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
|
package IO::Uncompress::Unzip;
require 5.004 ;
# for RFC1952
use strict ;
use warnings;
use bytes;
use IO::Uncompress::RawInflate 2.035 ;
use IO::Compress::Base::Common 2.035 qw(:Status createSelfTiedObject);
use IO::Uncompress::Adapter::Inflate 2.035 ;
use IO::Uncompress::Adapter::Identity 2.035 ;
use IO::Compress::Zlib::Extra 2.035 ;
use IO::Compress::Zip::Constants 2.035 ;
use Compress::Raw::Zlib 2.035 qw(crc32) ;
BEGIN
{
eval { require IO::Uncompress::Adapter::Bunzip2 ;
import IO::Uncompress::Adapter::Bunzip2 } ;
# eval { require IO::Uncompress::Adapter::UnLzma ;
# import IO::Uncompress::Adapter::UnLzma } ;
}
require Exporter ;
our ($VERSION, @ISA, @EXPORT_OK, %EXPORT_TAGS, $UnzipError, %headerLookup);
$VERSION = '2.035';
$UnzipError = '';
@ISA = qw(Exporter IO::Uncompress::RawInflate);
@EXPORT_OK = qw( $UnzipError unzip );
%EXPORT_TAGS = %IO::Uncompress::RawInflate::EXPORT_TAGS ;
push @{ $EXPORT_TAGS{all} }, @EXPORT_OK ;
Exporter::export_ok_tags('all');
%headerLookup = (
ZIP_CENTRAL_HDR_SIG, \&skipCentralDirectory,
ZIP_END_CENTRAL_HDR_SIG, \&skipEndCentralDirectory,
ZIP64_END_CENTRAL_REC_HDR_SIG, \&skipCentralDirectory64Rec,
ZIP64_END_CENTRAL_LOC_HDR_SIG, \&skipCentralDirectory64Loc,
ZIP64_ARCHIVE_EXTRA_SIG, \&skipArchiveExtra,
ZIP64_DIGITAL_SIGNATURE_SIG, \&skipDigitalSignature,
);
sub new
{
my $class = shift ;
my $obj = createSelfTiedObject($class, \$UnzipError);
$obj->_create(undef, 0, @_);
}
sub unzip
{
my $obj = createSelfTiedObject(undef, \$UnzipError);
return $obj->_inf(@_) ;
}
sub getExtraParams
{
use IO::Compress::Base::Common 2.035 qw(:Parse);
return (
# # Zip header fields
'Name' => [1, 1, Parse_any, undef],
# 'Stream' => [1, 1, Parse_boolean, 1],
# This means reading the central directory to get
# 1. the local header offsets
# 2. The compressed data length
);
}
sub ckParams
{
my $self = shift ;
my $got = shift ;
# unzip always needs crc32
$got->value('CRC32' => 1);
*$self->{UnzipData}{Name} = $got->value('Name');
return 1;
}
sub mkUncomp
{
my $self = shift ;
my $got = shift ;
my $magic = $self->ckMagic()
or return 0;
*$self->{Info} = $self->readHeader($magic)
or return undef ;
return 1;
}
sub ckMagic
{
my $self = shift;
my $magic ;
$self->smartReadExact(\$magic, 4);
*$self->{HeaderPending} = $magic ;
return $self->HeaderError("Minimum header size is " .
4 . " bytes")
if length $magic != 4 ;
return $self->HeaderError("Bad Magic")
if ! _isZipMagic($magic) ;
*$self->{Type} = 'zip';
return $magic ;
}
sub fastForward
{
my $self = shift;
my $offset = shift;
# TODO - if Stream isn't enabled & reading from file, use seek
my $buffer = '';
my $c = 1024 * 16;
while ($offset > 0)
{
$c = length $offset
if length $offset < $c ;
$offset -= $c;
$self->smartReadExact(\$buffer, $c)
or return 0;
}
return 1;
}
sub readHeader
{
my $self = shift;
my $magic = shift ;
my $name = *$self->{UnzipData}{Name} ;
my $hdr = $self->_readZipHeader($magic) ;
while (defined $hdr)
{
if (! defined $name || $hdr->{Name} eq $name)
{
return $hdr ;
}
# skip the data
# TODO - when Stream is off, use seek
my $buffer;
if (*$self->{ZipData}{Streaming}) {
while (1) {
my $b;
my $status = $self->smartRead(\$b, 1024 * 16);
return undef
if $status <= 0 ;
my $temp_buf;
my $out;
$status = *$self->{Uncomp}->uncompr(\$b, \$temp_buf, 0, $out);
return $self->saveErrorString(undef, *$self->{Uncomp}{Error},
*$self->{Uncomp}{ErrorNo})
if $self->saveStatus($status) == STATUS_ERROR;
if ($status == STATUS_ENDSTREAM) {
*$self->{Uncomp}->reset();
$self->pushBack($b) ;
last;
}
}
# skip the trailer
$self->smartReadExact(\$buffer, $hdr->{TrailerLength})
or return $self->saveErrorString(undef, "Truncated file");
}
else {
my $c = $hdr->{CompressedLength}->get64bit();
$self->fastForward($c)
or return $self->saveErrorString(undef, "Truncated file");
$buffer = '';
}
$self->chkTrailer($buffer) == STATUS_OK
or return $self->saveErrorString(undef, "Truncated file");
$hdr = $self->_readFullZipHeader();
return $self->saveErrorString(undef, "Cannot find '$name'")
if $self->smartEof();
}
return undef;
}
sub chkTrailer
{
my $self = shift;
my $trailer = shift;
my ($sig, $CRC32, $cSize, $uSize) ;
my ($cSizeHi, $uSizeHi) = (0, 0);
if (*$self->{ZipData}{Streaming}) {
$sig = unpack ("V", substr($trailer, 0, 4));
$CRC32 = unpack ("V", substr($trailer, 4, 4));
if (*$self->{ZipData}{Zip64} ) {
$cSize = U64::newUnpack_V64 substr($trailer, 8, 8);
$uSize = U64::newUnpack_V64 substr($trailer, 16, 8);
}
else {
$cSize = U64::newUnpack_V32 substr($trailer, 8, 4);
$uSize = U64::newUnpack_V32 substr($trailer, 12, 4);
}
return $self->TrailerError("Data Descriptor signature, got $sig")
if $sig != ZIP_DATA_HDR_SIG;
}
else {
($CRC32, $cSize, $uSize) =
(*$self->{ZipData}{Crc32},
*$self->{ZipData}{CompressedLen},
*$self->{ZipData}{UnCompressedLen});
}
*$self->{Info}{CRC32} = *$self->{ZipData}{CRC32} ;
*$self->{Info}{CompressedLength} = $cSize->get64bit();
*$self->{Info}{UncompressedLength} = $uSize->get64bit();
if (*$self->{Strict}) {
return $self->TrailerError("CRC mismatch")
if $CRC32 != *$self->{ZipData}{CRC32} ;
return $self->TrailerError("CSIZE mismatch.")
