-
Notifications
You must be signed in to change notification settings - Fork 1.4k
Expand file tree
/
Copy pathzipfile.c
More file actions
2300 lines (2099 loc) · 66.6 KB
/
Copy pathzipfile.c
File metadata and controls
2300 lines (2099 loc) · 66.6 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
** 2017-12-26
**
** The author disclaims copyright to this source code. In place of
** a legal notice, here is a blessing:
**
** May you do good and not evil.
** May you find forgiveness for yourself and forgive others.
** May you share freely, never taking more than you give.
**
******************************************************************************
**
** This file implements a virtual table for reading and writing ZIP archive
** files.
**
** Usage example:
**
** SELECT name, sz, datetime(mtime,'unixepoch') FROM zipfile($filename);
**
** Current limitations:
**
** * No support for encryption
** * No support for ZIP archives spanning multiple files
** * No support for zip64 extensions
** * Only the "inflate/deflate" (zlib) compression method is supported
*/
#include "sqlite3ext.h"
SQLITE_EXTENSION_INIT1
#include <stdio.h>
#include <string.h>
#include <assert.h>
#ifndef SQLITE_NO_STDINT
# include <stdint.h>
#endif
#include <zlib.h>
/* When used as part of the CLI, the sqlite3_stdio.h module will have
** been included before this one. In that case use the sqlite3_stdio.h
** #defines. If not, create our own for fopen().
*/
#ifndef _SQLITE3_STDIO_H_
# define sqlite3_fopen fopen
#endif
#ifndef SQLITE_OMIT_VIRTUALTABLE
#ifndef SQLITE_AMALGAMATION
#ifndef UINT32_TYPE
# ifdef HAVE_UINT32_T
# define UINT32_TYPE uint32_t
# else
# define UINT32_TYPE unsigned int
# endif
#endif
#ifndef UINT16_TYPE
# ifdef HAVE_UINT16_T
# define UINT16_TYPE uint16_t
# else
# define UINT16_TYPE unsigned short int
# endif
#endif
typedef sqlite3_int64 i64;
typedef unsigned char u8;
typedef UINT32_TYPE u32; /* 4-byte unsigned integer */
typedef UINT16_TYPE u16; /* 2-byte unsigned integer */
#define MIN(a,b) ((a)<(b) ? (a) : (b))
#if defined(SQLITE_COVERAGE_TEST) || defined(SQLITE_MUTATION_TEST)
# define SQLITE_OMIT_AUXILIARY_SAFETY_CHECKS 1
#endif
#if defined(SQLITE_OMIT_AUXILIARY_SAFETY_CHECKS)
# define ALWAYS(X) (1)
# define NEVER(X) (0)
#elif !defined(NDEBUG)
# define ALWAYS(X) ((X)?1:(assert(0),0))
# define NEVER(X) ((X)?(assert(0),1):0)
#else
# define ALWAYS(X) (X)
# define NEVER(X) (X)
#endif
#endif /* SQLITE_AMALGAMATION */
/*
** Definitions for mode bitmasks S_IFDIR, S_IFREG and S_IFLNK.
**
** In some ways it would be better to obtain these values from system
** header files. But, the dependency is undesirable and (a) these
** have been stable for decades, (b) the values are part of POSIX and
** are also made explicit in [man stat], and (c) are part of the
** file format for zip archives.
*/
#ifndef S_IFDIR
# define S_IFDIR 0040000
#endif
#ifndef S_IFREG
# define S_IFREG 0100000
#endif
#ifndef S_IFLNK
# define S_IFLNK 0120000
#endif
static const char ZIPFILE_SCHEMA[] =
"CREATE TABLE y("
"name PRIMARY KEY," /* 0: Name of file in zip archive */
"mode," /* 1: POSIX mode for file */
"mtime," /* 2: Last modification time (secs since 1970)*/
"sz," /* 3: Size of object */
"rawdata," /* 4: Raw data */
"data," /* 5: Uncompressed data */
"method," /* 6: Compression method (integer) */
"z HIDDEN" /* 7: Name of zip file */
") WITHOUT ROWID;";
#define ZIPFILE_F_COLUMN_IDX 7 /* Index of column "file" in the above */
#define ZIPFILE_MX_NAME (250) /* Windows limitation on filename size */
/*
** The buffer should be large enough to contain 3 65536 byte strings - the
** filename, the extra field and the file comment.
*/
#define ZIPFILE_BUFFER_SIZE (200*1024)
