-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy pathreader_test.go
1860 lines (1789 loc) · 56.3 KB
/
reader_test.go
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
// Copyright 2010 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package zip
import (
"bytes"
"encoding/base64"
"encoding/binary"
"encoding/hex"
"io"
"io/fs"
"os"
"path/filepath"
"regexp"
"slices"
"strings"
"testing"
"testing/fstest"
"time"
)
type ZipTest struct {
Name string
Source func() (r io.ReaderAt, size int64) // if non-nil, used instead of testdata/<Name> file
Comment string
File []ZipTestFile
Obscured bool // needed for Apple notarization (golang.org/issue/34986)
Error error // the error that Opening this file should return
}
type ZipTestFile struct {
Name string
Mode fs.FileMode
NonUTF8 bool
ModTime time.Time
Modified time.Time
// Information describing expected zip file content.
// First, reading the entire content should produce the error ContentErr.
// Second, if ContentErr==nil, the content should match Content.
// If content is large, an alternative to setting Content is to set File,
// which names a file in the testdata/ directory containing the
// uncompressed expected content.
// If content is very large, an alternative to setting Content or File
// is to set Size, which will then be checked against the header-reported size
// but will bypass the decompressing of the actual data.
// This last option is used for testing very large (multi-GB) compressed files.
ContentErr error
Content []byte
File string
Size uint64
}
var tests = []ZipTest{
{
Name: "test.zip",
Comment: "This is a zipfile comment.",
File: []ZipTestFile{
{
Name: "test.txt",
Content: []byte("This is a test text file.\n"),
Modified: time.Date(2010, 9, 5, 12, 12, 1, 0, timeZone(+10*time.Hour)),
Mode: 0644,
},
{
Name: "gophercolor16x16.png",
File: "gophercolor16x16.png",
Modified: time.Date(2010, 9, 5, 15, 52, 58, 0, timeZone(+10*time.Hour)),
Mode: 0644,
},
},
},
{
Name: "test-trailing-junk.zip",
Comment: "This is a zipfile comment.",
File: []ZipTestFile{
{
Name: "test.txt",
Content: []byte("This is a test text file.\n"),
Modified: time.Date(2010, 9, 5, 12, 12, 1, 0, timeZone(+10*time.Hour)),
Mode: 0644,
},
{
Name: "gophercolor16x16.png",
File: "gophercolor16x16.png",
Modified: time.Date(2010, 9, 5, 15, 52, 58, 0, timeZone(+10*time.Hour)),
Mode: 0644,
},
},
},
{
Name: "test-prefix.zip",
Comment: "This is a zipfile comment.",
File: []ZipTestFile{
{
Name: "test.txt",
Content: []byte("This is a test text file.\n"),
Modified: time.Date(2010, 9, 5, 12, 12, 1, 0, timeZone(+10*time.Hour)),
Mode: 0644,
},
{
Name: "gophercolor16x16.png",
File: "gophercolor16x16.png",
Modified: time.Date(2010, 9, 5, 15, 52, 58, 0, timeZone(+10*time.Hour)),
Mode: 0644,
},
},
},
{
Name: "test-baddirsz.zip",
Comment: "This is a zipfile comment.",
File: []ZipTestFile{
{
Name: "test.txt",
Content: []byte("This is a test text file.\n"),
Modified: time.Date(2010, 9, 5, 12, 12, 1, 0, timeZone(+10*time.Hour)),
Mode: 0644,
},
{
Name: "gophercolor16x16.png",
File: "gophercolor16x16.png",
Modified: time.Date(2010, 9, 5, 15, 52, 58, 0, timeZone(+10*time.Hour)),
Mode: 0644,
},
},
},
{
Name: "test-badbase.zip",
Comment: "This is a zipfile comment.",
File: []ZipTestFile{
{
Name: "test.txt",
Content: []byte("This is a test text file.\n"),
Modified: time.Date(2010, 9, 5, 12, 12, 1, 0, timeZone(+10*time.Hour)),
Mode: 0644,
},
{
Name: "gophercolor16x16.png",
File: "gophercolor16x16.png",
Modified: time.Date(2010, 9, 5, 15, 52, 58, 0, timeZone(+10*time.Hour)),
Mode: 0644,
},
},
},
{
Name: "r.zip",
Source: returnRecursiveZip,
File: []ZipTestFile{
{
Name: "r/r.zip",
Content: rZipBytes(),
Modified: time.Date(2010, 3, 4, 0, 24, 16, 0, time.UTC),
Mode: 0666,
},
},
},
{
Name: "symlink.zip",
File: []ZipTestFile{
{
Name: "symlink",
Content: []byte("../target"),
Modified: time.Date(2012, 2, 3, 19, 56, 48, 0, timeZone(-2*time.Hour)),
Mode: 0777 | fs.ModeSymlink,
},
},
},
{
Name: "readme.zip",
},
{
Name: "readme.notzip",
Error: ErrFormat,
},
{
Name: "dd.zip",
File: []ZipTestFile{
{
Name: "filename",
Content: []byte("This is a test textfile.\n"),
Modified: time.Date(2011, 2, 2, 13, 6, 20, 0, time.UTC),
Mode: 0666,
},
},
},
{
// created in windows XP file manager.
