forked from git/git
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathbuiltin-pack-objects.c
1741 lines (1564 loc) · 43.9 KB
/
builtin-pack-objects.c
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
#include "builtin.h"
#include "cache.h"
#include "object.h"
#include "blob.h"
#include "commit.h"
#include "tag.h"
#include "tree.h"
#include "delta.h"
#include "pack.h"
#include "csum-file.h"
#include "tree-walk.h"
#include "diff.h"
#include "revision.h"
#include "list-objects.h"
#include "progress.h"
static const char pack_usage[] = "\
git-pack-objects [{ -q | --progress | --all-progress }] \n\
[--local] [--incremental] [--window=N] [--depth=N] \n\
[--no-reuse-delta] [--no-reuse-object] [--delta-base-offset] \n\
[--non-empty] [--revs [--unpacked | --all]*] [--reflog] \n\
[--stdout | base-name] [<ref-list | <object-list]";
struct object_entry {
unsigned char sha1[20];
uint32_t crc32; /* crc of raw pack data for this object */
off_t offset; /* offset into the final pack file */
unsigned long size; /* uncompressed size */
unsigned int hash; /* name hint hash */
unsigned int depth; /* delta depth */
struct packed_git *in_pack; /* already in pack */
off_t in_pack_offset;
struct object_entry *delta; /* delta base object */
struct object_entry *delta_child; /* deltified objects who bases me */
struct object_entry *delta_sibling; /* other deltified objects who
* uses the same base as me
*/
unsigned long delta_size; /* delta data size (uncompressed) */
enum object_type type;
enum object_type in_pack_type; /* could be delta */
unsigned char in_pack_header_size;
unsigned char preferred_base; /* we do not pack this, but is available
* to be used as the base objectto delta
* objects against.
*/
};
/*
* Objects we are going to pack are collected in objects array (dynamically
* expanded). nr_objects & nr_alloc controls this array. They are stored
* in the order we see -- typically rev-list --objects order that gives us
* nice "minimum seek" order.
*/
static struct object_entry *objects;
static uint32_t nr_objects, nr_alloc, nr_result;
static int non_empty;
static int no_reuse_delta, no_reuse_object;
static int local;
static int incremental;
static int allow_ofs_delta;
static const char *pack_tmp_name, *idx_tmp_name;
static char tmpname[PATH_MAX];
static unsigned char pack_file_sha1[20];
static int progress = 1;
static int window = 10;
static int depth = 50;
static int pack_to_stdout;
static int num_preferred_base;
static struct progress progress_state;
static int pack_compression_level = Z_DEFAULT_COMPRESSION;
static int pack_compression_seen;
/*
* The object names in objects array are hashed with this hashtable,
* to help looking up the entry by object name.
* This hashtable is built after all the objects are seen.
*/
static int *object_ix;
static int object_ix_hashsz;
/*
* Pack index for existing packs give us easy access to the offsets into
* corresponding pack file where each object's data starts, but the entries
* do not store the size of the compressed representation (uncompressed
* size is easily available by examining the pack entry header). It is
* also rather expensive to find the sha1 for an object given its offset.
*
* We build a hashtable of existing packs (pack_revindex), and keep reverse
* index here -- pack index file is sorted by object name mapping to offset;
* this pack_revindex[].revindex array is a list of offset/index_nr pairs
* ordered by offset, so if you know the offset of an object, next offset
* is where its packed representation ends and the index_nr can be used to
* get the object sha1 from the main index.
*/
struct revindex_entry {
off_t offset;
unsigned int nr;
};
struct pack_revindex {
struct packed_git *p;
struct revindex_entry *revindex;
};
static struct pack_revindex *pack_revindex;
static int pack_revindex_hashsz;
/*
* stats
*/
static uint32_t written, written_delta;
static uint32_t reused, reused_delta;
static int pack_revindex_ix(struct packed_git *p)
{
unsigned long ui = (unsigned long)p;
int i;
ui = ui ^ (ui >> 16); /* defeat structure alignment */
i = (int)(ui % pack_revindex_hashsz);
while (pack_revindex[i].p) {
if (pack_revindex[i].p == p)
return i;
if (++i == pack_revindex_hashsz)
i = 0;
}
return -1 - i;
}
static void prepare_pack_ix(void)
{
int num;
struct packed_git *p;
for (num = 0, p = packed_git; p; p = p->next)
num++;
if (!num)
return;
pack_revindex_hashsz = num * 11;
pack_revindex = xcalloc(sizeof(*pack_revindex), pack_revindex_hashsz);
for (p = packed_git; p; p = p->next) {
num = pack_revindex_ix(p);
num = - 1 - num;
pack_revindex[num].p = p;
}
/* revindex elements are lazily initialized */
}
static int cmp_offset(const void *a_, const void *b_)
{
const struct revindex_entry *a = a_;
const struct revindex_entry *b = b_;
return (a->offset < b->offset) ? -1 : (a->offset > b->offset) ? 1 : 0;
}
/*
* Ordered list of offsets of objects in the pack.
