summaryrefslogtreecommitdiffstats
path: root/Lib/zipfile.py
blob: bda61343571601a4f13a409d5e5020ed677b150b (plain)
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
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
"""
Read and write ZIP files.

XXX references to utf-8 need further investigation.
"""
import io
import os
import re
import importlib.util
import sys
import time
import stat
import shutil
import struct
import binascii


try:
    import zlib # We may need its compression method
    crc32 = zlib.crc32
except ImportError:
    zlib = None
    crc32 = binascii.crc32

try:
    import bz2 # We may need its compression method
except ImportError:
    bz2 = None

try:
    import lzma # We may need its compression method
except ImportError:
    lzma = None

__all__ = ["BadZipFile", "BadZipfile", "error",
           "ZIP_STORED", "ZIP_DEFLATED", "ZIP_BZIP2", "ZIP_LZMA",
           "is_zipfile", "ZipInfo", "ZipFile", "PyZipFile", "LargeZipFile"]

class BadZipFile(Exception):
    pass


class LargeZipFile(Exception):
    """
    Raised when writing a zipfile, the zipfile requires ZIP64 extensions
    and those extensions are disabled.
    """

error = BadZipfile = BadZipFile      # Pre-3.2 compatibility names


ZIP64_LIMIT = (1 << 31) - 1
ZIP_FILECOUNT_LIMIT = (1 << 16) - 1
ZIP_MAX_COMMENT = (1 << 16) - 1

# constants for Zip file compression methods
ZIP_STORED = 0
ZIP_DEFLATED = 8
ZIP_BZIP2 = 12
ZIP_LZMA = 14
# Other ZIP compression methods not supported

DEFAULT_VERSION = 20
ZIP64_VERSION = 45
BZIP2_VERSION = 46
LZMA_VERSION = 63
# we recognize (but not necessarily support) all features up to that version
MAX_EXTRACT_VERSION = 63

# Below are some formats and associated data for reading/writing headers using
# the struct module.  The names and structures of headers/records are those used
# in the PKWARE description of the ZIP file format:
#     http://www.pkware.com/documents/casestudies/APPNOTE.TXT
# (URL valid as of January 2008)

# The "end of central directory" structure, magic number, size, and indices
# (section V.I in the format document)
structEndArchive = b"<4s4H2LH"
stringEndArchive = b"PK\005\006"
sizeEndCentDir = struct.calcsize(structEndArchive)

_ECD_SIGNATURE = 0
_ECD_DISK_NUMBER = 1
_ECD_DISK_START = 2
_ECD_ENTRIES_THIS_DISK = 3
_ECD_ENTRIES_TOTAL = 4
_ECD_SIZE = 5
_ECD_OFFSET = 6
_ECD_COMMENT_SIZE = 7
# These last two indices are not part of the structure as defined in the
# spec, but they are used internally by this module as a convenience
_ECD_COMMENT = 8
_ECD_LOCATION = 9

# The "central directory" structure, magic number, size, and indices
# of entries in the structure (section V.F in the format document)
structCentralDir = "<4s4B4HL2L5H2L"
stringCentralDir = b"PK\001\002"
sizeCentralDir = struct.calcsize(structCentralDir)

# indexes of entries in the central directory structure
_CD_SIGNATURE = 0
_CD_CREATE_VERSION = 1
_CD_CREATE_SYSTEM = 2
_CD_EXTRACT_VERSION = 3
_CD_EXTRACT_SYSTEM = 4
_CD_FLAG_BITS = 5
_CD_COMPRESS_TYPE = 6
_CD_TIME = 7
_CD_DATE = 8
_CD_CRC = 9
_CD_COMPRESSED_SIZE = 10
_CD_UNCOMPRESSED_SIZE = 11
_CD_FILENAME_LENGTH = 12
_CD_EXTRA_FIELD_LENGTH = 13
_CD_COMMENT_LENGTH = 14
_CD_DISK_NUMBER_START = 15
_CD_INTERNAL_FILE_ATTRIBUTES = 16
_CD_EXTERNAL_FILE_ATTRIBUTES = 17
_CD_LOCAL_HEADER_OFFSET = 18

# The "local file header" structure, magic number, size, and indices
# (section V.A in the format document)
structFileHeader = "<4s2B4HL2L2H"
stringFileHeader = b"PK\003\004"
sizeFileHeader = struct.calcsize(structFileHeader)

_FH_SIGNATURE = 0
_FH_EXTRACT_VERSION = 1
_FH_EXTRACT_SYSTEM = 2
_FH_GENERAL_PURPOSE_FLAG_BITS = 3
_FH_COMPRESSION_METHOD = 4
_FH_LAST_MOD_TIME = 5
_FH_LAST_MOD_DATE = 6
_FH_CRC = 7
_FH_COMPRESSED_SIZE = 8
_FH_UNCOMPRESSED_SIZE = 9
_FH_FILENAME_LENGTH = 10
_FH_EXTRA_FIELD_LENGTH = 11

# The "Zip64 end of central directory locator" structure, magic number, and size
structEndArchive64Locator = "<4sLQL"
stringEndArchive64Locator = b"PK\x06\x07"
sizeEndCentDir64Locator = struct.calcsize(structEndArchive64Locator)

# The "Zip64 end of central directory" record, magic number, size, and indices
# (section V.G in the format document)
structEndArchive64 = "<4sQ2H2L4Q"
stringEndArchive64 = b"PK\x06\x06"
sizeEndCentDir64 = struct.calcsize(structEndArchive64)

_CD64_SIGNATURE = 0
_CD64_DIRECTORY_RECSIZE = 1
_CD64_CREATE_VERSION = 2
_CD64_EXTRACT_VERSION = 3
_CD64_DISK_NUMBER = 4
_CD64_DISK_NUMBER_START = 5
_CD64_NUMBER_ENTRIES_THIS_DISK = 6
_CD64_NUMBER_ENTRIES_TOTAL = 7
_CD64_DIRECTORY_SIZE = 8
_CD64_OFFSET_START_CENTDIR = 9

def _check_zipfile(fp):
    try:
        if _EndRecData(fp):
            return True         # file has correct magic number
    except OSError:
        pass
    return False

def is_zipfile(filename):
    """Quickly see if a file is a ZIP file by checking the magic number.

    The filename argument may be a file or file-like object too.
    """
    result = False
    try:
        if hasattr(filename, "read"):
            result = _check_zipfile(fp=filename)
        else:
            with open(filename, "rb") as fp:
                result = _check_zipfile(fp)
    except OSError:
        pass
    return result

def _EndRecData64(fpin, offset, endrec):
    """
    Read the ZIP64 end-of-archive records and use that to update endrec
    """
    try:
        fpin.seek(offset - sizeEndCentDir64Locator, 2)
    except OSError:
        # If the seek fails, the file is not large enough to contain a ZIP64
        # end-of-archive record, so just return the end record we were given.
        return endrec

    data = fpin.read(sizeEndCentDir64Locator)
    if len(data) != sizeEndCentDir64Locator:
        return endrec
    sig, diskno, reloff, disks = struct.unpack(structEndArchive64Locator, data)
    if sig != stringEndArchive64Locator:
        return endrec

    if diskno != 0 or disks != 1:
        raise BadZipFile("zipfiles that span multiple disks are not supported")

    # Assume no 'zip64 extensible data'
    fpin.seek(offset - sizeEndCentDir64Locator - sizeEndCentDir64, 2)
    data = fpin.read(sizeEndCentDir64)
    if len(data) != sizeEndCentDir64:
        return endrec
    sig, sz, create_version, read_version, disk_num, disk_dir, \
        dircount, dircount2, dirsize, diroffset = \
        struct.unpack(structEndArchive64, data)
    if sig != stringEndArchive64:
        return endrec

    # Update the original endrec using data from the ZIP64 record
    endrec[_ECD_SIGNATURE] = sig
    endrec[_ECD_DISK_NUMBER] = disk_num
    endrec[_ECD_DISK_START] = disk_dir
    endrec[_ECD_ENTRIES_THIS_DISK] = dircount
    endrec[_ECD_ENTRIES_TOTAL] = dircount2
    endrec[_ECD_SIZE] = dirsize
    endrec[_ECD_OFFSET] = diroffset
    return endrec


def _EndRecData(fpin):
    """Return data from the "End of Central Directory" record, or None.

