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
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
|
#!/usr/bin/env python3
#-------------------------------------------------------------------
# tarfile.py
#-------------------------------------------------------------------
# Copyright (C) 2002 Lars Gustaebel <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 = "0.9.0"
__author__ = "Lars Gust\u00e4bel (lars@gustaebel.de)"
__credits__ = "Gustavo Niemeyer, Niels Gust\u00e4bel, Richard Townsend."
#---------
# Imports
#---------
from builtins import open as bltn_open
import sys
import os
import io
import shutil
import stat
import time
import struct
import copy
import re
try:
import pwd
except ImportError:
pwd = None
try:
import grp
except ImportError:
grp = None
# os.symlink on Windows prior to 6.0 raises NotImplementedError
symlink_exception = (AttributeError, NotImplementedError)
try:
# OSError (winerror=1314) will be raised if the caller does not hold the
# SeCreateSymbolicLinkPrivilege privilege
symlink_exception += (OSError,)
except NameError:
pass
# from tarfile import *
__all__ = ["TarFile", "TarInfo", "is_tarfile", "TarError", "ReadError",
"CompressionError", "StreamError", "ExtractError", "HeaderError",
"ENCODING", "USTAR_FORMAT", "GNU_FORMAT", "PAX_FORMAT",
"DEFAULT_FORMAT", "open"]
#---------------------------------------------------------
# tar constants
#---------------------------------------------------------
NUL = b"\0" # the null character
BLOCKSIZE = 512 # length of processing blocks
RECORDSIZE = BLOCKSIZE * 20 # length of records
GNU_MAGIC = b"ustar \0" # magic gnu tar string
POSIX_MAGIC = b"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 = b"0" # regular file
AREGTYPE = b"\0" # regular file
LNKTYPE = b"1" # link (inside tarfile)
SYMTYPE = b"2" # symbolic link
CHRTYPE = b"3" # character special device
BLKTYPE = b"4" # block special device
DIRTYPE = b"5" # directory
FIFOTYPE = b"6" # fifo special device
CONTTYPE = b"7" # contiguous file
GNUTYPE_LONGNAME = b"L" # GNU tar longname
GNUTYPE_LONGLINK = b"K" # GNU tar longlink
GNUTYPE_SPARSE = b"S" # GNU tar sparse file
XHDTYPE = b"x" # POSIX.1-2001 extended header
XGLTYPE = b"g" # POSIX.1-2001 global header
SOLARIS_XHDTYPE = b"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 = PAX_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 from a pax header that are affected by hdrcharset.
PAX_NAME_FIELDS = {"path", "linkpath", "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
}
#---------------------------------------------------------
# initialization
#---------------------------------------------------------
if os.name == "nt":
ENCODING = "utf-8"
else:
ENCODING = sys.getfilesystemencoding()
#---------------------------------------------------------
# Some useful functions
#---------------------------------------------------------
def stn(s, length, encoding, errors):
"""Convert a string to a null-terminated bytes object.
"""
s = s.encode(encoding, errors)
return s[:length] + (length - len(s)) * NUL
def nts(s, encoding, errors):
"""Convert a null-terminated bytes object to a string.
"""
p = s.find(b"\0")
if p != -1:
s = s[:p]
return s.decode(encoding, errors)
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] in (0o200, 0o377):
n = 0
for i in range(len(s) - 1):
n <<= 8
n += s[i + 1]
if s[0] == 0o377:
n = -(256 ** (len(s) - 1) - n)
else:
try:
s = nts(s, "ascii", "strict")
n = int(s.strip() or "0", 8)
except ValueError:
raise InvalidHeaderError("invalid header")
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 0o200 or 0o377 byte indicate this
# particular encoding, the following digits-1 bytes are a big-endian
# base-256 representation. This allows values up to (256**(digits-1))-1.
# A 0o200 byte indicates a positive number, a 0o377 byte a negative
# number.
original_n = n
n = int(n)
if 0 <= n < 8 ** (digits - 1):
s = bytes("%0*o" % (digits - 1, n), "ascii") + NUL
elif format == GNU_FORMAT and -256 ** (digits - 1) <= n < 256 ** (digits - 1):
if n >= 0:
s = bytearray([0o200])
else:
s = bytearray([0o377])
n = 256 ** digits + n
for i in range(digits - 1):
s.insert(1, n & 0o377)
n >>= 8
else:
raise ValueError("overflow in number field")
return s
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_from("148B8x356B", buf))
signed_chksum = 256 + sum(struct.unpack_from("148b8x356b", buf))
return unsigned_chksum, signed_chksum
def copyfileobj(src, dst, length=None, exception=OSError, bufsize=None):
"""Copy length bytes from fileobj src to fileobj dst.
If length is None, copy the entire content.
"""
bufsize = bufsize or 16 * 1024
if length == 0:
return
if length is None:
shutil.copyfileobj(src, dst, bufsize)
return
blocks, remainder = divmod(length, bufsize)
for b in range(blocks):
buf = src.read(bufsize)
if len(buf) < bufsize:
raise exception("unexpected end of data")
dst.write(buf)
if remainder != 0:
buf = src.read(remainder)
if len(buf) < remainder:
raise exception("unexpected end of data")
dst.write(buf)
return
def _safe_print(s):
encoding = getattr(sys.stdout, 'encoding', None)
if encoding is not None:
s = s.encode(encoding, 'backslashreplace').decode(encoding)
print(s, end=' ')
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, 0o666)
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 = b""
self.pos = 0
self.closed = False
try:
if comptype == "gz":
try:
import zlib
except ImportError:
raise CompressionError("zlib module is not available") from None
self.zlib = zlib
self.crc = zlib.crc32(b"")
if mode == "r":
self._init_read_gz()
self.exception = zlib.error
else:
self._init_write_gz()
elif comptype == "bz2":
try:
import bz2
except ImportError:
raise CompressionError("bz2 module is not available") from None
if mode == "r":
self.dbuf = b""
self.cmp = bz2.BZ2Decompressor()
self.exception = OSError
else:
self.cmp = bz2.BZ2Compressor()
elif comptype == "xz":
try:
import lzma
except ImportError:
raise CompressionError("lzma module is not available") from None
if mode == "r":
self.dbuf = b""
self.cmp = lzma.LZMADecompressor()
self.exception = lzma.LZMAError
else:
self.cmp = lzma.LZMACompressor()
elif comptype != "tar":
raise CompressionError("unknown compression type %r" % comptype)
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", int(time.time()))
self.__write(b"\037\213\010\010" + timestamp + b"\002\377")
if self.name.endswith(".gz"):
self.name = self.name[:-3]
# Honor "directory components removed" from RFC1952
self.name = os.path.basename(self.name)
# RFC1952 says we must use ISO-8859-1 for the FNAME field.
self.__write(self.name.encode("iso-8859-1", "replace") + NUL)
def write(self, s):
"""Write string s to the stream.
"""
if self.comptype == "gz":
self.crc = self.zlib.crc32(s, self.crc)
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 = b""
if self.comptype == "gz":
self.fileobj.write(struct.pack("<L", self.crc))
self.fileobj.write(struct.pack("<L", self.pos & 0xffffFFFF))
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 = b""
# taken from gzip.GzipFile with some alterations
if self.__read(2) != b"\037\213":
raise ReadError("not a gzip file")
if self.__read(1) != b"\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 range(blocks):
self.read(self.bufsize)
self.read(remainder)
else:
raise StreamError("seeking backwards is not allowed")
return self.pos
def read(self, size):
"""Return the next size number of bytes from the stream."""
assert size is not None
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:
# Skip underlying buffer to avoid unaligned double buffering.
if self.buf:
buf = self.buf
self.buf = b""
else:
buf = self.fileobj.read(self.bufsize)
if not buf:
break
try:
buf = self.cmp.decompress(buf)
except self.exception as e:
raise ReadError("invalid compressed data") from e
t.append(buf)
c += len(buf)
t = b"".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 = b"".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
return self.buf
def getcomptype(self):
if self.buf.startswith(b"\x1f\x8b\x08"):
return "gz"
elif self.buf[0:3] == b"BZh" and self.buf[4:10] == b"1AY&SY":
return "bz2"
elif self.buf.startswith((b"\x5d\x00\x00\x80", b"\xfd7zXZ")):
return "xz"
else:
return "tar"
def close(self):
self.fileobj.close()
# class StreamProxy
#------------------------
# 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, blockinfo=None):
self.fileobj = fileobj
self.offset = offset
self.size = size
self.position = 0
self.name = getattr(fileobj, "name", None)
self.closed = False
if blockinfo is None:
blockinfo = [(0, size)]
# Construct a map with data and zero blocks.
self.map_index = 0
self.map = []
lastpos = 0
realpos = self.offset
for offset, size in blockinfo:
if offset > lastpos:
self.map.append((False, lastpos, offset, None))
self.map.append((True, offset, offset + size, realpos))
realpos += size
lastpos = offset + size
if lastpos < self.size:
self.map.append((False, lastpos, self.size, None))
def flush(self):
pass
def readable(self):
return True
def writable(self):
return False
def seekable(self):
return self.fileobj.seekable()
def tell(self):
"""Return the current file position.