if ! $cSize->equal(*$self->{CompSize});
return $self->TrailerError("USIZE mismatch.")
if ! $uSize->equal(*$self->{UnCompSize});
}
my $reachedEnd = STATUS_ERROR ;
# check for central directory or end of central directory
while (1)
{
my $magic ;
my $got = $self->smartRead(\$magic, 4);
return $self->saveErrorString(STATUS_ERROR, "Truncated file")
if $got != 4 && *$self->{Strict};
if ($got == 0) {
return STATUS_EOF ;
}
elsif ($got < 0) {
return STATUS_ERROR ;
}
elsif ($got < 4) {
$self->pushBack($magic) ;
return STATUS_OK ;
}
my $sig = unpack("V", $magic) ;
my $hdr;
if ($hdr = $headerLookup{$sig})
{
if (&$hdr($self, $magic) != STATUS_OK ) {
if (*$self->{Strict}) {
return STATUS_ERROR ;
}
else {
$self->clearError();
return STATUS_OK ;
}
}
if ($sig == ZIP_END_CENTRAL_HDR_SIG)
{
return STATUS_OK ;
last;
}
}
elsif ($sig == ZIP_LOCAL_HDR_SIG)
{
$self->pushBack($magic) ;
return STATUS_OK ;
}
else
{
# put the data back
$self->pushBack($magic) ;
last;
}
}
return $reachedEnd ;
}
sub skipCentralDirectory
{
my $self = shift;
my $magic = shift ;
my $buffer;
$self->smartReadExact(\$buffer, 46 - 4)
or return $self->TrailerError("Minimum header size is " .
46 . " bytes") ;
my $keep = $magic . $buffer ;
*$self->{HeaderPending} = $keep ;
#my $versionMadeBy = unpack ("v", substr($buffer, 4-4, 2));
#my $extractVersion = unpack ("v", substr($buffer, 6-4, 2));
#my $gpFlag = unpack ("v", substr($buffer, 8-4, 2));
#my $compressedMethod = unpack ("v", substr($buffer, 10-4, 2));
#my $lastModTime = unpack ("V", substr($buffer, 12-4, 4));
#my $crc32 = unpack ("V", substr($buffer, 16-4, 4));
my $compressedLength = unpack ("V", substr($buffer, 20-4, 4));
my $uncompressedLength = unpack ("V", substr($buffer, 24-4, 4));
my $filename_length = unpack ("v", substr($buffer, 28-4, 2));
my $extra_length = unpack ("v", substr($buffer, 30-4, 2));
my $comment_length = unpack ("v", substr($buffer, 32-4, 2));
#my $disk_start = unpack ("v", substr($buffer, 34-4, 2));
#my $int_file_attrib = unpack ("v", substr($buffer, 36-4, 2));
#my $ext_file_attrib = unpack ("V", substr($buffer, 38-4, 2));
#my $lcl_hdr_offset = unpack ("V", substr($buffer, 42-4, 2));
my $filename;
my $extraField;
my $comment ;
if ($filename_length)
{
$self->smartReadExact(\$filename, $filename_length)
or return $self->TruncatedTrailer("filename");
$keep .= $filename ;
}
if ($extra_length)
{
$self->smartReadExact(\$extraField, $extra_length)
or return $self->TruncatedTrailer("extra");
$keep .= $extraField ;
}
if ($comment_length)
{
$self->smartReadExact(\$comment, $comment_length)
or return $self->TruncatedTrailer("comment");
$keep .= $comment ;
}
return STATUS_OK ;
}
sub skipArchiveExtra
{
my $self = shift;
my $magic = shift ;
my $buffer;
$self->smartReadExact(\$buffer, 4)
or return $self->TrailerError("Minimum header size is " .
4 . " bytes") ;
my $keep = $magic . $buffer ;
my $size = unpack ("V", $buffer);
$self->smartReadExact(\$buffer, $size)
or return $self->TrailerError("Minimum header size is " .
$size . " bytes") ;
$keep .= $buffer ;
*$self->{HeaderPending} = $keep ;
return STATUS_OK ;
}
sub skipCentralDirectory64Rec
{
my $self = shift;
my $magic = shift ;
my $buffer;
$self->smartReadExact(\$buffer, 8)
or return $self->TrailerError("Minimum header size is " .