*/
static void prepare_pack_revindex(struct pack_revindex *rix)
{
struct packed_git *p = rix->p;
int num_ent = p->num_objects;
int i;
const char *index = p->index_data;
rix->revindex = xmalloc(sizeof(*rix->revindex) * (num_ent + 1));
index += 4 * 256;
if (p->index_version > 1) {
const uint32_t *off_32 =
(uint32_t *)(index + 8 + p->num_objects * (20 + 4));
const uint32_t *off_64 = off_32 + p->num_objects;
for (i = 0; i < num_ent; i++) {
uint32_t off = ntohl(*off_32++);
if (!(off & 0x80000000)) {
rix->revindex[i].offset = off;
} else {
rix->revindex[i].offset =
((uint64_t)ntohl(*off_64++)) << 32;
rix->revindex[i].offset |=
ntohl(*off_64++);
}
rix->revindex[i].nr = i;
}
} else {
for (i = 0; i < num_ent; i++) {
uint32_t hl = *((uint32_t *)(index + 24 * i));
rix->revindex[i].offset = ntohl(hl);
rix->revindex[i].nr = i;
}
}
/* This knows the pack format -- the 20-byte trailer
* follows immediately after the last object data.
*/
rix->revindex[num_ent].offset = p->pack_size - 20;
rix->revindex[num_ent].nr = -1;
qsort(rix->revindex, num_ent, sizeof(*rix->revindex), cmp_offset);
}
static struct revindex_entry * find_packed_object(struct packed_git *p,
off_t ofs)
{
int num;
int lo, hi;
struct pack_revindex *rix;
struct revindex_entry *revindex;
num = pack_revindex_ix(p);
if (num < 0)
die("internal error: pack revindex uninitialized");
rix = &pack_revindex[num];
if (!rix->revindex)
prepare_pack_revindex(rix);
revindex = rix->revindex;
lo = 0;
hi = p->num_objects + 1;
do {
int mi = (lo + hi) / 2;
if (revindex[mi].offset == ofs) {
return revindex + mi;
}
else if (ofs < revindex[mi].offset)
hi = mi;
else
lo = mi + 1;
} while (lo < hi);
die("internal error: pack revindex corrupt");
}
static const unsigned char *find_packed_object_name(struct packed_git *p,
off_t ofs)
{
struct revindex_entry *entry = find_packed_object(p, ofs);
return nth_packed_object_sha1(p, entry->nr);
}
static void *delta_against(void *buf, unsigned long size, struct object_entry *entry)
{
unsigned long othersize, delta_size;
enum object_type type;
void *otherbuf = read_sha1_file(entry->delta->sha1, &type, &othersize);
void *delta_buf;
if (!otherbuf)
die("unable to read %s", sha1_to_hex(entry->delta->sha1));
delta_buf = diff_delta(otherbuf, othersize,
buf, size, &delta_size, 0);
if (!delta_buf || delta_size != entry->delta_size)
die("delta size changed");
free(buf);
free(otherbuf);
return delta_buf;
}
/*
* The per-object header is a pretty dense thing, which is
* - first byte: low four bits are "size", then three bits of "type",
* and the high bit is "size continues".
* - each byte afterwards: low seven bits are size continuation,
* with the high bit being "size continues"
*/
static int encode_header(enum object_type type, unsigned long size, unsigned char *hdr)
{
int n = 1;
unsigned char c;
if (type < OBJ_COMMIT || type > OBJ_REF_DELTA)
die("bad type %d", type);
c = (type << 4) | (size & 15);
size >>= 4;
while (size) {
*hdr++ = c | 0x80;
c = size & 0x7f;
size >>= 7;
n++;
}
*hdr = c;
return n;
}
/*
* we are going to reuse the existing object data as is. make
* sure it is not corrupt.