    The data is a list of the nine items in the ZIP "End of central dir"
    record followed by a tenth item, the file seek offset of this record."""

    # Determine file size
    fpin.seek(0, 2)
    filesize = fpin.tell()

    # Check to see if this is ZIP file with no archive comment (the
    # "end of central directory" structure should be the last item in the
    # file if this is the case).
    try:
        fpin.seek(-sizeEndCentDir, 2)
    except OSError:
        return None
    data = fpin.read()
    if (len(data) == sizeEndCentDir and
        data[0:4] == stringEndArchive and
        data[-2:] == b"\000\000"):
        # the signature is correct and there's no comment, unpack structure
        endrec = struct.unpack(structEndArchive, data)
        endrec=list(endrec)

        # Append a blank comment and record start offset
        endrec.append(b"")
        endrec.append(filesize - sizeEndCentDir)

        # Try to read the "Zip64 end of central directory" structure
        return _EndRecData64(fpin, -sizeEndCentDir, endrec)

    # Either this is not a ZIP file, or it is a ZIP file with an archive
    # comment.  Search the end of the file for the "end of central directory"
    # record signature. The comment is the last item in the ZIP file and may be
    # up to 64K long.  It is assumed that the "end of central directory" magic
    # number does not appear in the comment.
    maxCommentStart = max(filesize - (1 << 16) - sizeEndCentDir, 0)
    fpin.seek(maxCommentStart, 0)
    data = fpin.read()
    start = data.rfind(stringEndArchive)
    if start >= 0:
        # found the magic number; attempt to unpack and interpret
        recData = data[start:start+sizeEndCentDir]
        if len(recData) != sizeEndCentDir:
            # Zip file is corrupted.
            return None
        endrec = list(struct.unpack(structEndArchive, recData))
        commentSize = endrec[_ECD_COMMENT_SIZE] #as claimed by the zip file
        comment = data[start+sizeEndCentDir:start+sizeEndCentDir+commentSize]
        endrec.append(comment)
        endrec.append(maxCommentStart + start)

        # Try to read the "Zip64 end of central directory" structure
        return _EndRecData64(fpin, maxCommentStart + start - filesize,
                             endrec)

    # Unable to find a valid end of central directory structure
    return None


class ZipInfo (object):
    """Class with attributes describing each file in the ZIP archive."""

    __slots__ = (
        'orig_filename',
        'filename',
        'date_time',
        'compress_type',
        'comment',
        'extra',
        'create_system',
        'create_version',
        'extract_version',
        'reserved',
        'flag_bits',
        'volume',
        'internal_attr',
        'external_attr',
        'header_offset',
        'CRC',
        'compress_size',
        'file_size',
        '_raw_time',
    )

    def __init__(self, filename="NoName", date_time=(1980,1,1,0,0,0)):
        self.orig_filename = filename   # Original file name in archive

        # Terminate the file name at the first null byte.  Null bytes in file
        # names are used as tricks by viruses in archives.
        null_byte = filename.find(chr(0))
        if null_byte >= 0:
            filename = filename[0:null_byte]
        # This is used to ensure paths in generated ZIP files always use
        # forward slashes as the directory separator, as required by the
        # ZIP format specification.
        if os.sep != "/" and os.sep in filename:
            filename = filename.replace(os.sep, "/")

        self.filename = filename        # Normalized file name
        self.date_time = date_time      # year, month, day, hour, min, sec

        if date_time[0] < 1980:
            raise ValueError('ZIP does not support timestamps before 1980')

        # Standard values:
        self.compress_type = ZIP_STORED # Type of compression for the file
        self.comment = b""              # Comment for each file
        self.extra = b""                # ZIP extra data
        if sys.platform == 'win32':
            self.create_system = 0          # System which created ZIP archive
        else:
            # Assume everything else is unix-y
            self.create_system = 3          # System which created ZIP archive
        self.create_version = DEFAULT_VERSION  # Version which created ZIP archive
        self.extract_version = DEFAULT_VERSION # Version needed to extract archive
        self.reserved = 0               # Must be zero
        self.flag_bits = 0              # ZIP flag bits
        self.volume = 0                 # Volume number of file header
        self.internal_attr = 0          # Internal attributes
        self.external_attr = 0          # External file attributes
        # Other attributes are set by class ZipFile:
        # header_offset         Byte offset to the file header
        # CRC                   CRC-32 of the uncompressed file
        # compress_size         Size of the compressed file
        # file_size             Size of the uncompressed file

    def FileHeader(self, zip64=None):
        """Return the per-file header as a string."""
        dt = self.date_time
        dosdate = (dt[0] - 1980) << 9 | dt[1] << 5 | dt[2]
        dostime = dt[3] << 11 | dt[4] << 5 | (dt[5] // 2)
        if self.flag_bits & 0x08:
            # Set these to zero because we write them after the file data
            CRC = compress_size = file_size = 0
        else:
            CRC = self.CRC
            compress_size = self.compress_size
            file_size = self.file_size

        extra = self.extra

        min_version = 0
        if zip64 is None:
            zip64 = file_size > ZIP64_LIMIT or compress_size > ZIP64_LIMIT
        if zip64:
            fmt = '<HHQQ'
            extra = extra + struct.pack(fmt,
                                        1, struct.calcsize(fmt)-4, file_size, compress_size)
        if file_size > ZIP64_LIMIT or compress_size > ZIP64_LIMIT:
            if not zip64:
                raise LargeZipFile("Filesize would require ZIP64 extensions")
            # File is larger than what fits into a 4 byte integer,
            # fall back to the ZIP64 extension
            file_size = 0xffffffff
            compress_size = 0xffffffff
            min_version = ZIP64_VERSION

        if self.compress_type == ZIP_BZIP2:
            min_version = max(BZIP2_VERSION, min_version)
        elif self.compress_type == ZIP_LZMA:
            min_version = max(LZMA_VERSION, min_version)

        self.extract_version = max(min_version, self.extract_version)
        self.create_version = max(min_version, self.create_version)
        filename, flag_bits = self._encodeFilenameFlags()
        header = struct.pack(structFileHeader, stringFileHeader,
                             self.extract_version, self.reserved, flag_bits,
                             self.compress_type, dostime, dosdate, CRC,
                             compress_size, file_size,
                             len(filename), len(extra))
        return header + filename + extra

    def _encodeFilenameFlags(self):
        try:
            return self.filename.encode('ascii'), self.flag_bits
        except UnicodeEncodeError:
            return self.filename.encode('utf-8'), self.flag_bits | 0x800

    def _decodeExtra(self):
        # Try to decode the extra field.
        extra = self.extra
        unpack = struct.unpack
        while len(extra) >= 4:
            tp, ln = unpack('<HH', extra[:4])
            if tp == 1:
                if ln >= 24:
                    counts = unpack('<QQQ', extra[4:28])
                elif ln == 16:
                    counts = unpack('<QQ', extra[4:20])
                elif ln == 8:
                    counts = unpack('<Q', extra[4:12])
                elif ln == 0:
                    counts = ()
                else:
                    raise RuntimeError("Corrupt extra field %s"%(ln,))

                idx = 0

                # ZIP64 extension (large files and/or large archives)
                if self.file_size in (0xffffffffffffffff, 0xffffffff):
                    self.file_size = counts[idx]
                    idx += 1

                if self.compress_size == 0xFFFFFFFF:
                    self.compress_size = counts[idx]
                    idx += 1

                if self.header_offset == 0xffffffff:
                    old = self.header_offset
                    self.header_offset = counts[idx]
                    idx+=1

            extra = extra[ln+4:]


class _ZipDecrypter:
    """Class to handle decryption of files stored within a ZIP archive.

