-
-
Notifications
You must be signed in to change notification settings - Fork 34.2k
Expand file tree
/
Copy pathpickletools.py
More file actions
2901 lines (2446 loc) · 91.7 KB
/
pickletools.py
File metadata and controls
2901 lines (2446 loc) · 91.7 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
'''"Executable documentation" for the pickle module.
Extensive comments about the pickle protocols and pickle-machine opcodes
can be found here. Some functions meant for external use:
genops(pickle)
Generate all the opcodes in a pickle, as (opcode, arg, position) triples.
dis(pickle, out=None, memo=None, indentlevel=4)
Print a symbolic disassembly of a pickle.
'''
import codecs
import io
import pickle
import re
import sys
__all__ = ['dis', 'genops', 'optimize']
bytes_types = pickle.bytes_types
# Other ideas:
#
# - A pickle verifier: read a pickle and check it exhaustively for
# well-formedness. dis() does a lot of this already.
#
# - A protocol identifier: examine a pickle and return its protocol number
# (== the highest .proto attr value among all the opcodes in the pickle).
# dis() already prints this info at the end.
#
# - A pickle optimizer: for example, tuple-building code is sometimes more
# elaborate than necessary, catering for the possibility that the tuple
# is recursive. Or lots of times a PUT is generated that's never accessed
# by a later GET.
# "A pickle" is a program for a virtual pickle machine (PM, but more accurately
# called an unpickling machine). It's a sequence of opcodes, interpreted by the
# PM, building an arbitrarily complex Python object.
#
# For the most part, the PM is very simple: there are no looping, testing, or
# conditional instructions, no arithmetic and no function calls. Opcodes are
# executed once each, from first to last, until a STOP opcode is reached.
#
# The PM has two data areas, "the stack" and "the memo".
#
# Many opcodes push Python objects onto the stack; e.g., INT pushes a Python
# integer object on the stack, whose value is gotten from a decimal string
# literal immediately following the INT opcode in the pickle bytestream. Other
# opcodes take Python objects off the stack. The result of unpickling is
# whatever object is left on the stack when the final STOP opcode is executed.
#
# The memo is simply an array of objects, or it can be implemented as a dict
# mapping little integers to objects. The memo serves as the PM's "long term
# memory", and the little integers indexing the memo are akin to variable
# names. Some opcodes pop a stack object into the memo at a given index,
# and others push a memo object at a given index onto the stack again.
#
# At heart, that's all the PM has. Subtleties arise for these reasons:
#
# + Object identity. Objects can be arbitrarily complex, and subobjects
# may be shared (for example, the list [a, a] refers to the same object a
# twice). It can be vital that unpickling recreate an isomorphic object
# graph, faithfully reproducing sharing.
#
# + Recursive objects. For example, after "L = []; L.append(L)", L is a
# list, and L[0] is the same list. This is related to the object identity
# point, and some sequences of pickle opcodes are subtle in order to
# get the right result in all cases.
#
# + Things pickle doesn't know everything about. Examples of things pickle
# does know everything about are Python's builtin scalar and container
# types, like ints and tuples. They generally have opcodes dedicated to
# them. For things like module references and instances of user-defined
# classes, pickle's knowledge is limited. Historically, many enhancements
# have been made to the pickle protocol in order to do a better (faster,
# and/or more compact) job on those.
#
# + Backward compatibility and micro-optimization. As explained below,
# pickle opcodes never go away, not even when better ways to do a thing
# get invented. The repertoire of the PM just keeps growing over time.
