"""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
from functools import partial
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("<Q", n))
                    write(data)
                f.seek(0)
                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 != 0:
                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[-1] != b'\n'[0]:
                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)[0] 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: