"""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, BuiltinFunctionType
from copyreg import dispatch_table
from copyreg import _extension_registry, _inverted_registry, _extension_cache
import marshal
import sys
import struct
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)
__all__.append('bytes_types')

# These are purely informational; no code uses these.
format_version = "3.0"                  # 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
                      ]                 # Old format versions we can read

# This is the highest protocol number we know how to read.
HIGHEST_PROTOCOL = 3

# 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

# 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

# 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

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

# 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.  The default
        protocol is 3; a backward-incompatible protocol designed for
        Python 3.0.

        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, a 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.x names to the old module names used in Python
        2.x, so that the pickle data stream is readable with Python 2.x.
        """
        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.write = file.write
        except AttributeError:
            raise TypeError("file must have a 'write' attribute")
        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, "write"):
            raise PicklingError("Pickler.__init__() was not called by "
                                "%s.__init__()" % (self.__class__.__name__,))
        if self.proto >= 2:
            self.write(PROTO + bytes([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 + bytes([i])
            else:
                return LONG_BINPUT + pack("<I", i)

        return PUT + repr(i).encode("ascii") + b'\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 + bytes([i])
            else:
                return LONG_BINGET + pack("<I", i)

        return GET + repr(i).encode("ascii") + b'\n'

    def save(self, obj, save_persistent_id=True):
        # 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:
            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 private dispatch table if any, or else copyreg.dispatch_table
        reduce = getattr(self, 'dispatch_table', dispatch_table).get(t)
        if reduce:
            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 #502085)
                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:
                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 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 (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):