    ZIP supports a password-based form of encryption. Even though known
    plaintext attacks have been found against it, it is still useful
    to be able to get data out of such a file.

    Usage:
        zd = _ZipDecrypter(mypwd)
        plain_char = zd(cypher_char)
        plain_text = map(zd, cypher_text)
    """

    def _GenerateCRCTable():
        """Generate a CRC-32 table.

        ZIP encryption uses the CRC32 one-byte primitive for scrambling some
        internal keys. We noticed that a direct implementation is faster than
        relying on binascii.crc32().
        """
        poly = 0xedb88320
        table = [0] * 256
        for i in range(256):
            crc = i
            for j in range(8):
                if crc & 1:
                    crc = ((crc >> 1) & 0x7FFFFFFF) ^ poly
                else:
                    crc = ((crc >> 1) & 0x7FFFFFFF)
            table[i] = crc
        return table
    crctable = None

    def _crc32(self, ch, crc):
        """Compute the CRC32 primitive on one byte."""
        return ((crc >> 8) & 0xffffff) ^ self.crctable[(crc ^ ch) & 0xff]

    def __init__(self, pwd):
        if _ZipDecrypter.crctable is None:
            _ZipDecrypter.crctable = _ZipDecrypter._GenerateCRCTable()
        self.key0 = 305419896
        self.key1 = 591751049
        self.key2 = 878082192
        for p in pwd:
            self._UpdateKeys(p)

    def _UpdateKeys(self, c):
        self.key0 = self._crc32(c, self.key0)
        self.key1 = (self.key1 + (self.key0 & 255)) & 4294967295
        self.key1 = (self.key1 * 134775813 + 1) & 4294967295
        self.key2 = self._crc32((self.key1 >> 24) & 255, self.key2)

    def __call__(self, c):
        """Decrypt a single character."""
        assert isinstance(c, int)
        k = self.key2 | 2
        c = c ^ (((k * (k^1)) >> 8) & 255)
        self._UpdateKeys(c)
        return c


class LZMACompressor:

    def __init__(self):
        self._comp = None

    def _init(self):
        props = lzma._encode_filter_properties({'id': lzma.FILTER_LZMA1})
        self._comp = lzma.LZMACompressor(lzma.FORMAT_RAW, filters=[
            lzma._decode_filter_properties(lzma.FILTER_LZMA1, props)
        ])
        return struct.pack('<BBH', 9, 4, len(props)) + props

    def compress(self, data):
        if self._comp is None:
            return self._init() + self._comp.compress(data)
        return self._comp.compress(data)

    def flush(self):
        if self._comp is None:
            return self._init() + self._comp.flush()
        return self._comp.flush()


class LZMADecompressor:

    def __init__(self):
        self._decomp = None
        self._unconsumed = b''
        self.eof = False

    def decompress(self, data):
        if self._decomp is None:
            self._unconsumed += data
            if len(self._unconsumed) <= 4:
                return b''
            psize, = struct.unpack('<H', self._unconsumed[2:4])
            if len(self._unconsumed) <= 4 + psize:
                return b''

            self._decomp = lzma.LZMADecompressor(lzma.FORMAT_RAW, filters=[
                lzma._decode_filter_properties(lzma.FILTER_LZMA1,
                                               self._unconsumed[4:4 + psize])
            ])
            data = self._unconsumed[4 + psize:]
            del self._unconsumed

        result = self._decomp.decompress(data)
        self.eof = self._decomp.eof
        return result


compressor_names = {
    0: 'store',
    1: 'shrink',
    2: 'reduce',
    3: 'reduce',
    4: 'reduce',
    5: 'reduce',
    6: 'implode',
    7: 'tokenize',
    8: 'deflate',
    9: 'deflate64',
    10: 'implode',
    12: 'bzip2',
    14: 'lzma',
    18: 'terse',
    19: 'lz77',
    97: 'wavpack',
    98: 'ppmd',
}

def _check_compression(compression):
    if compression == ZIP_STORED:
        pass
    elif compression == ZIP_DEFLATED:
        if not zlib:
            raise RuntimeError(
                "Compression requires the (missing) zlib module")
    elif compression == ZIP_BZIP2:
        if not bz2:
            raise RuntimeError(
                "Compression requires the (missing) bz2 module")
    elif compression == ZIP_LZMA:
        if not lzma:
            raise RuntimeError(
                "Compression requires the (missing) lzma module")
    else:
        raise RuntimeError("That compression method is not supported")


def _get_compressor(compress_type):
    if compress_type == ZIP_DEFLATED:
        return zlib.compressobj(zlib.Z_DEFAULT_COMPRESSION,
                                zlib.DEFLATED, -15)
    elif compress_type == ZIP_BZIP2:
        return bz2.BZ2Compressor()
    elif compress_type == ZIP_LZMA:
        return LZMACompressor()
    else:
        return None


def _get_decompressor(compress_type):
    if compress_type == ZIP_STORED:
        return None
    elif compress_type == ZIP_DEFLATED:
        return zlib.decompressobj(-15)
    elif compress_type == ZIP_BZIP2:
        return bz2.BZ2Decompressor()
    elif compress_type == ZIP_LZMA:
        return LZMADecompressor()
    else:
        descr = compressor_names.get(compress_type)
        if descr:
            raise NotImplementedError("compression type %d (%s)" % (compress_type, descr))
        else:
            raise NotImplementedError("compression type %d" % (compress_type,))


class ZipExtFile(io.BufferedIOBase):
    """File-like object for reading an archive member.
       Is returned by ZipFile.open().
    """

    # Max size supported by decompressor.
    MAX_N = 1 << 31 - 1

    # Read from compressed files in 4k blocks.
    MIN_READ_SIZE = 4096

    # Search for universal newlines or line chunks.
    PATTERN = re.compile(br'^(?P<chunk>[^\r\n]+)|(?P<newline>\n|\r\n?)')

    def __init__(self, fileobj, mode, zipinfo, decrypter=None,
                 close_fileobj=False):
        self._fileobj = fileobj
        self._decrypter = decrypter
        self._close_fileobj = close_fileobj

        self._compress_type = zipinfo.compress_type
        self._compress_left = zipinfo.compress_size
        self._left = zipinfo.file_size

        self._decompressor = _get_decompressor(self._compress_type)

        self._eof = False
        self._readbuffer = b''
        self._offset = 0

        self._universal = 'U' in mode
        self.newlines = None

        # Adjust read size for encrypted files since the first 12 bytes
        # are for the encryption/password information.
        if self._decrypter is not None:
            self._compress_left -= 12

        self.mode = mode
        self.name = zipinfo.filename

        if hasattr(zipinfo, 'CRC'):
            self._expected_crc = zipinfo.CRC
            self._running_crc = crc32(b'') & 0xffffffff
        else:
            self._expected_crc = None

    def readline(self, limit=-1):
        """Read and return a line from the stream.