*/
static int check_pack_inflate(struct packed_git *p,
struct pack_window **w_curs,
off_t offset,
off_t len,
unsigned long expect)
{
z_stream stream;
unsigned char fakebuf[4096], *in;
int st;
memset(&stream, 0, sizeof(stream));
inflateInit(&stream);
do {
in = use_pack(p, w_curs, offset, &stream.avail_in);
stream.next_in = in;
stream.next_out = fakebuf;
stream.avail_out = sizeof(fakebuf);
st = inflate(&stream, Z_FINISH);
offset += stream.next_in - in;
} while (st == Z_OK || st == Z_BUF_ERROR);
inflateEnd(&stream);
return (st == Z_STREAM_END &&
stream.total_out == expect &&
stream.total_in == len) ? 0 : -1;
}
static int check_pack_crc(struct packed_git *p, struct pack_window **w_curs,
off_t offset, off_t len, unsigned int nr)
{
const uint32_t *index_crc;
uint32_t data_crc = crc32(0, Z_NULL, 0);
do {
unsigned int avail;
void *data = use_pack(p, w_curs, offset, &avail);
if (avail > len)
avail = len;
data_crc = crc32(data_crc, data, avail);
offset += avail;
len -= avail;
} while (len);
index_crc = p->index_data;
index_crc += 2 + 256 + p->num_objects * (20/4) + nr;
return data_crc != ntohl(*index_crc);
}
static void copy_pack_data(struct sha1file *f,
struct packed_git *p,
struct pack_window **w_curs,
off_t offset,
off_t len)
{
unsigned char *in;
unsigned int avail;
while (len) {
in = use_pack(p, w_curs, offset, &avail);
if (avail > len)
avail = (unsigned int)len;
sha1write(f, in, avail);
offset += avail;
len -= avail;
}
}
static unsigned long write_object(struct sha1file *f,
struct object_entry *entry)
{
unsigned long size;
enum object_type type;
void *buf;
unsigned char header[10];
unsigned hdrlen;
off_t datalen;
enum object_type obj_type;
int to_reuse = 0;
if (!pack_to_stdout)
crc32_begin(f);
obj_type = entry->type;
if (no_reuse_object)
to_reuse = 0; /* explicit */
else if (!entry->in_pack)
to_reuse = 0; /* can't reuse what we don't have */
else if (obj_type == OBJ_REF_DELTA || obj_type == OBJ_OFS_DELTA)
to_reuse = 1; /* check_object() decided it for us */
else if (obj_type != entry->in_pack_type)
to_reuse = 0; /* pack has delta which is unusable */
else if (entry->delta)
to_reuse = 0; /* we want to pack afresh */
else
to_reuse = 1; /* we have it in-pack undeltified,
* and we do not need to deltify it.
*/
if (!to_reuse) {
buf = read_sha1_file(entry->sha1, &type, &size);
if (!buf)
die("unable to read %s", sha1_to_hex(entry->sha1));
if (size != entry->size)
die("object %s size inconsistency (%lu vs %lu)",
sha1_to_hex(entry->sha1), size, entry->size);
if (entry->delta) {
buf = delta_against(buf, size, entry);
size = entry->delta_size;
obj_type = (allow_ofs_delta && entry->delta->offset) ?
OBJ_OFS_DELTA : OBJ_REF_DELTA;
}
/*
* The object header is a byte of 'type' followed by zero or
* more bytes of length.
*/
hdrlen = encode_header(obj_type, size, header);
sha1write(f, header, hdrlen);
if (obj_type == OBJ_OFS_DELTA) {
/*
* Deltas with relative base contain an additional
* encoding of the relative offset for the delta
* base from this object's position in the pack.
*/
off_t ofs = entry->offset - entry->delta->offset;
unsigned pos = sizeof(header) - 1;
header[pos] = ofs & 127;
while (ofs >>= 7)
header[--pos] = 128 | (--ofs & 127);
sha1write(f, header + pos, sizeof(header) - pos);
hdrlen += sizeof(header) - pos;
} else if (obj_type == OBJ_REF_DELTA) {
/*
* Deltas with a base reference contain
* an additional 20 bytes for the base sha1.
*/
sha1write(f, entry->delta->sha1, 20);
hdrlen += 20;
}
datalen = sha1write_compressed(f, buf, size, pack_compression_level);
free(buf);
}
else {
struct packed_git *p = entry->in_pack;
struct pack_window *w_curs = NULL;
struct revindex_entry *revidx;
off_t offset;
if (entry->delta) {
obj_type = (allow_ofs_delta && entry->delta->offset) ?