"""
return self.position
def seek(self, position, whence=io.SEEK_SET):
"""Seek to a position in the file.
"""
if whence == io.SEEK_SET:
self.position = min(max(position, 0), self.size)
elif whence == io.SEEK_CUR:
if position < 0:
self.position = max(self.position + position, 0)
else:
self.position = min(self.position + position, self.size)
elif whence == io.SEEK_END:
self.position = max(min(self.size + position, self.size), 0)
else:
raise ValueError("Invalid argument")
return self.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)
buf = b""
while size > 0:
while True:
data, start, stop, offset = self.map[self.map_index]
if start <= self.position < stop:
break
else:
self.map_index += 1
if self.map_index == len(self.map):
self.map_index = 0
length = min(size, stop - self.position)
if data:
self.fileobj.seek(offset + (self.position - start))
b = self.fileobj.read(length)
if len(b) != length:
raise ReadError("unexpected end of data")
buf += b
else:
buf += NUL * length
size -= length
self.position += length
return buf
def readinto(self, b):
buf = self.read(len(b))
b[:len(buf)] = buf
return len(buf)
def close(self):
self.closed = True
#class _FileInFile
class ExFileObject(io.BufferedReader):
def __init__(self, tarfile, tarinfo):
fileobj = _FileInFile(tarfile.fileobj, tarinfo.offset_data,
tarinfo.size, tarinfo.sparse)
super().__init__(fileobj)
#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.
"""
__slots__ = dict(
name = 'Name of the archive member.',
mode = 'Permission bits.',
uid = 'User ID of the user who originally stored this member.',
gid = 'Group ID of the user who originally stored this member.',
size = 'Size in bytes.',
mtime = 'Time of last modification.',
chksum = 'Header checksum.',
type = ('File type. type is usually one of these constants: '
'REGTYPE, AREGTYPE, LNKTYPE, SYMTYPE, DIRTYPE, FIFOTYPE, '
'CONTTYPE, CHRTYPE, BLKTYPE, GNUTYPE_SPARSE.'),
linkname = ('Name of the target file name, which is only present '
'in TarInfo objects of type LNKTYPE and SYMTYPE.'),
uname = 'User name.',
gname = 'Group name.',
devmajor = 'Device major number.',
devminor = 'Device minor number.',
offset = 'The tar header starts here.',
offset_data = "The file's data starts here.",
pax_headers = ('A dictionary containing key-value pairs of an '
'associated pax extended header.'),
sparse = 'Sparse member information.',
tarfile = None,
_sparse_structs = None,
_link_target = None,
)
def __init__(self, name=""):
"""Construct a TarInfo object. name is the optional name
of the member.
"""
self.name = name # member name
self.mode = 0o644 # 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.sparse = None # sparse member information
self.pax_headers = {} # pax header information
@property
def path(self):
'In pax headers, "name" is called "path".'
return self.name
@path.setter
def path(self, name):
self.name = name
@property
def linkpath(self):
'In pax headers, "linkname" is called "linkpath".'
return self.linkname
@linkpath.setter
def linkpath(self, linkname):
self.linkname = linkname
def __repr__(self):
return "<%s %r at %#x>" % (self.__class__.__name__,self.name,id(self))
def get_info(self):
"""Return the TarInfo's attributes as a dictionary.
"""
info = {
"name": self.name,
"mode": self.mode & 0o7777,
"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"] += "/"
return info
def tobuf(self, format=DEFAULT_FORMAT, encoding=ENCODING, errors="surrogateescape"):
"""Return a tar header as a string of 512 byte blocks.
"""
info = self.get_info()
if format == USTAR_FORMAT:
return self.create_ustar_header(info, encoding, errors)
elif format == GNU_FORMAT:
return self.create_gnu_header(info, encoding, errors)
elif format == PAX_FORMAT:
return self.create_pax_header(info, encoding)
else:
raise ValueError("invalid format")
def create_ustar_header(self, info, encoding, errors):
"""Return the object as a ustar header block.
"""
info["magic"] = POSIX_MAGIC
if len(info["linkname"].encode(encoding, errors)) > LENGTH_LINK:
raise ValueError("linkname is too long")
if len(info["name"].encode(encoding, errors)) > LENGTH_NAME:
info["prefix"], info["name"] = self._posix_split_name(info["name"], encoding, errors)
return self._create_header(info, USTAR_FORMAT, encoding, errors)
def create_gnu_header(self, info, encoding, errors):
"""Return the object as a GNU header block sequence.
"""
info["magic"] = GNU_MAGIC
buf = b""
if len(info["linkname"].encode(encoding, errors)) > LENGTH_LINK:
buf += self._create_gnu_long_header(info["linkname"], GNUTYPE_LONGLINK, encoding, errors)
if len(info["name"].encode(encoding, errors)) > LENGTH_NAME:
buf += self._create_gnu_long_header(info["name"], GNUTYPE_LONGNAME, encoding, errors)
return buf + self._create_header(info, GNU_FORMAT, encoding, errors)
def create_pax_header(self, info, encoding):
"""Return the object as a ustar header block. If it cannot be
represented this way, prepend a pax extended header sequence
with supplement information.
"""
info["magic"] = POSIX_MAGIC
pax_headers = self.pax_headers.copy()
# Test string fields for values that exceed the field length or cannot
# be represented in ASCII encoding.
for name, hname, length in (
("name", "path", LENGTH_NAME), ("linkname", "linkpath", LENGTH_LINK),
("uname", "uname", 32), ("gname", "gname", 32)):
if hname in pax_headers:
# The pax header has priority.
continue
# Try to encode the string as ASCII.
try:
info[name].encode("ascii", "strict")
except UnicodeEncodeError:
pax_headers[hname] = info[name]
continue
if len(info[name]) > length:
pax_headers[hname] = info[name]
# Test number fields for values that exceed the field limit or values
# that like to be stored as float.
for name, digits in (("uid", 8), ("gid", 8), ("size", 12), ("mtime", 12)):
needs_pax = False
val = info[name]
val_is_float = isinstance(val, float)
val_int = round(val) if val_is_float else val
if not 0 <= val_int < 8 ** (digits - 1):
# Avoid overflow.
info[name] = 0
needs_pax = True
elif val_is_float:
# Put rounded value in ustar header, and full
# precision value in pax header.
info[name] = val_int
needs_pax = True
# The existing pax header has priority.
if needs_pax and name not in pax_headers:
pax_headers[name] = str(val)
# Create a pax extended header if necessary.
if pax_headers:
buf = self._create_pax_generic_header(pax_headers, XHDTYPE, encoding)
else:
buf = b""
return buf + self._create_header(info, USTAR_FORMAT, "ascii", "replace")
@classmethod
def create_pax_global_header(cls, pax_headers):
"""Return the object as a pax global header block sequence.
"""
return cls._create_pax_generic_header(pax_headers, XGLTYPE, "utf-8")
def _posix_split_name(self, name, encoding, errors):
"""Split a name longer than 100 chars into a prefix
and a name part.
"""
components = name.split("/")
for i in range(1, len(components)):
prefix = "/".join(components[:i])
name = "/".join(components[i:])
if len(prefix.encode(encoding, errors)) <= LENGTH_PREFIX and \
len(name.encode(encoding, errors)) <= LENGTH_NAME:
break
else:
raise ValueError("name is too long")
return prefix, name
@staticmethod
def _create_header(info, format, encoding, errors):
"""Return a header block. info is a dictionary with file
information, format must be one of the *_FORMAT constants.
