-
-
Notifications
You must be signed in to change notification settings - Fork 34.2k
Expand file tree
/
Copy pathtarfile.py
More file actions
2630 lines (2292 loc) · 88.4 KB
/
tarfile.py
File metadata and controls
2630 lines (2292 loc) · 88.4 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
# -*- coding: iso-8859-1 -*-
#-------------------------------------------------------------------
# tarfile.py
#-------------------------------------------------------------------
# Copyright (C) 2002 Lars Gustäbel <lars@gustaebel.de>
# All rights reserved.
#
# Permission is hereby granted, free of charge, to any person
# obtaining a copy of this software and associated documentation
# files (the "Software"), to deal in the Software without
# restriction, including without limitation the rights to use,
# copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the
# Software is furnished to do so, subject to the following
# conditions:
#
# The above copyright notice and this permission notice shall be
# included in all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
# OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
# HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
# WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
# OTHER DEALINGS IN THE SOFTWARE.
#
"""Read from and write to tar format archives.
"""
__version__ = "$Revision: 85213 $"
# $Source$
version = "0.9.0"
__author__ = "Lars Gustäbel (lars@gustaebel.de)"
__date__ = "$Date$"
__cvsid__ = "$Id$"
__credits__ = "Gustavo Niemeyer, Niels Gustäbel, Richard Townsend."
#---------
# Imports
#---------
from __builtin__ import open as bltn_open
import sys
import os
import shutil
import stat
import errno
import time
import struct
import copy
import re
import operator
try:
import grp, pwd
except ImportError:
grp = pwd = None
# from tarfile import *
__all__ = ["TarFile", "TarInfo", "is_tarfile", "TarError"]
#---------------------------------------------------------
# tar constants
#---------------------------------------------------------
NUL = "\0" # the null character
BLOCKSIZE = 512 # length of processing blocks
RECORDSIZE = BLOCKSIZE * 20 # length of records
GNU_MAGIC = "ustar \0" # magic gnu tar string
POSIX_MAGIC = "ustar\x0000" # magic posix tar string
LENGTH_NAME = 100 # maximum length of a filename
LENGTH_LINK = 100 # maximum length of a linkname
LENGTH_PREFIX = 155 # maximum length of the prefix field
REGTYPE = "0" # regular file
AREGTYPE = "\0" # regular file
LNKTYPE = "1" # link (inside tarfile)
SYMTYPE = "2" # symbolic link
CHRTYPE = "3" # character special device
BLKTYPE = "4" # block special device
DIRTYPE = "5" # directory
FIFOTYPE = "6" # fifo special device
CONTTYPE = "7" # contiguous file
GNUTYPE_LONGNAME = "L" # GNU tar longname
GNUTYPE_LONGLINK = "K" # GNU tar longlink
GNUTYPE_SPARSE = "S" # GNU tar sparse file
XHDTYPE = "x" # POSIX.1-2001 extended header
XGLTYPE = "g" # POSIX.1-2001 global header
SOLARIS_XHDTYPE = "X" # Solaris extended header
USTAR_FORMAT = 0 # POSIX.1-1988 (ustar) format
GNU_FORMAT = 1 # GNU tar format
PAX_FORMAT = 2 # POSIX.1-2001 (pax) format
DEFAULT_FORMAT = GNU_FORMAT
#---------------------------------------------------------
# tarfile constants
#---------------------------------------------------------
# File types that tarfile supports:
SUPPORTED_TYPES = (REGTYPE, AREGTYPE, LNKTYPE,
SYMTYPE, DIRTYPE, FIFOTYPE,
CONTTYPE, CHRTYPE, BLKTYPE,
GNUTYPE_LONGNAME, GNUTYPE_LONGLINK,
GNUTYPE_SPARSE)
# File types that will be treated as a regular file.
REGULAR_TYPES = (REGTYPE, AREGTYPE,
CONTTYPE, GNUTYPE_SPARSE)
# File types that are part of the GNU tar format.
GNU_TYPES = (GNUTYPE_LONGNAME, GNUTYPE_LONGLINK,
GNUTYPE_SPARSE)
# Fields from a pax header that override a TarInfo attribute.
PAX_FIELDS = ("path", "linkpath", "size", "mtime",
"uid", "gid", "uname", "gname")