# For example, protocol 0 had two opcodes for building Python integers (INT
# and LONG), protocol 1 added three more for more-efficient pickling of short
# integers, and protocol 2 added two more for more-efficient pickling of
# long integers (before protocol 2, the only ways to pickle a Python long
# took time quadratic in the number of digits, for both pickling and
# unpickling). "Opcode bloat" isn't so much a subtlety as a source of
# wearying complication.
#
#
# Pickle protocols:
#
# For compatibility, the meaning of a pickle opcode never changes. Instead new
# pickle opcodes get added, and each version's unpickler can handle all the
# pickle opcodes in all protocol versions to date. So old pickles continue to
# be readable forever. The pickler can generally be told to restrict itself to
# the subset of opcodes available under previous protocol versions too, so that
# users can create pickles under the current version readable by older
# versions. However, a pickle does not contain its version number embedded
# within it. If an older unpickler tries to read a pickle using a later
# protocol, the result is most likely an exception due to seeing an unknown (in
# the older unpickler) opcode.
#
# The original pickle used what's now called "protocol 0", and what was called
# "text mode" before Python 2.3. The entire pickle bytestream is made up of
# printable 7-bit ASCII characters, plus the newline character, in protocol 0.
# That's why it was called text mode. Protocol 0 is small and elegant, but
# sometimes painfully inefficient.
#
# The second major set of additions is now called "protocol 1", and was called
# "binary mode" before Python 2.3. This added many opcodes with arguments
# consisting of arbitrary bytes, including NUL bytes and unprintable "high bit"
# bytes. Binary mode pickles can be substantially smaller than equivalent
# text mode pickles, and sometimes faster too; e.g., BININT represents a 4-byte
# int as 4 bytes following the opcode, which is cheaper to unpickle than the
# (perhaps) 11-character decimal string attached to INT. Protocol 1 also added
# a number of opcodes that operate on many stack elements at once (like APPENDS
# and SETITEMS), and "shortcut" opcodes (like EMPTY_DICT and EMPTY_TUPLE).
#
# The third major set of additions came in Python 2.3, and is called "protocol
# 2". This added:
#
# - A better way to pickle instances of new-style classes (NEWOBJ).
#
# - A way for a pickle to identify its protocol (PROTO).
#
# - Time- and space- efficient pickling of long ints (LONG{1,4}).
#
# - Shortcuts for small tuples (TUPLE{1,2,3}}.
#
# - Dedicated opcodes for bools (NEWTRUE, NEWFALSE).
#
# - The "extension registry", a vector of popular objects that can be pushed
# efficiently by index (EXT{1,2,4}). This is akin to the memo and GET, but
# the registry contents are predefined (there's nothing akin to the memo's
# PUT).
#
# Another independent change with Python 2.3 is the abandonment of any
# pretense that it might be safe to load pickles received from untrusted
# parties -- no sufficient security analysis has been done to guarantee
# this and there isn't a use case that warrants the expense of such an
# analysis.
#
# To this end, all tests for __safe_for_unpickling__ or for
# copyreg.safe_constructors are removed from the unpickling code.
# References to these variables in the descriptions below are to be seen
# as describing unpickling in Python 2.2 and before.
# Meta-rule: Descriptions are stored in instances of descriptor objects,
# with plain constructors. No meta-language is defined from which
# descriptors could be constructed. If you want, e.g., XML, write a little
# program to generate XML from the objects.
##############################################################################
