-
-
Notifications
You must be signed in to change notification settings - Fork 34.2k
Expand file tree
/
Copy pathpickle.py
More file actions
1931 lines (1675 loc) · 68.3 KB
/
pickle.py
File metadata and controls
1931 lines (1675 loc) · 68.3 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
"""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(bytes) -> 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 batched
from functools import partial
import sys
from sys import maxsize
from struct import pack, unpack
import io
import codecs
import _compat_pickle
__all__ = ["PickleError", "PicklingError", "UnpicklingError", "Pickler",
"Unpickler", "dump", "dumps", "load", "loads"]
try:
from _pickle import PickleBuffer
__all__.append("PickleBuffer")
_HAVE_PICKLE_BUFFER = True
except ImportError:
_HAVE_PICKLE_BUFFER = False
# Shortcut for use in isinstance testing
bytes_types = (bytes, bytearray)
# These are purely informational; no code uses these.
format_version = "5.0" # 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
"5.0", # Protocol 5
] # Old format versions we can read
# This is the highest protocol number we know how to read.
HIGHEST_PROTOCOL = 5
# The protocol we write by default. May be less than HIGHEST_PROTOCOL.
# Only bump this if the oldest still supported version of Python already
# includes it.
DEFAULT_PROTOCOL = 5
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
# 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
# Protocol 5
BYTEARRAY8 = b'\x96' # push bytearray
NEXT_BUFFER = b'\x97' # push next out-of-band buffer
READONLY_BUFFER = b'\x98' # make top of stack readonly
__all__.extend(x for x in dir() if x.isupper() and not x.startswith('_'))
class _Framer:
_FRAME_SIZE_MIN = 4
_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:
data = f.getbuffer()
write = self.file_write
if len(data) >= self._FRAME_SIZE_MIN:
# Issue a single call to the write method of the underlying
# file object for the frame opcode with the size of the
# frame. The concatenation is expected to be less expensive
# than issuing an additional call to write.
write(FRAME + pack("<Q", len(data)))
# Issue a separate call to write to append the frame
# contents without concatenation to the above to avoid a
# memory copy.
write(data)
# Start the new frame with a new io.BytesIO instance so that
# the file object can have delayed access to the previous frame
# contents via an unreleased memoryview of the previous
# io.BytesIO instance.
self.current_frame = io.BytesIO()
def write(self, data):
if self.current_frame:
return self.current_frame.write(data)
else:
return self.file_write(data)
def write_large_bytes(self, header, payload):
write = self.file_write
if self.current_frame:
# Terminate the current frame and flush it to the file.
self.commit_frame(force=True)
# Perform direct write of the header and payload of the large binary
# object. Be careful not to concatenate the header and the payload
# prior to calling 'write' as we do not want to allocate a large
# temporary bytes object.
# We intentionally do not insert a protocol 4 frame opcode to make
# it possible to optimize file.read calls in the loader.
write(header)
write(payload)
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 readinto(self, buf):
if self.current_frame:
n = self.current_frame.readinto(buf)
if n == 0 and len(buf) != 0:
self.current_frame = None
n = len(buf)
buf[:] = self.file_read(n)
return n
if n < len(buf):
raise UnpicklingError(
"pickle exhausted before end of frame")
return n
else:
n = len(buf)
buf[:] = self.file_read(n)
return n
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, dotted_path):
for subpath in dotted_path:
obj = getattr(obj, subpath)
return obj
def whichmodule(obj, name):
"""Find the module an object belong to."""
dotted_path = name.split('.')
module_name = getattr(obj, '__module__', None)
if '<locals>' in dotted_path:
raise PicklingError(f"Can't pickle local object {obj!r}")
if module_name is None:
# 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 sys.modules.copy().items():
if (module_name == '__main__'
or module_name == '__mp_main__' # bpo-42406
or module is None):
continue
try:
if _getattribute(module, dotted_path) is obj:
return module_name
except AttributeError:
pass
module_name = '__main__'
try:
__import__(module_name, level=0)
module = sys.modules[module_name]
except (ImportError, ValueError, KeyError) as exc:
raise PicklingError(f"Can't pickle {obj!r}: {exc!s}")
try:
if _getattribute(module, dotted_path) is obj:
return module_name
except AttributeError:
raise PicklingError(f"Can't pickle {obj!r}: "
f"it's not found as {module_name}.{name}")
raise PicklingError(
f"Can't pickle {obj!r}: it's not the same object as {module_name}.{name}")
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)
def _T(obj):
cls = type(obj)
module = cls.__module__
if module in (None, 'builtins', '__main__'):
return cls.__qualname__
return f'{module}.{cls.__qualname__}'
_NoValue = object()
# Pickling machinery
class _Pickler:
def __init__(self, file, protocol=None, *, fix_imports=True,
buffer_callback=None):
"""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, 4 and 5.
The default protocol is 5. It was introduced in Python 3.8, and
is incompatible with previous versions.
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 *buffer_callback* is None (the default), buffer views are
serialized into *file* as part of the pickle stream.