8 . " bytes") ;
my $keep = $magic . $buffer ;
my ($sizeLo, $sizeHi) = unpack ("V V", $buffer);
my $size = $sizeHi * 0xFFFFFFFF + $sizeLo;
$self->fastForward($size)
or return $self->TrailerError("Minimum header size is " .
$size . " bytes") ;
#$keep .= $buffer ;
#*$self->{HeaderPending} = $keep ;
#my $versionMadeBy = unpack ("v", substr($buffer, 0, 2));
#my $extractVersion = unpack ("v", substr($buffer, 2, 2));
#my $diskNumber = unpack ("V", substr($buffer, 4, 4));
#my $cntrlDirDiskNo = unpack ("V", substr($buffer, 8, 4));
#my $entriesInThisCD = unpack ("V V", substr($buffer, 12, 8));
#my $entriesInCD = unpack ("V V", substr($buffer, 20, 8));
#my $sizeOfCD = unpack ("V V", substr($buffer, 28, 8));
#my $offsetToCD = unpack ("V V", substr($buffer, 36, 8));
return STATUS_OK ;
}
sub skipCentralDirectory64Loc
{
my $self = shift;
my $magic = shift ;
my $buffer;
$self->smartReadExact(\$buffer, 20 - 4)
or return $self->TrailerError("Minimum header size is " .
20 . " bytes") ;
my $keep = $magic . $buffer ;
*$self->{HeaderPending} = $keep ;
#my $startCdDisk = unpack ("V", substr($buffer, 4-4, 4));
#my $offsetToCD = unpack ("V V", substr($buffer, 8-4, 8));
#my $diskCount = unpack ("V", substr($buffer, 16-4, 4));
return STATUS_OK ;
}
sub skipEndCentralDirectory
{
my $self = shift;
my $magic = shift ;
my $buffer;
$self->smartReadExact(\$buffer, 22 - 4)
or return $self->TrailerError("Minimum header size is " .
22 . " bytes") ;
my $keep = $magic . $buffer ;
*$self->{HeaderPending} = $keep ;
#my $diskNumber = unpack ("v", substr($buffer, 4-4, 2));
#my $cntrlDirDiskNo = unpack ("v", substr($buffer, 6-4, 2));
#my $entriesInThisCD = unpack ("v", substr($buffer, 8-4, 2));
#my $entriesInCD = unpack ("v", substr($buffer, 10-4, 2));
#my $sizeOfCD = unpack ("V", substr($buffer, 12-4, 2));
#my $offsetToCD = unpack ("V", substr($buffer, 16-4, 2));
my $comment_length = unpack ("v", substr($buffer, 20-4, 2));
my $comment ;
if ($comment_length)
{
$self->smartReadExact(\$comment, $comment_length)
or return $self->TruncatedTrailer("comment");
$keep .= $comment ;
}
return STATUS_OK ;
}
sub _isZipMagic
{
my $buffer = shift ;
return 0 if length $buffer < 4 ;
my $sig = unpack("V", $buffer) ;
return $sig == ZIP_LOCAL_HDR_SIG ;
}
sub _readFullZipHeader($)
{
my ($self) = @_ ;
my $magic = '' ;
$self->smartReadExact(\$magic, 4);
*$self->{HeaderPending} = $magic ;
return $self->HeaderError("Minimum header size is " .
30 . " bytes")
if length $magic != 4 ;
return $self->HeaderError("Bad Magic")
if ! _isZipMagic($magic) ;
my $status = $self->_readZipHeader($magic);
delete *$self->{Transparent} if ! defined $status ;
return $status ;
}
sub _readZipHeader($)
{
my ($self, $magic) = @_ ;
my ($HeaderCRC) ;
my ($buffer) = '' ;
$self->smartReadExact(\$buffer, 30 - 4)
or return $self->HeaderError("Minimum header size is " .
30 . " bytes") ;
my $keep = $magic . $buffer ;
*$self->{HeaderPending} = $keep ;
my $extractVersion = unpack ("v", substr($buffer, 4-4, 2));
my $gpFlag = unpack ("v", substr($buffer, 6-4, 2));
my $compressedMethod = unpack ("v", substr($buffer, 8-4, 2));
my $lastModTime = unpack ("V", substr($buffer, 10-4, 4));
my $crc32 = unpack ("V", substr($buffer, 14-4, 4));
my $compressedLength = U64::newUnpack_V32 substr($buffer, 18-4, 4);
my $uncompressedLength = U64::newUnpack_V32 substr($buffer, 22-4, 4);
my $filename_length = unpack ("v", substr($buffer, 26-4, 2));
my $extra_length = unpack ("v", substr($buffer, 28-4, 2));
my $filename;
my $extraField;
my @EXTRA = ();
my $streamingMode = ($gpFlag & ZIP_GP_FLAG_STREAMING_MASK) ? 1 : 0 ;
return $self->HeaderError("Streamed Stored content not supported")
if $streamingMode && $compressedMethod == 0 ;
return $self->HeaderError("Encrypted content not supported")
if $gpFlag & (ZIP_GP_FLAG_ENCRYPTED_MASK|ZIP_GP_FLAG_STRONG_ENCRYPTED_MASK);
return $self->HeaderError("Patch content not supported")
if $gpFlag & ZIP_GP_FLAG_PATCHED_MASK;
*$self->{ZipData}{Streaming} = $streamingMode;
if ($filename_length)
{
$self->smartReadExact(\$filename, $filename_length)
or return $self->TruncatedHeader("Filename");
$keep .= $filename ;
}
my $zip64 = 0 ;
if ($extra_length)
{
$self->smartReadExact(\$extraField, $extra_length)
or return $self->TruncatedHeader("Extra Field");
my $bad = IO::Compress::Zlib::Extra::parseRawExtra($extraField,
\@EXTRA, 1, 0);
return $self->HeaderError($bad)
if defined $bad;
$keep .= $extraField ;
my %Extra ;
for (@EXTRA)
{
$Extra{$_->[0]} = \$_->[1];
}
if (defined $Extra{ZIP_EXTRA_ID_ZIP64()})
{
$zip64 = 1 ;
my $buff = ${ $Extra{ZIP_EXTRA_ID_ZIP64()} };
