/usr/lib/python3.5/pickle.py is in libpython3.5-minimal 3.5.3-1+deb9u1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 | """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
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:
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 and 4. The
default protocol is 3; a backward-incompatible protocol designed
for Python 3.
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 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._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.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)
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 is not None:
self.write(self.get(x[0]))
return
# 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)
if reduce is not None:
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 is not None:
rv = reduce(self.proto)
else:
reduce = getattr(obj, "__reduce__", None)
if reduce is not None:
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):
# 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, obj=None):
# This API is called by some subclasses
if not isinstance(args, tuple):
raise PicklingError("args from save_reduce() must be a tuple")
if not callable(func):
raise PicklingError("func from save_reduce() must be callable")
save = self.save
write = self.write
func_name = getattr(func, "__name__", "")
if self.proto >= 4 and func_name == "__newobj_ex__":
cls, args, kwargs = args
if not hasattr(cls, "__new__"):
raise PicklingError("args[0] from {} args has no __new__"
.format(func_name))
if obj is not None and cls is not obj.__class__:
raise PicklingError("args[0] from {} args has the wrong class"
.format(func_name))
save(cls)
save(args)
save(kwargs)
write(NEWOBJ_EX)
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(
"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:
# 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)
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[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
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(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
n = len(obj)
if n <= 0xff:
self.write(SHORT_BINBYTES + pack("<B", n) + obj)
elif n > 0xffffffff and self.proto >= 4:
self.write(BINBYTES8 + pack("<Q", n) + obj)
else:
self.write(BINBYTES + pack("<I", n) + obj)
self.memoize(obj)
dispatch[bytes] = save_bytes
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(BINUNICODE8 + pack("<Q", n) + encoded)
else:
self.write(BINUNICODE + pack("<I", n) + encoded)
else:
obj = obj.replace("\\", "\\u005c")
obj = obj.replace("\n", "\\u000a")
self.write(UNICODE + obj.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 element in obj:
save(element)
# 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 element in obj:
save(element)
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
# No recursion.
write(TUPLE)
self.memoize(obj)
dispatch[tuple] = save_tuple
def save_list(self, obj):
if self.bin:
self.write(EMPTY_LIST)
else: # proto 0 -- can't use EMPTY_LIST
self.write(MARK + LIST)
self.memoize(obj)
self._batch_appends(obj)
dispatch[list] = save_list
_BATCHSIZE = 1000
def _batch_appends(self, items):
# Helper to batch up APPENDS sequences
save = self.save
write = self.write
if not self.bin:
for x in items:
save(x)
write(APPEND)
return
it = iter(items)
while True:
tmp = list(islice(it, self._BATCHSIZE))
n = len(tmp)
if n > 1:
write(MARK)
for x in tmp:
save(x)
write(APPENDS)
elif n:
save(tmp[0])
write(APPEND)
# else tmp is empty, and we're done
if n < self._BATCHSIZE:
return
def save_dict(self, obj):
if self.bin:
self.write(EMPTY_DICT)
else: # proto 0 -- can't use EMPTY_DICT
self.write(MARK + DICT)
self.memoize(obj)
self._batch_setitems(obj.items())
dispatch[dict] = save_dict
if PyStringMap is not None:
dispatch[PyStringMap] = save_dict
def _batch_setitems(self, items):
# Helper to batch up SETITEMS sequences; proto >= 1 only
save = self.save
write = self.write
if not self.bin:
for k, v in items:
save(k)
save(v)
write(SETITEM)
return
it = iter(items)
while True:
tmp = list(islice(it, self._BATCHSIZE))
n = len(tmp)
if n > 1:
write(MARK)
for k, v in tmp:
save(k)
save(v)
write(SETITEMS)
elif n:
k, v = tmp[0]
save(k)
save(v)
write(SETITEM)
# else tmp is empty, and we're done
if n < self._BATCHSIZE:
return
def save_set(self, obj):
save = self.save
write = self.write
if self.proto < 4:
self.save_reduce(set, (list(obj),), obj=obj)
return
write(EMPTY_SET)
self.memoize(obj)
it = iter(obj)
while True:
batch = list(islice(it, self._BATCHSIZE))
n = len(batch)
if n > 0:
write(MARK)
for item in batch:
save(item)
write(ADDITEMS)
if n < self._BATCHSIZE:
return
dispatch[set] = save_set
def save_frozenset(self, obj):
save = self.save
write = self.write
if self.proto < 4:
self.save_reduce(frozenset, (list(obj),), obj=obj)
return
write(MARK)
for item in obj:
save(item)
if id(obj) in self.memo:
