"""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 0 "1.1", # Protocol 0 with INST added "1.2", # Original protocol 1 "1.3", # Protocol 1 with BINFLOAT added "2.0", # Protocol 2 "3.0", # Protocol 3 "4.0", # Protocol 4 ] # Old format versions we can read # This is the highest protocol number we know how to read. HIGHEST_PROTOCOL = 4 # The protocol we write by default. May be less than HIGHEST_PROTOCOL. # We intentionally write a protocol that Python 2.x cannot read; # there are too many issues with that. DEFAULT_PROTOCOL = 3 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 1-character pickle code. # pickletools groups them by purpose. MARK = b'(' # push special markobject on stack STOP = b'.' # every pickle ends with STOP POP = b'0' # discard topmost stack item POP_MARK = b'1' # discard stack top through topmost markobject DUP = b'2' # 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 1-byte unsigned int LONG = b'L' # push long; decimal string argument BININT2 = b'M' # push 2-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' # " " ; " " " " < 256 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); 2 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' # " " " " " " ; " " 1-byte arg INST = b'i' # build & push class instance LONG_BINGET = b'j' # push item from memo on stack; index is 4-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 8-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 2 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; 1-byte index EXT2 = b'\x83' # ditto, but 2-byte index EXT4 = b'\x84' # ditto, but 4-byte index TUPLE1 = b'\x85' # build 1-tuple from stack top TUPLE2 = b'\x86' # build 2-tuple from two topmost stack items TUPLE3 = b'\x87' # build 3-tuple from three topmost stack items NEWTRUE = b'\x88' # push True NEWFALSE = b'\x89' # push False LONG1 = b'\x8a' # push long from < 256 bytes LONG4 = b'\x8b' # push really big long _tuplesize2code = [EMPTY_TUPLE, TUPLE1, TUPLE2, TUPLE3] # Protocol 3 (Python 3.x) BINBYTES = b'B' # push bytes; counted binary string argument SHORT_BINBYTES = b'C' # " " ; " " " " < 256 bytes # Protocol 4 SHORT_BINUNICODE = b'\x8c' # push short string; UTF-8 length < 256 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 = 64 * 1024 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() > 0: 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(" 1: raise AttributeError("Can't get qualified attribute {!r} on {!r}; " + "use protocols >= 4 to enable support" .format(name, obj)) for subpath in dotted_path: if subpath == '': raise AttributeError("Can't get local attribute {!r} on {!r}" .format(name, obj)) try: obj = getattr(obj, subpath) except AttributeError: raise AttributeError("Can't get attribute {!r} on {!r}" .format(name, obj)) return obj def whichmodule(obj, name, allow_qualname=False): """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, allow_qualname) 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 0 is a special case, returning an empty string, to save a byte in the LONG1 pickling context. >>> encode_long(0) b'' >>> encode_long(255) b'\xff\x00' >>> encode_long(32767) b'\xff\x7f' >>> encode_long(-256) b'\x00\xff' >>> encode_long(-32768) b'\x00\x80' >>> encode_long(-128) b'\x80' >>> encode_long(127) b'\x7f' >>> """ if x == 0: return b'' nbytes = (x.bit_length() >> 3) + 1 result = x.to_bytes(nbytes, byteorder='little', signed=True) if x < 0 and nbytes > 1: if result[-1] == 0xff and (result[-2] & 0x80) != 0: result = result[:-1] return result def decode_long(data): r"""Decode a long from a two's complement little-endian binary string. >>> decode_long(b'') 0 >>> decode_long(b"\xff\x00") 255 >>> decode_long(b"\xff\x7f") 32767 >>> decode_long(b"\x00\xff") -256 >>> decode_long(b"\x00\x80") -32768 >>> decode_long(b"\x80") -128 >>> decode_long(b"\x7f") 127 """ 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 0, 1, 2, 3 and 4. The default protocol is 3; a backward-incompatible protocol designed for Python 3. 