"""
has_device_fields = info.get("type") in (CHRTYPE, BLKTYPE)
if has_device_fields:
devmajor = itn(info.get("devmajor", 0), 8, format)
devminor = itn(info.get("devminor", 0), 8, format)
else:
devmajor = stn("", 8, encoding, errors)
devminor = stn("", 8, encoding, errors)
parts = [
stn(info.get("name", ""), 100, encoding, errors),
itn(info.get("mode", 0) & 0o7777, 8, format),
itn(info.get("uid", 0), 8, format),
itn(info.get("gid", 0), 8, format),
itn(info.get("size", 0), 12, format),
itn(info.get("mtime", 0), 12, format),
b" ", # checksum field
info.get("type", REGTYPE),
stn(info.get("linkname", ""), 100, encoding, errors),
info.get("magic", POSIX_MAGIC),
stn(info.get("uname", ""), 32, encoding, errors),
stn(info.get("gname", ""), 32, encoding, errors),
devmajor,
devminor,
stn(info.get("prefix", ""), 155, encoding, errors)
]
buf = struct.pack("%ds" % BLOCKSIZE, b"".join(parts))
chksum = calc_chksums(buf[-BLOCKSIZE:])[0]
buf = buf[:-364] + bytes("%06o\0" % chksum, "ascii") + buf[-357:]
return buf
@staticmethod
def _create_payload(payload):
"""Return the string payload filled with zero bytes
up to the next 512 byte border.
"""
blocks, remainder = divmod(len(payload), BLOCKSIZE)
if remainder > 0:
payload += (BLOCKSIZE - remainder) * NUL
return payload
@classmethod
def _create_gnu_long_header(cls, name, type, encoding, errors):
"""Return a GNUTYPE_LONGNAME or GNUTYPE_LONGLINK sequence
for name.
"""
name = name.encode(encoding, errors) + NUL
info = {}
info["name"] = "././@LongLink"
info["type"] = type
info["size"] = len(name)
info["magic"] = GNU_MAGIC
# create extended header + name blocks.
return cls._create_header(info, USTAR_FORMAT, encoding, errors) + \
cls._create_payload(name)
@classmethod
def _create_pax_generic_header(cls, pax_headers, type, encoding):
"""Return a POSIX.1-2008 extended or global header sequence
that contains a list of keyword, value pairs. The values
must be strings.
"""
# Check if one of the fields contains surrogate characters and thereby
# forces hdrcharset=BINARY, see _proc_pax() for more information.
binary = False
for keyword, value in pax_headers.items():
try:
value.encode("utf-8", "strict")
except UnicodeEncodeError:
binary = True
break
records = b""
if binary:
# Put the hdrcharset field at the beginning of the header.
records += b"21 hdrcharset=BINARY\n"
for keyword, value in pax_headers.items():
keyword = keyword.encode("utf-8")
if binary:
# Try to restore the original byte representation of `value'.
# Needless to say, that the encoding must match the string.
value = value.encode(encoding, "surrogateescape")
else:
value = value.encode("utf-8")
l = len(keyword) + len(value) + 3 # ' ' + '=' + '\n'
n = p = 0
while True:
n = l + len(str(p))
if n == p:
break
p = n
records += bytes(str(p), "ascii") + b" " + keyword + b"=" + value + b"\n"
# We use a hardcoded "././@PaxHeader" name like star does
# instead of the one that POSIX recommends.
info = {}
info["name"] = "././@PaxHeader"
info["type"] = type
info["size"] = len(records)
info["magic"] = POSIX_MAGIC
# Create pax header + record blocks.
return cls._create_header(info, USTAR_FORMAT, "ascii", "replace") + \
cls._create_payload(records)
@classmethod
def frombuf(cls, buf, encoding, errors):
"""Construct a TarInfo object from a 512 byte bytes object.
"""
if len(buf) == 0:
raise EmptyHeaderError("empty header")
if len(buf) != BLOCKSIZE:
raise TruncatedHeaderError("truncated header")
if buf.count(NUL) == BLOCKSIZE:
raise EOFHeaderError("end of file header")
chksum = nti(buf[148:156])
if chksum not in calc_chksums(buf):
raise InvalidHeaderError("bad checksum")
obj = cls()
obj.name = nts(buf[0:100], encoding, errors)
obj.mode = nti(buf[100:108])
obj.uid = nti(buf[108:116])
obj.gid = nti(buf[116:124])
obj.size = nti(buf[124:136])
obj.mtime = nti(buf[136:148])
obj.chksum = chksum
obj.type = buf[156:157]
obj.linkname = nts(buf[157:257], encoding, errors)
obj.uname = nts(buf[265:297], encoding, errors)
obj.gname = nts(buf[297:329], encoding, errors)
obj.devmajor = nti(buf[329:337])
obj.devminor = nti(buf[337:345])
prefix = nts(buf[345:500], encoding, errors)
# Old V7 tar format represents a directory as a regular
# file with a trailing slash.
if obj.type == AREGTYPE and obj.name.endswith("/"):
obj.type = DIRTYPE
# The old GNU sparse format occupies some of the unused
# space in the buffer for up to 4 sparse structures.
# Save them for later processing in _proc_sparse().
if obj.type == GNUTYPE_SPARSE:
pos = 386
structs = []
for i in range(4):
try:
offset = nti(buf[pos:pos + 12])
numbytes = nti(buf[pos + 12:pos + 24])
except ValueError:
break
structs.append((offset, numbytes))
pos += 24
isextended = bool(buf[482])
origsize = nti(buf[483:495])
obj._sparse_structs = (structs, isextended, origsize)
# Remove redundant slashes from directories.
if obj.isdir():
obj.name = obj.name.rstrip("/")
# Reconstruct a ustar longname.
if prefix and obj.type not in GNU_TYPES:
obj.name = prefix + "/" + obj.name
return obj
@classmethod
def fromtarfile(cls, tarfile):
"""Return the next TarInfo object from TarFile object
tarfile.
"""
buf = tarfile.fileobj.read(BLOCKSIZE)
obj = cls.frombuf(buf, tarfile.encoding, tarfile.errors)
obj.offset = tarfile.fileobj.tell() - BLOCKSIZE
return obj._proc_member(tarfile)
#--------------------------------------------------------------------------
# The following are methods that are called depending on the type of a
# member. The entry point is _proc_member() which can be overridden in a
# subclass to add custom _proc_*() methods. A _proc_*() method MUST
# implement the following
# operations:
# 1. Set self.offset_data to the position where the data blocks begin,
# if there is data that follows.
# 2. Set tarfile.offset to the position where the next member's header will
# begin.
# 3. Return self or another valid TarInfo object.
def _proc_member(self, tarfile):
"""Choose the right processing method depending on
the type and call it.
"""
if self.type in (GNUTYPE_LONGNAME, GNUTYPE_LONGLINK):
return self._proc_gnulong(tarfile)
elif self.type == GNUTYPE_SPARSE:
return self._proc_sparse(tarfile)
elif self.type in (XHDTYPE, XGLTYPE, SOLARIS_XHDTYPE):
return self._proc_pax(tarfile)
else:
return self._proc_builtin(tarfile)
def _proc_builtin(self, tarfile):
"""Process a builtin type or an unknown type which
will be treated as a regular file.
"""
self.offset_data = tarfile.fileobj.tell()
offset = self.offset_data
if self.isreg() or self.type not in SUPPORTED_TYPES:
# Skip the following data blocks.
offset += self._block(self.size)
tarfile.offset = offset
# Patch the TarInfo object with saved global
# header information.
self._apply_pax_info(tarfile.pax_headers, tarfile.encoding, tarfile.errors)
# Remove redundant slashes from directories. This is to be consistent
# with frombuf().
if self.isdir():
self.name = self.name.rstrip("/")
return self
def _proc_gnulong(self, tarfile):
"""Process the blocks that hold a GNU longname
or longlink member.
"""
buf = tarfile.fileobj.read(self._block(self.size))
# Fetch the next header and process it.
try:
next = self.fromtarfile(tarfile)
except HeaderError as e:
raise SubsequentHeaderError(str(e)) from None
# Patch the TarInfo object from the next header with
# the longname information.
next.offset = self.offset
if self.type == GNUTYPE_LONGNAME:
next.name = nts(buf, tarfile.encoding, tarfile.errors)
elif self.type == GNUTYPE_LONGLINK:
next.linkname = nts(buf, tarfile.encoding, tarfile.errors)
# Remove redundant slashes from directories. This is to be consistent
# with frombuf().
if next.isdir():
next.name = next.name.removesuffix("/")
return next
def _proc_sparse(self, tarfile):
"""Process a GNU sparse header plus extra headers.
