"""Create portable serialized representations of Python objects.

See module cPickle for a (much) faster implementation.

See module copy_reg 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

"""

__version__ = "$Revision: 65524 $"       # Code version

from types import *

from copy_reg import dispatch_table

from copy_reg import _extension_registry, _inverted_registry, _extension_cache

import marshal

import sys

import struct

import re

__all__ = ["PickleError", "PicklingError", "UnpicklingError", "Pickler",

           "Unpickler", "dump", "dumps", "load", "loads"]

# These are purely informational; no code uses these.

format_version = "2.0"                  # 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

                      ]                 # Old format versions we can read

# Keep in synch with cPickle.  This is the highest protocol number we

# know how to read.

HIGHEST_PROTOCOL = 2

# Why use struct.pack() for pickling but marshal.loads() for

# unpickling?  struct.pack() is 40% faster than marshal.dumps(), but

# marshal.loads() is twice as fast as struct.unpack()!

mloads = marshal.loads

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

# UnicodeType may or may not be exported (normally imported from types)

try:

    UnicodeType

except NameError:

    UnicodeType = 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            = '('   # push special markobject on stack

STOP            = '.'   # every pickle ends with STOP

POP             = '0'   # discard topmost stack item

POP_MARK        = '1'   # discard stack top through topmost markobject

DUP             = '2'   # duplicate top stack item

FLOAT           = 'F'   # push float object; decimal string argument

INT             = 'I'   # push integer or bool; decimal string argument

BININT          = 'J'   # push four-byte signed int

BININT1         = 'K'   # push 1-byte unsigned int

LONG            = 'L'   # push long; decimal string argument

BININT2         = 'M'   # push 2-byte unsigned int

NONE            = 'N'   # push None

PERSID          = 'P'   # push persistent object; id is taken from string arg

BINPERSID       = 'Q'   #  "       "         "  ;  "  "   "     "  stack

REDUCE          = 'R'   # apply callable to argtuple, both on stack

STRING          = 'S'   # push string; NL-terminated string argument

BINSTRING       = 'T'   # push string; counted binary string argument

SHORT_BINSTRING = 'U'   #  "     "   ;    "      "       "      " < 256 bytes

UNICODE         = 'V'   # push Unicode string; raw-unicode-escaped'd argument

BINUNICODE      = 'X'   #   "     "       "  ; counted UTF-8 string argument

APPEND          = 'a'   # append stack top to list below it

BUILD           = 'b'   # call __setstate__ or __dict__.update()