# 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.
write(POP_MARK + self.get(self.memo[id(obj)][0]))
return
write(FROZENSET)
self.memoize(obj)
dispatch[frozenset] = save_frozenset
def save_global(self, obj, name=None):
write = self.write
memo = self.memo
if name is None:
name = getattr(obj, '__qualname__', None)
if name is None:
name = obj.__name__
module_name = whichmodule(obj, name)
try:
__import__(module_name, level=0)
module = sys.modules[module_name]
obj2, parent = _getattribute(module, name)
except (ImportError, KeyError, AttributeError):
raise PicklingError(
"Can't pickle %r: it's not found as %s.%s" %
(obj, module_name, name))
else:
if obj2 is not obj:
raise PicklingError(
"Can't pickle %r: it's not the same object as %s.%s" %
(obj, module_name, name))
if self.proto >= 2:
code = _extension_registry.get((module_name, name))
if code:
assert code > 0
if code <= 0xff:
write(EXT1 + pack("<B", code))
elif code <= 0xffff:
write(EXT2 + pack("<H", code))
else:
write(EXT4 + pack("<i", code))
return
lastname = name.rpartition('.')[2]
if parent is module:
name = lastname
# Non-ASCII identifiers are supported only with protocols >= 3.
if self.proto >= 4:
self.save(module_name)
self.save(name)
write(STACK_GLOBAL)
elif parent is not module:
self.save_reduce(getattr, (parent, lastname))
elif self.proto >= 3:
write(GLOBAL + bytes(module_name, "utf-8") + b'\n' +
bytes(name, "utf-8") + b'\n')
else:
if self.fix_imports:
r_name_mapping = _compat_pickle.REVERSE_NAME_MAPPING
r_import_mapping = _compat_pickle.REVERSE_IMPORT_MAPPING
if (module_name, name) in r_name_mapping:
module_name, name = r_name_mapping[(module_name, name)]
elif module_name in r_import_mapping:
module_name = r_import_mapping[module_name]
try:
write(GLOBAL + bytes(module_name, "ascii") + b'\n' +
bytes(name, "ascii") + b'\n')
except UnicodeEncodeError:
raise PicklingError(
"can't pickle global identifier '%s.%s' using "
"pickle protocol %i" % (module, name, self.proto))
self.memoize(obj)
def save_type(self, obj):
if obj is type(None):
return self.save_reduce(type, (None,), obj=obj)
elif obj is type(NotImplemented):
return self.save_reduce(type, (NotImplemented,), obj=obj)
elif obj is type(...):
return self.save_reduce(type, (...,), obj=obj)
return self.save_global(obj)
dispatch[FunctionType] = save_global
dispatch[type] = save_type
# Unpickling machinery
class _Unpickler:
def __init__(self, file, *, fix_imports=True,
encoding="ASCII", errors="strict"):
"""This takes a binary file for reading a pickle data stream.
The protocol version of the pickle is detected automatically, so
no proto argument is needed.
The argument *file* must have two methods, a read() method that
takes an integer argument, and a readline() method that requires
no arguments. Both methods should return bytes. Thus *file*
can be a binary file object opened for reading, an io.BytesIO
object, or any other custom object that meets this interface.
The file-like object must have two methods, a read() method
that takes an integer argument, and a readline() method that
requires no arguments. Both methods should return bytes.
Thus file-like object can be a binary file object opened for
reading, a BytesIO object, or any other custom object that
meets this interface.
Optional keyword arguments are *fix_imports*, *encoding* and
*errors*, which are used to control compatibility support for
pickle stream generated by Python 2. If *fix_imports* is True,
pickle will try to map the old Python 2 names to the new names
used in Python 3. The *encoding* and *errors* tell pickle how
to decode 8-bit string instances pickled by Python 2; these
default to 'ASCII' and 'strict', respectively. *encoding* can be
'bytes' to read theses 8-bit string instances as bytes objects.
"""
self._file_readline = file.readline
self._file_read = file.read
self.memo = {}
self.encoding = encoding
self.errors = errors
self.proto = 0
self.fix_imports = fix_imports
def load(self):
"""Read a pickled object representation from the open file.
Return the reconstituted object hierarchy specified in the file.