# Some pickle opcodes have an argument, following the opcode in the
# bytestream. An argument is of a specific type, described by an instance
# of ArgumentDescriptor. These are not to be confused with arguments taken
# off the stack -- ArgumentDescriptor applies only to arguments embedded in
# the opcode stream, immediately following an opcode.
# Represents the number of bytes consumed by an argument delimited by the
# next newline character.
UP_TO_NEWLINE = -1
# Represents the number of bytes consumed by a two-argument opcode where
# the first argument gives the number of bytes in the second argument.
TAKEN_FROM_ARGUMENT1 = -2 # num bytes is 1-byte unsigned int
TAKEN_FROM_ARGUMENT4 = -3 # num bytes is 4-byte signed little-endian int
TAKEN_FROM_ARGUMENT4U = -4 # num bytes is 4-byte unsigned little-endian int
TAKEN_FROM_ARGUMENT8U = -5 # num bytes is 8-byte unsigned little-endian int
class ArgumentDescriptor(object):
__slots__ = (
# name of descriptor record, also a module global name; a string
'name',
# length of argument, in bytes; an int; UP_TO_NEWLINE and
# TAKEN_FROM_ARGUMENT{1,4,8} are negative values for variable-length
# cases
'n',
# a function taking a file-like object, reading this kind of argument
# from the object at the current position, advancing the current
# position by n bytes, and returning the value of the argument
'reader',
# human-readable docs for this arg descriptor; a string
'doc',
)
def __init__(self, name, n, reader, doc):
assert isinstance(name, str)
self.name = name
assert isinstance(n, int) and (n >= 0 or
n in (UP_TO_NEWLINE,
TAKEN_FROM_ARGUMENT1,
TAKEN_FROM_ARGUMENT4,
TAKEN_FROM_ARGUMENT4U,
TAKEN_FROM_ARGUMENT8U))
self.n = n
self.reader = reader
assert isinstance(doc, str)
self.doc = doc
from struct import unpack as _unpack
def read_uint1(f):
r"""
>>> import io
>>> read_uint1(io.BytesIO(b'\xff'))
255
"""
data = f.read(1)
if data:
return data[0]
raise ValueError("not enough data in stream to read uint1")
uint1 = ArgumentDescriptor(
name='uint1',
n=1,
reader=read_uint1,
doc="One-byte unsigned integer.")
def read_uint2(f):
r"""
>>> import io
>>> read_uint2(io.BytesIO(b'\xff\x00'))
255
>>> read_uint2(io.BytesIO(b'\xff\xff'))
65535
"""
data = f.read(2)
if len(data) == 2:
return _unpack("<H", data)[0]
raise ValueError("not enough data in stream to read uint2")
uint2 = ArgumentDescriptor(
name='uint2',
n=2,
reader=read_uint2,
doc="Two-byte unsigned integer, little-endian.")
def read_int4(f):
r"""
>>> import io
>>> read_int4(io.BytesIO(b'\xff\x00\x00\x00'))
255
>>> read_int4(io.BytesIO(b'\x00\x00\x00\x80')) == -(2**31)
True
"""
data = f.read(4)
if len(data) == 4:
return _unpack("<i", data)[0]
raise ValueError("not enough data in stream to read int4")
int4 = ArgumentDescriptor(
name='int4',
n=4,
reader=read_int4,
doc="Four-byte signed integer, little-endian, 2's complement.")
def read_uint4(f):
r"""
>>> import io
>>> read_uint4(io.BytesIO(b'\xff\x00\x00\x00'))
255
>>> read_uint4(io.BytesIO(b'\x00\x00\x00\x80')) == 2**31
True
"""
data = f.read(4)
if len(data) == 4:
return _unpack("<I", data)[0]
raise ValueError("not enough data in stream to read uint4")
uint4 = ArgumentDescriptor(
name='uint4',
n=4,
reader=read_uint4,
doc="Four-byte unsigned integer, little-endian.")
def read_uint8(f):
r"""
>>> import io
>>> read_uint8(io.BytesIO(b'\xff\x00\x00\x00\x00\x00\x00\x00'))
255
>>> read_uint8(io.BytesIO(b'\xff' * 8)) == 2**64-1
True
"""
data = f.read(8)
if len(data) == 8:
return _unpack("<Q", data)[0]
raise ValueError("not enough data in stream to read uint8")
uint8 = ArgumentDescriptor(
name='uint8',
n=8,
reader=read_uint8,
doc="Eight-byte unsigned integer, little-endian.")
def read_stringnl(f, decode=True, stripquotes=True):
r"""
>>> import io
>>> read_stringnl(io.BytesIO(b"'abcd'\nefg\n"))
'abcd'
>>> read_stringnl(io.BytesIO(b"\n"))
Traceback (most recent call last):
...
ValueError: no string quotes around b''
>>> read_stringnl(io.BytesIO(b"\n"), stripquotes=False)
''
>>> read_stringnl(io.BytesIO(b"''\n"))
''
>>> read_stringnl(io.BytesIO(b'"abcd"'))
Traceback (most recent call last):
...