# This code assumes that all the fields in the Zip64
# extra field aren't necessarily present. The spec says that
# they only exist if the equivalent local headers are -1.
if (! $streamingMode) {
my $offset = 0 ;
if ($uncompressedLength->get32bit() == 0xFFFFFFFF ) {
$uncompressedLength
= U64::newUnpack_V64 substr($buff, 0, 8);
$offset += 8 ;
}
if ($compressedLength->get32bit() == 0xFFFFFFFF) {
$compressedLength
= U64::newUnpack_V64 substr($buff, $offset, 8);
$offset += 8 ;
}
}
}
}
*$self->{ZipData}{Zip64} = $zip64;
if (! $streamingMode) {
*$self->{ZipData}{Streaming} = 0;
*$self->{ZipData}{Crc32} = $crc32;
*$self->{ZipData}{CompressedLen} = $compressedLength;
*$self->{ZipData}{UnCompressedLen} = $uncompressedLength;
*$self->{CompressedInputLengthRemaining} =
*$self->{CompressedInputLength} = $compressedLength->get64bit();
}
*$self->{ZipData}{CRC32} = crc32(undef);
*$self->{ZipData}{Method} = $compressedMethod;
if ($compressedMethod == ZIP_CM_DEFLATE)
{
*$self->{Type} = 'zip-deflate';
my $obj = IO::Uncompress::Adapter::Inflate::mkUncompObject(1,0,0);
*$self->{Uncomp} = $obj;
}
elsif ($compressedMethod == ZIP_CM_BZIP2)
{
return $self->HeaderError("Unsupported Compression format $compressedMethod")
if ! defined $IO::Uncompress::Adapter::Bunzip2::VERSION ;
*$self->{Type} = 'zip-bzip2';
my $obj = IO::Uncompress::Adapter::Bunzip2::mkUncompObject();
*$self->{Uncomp} = $obj;
}
# elsif ($compressedMethod == ZIP_CM_LZMA)
# {
# return $self->HeaderError("Unsupported Compression format $compressedMethod")
# if ! defined $IO::Uncompress::Adapter::UnLzma::VERSION ;
#
# *$self->{Type} = 'zip-lzma';
# my $LzmaHeader;
# $self->smartReadExact(\$LzmaHeader, 4)
# or return $self->saveErrorString(undef, "Truncated file");
# my ($verHi, $verLo) = unpack ("CC", substr($LzmaHeader, 0, 2));
# my $LzmaPropertiesSize = unpack ("v", substr($LzmaHeader, 2, 2));
#
#
# my $LzmaPropertyData;
# $self->smartReadExact(\$LzmaPropertyData, $LzmaPropertiesSize)
# or return $self->saveErrorString(undef, "Truncated file");
# #my $LzmaInfo = unpack ("C", substr($LzmaPropertyData, 0, 1));
# #my $LzmaDictSize = unpack ("V", substr($LzmaPropertyData, 1, 4));
#
# # Create an LZMA_Alone header
# $self->pushBack($LzmaPropertyData .
# $uncompressedLength->getPacked_V64());
#
# my $obj =
# IO::Uncompress::Adapter::UnLzma::mkUncompObject();
#
# *$self->{Uncomp} = $obj;
# }
elsif ($compressedMethod == ZIP_CM_STORE)
{
# TODO -- add support for reading uncompressed
*$self->{Type} = 'zip-stored';
my $obj = IO::Uncompress::Adapter::Identity::mkUncompObject();
*$self->{Uncomp} = $obj;
}
else
{
return $self->HeaderError("Unsupported Compression format $compressedMethod");
}
return {
'Type' => 'zip',
'FingerprintLength' => 4,
#'HeaderLength' => $compressedMethod == 8 ? length $keep : 0,
'HeaderLength' => length $keep,
'Zip64' => $zip64,
'TrailerLength' => ! $streamingMode ? 0 : $zip64 ? 24 : 16,
'Header' => $keep,
'CompressedLength' => $compressedLength ,
'UncompressedLength' => $uncompressedLength ,
'CRC32' => $crc32 ,
'Name' => $filename,
'Time' => _dosToUnixTime($lastModTime),
'Stream' => $streamingMode,
'MethodID' => $compressedMethod,
'MethodName' => $compressedMethod == ZIP_CM_DEFLATE
? "Deflated"
: $compressedMethod == ZIP_CM_BZIP2
? "Bzip2"
: $compressedMethod == ZIP_CM_LZMA
? "Lzma"
: $compressedMethod == ZIP_CM_STORE
? "Stored"
: "Unknown" ,
# 'TextFlag' => $flag & GZIP_FLG_FTEXT ? 1 : 0,
# 'HeaderCRCFlag' => $flag & GZIP_FLG_FHCRC ? 1 : 0,
# 'NameFlag' => $flag & GZIP_FLG_FNAME ? 1 : 0,
# 'CommentFlag' => $flag & GZIP_FLG_FCOMMENT ? 1 : 0,
# 'ExtraFlag' => $flag & GZIP_FLG_FEXTRA ? 1 : 0,
# 'Comment' => $comment,
# 'OsID' => $os,
# 'OsName' => defined $GZIP_OS_Names{$os}
# ? $GZIP_OS_Names{$os} : "Unknown",
# 'HeaderCRC' => $HeaderCRC,
# 'Flags' => $flag,
# 'ExtraFlags' => $xfl,
'ExtraFieldRaw' => $extraField,
'ExtraField' => [ @EXTRA ],
}
}
sub filterUncompressed
{
my $self = shift ;
if (*$self->{ZipData}{Method} == ZIP_CM_DEFLATE) {
*$self->{ZipData}{CRC32} = *$self->{Uncomp}->crc32() ;
}
else {
*$self->{ZipData}{CRC32} = crc32(${$_[0]}, *$self->{ZipData}{CRC32});
}
}
# from Archive::Zip & info-zip
sub _dosToUnixTime
{
my $dt = shift;
my $year = ( ( $dt >> 25 ) & 0x7f ) + 80;
my $mon = ( ( $dt >> 21 ) & 0x0f ) - 1;
my $mday = ( ( $dt >> 16 ) & 0x1f );
my $hour = ( ( $dt >> 11 ) & 0x1f );
my $min = ( ( $dt >> 5 ) & 0x3f );
my $sec = ( ( $dt << 1 ) & 0x3e );
use POSIX 'mktime';
my $time_t = mktime( $sec, $min, $hour, $mday, $mon, $year, 0, 0, -1 );