/*
** Magic numbers used to read and write zip files.
**
** ZIPFILE_NEWENTRY_MADEBY:
** Use this value for the "version-made-by" field in new zip file
** entries. The upper byte indicates "unix", and the lower byte
** indicates that the zip file matches pkzip specification 3.0.
** This is what info-zip seems to do.
**
** ZIPFILE_NEWENTRY_REQUIRED:
** Value for "version-required-to-extract" field of new entries.
** Version 2.0 is required to support folders and deflate compression.
**
** ZIPFILE_NEWENTRY_FLAGS:
** Value for "general-purpose-bit-flags" field of new entries. Bit
** 11 means "utf-8 filename and comment".
**
** ZIPFILE_SIGNATURE_CDS:
** First 4 bytes of a valid CDS record.
**
** ZIPFILE_SIGNATURE_LFH:
** First 4 bytes of a valid LFH record.
**
** ZIPFILE_SIGNATURE_EOCD
** First 4 bytes of a valid EOCD record.
*/
#define ZIPFILE_EXTRA_TIMESTAMP 0x5455
#define ZIPFILE_NEWENTRY_MADEBY ((3<<8) + 30)
#define ZIPFILE_NEWENTRY_REQUIRED 20
#define ZIPFILE_NEWENTRY_FLAGS 0x800
#define ZIPFILE_SIGNATURE_CDS 0x02014b50
#define ZIPFILE_SIGNATURE_LFH 0x04034b50
#define ZIPFILE_SIGNATURE_EOCD 0x06054b50
/*
** The sizes of the fixed-size part of each of the three main data
** structures in a zip archive.
*/
#define ZIPFILE_LFH_FIXED_SZ 30
#define ZIPFILE_EOCD_FIXED_SZ 22
#define ZIPFILE_CDS_FIXED_SZ 46
/*
*** 4.3.16 End of central directory record:
***
*** end of central dir signature 4 bytes (0x06054b50)
*** number of this disk 2 bytes
*** number of the disk with the
*** start of the central directory 2 bytes
*** total number of entries in the
*** central directory on this disk 2 bytes
*** total number of entries in
*** the central directory 2 bytes
*** size of the central directory 4 bytes
*** offset of start of central
*** directory with respect to
*** the starting disk number 4 bytes
*** .ZIP file comment length 2 bytes
*** .ZIP file comment (variable size)
*/
typedef struct ZipfileEOCD ZipfileEOCD;
struct ZipfileEOCD {
u16 iDisk;
u16 iFirstDisk;
u16 nEntry;
u16 nEntryTotal;
u32 nSize;
u32 iOffset;
};
/*
*** 4.3.12 Central directory structure:
***
*** ...
***
*** central file header signature 4 bytes (0x02014b50)
*** version made by 2 bytes
*** version needed to extract 2 bytes
*** general purpose bit flag 2 bytes
*** compression method 2 bytes
*** last mod file time 2 bytes
*** last mod file date 2 bytes
*** crc-32 4 bytes
*** compressed size 4 bytes
*** uncompressed size 4 bytes
*** file name length 2 bytes
*** extra field length 2 bytes
*** file comment length 2 bytes
*** disk number start 2 bytes
*** internal file attributes 2 bytes
*** external file attributes 4 bytes
*** relative offset of local header 4 bytes
*/
typedef struct ZipfileCDS ZipfileCDS;
struct ZipfileCDS {
u16 iVersionMadeBy;
u16 iVersionExtract;
u16 flags;
u16 iCompression;
u16 mTime;
u16 mDate;
u32 crc32;
u32 szCompressed;
u32 szUncompressed;
u16 nFile;
u16 nExtra;
u16 nComment;
u16 iDiskStart;
u16 iInternalAttr;
u32 iExternalAttr;
u32 iOffset;
char *zFile; /* Filename (sqlite3_malloc()) */
};
/*
*** 4.3.7 Local file header:
***
*** local file header signature 4 bytes (0x04034b50)
*** version needed to extract 2 bytes
*** general purpose bit flag 2 bytes
*** compression method 2 bytes
*** last mod file time 2 bytes
*** last mod file date 2 bytes
*** crc-32 4 bytes
*** compressed size 4 bytes
*** uncompressed size 4 bytes
*** file name length 2 bytes
*** extra field length 2 bytes
***
*/
typedef struct ZipfileLFH ZipfileLFH;
struct ZipfileLFH {
u16 iVersionExtract;
u16 flags;
u16 iCompression;
u16 mTime;
u16 mDate;
u32 crc32;
u32 szCompressed;
u32 szUncompressed;
u16 nFile;
u16 nExtra;
};
typedef struct ZipfileEntry ZipfileEntry;
struct ZipfileEntry {
ZipfileCDS cds; /* Parsed CDS record */
u32 mUnixTime; /* Modification time, in UNIX format */
u8 *aExtra; /* cds.nExtra+cds.nComment bytes of extra data */
i64 iDataOff; /* Offset to data in file (if aData==0) */
u8 *aData; /* cds.szCompressed bytes of compressed data */
ZipfileEntry *pNext; /* Next element in in-memory CDS */
};