Name: "winxp.zip",
File: []ZipTestFile{
{
Name: "hello",
Content: []byte("world \r\n"),
Modified: time.Date(2011, 12, 8, 10, 4, 24, 0, time.UTC),
Mode: 0666,
},
{
Name: "dir/bar",
Content: []byte("foo \r\n"),
Modified: time.Date(2011, 12, 8, 10, 4, 50, 0, time.UTC),
Mode: 0666,
},
{
Name: "dir/empty/",
Content: []byte{},
Modified: time.Date(2011, 12, 8, 10, 8, 6, 0, time.UTC),
Mode: fs.ModeDir | 0777,
},
{
Name: "readonly",
Content: []byte("important \r\n"),
Modified: time.Date(2011, 12, 8, 10, 6, 8, 0, time.UTC),
Mode: 0444,
},
},
},
{
// created by Zip 3.0 under Linux
Name: "unix.zip",
File: []ZipTestFile{
{
Name: "hello",
Content: []byte("world \r\n"),
Modified: time.Date(2011, 12, 8, 10, 4, 24, 0, timeZone(0)),
Mode: 0666,
},
{
Name: "dir/bar",
Content: []byte("foo \r\n"),
Modified: time.Date(2011, 12, 8, 10, 4, 50, 0, timeZone(0)),
Mode: 0666,
},
{
Name: "dir/empty/",
Content: []byte{},
Modified: time.Date(2011, 12, 8, 10, 8, 6, 0, timeZone(0)),
Mode: fs.ModeDir | 0777,
},
{
Name: "readonly",
Content: []byte("important \r\n"),
Modified: time.Date(2011, 12, 8, 10, 6, 8, 0, timeZone(0)),
Mode: 0444,
},
},
},
{
// created by Go, before we wrote the "optional" data
// descriptor signatures (which are required by macOS).
// Use obscured file to avoid Apple’s notarization service
// rejecting the toolchain due to an inability to unzip this archive.
// See golang.org/issue/34986
Name: "go-no-datadesc-sig.zip.base64",
Obscured: true,
File: []ZipTestFile{
{
Name: "foo.txt",
Content: []byte("foo\n"),
Modified: time.Date(2012, 3, 8, 16, 59, 10, 0, timeZone(-8*time.Hour)),
Mode: 0644,
},
{
Name: "bar.txt",
Content: []byte("bar\n"),
Modified: time.Date(2012, 3, 8, 16, 59, 12, 0, timeZone(-8*time.Hour)),
Mode: 0644,
},
},
},
{
// created by Go, after we wrote the "optional" data
// descriptor signatures (which are required by macOS)
Name: "go-with-datadesc-sig.zip",
File: []ZipTestFile{
{
Name: "foo.txt",
Content: []byte("foo\n"),
Modified: time.Date(1979, 11, 30, 0, 0, 0, 0, time.UTC),
Mode: 0666,
},
{
Name: "bar.txt",
Content: []byte("bar\n"),
Modified: time.Date(1979, 11, 30, 0, 0, 0, 0, time.UTC),
Mode: 0666,
},
},
},
{
Name: "Bad-CRC32-in-data-descriptor",
Source: returnCorruptCRC32Zip,
File: []ZipTestFile{
{
Name: "foo.txt",
Content: []byte("foo\n"),
Modified: time.Date(1979, 11, 30, 0, 0, 0, 0, time.UTC),
Mode: 0666,
ContentErr: ErrChecksum,
},
{
Name: "bar.txt",
Content: []byte("bar\n"),
Modified: time.Date(1979, 11, 30, 0, 0, 0, 0, time.UTC),
