
dispatch[TUPLE2[]] = load_tuple2 def load_tuple3(self):
self.stack[-:] = [(self.stack[-], self.stack[-], self.stack[-])]
dispatch[TUPLE3[]] = load_tuple3 def load_empty_list(self):
self.append([])
dispatch[EMPTY_LIST[]] = load_empty_list def load_empty_dictionary(self):
self.append({})
dispatch[EMPTY_DICT[]] = load_empty_dictionary def load_empty_set(self):
self.append(set())
dispatch[EMPTY_SET[]] = load_empty_set def load_frozenset(self):
k = self.marker()
self.stack[k:] = [frozenset(self.stack[k+:])]
dispatch[FROZENSET[]] = load_frozenset def load_list(self):
k = self.marker()
self.stack[k:] = [self.stack[k+:]]
dispatch[LIST[]] = load_list def load_dict(self):
k = self.marker()
items = self.stack[k+:]
d = {items[i]: items[i+]
for i in range(, len(items), )}
self.stack[k:] = [d]
dispatch[DICT[]] = load_dict # INST and OBJ differ only in how they get a class object. It's not
# only sensible to do the rest in a common routine, the two routines
# previously diverged and grew different bugs.
# klass is the class to instantiate, and k points to the topmost mark
# object, following which are the arguments for klass.__init__.
def _instantiate(self, klass, k):
args = tuple(self.stack[k+:])
del self.stack[k:]
if (args or not isinstance(klass, type) or
hasattr(klass, "__getinitargs__")):
try:
value = klass(*args)
except TypeError as err:
raise TypeError("in constructor for %s: %s" %
(klass.__name__, str(err)), sys.exc_info()[])
else:
value = klass.__new__(klass)
self.append(value) def load_inst(self):
module = self.readline()[:-].decode("ascii")
name = self.readline()[:-].decode("ascii")
klass = self.find_class(module, name)
self._instantiate(klass, self.marker())
dispatch[INST[]] = load_inst def load_obj(self):
# Stack is ... markobject classobject arg1 arg2 ...
k = self.marker()
klass = self.stack.pop(k+)
self._instantiate(klass, k)
dispatch[OBJ[]] = load_obj def load_newobj(self):
args = self.stack.pop()
cls = self.stack.pop()
obj = cls.__new__(cls, *args)
self.append(obj)
dispatch[NEWOBJ[]] = load_newobj def load_newobj_ex(self):
kwargs = self.stack.pop()
args = self.stack.pop()
cls = self.stack.pop()
obj = cls.__new__(cls, *args, **kwargs)
self.append(obj)
dispatch[NEWOBJ_EX[]] = load_newobj_ex def load_global(self):
module = self.readline()[:-].decode("utf-8")
name = self.readline()[:-].decode("utf-8")
klass = self.find_class(module, name)
self.append(klass)
dispatch[GLOBAL[]] = load_global def load_stack_global(self):
name = self.stack.pop()
module = self.stack.pop()
if type(name) is not str or type(module) is not str:
raise UnpicklingError("STACK_GLOBAL requires str")
self.append(self.find_class(module, name))
dispatch[STACK_GLOBAL[]] = load_stack_global def load_ext1(self):
code = self.read()[]
self.get_extension(code)
dispatch[EXT1[]] = load_ext1 def load_ext2(self):
code, = unpack('<H', self.read())
self.get_extension(code)
dispatch[EXT2[]] = load_ext2 def load_ext4(self):
code, = unpack('<i', self.read())
self.get_extension(code)
dispatch[EXT4[]] = load_ext4 def get_extension(self, code):
nil = []
obj = _extension_cache.get(code, nil)
if obj is not nil:
self.append(obj)
return
key = _inverted_registry.get(code)
if not key:
if code <= : # note that is forbidden
# Corrupt or hostile pickle.
raise UnpicklingError("EXT specifies code <= 0")
raise ValueError("unregistered extension code %d" % code)
obj = self.find_class(*key)
_extension_cache[code] = obj
self.append(obj) def find_class(self, module, name):
# Subclasses may override this.
if self.proto < and self.fix_imports:
if (module, name) in _compat_pickle.NAME_MAPPING:
module, name = _compat_pickle.NAME_MAPPING[(module, name)]
elif module in _compat_pickle.IMPORT_MAPPING:
module = _compat_pickle.IMPORT_MAPPING[module]
__import__(module, level=)
if self.proto >= :
return _getattribute(sys.modules[module], name)[]
else:
return getattr(sys.modules[module], name) def load_reduce(self):
stack = self.stack
args = stack.pop()
func = stack[-]
stack[-] = func(*args)
dispatch[REDUCE[]] = load_reduce def load_pop(self):
del self.stack[-]
dispatch[POP[]] = load_pop def load_pop_mark(self):
k = self.marker()
del self.stack[k:]
dispatch[POP_MARK[]] = load_pop_mark def load_dup(self):
self.append(self.stack[-])
dispatch[DUP[]] = load_dup def load_get(self):
i = int(self.readline()[:-])
self.append(self.memo[i])
dispatch[GET[]] = load_get def load_binget(self):
i = self.read()[]
self.append(self.memo[i])
dispatch[BINGET[]] = load_binget def load_long_binget(self):
i, = unpack('<I', self.read())
self.append(self.memo[i])
dispatch[LONG_BINGET[]] = load_long_binget def load_put(self):
i = int(self.readline()[:-])
if i < :
raise ValueError("negative PUT argument")
self.memo[i] = self.stack[-]
dispatch[PUT[]] = load_put def load_binput(self):
i = self.read()[]
if i < :
raise ValueError("negative BINPUT argument")
self.memo[i] = self.stack[-]
dispatch[BINPUT[]] = load_binput def load_long_binput(self):
i, = unpack('<I', self.read())
if i > maxsize:
raise ValueError("negative LONG_BINPUT argument")
self.memo[i] = self.stack[-]
dispatch[LONG_BINPUT[]] = load_long_binput def load_memoize(self):
memo = self.memo
memo[len(memo)] = self.stack[-]
dispatch[MEMOIZE[]] = load_memoize def load_append(self):
stack = self.stack
value = stack.pop()
list = stack[-]
list.append(value)
dispatch[APPEND[]] = load_append def load_appends(self):
stack = self.stack
mark = self.marker()
list_obj = stack[mark - ]
items = stack[mark + :]
if isinstance(list_obj, list):
list_obj.extend(items)
else:
append = list_obj.append
for item in items:
append(item)
del stack[mark:]
dispatch[APPENDS[]] = load_appends def load_setitem(self):
stack = self.stack
value = stack.pop()
key = stack.pop()
dict = stack[-]
dict[key] = value
dispatch[SETITEM[]] = load_setitem def load_setitems(self):
stack = self.stack
mark = self.marker()
dict = stack[mark - ]
for i in range(mark + , len(stack), ):
dict[stack[i]] = stack[i + ] del stack[mark:]
dispatch[SETITEMS[]] = load_setitems def load_additems(self):
stack = self.stack
mark = self.marker()
set_obj = stack[mark - ]
items = stack[mark + :]
if isinstance(set_obj, set):
set_obj.update(items)
else:
add = set_obj.add
for item in items:
add(item)
del stack[mark:]
dispatch[ADDITEMS[]] = load_additems def load_build(self):
stack = self.stack
state = stack.pop()
inst = stack[-]
setstate = getattr(inst, "__setstate__", None)
if setstate is not None:
setstate(state)
return
slotstate = None
if isinstance(state, tuple) and len(state) == :
state, slotstate = state
if state:
inst_dict = inst.__dict__
intern = sys.intern
for k, v in state.items():
if type(k) is str:
inst_dict[intern(k)] = v
else:
inst_dict[k] = v
if slotstate:
for k, v in slotstate.items():
setattr(inst, k, v)
dispatch[BUILD[]] = load_build def load_mark(self):
self.append(self.mark)
dispatch[MARK[]] = load_mark def load_stop(self):
value = self.stack.pop()
raise _Stop(value)
dispatch[STOP[]] = load_stop # Shorthands def _dump(obj, file, protocol=None, *, fix_imports=True):
_Pickler(file, protocol, fix_imports=fix_imports).dump(obj) def _dumps(obj, protocol=None, *, fix_imports=True):
f = io.BytesIO()
_Pickler(f, protocol, fix_imports=fix_imports).dump(obj)
res = f.getvalue()
assert isinstance(res, bytes_types)
return res def _load(file, *, fix_imports=True, encoding="ASCII", errors="strict"):
return _Unpickler(file, fix_imports=fix_imports,
encoding=encoding, errors=errors).load() def _loads(s, *, fix_imports=True, encoding="ASCII", errors="strict"):
if isinstance(s, str):
raise TypeError("Can't load pickle from unicode string")
file = io.BytesIO(s)
return _Unpickler(file, fix_imports=fix_imports,
encoding=encoding, errors=errors).load() # Use the faster _pickle if possible
try:
from _pickle import (
PickleError,
PicklingError,
UnpicklingError,
Pickler,
Unpickler,
dump,
dumps,
load,
loads
)
except ImportError:
Pickler, Unpickler = _Pickler, _Unpickler
dump, dumps, load, loads = _dump, _dumps, _load, _loads # Doctest
def _test():
import doctest
return doctest.testmod() if __name__ == "__main__":
import argparse
parser = argparse.ArgumentParser(
description='display contents of the pickle files')
parser.add_argument(
'pickle_file', type=argparse.FileType('br'),
nargs='*', help='the pickle file')
parser.add_argument(
'-t', '--test', action='store_true',
help='run self-test suite')
parser.add_argument(
'-v', action='store_true',
help='run verbosely; only affects self-test run')
args = parser.parse_args()
if args.test:
_test()
else:
if not args.pickle_file:
parser.print_help()
else:
import pprint
for f in args.pickle_file:
obj = load(f)
pprint.pprint(obj)