/*
** Cursor type for zipfile tables.
*/
typedef struct ZipfileCsr ZipfileCsr;
struct ZipfileCsr {
sqlite3_vtab_cursor base; /* Base class - must be first */
i64 iId; /* Cursor ID */
u8 bEof; /* True when at EOF */
u8 bNoop; /* If next xNext() call is no-op */
/* Used outside of write transactions */
FILE *pFile; /* Zip file */
i64 iNextOff; /* Offset of next record in central directory */
ZipfileEOCD eocd; /* Parse of central directory record */
ZipfileEntry *pFreeEntry; /* Free this list when cursor is closed or reset */
ZipfileEntry *pCurrent; /* Current entry */
ZipfileCsr *pCsrNext; /* Next cursor on same virtual table */
};
typedef struct ZipfileTab ZipfileTab;
struct ZipfileTab {
sqlite3_vtab base; /* Base class - must be first */
char *zFile; /* Zip file this table accesses (may be NULL) */
sqlite3 *db; /* Host database connection */
u8 *aBuffer; /* Temporary buffer used for various tasks */
ZipfileCsr *pCsrList; /* List of cursors */
i64 iNextCsrid;
/* The following are used by write transactions only */
ZipfileEntry *pFirstEntry; /* Linked list of all files (if pWriteFd!=0) */
ZipfileEntry *pLastEntry; /* Last element in pFirstEntry list */
FILE *pWriteFd; /* File handle open on zip archive */
i64 szCurrent; /* Current size of zip archive */
i64 szOrig; /* Size of archive at start of transaction */
};
/*
** Set the error message contained in context ctx to the results of
** vprintf(zFmt, ...).
*/
static void zipfileCtxErrorMsg(sqlite3_context *ctx, const char *zFmt, ...){
char *zMsg = 0;
va_list ap;
va_start(ap, zFmt);
zMsg = sqlite3_vmprintf(zFmt, ap);
sqlite3_result_error(ctx, zMsg, -1);
sqlite3_free(zMsg);
va_end(ap);
}
/*
** If string zIn is quoted, dequote it in place. Otherwise, if the string
** is not quoted, do nothing.
*/
static void zipfileDequote(char *zIn){
char q = zIn[0];
if( q=='"' || q=='\'' || q=='`' || q=='[' ){
int iIn = 1;
int iOut = 0;
if( q=='[' ) q = ']';
while( ALWAYS(zIn[iIn]) ){
char c = zIn[iIn++];
if( c==q && zIn[iIn++]!=q ) break;
zIn[iOut++] = c;
}
zIn[iOut] = '\0';
}
}
/*
** Construct a new ZipfileTab virtual table object.
**
** argv[0] -> module name ("zipfile")
** argv[1] -> database name
** argv[2] -> table name
** argv[...] -> "column name" and other module argument fields.
*/
static int zipfileConnect(
sqlite3 *db,
void *pAux,
int argc, const char *const*argv,
sqlite3_vtab **ppVtab,
char **pzErr
){
int nByte = sizeof(ZipfileTab) + ZIPFILE_BUFFER_SIZE;
int nFile = 0;
const char *zFile = 0;
ZipfileTab *pNew = 0;
int rc;
(void)pAux;
/* If the table name is not "zipfile", require that the argument be
** specified. This stops zipfile tables from being created as:
**
** CREATE VIRTUAL TABLE zzz USING zipfile();
**
** It does not prevent:
**
** CREATE VIRTUAL TABLE zipfile USING zipfile();
*/
assert( 0==sqlite3_stricmp(argv[0], "zipfile") );
if( (0!=sqlite3_stricmp(argv[2], "zipfile") && argc<4) || argc>4 ){
*pzErr = sqlite3_mprintf("zipfile constructor requires one argument");
return SQLITE_ERROR;
}
if( argc>3 ){
zFile = argv[3];
nFile = (int)strlen(zFile)+1;
}
rc = sqlite3_declare_vtab(db, ZIPFILE_SCHEMA);
if( rc==SQLITE_OK ){
pNew = (ZipfileTab*)sqlite3_malloc64((i64)nByte+nFile);
if( pNew==0 ) return SQLITE_NOMEM;
memset(pNew, 0, nByte+nFile);
pNew->db = db;
pNew->aBuffer = (u8*)&pNew[1];
if( zFile ){
pNew->zFile = (char*)&pNew->aBuffer[ZIPFILE_BUFFER_SIZE];
memcpy(pNew->zFile, zFile, nFile);
zipfileDequote(pNew->zFile);
}
}
sqlite3_vtab_config(db, SQLITE_VTAB_DIRECTONLY);
*ppVtab = (sqlite3_vtab*)pNew;
return rc;