# Fields in a pax header that are numbers, all other fields
# are treated as strings.
PAX_NUMBER_FIELDS = {
"atime": float,
"ctime": float,
"mtime": float,
"uid": int,
"gid": int,
"size": int
}
#---------------------------------------------------------
# Bits used in the mode field, values in octal.
#---------------------------------------------------------
S_IFLNK = 0120000 # symbolic link
S_IFREG = 0100000 # regular file
S_IFBLK = 0060000 # block device
S_IFDIR = 0040000 # directory
S_IFCHR = 0020000 # character device
S_IFIFO = 0010000 # fifo
TSUID = 04000 # set UID on execution
TSGID = 02000 # set GID on execution
TSVTX = 01000 # reserved
TUREAD = 0400 # read by owner
TUWRITE = 0200 # write by owner
TUEXEC = 0100 # execute/search by owner
TGREAD = 0040 # read by group
TGWRITE = 0020 # write by group
TGEXEC = 0010 # execute/search by group
TOREAD = 0004 # read by other
TOWRITE = 0002 # write by other
TOEXEC = 0001 # execute/search by other
#---------------------------------------------------------
# initialization
#---------------------------------------------------------
ENCODING = sys.getfilesystemencoding()
if ENCODING is None:
ENCODING = sys.getdefaultencoding()
#---------------------------------------------------------
# Some useful functions
#---------------------------------------------------------
def stn(s, length):
"""Convert a python string to a null-terminated string buffer.
"""
return s[:length] + (length - len(s)) * NUL
def nts(s):
"""Convert a null-terminated string field to a python string.
"""
# Use the string up to the first null char.
p = s.find("\0")
if p == -1:
return s
return s[:p]
def nti(s):
"""Convert a number field to a python number.
"""
# There are two possible encodings for a number field, see
# itn() below.
if s[0] != chr(0200):
try:
n = int(nts(s).strip() or "0", 8)
except ValueError:
raise InvalidHeaderError("invalid header")
else:
n = 0L
for i in xrange(len(s) - 1):
n <<= 8
n += ord(s[i + 1])
return n
def itn(n, digits=8, format=DEFAULT_FORMAT):
"""Convert a python number to a number field.
"""
# POSIX 1003.1-1988 requires numbers to be encoded as a string of
# octal digits followed by a null-byte, this allows values up to
# (8**(digits-1))-1. GNU tar allows storing numbers greater than
# that if necessary. A leading 0200 byte indicates this particular
# encoding, the following digits-1 bytes are a big-endian
# representation. This allows values up to (256**(digits-1))-1.
if 0 <= n < 8 ** (digits - 1):
s = "%0*o" % (digits - 1, n) + NUL
else:
if format != GNU_FORMAT or n >= 256 ** (digits - 1):
raise ValueError("overflow in number field")
if n < 0:
# XXX We mimic GNU tar's behaviour with negative numbers,
# this could raise OverflowError.
n = struct.unpack("L", struct.pack("l", n))[0]
s = ""
for i in xrange(digits - 1):
s = chr(n & 0377) + s
n >>= 8
s = chr(0200) + s
return s
def uts(s, encoding, errors):
"""Convert a unicode object to a string.
"""
if errors == "utf-8":
# An extra error handler similar to the -o invalid=UTF-8 option
# in POSIX.1-2001. Replace untranslatable characters with their
# UTF-8 representation.
try:
return s.encode(encoding, "strict")
except UnicodeEncodeError:
x = []
for c in s:
try:
x.append(c.encode(encoding, "strict"))
except UnicodeEncodeError:
x.append(c.encode("utf8"))
return "".join(x)
else:
return s.encode(encoding, errors)
def calc_chksums(buf):
"""Calculate the checksum for a member's header by summing up all
characters except for the chksum field which is treated as if
it was filled with spaces. According to the GNU tar sources,
some tars (Sun and NeXT) calculate chksum with signed char,
which will be different if there are chars in the buffer with
the high bit set. So we calculate two checksums, unsigned and
signed.
"""
unsigned_chksum = 256 + sum(struct.unpack("148B", buf[:148]) + struct.unpack("356B", buf[156:512]))
signed_chksum = 256 + sum(struct.unpack("148b", buf[:148]) + struct.unpack("356b", buf[156:512]))
return unsigned_chksum, signed_chksum
def copyfileobj(src, dst, length=None):
"""Copy length bytes from fileobj src to fileobj dst.
If length is None, copy the entire content.
