This repository was archived by the owner on Apr 19, 2021. It is now read-only.
forked from EFForg/https-everywhere
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathzipfile_deterministic.py
More file actions
1444 lines (1251 loc) · 53.5 KB
/
zipfile_deterministic.py
File metadata and controls
1444 lines (1251 loc) · 53.5 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#!/usr/bin/env python2.7
"""
A fork of the Zipfile module to read and write ZIP files from Python 2.6.
This module aims to create deterministic, byte-for-byte identical zip files.
Author: Yan Zhu, yan@mit.edu
Derived from Python 2.6, Copyright (c) 2001, 2002, 2003, 2004, 2005, 2006
Python Software Foundation; All Rights Reserved, License at
http://www.python.org/download/releases/2.6/license/
"""
import struct, os, time, sys, shutil
import binascii, cStringIO, stat
import unicodedata
try:
import zlib # We may need its compression method
crc32 = zlib.crc32
except ImportError:
zlib = None
crc32 = binascii.crc32
__all__ = ["BadZipfile", "error", "ZIP_STORED", "ZIP_DEFLATED", "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 # The exception raised by this module
ZIP64_LIMIT = (1 << 31) - 1
ZIP_FILECOUNT_LIMIT = 1 << 16
ZIP_MAX_COMMENT = (1 << 16) - 1
# constants for Zip file compression methods
ZIP_STORED = 0
ZIP_DEFLATED = 8
# Other ZIP compression methods not supported
DEFAULT_DATE = (1980,1,1,0,0,0) # hard-coded timestamp
# 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 = "<4s4H2LH"
stringEndArchive = "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 = "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 = "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 = "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 = "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 normalize_unicode(filename):
"""For dealing with different unicode normalizations in filenames."""
return unicodedata.normalize('NFC', unicode(filename, 'utf-8')).encode('utf-8')
def standardize_filename(filename):
"""Get OS-independent form of filename"""
# 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, "/")
return normalize_unicode(filename)
def is_zipfile(filename):
"""Quickly see if file is a ZIP file by checking the magic number."""
try:
fpin = open(filename, "rb")
endrec = _EndRecData(fpin)
fpin.close()
if endrec:
return True # file has correct magic number
except IOError:
pass
return False
def _EndRecData64(fpin, offset, endrec):
"""
Read the ZIP64 end-of-archive records and use that to update endrec
"""
fpin.seek(offset - sizeEndCentDir64Locator, 2)
data = fpin.read(sizeEndCentDir64Locator)
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)
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 IOError:
return None
data = fpin.read()
if data[0:4] == stringEndArchive and data[-2:] == "\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("")
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]
endrec = list(struct.unpack(structEndArchive, recData))
comment = data[start+sizeEndCentDir:]
# check that comment length is correct
if endrec[_ECD_COMMENT_SIZE] == len(comment):
# Append the archive comment and start offset
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
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=DEFAULT_DATE):
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.
self.filename = standardize_filename(filename) # Normalized file name
self.date_time = date_time # year, month, day, hour, min, sec
# Standard values:
self.compress_type = ZIP_STORED # Type of compression for the file
self.comment = "" # Comment for each file
self.extra = "" # 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 = 20 # Version which created ZIP archive
self.extract_version = 20 # 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):
"""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
if file_size > ZIP64_LIMIT or compress_size > ZIP64_LIMIT:
# File is larger than what fits into a 4 byte integer,
# fall back to the ZIP64 extension
fmt = '<HHQQ'
extra = extra + struct.pack(fmt,
1, struct.calcsize(fmt)-4, file_size, compress_size)
file_size = 0xffffffff
compress_size = 0xffffffff
self.extract_version = max(45, self.extract_version)
self.create_version = max(45, self.extract_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):
if isinstance(self.filename, unicode):
try:
return self.filename.encode('ascii'), self.flag_bits
except UnicodeEncodeError:
return self.filename.encode('utf-8'), self.flag_bits | 0x800
else:
return self.filename, self.flag_bits
def _decodeFilename(self):
if self.flag_bits & 0x800:
return self.filename.decode('utf-8')
else:
return self.filename
def _decodeExtra(self):
# Try to decode the extra field.
extra = self.extra
unpack = struct.unpack
while extra:
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 (0xffffffffffffffffL, 0xffffffffL):
self.file_size = counts[idx]
idx += 1
if self.compress_size == 0xFFFFFFFFL:
self.compress_size = counts[idx]
idx += 1
if self.header_offset == 0xffffffffL:
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 = _GenerateCRCTable()
def _crc32(self, ch, crc):
"""Compute the CRC32 primitive on one byte."""
return ((crc >> 8) & 0xffffff) ^ self.crctable[(crc ^ ord(ch)) & 0xff]
def __init__(self, pwd):
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(chr((self.key1 >> 24) & 255), self.key2)
def __call__(self, c):
"""Decrypt a single character."""
c = ord(c)
k = self.key2 | 2
c = c ^ (((k * (k^1)) >> 8) & 255)
c = chr(c)
self._UpdateKeys(c)
return c
class ZipExtFile:
"""File-like object for reading an archive member.