        If limit is specified, at most limit bytes will be read.
        """

        if not self._universal and limit < 0:
            # Shortcut common case - newline found in buffer.
            i = self._readbuffer.find(b'\n', self._offset) + 1
            if i > 0:
                line = self._readbuffer[self._offset: i]
                self._offset = i
                return line

        if not self._universal:
            return io.BufferedIOBase.readline(self, limit)

        line = b''
        while limit < 0 or len(line) < limit:
            readahead = self.peek(2)
            if readahead == b'':
                return line

            #
            # Search for universal newlines or line chunks.
            #
            # The pattern returns either a line chunk or a newline, but not
            # both. Combined with peek(2), we are assured that the sequence
            # '\r\n' is always retrieved completely and never split into
            # separate newlines - '\r', '\n' due to coincidental readaheads.
            #
            match = self.PATTERN.search(readahead)
            newline = match.group('newline')
            if newline is not None:
                if self.newlines is None:
                    self.newlines = []
                if newline not in self.newlines:
                    self.newlines.append(newline)
                self._offset += len(newline)
                return line + b'\n'

            chunk = match.group('chunk')
            if limit >= 0:
                chunk = chunk[: limit - len(line)]

            self._offset += len(chunk)
            line += chunk

        return line

    def peek(self, n=1):
        """Returns buffered bytes without advancing the position."""
        if n > len(self._readbuffer) - self._offset:
            chunk = self.read(n)
            if len(chunk) > self._offset:
                self._readbuffer = chunk + self._readbuffer[self._offset:]
                self._offset = 0
            else:
                self._offset -= len(chunk)

        # Return up to 512 bytes to reduce allocation overhead for tight loops.
        return self._readbuffer[self._offset: self._offset + 512]

    def readable(self):
        return True

    def read(self, n=-1):
        """Read and return up to n bytes.
        If the argument is omitted, None, or negative, data is read and returned until EOF is reached..
        """
        if n is None or n < 0:
            buf = self._readbuffer[self._offset:]
            self._readbuffer = b''
            self._offset = 0
            while not self._eof:
                buf += self._read1(self.MAX_N)
            return buf

        end = n + self._offset
        if end < len(self._readbuffer):
            buf = self._readbuffer[self._offset:end]
            self._offset = end
            return buf

        n = end - len(self._readbuffer)
        buf = self._readbuffer[self._offset:]
        self._readbuffer = b''
        self._offset = 0
        while n > 0 and not self._eof:
            data = self._read1(n)
            if n < len(data):
                self._readbuffer = data
                self._offset = n
                buf += data[:n]
                break
            buf += data
            n -= len(data)
        return buf

    def _update_crc(self, newdata):
        # Update the CRC using the given data.
        if self._expected_crc is None:
            # No need to compute the CRC if we don't have a reference value
            return
        self._running_crc = crc32(newdata, self._running_crc) & 0xffffffff
        # Check the CRC if we're at the end of the file
        if self._eof and self._running_crc != self._expected_crc:
            raise BadZipFile("Bad CRC-32 for file %r" % self.name)

    def read1(self, n):
        """Read up to n bytes with at most one read() system call."""

        if n is None or n < 0:
            buf = self._readbuffer[self._offset:]
            self._readbuffer = b''
            self._offset = 0
            while not self._eof:
                data = self._read1(self.MAX_N)
                if data:
                    buf += data
                    break
            return buf

        end = n + self._offset
        if end < len(self._readbuffer):
            buf = self._readbuffer[self._offset:end]
            self._offset = end
            return buf

        n = end - len(self._readbuffer)
        buf = self._readbuffer[self._offset:]
        self._readbuffer = b''
        self._offset = 0
        if n > 0:
            while not self._eof:
                data = self._read1(n)
                if n < len(data):
                    self._readbuffer = data
                    self._offset = n
                    buf += data[:n]
                    break
                if data:
                    buf += data
                    break
        return buf

    def _read1(self, n):
        # Read up to n compressed bytes with at most one read() system call,
        # decrypt and decompress them.
        if self._eof or n <= 0:
            return b''

        # Read from file.
        if self._compress_type == ZIP_DEFLATED:
            ## Handle unconsumed data.
            data = self._decompressor.unconsumed_tail
            if n > len(data):
                data += self._read2(n - len(data))
        else:
            data = self._read2(n)

        if self._compress_type == ZIP_STORED:
            self._eof = self._compress_left <= 0
        elif self._compress_type == ZIP_DEFLATED:
            n = max(n, self.MIN_READ_SIZE)
            data = self._decompressor.decompress(data, n)
            self._eof = (self._decompressor.eof or
                         self._compress_left <= 0 and
                         not self._decompressor.unconsumed_tail)
            if self._eof:
                data += self._decompressor.flush()
        else:
            data = self._decompressor.decompress(data)
            self._eof = self._decompressor.eof or self._compress_left <= 0

        data = data[:self._left]
        self._left -= len(data)
        if self._left <= 0:
            self._eof = True
        self._update_crc(data)
        return data

    def _read2(self, n):
        if self._compress_left <= 0:
            return b''

        n = max(n, self.MIN_READ_SIZE)
        n = min(n, self._compress_left)

        data = self._fileobj.read(n)
        self._compress_left -= len(data)
        if not data:
            raise EOFError

        if self._decrypter is not None:
            data = bytes(map(self._decrypter, data))
        return data

    def close(self):
        try:
            if self._close_fileobj:
                self._fileobj.close()
        finally:
            super().close()


class ZipFile:
    """ Class with methods to open, read, write, close, list zip files.

    z = ZipFile(file, mode="r", compression=ZIP_STORED, allowZip64=True)

    file: Either the path to the file, or a file-like object.
          If it is a path, the file will be opened and closed by ZipFile.
    mode: The mode can be either read "r", write "w" or append "a".
    compression: ZIP_STORED (no compression), ZIP_DEFLATED (requires zlib),
                 ZIP_BZIP2 (requires bz2) or ZIP_LZMA (requires lzma).
    allowZip64: if True ZipFile will create files with ZIP64 extensions when
                needed, otherwise it will raise an exception when this would
                be necessary.

    """

    fp = None                   # Set here since __del__ checks it
    _windows_illegal_name_trans_table = None

    def __init__(self, file, mode="r", compression=ZIP_STORED, allowZip64=True):
        """Open the ZIP file with mode read "r", write "w" or append "a"."""
        if mode not in ("r", "w", "a"):
            raise RuntimeError('ZipFile() requires mode "r", "w", or "a"')

        _check_compression(compression)

        self._allowZip64 = allowZip64
        self._didModify = False
        self.debug = 0  # Level of printing: 0 through 3
        self.NameToInfo = {}    # Find file info given name
        self.filelist = []      # List of ZipInfo instances for archive
        self.compression = compression  # Method of compression
        self.mode = key = mode.replace('b', '')[0]
        self.pwd = None
        self._comment = b''

        # Check if we were passed a file-like object
        if isinstance(file, str):
            # No, it's a filename
            self._filePassed = 0
            self.filename = file
            modeDict = {'r' : 'rb', 'w': 'wb', 'a' : 'r+b'}
            try:
                self.fp = io.open(file, modeDict[mode])
            except OSError:
                if mode == 'a':
                    mode = key = 'w'
                    self.fp = io.open(file, modeDict[mode])
                else:
                    raise
        else:
            self._filePassed = 1
            self.fp = file
            self.filename = getattr(file, 'name', None)

        try:
            if key == 'r':
                self._RealGetContents()
            elif key == 'w':
                # set the modified flag so central directory gets written
                # even if no files are added to the archive
                self._didModify = True
            elif key == 'a':
                try:
                    # See if file is a zip file
                    self._RealGetContents()
                    # seek to start of directory and overwrite
                    self.fp.seek(self.start_dir, 0)
                except BadZipFile:
                    # file is not a zip file, just append
                    self.fp.seek(0, 2)

                    # set the modified flag so central directory gets written
                    # even if no files are added to the archive
                    self._didModify = True
            else:
                raise RuntimeError('Mode must be "r", "w" or "a"')
        except:
            fp = self.fp
            self.fp = None
            if not self._filePassed:
                fp.close()
            raise

    def __enter__(self):
        return self

    def __exit__(self, type, value, traceback):
        self.close()

    def _RealGetContents(self):
        """Read in the table of contents for the ZIP file."""
        fp = self.fp
        try:
            endrec = _EndRecData(fp)
        except OSError:
            raise BadZipFile("File is not a zip file")
        if not endrec:
            raise BadZipFile("File is not a zip file")
        if self.debug > 1:
            print(endrec)
        size_cd = endrec[_ECD_SIZE]             # bytes in central directory
        offset_cd = endrec[_ECD_OFFSET]         # offset of central directory
        self._comment = endrec[_ECD_COMMENT]    # archive comment