ValueError: no newline found when trying to read stringnl
Embedded escapes are undone in the result.
>>> read_stringnl(io.BytesIO(br"'a\n\\b\x00c\td'" + b"\n'e'"))
'a\n\\b\x00c\td'
"""
data = f.readline()
if not data.endswith(b'\n'):
raise ValueError("no newline found when trying to read stringnl")
data = data[:-1] # lose the newline
if stripquotes:
for q in (b'"', b"'"):
if data.startswith(q):
if not data.endswith(q):
raise ValueError("strinq quote %r not found at both "
"ends of %r" % (q, data))
data = data[1:-1]
break
else:
raise ValueError("no string quotes around %r" % data)
if decode:
data = codecs.escape_decode(data)[0].decode("ascii")
return data
stringnl = ArgumentDescriptor(
name='stringnl',
n=UP_TO_NEWLINE,
reader=read_stringnl,
doc="""A newline-terminated string.
This is a repr-style string, with embedded escapes, and
bracketing quotes.
""")
def read_stringnl_noescape(f):
return read_stringnl(f, stripquotes=False)
stringnl_noescape = ArgumentDescriptor(
name='stringnl_noescape',
n=UP_TO_NEWLINE,
reader=read_stringnl_noescape,
doc="""A newline-terminated string.
This is a str-style string, without embedded escapes,
or bracketing quotes. It should consist solely of
printable ASCII characters.
""")
def read_stringnl_noescape_pair(f):
r"""
>>> import io
>>> read_stringnl_noescape_pair(io.BytesIO(b"Queue\nEmpty\njunk"))
'Queue Empty'
"""
return "%s %s" % (read_stringnl_noescape(f), read_stringnl_noescape(f))
stringnl_noescape_pair = ArgumentDescriptor(
name='stringnl_noescape_pair',
n=UP_TO_NEWLINE,
reader=read_stringnl_noescape_pair,
doc="""A pair of newline-terminated strings.
These are str-style strings, without embedded
escapes, or bracketing quotes. They should
consist solely of printable ASCII characters.
The pair is returned as a single string, with
a single blank separating the two strings.
""")
def read_string1(f):
r"""
>>> import io
>>> read_string1(io.BytesIO(b"\x00"))
''
>>> read_string1(io.BytesIO(b"\x03abcdef"))
'abc'
"""
n = read_uint1(f)
assert n >= 0
data = f.read(n)
if len(data) == n:
return data.decode("latin-1")
raise ValueError("expected %d bytes in a string1, but only %d remain" %
(n, len(data)))
string1 = ArgumentDescriptor(
name="string1",
n=TAKEN_FROM_ARGUMENT1,
reader=read_string1,
doc="""A counted string.
The first argument is a 1-byte unsigned int giving the number
of bytes in the string, and the second argument is that many
bytes.
""")
def read_string4(f):
r"""
>>> import io
>>> read_string4(io.BytesIO(b"\x00\x00\x00\x00abc"))
''
>>> read_string4(io.BytesIO(b"\x03\x00\x00\x00abcdef"))
'abc'
>>> read_string4(io.BytesIO(b"\x00\x00\x00\x03abcdef"))
Traceback (most recent call last):
...
ValueError: expected 50331648 bytes in a string4, but only 6 remain
"""
n = read_int4(f)
if n < 0:
raise ValueError("string4 byte count < 0: %d" % n)
data = f.read(n)
if len(data) == n:
return data.decode("latin-1")
raise ValueError("expected %d bytes in a string4, but only %d remain" %
(n, len(data)))
string4 = ArgumentDescriptor(
name="string4",
n=TAKEN_FROM_ARGUMENT4,
reader=read_string4,
doc="""A counted string.
The first argument is a 4-byte little-endian signed int giving
the number of bytes in the string, and the second argument is
that many bytes.