Is returned by ZipFile.open().
"""
def __init__(self, fileobj, zipinfo, decrypt=None):
self.fileobj = fileobj
self.decrypter = decrypt
self.bytes_read = 0L
self.rawbuffer = ''
self.readbuffer = ''
self.linebuffer = ''
self.eof = False
self.univ_newlines = False
self.nlSeps = ("\n", )
self.lastdiscard = ''
self.compress_type = zipinfo.compress_type
self.compress_size = zipinfo.compress_size
self.closed = False
self.mode = "r"
self.name = zipinfo.filename
# read from compressed files in 64k blocks
self.compreadsize = 64*1024
if self.compress_type == ZIP_DEFLATED:
self.dc = zlib.decompressobj(-15)
def set_univ_newlines(self, univ_newlines):
self.univ_newlines = univ_newlines
# pick line separator char(s) based on universal newlines flag
self.nlSeps = ("\n", )
if self.univ_newlines:
self.nlSeps = ("\r\n", "\r", "\n")
def __iter__(self):
return self
def next(self):
nextline = self.readline()
if not nextline:
raise StopIteration()
return nextline
def close(self):
self.closed = True
def _checkfornewline(self):
nl, nllen = -1, -1
if self.linebuffer:
# ugly check for cases where half of an \r\n pair was
# read on the last pass, and the \r was discarded. In this
# case we just throw away the \n at the start of the buffer.
if (self.lastdiscard, self.linebuffer[0]) == ('\r','\n'):
self.linebuffer = self.linebuffer[1:]
for sep in self.nlSeps:
nl = self.linebuffer.find(sep)
if nl >= 0:
nllen = len(sep)
return nl, nllen
return nl, nllen
def readline(self, size = -1):
"""Read a line with approx. size. If size is negative,
read a whole line.
"""
if size < 0:
size = 2147483647
elif size == 0:
return ''
# check for a newline already in buffer
nl, nllen = self._checkfornewline()
if nl >= 0:
# the next line was already in the buffer
nl = min(nl, size)
else:
# no line break in buffer - try to read more
size -= len(self.linebuffer)
while nl < 0 and size > 0:
buf = self.read(min(size, 100))
if not buf:
break
self.linebuffer += buf
size -= len(buf)
# check for a newline in buffer
nl, nllen = self._checkfornewline()
# we either ran out of bytes in the file, or
# met the specified size limit without finding a newline,
# so return current buffer
if nl < 0:
s = self.linebuffer
self.linebuffer = ''
return s
buf = self.linebuffer[:nl]
self.lastdiscard = self.linebuffer[nl:nl + nllen]
self.linebuffer = self.linebuffer[nl + nllen:]
# line is always returned with \n as newline char (except possibly
# for a final incomplete line in the file, which is handled above).
return buf + "\n"
def readlines(self, sizehint = -1):
"""Return a list with all (following) lines. The sizehint parameter
is ignored in this implementation.
"""
result = []
while True:
line = self.readline()
if not line: break
result.append(line)
return result
def read(self, size = None):
# act like file() obj and return empty string if size is 0
if size == 0:
return ''
# determine read size
bytesToRead = self.compress_size - self.bytes_read
# adjust read size for encrypted files since the first 12 bytes
# are for the encryption/password information
if self.decrypter is not None:
bytesToRead -= 12
if size is not None and size >= 0:
if self.compress_type == ZIP_STORED:
lr = len(self.readbuffer)
bytesToRead = min(bytesToRead, size - lr)
elif self.compress_type == ZIP_DEFLATED:
if len(self.readbuffer) > size:
# the user has requested fewer bytes than we've already
# pulled through the decompressor; don't read any more
bytesToRead = 0
else:
# user will use up the buffer, so read some more
lr = len(self.rawbuffer)
bytesToRead = min(bytesToRead, self.compreadsize - lr)
# avoid reading past end of file contents
if bytesToRead + self.bytes_read > self.compress_size:
bytesToRead = self.compress_size - self.bytes_read
# try to read from file (if necessary)
if bytesToRead > 0:
bytes = self.fileobj.read(bytesToRead)
self.bytes_read += len(bytes)
self.rawbuffer += bytes
# handle contents of raw buffer
if self.rawbuffer:
newdata = self.rawbuffer
self.rawbuffer = ''
# decrypt new data if we were given an object to handle that
if newdata and self.decrypter is not None:
newdata = ''.join(map(self.decrypter, newdata))
# decompress newly read data if necessary
if newdata and self.compress_type == ZIP_DEFLATED:
newdata = self.dc.decompress(newdata)
self.rawbuffer = self.dc.unconsumed_tail
if self.eof and len(self.rawbuffer) == 0:
# we're out of raw bytes (both from the file and
# the local buffer); flush just to make sure the
# decompressor is done
newdata += self.dc.flush()
# prevent decompressor from being used again
self.dc = None
self.readbuffer += newdata
# return what the user asked for
if size is None or len(self.readbuffer) <= size:
bytes = self.readbuffer
self.readbuffer = ''
else:
bytes = self.readbuffer[:size]
self.readbuffer = self.readbuffer[size:]
return bytes
class ZipFile:
""" Class with methods to open, read, write, close, list zip files.