        # "concat" is zero, unless zip was concatenated to another file
        concat = endrec[_ECD_LOCATION] - size_cd - offset_cd
        if endrec[_ECD_SIGNATURE] == stringEndArchive64:
            # If Zip64 extension structures are present, account for them
            concat -= (sizeEndCentDir64 + sizeEndCentDir64Locator)

        if self.debug > 2:
            inferred = concat + offset_cd
            print("given, inferred, offset", offset_cd, inferred, concat)
        # self.start_dir:  Position of start of central directory
        self.start_dir = offset_cd + concat
        fp.seek(self.start_dir, 0)
        data = fp.read(size_cd)
        fp = io.BytesIO(data)
        total = 0
        while total < size_cd:
            centdir = fp.read(sizeCentralDir)
            if len(centdir) != sizeCentralDir:
                raise BadZipFile("Truncated central directory")
            centdir = struct.unpack(structCentralDir, centdir)
            if centdir[_CD_SIGNATURE] != stringCentralDir:
                raise BadZipFile("Bad magic number for central directory")
            if self.debug > 2:
                print(centdir)
            filename = fp.read(centdir[_CD_FILENAME_LENGTH])
            flags = centdir[5]
            if flags & 0x800:
                # UTF-8 file names extension
                filename = filename.decode('utf-8')
            else:
                # Historical ZIP filename encoding
                filename = filename.decode('cp437')
            # Create ZipInfo instance to store file information
            x = ZipInfo(filename)
            x.extra = fp.read(centdir[_CD_EXTRA_FIELD_LENGTH])
            x.comment = fp.read(centdir[_CD_COMMENT_LENGTH])
            x.header_offset = centdir[_CD_LOCAL_HEADER_OFFSET]
            (x.create_version, x.create_system, x.extract_version, x.reserved,
             x.flag_bits, x.compress_type, t, d,
             x.CRC, x.compress_size, x.file_size) = centdir[1:12]
            if x.extract_version > MAX_EXTRACT_VERSION:
                raise NotImplementedError("zip file version %.1f" %
                                          (x.extract_version / 10))
            x.volume, x.internal_attr, x.external_attr = centdir[15:18]
            # Convert date/time code to (year, month, day, hour, min, sec)
            x._raw_time = t
            x.date_time = ( (d>>9)+1980, (d>>5)&0xF, d&0x1F,
                            t>>11, (t>>5)&0x3F, (t&0x1F) * 2 )

            x._decodeExtra()
            x.header_offset = x.header_offset + concat
            self.filelist.append(x)
            self.NameToInfo[x.filename] = x

            # update total bytes read from central directory
            total = (total + sizeCentralDir + centdir[_CD_FILENAME_LENGTH]
                     + centdir[_CD_EXTRA_FIELD_LENGTH]
                     + centdir[_CD_COMMENT_LENGTH])

            if self.debug > 2:
                print("total", total)


    def namelist(self):
        """Return a list of file names in the archive."""
        return [data.filename for data in self.filelist]

    def infolist(self):
        """Return a list of class ZipInfo instances for files in the
        archive."""
        return self.filelist

    def printdir(self, file=None):
        """Print a table of contents for the zip file."""
        print("%-46s %19s %12s" % ("File Name", "Modified    ", "Size"),
              file=file)
        for zinfo in self.filelist:
            date = "%d-%02d-%02d %02d:%02d:%02d" % zinfo.date_time[:6]
            print("%-46s %s %12d" % (zinfo.filename, date, zinfo.file_size),
                  file=file)

    def testzip(self):
        """Read all the files and check the CRC."""
        chunk_size = 2 ** 20
        for zinfo in self.filelist:
            try:
                # Read by chunks, to avoid an OverflowError or a
                # MemoryError with very large embedded files.
                with self.open(zinfo.filename, "r") as f:
                    while f.read(chunk_size):     # Check CRC-32
                        pass
            except BadZipFile:
                return zinfo.filename

    def getinfo(self, name):
        """Return the instance of ZipInfo given 'name'."""
        info = self.NameToInfo.get(name)
        if info is None:
            raise KeyError(
                'There is no item named %r in the archive' % name)

        return info

    def setpassword(self, pwd):
        """Set default password for encrypted files."""
        if pwd and not isinstance(pwd, bytes):
            raise TypeError("pwd: expected bytes, got %s" % type(pwd))
        if pwd:
            self.pwd = pwd
        else:
            self.pwd = None

    @property
    def comment(self):
        """The comment text associated with the ZIP file."""
        return self._comment

    @comment.setter
    def comment(self, comment):
        if not isinstance(comment, bytes):
            raise TypeError("comment: expected bytes, got %s" % type(comment))
        # check for valid comment length
        if len(comment) > ZIP_MAX_COMMENT:
            import warnings
            warnings.warn('Archive comment is too long; truncating to %d bytes'
                          % ZIP_MAX_COMMENT, stacklevel=2)
            comment = comment[:ZIP_MAX_COMMENT]
        self._comment = comment
        self._didModify = True

    def read(self, name, pwd=None):
        """Return file bytes (as a string) for name."""
        with self.open(name, "r", pwd) as fp:
            return fp.read()

    def open(self, name, mode="r", pwd=None):
        """Return file-like object for 'name'."""
        if mode not in ("r", "U", "rU"):
            raise RuntimeError('open() requires mode "r", "U", or "rU"')
        if 'U' in mode:
            import warnings
            warnings.warn("'U' mode is deprecated",
                          DeprecationWarning, 2)
        if pwd and not isinstance(pwd, bytes):
            raise TypeError("pwd: expected bytes, got %s" % type(pwd))
        if not self.fp:
            raise RuntimeError(
                "Attempt to read ZIP archive that was already closed")

        # Only open a new file for instances where we were not
        # given a file object in the constructor
        if self._filePassed:
            zef_file = self.fp
        else:
            zef_file = io.open(self.filename, 'rb')

        try:
            # Make sure we have an info object
            if isinstance(name, ZipInfo):
                # 'name' is already an info object
                zinfo = name
            else:
                # Get info object for name
                zinfo = self.getinfo(name)
            zef_file.seek(zinfo.header_offset, 0)

            # Skip the file header:
            fheader = zef_file.read(sizeFileHeader)
            if len(fheader) != sizeFileHeader:
                raise BadZipFile("Truncated file header")
            fheader = struct.unpack(structFileHeader, fheader)
            if fheader[_FH_SIGNATURE] != stringFileHeader:
                raise BadZipFile("Bad magic number for file header")

            fname = zef_file.read(fheader[_FH_FILENAME_LENGTH])
            if fheader[_FH_EXTRA_FIELD_LENGTH]:
                zef_file.read(fheader[_FH_EXTRA_FIELD_LENGTH])

            if zinfo.flag_bits & 0x20:
                # Zip 2.7: compressed patched data
                raise NotImplementedError("compressed patched data (flag bit 5)")

            if zinfo.flag_bits & 0x40:
                # strong encryption
                raise NotImplementedError("strong encryption (flag bit 6)")

            if zinfo.flag_bits & 0x800:
                # UTF-8 filename
                fname_str = fname.decode("utf-8")
            else:
                fname_str = fname.decode("cp437")

            if fname_str != zinfo.orig_filename:
                raise BadZipFile(
                    'File name in directory %r and header %r differ.'
                    % (zinfo.orig_filename, fname))