Mode: 0666,
},
},
},
// Tests that we verify (and accept valid) crc32s on files
// with crc32s in their file header (not in data descriptors)
{
Name: "crc32-not-streamed.zip",
File: []ZipTestFile{
{
Name: "foo.txt",
Content: []byte("foo\n"),
Modified: time.Date(2012, 3, 8, 16, 59, 10, 0, timeZone(-8*time.Hour)),
Mode: 0644,
},
{
Name: "bar.txt",
Content: []byte("bar\n"),
Modified: time.Date(2012, 3, 8, 16, 59, 12, 0, timeZone(-8*time.Hour)),
Mode: 0644,
},
},
},
// Tests that we verify (and reject invalid) crc32s on files
// with crc32s in their file header (not in data descriptors)
{
Name: "crc32-not-streamed.zip",
Source: returnCorruptNotStreamedZip,
File: []ZipTestFile{
{
Name: "foo.txt",
Content: []byte("foo\n"),
Modified: time.Date(2012, 3, 8, 16, 59, 10, 0, timeZone(-8*time.Hour)),
Mode: 0644,
ContentErr: ErrChecksum,
},
{
Name: "bar.txt",
Content: []byte("bar\n"),
Modified: time.Date(2012, 3, 8, 16, 59, 12, 0, timeZone(-8*time.Hour)),
Mode: 0644,
},
},
},
{
Name: "zip64.zip",
File: []ZipTestFile{
{
Name: "README",
Content: []byte("This small file is in ZIP64 format.\n"),
Modified: time.Date(2012, 8, 10, 14, 33, 32, 0, time.UTC),
Mode: 0644,
},
},
},
// Another zip64 file with different Extras fields. (golang.org/issue/7069)
{
Name: "zip64-2.zip",
File: []ZipTestFile{
{
Name: "README",
Content: []byte("This small file is in ZIP64 format.\n"),
Modified: time.Date(2012, 8, 10, 14, 33, 32, 0, timeZone(-4*time.Hour)),
Mode: 0644,
},
},
},
// Largest possible non-zip64 file, with no zip64 header.
{
Name: "big.zip",
Source: returnBigZipBytes,
File: []ZipTestFile{
{
Name: "big.file",
Content: nil,
Size: 1<<32 - 1,
Modified: time.Date(1979, 11, 30, 0, 0, 0, 0, time.UTC),
Mode: 0666,
},
},
},
{
Name: "utf8-7zip.zip",
File: []ZipTestFile{
{
Name: "世界",
Content: []byte{},
Mode: 0666,
Modified: time.Date(2017, 11, 6, 13, 9, 27, 867862500, timeZone(-8*time.Hour)),
},
},
},
{
Name: "utf8-infozip.zip",
File: []ZipTestFile{
{
Name: "世界",
Content: []byte{},
Mode: 0644,
// Name is valid UTF-8, but format does not have UTF-8 flag set.
// We don't do UTF-8 detection for multi-byte runes due to
// false-positives with other encodings (e.g., Shift-JIS).
// Format says encoding is not UTF-8, so we trust it.
NonUTF8: true,
Modified: time.Date(2017, 11, 6, 13, 9, 27, 0, timeZone(-8*time.Hour)),
},
},
},
{
Name: "utf8-osx.zip",
File: []ZipTestFile{
{
Name: "世界",
Content: []byte{},
Mode: 0644,
// Name is valid UTF-8, but format does not have UTF-8 set.