GLOBAL          = 'c'   # push self.find_class(modname, name); 2 string args

DICT            = 'd'   # build a dict from stack items

EMPTY_DICT      = '}'   # push empty dict

APPENDS         = 'e'   # extend list on stack by topmost stack slice

GET             = 'g'   # push item from memo on stack; index is string arg

BINGET          = 'h'   #   "    "    "    "   "   "  ;   "    " 1-byte arg

INST            = 'i'   # build & push class instance

LONG_BINGET     = 'j'   # push item from memo on stack; index is 4-byte arg

LIST            = 'l'   # build list from topmost stack items

EMPTY_LIST      = ']'   # push empty list

OBJ             = 'o'   # build & push class instance

PUT             = 'p'   # store stack top in memo; index is string arg

BINPUT          = 'q'   #   "     "    "   "   " ;   "    " 1-byte arg

LONG_BINPUT     = 'r'   #   "     "    "   "   " ;   "    " 4-byte arg

SETITEM         = 's'   # add key+value pair to dict

TUPLE           = 't'   # build tuple from topmost stack items

EMPTY_TUPLE     = ')'   # push empty tuple

SETITEMS        = 'u'   # modify dict by adding topmost key+value pairs

BINFLOAT        = 'G'   # push float; arg is 8-byte float encoding

TRUE            = 'I01\n'  # not an opcode; see INT docs in pickletools.py

FALSE           = 'I00\n'  # not an opcode; see INT docs in pickletools.py

# Protocol 2

PROTO           = '\x80'  # identify pickle protocol

NEWOBJ          = '\x81'  # build object by applying cls.__new__ to argtuple

EXT1            = '\x82'  # push object from extension registry; 1-byte index

EXT2            = '\x83'  # ditto, but 2-byte index

EXT4            = '\x84'  # ditto, but 4-byte index

TUPLE1          = '\x85'  # build 1-tuple from stack top

TUPLE2          = '\x86'  # build 2-tuple from two topmost stack items

TUPLE3          = '\x87'  # build 3-tuple from three topmost stack items

NEWTRUE         = '\x88'  # push True

NEWFALSE        = '\x89'  # push False

LONG1           = '\x8a'  # push long from < 256 bytes

LONG4           = '\x8b'  # push really big long

_tuplesize2code = [EMPTY_TUPLE, TUPLE1, TUPLE2, TUPLE3]

__all__.extend([x for x in dir() if re.match("[A-Z][A-Z0-9_]+$",x)])

del x

# Pickling machinery

class Pickler:

    def __init__(self, file, protocol=None):

        """This takes a file-like object for writing a pickle data stream.

        The optional protocol argument tells the pickler to use the

        given protocol; supported protocols are 0, 1, 2.  The default

        protocol is 0, to be backwards compatible.  (Protocol 0 is the

        only protocol that can be written to a file opened in text

        mode and read back successfully.  When using a protocol higher

        than 0, make sure the file is opened in binary mode, both when

        pickling and unpickling.)

        Protocol 1 is more efficient than protocol 0; protocol 2 is

        more efficient than protocol 1.

        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 parameter must have a write() method that accepts a single

        string argument.  It can thus be an open file object, a StringIO

        object, or any other custom object that meets this interface.

        """

        if protocol is None:

            protocol = 0

        if protocol < 0:

            protocol = HIGHEST_PROTOCOL

        elif not 0 <= protocol <= HIGHEST_PROTOCOL:

            raise ValueError("pickle protocol must be <= %d" % HIGHEST_PROTOCOL)

        self.write = file.write

        self.memo = {}

        self.proto = int(protocol)

        self.bin = protocol >= 1

        self.fast = 0

    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."""

        if self.proto >= 2:

            self.write(PROTO + chr(self.proto))

        self.save(obj)

        self.write(STOP)

    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

        memo_len = len(self.memo)

        self.write(self.put(memo_len))

        self.memo[id(obj)] = memo_len, obj

    # Return a PUT (BINPUT, LONG_BINPUT) opcode string, with argument i.

    def put(self, i, pack=struct.pack):

        if self.bin:

            if i < 256:

                return BINPUT + chr(i)

            else:

                return LONG_BINPUT + pack("<i", i)

        return PUT + repr(i) + '\n'

    # Return a GET (BINGET, LONG_BINGET) opcode string, with argument i.

    def get(self, i, pack=struct.pack):

        if self.bin:

            if i < 256:

                return BINGET + chr(i)

            else:

                return LONG_BINGET + pack("<i", i)

        return GET + repr(i) + '\n'

    def save(self, obj):

        # Check for persistent id (defined by a subclass)

        pid = self.persistent_id(obj)

        if pid:

            self.save_pers(pid)

            return

        # Check the memo

        x = self.memo.get(id(obj))

        if x:

            self.write(self.get(x[0]))

            return

        # Check the type dispatch table

        t = type(obj)

        f = self.dispatch.get(t)

        if f:

            f(self, obj) # Call unbound method with explicit self

            return

        # Check for a class with a custom metaclass; treat as regular class

        try:

            issc = issubclass(t, TypeType)

        except TypeError: # t is not a class (old Boost; see SF #502085)

            issc = 0

        if issc:

            self.save_global(obj)

            return

        # Check copy_reg.dispatch_table

        reduce = dispatch_table.get(t)

        if reduce:

            rv = reduce(obj)

        else:

            # Check for a __reduce_ex__ method, fall back to __reduce__

            reduce = getattr(obj, "__reduce_ex__", None)

            if reduce:

                rv = reduce(self.proto)

            else:

                reduce = getattr(obj, "__reduce__", None)

                if reduce:

                    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 type(rv) is StringType:

            self.save_global(obj, rv)

            return

        # Assert that reduce() returned a tuple

        if type(rv) is not TupleType:

            raise PicklingError("%s must return string or tuple" % reduce)