}
/*
** Free the ZipfileEntry structure indicated by the only argument.
*/
static void zipfileEntryFree(ZipfileEntry *p){
if( p ){
sqlite3_free(p->cds.zFile);
sqlite3_free(p);
}
}
/*
** Release resources that should be freed at the end of a write
** transaction.
*/
static void zipfileCleanupTransaction(ZipfileTab *pTab){
ZipfileEntry *pEntry;
ZipfileEntry *pNext;
if( pTab->pWriteFd ){
fclose(pTab->pWriteFd);
pTab->pWriteFd = 0;
}
for(pEntry=pTab->pFirstEntry; pEntry; pEntry=pNext){
pNext = pEntry->pNext;
zipfileEntryFree(pEntry);
}
pTab->pFirstEntry = 0;
pTab->pLastEntry = 0;
pTab->szCurrent = 0;
pTab->szOrig = 0;
}
/*
** This method is the destructor for zipfile vtab objects.
*/
static int zipfileDisconnect(sqlite3_vtab *pVtab){
zipfileCleanupTransaction((ZipfileTab*)pVtab);
sqlite3_free(pVtab);
return SQLITE_OK;
}
/*
** Constructor for a new ZipfileCsr object.
*/
static int zipfileOpen(sqlite3_vtab *p, sqlite3_vtab_cursor **ppCsr){
ZipfileTab *pTab = (ZipfileTab*)p;
ZipfileCsr *pCsr;
pCsr = sqlite3_malloc64(sizeof(*pCsr));
*ppCsr = (sqlite3_vtab_cursor*)pCsr;
if( pCsr==0 ){
return SQLITE_NOMEM;
}
memset(pCsr, 0, sizeof(*pCsr));
pCsr->iId = ++pTab->iNextCsrid;
pCsr->pCsrNext = pTab->pCsrList;
pTab->pCsrList = pCsr;
return SQLITE_OK;
}
/*
** Reset a cursor back to the state it was in when first returned
** by zipfileOpen().
*/
static void zipfileResetCursor(ZipfileCsr *pCsr){
ZipfileEntry *p;
ZipfileEntry *pNext;
pCsr->bEof = 0;
if( pCsr->pFile ){
fclose(pCsr->pFile);
pCsr->pFile = 0;
zipfileEntryFree(pCsr->pCurrent);
pCsr->pCurrent = 0;
}
for(p=pCsr->pFreeEntry; p; p=pNext){
pNext = p->pNext;
zipfileEntryFree(p);
}
pCsr->pFreeEntry = 0;
}
/*
** Destructor for an ZipfileCsr.
*/
static int zipfileClose(sqlite3_vtab_cursor *cur){
ZipfileCsr *pCsr = (ZipfileCsr*)cur;
ZipfileTab *pTab = (ZipfileTab*)(pCsr->base.pVtab);
ZipfileCsr **pp;
zipfileResetCursor(pCsr);
/* Remove this cursor from the ZipfileTab.pCsrList list. */
for(pp=&pTab->pCsrList; *pp!=pCsr; pp=&((*pp)->pCsrNext));
*pp = pCsr->pCsrNext;
sqlite3_free(pCsr);
return SQLITE_OK;
}
/*
** Set the error message for the virtual table associated with cursor
** pCsr to the results of vprintf(zFmt, ...).
*/
static void zipfileTableErr(ZipfileTab *pTab, const char *zFmt, ...){
va_list ap;
va_start(ap, zFmt);
sqlite3_free(pTab->base.zErrMsg);
pTab->base.zErrMsg = sqlite3_vmprintf(zFmt, ap);
va_end(ap);
}
static void zipfileCursorErr(ZipfileCsr *pCsr, const char *zFmt, ...){
va_list ap;
va_start(ap, zFmt);
sqlite3_free(pCsr->base.pVtab->zErrMsg);
pCsr->base.pVtab->zErrMsg = sqlite3_vmprintf(zFmt, ap);
va_end(ap);