z = ZipFile(file, mode="r", compression=ZIP_STORED, allowZip64=False)
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) or ZIP_DEFLATED (requires zlib).
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
def __init__(self, file, mode="r", compression=ZIP_STORED, allowZip64=False):
"""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"')
if compression == ZIP_STORED:
pass
elif compression == ZIP_DEFLATED:
if not zlib:
raise RuntimeError,\
"Compression requires the (missing) zlib module"
else:
raise RuntimeError, "That compression method is not supported"
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 = ''
# Check if we were passed a file-like object
if isinstance(file, basestring):
self._filePassed = 0
self.filename = file
modeDict = {'r' : 'rb', 'w': 'wb', 'a' : 'r+b'}
try:
self.fp = open(file, modeDict[mode])
except IOError:
if mode == 'a':
mode = key = 'w'
self.fp = open(file, modeDict[mode])
else:
raise
else:
self._filePassed = 1
self.fp = file
self.filename = getattr(file, 'name', None)
if key == 'r':
self._GetContents()
elif key == 'w':
pass
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)
else:
if not self._filePassed:
self.fp.close()
self.fp = None
raise RuntimeError, 'Mode must be "r", "w" or "a"'
def _GetContents(self):
"""Read the directory, making sure we close the file if the format
is bad."""
try:
self._RealGetContents()
except BadZipfile:
if not self._filePassed:
self.fp.close()
self.fp = None
raise
def _RealGetContents(self):
"""Read in the table of contents for the ZIP file."""
fp = self.fp
endrec = _EndRecData(fp)
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 = cStringIO.StringIO(data)
total = 0
while total < size_cd:
centdir = fp.read(sizeCentralDir)
if centdir[0:4] != stringCentralDir:
raise BadZipfile, "Bad magic number for central directory"
centdir = struct.unpack(structCentralDir, centdir)
if self.debug > 2:
print centdir
filename = fp.read(centdir[_CD_FILENAME_LENGTH])
# 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]
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
x.filename = x._decodeFilename()
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."""
l = []
for data in self.filelist:
l.append(data.filename)
return l
def infolist(self):
"""Return a list of class ZipInfo instances for files in the
archive."""
return self.filelist
def printdir(self):
"""Print a table of contents for the zip file."""
print "%-46s %19s %12s" % ("File Name", "Modified ", "Size")
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)
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.
f = self.open(zinfo.filename, "r")
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."""
self.pwd = pwd
def read(self, name, pwd=None):
"""Return file bytes (as a string) for name."""
return self.open(name, "r", pwd).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 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 = open(self.filename, 'rb')
# 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 fheader[0:4] != stringFileHeader:
raise BadZipfile, "Bad magic number for file header"
fheader = struct.unpack(structFileHeader, fheader)
fname = zef_file.read(fheader[_FH_FILENAME_LENGTH])
if fheader[_FH_EXTRA_FIELD_LENGTH]:
zef_file.read(fheader[_FH_EXTRA_FIELD_LENGTH])
if fname != zinfo.orig_filename:
raise BadZipfile, \
'File name in directory "%s" and header "%s" 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.
bytes = zef_file.read(12)
h = map(zd, bytes[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 ord(h[11]) != check_byte:
raise RuntimeError("Bad password for file", name)
# build and return a ZipExtFile
if zd is None:
zef = ZipExtFile(zef_file, zinfo)
else:
zef = ZipExtFile(zef_file, zinfo, zd)
# set universal newlines on ZipExtFile if necessary
if "U" in mode:
zef.set_univ_newlines(True)
return zef
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)
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.
# Strip trailing path separator, unless it represents the root.
if (targetpath[-1:] in (os.path.sep, os.path.altsep)
and len(os.path.splitdrive(targetpath)[1]) > 1):
targetpath = targetpath[:-1]
# don't include leading "/" from file name if present
if member.filename[0] == '/':
targetpath = os.path.join(targetpath, member.filename[1:])
else:
targetpath = os.path.join(targetpath, member.filename)
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
source = self.open(member, pwd=pwd)
target = file(targetpath, "wb")
shutil.copyfileobj(source, target)
source.close()
target.close()
return targetpath
def _writecheck(self, zinfo):
"""Check for errors before writing a file to the archive."""