NonUTF8: true,
Modified: time.Date(2017, 11, 6, 13, 9, 27, 0, timeZone(-8*time.Hour)),
},
},
},
{
Name: "utf8-winrar.zip",
File: []ZipTestFile{
{
Name: "世界",
Content: []byte{},
Mode: 0666,
Modified: time.Date(2017, 11, 6, 13, 9, 27, 867862500, timeZone(-8*time.Hour)),
},
},
},
{
Name: "utf8-winzip.zip",
File: []ZipTestFile{
{
Name: "世界",
Content: []byte{},
Mode: 0666,
Modified: time.Date(2017, 11, 6, 13, 9, 27, 867000000, timeZone(-8*time.Hour)),
},
},
},
{
Name: "time-7zip.zip",
File: []ZipTestFile{
{
Name: "test.txt",
Content: []byte{},
Size: 1<<32 - 1,
Modified: time.Date(2017, 10, 31, 21, 11, 57, 244817900, timeZone(-7*time.Hour)),
Mode: 0666,
},
},
},
{
Name: "time-infozip.zip",
File: []ZipTestFile{
{
Name: "test.txt",
Content: []byte{},
Size: 1<<32 - 1,
Modified: time.Date(2017, 10, 31, 21, 11, 57, 0, timeZone(-7*time.Hour)),
Mode: 0644,
},
},
},
{
Name: "time-osx.zip",
File: []ZipTestFile{
{
Name: "test.txt",
Content: []byte{},
Size: 1<<32 - 1,
Modified: time.Date(2017, 10, 31, 21, 11, 57, 0, timeZone(-7*time.Hour)),
Mode: 0644,
},
},
},
{
Name: "time-win7.zip",
File: []ZipTestFile{
{
Name: "test.txt",
Content: []byte{},
Size: 1<<32 - 1,
Modified: time.Date(2017, 10, 31, 21, 11, 58, 0, time.UTC),
Mode: 0666,
},
},
},
{
Name: "time-winrar.zip",
File: []ZipTestFile{
{
Name: "test.txt",
Content: []byte{},
Size: 1<<32 - 1,
Modified: time.Date(2017, 10, 31, 21, 11, 57, 244817900, timeZone(-7*time.Hour)),
Mode: 0666,
},
},
},
{
Name: "time-winzip.zip",
File: []ZipTestFile{
{
Name: "test.txt",
Content: []byte{},
Size: 1<<32 - 1,
Modified: time.Date(2017, 10, 31, 21, 11, 57, 244000000, timeZone(-7*time.Hour)),
Mode: 0666,
},
},
},
{
Name: "time-go.zip",
File: []ZipTestFile{
{
Name: "test.txt",
Content: []byte{},
Size: 1<<32 - 1,
Modified: time.Date(2017, 10, 31, 21, 11, 57, 0, timeZone(-7*time.Hour)),
Mode: 0666,
},
},
},
{
Name: "time-22738.zip",
File: []ZipTestFile{
{
Name: "file",
Content: []byte{},
Mode: 0666,
Modified: time.Date(1999, 12, 31, 19, 0, 0, 0, timeZone(-5*time.Hour)),
ModTime: time.Date(1999, 12, 31, 19, 0, 0, 0, time.UTC),
},
},
},
{
Name: "dupdir.zip",
File: []ZipTestFile{
{
Name: "a/",
Content: []byte{},
Mode: fs.ModeDir | 0666,
Modified: time.Date(2021, 12, 29, 0, 0, 0, 0, timeZone(0)),
},
{
Name: "a/b",
Content: []byte{},
Mode: 0666,
Modified: time.Date(2021, 12, 29, 0, 0, 0, 0, timeZone(0)),
},
{
Name: "a/b/",
Content: []byte{},
Mode: fs.ModeDir | 0666,
Modified: time.Date(2021, 12, 29, 0, 0, 0, 0, timeZone(0)),
},
{
Name: "a/b/c",
Content: []byte{},
Mode: 0666,
Modified: time.Date(2021, 12, 29, 0, 0, 0, 0, timeZone(0)),
},
},
},
// Issue 66869: Don't skip over an EOCDR with a truncated comment.
// The test file sneakily hides a second EOCDR before the first one;
// previously we would extract one file ("file") from this archive,
// while most other tools would reject the file or extract a different one ("FILE").