"""
# We already collected some sparse structures in frombuf().
structs, isextended, origsize = self._sparse_structs
del self._sparse_structs
# Collect sparse structures from extended header blocks.
while isextended:
buf = tarfile.fileobj.read(BLOCKSIZE)
pos = 0
for i in range(21):
try:
offset = nti(buf[pos:pos + 12])
numbytes = nti(buf[pos + 12:pos + 24])
except ValueError:
break
if offset and numbytes:
structs.append((offset, numbytes))
pos += 24
isextended = bool(buf[504])
self.sparse = structs
self.offset_data = tarfile.fileobj.tell()
tarfile.offset = self.offset_data + self._block(self.size)
self.size = origsize
return self
def _proc_pax(self, tarfile):
"""Process an extended or global header as described in
POSIX.1-2008.
"""
# Read the header information.
buf = tarfile.fileobj.read(self._block(self.size))
# A pax header stores supplemental information for either
# the following file (extended) or all following files
# (global).
if self.type == XGLTYPE:
pax_headers = tarfile.pax_headers
else:
pax_headers = tarfile.pax_headers.copy()
# Check if the pax header contains a hdrcharset field. This tells us
# the encoding of the path, linkpath, uname and gname fields. Normally,
# these fields are UTF-8 encoded but since POSIX.1-2008 tar
# implementations are allowed to store them as raw binary strings if
# the translation to UTF-8 fails.
match = re.search(br"\d+ hdrcharset=([^\n]+)\n", buf)
if match is not None:
pax_headers["hdrcharset"] = match.group(1).decode("utf-8")
# For the time being, we don't care about anything other than "BINARY".
# The only other value that is currently allowed by the standard is
# "ISO-IR 10646 2000 UTF-8" in other words UTF-8.
hdrcharset = pax_headers.get("hdrcharset")
if hdrcharset == "BINARY":
encoding = tarfile.encoding
else:
encoding = "utf-8"
# Parse pax header information. A record looks like that:
# "%d %s=%s\n" % (length, keyword, value). length is the size
# of the complete record including the length field itself and
# the newline. keyword and value are both UTF-8 encoded strings.
regex = re.compile(br"(\d+) ([^=]+)=")
pos = 0
while True:
match = regex.match(buf, pos)
if not match:
break
length, keyword = match.groups()
length = int(length)
if length == 0:
raise InvalidHeaderError("invalid header")
value = buf[match.end(2) + 1:match.start(1) + length - 1]
# Normally, we could just use "utf-8" as the encoding and "strict"
# as the error handler, but we better not take the risk. For
# example, GNU tar <= 1.23 is known to store filenames it cannot
# translate to UTF-8 as raw strings (unfortunately without a
# hdrcharset=BINARY header).
# We first try the strict standard encoding, and if that fails we
# fall back on the user's encoding and error handler.
keyword = self._decode_pax_field(keyword, "utf-8", "utf-8",
tarfile.errors)
if keyword in PAX_NAME_FIELDS:
value = self._decode_pax_field(value, encoding, tarfile.encoding,
tarfile.errors)
else:
value = self._decode_pax_field(value, "utf-8", "utf-8",
tarfile.errors)
pax_headers[keyword] = value
pos += length
# Fetch the next header.
try:
next = self.fromtarfile(tarfile)
except HeaderError as e:
raise SubsequentHeaderError(str(e)) from None
# Process GNU sparse information.
if "GNU.sparse.map" in pax_headers:
# GNU extended sparse format version 0.1.
self._proc_gnusparse_01(next, pax_headers)
elif "GNU.sparse.size" in pax_headers:
# GNU extended sparse format version 0.0.
self._proc_gnusparse_00(next, pax_headers, buf)
elif pax_headers.get("GNU.sparse.major") == "1" and pax_headers.get("GNU.sparse.minor") == "0":
# GNU extended sparse format version 1.0.
self._proc_gnusparse_10(next, pax_headers, tarfile)
if self.type in (XHDTYPE, SOLARIS_XHDTYPE):
# Patch the TarInfo object with the extended header info.
next._apply_pax_info(pax_headers, tarfile.encoding, tarfile.errors)
next.offset = self.offset
if "size" in pax_headers:
# If the extended header replaces the size field,
# we need to recalculate the offset where the next
# header starts.
offset = next.offset_data
if next.isreg() or next.type not in SUPPORTED_TYPES:
offset += next._block(next.size)
tarfile.offset = offset
return next
def _proc_gnusparse_00(self, next, pax_headers, buf):
"""Process a GNU tar extended sparse header, version 0.0.
"""
offsets = []
for match in re.finditer(br"\d+ GNU.sparse.offset=(\d+)\n", buf):
offsets.append(int(match.group(1)))
numbytes = []
for match in re.finditer(br"\d+ GNU.sparse.numbytes=(\d+)\n", buf):
numbytes.append(int(match.group(1)))
next.sparse = list(zip(offsets, numbytes))
def _proc_gnusparse_01(self, next, pax_headers):
"""Process a GNU tar extended sparse header, version 0.1.
"""
sparse = [int(x) for x in pax_headers["GNU.sparse.map"].split(",")]
next.sparse = list(zip(sparse[::2], sparse[1::2]))
def _proc_gnusparse_10(self, next, pax_headers, tarfile):
"""Process a GNU tar extended sparse header, version 1.0.
"""
fields = None
sparse = []
buf = tarfile.fileobj.read(BLOCKSIZE)
fields, buf = buf.split(b"\n", 1)
fields = int(fields)
while len(sparse) < fields * 2:
if b"\n" not in buf:
buf += tarfile.fileobj.read(BLOCKSIZE)
number, buf = buf.split(b"\n", 1)
sparse.append(int(number))
next.offset_data = tarfile.fileobj.tell()
next.sparse = list(zip(sparse[::2], sparse[1::2]))
def _apply_pax_info(self, pax_headers, encoding, errors):
"""Replace fields with supplemental information from a previous
pax extended or global header.
"""
for keyword, value in pax_headers.items():
if keyword == "GNU.sparse.name":
setattr(self, "path", value)
elif keyword == "GNU.sparse.size":
setattr(self, "size", int(value))
elif keyword == "GNU.sparse.realsize":
setattr(self, "size", int(value))
elif keyword in PAX_FIELDS:
if keyword in PAX_NUMBER_FIELDS:
try:
value = PAX_NUMBER_FIELDS[keyword](value)
except ValueError:
value = 0
if keyword == "path":
value = value.rstrip("/")
setattr(self, keyword, value)
self.pax_headers = pax_headers.copy()
def _decode_pax_field(self, value, encoding, fallback_encoding, fallback_errors):
"""Decode a single field from a pax record.
"""
try:
return value.decode(encoding, "strict")
except UnicodeDecodeError:
return value.decode(fallback_encoding, fallback_errors)
def _block(self, count):
"""Round up a byte count by BLOCKSIZE and return it,
e.g. _block(834) => 1024.
"""
blocks, remainder = divmod(count, BLOCKSIZE)
if remainder:
blocks += 1
return blocks * BLOCKSIZE
def isreg(self):
'Return True if the Tarinfo object is a regular file.'
return self.type in REGULAR_TYPES
def isfile(self):
'Return True if the Tarinfo object is a regular file.'
return self.isreg()
def isdir(self):
'Return True if it is a directory.'
return self.type == DIRTYPE
def issym(self):
'Return True if it is a symbolic link.'
return self.type == SYMTYPE
def islnk(self):
'Return True if it is a hard link.'
return self.type == LNKTYPE
def ischr(self):
'Return True if it is a character device.'
return self.type == CHRTYPE
def isblk(self):
'Return True if it is a block device.'
return self.type == BLKTYPE
def isfifo(self):
'Return True if it is a FIFO.'
return self.type == FIFOTYPE
def issparse(self):
return self.sparse is not None
def isdev(self):
'Return True if it is one of character device, block device or FIFO.'
return self.type in (CHRTYPE, BLKTYPE, FIFOTYPE)
# class TarInfo
class TarFile(object):
"""The TarFile Class provides an interface to tar archives.
"""
debug = 0 # May be set from 0 (no msgs) to 3 (all msgs)
dereference = False # If true, add content of linked file to the
# tar file, else the link.
ignore_zeros = False # If true, skips empty or invalid blocks and
# continues processing.
errorlevel = 1 # If 0, fatal errors only appear in debug
# messages (if debug >= 0). If > 0, errors
# are passed to the caller as exceptions.
format = DEFAULT_FORMAT # The format to use when creating an archive.
encoding = ENCODING # Encoding for 8-bit character strings.
errors = None # Error handler for unicode conversion.
tarinfo = TarInfo # The default TarInfo class to use.
fileobject = ExFileObject # The file-object for extractfile().
def __init__(self, name=None, mode="r", fileobj=None, format=None,
tarinfo=None, dereference=None, ignore_zeros=None, encoding=None,
errors="surrogateescape", pax_headers=None, debug=None,
errorlevel=None, copybufsize=None):
"""Open an (uncompressed) tar archive `name'. `mode' is either 'r' to
read from an existing archive, 'a' to append data to an existing
file or 'w' to create a new file overwriting an existing one. `mode'
defaults to 'r'.