"""
if length == 0:
return
if length is None:
shutil.copyfileobj(src, dst)
return
BUFSIZE = 16 * 1024
blocks, remainder = divmod(length, BUFSIZE)
for b in xrange(blocks):
buf = src.read(BUFSIZE)
if len(buf) < BUFSIZE:
raise IOError("end of file reached")
dst.write(buf)
if remainder != 0:
buf = src.read(remainder)
if len(buf) < remainder:
raise IOError("end of file reached")
dst.write(buf)
return
filemode_table = (
((S_IFLNK, "l"),
(S_IFREG, "-"),
(S_IFBLK, "b"),
(S_IFDIR, "d"),
(S_IFCHR, "c"),
(S_IFIFO, "p")),
((TUREAD, "r"),),
((TUWRITE, "w"),),
((TUEXEC|TSUID, "s"),
(TSUID, "S"),
(TUEXEC, "x")),
((TGREAD, "r"),),
((TGWRITE, "w"),),
((TGEXEC|TSGID, "s"),
(TSGID, "S"),
(TGEXEC, "x")),
((TOREAD, "r"),),
((TOWRITE, "w"),),
((TOEXEC|TSVTX, "t"),
(TSVTX, "T"),
(TOEXEC, "x"))
)
def filemode(mode):
"""Convert a file's mode to a string of the form
-rwxrwxrwx.
Used by TarFile.list()
"""
perm = []
for table in filemode_table:
for bit, char in table:
if mode & bit == bit:
perm.append(char)
break
else:
perm.append("-")
return "".join(perm)
class TarError(Exception):
"""Base exception."""
pass
class ExtractError(TarError):
"""General exception for extract errors."""
pass
class ReadError(TarError):
"""Exception for unreadable tar archives."""
pass
class CompressionError(TarError):
"""Exception for unavailable compression methods."""
pass
class StreamError(TarError):
"""Exception for unsupported operations on stream-like TarFiles."""
pass
class HeaderError(TarError):
"""Base exception for header errors."""
pass
class EmptyHeaderError(HeaderError):
"""Exception for empty headers."""
pass
class TruncatedHeaderError(HeaderError):
"""Exception for truncated headers."""
pass
class EOFHeaderError(HeaderError):
"""Exception for end of file headers."""
pass
class InvalidHeaderError(HeaderError):
"""Exception for invalid headers."""
pass
class SubsequentHeaderError(HeaderError):
"""Exception for missing and invalid extended headers."""
pass
#---------------------------
# internal stream interface
#---------------------------
class _LowLevelFile:
"""Low-level file object. Supports reading and writing.
It is used instead of a regular file object for streaming
access.
"""
def __init__(self, name, mode):
mode = {
"r": os.O_RDONLY,
"w": os.O_WRONLY | os.O_CREAT | os.O_TRUNC,
}[mode]
if hasattr(os, "O_BINARY"):
mode |= os.O_BINARY
self.fd = os.open(name, mode, 0666)
def close(self):
os.close(self.fd)
def read(self, size):
return os.read(self.fd, size)
def write(self, s):
os.write(self.fd, s)
class _Stream:
"""Class that serves as an adapter between TarFile and
a stream-like object. The stream-like object only
needs to have a read() or write() method and is accessed
blockwise. Use of gzip or bzip2 compression is possible.
A stream-like object could be for example: sys.stdin,
sys.stdout, a socket, a tape device etc.
_Stream is intended to be used only internally.
"""
def __init__(self, name, mode, comptype, fileobj, bufsize):
"""Construct a _Stream object.
"""
self._extfileobj = True
if fileobj is None:
fileobj = _LowLevelFile(name, mode)
self._extfileobj = False
if comptype == '*':
# Enable transparent compression detection for the
# stream interface
fileobj = _StreamProxy(fileobj)
comptype = fileobj.getcomptype()
self.name = name or ""
self.mode = mode
self.comptype = comptype
self.fileobj = fileobj
self.bufsize = bufsize
self.buf = ""
self.pos = 0L
self.closed = False
try:
if comptype == "gz":
try:
import zlib
except ImportError:
raise CompressionError("zlib module is not available")
self.zlib = zlib
self.crc = zlib.crc32("") & 0xffffffffL
if mode == "r":
self._init_read_gz()
else:
self._init_write_gz()
elif comptype == "bz2":
try:
import bz2
except ImportError:
raise CompressionError("bz2 module is not available")
if mode == "r":
self.dbuf = ""
self.cmp = bz2.BZ2Decompressor()
else:
self.cmp = bz2.BZ2Compressor()
except:
if not self._extfileobj:
self.fileobj.close()
self.closed = True
raise
def __del__(self):
if hasattr(self, "closed") and not self.closed:
self.close()
def _init_write_gz(self):
"""Initialize for writing with gzip compression.