            # check for encrypted flag & handle password
            is_encrypted = zinfo.flag_bits & 0x1
            zd = None
            if is_encrypted:
                if not pwd:
                    pwd = self.pwd
                if not pwd:
                    raise RuntimeError("File %s is encrypted, password "
                                       "required for extraction" % name)

                zd = _ZipDecrypter(pwd)
                # The first 12 bytes in the cypher stream is an encryption header
                #  used to strengthen the algorithm. The first 11 bytes are
                #  completely random, while the 12th contains the MSB of the CRC,
                #  or the MSB of the file time depending on the header type
                #  and is used to check the correctness of the password.
                header = zef_file.read(12)
                h = list(map(zd, header[0:12]))
                if zinfo.flag_bits & 0x8:
                    # compare against the file type from extended local headers
                    check_byte = (zinfo._raw_time >> 8) & 0xff
                else:
                    # compare against the CRC otherwise
                    check_byte = (zinfo.CRC >> 24) & 0xff
                if h[11] != check_byte:
                    raise RuntimeError("Bad password for file", name)

            return ZipExtFile(zef_file, mode, zinfo, zd,
                              close_fileobj=not self._filePassed)
        except:
            if not self._filePassed:
                zef_file.close()
            raise

    def extract(self, member, path=None, pwd=None):
        """Extract a member from the archive to the current working directory,
           using its full name. Its file information is extracted as accurately
           as possible. `member' may be a filename or a ZipInfo object. You can
           specify a different directory using `path'.
        """
        if not isinstance(member, ZipInfo):
            member = self.getinfo(member)

        if path is None:
            path = os.getcwd()

        return self._extract_member(member, path, pwd)

    def extractall(self, path=None, members=None, pwd=None):
        """Extract all members from the archive to the current working
           directory. `path' specifies a different directory to extract to.
           `members' is optional and must be a subset of the list returned
           by namelist().
        """
        if members is None:
            members = self.namelist()

        for zipinfo in members:
            self.extract(zipinfo, path, pwd)

    @classmethod
    def _sanitize_windows_name(cls, arcname, pathsep):
        """Replace bad characters and remove trailing dots from parts."""
        table = cls._windows_illegal_name_trans_table
        if not table:
            illegal = ':<>|"?*'
            table = str.maketrans(illegal, '_' * len(illegal))
            cls._windows_illegal_name_trans_table = table
        arcname = arcname.translate(table)
        # remove trailing dots
        arcname = (x.rstrip('.') for x in arcname.split(pathsep))
        # rejoin, removing empty parts.
        arcname = pathsep.join(x for x in arcname if x)
        return arcname

    def _extract_member(self, member, targetpath, pwd):
        """Extract the ZipInfo object 'member' to a physical
           file on the path targetpath.
        """
        # build the destination pathname, replacing
        # forward slashes to platform specific separators.
        arcname = member.filename.replace('/', os.path.sep)

        if os.path.altsep:
            arcname = arcname.replace(os.path.altsep, os.path.sep)
        # interpret absolute pathname as relative, remove drive letter or
        # UNC path, redundant separators, "." and ".." components.
        arcname = os.path.splitdrive(arcname)[1]
        invalid_path_parts = ('', os.path.curdir, os.path.pardir)
        arcname = os.path.sep.join(x for x in arcname.split(os.path.sep)
                                   if x not in invalid_path_parts)
        if os.path.sep == '\\':
            # filter illegal characters on Windows
            arcname = self._sanitize_windows_name(arcname, os.path.sep)

        targetpath = os.path.join(targetpath, arcname)
        targetpath = os.path.normpath(targetpath)

        # Create all upper directories if necessary.
        upperdirs = os.path.dirname(targetpath)
        if upperdirs and not os.path.exists(upperdirs):
            os.makedirs(upperdirs)

        if member.filename[-1] == '/':
            if not os.path.isdir(targetpath):
                os.mkdir(targetpath)
            return targetpath

        with self.open(member, pwd=pwd) as source, \
             open(targetpath, "wb") as target:
            shutil.copyfileobj(source, target)

        return targetpath

    def _writecheck(self, zinfo):
        """Check for errors before writing a file to the archive."""
        if zinfo.filename in self.NameToInfo:
            import warnings
            warnings.warn('Duplicate name: %r' % zinfo.filename, stacklevel=3)
        if self.mode not in ("w", "a"):
            raise RuntimeError('write() requires mode "w" or "a"')
        if not self.fp:
            raise RuntimeError(
                "Attempt to write ZIP archive that was already closed")
        _check_compression(zinfo.compress_type)
        if not self._allowZip64:
            requires_zip64 = None
            if len(self.filelist) >= ZIP_FILECOUNT_LIMIT:
                requires_zip64 = "Files count"
            elif zinfo.file_size > ZIP64_LIMIT:
                requires_zip64 = "Filesize"
            elif zinfo.header_offset > ZIP64_LIMIT:
                requires_zip64 = "Zipfile size"
            if requires_zip64:
                raise LargeZipFile(requires_zip64 +
                                   " would require ZIP64 extensions")

    def write(self, filename, arcname=None, compress_type=None):
        """Put the bytes from filename into the archive under the name
        arcname."""
        if not self.fp:
            raise RuntimeError(
                "Attempt to write to ZIP archive that was already closed")

        st = os.stat(filename)
        isdir = stat.S_ISDIR(st.st_mode)
        mtime = time.localtime(st.st_mtime)
        date_time = mtime[0:6]
        # Create ZipInfo instance to store file information
        if arcname is None:
            arcname = filename
        arcname = os.path.normpath(os.path.splitdrive(arcname)[1])
        while arcname[0] in (os.sep, os.altsep):
            arcname = arcname[1:]
        if isdir:
            arcname += '/'
        zinfo = ZipInfo(arcname, date_time)
        zinfo.external_attr = (st[0] & 0xFFFF) << 16      # Unix attributes
        if compress_type is None:
            zinfo.compress_type = self.compression
        else:
            zinfo.compress_type = compress_type

        zinfo.file_size = st.st_size
        zinfo.flag_bits = 0x00
        zinfo.header_offset = self.fp.tell()    # Start of header bytes
        if zinfo.compress_type == ZIP_LZMA:
            # Compressed data includes an end-of-stream (EOS) marker
            zinfo.flag_bits |= 0x02

        self._writecheck(zinfo)
        self._didModify = True

        if isdir:
            zinfo.file_size = 0
            zinfo.compress_size = 0
            zinfo.CRC = 0
            zinfo.external_attr |= 0x10  # MS-DOS directory flag
            self.filelist.append(zinfo)
            self.NameToInfo[zinfo.filename] = zinfo
            self.fp.write(zinfo.FileHeader(False))
            return

        cmpr = _get_compressor(zinfo.compress_type)
        with open(filename, "rb") as fp:
            # Must overwrite CRC and sizes with correct data later
            zinfo.CRC = CRC = 0
            zinfo.compress_size = compress_size = 0
            # Compressed size can be larger than uncompressed size
            zip64 = self._allowZip64 and \
                zinfo.file_size * 1.05 > ZIP64_LIMIT
            self.fp.write(zinfo.FileHeader(zip64))
            file_size = 0
            while 1:
                buf = fp.read(1024 * 8)
                if not buf:
                    break
                file_size = file_size + len(buf)
                CRC = crc32(buf, CRC) & 0xffffffff
                if cmpr:
                    buf = cmpr.compress(buf)
                    compress_size = compress_size + len(buf)
                self.fp.write(buf)
        if cmpr:
            buf = cmpr.flush()
            compress_size = compress_size + len(buf)
            self.fp.write(buf)
            zinfo.compress_size = compress_size
        else:
            zinfo.compress_size = file_size
        zinfo.CRC = CRC
        zinfo.file_size = file_size
        if not zip64 and self._allowZip64:
            if file_size > ZIP64_LIMIT:
                raise RuntimeError('File size has increased during compressing')
            if compress_size > ZIP64_LIMIT:
                raise RuntimeError('Compressed size larger than uncompressed size')
        # Seek backwards and write file header (which will now include
        # correct CRC and file sizes)
        position = self.fp.tell()       # Preserve current position in file
        self.fp.seek(zinfo.header_offset, 0)
        self.fp.write(zinfo.FileHeader(zip64))
        self.fp.seek(position, 0)
        self.filelist.append(zinfo)
        self.NameToInfo[zinfo.filename] = zinfo