If `fileobj' is given, it is used for reading or writing data. If it
can be determined, `mode' is overridden by `fileobj's mode.
`fileobj' is not closed, when TarFile is closed.
"""
modes = {"r": "rb", "a": "r+b", "w": "wb", "x": "xb"}
if mode not in modes:
raise ValueError("mode must be 'r', 'a', 'w' or 'x'")
self.mode = mode
self._mode = modes[mode]
if not fileobj:
if self.mode == "a" and not os.path.exists(name):
# Create nonexistent files in append mode.
self.mode = "w"
self._mode = "wb"
fileobj = bltn_open(name, self._mode)
self._extfileobj = False
else:
if (name is None and hasattr(fileobj, "name") and
isinstance(fileobj.name, (str, bytes))):
name = fileobj.name
if hasattr(fileobj, "mode"):
self._mode = fileobj.mode
self._extfileobj = True
self.name = os.path.abspath(name) if name else None
self.fileobj = fileobj
# Init attributes.
if format is not None:
self.format = format
if tarinfo is not None:
self.tarinfo = tarinfo
if dereference is not None:
self.dereference = dereference
if ignore_zeros is not None:
self.ignore_zeros = ignore_zeros
if encoding is not None:
self.encoding = encoding
self.errors = errors
if pax_headers is not None and self.format == PAX_FORMAT:
self.pax_headers = pax_headers
else:
self.pax_headers = {}
if debug is not None:
self.debug = debug
if errorlevel is not None:
self.errorlevel = errorlevel
# Init datastructures.
self.copybufsize = copybufsize
self.closed = False
self.members = [] # list of members as TarInfo objects
self._loaded = False # flag if all members have been read
self.offset = self.fileobj.tell()
# current position in the archive file
self.inodes = {} # dictionary caching the inodes of
# archive members already added
try:
if self.mode == "r":
self.firstmember = None
self.firstmember = self.next()
if self.mode == "a":
# Move to the end of the archive,
# before the first empty block.
while True:
self.fileobj.seek(self.offset)
try:
tarinfo = self.tarinfo.fromtarfile(self)
self.members.append(tarinfo)
except EOFHeaderError:
self.fileobj.seek(self.offset)
break
except HeaderError as e:
raise ReadError(str(e)) from None
if self.mode in ("a", "w", "x"):
self._loaded = True
if self.pax_headers:
buf = self.tarinfo.create_pax_global_header(self.pax_headers.copy())
self.fileobj.write(buf)
self.offset += len(buf)
except:
if not self._extfileobj:
self.fileobj.close()
self.closed = True
raise
#--------------------------------------------------------------------------
# Below are the classmethods which act as alternate constructors to the
# TarFile class. The open() method is the only one that is needed for
# public use; it is the "super"-constructor and is able to select an
# adequate "sub"-constructor for a particular compression using the mapping
# from OPEN_METH.
#
# This concept allows one to subclass TarFile without losing the comfort of
# the super-constructor. A sub-constructor is registered and made available
# by adding it to the mapping in OPEN_METH.
@classmethod
def open(cls, name=None, mode="r", fileobj=None, bufsize=RECORDSIZE, **kwargs):
"""Open a tar archive for reading, writing or appending. Return
an appropriate TarFile class.
mode:
'r' or 'r:*' open for reading with transparent compression
'r:' open for reading exclusively uncompressed
'r:gz' open for reading with gzip compression
'r:bz2' open for reading with bzip2 compression
'r:xz' open for reading with lzma compression
'a' or 'a:' open for appending, creating the file if necessary
'w' or 'w:' open for writing without compression
'w:gz' open for writing with gzip compression
'w:bz2' open for writing with bzip2 compression
'w:xz' open for writing with lzma compression
'x' or 'x:' create a tarfile exclusively without compression, raise
an exception if the file is already created
'x:gz' create a gzip compressed tarfile, raise an exception
if the file is already created
'x:bz2' create a bzip2 compressed tarfile, raise an exception
if the file is already created
'x:xz' create an lzma compressed tarfile, raise an exception
if the file is already created
'r|*' open a stream of tar blocks with transparent compression
'r|' open an uncompressed stream of tar blocks for reading
'r|gz' open a gzip compressed stream of tar blocks
'r|bz2' open a bzip2 compressed stream of tar blocks
'r|xz' open an lzma compressed stream of tar blocks
'w|' open an uncompressed stream for writing
'w|gz' open a gzip compressed stream for writing
'w|bz2' open a bzip2 compressed stream for writing
'w|xz' open an lzma compressed stream for writing
"""
if not name and not fileobj:
raise ValueError("nothing to open")
if mode in ("r", "r:*"):
# Find out which *open() is appropriate for opening the file.
def not_compressed(comptype):
return cls.OPEN_METH[comptype] == 'taropen'
error_msgs = []
for comptype in sorted(cls.OPEN_METH, key=not_compressed):
func = getattr(cls, cls.OPEN_METH[comptype])
if fileobj is not None:
saved_pos = fileobj.tell()
try:
return func(name, "r", fileobj, **kwargs)
except (ReadError, CompressionError) as e:
error_msgs.append(f'- method {comptype}: {e!r}')
if fileobj is not None:
fileobj.seek(saved_pos)
continue
error_msgs_summary = '\n'.join(error_msgs)
raise ReadError(f"file could not be opened successfully:\n{error_msgs_summary}")
elif ":" in mode:
filemode, comptype = mode.split(":", 1)
filemode = filemode or "r"
comptype = comptype or "tar"
# Select the *open() function according to
# given compression.
if comptype in cls.OPEN_METH:
func = getattr(cls, cls.OPEN_METH[comptype])
else:
raise CompressionError("unknown compression type %r" % comptype)
return func(name, filemode, fileobj, **kwargs)
elif "|" in mode:
filemode, comptype = mode.split("|", 1)
filemode = filemode or "r"
comptype = comptype or "tar"
if filemode not in ("r", "w"):
raise ValueError("mode must be 'r' or 'w'")
stream = _Stream(name, filemode, comptype, fileobj, bufsize)
try:
t = cls(name, filemode, stream, **kwargs)
except:
stream.close()
raise
t._extfileobj = False
return t
elif mode in ("a", "w", "x"):
return cls.taropen(name, mode, fileobj, **kwargs)
raise ValueError("undiscernible mode")
@classmethod
def taropen(cls, name, mode="r", fileobj=None, **kwargs):
"""Open uncompressed tar archive name for reading or writing.
"""
if mode not in ("r", "a", "w", "x"):
raise ValueError("mode must be 'r', 'a', 'w' or 'x'")
return cls(name, mode, fileobj, **kwargs)
@classmethod
def gzopen(cls, name, mode="r", fileobj=None, compresslevel=9, **kwargs):
"""Open gzip compressed tar archive name for reading or writing.
Appending is not allowed.
"""
if mode not in ("r", "w", "x"):
raise ValueError("mode must be 'r', 'w' or 'x'")
try:
from gzip import GzipFile
except ImportError:
raise CompressionError("gzip module is not available") from None
try:
fileobj = GzipFile(name, mode + "b", compresslevel, fileobj)
except OSError as e:
if fileobj is not None and mode == 'r':
raise ReadError("not a gzip file") from e
raise
try:
t = cls.taropen(name, mode, fileobj, **kwargs)
except OSError as e:
fileobj.close()
if mode == 'r':
raise ReadError("not a gzip file") from e
raise
except:
fileobj.close()
raise
t._extfileobj = False
return t
@classmethod
def bz2open(cls, name, mode="r", fileobj=None, compresslevel=9, **kwargs):
"""Open bzip2 compressed tar archive name for reading or writing.
Appending is not allowed.
"""
if mode not in ("r", "w", "x"):
raise ValueError("mode must be 'r', 'w' or 'x'")
try:
from bz2 import BZ2File
except ImportError:
raise CompressionError("bz2 module is not available") from None
fileobj = BZ2File(fileobj or name, mode, compresslevel=compresslevel)
try:
t = cls.taropen(name, mode, fileobj, **kwargs)
except (OSError, EOFError) as e:
fileobj.close()
if mode == 'r':
raise ReadError("not a bzip2 file") from e
raise
except:
fileobj.close()
raise
t._extfileobj = False
return t
@classmethod
def xzopen(cls, name, mode="r", fileobj=None, preset=None, **kwargs):
"""Open lzma compressed tar archive name for reading or writing.