}
/*
** Read nRead bytes of data from offset iOff of file pFile into buffer
** aRead[]. Return SQLITE_OK if successful, or an SQLite error code
** otherwise.
**
** If an error does occur, output variable (*pzErrmsg) may be set to point
** to an English language error message. It is the responsibility of the
** caller to eventually free this buffer using
** sqlite3_free().
*/
static int zipfileReadData(
FILE *pFile, /* Read from this file */
u8 *aRead, /* Read into this buffer */
i64 nRead, /* Number of bytes to read */
i64 iOff, /* Offset to read from */
char **pzErrmsg /* OUT: Error message (from sqlite3_malloc) */
){
size_t n;
fseek(pFile, (long)iOff, SEEK_SET);
n = fread(aRead, 1, (long)nRead, pFile);
if( n!=(size_t)nRead ){
sqlite3_free(*pzErrmsg);
*pzErrmsg = sqlite3_mprintf("error in fread()");
return SQLITE_ERROR;
}
return SQLITE_OK;
}
static int zipfileAppendData(
ZipfileTab *pTab,
const u8 *aWrite,
int nWrite
){
if( nWrite>0 ){
size_t n = nWrite;
fseek(pTab->pWriteFd, (long)pTab->szCurrent, SEEK_SET);
n = fwrite(aWrite, 1, nWrite, pTab->pWriteFd);
if( (int)n!=nWrite ){
zipfileTableErr(pTab,"error in fwrite()");
return SQLITE_ERROR;
}
pTab->szCurrent += nWrite;
}
return SQLITE_OK;
}
/*
** Read and return a 16-bit little-endian unsigned integer from buffer aBuf.
*/
static u16 zipfileGetU16(const u8 *aBuf){
return (aBuf[1] << 8) + aBuf[0];
}
/*
** Read and return a 32-bit little-endian unsigned integer from buffer aBuf.
*/
static u32 zipfileGetU32(const u8 *aBuf){
if( aBuf==0 ) return 0;
return ((u32)(aBuf[3]) << 24)
+ ((u32)(aBuf[2]) << 16)
+ ((u32)(aBuf[1]) << 8)
+ ((u32)(aBuf[0]) << 0);
}
/*
** Write a 16-bit little endiate integer into buffer aBuf.
*/
static void zipfilePutU16(u8 *aBuf, u16 val){
aBuf[0] = val & 0xFF;
aBuf[1] = (val>>8) & 0xFF;
}
/*
** Write a 32-bit little endiate integer into buffer aBuf.
*/
static void zipfilePutU32(u8 *aBuf, u32 val){
aBuf[0] = val & 0xFF;
aBuf[1] = (val>>8) & 0xFF;
aBuf[2] = (val>>16) & 0xFF;
aBuf[3] = (val>>24) & 0xFF;
}
#define zipfileRead32(aBuf) ( aBuf+=4, zipfileGetU32(aBuf-4) )
#define zipfileRead16(aBuf) ( aBuf+=2, zipfileGetU16(aBuf-2) )
#define zipfileWrite32(aBuf,val) { zipfilePutU32(aBuf,val); aBuf+=4; }
#define zipfileWrite16(aBuf,val) { zipfilePutU16(aBuf,val); aBuf+=2; }
/*
** Magic numbers used to read CDS records.
*/
#define ZIPFILE_CDS_NFILE_OFF 28
#define ZIPFILE_CDS_SZCOMPRESSED_OFF 20
/*
** Decode the CDS record in buffer aBuf into (*pCDS). Return SQLITE_ERROR
** if the record is not well-formed, or SQLITE_OK otherwise.
*/
static int zipfileReadCDS(u8 *aBuf, ZipfileCDS *pCDS){
u8 *aRead = aBuf;
u32 sig = zipfileRead32(aRead);
int rc = SQLITE_OK;
if( sig!=ZIPFILE_SIGNATURE_CDS ){
rc = SQLITE_ERROR;
}else{
pCDS->iVersionMadeBy = zipfileRead16(aRead);
pCDS->iVersionExtract = zipfileRead16(aRead);
pCDS->flags = zipfileRead16(aRead);
pCDS->iCompression = zipfileRead16(aRead);
pCDS->mTime = zipfileRead16(aRead);
pCDS->mDate = zipfileRead16(aRead);
pCDS->crc32 = zipfileRead32(aRead);
pCDS->szCompressed = zipfileRead32(aRead);
pCDS->szUncompressed = zipfileRead32(aRead);
assert( aRead==&aBuf[ZIPFILE_CDS_NFILE_OFF] );
pCDS->nFile = zipfileRead16(aRead);
pCDS->nExtra = zipfileRead16(aRead);
pCDS->nComment = zipfileRead16(aRead);
pCDS->iDiskStart = zipfileRead16(aRead);
pCDS->iInternalAttr = zipfileRead16(aRead);
pCDS->iExternalAttr = zipfileRead32(aRead);
pCDS->iOffset = zipfileRead32(aRead);
assert( aRead==&aBuf[ZIPFILE_CDS_FIXED_SZ] );
}
return rc;