If *buffer_callback* is not None, then it can be called any number
of times with a buffer view. If the callback returns a false value
(such as None), the given buffer is out-of-band; otherwise the
buffer is serialized in-band, i.e. inside the pickle stream.
It is an error if *buffer_callback* is not None and *protocol*
is None or smaller than 5.
"""
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)
if buffer_callback is not None and protocol < 5:
raise ValueError("buffer_callback needs protocol >= 5")
self._buffer_callback = buffer_callback
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._write_large_bytes = self.framer.write_large_bytes
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("<B", self.proto))
if self.proto >= 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("<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 < 256:
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)
if save_persistent_id:
pid = self.persistent_id(obj)
if pid is not None:
self.save_pers(pid)
return
# Check the memo
x = self.memo.get(id(obj))
if x is not None:
self.write(self.get(x[0]))
return
rv = NotImplemented
reduce = getattr(self, "reducer_override", _NoValue)
if reduce is not _NoValue:
rv = reduce(obj)
if rv is NotImplemented:
# 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, _NoValue)
if reduce is not _NoValue:
rv = reduce(obj)
else:
# Check for a class with a custom metaclass; treat as regular
# class
if issubclass(t, type):
self.save_global(obj)
return
# Check for a __reduce_ex__ method, fall back to __reduce__
reduce = getattr(obj, "__reduce_ex__", _NoValue)
if reduce is not _NoValue:
rv = reduce(self.proto)
else:
reduce = getattr(obj, "__reduce__", _NoValue)
if reduce is not _NoValue:
rv = reduce()
else:
raise PicklingError(f"Can't pickle {_T(t)} object")
# Check for string returned by reduce(), meaning "save as global"
if isinstance(rv, str):
self.save_global(obj, rv)
return
try:
# Assert that reduce() returned a tuple
if not isinstance(rv, tuple):
raise PicklingError(f'__reduce__ must return a string or tuple, not {_T(rv)}')
# Assert that it returned an appropriately sized tuple
l = len(rv)
if not (2 <= l <= 6):
raise PicklingError("tuple returned by __reduce__ "
"must contain 2 through 6 elements")
# Save the reduce() output and finally memoize the object
self.save_reduce(obj=obj, *rv)
except BaseException as exc:
exc.add_note(f'when serializing {_T(obj)} object')
raise
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:
try:
self.write(PERSID + str(pid).encode("ascii") + b'\n')
except UnicodeEncodeError:
raise PicklingError(
"persistent IDs in protocol 0 must be ASCII strings")
def save_reduce(self, func, args, state=None, listitems=None,
dictitems=None, state_setter=None, *, obj=None):
# This API is called by some subclasses
if not callable(func):
raise PicklingError(f"first item of the tuple returned by __reduce__ "
f"must be callable, not {_T(func)}")
if not isinstance(args, tuple):
raise PicklingError(f"second item of the tuple returned by __reduce__ "
f"must be a tuple, not {_T(args)}")
save = self.save
write = self.write
func_name = getattr(func, "__name__", "")
if self.proto >= 2 and func_name == "__newobj_ex__":
cls, args, kwargs = args
if not hasattr(cls, "__new__"):
raise PicklingError("first argument to __newobj_ex__() has no __new__")
if obj is not None and cls is not obj.__class__:
raise PicklingError(f"first argument to __newobj_ex__() "
f"must be {obj.__class__!r}, not {cls!r}")
if self.proto >= 4:
try:
save(cls)
except BaseException as exc:
exc.add_note(f'when serializing {_T(obj)} class')
raise
try:
save(args)
save(kwargs)
except BaseException as exc:
exc.add_note(f'when serializing {_T(obj)} __new__ arguments')
raise
write(NEWOBJ_EX)
else:
func = partial(cls.__new__, cls, *args, **kwargs)
try:
save(func)
except BaseException as exc:
exc.add_note(f'when serializing {_T(obj)} reconstructor')
raise
save(())
write(REDUCE)
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("first argument to __newobj__() has no __new__")
if obj is not None and cls is not obj.__class__:
raise PicklingError(f"first argument to __newobj__() "
f"must be {obj.__class__!r}, not {cls!r}")
args = args[1:]
try:
save(cls)
except BaseException as exc:
exc.add_note(f'when serializing {_T(obj)} class')
raise
try:
save(args)
except BaseException as exc:
exc.add_note(f'when serializing {_T(obj)} __new__ arguments')
raise
write(NEWOBJ)
else:
try:
save(func)
except BaseException as exc:
exc.add_note(f'when serializing {_T(obj)} reconstructor')
raise
try:
save(args)
except BaseException as exc:
exc.add_note(f'when serializing {_T(obj)} reconstructor arguments')
raise
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, obj)
if dictitems is not None:
self._batch_setitems(dictitems, obj)
if state is not None:
if state_setter is None:
try:
save(state)
except BaseException as exc:
exc.add_note(f'when serializing {_T(obj)} state')
raise
write(BUILD)
else:
# If a state_setter is specified, call it instead of load_build
# to update obj's with its previous state.
# First, push state_setter and its tuple of expected arguments
# (obj, state) onto the stack.
try:
save(state_setter)
except BaseException as exc:
exc.add_note(f'when serializing {_T(obj)} state setter')
raise
save(obj) # simple BINGET opcode as obj is already memoized.