""")
def read_bytes1(f):
r"""
>>> import io
>>> read_bytes1(io.BytesIO(b"\x00"))
b''
>>> read_bytes1(io.BytesIO(b"\x03abcdef"))
b'abc'
"""
n = read_uint1(f)
assert n >= 0
data = f.read(n)
if len(data) == n:
return data
raise ValueError("expected %d bytes in a bytes1, but only %d remain" %
(n, len(data)))
bytes1 = ArgumentDescriptor(
name="bytes1",
n=TAKEN_FROM_ARGUMENT1,
reader=read_bytes1,
doc="""A counted bytes string.
The first argument is a 1-byte unsigned int giving the number
of bytes, and the second argument is that many bytes.
""")
def read_bytes4(f):
r"""
>>> import io
>>> read_bytes4(io.BytesIO(b"\x00\x00\x00\x00abc"))
b''
>>> read_bytes4(io.BytesIO(b"\x03\x00\x00\x00abcdef"))
b'abc'
>>> read_bytes4(io.BytesIO(b"\x00\x00\x00\x03abcdef"))
Traceback (most recent call last):
...
ValueError: expected 50331648 bytes in a bytes4, but only 6 remain
"""
n = read_uint4(f)
assert n >= 0
if n > sys.maxsize:
raise ValueError("bytes4 byte count > sys.maxsize: %d" % n)
data = f.read(n)
if len(data) == n:
return data
raise ValueError("expected %d bytes in a bytes4, but only %d remain" %
(n, len(data)))
bytes4 = ArgumentDescriptor(
name="bytes4",
n=TAKEN_FROM_ARGUMENT4U,
reader=read_bytes4,
doc="""A counted bytes string.
The first argument is a 4-byte little-endian unsigned int giving
the number of bytes, and the second argument is that many bytes.
""")
def read_bytes8(f):
r"""
>>> import io, struct, sys
>>> read_bytes8(io.BytesIO(b"\x00\x00\x00\x00\x00\x00\x00\x00abc"))
b''
>>> read_bytes8(io.BytesIO(b"\x03\x00\x00\x00\x00\x00\x00\x00abcdef"))
b'abc'
>>> bigsize8 = struct.pack("<Q", sys.maxsize//3)
>>> read_bytes8(io.BytesIO(bigsize8 + b"abcdef")) #doctest: +ELLIPSIS
Traceback (most recent call last):
...
ValueError: expected ... bytes in a bytes8, but only 6 remain
"""
n = read_uint8(f)
assert n >= 0
if n > sys.maxsize:
raise ValueError("bytes8 byte count > sys.maxsize: %d" % n)
data = f.read(n)
if len(data) == n:
return data
raise ValueError("expected %d bytes in a bytes8, but only %d remain" %
(n, len(data)))
bytes8 = ArgumentDescriptor(
name="bytes8",
n=TAKEN_FROM_ARGUMENT8U,
reader=read_bytes8,
doc="""A counted bytes string.
The first argument is an 8-byte little-endian unsigned int giving
the number of bytes, and the second argument is that many bytes.
""")
def read_bytearray8(f):
r"""
>>> import io, struct, sys
>>> read_bytearray8(io.BytesIO(b"\x00\x00\x00\x00\x00\x00\x00\x00abc"))
bytearray(b'')
>>> read_bytearray8(io.BytesIO(b"\x03\x00\x00\x00\x00\x00\x00\x00abcdef"))
bytearray(b'abc')
>>> bigsize8 = struct.pack("<Q", sys.maxsize//3)
>>> read_bytearray8(io.BytesIO(bigsize8 + b"abcdef")) #doctest: +ELLIPSIS
Traceback (most recent call last):
...
ValueError: expected ... bytes in a bytearray8, but only 6 remain
"""
n = read_uint8(f)
assert n >= 0
if n > sys.maxsize:
raise ValueError("bytearray8 byte count > sys.maxsize: %d" % n)
data = f.read(n)
if len(data) == n:
return bytearray(data)
raise ValueError("expected %d bytes in a bytearray8, but only %d remain" %
(n, len(data)))
bytearray8 = ArgumentDescriptor(
name="bytearray8",
n=TAKEN_FROM_ARGUMENT8U,
reader=read_bytearray8,
doc="""A counted bytearray.