{
Name: "comment-truncated.zip",
Error: ErrFormat,
},
}
func TestReader(t *testing.T) {
for _, zt := range tests {
t.Run(zt.Name, func(t *testing.T) {
readTestZip(t, zt)
})
}
}
func readTestZip(t *testing.T, zt ZipTest) {
var z *Reader
var err error
var raw []byte
if zt.Source != nil {
rat, size := zt.Source()
z, err = NewReader(rat, size)
raw = make([]byte, size)
if _, err := rat.ReadAt(raw, 0); err != nil {
t.Errorf("ReadAt error=%v", err)
return
}
} else {
path := filepath.Join("testdata", zt.Name)
if zt.Obscured {
tf, err := decodeToTempFile(path)
if err != nil {
t.Errorf("obscuretestdata.DecodeToTempFile(%s): %v", path, err)
return
}
defer os.Remove(tf)
path = tf
}
var rc *ReadCloser
rc, err = OpenReader(path)
if err == nil {
defer rc.Close()
z = &rc.Reader
}
var err2 error
raw, err2 = os.ReadFile(path)
if err2 != nil {
t.Errorf("ReadFile(%s) error=%v", path, err2)
return
}
}
if err != zt.Error {
t.Errorf("error=%v, want %v", err, zt.Error)
return
}
// bail if file is not zip
if err == ErrFormat {
return
}
// bail here if no Files expected to be tested
// (there may actually be files in the zip, but we don't care)
if zt.File == nil {
return
}
if z.Comment != zt.Comment {
t.Errorf("comment=%q, want %q", z.Comment, zt.Comment)
}
if len(z.File) != len(zt.File) {
t.Fatalf("file count=%d, want %d", len(z.File), len(zt.File))
}
// test read of each file
for i, ft := range zt.File {
readTestFile(t, zt, ft, z.File[i], raw)
}
if t.Failed() {
return
}
// test simultaneous reads
n := 0
done := make(chan bool)
for i := 0; i < 5; i++ {
for j, ft := range zt.File {
go func(j int, ft ZipTestFile) {
readTestFile(t, zt, ft, z.File[j], raw)
done <- true
}(j, ft)
n++
}
}
for ; n > 0; n-- {
<-done
}
}
func equalTimeAndZone(t1, t2 time.Time) bool {
name1, offset1 := t1.Zone()
name2, offset2 := t2.Zone()
return t1.Equal(t2) && name1 == name2 && offset1 == offset2
}
func readTestFile(t *testing.T, zt ZipTest, ft ZipTestFile, f *File, raw []byte) {
if f.Name != ft.Name {
t.Errorf("name=%q, want %q", f.Name, ft.Name)
}
if !ft.Modified.IsZero() && !equalTimeAndZone(f.Modified, ft.Modified) {
t.Errorf("%s: Modified=%s, want %s", f.Name, f.Modified, ft.Modified)
}
if !ft.ModTime.IsZero() && !equalTimeAndZone(f.ModTime(), ft.ModTime) {
t.Errorf("%s: ModTime=%s, want %s", f.Name, f.ModTime(), ft.ModTime)
}
testFileMode(t, f, ft.Mode)
size := uint64(f.UncompressedSize)
if size == uint32max {
size = f.UncompressedSize64
} else if size != f.UncompressedSize64 {
t.Errorf("%v: UncompressedSize=%#x does not match UncompressedSize64=%#x", f.Name, size, f.UncompressedSize64)
}
// Check that OpenRaw returns the correct byte segment
rw, err := f.OpenRaw()
if err != nil {
t.Errorf("%v: OpenRaw error=%v", f.Name, err)
return
}
start, err := f.DataOffset()
if err != nil {
t.Errorf("%v: DataOffset error=%v", f.Name, err)
return
}
got, err := io.ReadAll(rw)
if err != nil {
t.Errorf("%v: OpenRaw ReadAll error=%v", f.Name, err)
return
}
end := uint64(start) + f.CompressedSize64
want := raw[start:end]
if !bytes.Equal(got, want) {
t.Logf("got %q", got)
t.Logf("want %q", want)
t.Errorf("%v: OpenRaw returned unexpected bytes", f.Name)
return
}
r, err := f.Open()
if err != nil {
t.Errorf("%v", err)
return
}
// For very large files, just check that the size is correct.
// The content is expected to be all zeros.