"""
# Check whether Unpickler was initialized correctly. This is
# only needed to mimic the behavior of _pickle.Unpickler.dump().
if not hasattr(self, "_file_read"):
raise UnpicklingError("Unpickler.__init__() was not called by "
"%s.__init__()" % (self.__class__.__name__,))
self._unframer = _Unframer(self._file_read, self._file_readline)
self.read = self._unframer.read
self.readline = self._unframer.readline
self.mark = object() # any new unique object
self.stack = []
self.append = self.stack.append
self.proto = 0
read = self.read
dispatch = self.dispatch
try:
while True:
key = read(1)
if not key:
raise EOFError
assert isinstance(key, bytes_types)
dispatch[key[0]](self)
except _Stop as stopinst:
return stopinst.value
# Return largest index k such that self.stack[k] is self.mark.
# If the stack doesn't contain a mark, eventually raises IndexError.
# This could be sped by maintaining another stack, of indices at which
# the mark appears. For that matter, the latter stack would suffice,
# and we wouldn't need to push mark objects on self.stack at all.
# Doing so is probably a good thing, though, since if the pickle is
# corrupt (or hostile) we may get a clue from finding self.mark embedded
# in unpickled objects.
def marker(self):
stack = self.stack
mark = self.mark
k = len(stack)-1
while stack[k] is not mark: k = k-1
return k
def persistent_load(self, pid):
raise UnpicklingError("unsupported persistent id encountered")
dispatch = {}
def load_proto(self):
proto = self.read(1)[0]
if not 0 <= proto <= HIGHEST_PROTOCOL:
raise ValueError("unsupported pickle protocol: %d" % proto)
self.proto = proto
dispatch[PROTO[0]] = load_proto
def load_frame(self):
frame_size, = unpack('<Q', self.read(8))
if frame_size > sys.maxsize:
raise ValueError("frame size > sys.maxsize: %d" % frame_size)
self._unframer.load_frame(frame_size)
dispatch[FRAME[0]] = load_frame
def load_persid(self):
try:
pid = self.readline()[:-1].decode("ascii")
except UnicodeDecodeError:
raise UnpicklingError(
"persistent IDs in protocol 0 must be ASCII strings")
self.append(self.persistent_load(pid))
dispatch[PERSID[0]] = load_persid
def load_binpersid(self):
pid = self.stack.pop()
self.append(self.persistent_load(pid))
dispatch[BINPERSID[0]] = load_binpersid
def load_none(self):
self.append(None)
dispatch[NONE[0]] = load_none
def load_false(self):
self.append(False)
dispatch[NEWFALSE[0]] = load_false
def load_true(self):
self.append(True)
dispatch[NEWTRUE[0]] = load_true
def load_int(self):
data = self.readline()
if data == FALSE[1:]:
val = False
elif data == TRUE[1:]:
val = True
else:
val = int(data, 0)
self.append(val)
dispatch[INT[0]] = load_int
def load_binint(self):
self.append(unpack('<i', self.read(4))[0])
dispatch[BININT[0]] = load_binint
def load_binint1(self):
self.append(self.read(1)[0])
dispatch[BININT1[0]] = load_binint1
def load_binint2(self):
self.append(unpack('<H', self.read(2))[0])
dispatch[BININT2[0]] = load_binint2
def load_long(self):
val = self.readline()[:-1]
if val and val[-1] == b'L'[0]:
val = val[:-1]
self.append(int(val, 0))
dispatch[LONG[0]] = load_long
def load_long1(self):
n = self.read(1)[0]
data = self.read(n)
self.append(decode_long(data))
dispatch[LONG1[0]] = load_long1
def load_long4(self):
n, = unpack('<i', self.read(4))
if n < 0:
# Corrupt or hostile pickle -- we never write one like this
raise UnpicklingError("LONG pickle has negative byte count")
data = self.read(n)
self.append(decode_long(data))
dispatch[LONG4[0]] = load_long4
def load_float(self):
self.append(float(self.readline()[:-1]))
dispatch[FLOAT[0]] = load_float
def load_binfloat(self):
self.append(unpack('>d', self.read(8))[0])
dispatch[BINFLOAT[0]] = load_binfloat
def _decode_string(self, value):