"""
self.cmp = self.zlib.compressobj(9, self.zlib.DEFLATED,
-self.zlib.MAX_WBITS,
self.zlib.DEF_MEM_LEVEL,
0)
timestamp = struct.pack("<L", long(time.time()))
self.__write("\037\213\010\010%s\002\377" % timestamp)
if type(self.name) is unicode:
self.name = self.name.encode("iso-8859-1", "replace")
if self.name.endswith(".gz"):
self.name = self.name[:-3]
self.__write(self.name + NUL)
def write(self, s):
"""Write string s to the stream.
"""
if self.comptype == "gz":
self.crc = self.zlib.crc32(s, self.crc) & 0xffffffffL
self.pos += len(s)
if self.comptype != "tar":
s = self.cmp.compress(s)
self.__write(s)
def __write(self, s):
"""Write string s to the stream if a whole new block
is ready to be written.
"""
self.buf += s
while len(self.buf) > self.bufsize:
self.fileobj.write(self.buf[:self.bufsize])
self.buf = self.buf[self.bufsize:]
def close(self):
"""Close the _Stream object. No operation should be
done on it afterwards.
"""
if self.closed:
return
self.closed = True
try:
if self.mode == "w" and self.comptype != "tar":
self.buf += self.cmp.flush()
if self.mode == "w" and self.buf:
self.fileobj.write(self.buf)
self.buf = ""
if self.comptype == "gz":
# The native zlib crc is an unsigned 32-bit integer, but
# the Python wrapper implicitly casts that to a signed C
# long. So, on a 32-bit box self.crc may "look negative",
# while the same crc on a 64-bit box may "look positive".
# To avoid irksome warnings from the `struct` module, force
# it to look positive on all boxes.
self.fileobj.write(struct.pack("<L", self.crc & 0xffffffffL))
self.fileobj.write(struct.pack("<L", self.pos & 0xffffFFFFL))
finally:
if not self._extfileobj:
self.fileobj.close()
def _init_read_gz(self):
"""Initialize for reading a gzip compressed fileobj.
"""
self.cmp = self.zlib.decompressobj(-self.zlib.MAX_WBITS)
self.dbuf = ""
# taken from gzip.GzipFile with some alterations
if self.__read(2) != "\037\213":
raise ReadError("not a gzip file")
if self.__read(1) != "\010":
raise CompressionError("unsupported compression method")
flag = ord(self.__read(1))
self.__read(6)
if flag & 4:
xlen = ord(self.__read(1)) + 256 * ord(self.__read(1))
self.read(xlen)
if flag & 8:
while True:
s = self.__read(1)
if not s or s == NUL:
break
if flag & 16:
while True:
s = self.__read(1)
if not s or s == NUL:
break
if flag & 2:
self.__read(2)
def tell(self):
"""Return the stream's file pointer position.
"""
return self.pos
def seek(self, pos=0):
"""Set the stream's file pointer to pos. Negative seeking
is forbidden.
"""
if pos - self.pos >= 0:
blocks, remainder = divmod(pos - self.pos, self.bufsize)
for i in xrange(blocks):
self.read(self.bufsize)
self.read(remainder)
else:
raise StreamError("seeking backwards is not allowed")
return self.pos
def read(self, size=None):
"""Return the next size number of bytes from the stream.
If size is not defined, return all bytes of the stream
up to EOF.
"""
if size is None:
t = []
while True:
buf = self._read(self.bufsize)
if not buf:
break
t.append(buf)
buf = "".join(t)
else:
buf = self._read(size)
self.pos += len(buf)
return buf
def _read(self, size):
"""Return size bytes from the stream.
"""
if self.comptype == "tar":
return self.__read(size)
c = len(self.dbuf)
t = [self.dbuf]
while c < size:
buf = self.__read(self.bufsize)
if not buf:
break
try:
buf = self.cmp.decompress(buf)
except IOError:
raise ReadError("invalid compressed data")
t.append(buf)
c += len(buf)
t = "".join(t)
self.dbuf = t[size:]
return t[:size]
def __read(self, size):
"""Return size bytes from stream. If internal buffer is empty,
read another block from the stream.