// Don't bother uncompressing: too big.
if ft.Content == nil && ft.File == "" && ft.Size > 0 {
if size != ft.Size {
t.Errorf("%v: uncompressed size %#x, want %#x", ft.Name, size, ft.Size)
}
r.Close()
return
}
var b bytes.Buffer
_, err = io.Copy(&b, r)
if err != ft.ContentErr {
t.Errorf("copying contents: %v (want %v)", err, ft.ContentErr)
}
if err != nil {
return
}
r.Close()
if g := uint64(b.Len()); g != size {
t.Errorf("%v: read %v bytes but f.UncompressedSize == %v", f.Name, g, size)
}
var c []byte
if ft.Content != nil {
c = ft.Content
} else if c, err = os.ReadFile("testdata/" + ft.File); err != nil {
t.Error(err)
return
}
if b.Len() != len(c) {
t.Errorf("%s: len=%d, want %d", f.Name, b.Len(), len(c))
return
}
for i, b := range b.Bytes() {
if b != c[i] {
t.Errorf("%s: content[%d]=%q want %q", f.Name, i, b, c[i])
return
}
}
}
func testFileMode(t *testing.T, f *File, want fs.FileMode) {
mode := f.Mode()
if want == 0 {
t.Errorf("%s mode: got %v, want none", f.Name, mode)
} else if mode != want {
t.Errorf("%s mode: want %v, got %v", f.Name, want, mode)
}
}
func TestInvalidFiles(t *testing.T) {
const size = 1024 * 70 // 70kb
b := make([]byte, size)
// zeroes
_, err := NewReader(bytes.NewReader(b), size)
if err != ErrFormat {
t.Errorf("zeroes: error=%v, want %v", err, ErrFormat)
}
// repeated directoryEndSignatures
sig := make([]byte, 4)
binary.LittleEndian.PutUint32(sig, directoryEndSignature)
for i := 0; i < size-4; i += 4 {
copy(b[i:i+4], sig)
}
_, err = NewReader(bytes.NewReader(b), size)
if err != ErrFormat {
t.Errorf("sigs: error=%v, want %v", err, ErrFormat)
}
// negative size
_, err = NewReader(bytes.NewReader([]byte("foobar")), -1)
if err == nil {
t.Errorf("archive/zip.NewReader: expected error when negative size is passed")
}
}
func messWith(fileName string, corrupter func(b []byte)) (r io.ReaderAt, size int64) {
data, err := os.ReadFile(filepath.Join("testdata", fileName))
if err != nil {
panic("Error reading " + fileName + ": " + err.Error())
}
corrupter(data)
return bytes.NewReader(data), int64(len(data))
}
func returnCorruptCRC32Zip() (r io.ReaderAt, size int64) {
return messWith("go-with-datadesc-sig.zip", func(b []byte) {
// Corrupt one of the CRC32s in the data descriptor:
b[0x2d]++
})
}
func returnCorruptNotStreamedZip() (r io.ReaderAt, size int64) {
return messWith("crc32-not-streamed.zip", func(b []byte) {
// Corrupt foo.txt's final crc32 byte, in both
// the file header and TOC. (0x7e -> 0x7f)
b[0x11]++
b[0x9d]++
// TODO(bradfitz): add a new test that only corrupts
// one of these values, and verify that that's also an
// error. Currently, the reader code doesn't verify the
// fileheader and TOC's crc32 match if they're both
// non-zero and only the second line above, the TOC,
// is what matters.
})
}
// rZipBytes returns the bytes of a recursive zip file, without
// putting it on disk and triggering certain virus scanners.