return 0 if ! defined $time_t;
return $time_t;
}
1;
__END__
=head1 NAME
IO::Uncompress::Unzip - Read zip files/buffers
=head1 SYNOPSIS
use IO::Uncompress::Unzip qw(unzip $UnzipError) ;
my $status = unzip $input => $output [,OPTS]
or die "unzip failed: $UnzipError\n";
my $z = new IO::Uncompress::Unzip $input [OPTS]
or die "unzip failed: $UnzipError\n";
$status = $z->read($buffer)
$status = $z->read($buffer, $length)
$status = $z->read($buffer, $length, $offset)
$line = $z->getline()
$char = $z->getc()
$char = $z->ungetc()
$char = $z->opened()
$status = $z->inflateSync()
$data = $z->trailingData()
$status = $z->nextStream()
$data = $z->getHeaderInfo()
$z->tell()
$z->seek($position, $whence)
$z->binmode()
$z->fileno()
$z->eof()
$z->close()
$UnzipError ;
# IO::File mode
<$z>
read($z, $buffer);
read($z, $buffer, $length);
read($z, $buffer, $length, $offset);
tell($z)
seek($z, $position, $whence)
binmode($z)
fileno($z)
eof($z)
close($z)
=head1 DESCRIPTION
This module provides a Perl interface that allows the reading of
zlib files/buffers.
For writing zip files/buffers, see the companion module IO::Compress::Zip.
=head1 Functional Interface
A top-level function, C<unzip>, is provided to carry out
"one-shot" uncompression between buffers and/or files. For finer
control over the uncompression process, see the L</"OO Interface">
section.
use IO::Uncompress::Unzip qw(unzip $UnzipError) ;
unzip $input => $output [,OPTS]
or die "unzip failed: $UnzipError\n";
The functional interface needs Perl5.005 or better.
=head2 unzip $input => $output [, OPTS]
C<unzip> expects at least two parameters, C<$input> and C<$output>.
=head3 The C<$input> parameter
The parameter, C<$input>, is used to define the source of
the compressed data.
It can take one of the following forms:
=over 5
=item A filename
If the C<$input> parameter is a simple scalar, it is assumed to be a
filename. This file will be opened for reading and the input data
will be read from it.
=item A filehandle
If the C<$input> parameter is a filehandle, the input data will be
read from it.
The string '-' can be used as an alias for standard input.
=item A scalar reference
If C<$input> is a scalar reference, the input data will be read
from C<$$input>.
=item An array reference
If C<$input> is an array reference, each element in the array must be a
filename.
The input data will be read from each file in turn.
The complete array will be walked to ensure that it only
contains valid filenames before any data is uncompressed.
=item An Input FileGlob string
If C<$input> is a string that is delimited by the characters "<" and ">"
C<unzip> will assume that it is an I<input fileglob string>. The
input is the list of files that match the fileglob.
See L<File::GlobMapper|File::GlobMapper> for more details.
=back
If the C<$input> parameter is any other type, C<undef> will be returned.
=head3 The C<$output> parameter
The parameter C<$output> is used to control the destination of the
uncompressed data. This parameter can take one of these forms.
=over 5
=item A filename
If the C<$output> parameter is a simple scalar, it is assumed to be a
filename. This file will be opened for writing and the uncompressed
data will be written to it.
=item A filehandle
If the C<$output> parameter is a filehandle, the uncompressed data
will be written to it.
The string '-' can be used as an alias for standard output.
=item A scalar reference
If C<$output> is a scalar reference, the uncompressed data will be
stored in C<$$output>.
=item An Array Reference
If C<$output> is an array reference, the uncompressed data will be
pushed onto the array.
=item An Output FileGlob
If C<$output> is a string that is delimited by the characters "<" and ">"
C<unzip> will assume that it is an I<output fileglob string>. The
output is the list of files that match the fileglob.
When C<$output> is an fileglob string, C<$input> must also be a fileglob
string. Anything else is an error.
See L<File::GlobMapper|File::GlobMapper> for more details.
=back
If the C<$output> parameter is any other type, C<undef> will be returned.
=head2 Notes
When C<$input> maps to multiple compressed files/buffers and C<$output> is
a single file/buffer, after uncompression C<$output> will contain a
concatenation of all the uncompressed data from each of the input
files/buffers.
=head2 Optional Parameters
Unless specified below, the optional parameters for C<unzip>,
C<OPTS>, are the same as those used with the OO interface defined in the
L</"Constructor Options"> section below.