# Used to allow strings from Python 2 to be decoded either as
# bytes or Unicode strings. This should be used only with the
# STRING, BINSTRING and SHORT_BINSTRING opcodes.
if self.encoding == "bytes":
return value
else:
return value.decode(self.encoding, self.errors)
def load_string(self):
data = self.readline()[:-1]
# Strip outermost quotes
if len(data) >= 2 and data[0] == data[-1] and data[0] in b'"\'':
data = data[1:-1]
else:
raise UnpicklingError("the STRING opcode argument must be quoted")
self.append(self._decode_string(codecs.escape_decode(data)[0]))
dispatch[STRING[0]] = load_string
def load_binstring(self):
# Deprecated BINSTRING uses signed 32-bit length
len, = unpack('<i', self.read(4))
if len < 0:
raise UnpicklingError("BINSTRING pickle has negative byte count")
data = self.read(len)
self.append(self._decode_string(data))
dispatch[BINSTRING[0]] = load_binstring
def load_binbytes(self):
len, = unpack('<I', self.read(4))
if len > maxsize:
raise UnpicklingError("BINBYTES exceeds system's maximum size "
"of %d bytes" % maxsize)
self.append(self.read(len))
dispatch[BINBYTES[0]] = load_binbytes
def load_unicode(self):
self.append(str(self.readline()[:-1], 'raw-unicode-escape'))
dispatch[UNICODE[0]] = load_unicode
def load_binunicode(self):
len, = unpack('<I', self.read(4))
if len > maxsize:
raise UnpicklingError("BINUNICODE exceeds system's maximum size "
"of %d bytes" % maxsize)
self.append(str(self.read(len), 'utf-8', 'surrogatepass'))
dispatch[BINUNICODE[0]] = load_binunicode
def load_binunicode8(self):
len, = unpack('<Q', self.read(8))
if len > maxsize:
raise UnpicklingError("BINUNICODE8 exceeds system's maximum size "
"of %d bytes" % maxsize)
self.append(str(self.read(len), 'utf-8', 'surrogatepass'))
dispatch[BINUNICODE8[0]] = load_binunicode8
def load_binbytes8(self):
len, = unpack('<Q', self.read(8))
if len > maxsize:
raise UnpicklingError("BINBYTES8 exceeds system's maximum size "
"of %d bytes" % maxsize)
self.append(self.read(len))
dispatch[BINBYTES8[0]] = load_binbytes8
def load_short_binstring(self):
len = self.read(1)[0]
data = self.read(len)
self.append(self._decode_string(data))
dispatch[SHORT_BINSTRING[0]] = load_short_binstring
def load_short_binbytes(self):
len = self.read(1)[0]
self.append(self.read(len))
dispatch[SHORT_BINBYTES[0]] = load_short_binbytes
def load_short_binunicode(self):
len = self.read(1)[0]
self.append(str(self.read(len), 'utf-8', 'surrogatepass'))
dispatch[SHORT_BINUNICODE[0]] = load_short_binunicode
def load_tuple(self):
k = self.marker()
self.stack[k:] = [tuple(self.stack[k+1:])]
dispatch[TUPLE[0]] = load_tuple
def load_empty_tuple(self):
self.append(())
dispatch[EMPTY_TUPLE[0]] = load_empty_tuple
def load_tuple1(self):
self.stack[-1] = (self.stack[-1],)
dispatch[TUPLE1[0]] = load_tuple1
def load_tuple2(self):
self.stack[-2:] = [(self.stack[-2], self.stack[-1])]
dispatch[TUPLE2[0]] = load_tuple2
def load_tuple3(self):
self.stack[-3:] = [(self.stack[-3], self.stack[-2], self.stack[-1])]
dispatch[TUPLE3[0]] = load_tuple3
def load_empty_list(self):
self.append([])
dispatch[EMPTY_LIST[0]] = load_empty_list
def load_empty_dictionary(self):
self.append({})
dispatch[EMPTY_DICT[0]] = load_empty_dictionary
def load_empty_set(self):
self.append(set())
dispatch[EMPTY_SET[0]] = load_empty_set
def load_frozenset(self):
k = self.marker()
self.stack[k:] = [frozenset(self.stack[k+1:])]
dispatch[FROZENSET[0]] = load_frozenset
def load_list(self):
k = self.marker()
self.stack[k:] = [self.stack[k+1:]]
dispatch[LIST[0]] = load_list
def load_dict(self):
k = self.marker()
items = self.stack[k+1:]
d = {items[i]: items[i+1]
for i in range(0, len(items), 2)}
self.stack[k:] = [d]