func rZipBytes() []byte {
s := `
0000000 50 4b 03 04 14 00 00 00 08 00 08 03 64 3c f9 f4
0000010 89 64 48 01 00 00 b8 01 00 00 07 00 00 00 72 2f
0000020 72 2e 7a 69 70 00 25 00 da ff 50 4b 03 04 14 00
0000030 00 00 08 00 08 03 64 3c f9 f4 89 64 48 01 00 00
0000040 b8 01 00 00 07 00 00 00 72 2f 72 2e 7a 69 70 00
0000050 2f 00 d0 ff 00 25 00 da ff 50 4b 03 04 14 00 00
0000060 00 08 00 08 03 64 3c f9 f4 89 64 48 01 00 00 b8
0000070 01 00 00 07 00 00 00 72 2f 72 2e 7a 69 70 00 2f
0000080 00 d0 ff c2 54 8e 57 39 00 05 00 fa ff c2 54 8e
0000090 57 39 00 05 00 fa ff 00 05 00 fa ff 00 14 00 eb
00000a0 ff c2 54 8e 57 39 00 05 00 fa ff 00 05 00 fa ff
00000b0 00 14 00 eb ff 42 88 21 c4 00 00 14 00 eb ff 42
00000c0 88 21 c4 00 00 14 00 eb ff 42 88 21 c4 00 00 14
00000d0 00 eb ff 42 88 21 c4 00 00 14 00 eb ff 42 88 21
00000e0 c4 00 00 00 00 ff ff 00 00 00 ff ff 00 34 00 cb
00000f0 ff 42 88 21 c4 00 00 00 00 ff ff 00 00 00 ff ff
0000100 00 34 00 cb ff 42 e8 21 5e 0f 00 00 00 ff ff 0a
0000110 f0 66 64 12 61 c0 15 dc e8 a0 48 bf 48 af 2a b3
0000120 20 c0 9b 95 0d c4 67 04 42 53 06 06 06 40 00 06
0000130 00 f9 ff 6d 01 00 00 00 00 42 e8 21 5e 0f 00 00
0000140 00 ff ff 0a f0 66 64 12 61 c0 15 dc e8 a0 48 bf
0000150 48 af 2a b3 20 c0 9b 95 0d c4 67 04 42 53 06 06
0000160 06 40 00 06 00 f9 ff 6d 01 00 00 00 00 50 4b 01
0000170 02 14 00 14 00 00 00 08 00 08 03 64 3c f9 f4 89
0000180 64 48 01 00 00 b8 01 00 00 07 00 00 00 00 00 00
0000190 00 00 00 00 00 00 00 00 00 00 00 72 2f 72 2e 7a
00001a0 69 70 50 4b 05 06 00 00 00 00 01 00 01 00 35 00
00001b0 00 00 6d 01 00 00 00 00`
s = regexp.MustCompile(`[0-9a-f]{7}`).ReplaceAllString(s, "")
s = regexp.MustCompile(`\s+`).ReplaceAllString(s, "")
b, err := hex.DecodeString(s)
if err != nil {
panic(err)
}
return b
}
func returnRecursiveZip() (r io.ReaderAt, size int64) {
b := rZipBytes()
return bytes.NewReader(b), int64(len(b))
}
// biggestZipBytes returns the bytes of a zip file biggest.zip
// that contains a zip file bigger.zip that contains a zip file
// big.zip that contains big.file, which contains 2³²-1 zeros.
// The big.zip file is interesting because it has no zip64 header,
// much like the innermost zip files in the well-known 42.zip.
//
// biggest.zip was generated by changing isZip64 to use > uint32max
// instead of >= uint32max and then running this program:
//
// package main
//
// import (
// "archive/zip"
// "bytes"
// "io"
// "log"
// "os"
// )
//
// type zeros struct{}
//
// func (zeros) Read(b []byte) (int, error) {
// clear(b)
// return len(b), nil
// }
//
// func main() {
// bigZip := makeZip("big.file", io.LimitReader(zeros{}, 1<<32-1))
// if err := os.WriteFile("/tmp/big.zip", bigZip, 0666); err != nil {
// log.Fatal(err)
// }
//
// biggerZip := makeZip("big.zip", bytes.NewReader(bigZip))
// if err := os.WriteFile("/tmp/bigger.zip", biggerZip, 0666); err != nil {
// log.Fatal(err)
// }
//
// biggestZip := makeZip("bigger.zip", bytes.NewReader(biggerZip))
// if err := os.WriteFile("/tmp/biggest.zip", biggestZip, 0666); err != nil {
// log.Fatal(err)
// }
// }
//
// func makeZip(name string, r io.Reader) []byte {
// var buf bytes.Buffer
// w := zip.NewWriter(&buf)
// wf, err := w.Create(name)
// if err != nil {
// log.Fatal(err)
// }
// if _, err = io.Copy(wf, r); err != nil {
// log.Fatal(err)
// }
// if err := w.Close(); err != nil {
// log.Fatal(err)
// }
// return buf.Bytes()
// }
//
// The 4 GB of zeros compresses to 4 MB, which compresses to 20 kB,
// which compresses to 1252 bytes (in the hex dump below).