    def writestr(self, zinfo_or_arcname, data, compress_type=None):
        """Write a file into the archive.  The contents is 'data', which
        may be either a 'str' or a 'bytes' instance; if it is a 'str',
        it is encoded as UTF-8 first.
        'zinfo_or_arcname' is either a ZipInfo instance or
        the name of the file in the archive."""
        if isinstance(data, str):
            data = data.encode("utf-8")
        if not isinstance(zinfo_or_arcname, ZipInfo):
            zinfo = ZipInfo(filename=zinfo_or_arcname,
                            date_time=time.localtime(time.time())[:6])
            zinfo.compress_type = self.compression
            if zinfo.filename[-1] == '/':
                zinfo.external_attr = 0o40775 << 16   # drwxrwxr-x
                zinfo.external_attr |= 0x10           # MS-DOS directory flag
            else:
                zinfo.external_attr = 0o600 << 16     # ?rw-------
        else:
            zinfo = zinfo_or_arcname

        if not self.fp:
            raise RuntimeError(
                "Attempt to write to ZIP archive that was already closed")

        zinfo.file_size = len(data)            # Uncompressed size
        zinfo.header_offset = self.fp.tell()    # Start of header data
        if compress_type is not None:
            zinfo.compress_type = compress_type
        if zinfo.compress_type == ZIP_LZMA:
            # Compressed data includes an end-of-stream (EOS) marker
            zinfo.flag_bits |= 0x02

        self._writecheck(zinfo)
        self._didModify = True
        zinfo.CRC = crc32(data) & 0xffffffff       # CRC-32 checksum
        co = _get_compressor(zinfo.compress_type)
        if co:
            data = co.compress(data) + co.flush()
            zinfo.compress_size = len(data)    # Compressed size
        else:
            zinfo.compress_size = zinfo.file_size
        zip64 = zinfo.file_size > ZIP64_LIMIT or \
            zinfo.compress_size > ZIP64_LIMIT
        if zip64 and not self._allowZip64:
            raise LargeZipFile("Filesize would require ZIP64 extensions")
        self.fp.write(zinfo.FileHeader(zip64))
        self.fp.write(data)
        if zinfo.flag_bits & 0x08:
            # Write CRC and file sizes after the file data
            fmt = '<LQQ' if zip64 else '<LLL'
            self.fp.write(struct.pack(fmt, zinfo.CRC, zinfo.compress_size,
                                      zinfo.file_size))
        self.fp.flush()
        self.filelist.append(zinfo)
        self.NameToInfo[zinfo.filename] = zinfo

    def __del__(self):
        """Call the "close()" method in case the user forgot."""
        self.close()

    def close(self):
        """Close the file, and for mode "w" and "a" write the ending
        records."""
        if self.fp is None:
            return

        try:
            if self.mode in ("w", "a") and self._didModify: # write ending records
                pos1 = self.fp.tell()
                for zinfo in self.filelist:         # write central directory
                    dt = zinfo.date_time
                    dosdate = (dt[0] - 1980) << 9 | dt[1] << 5 | dt[2]
                    dostime = dt[3] << 11 | dt[4] << 5 | (dt[5] // 2)
                    extra = []
                    if zinfo.file_size > ZIP64_LIMIT \
                       or zinfo.compress_size > ZIP64_LIMIT:
                        extra.append(zinfo.file_size)
                        extra.append(zinfo.compress_size)
                        file_size = 0xffffffff
                        compress_size = 0xffffffff
                    else:
                        file_size = zinfo.file_size
                        compress_size = zinfo.compress_size

                    if zinfo.header_offset > ZIP64_LIMIT:
                        extra.append(zinfo.header_offset)
                        header_offset = 0xffffffff
                    else:
                        header_offset = zinfo.header_offset

                    extra_data = zinfo.extra
                    min_version = 0
                    if extra:
                        # Append a ZIP64 field to the extra's
                        extra_data = struct.pack(
                            '<HH' + 'Q'*len(extra),
                            1, 8*len(extra), *extra) + extra_data

                        min_version = ZIP64_VERSION

                    if zinfo.compress_type == ZIP_BZIP2:
                        min_version = max(BZIP2_VERSION, min_version)
                    elif zinfo.compress_type == ZIP_LZMA:
                        min_version = max(LZMA_VERSION, min_version)

                    extract_version = max(min_version, zinfo.extract_version)
                    create_version = max(min_version, zinfo.create_version)
                    try:
                        filename, flag_bits = zinfo._encodeFilenameFlags()
                        centdir = struct.pack(structCentralDir,
                                              stringCentralDir, create_version,
                                              zinfo.create_system, extract_version, zinfo.reserved,
                                              flag_bits, zinfo.compress_type, dostime, dosdate,
                                              zinfo.CRC, compress_size, file_size,
                                              len(filename), len(extra_data), len(zinfo.comment),
                                              0, zinfo.internal_attr, zinfo.external_attr,
                                              header_offset)
                    except DeprecationWarning:
                        print((structCentralDir, stringCentralDir, create_version,
                               zinfo.create_system, extract_version, zinfo.reserved,
                               zinfo.flag_bits, zinfo.compress_type, dostime, dosdate,
                               zinfo.CRC, compress_size, file_size,
                               len(zinfo.filename), len(extra_data), len(zinfo.comment),
                               0, zinfo.internal_attr, zinfo.external_attr,
                               header_offset), file=sys.stderr)
                        raise
                    self.fp.write(centdir)
                    self.fp.write(filename)
                    self.fp.write(extra_data)
                    self.fp.write(zinfo.comment)

                pos2 = self.fp.tell()
                # Write end-of-zip-archive record
                centDirCount = len(self.filelist)
                centDirSize = pos2 - pos1
                centDirOffset = pos1
                requires_zip64 = None
                if centDirCount > ZIP_FILECOUNT_LIMIT:
                    requires_zip64 = "Files count"
                elif centDirOffset > ZIP64_LIMIT:
                    requires_zip64 = "Central directory offset"
                elif centDirSize > ZIP64_LIMIT:
                    requires_zip64 = "Central directory size"
                if requires_zip64:
                    # Need to write the ZIP64 end-of-archive records
                    if not self._allowZip64:
                        raise LargeZipFile(requires_zip64 +
                                           " would require ZIP64 extensions")
                    zip64endrec = struct.pack(
                        structEndArchive64, stringEndArchive64,
                        44, 45, 45, 0, 0, centDirCount, centDirCount,
                        centDirSize, centDirOffset)
                    self.fp.write(zip64endrec)

                    zip64locrec = struct.pack(
                        structEndArchive64Locator,
                        stringEndArchive64Locator, 0, pos2, 1)
                    self.fp.write(zip64locrec)
                    centDirCount = min(centDirCount, 0xFFFF)
                    centDirSize = min(centDirSize, 0xFFFFFFFF)
                    centDirOffset = min(centDirOffset, 0xFFFFFFFF)

                endrec = struct.pack(structEndArchive, stringEndArchive,
                                     0, 0, centDirCount, centDirCount,
                                     centDirSize, centDirOffset, len(self._comment))
                self.fp.write(endrec)
                self.fp.write(self._comment)
                self.fp.flush()
        finally:
            fp = self.fp
            self.fp = None
            if not self._filePassed:
                fp.close()


class PyZipFile(ZipFile):
    """Class to create ZIP archives with Python library files and packages."""

    def __init__(self, file, mode="r", compression=ZIP_STORED,
                 allowZip64=True, optimize=-1):
        ZipFile.__init__(self, file, mode=mode, compression=compression,
                         allowZip64=allowZip64)
        self._optimize = optimize

    def writepy(self, pathname, basename="", filterfunc=None):
        """Add all files from "pathname" to the ZIP archive.