try:
save(state)
except BaseException as exc:
exc.add_note(f'when serializing {_T(obj)} state')
raise
write(TUPLE2)
# Trigger a state_setter(obj, state) function call.
write(REDUCE)
# The purpose of state_setter is to carry-out an
# inplace modification of obj. We do not care about what the
# method might return, so its output is eventually removed from
# the stack.
write(POP)
# 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("<B", obj))
return
if obj <= 0xffff:
self.write(BININT2 + pack("<H", obj))
return
# Next check for 4-byte signed ints:
if -0x80000000 <= obj <= 0x7fffffff:
self.write(BININT + pack("<i", obj))
return
if self.proto >= 2:
encoded = encode_long(obj)
n = len(encoded)
if n < 256:
self.write(LONG1 + pack("<B", n) + encoded)
else:
self.write(LONG4 + pack("<i", n) + encoded)
return
if -0x80000000 <= obj <= 0x7fffffff:
self.write(INT + repr(obj).encode("ascii") + b'\n')
else:
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_no_memo(self, obj):
# helper for writing bytes objects for protocol >= 3
# without memoizing them
assert self.proto >= 3
n = len(obj)
if n <= 0xff:
self.write(SHORT_BINBYTES + pack("<B", n) + obj)
elif n > 0xffffffff and self.proto >= 4:
self._write_large_bytes(BINBYTES8 + pack("<Q", n), obj)
elif n >= self.framer._FRAME_SIZE_TARGET:
self._write_large_bytes(BINBYTES + pack("<I", n), obj)
else:
self.write(BINBYTES + pack("<I", n) + obj)
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
self._save_bytes_no_memo(obj)
self.memoize(obj)
dispatch[bytes] = save_bytes
def _save_bytearray_no_memo(self, obj):
# helper for writing bytearray objects for protocol >= 5
# without memoizing them
assert self.proto >= 5
n = len(obj)
if n >= self.framer._FRAME_SIZE_TARGET:
self._write_large_bytes(BYTEARRAY8 + pack("<Q", n), obj)
else:
self.write(BYTEARRAY8 + pack("<Q", n) + obj)
def save_bytearray(self, obj):
if self.proto < 5:
if not obj: # bytearray is empty
self.save_reduce(bytearray, (), obj=obj)
else:
self.save_reduce(bytearray, (bytes(obj),), obj=obj)
return
self._save_bytearray_no_memo(obj)
self.memoize(obj)
dispatch[bytearray] = save_bytearray
if _HAVE_PICKLE_BUFFER:
def save_picklebuffer(self, obj):
if self.proto < 5:
raise PicklingError("PickleBuffer can only be pickled with "
"protocol >= 5")
with obj.raw() as m:
if not m.contiguous:
raise PicklingError("PickleBuffer can not be pickled when "
"pointing to a non-contiguous buffer")
in_band = True
if self._buffer_callback is not None:
in_band = bool(self._buffer_callback(obj))
if in_band:
# Write data in-band
# XXX The C implementation avoids a copy here
buf = m.tobytes()
in_memo = id(buf) in self.memo
if m.readonly:
if in_memo:
self._save_bytes_no_memo(buf)
else:
self.save_bytes(buf)
else:
if in_memo:
self._save_bytearray_no_memo(buf)
else:
self.save_bytearray(buf)
else:
# Write data out-of-band
self.write(NEXT_BUFFER)
if m.readonly:
self.write(READONLY_BUFFER)
dispatch[PickleBuffer] = save_picklebuffer
def save_str(self, obj):
if self.bin:
encoded = obj.encode('utf-8', 'surrogatepass')
n = len(encoded)
if n <= 0xff and self.proto >= 4:
self.write(SHORT_BINUNICODE + pack("<B", n) + encoded)
elif n > 0xffffffff and self.proto >= 4:
self._write_large_bytes(BINUNICODE8 + pack("<Q", n), encoded)
elif n >= self.framer._FRAME_SIZE_TARGET:
self._write_large_bytes(BINUNICODE + pack("<I", n), encoded)
else:
self.write(BINUNICODE + pack("<I", n) + encoded)
else:
# Escape what raw-unicode-escape doesn't, but memoize the original.
tmp = obj.replace("\\", "\\u005c")
tmp = tmp.replace("\0", "\\u0000")
tmp = tmp.replace("\n", "\\u000a")
tmp = tmp.replace("\r", "\\u000d")
tmp = tmp.replace("\x1a", "\\u001a") # EOF on DOS
self.write(UNICODE + tmp.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 <= 3 and self.proto >= 2:
for i, element in enumerate(obj):
try:
save(element)
except BaseException as exc:
exc.add_note(f'when serializing {_T(obj)} item {i}')
raise
# 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 i, element in enumerate(obj):
try:
save(element)
except BaseException as exc:
exc.add_note(f'when serializing {_T(obj)} item {i}')
raise
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