//
// It's here in hex for the same reason as rZipBytes above: to avoid
// problems with on-disk virus scanners or other zip processors.
func biggestZipBytes() []byte {
s := `
0000000 50 4b 03 04 14 00 08 00 08 00 00 00 00 00 00 00
0000010 00 00 00 00 00 00 00 00 00 00 0a 00 00 00 62 69
0000020 67 67 65 72 2e 7a 69 70 ec dc 6b 4c 53 67 18 07
0000030 f0 16 c5 ca 65 2e cb b8 94 20 61 1f 44 33 c7 cd
0000040 c0 86 4a b5 c0 62 8a 61 05 c6 cd 91 b2 54 8c 1b
0000050 63 8b 03 9c 1b 95 52 5a e3 a0 19 6c b2 05 59 44
0000060 64 9d 73 83 71 11 46 61 14 b9 1d 14 09 4a c3 60
0000070 2e 4c 6e a5 60 45 02 62 81 95 b6 94 9e 9e 77 e7
0000080 d0 43 b6 f8 71 df 96 3c e7 a4 69 ce bf cf e9 79
0000090 ce ef 79 3f bf f1 31 db b6 bb 31 76 92 e7 f3 07
00000a0 8b fc 9c ca cc 08 cc cb cc 5e d2 1c 88 d9 7e bb
00000b0 4f bb 3a 3f 75 f1 5d 7f 8f c2 68 67 77 8f 25 ff
00000c0 84 e2 93 2d ef a4 95 3d 71 4e 2c b9 b0 87 c3 be
00000d0 3d f8 a7 60 24 61 c5 ef ae 9e c8 6c 6d 4e 69 c8
00000e0 67 65 34 f8 37 76 2d 76 5c 54 f3 95 65 49 c7 0f
00000f0 18 71 4b 7e 5b 6a d1 79 47 61 41 b0 4e 2a 74 45
0000100 43 58 12 b2 5a a5 c6 7d 68 55 88 d4 98 75 18 6d
0000110 08 d1 1f 8f 5a 9e 96 ee 45 cf a4 84 4e 4b e8 50
0000120 a7 13 d9 06 de 52 81 97 36 b2 d7 b8 fc 2b 5f 55
0000130 23 1f 32 59 cf 30 27 fb e2 8a b9 de 45 dd 63 9c
0000140 4b b5 8b 96 4c 7a 62 62 cc a1 a7 cf fa f1 fe dd
0000150 54 62 11 bf 36 78 b3 c7 b1 b5 f2 61 4d 4e dd 66
0000160 32 2e e6 70 34 5f f4 c9 e6 6c 43 6f da 6b c6 c3
0000170 09 2c ce 09 57 7f d2 7e b4 23 ba 7c 1b 99 bc 22
0000180 3e f1 de 91 2f e3 9c 1b 82 cc c2 84 39 aa e6 de
0000190 b4 69 fc cc cb 72 a6 61 45 f0 d3 1d 26 19 7c 8d
00001a0 29 c8 66 02 be 77 6a f9 3d 34 79 17 19 c8 96 24
00001b0 a3 ac e4 dd 3b 1a 8e c6 fe 96 38 6b bf 67 5a 23
00001c0 f4 16 f4 e6 8a b4 fc c2 cd bf 95 66 1d bb 35 aa
00001d0 92 7d 66 d8 08 8d a5 1f 54 2a af 09 cf 61 ff d2
00001e0 85 9d 8f b6 d7 88 07 4a 86 03 db 64 f3 d9 92 73
00001f0 df ec a7 fc 23 4c 8d 83 79 63 2a d9 fd 8d b3 c8
0000200 8f 7e d4 19 85 e6 8d 1c 76 f0 8b 58 32 fd 9a d6
0000210 85 e2 48 ad c3 d5 60 6f 7e 22 dd ef 09 49 7c 7f
0000220 3a 45 c3 71 b7 df f3 4c 63 fb b5 d9 31 5f 6e d6
0000230 24 1d a4 4a fe 32 a7 5c 16 48 5c 3e 08 6b 8a d3
0000240 25 1d a2 12 a5 59 24 ea 20 5f 52 6d ad 94 db 6b
0000250 94 b9 5d eb 4b a7 5c 44 bb 1e f2 3c 6b cf 52 c9
0000260 e9 e5 ba 06 b9 c4 e5 0a d0 00 0d d0 00 0d d0 00
0000270 0d d0 00 0d d0 00 0d d0 00 0d d0 00 0d d0 00 0d
0000280 d0 00 0d d0 00 0d d0 00 0d d0 00 0d d0 00 0d d0
0000290 00 0d d0 00 0d d0 00 0d d0 00 0d d0 00 0d d0 00