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 3, pickle will try to map the new Python 3 names to the old module names used in Python 2, so that the pickle data stream is readable with Python 2. """ if protocol is None: protocol = DEFAULT_PROTOCOL if protocol < 0: protocol = HIGHEST_PROTOCOL elif not 0 <= 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 >= 1 self.fast = 0 self.fix_imports = fix_imports and protocol < 3 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 >= 2: self.write(PROTO + pack("= 4: 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 2-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 >= 4: return MEMOIZE elif self.bin: if idx < 256: return BINPUT + pack("= 4 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 >= 2 and func_name == "__newobj__": # A __reduce__ implementation can direct protocol 2 or newer to # use the more efficient NEWOBJ opcode, while still # allowing protocol 0 and 1 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 0 and 1 will pickle a reference to __newobj__, # while protocol 2 (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 0 or 1 in Python 2.3 should be unpicklable by # Python 2.2). cls = args[0] 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[1:] 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)][0])) else: self.memoize(obj) # More new special cases (that work with older protocols as # well): when __reduce__ returns a tuple with 4 or 5 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 >= 2: 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 4-byte 2's-comp # format, we can store it more efficiently than the general # case. # First one- and two-byte unsigned ints: if obj >= 0: if obj <= 0xff: self.write(BININT1 + pack("= 2: encoded = encode_long(obj) n = len(encoded) if n < 256: self.write(LONG1 + 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 < 3: 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(" 0xffffffff and self.proto >= 4: self.write(BINBYTES8 + pack("= 4: self.write(SHORT_BINUNICODE + pack(" 0xffffffff and self.proto >= 4: self.write(BINUNICODE8 + pack("= 2: 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)][0]) self.write(POP * n + get) else: self.write(_tuplesize2code[n]) self.memoize(obj) return # proto 0 or proto 1 and tuple isn't empty, or proto > 1 and tuple # has more than 3 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)][0]) if self.bin: write(POP_MARK + get) else: # proto 0 -- POP_MARK not available write(POP * (n+1) + 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 0 -- can't use EMPTY_LIST self.write(MARK + LIST) self.memoize(obj) self._batch_appends(obj) dispatch[list] = save_list _BATCHSIZE = 1000 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 > 1: write(MARK) for x in tmp: save(x) write(APPENDS) elif n: save(tmp[0]) 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 0 -- 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 >= 1 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 > 1: write(MARK) for k, v in tmp: save(k) save(v) write(SETITEMS) elif n: k, v = tmp[0] 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 < 4: 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 > 0: 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 < 4: 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)][0])) 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 and self.proto >= 4: name = getattr(obj, '__qualname__', None) if name is None: name = obj.__name__ module_name = whichmodule(obj, name, allow_qualname=self.proto >= 4) try: __import__(module_name, level=0) module = sys.modules[module_name] obj2 = _getattribute(module, name, allow_qualname=self.proto >= 4) 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 >= 2: code = _extension_registry.get((module_name, name)) if code: assert code > 0 if code <= 0xff: write(EXT1 + pack("= 3. if self.proto >= 4: self.save(module_name) self.save(name) write(STACK_GLOBAL) elif self.proto >= 3: 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 compatiblity support for pickle stream generated by Python 2. If *fix_imports* is True, pickle will try to map the old Python 2 names to the new names used in Python 3. The *encoding* and *errors* tell pickle how to decode 8-bit string instances pickled by Python 2; these default to 'ASCII' and 