The first argument is an 8-byte little-endian unsigned int giving
the number of bytes, and the second argument is that many bytes.
""")
def read_unicodestringnl(f):
r"""
>>> import io
>>> read_unicodestringnl(io.BytesIO(b"abc\\uabcd\njunk")) == 'abc\uabcd'
True
"""
data = f.readline()
if not data.endswith(b'\n'):
raise ValueError("no newline found when trying to read "
"unicodestringnl")
data = data[:-1] # lose the newline
return str(data, 'raw-unicode-escape')
unicodestringnl = ArgumentDescriptor(
name='unicodestringnl',
n=UP_TO_NEWLINE,
reader=read_unicodestringnl,
doc="""A newline-terminated Unicode string.
This is raw-unicode-escape encoded, so consists of
printable ASCII characters, and may contain embedded
escape sequences.
""")
def read_unicodestring1(f):
r"""
>>> import io
>>> s = 'abcd\uabcd'
>>> enc = s.encode('utf-8')
>>> enc
b'abcd\xea\xaf\x8d'
>>> n = bytes([len(enc)]) # little-endian 1-byte length
>>> t = read_unicodestring1(io.BytesIO(n + enc + b'junk'))
>>> s == t
True
>>> read_unicodestring1(io.BytesIO(n + enc[:-1]))
Traceback (most recent call last):
...
ValueError: expected 7 bytes in a unicodestring1, but only 6 remain
"""
n = read_uint1(f)
assert n >= 0
data = f.read(n)
if len(data) == n:
return str(data, 'utf-8', 'surrogatepass')
raise ValueError("expected %d bytes in a unicodestring1, but only %d "
"remain" % (n, len(data)))
unicodestring1 = ArgumentDescriptor(
name="unicodestring1",
n=TAKEN_FROM_ARGUMENT1,
reader=read_unicodestring1,
doc="""A counted Unicode string.
The first argument is a 1-byte little-endian signed int
giving the number of bytes in the string, and the second
argument-- the UTF-8 encoding of the Unicode string --
contains that many bytes.
""")
def read_unicodestring4(f):
r"""
>>> import io
>>> s = 'abcd\uabcd'
>>> enc = s.encode('utf-8')
>>> enc
b'abcd\xea\xaf\x8d'
>>> n = bytes([len(enc), 0, 0, 0]) # little-endian 4-byte length
>>> t = read_unicodestring4(io.BytesIO(n + enc + b'junk'))
>>> s == t
True
>>> read_unicodestring4(io.BytesIO(n + enc[:-1]))
Traceback (most recent call last):
...
ValueError: expected 7 bytes in a unicodestring4, but only 6 remain
"""
n = read_uint4(f)
assert n >= 0
if n > sys.maxsize:
raise ValueError("unicodestring4 byte count > sys.maxsize: %d" % n)
data = f.read(n)
if len(data) == n:
return str(data, 'utf-8', 'surrogatepass')
raise ValueError("expected %d bytes in a unicodestring4, but only %d "
"remain" % (n, len(data)))
unicodestring4 = ArgumentDescriptor(
name="unicodestring4",
n=TAKEN_FROM_ARGUMENT4U,
reader=read_unicodestring4,
doc="""A counted Unicode string.
The first argument is a 4-byte little-endian signed int
giving the number of bytes in the string, and the second
argument-- the UTF-8 encoding of the Unicode string --
contains that many bytes.
""")
def read_unicodestring8(f):
r"""
>>> import io
>>> s = 'abcd\uabcd'
>>> enc = s.encode('utf-8')
>>> enc
b'abcd\xea\xaf\x8d'
>>> n = bytes([len(enc)]) + b'\0' * 7 # little-endian 8-byte length
>>> t = read_unicodestring8(io.BytesIO(n + enc + b'junk'))
>>> s == t
True
>>> read_unicodestring8(io.BytesIO(n + enc[:-1]))
Traceback (most recent call last):
...