dispatch[DICT[0]] = load_dict
# INST and OBJ differ only in how they get a class object. It's not
# only sensible to do the rest in a common routine, the two routines
# previously diverged and grew different bugs.
# klass is the class to instantiate, and k points to the topmost mark
# object, following which are the arguments for klass.__init__.
def _instantiate(self, klass, k):
args = tuple(self.stack[k+1:])
del self.stack[k:]
if (args or not isinstance(klass, type) or
hasattr(klass, "__getinitargs__")):
try:
value = klass(*args)
except TypeError as err:
raise TypeError("in constructor for %s: %s" %
(klass.__name__, str(err)), sys.exc_info()[2])
else:
value = klass.__new__(klass)
self.append(value)
def load_inst(self):
module = self.readline()[:-1].decode("ascii")
name = self.readline()[:-1].decode("ascii")
klass = self.find_class(module, name)
self._instantiate(klass, self.marker())
dispatch[INST[0]] = load_inst
def load_obj(self):
# Stack is ... markobject classobject arg1 arg2 ...
k = self.marker()
klass = self.stack.pop(k+1)
self._instantiate(klass, k)
dispatch[OBJ[0]] = load_obj
def load_newobj(self):
args = self.stack.pop()
cls = self.stack.pop()
obj = cls.__new__(cls, *args)
self.append(obj)
dispatch[NEWOBJ[0]] = load_newobj
def load_newobj_ex(self):
kwargs = self.stack.pop()
args = self.stack.pop()
cls = self.stack.pop()
obj = cls.__new__(cls, *args, **kwargs)
self.append(obj)
dispatch[NEWOBJ_EX[0]] = load_newobj_ex
def load_global(self):
module = self.readline()[:-1].decode("utf-8")
name = self.readline()[:-1].decode("utf-8")
klass = self.find_class(module, name)
self.append(klass)
dispatch[GLOBAL[0]] = load_global
def load_stack_global(self):
name = self.stack.pop()
module = self.stack.pop()
if type(name) is not str or type(module) is not str:
raise UnpicklingError("STACK_GLOBAL requires str")
self.append(self.find_class(module, name))
dispatch[STACK_GLOBAL[0]] = load_stack_global
def load_ext1(self):
code = self.read(1)[0]
self.get_extension(code)
dispatch[EXT1[0]] = load_ext1
def load_ext2(self):
code, = unpack('<H', self.read(2))
self.get_extension(code)
dispatch[EXT2[0]] = load_ext2
def load_ext4(self):
code, = unpack('<i', self.read(4))
self.get_extension(code)
dispatch[EXT4[0]] = load_ext4
def get_extension(self, code):
nil = []
obj = _extension_cache.get(code, nil)
if obj is not nil:
self.append(obj)
return
key = _inverted_registry.get(code)
if not key:
if code <= 0: # note that 0 is forbidden
# Corrupt or hostile pickle.
raise UnpicklingError("EXT specifies code <= 0")
raise ValueError("unregistered extension code %d" % code)
obj = self.find_class(*key)
_extension_cache[code] = obj
self.append(obj)
def find_class(self, module, name):
# Subclasses may override this.
if self.proto < 3 and self.fix_imports:
if (module, name) in _compat_pickle.NAME_MAPPING:
module, name = _compat_pickle.NAME_MAPPING[(module, name)]
elif module in _compat_pickle.IMPORT_MAPPING:
module = _compat_pickle.IMPORT_MAPPING[module]
__import__(module, level=0)
if self.proto >= 4:
return _getattribute(sys.modules[module], name)[0]
else:
return getattr(sys.modules[module], name)
def load_reduce(self):
stack = self.stack
args = stack.pop()
func = stack[-1]
stack[-1] = func(*args)
dispatch[REDUCE[0]] = load_reduce
def load_pop(self):
del self.stack[-1]
dispatch[POP[0]] = load_pop
def load_pop_mark(self):
k = self.marker()
del self.stack[k:]
dispatch[POP_MARK[0]] = load_pop_mark
def load_dup(self):
self.append(self.stack[-1])
dispatch[DUP[0]] = load_dup
def load_get(self):
i = int(self.readline()[:-1])
self.append(self.memo[i])
dispatch[GET[0]] = load_get
def load_binget(self):
i = self.read(1)[0]
self.append(self.memo[i])
dispatch[BINGET[0]] = load_binget
def load_long_binget(self):
i, = unpack('<I', self.read(4))
self.append(self.memo[i])
dispatch[LONG_BINGET[0]] = load_long_binget
def load_put(self):
i = int(self.readline()[:-1])
if i < 0:
raise ValueError("negative PUT argument")