'strict', respectively. *encoding* can be 'bytes' to read theses 8-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 = 0 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 = 0 read = self.read dispatch = self.dispatch try: while True: key = read(1) if not key: raise EOFError assert isinstance(key, bytes_types) dispatch[key[0]](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)-1 while stack[k] is not mark: k = k-1 return k def persistent_load(self, pid): raise UnpicklingError("unsupported persistent id encountered") dispatch = {} def load_proto(self): proto = self.read(1)[0] if not 0 <= proto <= HIGHEST_PROTOCOL: raise ValueError("unsupported pickle protocol: %d" % proto) self.proto = proto dispatch[PROTO[0]] = load_proto def load_frame(self): frame_size, = unpack(' sys.maxsize: raise ValueError("frame size > sys.maxsize: %d" % frame_size) self._unframer.load_frame(frame_size) dispatch[FRAME[0]] = load_frame def load_persid(self): pid = self.readline()[:-1].decode("ascii") self.append(self.persistent_load(pid)) dispatch[PERSID[0]] = load_persid def load_binpersid(self): pid = self.stack.pop() self.append(self.persistent_load(pid)) dispatch[BINPERSID[0]] = load_binpersid def load_none(self): self.append(None) dispatch[NONE[0]] = load_none def load_false(self): self.append(False) dispatch[NEWFALSE[0]] = load_false def load_true(self): self.append(True) dispatch[NEWTRUE[0]] = load_true def load_int(self): data = self.readline() if data == FALSE[1:]: val = False elif data == TRUE[1:]: val = True else: val = int(data, 0) self.append(val) dispatch[INT[0]] = load_int def load_binint(self): self.append(unpack('d', self.read(8))[0]) dispatch[BINFLOAT[0]] = load_binfloat def _decode_string(self, value): # Used to allow strings from Python 2 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()[:-1] # Strip outermost quotes if len(data) >= 2 and data[0] == data[-1] and data[0] in b'"\'': data = data[1:-1] else: raise UnpicklingError("the STRING opcode argument must be quoted") self.append(self._decode_string(codecs.escape_decode(data)[0])) dispatch[STRING[0]] = load_string def load_binstring(self): # Deprecated BINSTRING uses signed 32-bit length len, = unpack(' maxsize: raise UnpicklingError("BINBYTES exceeds system's maximum size " "of %d bytes" % maxsize) self.append(self.read(len)) dispatch[BINBYTES[0]] = load_binbytes def load_unicode(self): self.append(str(self.readline()[:-1], 'raw-unicode-escape')) dispatch[UNICODE[0]] = load_unicode def load_binunicode(self): len, = unpack(' maxsize: raise UnpicklingError("BINUNICODE exceeds system's maximum size " "of %d bytes" % maxsize) self.append(str(self.read(len), 'utf-8', 'surrogatepass')) dispatch[BINUNICODE[0]] = load_binunicode def load_binunicode8(self): len, = unpack(' maxsize: raise UnpicklingError("BINUNICODE8 exceeds system's maximum size " "of %d bytes" % maxsize) self.append(str(self.read(len), 'utf-8', 'surrogatepass')) dispatch[BINUNICODE8[0]] = load_binunicode8 def load_binbytes8(self): len, = unpack(' maxsize: raise UnpicklingError("BINBYTES8 exceeds system's maximum size " "of %d bytes" % maxsize) self.append(self.read(len)) dispatch[BINBYTES8[0]] = load_binbytes8 def load_short_binstring(self): len = self.read(1)[0] data = self.read(len) self.append(self._decode_string(data)) dispatch[SHORT_BINSTRING[0]] = load_short_binstring def load_short_binbytes(self): len = self.read(1)[0] self.append(self.read(len)) dispatch[SHORT_BINBYTES[0]] = load_short_binbytes def load_short_binunicode(self): len = self.read(1)[0] self.append(str(self.read(len), 'utf-8', 'surrogatepass')) dispatch[SHORT_BINUNICODE[0]] = load_short_binunicode def load_tuple(self): k = self.marker() self.stack[k:] = [tuple(self.stack[k+1:])] dispatch[TUPLE[0]] = load_tuple def load_empty_tuple(self): self.append(()) dispatch[EMPTY_TUPLE[0]] = load_empty_tuple def load_tuple1(self): self.stack[-1] = (self.stack[-1],) dispatch[TUPLE1[0]] = load_tuple1 def load_tuple2(self): self.stack[-2:] = [(self.stack[-2], self.stack[-1])] dispatch[TUPLE2[0]] = load_tuple2 def load_tuple3(self): self.stack[-3:] = [(self.stack[-3], self.stack[-2], self.stack[-1])] dispatch[TUPLE3[0]] = load_tuple3 