Appending is not allowed.
"""
if mode not in ("r", "w", "x"):
raise ValueError("mode must be 'r', 'w' or 'x'")
try:
from lzma import LZMAFile, LZMAError
except ImportError:
raise CompressionError("lzma module is not available") from None
fileobj = LZMAFile(fileobj or name, mode, preset=preset)
try:
t = cls.taropen(name, mode, fileobj, **kwargs)
except (LZMAError, EOFError) as e:
fileobj.close()
if mode == 'r':
raise ReadError("not an lzma file") from e
raise
except:
fileobj.close()
raise
t._extfileobj = False
return t
# All *open() methods are registered here.
OPEN_METH = {
"tar": "taropen", # uncompressed tar
"gz": "gzopen", # gzip compressed tar
"bz2": "bz2open", # bzip2 compressed tar
"xz": "xzopen" # lzma compressed tar
}
#--------------------------------------------------------------------------
# The public methods which TarFile provides:
def close(self):
"""Close the TarFile. In write-mode, two finishing zero blocks are
appended to the archive.
"""
if self.closed:
return
self.closed = True
try:
if self.mode in ("a", "w", "x"):
self.fileobj.write(NUL * (BLOCKSIZE * 2))
self.offset += (BLOCKSIZE * 2)
# fill up the end with zero-blocks
# (like option -b20 for tar does)
blocks, remainder = divmod(self.offset, RECORDSIZE)
if remainder > 0:
self.fileobj.write(NUL * (RECORDSIZE - remainder))
finally:
if not self._extfileobj:
self.fileobj.close()
def getmember(self, name):
"""Return a TarInfo object for member `name'. If `name' can not be
found in the archive, KeyError is raised. If a member occurs more
than once in the archive, its last occurrence is assumed to be the
most up-to-date version.
"""
tarinfo = self._getmember(name.rstrip('/'))
if tarinfo is None:
raise KeyError("filename %r not found" % name)
return tarinfo
def getmembers(self):
"""Return the members of the archive as a list of TarInfo objects. The
list has the same order as the members in the archive.
"""
self._check()
if not self._loaded: # if we want to obtain a list of
self._load() # all members, we first have to
# scan the whole archive.
return self.members
def getnames(self):
"""Return the members of the archive as a list of their names. It has
the same order as the list returned by getmembers().
"""
return [tarinfo.name for tarinfo in self.getmembers()]
def gettarinfo(self, name=None, arcname=None, fileobj=None):
"""Create a TarInfo object from the result of os.stat or equivalent
on an existing file. The file is either named by `name', or
specified as a file object `fileobj' with a file descriptor. If
given, `arcname' specifies an alternative name for the file in the
archive, otherwise, the name is taken from the 'name' attribute of
'fileobj', or the 'name' argument. The name should be a text
string.
"""
self._check("awx")
# When fileobj is given, replace name by
# fileobj's real name.
if fileobj is not None:
name = fileobj.name
# Building the name of the member in the archive.
# Backward slashes are converted to forward slashes,
# Absolute paths are turned to relative paths.
if arcname is None:
arcname = name
drv, arcname = os.path.splitdrive(arcname)
arcname = arcname.replace(os.sep, "/")
arcname = arcname.lstrip("/")
# Now, fill the TarInfo object with
# information specific for the file.
tarinfo = self.tarinfo()
tarinfo.tarfile = self # Not needed
# Use os.stat or os.lstat, depending on if symlinks shall be resolved.
if fileobj is None:
if not self.dereference:
statres = os.lstat(name)
else:
statres = os.stat(name)
else:
statres = os.fstat(fileobj.fileno())
linkname = ""
stmd = statres.st_mode
if stat.S_ISREG(stmd):
inode = (statres.st_ino, statres.st_dev)
if not self.dereference and statres.st_nlink > 1 and \
inode in self.inodes and arcname != self.inodes[inode]:
# Is it a hardlink to an already
# archived file?
type = LNKTYPE
linkname = self.inodes[inode]
else:
# The inode is added only if its valid.
# For win32 it is always 0.
type = REGTYPE
if inode[0]:
self.inodes[inode] = arcname
elif stat.S_ISDIR(stmd):
type = DIRTYPE
elif stat.S_ISFIFO(stmd):
type = FIFOTYPE
elif stat.S_ISLNK(stmd):
type = SYMTYPE
linkname = os.readlink(name)
elif stat.S_ISCHR(stmd):
type = CHRTYPE
elif stat.S_ISBLK(stmd):
type = BLKTYPE
else:
return None
# Fill the TarInfo object with all
# information we can get.
tarinfo.name = arcname
tarinfo.mode = stmd
tarinfo.uid = statres.st_uid
tarinfo.gid = statres.st_gid
if type == REGTYPE:
tarinfo.size = statres.st_size
else:
tarinfo.size = 0
tarinfo.mtime = statres.st_mtime
tarinfo.type = type
tarinfo.linkname = linkname
if pwd:
try:
tarinfo.uname = pwd.getpwuid(tarinfo.uid)[0]
except KeyError:
pass
if grp:
try:
tarinfo.gname = grp.getgrgid(tarinfo.gid)[0]
except KeyError:
pass
if type in (CHRTYPE, BLKTYPE):
if hasattr(os, "major") and hasattr(os, "minor"):
tarinfo.devmajor = os.major(statres.st_rdev)
tarinfo.devminor = os.minor(statres.st_rdev)
return tarinfo
def list(self, verbose=True, *, members=None):
"""Print a table of contents to sys.stdout. If `verbose' is False, only
the names of the members are printed. If it is True, an `ls -l'-like
output is produced. `members' is optional and must be a subset of the
list returned by getmembers().
"""
self._check()
if members is None:
members = self
for tarinfo in members:
if verbose:
_safe_print(stat.filemode(tarinfo.mode))
_safe_print("%s/%s" % (tarinfo.uname or tarinfo.uid,
tarinfo.gname or tarinfo.gid))
if tarinfo.ischr() or tarinfo.isblk():
_safe_print("%10s" %
("%d,%d" % (tarinfo.devmajor, tarinfo.devminor)))
else:
_safe_print("%10d" % tarinfo.size)
_safe_print("%d-%02d-%02d %02d:%02d:%02d" \
% time.localtime(tarinfo.mtime)[:6])
_safe_print(tarinfo.name + ("/" if tarinfo.isdir() else ""))
if verbose:
if tarinfo.issym():
_safe_print("-> " + tarinfo.linkname)
if tarinfo.islnk():
_safe_print("link to " + tarinfo.linkname)
print()
def add(self, name, arcname=None, recursive=True, *, filter=None):
"""Add the file `name' to the archive. `name' may be any type of file
(directory, fifo, symbolic link, etc.). If given, `arcname'
specifies an alternative name for the file in the archive.
Directories are added recursively by default. This can be avoided by
setting `recursive' to False. `filter' is a function
that expects a TarInfo object argument and returns the changed
TarInfo object, if it returns None the TarInfo object will be
excluded from the archive.
"""
self._check("awx")
if arcname is None:
arcname = name
# Skip if somebody tries to archive the archive...
if self.name is not None and os.path.abspath(name) == self.name:
self._dbg(2, "tarfile: Skipped %r" % name)
return
self._dbg(1, name)
# Create a TarInfo object from the file.
tarinfo = self.gettarinfo(name, arcname)
if tarinfo is None:
self._dbg(1, "tarfile: Unsupported type %r" % name)
return
# Change or exclude the TarInfo object.
if filter is not None:
tarinfo = filter(tarinfo)
if tarinfo is None:
self._dbg(2, "tarfile: Excluded %r" % name)
return
# Append the tar header and data to the archive.
if tarinfo.isreg():
with bltn_open(name, "rb") as f:
self.addfile(tarinfo, f)
elif tarinfo.isdir():
self.addfile(tarinfo)
if recursive:
for f in sorted(os.listdir(name)):
self.add(os.path.join(name, f), os.path.join(arcname, f),
recursive, filter=filter)
else:
self.addfile(tarinfo)
def addfile(self, tarinfo, fileobj=None):
"""Add the TarInfo object `tarinfo' to the archive. If `fileobj' is
given, it should be a binary file, and tarinfo.size bytes are read
from it and added to the archive. You can create TarInfo objects
directly, or by using gettarinfo().