=over 5
=item C<< AutoClose => 0|1 >>
This option applies to any input or output data streams to
C<unzip> that are filehandles.
If C<AutoClose> is specified, and the value is true, it will result in all
input and/or output filehandles being closed once C<unzip> has
completed.
This parameter defaults to 0.
=item C<< BinModeOut => 0|1 >>
When writing to a file or filehandle, set C<binmode> before writing to the
file.
Defaults to 0.
=item C<< Append => 0|1 >>
The behaviour of this option is dependent on the type of output data
stream.
=over 5
=item * A Buffer
If C<Append> is enabled, all uncompressed data will be append to the end of
the output buffer. Otherwise the output buffer will be cleared before any
uncompressed data is written to it.
=item * A Filename
If C<Append> is enabled, the file will be opened in append mode. Otherwise
the contents of the file, if any, will be truncated before any uncompressed
data is written to it.
=item * A Filehandle
If C<Append> is enabled, the filehandle will be positioned to the end of
the file via a call to C<seek> before any uncompressed data is
written to it. Otherwise the file pointer will not be moved.
=back
When C<Append> is specified, and set to true, it will I<append> all uncompressed
data to the output data stream.
So when the output is a filehandle it will carry out a seek to the eof
before writing any uncompressed data. If the output is a filename, it will be opened for
appending. If the output is a buffer, all uncompressed data will be
appended to the existing buffer.
Conversely when C<Append> is not specified, or it is present and is set to
false, it will operate as follows.
When the output is a filename, it will truncate the contents of the file
before writing any uncompressed data. If the output is a filehandle
its position will not be changed. If the output is a buffer, it will be
wiped before any uncompressed data is output.
Defaults to 0.
=item C<< MultiStream => 0|1 >>
If the input file/buffer contains multiple compressed data streams, this
option will uncompress the whole lot as a single data stream.
Defaults to 0.
=item C<< TrailingData => $scalar >>
Returns the data, if any, that is present immediately after the compressed
data stream once uncompression is complete.
This option can be used when there is useful information immediately
following the compressed data stream, and you don't know the length of the
compressed data stream.
If the input is a buffer, C<trailingData> will return everything from the
end of the compressed data stream to the end of the buffer.
If the input is a filehandle, C<trailingData> will return the data that is
left in the filehandle input buffer once the end of the compressed data
stream has been reached. You can then use the filehandle to read the rest
of the input file.
Don't bother using C<trailingData> if the input is a filename.
If you know the length of the compressed data stream before you start
uncompressing, you can avoid having to use C<trailingData> by setting the
C<InputLength> option.
=back
=head2 Examples
Say you have a zip file, C<file1.zip>, that only contains a
single member, you can read it and write the uncompressed data to the
file C<file1.txt> like this.
use strict ;
use warnings ;
use IO::Uncompress::Unzip qw(unzip $UnzipError) ;
my $input = "file1.zip";
my $output = "file1.txt";
unzip $input => $output
or die "unzip failed: $UnzipError\n";
If you have a zip file that contains multiple members and want to read a
specific member from the file, say C<"data1">, use the C<Name> option
use strict ;
use warnings ;
use IO::Uncompress::Unzip qw(unzip $UnzipError) ;
my $input = "file1.zip";
my $output = "file1.txt";
unzip $input => $output, Name => "data1"
or die "unzip failed: $UnzipError\n";
Alternatively, if you want to read the C<"data1"> member into memory, use
a scalar reference for the C<output> partameter.
use strict ;
use warnings ;
use IO::Uncompress::Unzip qw(unzip $UnzipError) ;
my $input = "file1.zip";
my $output ;
unzip $input => \$output, Name => "data1"
or die "unzip failed: $UnzipError\n";
# $output now contains the uncompressed data
To read from an existing Perl filehandle, C<$input>, and write the
uncompressed data to a buffer, C<$buffer>.
use strict ;
use warnings ;
use IO::Uncompress::Unzip qw(unzip $UnzipError) ;
use IO::File ;
my $input = new IO::File "<file1.zip"
or die "Cannot open 'file1.zip': $!\n" ;
my $buffer ;
unzip $input => \$buffer
or die "unzip failed: $UnzipError\n";
=head1 OO Interface
=head2 Constructor
The format of the constructor for IO::Uncompress::Unzip is shown below
my $z = new IO::Uncompress::Unzip $input [OPTS]
or die "IO::Uncompress::Unzip failed: $UnzipError\n";
Returns an C<IO::Uncompress::Unzip> object on success and undef on failure.
The variable C<$UnzipError> will contain an error message on failure.
If you are running Perl 5.005 or better the object, C<$z>, returned from
IO::Uncompress::Unzip can be used exactly like an L<IO::File|IO::File> filehandle.
This means that all normal input file operations can be carried out with
C<$z>. For example, to read a line from a compressed file/buffer you can
use either of these forms
$line = $z->getline();
$line = <$z>;
The mandatory parameter C<$input> is used to determine the source of the
compressed data. This parameter can take one of three forms.
=over 5
=item A filename
If the C<$input> parameter is a scalar, it is assumed to be a filename. This
file will be opened for reading and the compressed data will be read from it.
=item A filehandle
If the C<$input> parameter is a filehandle, the compressed data will be
read from it.
The string '-' can be used as an alias for standard input.
=item A scalar reference
If C<$input> is a scalar reference, the compressed data will be read from
C<$$output>.
=back
=head2 Constructor Options
The option names defined below are case insensitive and can be optionally
prefixed by a '-'. So all of the following are valid
-AutoClose
-autoclose
AUTOCLOSE
autoclose
OPTS is a combination of the following options:
=over 5
=item C<< Name => "membername" >>
Open "membername" from the zip file for reading.