}
/*
** Decode the LFH record in buffer aBuf into (*pLFH). Return SQLITE_ERROR
** if the record is not well-formed, or SQLITE_OK otherwise.
*/
static int zipfileReadLFH(
u8 *aBuffer,
ZipfileLFH *pLFH
){
u8 *aRead = aBuffer;
int rc = SQLITE_OK;
u32 sig = zipfileRead32(aRead);
if( sig!=ZIPFILE_SIGNATURE_LFH ){
rc = SQLITE_ERROR;
}else{
pLFH->iVersionExtract = zipfileRead16(aRead);
pLFH->flags = zipfileRead16(aRead);
pLFH->iCompression = zipfileRead16(aRead);
pLFH->mTime = zipfileRead16(aRead);
pLFH->mDate = zipfileRead16(aRead);
pLFH->crc32 = zipfileRead32(aRead);
pLFH->szCompressed = zipfileRead32(aRead);
pLFH->szUncompressed = zipfileRead32(aRead);
pLFH->nFile = zipfileRead16(aRead);
pLFH->nExtra = zipfileRead16(aRead);
if( pLFH->nFile>ZIPFILE_MX_NAME ) rc = SQLITE_ERROR;
}
return rc;
}
/*
** Buffer aExtra (size nExtra bytes) contains zip archive "extra" fields.
** Scan through this buffer to find an "extra-timestamp" field. If one
** exists, extract the 32-bit modification-timestamp from it and store
** the value in output parameter *pmTime.
**
** Zero is returned if no extra-timestamp record could be found (and so
** *pmTime is left unchanged), or non-zero otherwise.
**
** The general format of an extra field is:
**
** Header ID 2 bytes
** Data Size 2 bytes
** Data N bytes
*/
static int zipfileScanExtra(u8 *aExtra, int nExtra, u32 *pmTime){
int ret = 0;
u8 *p = aExtra;
u8 *pEnd = &aExtra[nExtra];
/* Stop when there are less than 9 bytes left to scan in the buffer. This
** is because the timestamp field requires exactly 9 bytes - 4 bytes of
** header fields and 5 bytes of data. If there are less than 9 bytes
** remaining, either it is some other field or else the extra data
** is corrupt. Either way, do not process it. */
while( p+(2*sizeof(u16) + 1 + sizeof(u32))<=pEnd ){
u16 id = zipfileRead16(p);
u16 nByte = zipfileRead16(p);
switch( id ){
case ZIPFILE_EXTRA_TIMESTAMP: {
u8 b = p[0];
if( b & 0x01 ){ /* 0x01 -> modtime is present */
*pmTime = zipfileGetU32(&p[1]);
ret = 1;
}
break;
}
}
p += nByte;
}
return ret;
}
/*
** Convert the standard MS-DOS timestamp stored in the mTime and mDate
** fields of the CDS structure passed as the only argument to a 32-bit
** UNIX seconds-since-the-epoch timestamp. Return the result.
**
** "Standard" MS-DOS time format:
**
** File modification time:
** Bits 00-04: seconds divided by 2
** Bits 05-10: minute
** Bits 11-15: hour
** File modification date:
** Bits 00-04: day
** Bits 05-08: month (1-12)
** Bits 09-15: years from 1980
**
** https://msdn.microsoft.com/en-us/library/9kkf9tah.aspx
*/
static u32 zipfileMtime(ZipfileCDS *pCDS){
int Y,M,D,X1,X2,A,B,sec,min,hr;
i64 JDsec;
Y = (1980 + ((pCDS->mDate >> 9) & 0x7F));
M = ((pCDS->mDate >> 5) & 0x0F);
D = (pCDS->mDate & 0x1F);
sec = (pCDS->mTime & 0x1F)*2;
min = (pCDS->mTime >> 5) & 0x3F;
hr = (pCDS->mTime >> 11) & 0x1F;
if( M<=2 ){
Y--;
M += 12;
}
X1 = 36525*(Y+4716)/100;
X2 = 306001*(M+1)/10000;
A = Y/100;
B = 2 - A + (A/4);
JDsec = (i64)((X1 + X2 + D + B - 1524.5)*86400) + hr*3600 + min*60 + sec;
return (u32)(JDsec - (i64)24405875*(i64)8640);