"""
self._check("awx")
tarinfo = copy.copy(tarinfo)
buf = tarinfo.tobuf(self.format, self.encoding, self.errors)
self.fileobj.write(buf)
self.offset += len(buf)
bufsize=self.copybufsize
# If there's data to follow, append it.
if fileobj is not None:
copyfileobj(fileobj, self.fileobj, tarinfo.size, bufsize=bufsize)
blocks, remainder = divmod(tarinfo.size, BLOCKSIZE)
if remainder > 0:
self.fileobj.write(NUL * (BLOCKSIZE - remainder))
blocks += 1
self.offset += blocks * BLOCKSIZE
self.members.append(tarinfo)
def extractall(self, path=".", members=None, *, numeric_owner=False):
"""Extract all members from the archive to the current working
directory and set owner, modification time and permissions on
directories afterwards. `path' specifies a different directory
to extract to. `members' is optional and must be a subset of the
list returned by getmembers(). If `numeric_owner` is True, only
the numbers for user/group names are used and not the names.
"""
directories = []
if members is None:
members = self
for tarinfo in members:
if tarinfo.isdir():
# Extract directories with a safe mode.
directories.append(tarinfo)
tarinfo = copy.copy(tarinfo)
tarinfo.mode = 0o700
# Do not set_attrs directories, as we will do that further down
self.extract(tarinfo, path, set_attrs=not tarinfo.isdir(),
numeric_owner=numeric_owner)
# Reverse sort directories.
directories.sort(key=lambda a: a.name)
directories.reverse()
# Set correct owner, mtime and filemode on directories.
for tarinfo in directories:
dirpath = os.path.join(path, tarinfo.name)
try:
self.chown(tarinfo, dirpath, numeric_owner=numeric_owner)
self.utime(tarinfo, dirpath)
self.chmod(tarinfo, dirpath)
except ExtractError as e:
if self.errorlevel > 1:
raise
else:
self._dbg(1, "tarfile: %s" % e)
def extract(self, member, path="", set_attrs=True, *, numeric_owner=False):
"""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 TarInfo object. You can
specify a different directory using `path'. File attributes (owner,
mtime, mode) are set unless `set_attrs' is False. If `numeric_owner`
is True, only the numbers for user/group names are used and not
the names.
"""
self._check("r")
if isinstance(member, str):
tarinfo = self.getmember(member)
else:
tarinfo = member
# Prepare the link target for makelink().
if tarinfo.islnk():
tarinfo._link_target = os.path.join(path, tarinfo.linkname)
try:
self._extract_member(tarinfo, os.path.join(path, tarinfo.name),
set_attrs=set_attrs,
numeric_owner=numeric_owner)
except OSError as e:
if self.errorlevel > 0:
raise
else:
if e.filename is None:
self._dbg(1, "tarfile: %s" % e.strerror)
else:
self._dbg(1, "tarfile: %s %r" % (e.strerror, e.filename))
except ExtractError as e:
if self.errorlevel > 1:
raise
else:
self._dbg(1, "tarfile: %s" % e)
def extractfile(self, member):
"""Extract a member from the archive as a file object. `member' may be
a filename or a TarInfo object. If `member' is a regular file or
a link, an io.BufferedReader object is returned. For all other
existing members, None is returned. If `member' does not appear
in the archive, KeyError is raised.
"""
self._check("r")
if isinstance(member, str):
tarinfo = self.getmember(member)
else:
tarinfo = member
if tarinfo.isreg() or tarinfo.type not in SUPPORTED_TYPES:
# Members with unknown types are treated as regular files.
return self.fileobject(self, tarinfo)
elif tarinfo.islnk() or tarinfo.issym():
if isinstance(self.fileobj, _Stream):
# A small but ugly workaround for the case that someone tries
# to extract a (sym)link as a file-object from a non-seekable
# stream of tar blocks.
raise StreamError("cannot extract (sym)link as file object")
else:
# A (sym)link's file object is its target's file object.
return self.extractfile(self._find_link_target(tarinfo))
else:
# If there's no data associated with the member (directory, chrdev,
# blkdev, etc.), return None instead of a file object.
return None
def _extract_member(self, tarinfo, targetpath, set_attrs=True,
numeric_owner=False):
"""Extract the TarInfo object tarinfo to a physical
file called targetpath.
"""
# Fetch the TarInfo object for the given name
# and build the destination pathname, replacing
# forward slashes to platform specific separators.
targetpath = targetpath.rstrip("/")
targetpath = targetpath.replace("/", os.sep)
# Create all upper directories.
upperdirs = os.path.dirname(targetpath)
if upperdirs and not os.path.exists(upperdirs):
# Create directories that are not part of the archive with
# default permissions.
os.makedirs(upperdirs)
if tarinfo.islnk() or tarinfo.issym():
self._dbg(1, "%s -> %s" % (tarinfo.name, tarinfo.linkname))
else:
self._dbg(1, tarinfo.name)
if tarinfo.isreg():
self.makefile(tarinfo, targetpath)
elif tarinfo.isdir():
self.makedir(tarinfo, targetpath)
elif tarinfo.isfifo():
self.makefifo(tarinfo, targetpath)
elif tarinfo.ischr() or tarinfo.isblk():
self.makedev(tarinfo, targetpath)
elif tarinfo.islnk() or tarinfo.issym():
self.makelink(tarinfo, targetpath)
elif tarinfo.type not in SUPPORTED_TYPES:
self.makeunknown(tarinfo, targetpath)
else:
self.makefile(tarinfo, targetpath)
if set_attrs:
self.chown(tarinfo, targetpath, numeric_owner)
if not tarinfo.issym():
self.chmod(tarinfo, targetpath)
self.utime(tarinfo, targetpath)
#--------------------------------------------------------------------------
# Below are the different file methods. They are called via
# _extract_member() when extract() is called. They can be replaced in a
# subclass to implement other functionality.
def makedir(self, tarinfo, targetpath):
"""Make a directory called targetpath.
"""
try:
# Use a safe mode for the directory, the real mode is set
# later in _extract_member().
os.mkdir(targetpath, 0o700)
except FileExistsError:
pass
def makefile(self, tarinfo, targetpath):
"""Make a file called targetpath.
"""
source = self.fileobj
source.seek(tarinfo.offset_data)
bufsize = self.copybufsize
with bltn_open(targetpath, "wb") as target:
if tarinfo.sparse is not None:
for offset, size in tarinfo.sparse:
target.seek(offset)
copyfileobj(source, target, size, ReadError, bufsize)
target.seek(tarinfo.size)
target.truncate()
else:
copyfileobj(source, target, tarinfo.size, ReadError, bufsize)
def makeunknown(self, tarinfo, targetpath):
"""Make a file from a TarInfo object with an unknown type
at targetpath.
"""
self.makefile(tarinfo, targetpath)
self._dbg(1, "tarfile: Unknown file type %r, " \
"extracted as regular file." % tarinfo.type)
def makefifo(self, tarinfo, targetpath):
"""Make a fifo called targetpath.
"""
if hasattr(os, "mkfifo"):
os.mkfifo(targetpath)
else:
raise ExtractError("fifo not supported by system")
def makedev(self, tarinfo, targetpath):
"""Make a character or block device called targetpath.
"""
if not hasattr(os, "mknod") or not hasattr(os, "makedev"):
raise ExtractError("special devices not supported by system")
mode = tarinfo.mode
if tarinfo.isblk():
mode |= stat.S_IFBLK
else:
mode |= stat.S_IFCHR
os.mknod(targetpath, mode,
os.makedev(tarinfo.devmajor, tarinfo.devminor))
def makelink(self, tarinfo, targetpath):
"""Make a (symbolic) link called targetpath. If it cannot be created
(platform limitation), we try to make a copy of the referenced file
instead of a link.
"""
try:
# For systems that support symbolic and hard links.
if tarinfo.issym():
if os.path.lexists(targetpath):
# Avoid FileExistsError on following os.symlink.
os.unlink(targetpath)
os.symlink(tarinfo.linkname, targetpath)
else:
# See extract().
if os.path.exists(tarinfo._link_target):
os.link(tarinfo._link_target, targetpath)
else:
self._extract_member(self._find_link_target(tarinfo),
targetpath)
except symlink_exception:
try:
self._extract_member(self._find_link_target(tarinfo),
targetpath)
except KeyError:
raise ExtractError("unable to resolve link inside archive") from None
def chown(self, tarinfo, targetpath, numeric_owner):
"""Set owner of targetpath according to tarinfo. If numeric_owner
is True, use .gid/.uid instead of .gname/.uname. If numeric_owner
is False, fall back to .gid/.uid when the search based on name
fails.