        If pathname is a package directory, search the directory and
        all package subdirectories recursively for all *.py and enter
        the modules into the archive.  If pathname is a plain
        directory, listdir *.py and enter all modules.  Else, pathname
        must be a Python *.py file and the module will be put into the
        archive.  Added modules are always module.pyo or module.pyc.
        This method will compile the module.py into module.pyc if
        necessary.
        If filterfunc(pathname) is given, it is called with every argument.
        When it is False, the file or directory is skipped.
        """
        if filterfunc and not filterfunc(pathname):
            if self.debug:
                label = 'path' if os.path.isdir(pathname) else 'file'
                print('%s "%s" skipped by filterfunc' % (label, pathname))
            return
        dir, name = os.path.split(pathname)
        if os.path.isdir(pathname):
            initname = os.path.join(pathname, "__init__.py")
            if os.path.isfile(initname):
                # This is a package directory, add it
                if basename:
                    basename = "%s/%s" % (basename, name)
                else:
                    basename = name
                if self.debug:
                    print("Adding package in", pathname, "as", basename)
                fname, arcname = self._get_codename(initname[0:-3], basename)
                if self.debug:
                    print("Adding", arcname)
                self.write(fname, arcname)
                dirlist = os.listdir(pathname)
                dirlist.remove("__init__.py")
                # Add all *.py files and package subdirectories
                for filename in dirlist:
                    path = os.path.join(pathname, filename)
                    root, ext = os.path.splitext(filename)
                    if os.path.isdir(path):
                        if os.path.isfile(os.path.join(path, "__init__.py")):
                            # This is a package directory, add it
                            self.writepy(path, basename,
                                         filterfunc=filterfunc)  # Recursive call
                    elif ext == ".py":
                        if filterfunc and not filterfunc(path):
                            if self.debug:
                                print('file "%s" skipped by filterfunc' % path)
                            continue
                        fname, arcname = self._get_codename(path[0:-3],
                                                            basename)
                        if self.debug:
                            print("Adding", arcname)
                        self.write(fname, arcname)
            else:
                # This is NOT a package directory, add its files at top level
                if self.debug:
                    print("Adding files from directory", pathname)
                for filename in os.listdir(pathname):
                    path = os.path.join(pathname, filename)
                    root, ext = os.path.splitext(filename)
                    if ext == ".py":
                        if filterfunc and not filterfunc(path):
                            if self.debug:
                                print('file "%s" skipped by filterfunc' % path)
                            continue
                        fname, arcname = self._get_codename(path[0:-3],
                                                            basename)
                        if self.debug:
                            print("Adding", arcname)
                        self.write(fname, arcname)
        else:
            if pathname[-3:] != ".py":
                raise RuntimeError(
                    'Files added with writepy() must end with ".py"')
            fname, arcname = self._get_codename(pathname[0:-3], basename)
            if self.debug:
                print("Adding file", arcname)
            self.write(fname, arcname)

    def _get_codename(self, pathname, basename):
        """Return (filename, archivename) for the path.

        Given a module name path, return the correct file path and
        archive name, compiling if necessary.  For example, given
        /python/lib/string, return (/python/lib/string.pyc, string).
        """
        def _compile(file, optimize=-1):
            import py_compile
            if self.debug:
                print("Compiling", file)
            try:
                py_compile.compile(file, doraise=True, optimize=optimize)
            except py_compile.PyCompileError as err:
                print(err.msg)
                return False
            return True

        file_py  = pathname + ".py"
        file_pyc = pathname + ".pyc"
        file_pyo = pathname + ".pyo"
        pycache_pyc = importlib.util.cache_from_source(file_py, True)
        pycache_pyo = importlib.util.cache_from_source(file_py, False)
        if self._optimize == -1:
            # legacy mode: use whatever file is present
            if (os.path.isfile(file_pyo) and
                os.stat(file_pyo).st_mtime >= os.stat(file_py).st_mtime):
                # Use .pyo file.
                arcname = fname = file_pyo
            elif (os.path.isfile(file_pyc) and
                  os.stat(file_pyc).st_mtime >= os.stat(file_py).st_mtime):
                # Use .pyc file.
                arcname = fname = file_pyc
            elif (os.path.isfile(pycache_pyc) and
                  os.stat(pycache_pyc).st_mtime >= os.stat(file_py).st_mtime):
                # Use the __pycache__/*.pyc file, but write it to the legacy pyc
                # file name in the archive.
                fname = pycache_pyc
                arcname = file_pyc
            elif (os.path.isfile(pycache_pyo) and
                  os.stat(pycache_pyo).st_mtime >= os.stat(file_py).st_mtime):
                # Use the __pycache__/*.pyo file, but write it to the legacy pyo
                # file name in the archive.
                fname = pycache_pyo
                arcname = file_pyo
            else:
                # Compile py into PEP 3147 pyc file.
                if _compile(file_py):
                    fname = (pycache_pyc if __debug__ else pycache_pyo)
                    arcname = (file_pyc if __debug__ else file_pyo)
                else:
                    fname = arcname = file_py
        else:
            # new mode: use given optimization level
            if self._optimize == 0:
                fname = pycache_pyc
                arcname = file_pyc
            else:
                fname = pycache_pyo
                arcname = file_pyo
            if not (os.path.isfile(fname) and
                    os.stat(fname).st_mtime >= os.stat(file_py).st_mtime):
                if not _compile(file_py, optimize=self._optimize):
                    fname = arcname = file_py
        archivename = os.path.split(arcname)[1]
        if basename:
            archivename = "%s/%s" % (basename, archivename)
        return (fname, archivename)


def main(args = None):
    import textwrap
    USAGE=textwrap.dedent("""\
        Usage:
            zipfile.py -l zipfile.zip        # Show listing of a zipfile
            zipfile.py -t zipfile.zip        # Test if a zipfile is valid
            zipfile.py -e zipfile.zip target # Extract zipfile into target dir
            zipfile.py -c zipfile.zip src ... # Create zipfile from sources
        """)
    if args is None:
        args = sys.argv[1:]

    if not args or args[0] not in ('-l', '-c', '-e', '-t'):
        print(USAGE)
        sys.exit(1)

    if args[0] == '-l':
        if len(args) != 2:
            print(USAGE)
            sys.exit(1)
        with ZipFile(args[1], 'r') as zf:
            zf.printdir()

    elif args[0] == '-t':
        if len(args) != 2:
            print(USAGE)
            sys.exit(1)
        with ZipFile(args[1], 'r') as zf:
            badfile = zf.testzip()
        if badfile:
            print("The following enclosed file is corrupted: {!r}".format(badfile))
        print("Done testing")

    elif args[0] == '-e':
        if len(args) != 3:
            print(USAGE)
            sys.exit(1)

        with ZipFile(args[1], 'r') as zf:
            zf.extractall(args[2])

    elif args[0] == '-c':
        if len(args) < 3:
            print(USAGE)
            sys.exit(1)

        def addToZip(zf, path, zippath):
            if os.path.isfile(path):
                zf.write(path, zippath, ZIP_DEFLATED)
            elif os.path.isdir(path):
                if zippath:
                    zf.write(path, zippath)
                for nm in os.listdir(path):
                    addToZip(zf,
                             os.path.join(path, nm), os.path.join(zippath, nm))
            # else: ignore

        with ZipFile(args[1], 'w') as zf:
            for path in args[2:]:
                zippath = os.path.basename(path)
                if not zippath:
                    zippath = os.path.basename(os.path.dirname(path))
                if zippath in ('', os.curdir, os.pardir):
                    zippath = ''
                addToZip(zf, path, zippath)

if __name__ == "__main__":
    main()