"""
c = len(self.buf)
t = [self.buf]
while c < size:
buf = self.fileobj.read(self.bufsize)
if not buf:
break
t.append(buf)
c += len(buf)
t = "".join(t)
self.buf = t[size:]
return t[:size]
# class _Stream
class _StreamProxy(object):
"""Small proxy class that enables transparent compression
detection for the Stream interface (mode 'r|*').
"""
def __init__(self, fileobj):
self.fileobj = fileobj
self.buf = self.fileobj.read(BLOCKSIZE)
def read(self, size):
self.read = self.fileobj.read
<
4CA7
div>
return self.buf
def getcomptype(self):
if self.buf.startswith("\037\213\010"):
return "gz"
if self.buf[0:3] == "BZh" and self.buf[4:10] == "1AY&SY":
return "bz2"
return "tar"
def close(self):
self.fileobj.close()
# class StreamProxy
class _BZ2Proxy(object):
"""Small proxy class that enables external file object
support for "r:bz2" and "w:bz2" modes. This is actually
a workaround for a limitation in bz2 module's BZ2File
class which (unlike gzip.GzipFile) has no support for
a file object argument.
"""
blocksize = 16 * 1024
def __init__(self, fileobj, mode):
self.fileobj = fileobj
self.mode = mode
self.name = getattr(self.fileobj, "name", None)
self.init()
def init(self):
import bz2
self.pos = 0
if self.mode == "r":
self.bz2obj = bz2.BZ2Decompressor()
self.fileobj.seek(0)
self.buf = ""
else:
self.bz2obj = bz2.BZ2Compressor()
def read(self, size):
b = [self.buf]
x = len(self.buf)
while x < size:
raw = self.fileobj.read(self.blocksize)
if not raw:
break
data = self.bz2obj.decompress(raw)
b.append(data)
x += len(data)
self.buf = "".join(b)
buf = self.buf[:size]
self.buf = self.buf[size:]
self.pos += len(buf)
return buf
def seek(self, pos):
if pos < self.pos:
self.init()
self.read(pos - self.pos)
def tell(self):
return self.pos
def write(self, data):
self.pos += len(data)
raw = self.bz2obj.compress(data)
self.fileobj.write(raw)
def close(self):
if self.mode == "w":
raw = self.bz2obj.flush()
self.fileobj.write(raw)
# class _BZ2Proxy
#------------------------
# Extraction file object
#------------------------
class _FileInFile(object):
"""A thin wrapper around an existing file object that
provides a part of its data as an individual file
object.
"""
def __init__(self, fileobj, offset, size, sparse=None):
self.fileobj = fileobj
self.offset = offset
self.size = size
self.sparse = sparse
self.position = 0
def tell(self):
"""Return the current file position.
"""
return self.position
def seek(self, position):
"""Seek to a position in the file.
"""
self.position = position
def read(self, size=None):
"""Read data from the file.
"""
if size is None:
size = self.size - self.position
else:
size = min(size, self.size - self.position)
if self.sparse is None:
return self.readnormal(size)
else:
return self.readsparse(size)
def __read(self, size):
buf = self.fileobj.read(size)
if len(buf) != size:
raise ReadError("unexpected end of data")
return buf
def readnormal(self, size):
"""Read operation for regular files.
"""
self.fileobj.seek(self.offset + self.position)
self.position += size
return self.__read(size)
def readsparse(self, size):
"""Read operation for sparse files.
"""
data = []
while size > 0:
buf = self.readsparsesection(size)
if not buf:
break
size -= len(buf)
data.append(buf)
return "".join(data)
def readsparsesection(self, size):
"""Read a single section of a sparse file.
"""
section = self.sparse.find(self.position)
if section is None:
return ""
size = min(size, section.offset + section.size - self.position)
if isinstance(section, _data):
realpos = section.realpos + self.position - section.offset
self.fileobj.seek(self.offset + realpos)
self.position += size
return self.__read(size)
else:
self.position += size
return NUL * size
#class _FileInFile
class ExFileObject(object):
"""File-like object for reading an archive member.
Is returned by TarFile.extractfile().
"""
blocksize = 1024
def __init__(self, tarfile, tarinfo):
self.fileobj = _FileInFile(tarfile.fileobj,
tarinfo.offset_data,
tarinfo.size,
getattr(tarinfo, "sparse", None))
self.name = tarinfo.name
self.mode = "r"
self.closed = False
self.size = tarinfo.size
self.position = 0
self.buffer = ""
def read(self, size=None):
"""Read at most size bytes from the file. If size is not
present or None, read all data until EOF is reached.