}
/*
** The opposite of zipfileMtime(). This function populates the mTime and
** mDate fields of the CDS structure passed as the first argument according
** to the UNIX timestamp value passed as the second.
*/
static void zipfileMtimeToDos(ZipfileCDS *pCds, u32 mUnixTime){
/* Convert unix timestamp to JD (2440588 is noon on 1/1/1970) */
i64 JD = (i64)2440588 + mUnixTime / (24*60*60);
int A, B, C, D, E;
int yr, mon, day;
int hr, min, sec;
A = (int)((JD - 1867216.25)/36524.25);
A = (int)(JD + 1 + A - (A/4));
B = A + 1524;
C = (int)((B - 122.1)/365.25);
D = (36525*(C&32767))/100;
E = (int)((B-D)/30.6001);
day = B - D - (int)(30.6001*E);
mon = (E<14 ? E-1 : E-13);
yr = mon>2 ? C-4716 : C-4715;
hr = (mUnixTime % (24*60*60)) / (60*60);
min = (mUnixTime % (60*60)) / 60;
sec = (mUnixTime % 60);
if( yr>=1980 ){
pCds->mDate = (u16)(day + (mon << 5) + ((yr-1980) << 9));
pCds->mTime = (u16)(sec/2 + (min<<5) + (hr<<11));
}else{
pCds->mDate = pCds->mTime = 0;
}
assert( mUnixTime<315507600
|| mUnixTime==zipfileMtime(pCds)
|| ((mUnixTime % 2) && mUnixTime-1==zipfileMtime(pCds))
/* || (mUnixTime % 2) */
);
}
/*
** Set (*pzErr) to point to a buffer from sqlite3_malloc() containing a
** generic corruption message and return SQLITE_CORRUPT;
*/
static int zipfileCorrupt(char **pzErr){
sqlite3_free(*pzErr);
*pzErr = sqlite3_mprintf("zip archive is corrupt");
return SQLITE_CORRUPT;
}
/*
** If aBlob is not NULL, then it is a pointer to a buffer (nBlob bytes in
** size) containing an entire zip archive image. Or, if aBlob is NULL,
** then pFile is a file-handle open on a zip file. In either case, this
** function creates a ZipfileEntry object based on the zip archive entry
** for which the CDS record is at offset iOff.
**
** If successful, SQLITE_OK is returned and (*ppEntry) set to point to
** the new object. Otherwise, an SQLite error code is returned and the
** final value of (*ppEntry) undefined.
*/
static int zipfileGetEntry(
ZipfileTab *pTab, /* Store any error message here */
const u8 *aBlob, /* Pointer to in-memory file image */
i64 nBlob, /* Size of aBlob[] in bytes */
FILE *pFile, /* If aBlob==0, read from this file */
i64 iOff, /* Offset of CDS record */
ZipfileEntry **ppEntry /* OUT: Pointer to new object */
){
u8 *aRead;
char **pzErr = &pTab->base.zErrMsg;
int rc = SQLITE_OK;
if( aBlob==0 ){
aRead = pTab->aBuffer;
rc = zipfileReadData(pFile, aRead, ZIPFILE_CDS_FIXED_SZ, iOff, pzErr);
}else{
if( (iOff+ZIPFILE_CDS_FIXED_SZ)>nBlob ){
/* Not enough data for the CDS structure. Corruption. */
return zipfileCorrupt(pzErr);
}
aRead = (u8*)&aBlob[iOff];
}
if( rc==SQLITE_OK ){
sqlite3_int64 nAlloc;
ZipfileEntry *pNew;
int nFile = zipfileGetU16(&aRead[ZIPFILE_CDS_NFILE_OFF]);
int nExtra = zipfileGetU16(&aRead[ZIPFILE_CDS_NFILE_OFF+2]);
nExtra += zipfileGetU16(&aRead[ZIPFILE_CDS_NFILE_OFF+4]);
nAlloc = sizeof(ZipfileEntry) + nExtra;
if( aBlob ){
nAlloc += zipfileGetU32(&aRead[ZIPFILE_CDS_SZCOMPRESSED_OFF]);
}
pNew = (ZipfileEntry*)sqlite3_malloc64(nAlloc);
if( pNew==0 ){
rc = SQLITE_NOMEM;
}else{
memset(pNew, 0, sizeof(ZipfileEntry));