=item C<< AutoClose => 0|1 >>
This option is only valid when the C<$input> parameter is a filehandle. If
specified, and the value is true, it will result in the file being closed once
either the C<close> method is called or the IO::Uncompress::Unzip object is
destroyed.
This parameter defaults to 0.
=item C<< MultiStream => 0|1 >>
Treats the complete zip file/buffer as a single compressed data
stream. When reading in multi-stream mode each member of the zip
file/buffer will be uncompressed in turn until the end of the file/buffer
is encountered.
This parameter defaults to 0.
=item C<< Prime => $string >>
This option will uncompress the contents of C<$string> before processing the
input file/buffer.
This option can be useful when the compressed data is embedded in another
file/data structure and it is not possible to work out where the compressed
data begins without having to read the first few bytes. If this is the
case, the uncompression can be I<primed> with these bytes using this
option.
=item C<< Transparent => 0|1 >>
If this option is set and the input file/buffer is not compressed data,
the module will allow reading of it anyway.
In addition, if the input file/buffer does contain compressed data and
there is non-compressed data immediately following it, setting this option
will make this module treat the whole file/buffer as a single data stream.
This option defaults to 1.
=item C<< BlockSize => $num >>
When reading the compressed input data, IO::Uncompress::Unzip will read it in
blocks of C<$num> bytes.
This option defaults to 4096.
=item C<< InputLength => $size >>
When present this option will limit the number of compressed bytes read
from the input file/buffer to C<$size>. This option can be used in the
situation where there is useful data directly after the compressed data
stream and you know beforehand the exact length of the compressed data
stream.
This option is mostly used when reading from a filehandle, in which case
the file pointer will be left pointing to the first byte directly after the
compressed data stream.
This option defaults to off.
=item C<< Append => 0|1 >>
This option controls what the C<read> method does with uncompressed data.
If set to 1, all uncompressed data will be appended to the output parameter
of the C<read> method.
If set to 0, the contents of the output parameter of the C<read> method
will be overwritten by the uncompressed data.
Defaults to 0.
=item C<< Strict => 0|1 >>
This option controls whether the extra checks defined below are used when
carrying out the decompression. When Strict is on, the extra tests are
carried out, when Strict is off they are not.
The default for this option is off.
=back
=head2 Examples
TODO
=head1 Methods
=head2 read
Usage is
$status = $z->read($buffer)
Reads a block of compressed data (the size the the compressed block is
determined by the C<Buffer> option in the constructor), uncompresses it and
writes any uncompressed data into C<$buffer>. If the C<Append> parameter is
set in the constructor, the uncompressed data will be appended to the
C<$buffer> parameter. Otherwise C<$buffer> will be overwritten.
Returns the number of uncompressed bytes written to C<$buffer>, zero if eof
or a negative number on error.
=head2 read
Usage is
$status = $z->read($buffer, $length)
$status = $z->read($buffer, $length, $offset)
$status = read($z, $buffer, $length)
$status = read($z, $buffer, $length, $offset)
Attempt to read C<$length> bytes of uncompressed data into C<$buffer>.
The main difference between this form of the C<read> method and the
previous one, is that this one will attempt to return I<exactly> C<$length>
bytes. The only circumstances that this function will not is if end-of-file
or an IO error is encountered.
Returns the number of uncompressed bytes written to C<$buffer>, zero if eof
or a negative number on error.
=head2 getline
Usage is
$line = $z->getline()
$line = <$z>
Reads a single line.
This method fully supports the use of of the variable C<$/> (or
C<$INPUT_RECORD_SEPARATOR> or C<$RS> when C<English> is in use) to
determine what constitutes an end of line. Paragraph mode, record mode and
file slurp mode are all supported.
=head2 getc
Usage is
$char = $z->getc()
Read a single character.
=head2 ungetc
Usage is
$char = $z->ungetc($string)
=head2 inflateSync
Usage is
$status = $z->inflateSync()
TODO
=head2 getHeaderInfo
Usage is
$hdr = $z->getHeaderInfo();
@hdrs = $z->getHeaderInfo();
This method returns either a hash reference (in scalar context) or a list
or hash references (in array context) that contains information about each
of the header fields in the compressed data stream(s).
=head2 tell
Usage is
$z->tell()
tell $z
Returns the uncompressed file offset.
=head2 eof
Usage is
$z->eof();
eof($z);
Returns true if the end of the compressed input stream has been reached.
=head2 seek
$z->seek($position, $whence);
seek($z, $position, $whence);
Provides a sub-set of the C<seek> functionality, with the restriction
that it is only legal to seek forward in the input file/buffer.
It is a fatal error to attempt to seek backward.
The C<$whence> parameter takes one the usual values, namely SEEK_SET,
SEEK_CUR or SEEK_END.
Returns 1 on success, 0 on failure.
=head2 binmode
Usage is
$z->binmode
binmode $z ;
This is a noop provided for completeness.
=head2 opened
$z->opened()
Returns true if the object currently refers to a opened file/buffer.
=head2 autoflush
my $prev = $z->autoflush()
my $prev = $z->autoflush(EXPR)
If the C<$z> object is associated with a file or a filehandle, this method
returns the current autoflush setting for the underlying filehandle. If
C<EXPR> is present, and is non-zero, it will enable flushing after every
write/print operation.
If C<$z> is associated with a buffer, this method has no effect and always
returns C<undef>.
B<Note> that the special variable C<$|> B<cannot> be used to set or
retrieve the autoflush setting.
=head2 input_line_number
$z->input_line_number()
$z->input_line_number(EXPR)
Returns the current uncompressed line number. If C<EXPR> is present it has
the effect of setting the line number. Note that setting the line number
does not change the current position within the file/buffer being read.