def load_empty_list(self): self.append([]) dispatch[EMPTY_LIST[0]] = load_empty_list def load_empty_dictionary(self): self.append({}) dispatch[EMPTY_DICT[0]] = load_empty_dictionary def load_empty_set(self): self.append(set()) dispatch[EMPTY_SET[0]] = load_empty_set def load_frozenset(self): k = self.marker() self.stack[k:] = [frozenset(self.stack[k+1:])] dispatch[FROZENSET[0]] = load_frozenset def load_list(self): k = self.marker() self.stack[k:] = [self.stack[k+1:]] dispatch[LIST[0]] = load_list def load_dict(self): k = self.marker() items = self.stack[k+1:] d = {items[i]: items[i+1] for i in range(0, len(items), 2)} self.stack[k:] = [d] dispatch[DICT[0]] = 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+1:]) 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()[2]) else: value = klass.__new__(klass) self.append(value) def load_inst(self): module = self.readline()[:-1].decode("ascii") name = self.readline()[:-1].decode("ascii") klass = self.find_class(module, name) self._instantiate(klass, self.marker()) dispatch[INST[0]] = load_inst def load_obj(self): # Stack is ... markobject classobject arg1 arg2 ... k = self.marker() klass = self.stack.pop(k+1) self._instantiate(klass, k) dispatch[OBJ[0]] = load_obj def load_newobj(self): args = self.stack.pop() cls = self.stack.pop() obj = cls.__new__(cls, *args) self.append(obj) dispatch[NEWOBJ[0]] = 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[0]] = load_newobj_ex def load_global(self): module = self.readline()[:-1].decode("utf-8") name = self.readline()[:-1].decode("utf-8") klass = self.find_class(module, name) self.append(klass) dispatch[GLOBAL[0]] = 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[0]] = load_stack_global def load_ext1(self): code = self.read(1)[0] self.get_extension(code) dispatch[EXT1[0]] = load_ext1 def load_ext2(self): code, = unpack('= 4) def load_reduce(self): stack = self.stack args = stack.pop() func = stack[-1] stack[-1] = func(*args) dispatch[REDUCE[0]] = load_reduce def load_pop(self): del self.stack[-1] dispatch[POP[0]] = load_pop def load_pop_mark(self): k = self.marker() del self.stack[k:] dispatch[POP_MARK[0]] = load_pop_mark def load_dup(self): self.append(self.stack[-1]) dispatch[DUP[0]] = load_dup def load_get(self): i = int(self.readline()[:-1]) self.append(self.memo[i]) dispatch[GET[0]] = load_get def load_binget(self): i = self.read(1)[0] self.append(self.memo[i]) dispatch[BINGET[0]] = load_binget def load_long_binget(self): i, = unpack(' maxsize: raise ValueError("negative LONG_BINPUT argument") self.memo[i] = self.stack[-1] dispatch[LONG_BINPUT[0]] = load_long_binput def load_memoize(self): memo = self.memo memo[len(memo)] = self.stack[-1] dispatch[MEMOIZE[0]] = load_memoize def load_append(self): stack = self.stack value = stack.pop() list = stack[-1] list.append(value) dispatch[APPEND[0]] = load_append def load_appends(self): stack = self.stack mark = self.marker() list_obj = stack[mark - 1] items = stack[mark + 1:] 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[0]] = load_appends def load_setitem(self): stack = self.stack value = stack.pop() key = stack.pop() dict = stack[-1] dict[key] = value dispatch[SETITEM[0]] = load_setitem def load_setitems(self): stack = self.stack mark = self.marker() dict = stack[mark - 1] for i in range(mark + 1, len(stack), 2): dict[stack[i]] = stack[i + 1] del stack[mark:] dispatch[SETITEMS[0]] = load_setitems def load_additems(self): stack = self.stack mark = self.marker() set_obj = stack[mark - 1] items = stack[mark + 1:] 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[0]] = load_additems def load_build(self): stack = self.stack state = stack.pop() inst = stack[-1] setstate = getattr(inst, "__setstate__", None) if setstate is not None: setstate(state) return slotstate = None if isinstance(state, tuple) and len(state) == 2: 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[0]] = load_build def load_mark(self): self.append(self.mark) dispatch[MARK[0]] = load_mark def load_stop(self): value = self.stack.pop() raise _Stop(value) dispatch[STOP[0]] = 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)