self.memo[i] = self.stack[-1]
dispatch[PUT[0]] = load_put
def load_binput(self):
i = self.read(1)[0]
if i < 0:
raise ValueError("negative BINPUT argument")
self.memo[i] = self.stack[-1]
dispatch[BINPUT[0]] = load_binput
def load_long_binput(self):
i, = unpack('<I', self.read(4))
if i > maxsize:
raise ValueError("negative LONG_BINPUT argument")
self.memo[i] = self.stack[-1]
dispatch[LONG_BINPUT[0]] = load_long_binput
def load_memoize(self):
memo = self.memo
memo[len(memo)] = self.stack[-1]
dispatch[MEMOIZE[0]] = load_memoize
def load_append(self):
stack = self.stack
value = stack.pop()
list = stack[-1]
list.append(value)
dispatch[APPEND[0]] = load_append
def load_appends(self):
stack = self.stack
mark = self.marker()
list_obj = stack[mark - 1]
items = stack[mark + 1:]
if isinstance(list_obj, list):
list_obj.extend(items)
else:
append = list_obj.append
for item in items:
append(item)
del stack[mark:]
dispatch[APPENDS[0]] = load_appends
def load_setitem(self):
stack = self.stack
value = stack.pop()
key = stack.pop()
dict = stack[-1]
dict[key] = value
dispatch[SETITEM[0]] = load_setitem
def load_setitems(self):
stack = self.stack
mark = self.marker()
dict = stack[mark - 1]
for i in range(mark + 1, len(stack), 2):
dict[stack[i]] = stack[i + 1]
del stack[mark:]
dispatch[SETITEMS[0]] = load_setitems
def load_additems(self):
stack = self.stack
mark = self.marker()
set_obj = stack[mark - 1]
items = stack[mark + 1:]
if isinstance(set_obj, set):
set_obj.update(items)
else:
add = set_obj.add
for item in items:
add(item)
del stack[mark:]
dispatch[ADDITEMS[0]] = load_additems
def load_build(self):
stack = self.stack
state = stack.pop()
inst = stack[-1]
setstate = getattr(inst, "__setstate__", None)
if setstate is not None:
setstate(state)
return
slotstate = None
if isinstance(state, tuple) and len(state) == 2:
state, slotstate = state
if state:
inst_dict = inst.__dict__
intern = sys.intern
for k, v in state.items():
if type(k) is str:
inst_dict[intern(k)] = v
else:
inst_dict[k] = v
if slotstate:
for k, v in slotstate.items():
setattr(inst, k, v)
dispatch[BUILD[0]] = load_build
def load_mark(self):
self.append(self.mark)
dispatch[MARK[0]] = load_mark
def load_stop(self):
value = self.stack.pop()
raise _Stop(value)
dispatch[STOP[0]] = load_stop
# Shorthands
def _dump(obj, file, protocol=None, *, fix_imports=True):
_Pickler(file, protocol, fix_imports=fix_imports).dump(obj)
def _dumps(obj, protocol=None, *, fix_imports=True):
f = io.BytesIO()
_Pickler(f, protocol, fix_imports=fix_imports).dump(obj)
res = f.getvalue()
assert isinstance(res, bytes_types)
return res
def _load(file, *, fix_imports=True, encoding="ASCII", errors="strict"):
return _Unpickler(file, fix_imports=fix_imports,
encoding=encoding, errors=errors).load()
def _loads(s, *, fix_imports=True, encoding="ASCII", errors="strict"):
if isinstance(s, str):
raise TypeError("Can't load pickle from unicode string")
file = io.BytesIO(s)
return _Unpickler(file, fix_imports=fix_imports,
encoding=encoding, errors=errors).load()
# Use the faster _pickle if possible
try:
from _pickle import (
PickleError,
PicklingError,
UnpicklingError,
Pickler,
Unpickler,
dump,
dumps,
load,
loads
)
except ImportError:
Pickler, Unpickler = _Pickler, _Unpickler
dump, dumps, load, loads = _dump, _dumps, _load, _loads
# Doctest
def _test():
import doctest
return doctest.testmod()
if __name__ == "__main__":
import argparse
parser = argparse.ArgumentParser(
description='display contents of the pickle files')
parser.add_argument(
'pickle_file', type=argparse.FileType('br'),
nargs='*', help='the pickle file')
parser.add_argument(
'-t', '--test', action='store_true',
help='run self-test suite')
parser.add_argument(
'-v', action='store_true',
help='run verbosely; only affects self-test run')
args = parser.parse_args()
if args.test:
_test()
else:
if not args.pickle_file:
parser.print_help()
else:
import pprint
for f in args.pickle_file:
obj = load(f)
pprint.pprint(obj)
|