The contents of C<$/> are used to to determine what constitutes a line
terminator.
=head2 fileno
$z->fileno()
fileno($z)
If the C<$z> object is associated with a file or a filehandle, C<fileno>
will return the underlying file descriptor. Once the C<close> method is
called C<fileno> will return C<undef>.
If the C<$z> object is associated with a buffer, this method will return
C<undef>.
=head2 close
$z->close() ;
close $z ;
Closes the output file/buffer.
For most versions of Perl this method will be automatically invoked if
the IO::Uncompress::Unzip object is destroyed (either explicitly or by the
variable with the reference to the object going out of scope). The
exceptions are Perl versions 5.005 through 5.00504 and 5.8.0. In
these cases, the C<close> method will be called automatically, but
not until global destruction of all live objects when the program is
terminating.
Therefore, if you want your scripts to be able to run on all versions
of Perl, you should call C<close> explicitly and not rely on automatic
closing.
Returns true on success, otherwise 0.
If the C<AutoClose> option has been enabled when the IO::Uncompress::Unzip
object was created, and the object is associated with a file, the
underlying file will also be closed.
=head2 nextStream
Usage is
my $status = $z->nextStream();
Skips to the next compressed data stream in the input file/buffer. If a new
compressed data stream is found, the eof marker will be cleared and C<$.>
will be reset to 0.
Returns 1 if a new stream was found, 0 if none was found, and -1 if an
error was encountered.
=head2 trailingData
Usage is
my $data = $z->trailingData();
Returns the data, if any, that is present immediately after the compressed
data stream once uncompression is complete. It only makes sense to call
this method once the end of the compressed data stream has been
encountered.
This option can be used when there is useful information immediately
following the compressed data stream, and you don't know the length of the
compressed data stream.
If the input is a buffer, C<trailingData> will return everything from the
end of the compressed data stream to the end of the buffer.
If the input is a filehandle, C<trailingData> will return the data that is
left in the filehandle input buffer once the end of the compressed data
stream has been reached. You can then use the filehandle to read the rest
of the input file.
Don't bother using C<trailingData> if the input is a filename.
If you know the length of the compressed data stream before you start
uncompressing, you can avoid having to use C<trailingData> by setting the
C<InputLength> option in the constructor.
=head1 Importing
No symbolic constants are required by this IO::Uncompress::Unzip at present.
=over 5
=item :all
Imports C<unzip> and C<$UnzipError>.
Same as doing this
use IO::Uncompress::Unzip qw(unzip $UnzipError) ;
=back
=head1 EXAMPLES
=head2 Working with Net::FTP
See L<IO::Uncompress::Unzip::FAQ|IO::Uncompress::Unzip::FAQ/"Compressed files and Net::FTP">
=head2 Walking through a zip file
The code below can be used to traverse a zip file, one compressed data
stream at a time.
use IO::Uncompress::Unzip qw($UnzipError);
my $zipfile = "somefile.zip";
my $u = new IO::Uncompress::Unzip $zipfile
or die "Cannot open $zipfile: $UnzipError";
my $status;
for ($status = 1; ! $u->eof(); $status = $u->nextStream())
{
my $name = $u->getHeaderInfo()->{Name};
warn "Processing member $name\n" ;
my $buff;
while (($status = $u->read($buff)) > 0) {
# Do something here
}
last if $status < 0;
}
die "Error processing $zipfile: $!\n"
if $status < 0 ;
Each individual compressed data stream is read until the logical
end-of-file is reached. Then C<nextStream> is called. This will skip to the
start of the next compressed data stream and clear the end-of-file flag.
It is also worth noting that C<nextStream> can be called at any time -- you
don't have to wait until you have exhausted a compressed data stream before
skipping to the next one.
=head1 SEE ALSO
L<Compress::Zlib>, L<IO::Compress::Gzip>, L<IO::Uncompress::Gunzip>, L<IO::Compress::Deflate>, L<IO::Uncompress::Inflate>, L<IO::Compress::RawDeflate>, L<IO::Uncompress::RawInflate>, L<IO::Compress::Bzip2>, L<IO::Uncompress::Bunzip2>, L<IO::Compress::Lzma>, L<IO::Uncompress::UnLzma>, L<IO::Compress::Xz>, L<IO::Uncompress::UnXz>, L<IO::Compress::Lzop>, L<IO::Uncompress::UnLzop>, L<IO::Compress::Lzf>, L<IO::Uncompress::UnLzf>, L<IO::Uncompress::AnyInflate>, L<IO::Uncompress::AnyUncompress>
L<Compress::Zlib::FAQ|Compress::Zlib::FAQ>
L<File::GlobMapper|File::GlobMapper>, L<Archive::Zip|Archive::Zip>,
L<Archive::Tar|Archive::Tar>,
L<IO::Zlib|IO::Zlib>
For RFC 1950, 1951 and 1952 see
F<http://www.faqs.org/rfcs/rfc1950.html>,
F<http://www.faqs.org/rfcs/rfc1951.html> and
F<http://www.faqs.org/rfcs/rfc1952.html>
The I<zlib> compression library was written by Jean-loup Gailly
F<gzip@prep.ai.mit.edu> and Mark Adler F<madler@alumni.caltech.edu>.
The primary site for the I<zlib> compression library is
F<http://www.zlib.org>.
The primary site for gzip is F<http://www.gzip.org>.
=head1 AUTHOR
This module was written by Paul Marquess, F<pmqs@cpan.org>.
=head1 MODIFICATION HISTORY
See the Changes file.
=head1 COPYRIGHT AND LICENSE
Copyright (c) 2005-2011 Paul Marquess. All rights reserved.
This program is free software; you can redistribute it and/or
modify it under the same terms as Perl itself.
|