        # Assert that it returned an appropriately sized tuple

        l = len(rv)

        if not (2 <= l <= 5):

            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)

            self.write(BINPERSID)

        else:

            self.write(PERSID + str(pid) + '\n')

    def save_reduce(self, func, args, state=None,

                    listitems=None, dictitems=None, obj=None):

        # This API is called by some subclasses

        # Assert that args is a tuple or None

        if not isinstance(args, TupleType):

            raise PicklingError("args from reduce() should be a tuple")

        # Assert that func is callable

        if not hasattr(func, '__call__'):

            raise PicklingError("func from reduce should be callable")

        save = self.save

        write = self.write

        # Protocol 2 special case: if func's name is __newobj__, use NEWOBJ

        if self.proto >= 2 and getattr(func, "__name__", "") == "__newobj__":

            # A __reduce__ implementation can direct protocol 2 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

            # new-style 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:

            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[NoneType] = save_none

    def save_bool(self, obj):

        if self.proto >= 2:

            self.write(obj and NEWTRUE or NEWFALSE)

        else:

            self.write(obj and TRUE or FALSE)

    dispatch[bool] = save_bool

    def save_int(self, obj, pack=struct.pack):

        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 + chr(obj))

                    return

                if obj <= 0xffff:

                    self.write("%c%c%c" % (BININT2, obj&0xff, obj>>8))

                    return

            # Next check for 4-byte signed ints:

            high_bits = obj >> 31  # note that Python shift sign-extends

            if high_bits == 0 or high_bits == -1:

                # All high bits are copies of bit 2**31, so the value

                # fits in a 4-byte signed int.

                self.write(BININT + pack("<i", obj))

                return

        # Text pickle, or int too big to fit in signed 4-byte format.

        self.write(INT + repr(obj) + '\n')

    dispatch[IntType] = save_int

    def save_long(self, obj, pack=struct.pack):

        if self.proto >= 2:

            bytes = encode_long(obj)

            n = len(bytes)

            if n < 256:

                self.write(LONG1 + chr(n) + bytes)

            else:

                self.write(LONG4 + pack("<i", n) + bytes)

            return

        self.write(LONG + repr(obj) + '\n')

    dispatch[LongType] = save_long

    def save_float(self, obj, pack=struct.pack):

        if self.bin:

            self.write(BINFLOAT + pack('>d', obj))

        else:

            self.write(FLOAT + repr(obj) + '\n')

    dispatch[FloatType] = save_float

    def save_string(self, obj, pack=struct.pack):

        if self.bin:

            n = len(obj)

            if n < 256:

                self.write(SHORT_BINSTRING + chr(n) + obj)

            else:

                self.write(BINSTRING + pack("<i", n) + obj)

        else:

            self.write(STRING + repr(obj) + '\n')

        self.memoize(obj)

    dispatch[StringType] = save_string

    def save_unicode(self, obj, pack=struct.pack):

        if self.bin:

            encoding = obj.encode('utf-8')

            n = len(encoding)

            self.write(BINUNICODE + pack("<i", n) + encoding)

        else:

            obj = obj.replace("\\", "\\u005c")

            obj = obj.replace("\n", "\\u000a")

            self.write(UNICODE + obj.encode('raw-unicode-escape') + '\n')

        self.memoize(obj)

    dispatch[UnicodeType] = save_unicode

    if StringType == UnicodeType:

        # This is true for Jython

        def save_string(self, obj, pack=struct.pack):

            unicode = obj.isunicode()

            if self.bin:

                if unicode:

                    obj = obj.encode("utf-8")

                l = len(obj)

                if l < 256 and not unicode:

                    self.write(SHORT_BINSTRING + chr(l) + obj)

                else:

                    s = pack("<i", l)

                    if unicode:

                        self.write(BINUNICODE + s + obj)

                    else:

                        self.write(BINSTRING + s + obj)

            else:

                if unicode:

                    obj = obj.replace("\\", "\\u005c")

                    obj = obj.replace("\n", "\\u000a")

                    obj = obj.encode('raw-unicode-escape')

                    self.write(UNICODE + obj + '\n')

                else:

                    self.write(STRING + repr(obj) + '\n')

            self.memoize(obj)