rc = zipfileReadCDS(aRead, &pNew->cds);
if( rc!=SQLITE_OK ){
zipfileTableErr(pTab, "failed to read CDS at offset %lld", iOff);
}else if( aBlob==0 ){
rc = zipfileReadData(
pFile, aRead, nExtra+nFile, iOff+ZIPFILE_CDS_FIXED_SZ, pzErr
);
}else{
aRead = (u8*)&aBlob[iOff + ZIPFILE_CDS_FIXED_SZ];
if( (iOff + ZIPFILE_CDS_FIXED_SZ + nFile + nExtra)>nBlob ){
rc = zipfileCorrupt(pzErr);
}
}
}
if( rc==SQLITE_OK ){
u32 *pt = &pNew->mUnixTime;
/* aRead[0..nFile-1] might contain embedded \000 characters
** See Bug 2026-05-31T11:43:05Z */
pNew->cds.zFile = sqlite3_malloc64(nFile+1);
if( pNew->cds.zFile!=0 ){
memcpy(pNew->cds.zFile, aRead, nFile);
pNew->cds.zFile[nFile] = 0;
}
pNew->aExtra = (u8*)&pNew[1];
memcpy(pNew->aExtra, &aRead[nFile], nExtra);
if( pNew->cds.zFile==0 ){
rc = SQLITE_NOMEM;
}else if( 0==zipfileScanExtra(&aRead[nFile], pNew->cds.nExtra, pt) ){
pNew->mUnixTime = zipfileMtime(&pNew->cds);
}
}
if( rc==SQLITE_OK ){
static const int szFix = ZIPFILE_LFH_FIXED_SZ;
ZipfileLFH lfh;
if( pFile ){
rc = zipfileReadData(pFile, aRead, szFix, pNew->cds.iOffset, pzErr);
}else{
aRead = (u8*)&aBlob[pNew->cds.iOffset];
if( ((i64)pNew->cds.iOffset + ZIPFILE_LFH_FIXED_SZ)>nBlob ){
rc = zipfileCorrupt(pzErr);
}
}
memset(&lfh, 0, sizeof(lfh));
if( rc==SQLITE_OK ) rc = zipfileReadLFH(aRead, &lfh);
if( rc==SQLITE_OK ){
pNew->iDataOff = (i64)pNew->cds.iOffset + ZIPFILE_LFH_FIXED_SZ;
pNew->iDataOff += lfh.nFile + lfh.nExtra;
if( aBlob && pNew->cds.szCompressed ){
if( pNew->iDataOff + pNew->cds.szCompressed > nBlob ){
rc = zipfileCorrupt(pzErr);
}else{
pNew->aData = &pNew->aExtra[nExtra];
memcpy(pNew->aData, &aBlob[pNew->iDataOff], pNew->cds.szCompressed);
}
}
}else{
zipfileTableErr(pTab, "failed to read LFH at offset %d",
(int)pNew->cds.iOffset
);
}
}
if( rc!=SQLITE_OK ){
zipfileEntryFree(pNew);
}else{
*ppEntry = pNew;
}
}
return rc;
}
/*
** Advance an ZipfileCsr to its next row of output.
*/
static int zipfileNext(sqlite3_vtab_cursor *cur){
ZipfileCsr *pCsr = (ZipfileCsr*)cur;
int rc = SQLITE_OK;
if( pCsr->pFile ){
i64 iEof = (i64)pCsr->eocd.iOffset + (i64)pCsr->eocd.nSize;
zipfileEntryFree(pCsr->pCurrent);
pCsr->pCurrent = 0;
if( pCsr->iNextOff>=iEof ){
pCsr->bEof = 1;
}else{
ZipfileEntry *p = 0;
ZipfileTab *pTab = (ZipfileTab*)(cur->pVtab);
rc = zipfileGetEntry(pTab, 0, 0, pCsr->pFile, pCsr->iNextOff, &p);
if( rc==SQLITE_OK ){
pCsr->iNextOff += ZIPFILE_CDS_FIXED_SZ;
pCsr->iNextOff += (int)p->cds.nExtra + p->cds.nFile + p->cds.nComment;
}
pCsr->pCurrent = p;
}
}else{
if( !pCsr->bNoop ){
pCsr->pCurrent = pCsr->pCurrent->pNext;
}
if( pCsr->pCurrent==0 ){
pCsr->bEof = 1;
}
}
pCsr->bNoop = 0;
return rc;
}
static void zipfileFree(void *p) {
sqlite3_free(p);
}
/*
** Buffer aIn (size nIn bytes) contains compressed data. Uncompressed, the
** size is nOut bytes. This function uncompresses the data and sets the
** return value in context pCtx to the result (a blob).
**
** If an error occurs, an error code is left in pCtx instead.
*/
static void zipfileInflate(
sqlite3_context *pCtx, /* Store result here */