ValueError: expected 7 bytes in a unicodestring8, but only 6 remain
"""
n = read_uint8(f)
assert n >= 0
if n > sys.maxsize:
raise ValueError("unicodestring8 byte count > sys.maxsize: %d" % n)
data = f.read(n)
if len(data) == n:
return str(data, 'utf-8', 'surrogatepass')
raise ValueError("expected %d bytes in a unicodestring8, but only %d "
"remain" % (n, len(data)))
unicodestring8 = ArgumentDescriptor(
name="unicodestring8",
n=TAKEN_FROM_ARGUMENT8U,
reader=read_unicodestring8,
doc="""A counted Unicode string.
The first argument is an 8-byte little-endian signed int
giving the number of bytes in the string, and the second
argument-- the UTF-8 encoding of the Unicode string --
contains that many bytes.
""")
def read_decimalnl_short(f):
r"""
>>> import io
>>> read_decimalnl_short(io.BytesIO(b"1234\n56"))
1234
>>> read_decimalnl_short(io.BytesIO(b"1234L\n56"))
Traceback (most recent call last):
...
ValueError: invalid literal for int() with base 10: b'1234L'
"""
s = read_stringnl(f, decode=False, stripquotes=False)
# There's a hack for True and False here.
if s == b"00":
return False
elif s == b"01":
return True
return int(s)
def read_decimalnl_long(f):
r"""
>>> import io
>>> read_decimalnl_long(io.BytesIO(b"1234L\n56"))
1234
>>> read_decimalnl_long(io.BytesIO(b"123456789012345678901234L\n6"))
123456789012345678901234
"""
s = read_stringnl(f, decode=False, stripquotes=False)
if s[-1:] == b'L':
s = s[:-1]
return int(s)
decimalnl_short = ArgumentDescriptor(
name='decimalnl_short',
n=UP_TO_NEWLINE,
reader=read_decimalnl_short,
doc="""A newline-terminated decimal integer literal.
This never has a trailing 'L', and the integer fit
in a short Python int on the box where the pickle
was written -- but there's no guarantee it will fit
in a short Python int on the box where the pickle
is read.
""")
decimalnl_long = ArgumentDescriptor(
name='decimalnl_long',
n=UP_TO_NEWLINE,
reader=read_decimalnl_long,
doc="""A newline-terminated decimal integer literal.
This has a trailing 'L', and can represent integers
of any size.
""")
def read_floatnl(f):
r"""
>>> import io
>>> read_floatnl(io.BytesIO(b"-1.25\n6"))
-1.25
"""
s = read_stringnl(f, decode=False, stripquotes=False)
return float(s)
floatnl = ArgumentDescriptor(
name='floatnl',
n=UP_TO_NEWLINE,
reader=read_floatnl,
doc="""A newline-terminated decimal floating literal.
In general this requires 17 significant digits for roundtrip
identity, and pickling then unpickling infinities, NaNs, and
minus zero doesn't work across boxes, or on some boxes even
on itself (e.g., Windows can't read the strings it produces
for infinities or NaNs).
""")
def read_float8(f):
r"""
>>> import io, struct
>>> raw = struct.pack(">d", -1.25)
>>> raw
b'\xbf\xf4\x00\x00\x00\x00\x00\x00'
>>> read_float8(io.BytesIO(raw + b"\n"))
-1.25
"""
data = f.read(8)
if len(data) == 8:
return _unpack(">d", data)[0]
raise ValueError("not enough data in stream to read float8")
float8 = ArgumentDescriptor(
name='float8',
n=8,
reader=read_float8,
doc="""An 8-byte binary representation of a float, big-endian.
The format is unique to Python, and shared with the struct
module (format string '>d') "in theory" (the struct and pickle
implementations don't share the code -- they should). It's
strongly related to the IEEE-754 double format, and, in normal
cases, is in fact identical to the big-endian 754 double format.