"""
if hasattr(os, "geteuid") and os.geteuid() == 0:
# We have to be root to do so.
g = tarinfo.gid
u = tarinfo.uid
if not numeric_owner:
try:
if grp:
g = grp.getgrnam(tarinfo.gname)[2]
except KeyError:
pass
try:
if pwd:
u = pwd.getpwnam(tarinfo.uname)[2]
except KeyError:
pass
try:
if tarinfo.issym() and hasattr(os, "lchown"):
os.lchown(targetpath, u, g)
else:
os.chown(targetpath, u, g)
except OSError as e:
raise ExtractError("could not change owner") from e
def chmod(self, tarinfo, targetpath):
"""Set file permissions of targetpath according to tarinfo.
"""
try:
os.chmod(targetpath, tarinfo.mode)
except OSError as e:
raise ExtractError("could not change mode") from e
def utime(self, tarinfo, targetpath):
"""Set modification time of targetpath according to tarinfo.
"""
if not hasattr(os, 'utime'):
return
try:
os.utime(targetpath, (tarinfo.mtime, tarinfo.mtime))
except OSError as e:
raise ExtractError("could not change modification time") from e
#--------------------------------------------------------------------------
def next(self):
"""Return the next member of the archive as a TarInfo object, when
TarFile is opened for reading. Return None if there is no more
available.
"""
self._check("ra")
if self.firstmember is not None:
m = self.firstmember
self.firstmember = None
return m
# Advance the file pointer.
if self.offset != self.fileobj.tell():
self.fileobj.seek(self.offset - 1)
if not self.fileobj.read(1):
raise ReadError("unexpected end of data")
# Read the next block.
tarinfo = None
while True:
try:
tarinfo = self.tarinfo.fromtarfile(self)
except EOFHeaderError as e:
if self.ignore_zeros:
self._dbg(2, "0x%X: %s" % (self.offset, e))
self.offset += BLOCKSIZE
continue
except InvalidHeaderError as e:
if self.ignore_zeros:
self._dbg(2, "0x%X: %s" % (self.offset, e))
self.offset += BLOCKSIZE
continue
elif self.offset == 0:
raise ReadError(str(e)) from None
except EmptyHeaderError:
if self.offset == 0:
raise ReadError("empty file") from None
except TruncatedHeaderError as e:
if self.offset == 0:
raise ReadError(str(e)) from None
except SubsequentHeaderError as e:
raise ReadError(str(e)) from None
except Exception as e:
try:
import zlib
if isinstance(e, zlib.error):
raise ReadError(f'zlib error: {e}') from None
else:
raise e
except ImportError:
raise e
break
if tarinfo is not None:
self.members.append(tarinfo)
else:
self._loaded = True
return tarinfo
#--------------------------------------------------------------------------
# Little helper methods:
def _getmember(self, name, tarinfo=None, normalize=False):
"""Find an archive member by name from bottom to top.
If tarinfo is given, it is used as the starting point.
"""
# Ensure that all members have been loaded.
members = self.getmembers()
# Limit the member search list up to tarinfo.
if tarinfo is not None:
members = members[:members.index(tarinfo)]
if normalize:
name = os.path.normpath(name)
for member in reversed(members):
if normalize:
member_name = os.path.normpath(member.name)
else:
member_name = member.name
if name == member_name:
return member
def _load(self):
"""Read through the entire archive file and look for readable
members.
"""
while True:
tarinfo = self.next()
if tarinfo is None:
break
self._loaded = True
def _check(self, mode=None):
"""Check if TarFile is still open, and if the operation's mode
corresponds to TarFile's mode.
"""
if self.closed:
raise OSError("%s is closed" % self.__class__.__name__)
if mode is not None and self.mode not in mode:
raise OSError("bad operation for mode %r" % self.mode)
def _find_link_target(self, tarinfo):
"""Find the target member of a symlink or hardlink member in the
archive.
"""
if tarinfo.issym():
# Always search the entire archive.
linkname = "/".join(filter(None, (os.path.dirname(tarinfo.name), tarinfo.linkname)))
limit = None
else:
# Search the archive before the link, because a hard link is
# just a reference to an already archived file.
linkname = tarinfo.linkname
limit = tarinfo
member = self._getmember(linkname, tarinfo=limit, normalize=True)
if member is None:
raise KeyError("linkname %r not found" % linkname)
return member
def __iter__(self):
"""Provide an iterator object.
"""
if self._loaded:
yield from self.members
return
# Yield items using TarFile's next() method.
# When all members have been read, set TarFile as _loaded.
index = 0
# Fix for SF #1100429: Under rare circumstances it can
# happen that getmembers() is called during iteration,
# which will have already exhausted the next() method.
if self.firstmember is not None:
tarinfo = self.next()
index += 1
yield tarinfo
while True:
if index < len(self.members):
tarinfo = self.members[index]
elif not self._loaded:
tarinfo = self.next()
if not tarinfo:
self._loaded = True
return
else:
return
index += 1
yield tarinfo
def _dbg(self, level, msg):
"""Write debugging output to sys.stderr.
"""
if level <= self.debug:
print(msg, file=sys.stderr)
def __enter__(self):
self._check()
return self
def __exit__(self, type, value, traceback):
if type is None:
self.close()
else:
# An exception occurred. We must not call close() because
# it would try to write end-of-archive blocks and padding.
if not self._extfileobj:
self.fileobj.close()
self.closed = True
#--------------------
# exported functions
#--------------------
def is_tarfile(name):
"""Return True if name points to a tar archive that we
are able to handle, else return False.
'name' should be a string, file, or file-like object.
"""
try:
if hasattr(name, "read"):
pos = name.tell()
t = open(fileobj=name)
name.seek(pos)
else:
t = open(name)
t.close()
return True
except TarError:
return False
open = TarFile.open
def main():
import argparse
description = 'A simple command-line interface for tarfile module.'
parser = argparse.ArgumentParser(description=description)
parser.add_argument('-v', '--verbose', action='store_true', default=False,
help='Verbose output')
group = parser.add_mutually_exclusive_group(required=True)
group.add_argument('-l', '--list', metavar='<tarfile>',
help='Show listing of a tarfile')
group.add_argument('-e', '--extract', nargs='+',
metavar=('<tarfile>', '<output_dir>'),
help='Extract tarfile into target dir')
group.add_argument('-c', '--create', nargs='+',
metavar=('<name>', '<file>'),
help='Create tarfile from sources')
group.add_argument('-t', '--test', metavar='<tarfile>',
help='Test if a tarfile is valid')
args = parser.parse_args()
if args.test is not None:
src = args.test
if is_tarfile(src):
with open(src, 'r') as tar:
tar.getmembers()
print(tar.getmembers(), file=sys.stderr)
if args.verbose:
print('{!r} is a tar archive.'.format(src))
else:
parser.exit(1, '{!r} is not a tar archive.\n'.format(src))
elif args.list is not None:
src = args.list
if is_tarfile(src):
with TarFile.open(src, 'r:*') as tf:
tf.list(verbose=args.verbose)
else:
parser.exit(1, '{!r} is not a tar archive.\n'.format(src))
elif args.extract is not None:
if len(args.extract) == 1:
src = args.extract[0]
curdir = os.curdir
elif len(args.extract) == 2:
src, curdir = args.extract
else:
parser.exit(1, parser.format_help())
if is_tarfile(src):
with TarFile.open(src, 'r:*') as tf:
tf.extractall(path=curdir)
if args.verbose:
if curdir == '.':
msg = '{!r} file is extracted.'.format(src)
else:
msg = ('{!r} file is extracted '
'into {!r} directory.').format(src, curdir)
print(msg)
else:
parser.exit(1, '{!r} is not a tar archive.\n'.format(src))
elif args.create is not None:
tar_name = args.create.pop(0)
_, ext = os.path.splitext(tar_name)
compressions = {
# gz
'.gz': 'gz',
'.tgz': 'gz',
# xz
'.xz': 'xz',
'.txz': 'xz',
# bz2
'.bz2': 'bz2',
'.tbz': 'bz2',
'.tbz2': 'bz2',
'.tb2': 'bz2',
}
tar_mode = 'w:' + compressions[ext] if ext in compressions else 'w'
tar_files = args.create
with TarFile.open(tar_name, tar_mode) as tf:
for file_name in tar_files:
tf.add(file_name)
if args.verbose:
print('{!r} file created.'.format(tar_name))
if __name__ == '__main__':
main()
|