"""
if self.closed:
raise ValueError("I/O operation on closed file")
buf = ""
if self.buffer:
if size is None:
buf = self.buffer
self.buffer = ""
else:
buf = self.buffer[:size]
self.buffer = self.buffer[size:]
if size is None:
buf += self.fileobj.read()
else:
buf += self.fileobj.read(size - len(buf))
self.position += len(buf)
return buf
def readline(self, size=-1):
"""Read one entire line from the file. If size is present
and non-negative, return a string with at most that
size, which may be an incomplete line.
"""
if self.closed:
raise ValueError("I/O operation on closed file")
if "\n" in self.buffer:
pos = self.buffer.find("\n") + 1
else:
buffers = [self.buffer]
while True:
buf = self.fileobj.read(self.blocksize)
buffers.append(buf)
if not buf or "\n" in buf:
self.buffer = "".join(buffers)
pos = self.buffer.find("\n") + 1
if pos == 0:
# no newline found.
pos = len(self.buffer)
break
if size != -1:
pos = min(size, pos)
buf = self.buffer[:pos]
self.buffer = self.buffer[pos:]
self.position += len(buf)
return buf
def readlines(self):
"""Return a list with all remaining lines.
"""
result = []
while True:
line = self.readline()
if not line: break
result.append(line)
return result
def tell(self):
"""Return the current file position.
"""
if self.closed:
raise ValueError("I/O operation on closed file")
return self.position
def seek(self, pos, whence=os.SEEK_SET):
"""Seek to a position in the file.
"""
if self.closed:
raise ValueError("I/O operation on closed file")
if whence == os.SEEK_SET:
self.position = min(max(pos, 0), self.size)
elif whence == os.SEEK_CUR:
if pos < 0:
self.position = max(self.position + pos, 0)
else:
self.position = min(self.position + pos, self.size)
elif whence == os.SEEK_END:
self.position = max(min(self.size + pos, self.size), 0)
else:
raise ValueError("Invalid argument")
4CA7
self.buffer = ""
self.fileobj.seek(self.position)
def close(self):
"""Close the file object.
"""
self.closed = True
def __iter__(self):
"""Get an iterator over the file's lines.
"""
while True:
line = self.readline()
if not line:
break
yield line
#class ExFileObject
#------------------
# Exported Classes
#------------------
class TarInfo(object):
"""Informational class which holds the details about an
archive member given by a tar header block.
TarInfo objects are returned by TarFile.getmember(),
TarFile.getmembers() and TarFile.gettarinfo() and are
usually created internally.
"""
def __init__(self, name=""):
"""Construct a TarInfo object. name is the optional name
of the member.
"""
self.name = name # member name
self.mode = 0644 # file permissions
self.uid = 0 # user id
self.gid = 0 # group id
self.size = 0 # file size
self.mtime = 0 # modification time
self.chksum = 0 # header checksum
self.type = REGTYPE # member type
self.linkname = "" # link name
self.uname = "" # user name
self.gname = "" # group name
self.devmajor = 0 # device major number
self.devminor = 0 # device minor number
self.offset = 0 # the tar header starts here
self.offset_data = 0 # the file's data starts here
self.pax_headers = {} # pax header information
# In pax headers the "name" and "linkname" field are called
# "path" and "linkpath".
def _getpath(self):
return self.name
def _setpath(self, name):
self.name = name
path = property(_getpath, _setpath)
def _getlinkpath(self):
return self.linkname
def _setlinkpath(self, linkname):
self.linkname = linkname
linkpath = property(_getlinkpath, _setlinkpath)
def __repr__(self):
return "<%s %r at %#x>" % (self.__class__.__name__,self.name,id(self))
def get_info(self, encoding, errors):
"""Return the TarInfo's attributes as a dictionary.
"""
info = {
"name": self.name,
"mode": self.mode & 07777,
"uid": self.uid,
"gid": self.gid,
"size": self.size,
"mtime": self.mtime,
"chksum": self.chksum,
"type": self.type,
"linkname": self.linkname,
"uname": self.uname,
"gname": self.gname,
"devmajor": self.devmajor,
"devminor": self.devminor
}
if info["type"] == DIRTYPE and not info["name"].endswith("/"):
info["name"] += "/"
for key in ("name", "linkname", "uname", "gname"):
if type(info[key]) is unicode:
info[key] = info[key].encode(encoding, errors)
return info
def tobuf(self, format=DEFAULT_FORMAT, encoding=ENCODING, errors="strict"):