On other boxes the dynamic range is limited to that of a 754
double, and "add a half and chop" rounding is used to reduce
the precision to 53 bits. However, even on a 754 box,
infinities, NaNs, and minus zero may not be handled correctly
(may not survive roundtrip pickling intact).
""")
# Protocol 2 formats
from pickle import decode_long
def read_long1(f):
r"""
>>> import io
>>> read_long1(io.BytesIO(b"\x00"))
0
>>> read_long1(io.BytesIO(b"\x02\xff\x00"))
255
>>> read_long1(io.BytesIO(b"\x02\xff\x7f"))
32767
>>> read_long1(io.BytesIO(b"\x02\x00\xff"))
-256
>>> read_long1(io.BytesIO(b"\x02\x00\x80"))
-32768
"""
n = read_uint1(f)
data = f.read(n)
if len(data) != n:
raise ValueError("not enough data in stream to read long1")
return decode_long(data)
long1 = ArgumentDescriptor(
name="long1",
n=TAKEN_FROM_ARGUMENT1,
reader=read_long1,
doc="""A binary long, little-endian, using 1-byte size.
This first reads one byte as an unsigned size, then reads that
many bytes and interprets them as a little-endian 2's-complement long.
If the size is 0, that's taken as a shortcut for the long 0L.
""")
def read_long4(f):
r"""
>>> import io
>>> read_long4(io.BytesIO(b"\x02\x00\x00\x00\xff\x00"))
255
>>> read_long4(io.BytesIO(b"\x02\x00\x00\x00\xff\x7f"))
32767
>>> read_long4(io.BytesIO(b"\x02\x00\x00\x00\x00\xff"))
-256
>>> read_long4(io.BytesIO(b"\x02\x00\x00\x00\x00\x80"))
-32768
>>> read_long1(io.BytesIO(b"\x00\x00\x00\x00"))
0
"""
n = read_int4(f)
if n < 0:
raise ValueError("long4 byte count < 0: %d" % n)
data = f.read(n)
if len(data) != n:
raise ValueError("not enough data in stream to read long4")
return decode_long(data)
long4 = ArgumentDescriptor(
name="long4",
n=TAKEN_FROM_ARGUMENT4,
reader=read_long4,
doc="""A binary representation of a long, little-endian.
This first reads four bytes as a signed size (but requires the
size to be >= 0), then reads that many bytes and interprets them
as a little-endian 2's-complement long. If the size is 0, that's taken
as a shortcut for the int 0, although LONG1 should really be used
then instead (and in any case where # of bytes < 256).
""")
##############################################################################
# Object descriptors. The stack used by the pickle machine holds objects,
# and in the stack_before and stack_after attributes of OpcodeInfo
# descriptors we need names to describe the various types of objects that can
# appear on the stack.
class StackObject(object):
__slots__ = (
# name of descriptor record, for info only
'name',
# type of object, or tuple of type objects (meaning the object can
# be of any type in the tuple)
'obtype',
# human-readable docs for this kind of stack object; a string
'doc',
)
def __init__(self, name, obtype, doc):
assert isinstance(name, str)
self.name = name
assert isinstance(obtype, type) or isinstance(obtype, tuple)
if isinstance(obtype, tuple):
for contained in obtype:
assert isinstance(contained, type)
self.obtype = obtype
assert isinstance(doc, str)
self.doc = doc
def __repr__(self):
return self.name
pyint = pylong = StackObject(
name='int',
obtype=int,
doc="A Python integer object.")
pyinteger_or_bool = StackObject(
name='int_or_bool',
obtype=(int, bool),
doc="A Python integer or boolean object.")
pybool = StackObject(
name='bool',
obtype=bool,
doc="A Python boolean object.")
pyfloat = StackObject(
name='float',
obtype=float,
doc="A Python float object.")
pybytes_or_str = pystring = StackObject(
name='bytes_or_str',
obtype=(bytes, str),