OBJ_OFS_DELTA : OBJ_REF_DELTA;
reused_delta++;
}
hdrlen = encode_header(obj_type, entry->size, header);
sha1write(f, header, hdrlen);
if (obj_type == OBJ_OFS_DELTA) {
off_t ofs = entry->offset - entry->delta->offset;
unsigned pos = sizeof(header) - 1;
header[pos] = ofs & 127;
while (ofs >>= 7)
header[--pos] = 128 | (--ofs & 127);
sha1write(f, header + pos, sizeof(header) - pos);
hdrlen += sizeof(header) - pos;
} else if (obj_type == OBJ_REF_DELTA) {
sha1write(f, entry->delta->sha1, 20);
hdrlen += 20;
}
offset = entry->in_pack_offset;
revidx = find_packed_object(p, offset);
datalen = revidx[1].offset - offset;
if (!pack_to_stdout && p->index_version > 1 &&
check_pack_crc(p, &w_curs, offset, datalen, revidx->nr))
die("bad packed object CRC for %s", sha1_to_hex(entry->sha1));
offset += entry->in_pack_header_size;
datalen -= entry->in_pack_header_size;
if (!pack_to_stdout && p->index_version == 1 &&
check_pack_inflate(p, &w_curs, offset, datalen, entry->size))
die("corrupt packed object for %s", sha1_to_hex(entry->sha1));
copy_pack_data(f, p, &w_curs, offset, datalen);
unuse_pack(&w_curs);
reused++;
}
if (entry->delta)
written_delta++;
written++;
if (!pack_to_stdout)
entry->crc32 = crc32_end(f);
return hdrlen + datalen;
}
static off_t write_one(struct sha1file *f,
struct object_entry *e,
off_t offset)
{
unsigned long size;
/* offset is non zero if object is written already. */
if (e->offset || e->preferred_base)
return offset;
/* if we are deltified, write out base object first. */
if (e->delta)
offset = write_one(f, e->delta, offset);
e->offset = offset;
size = write_object(f, e);
/* make sure off_t is sufficiently large not to wrap */
if (offset > offset + size)
die("pack too large for current definition of off_t");
return offset + size;
}
static int open_object_dir_tmp(const char *path)
{
snprintf(tmpname, sizeof(tmpname), "%s/%s", get_object_directory(), path);
return mkstemp(tmpname);
}
static off_t write_pack_file(void)
{
uint32_t i;
struct sha1file *f;
off_t offset, last_obj_offset = 0;
struct pack_header hdr;
int do_progress = progress;
if (pack_to_stdout) {
f = sha1fd(1, "<stdout>");
do_progress >>= 1;
} else {
int fd = open_object_dir_tmp("tmp_pack_XXXXXX");
if (fd < 0)
die("unable to create %s: %s\n", tmpname, strerror(errno));
pack_tmp_name = xstrdup(tmpname);
f = sha1fd(fd, pack_tmp_name);
}
if (do_progress)
start_progress(&progress_state, "Writing %u objects...", "", nr_result);
hdr.hdr_signature = htonl(PACK_SIGNATURE);
hdr.hdr_version = htonl(PACK_VERSION);
hdr.hdr_entries = htonl(nr_result);
sha1write(f, &hdr, sizeof(hdr));
offset = sizeof(hdr);
if (!nr_result)
goto done;
for (i = 0; i < nr_objects; i++) {
last_obj_offset = offset;
offset = write_one(f, objects + i, offset);
if (do_progress)
display_progress(&progress_state, written);
}
if (do_progress)
stop_progress(&progress_state);
done:
if (written != nr_result)
die("wrote %u objects while expecting %u", written, nr_result);
sha1close(f, pack_file_sha1, 1);
return last_obj_offset;
}
static int sha1_sort(const void *_a, const void *_b)
{
const struct object_entry *a = *(struct object_entry **)_a;
const struct object_entry *b = *(struct object_entry **)_b;
return hashcmp(a->sha1, b->sha1);
}
static uint32_t index_default_version = 1;
static uint32_t index_off32_limit = 0x7fffffff;
static void write_index_file(off_t last_obj_offset, unsigned char *sha1)
{
struct sha1file *f;
struct object_entry **sorted_by_sha, **list, **last;
uint32_t array[256];
uint32_t i, index_version;
SHA_CTX ctx;
int fd = open_object_dir_tmp("tmp_idx_XXXXXX");
if (fd < 0)
die("unable to create %s: %s\n", tmpname, strerror(errno));
idx_tmp_name = xstrdup(tmpname);
f = sha1fd(fd, idx_tmp_name);
if (nr_result) {
uint32_t j = 0;
sorted_by_sha =
xcalloc(nr_result, sizeof(struct object_entry *));
for (i = 0; i < nr_objects; i++)
if (!objects[i].preferred_base)
sorted_by_sha[j++] = objects + i;
if (j != nr_result)
die("listed %u objects while expecting %u", j, nr_result);
qsort(sorted_by_sha, nr_result, sizeof(*sorted_by_sha), sha1_sort);
list = sorted_by_sha;
last = sorted_by_sha + nr_result;
} else
sorted_by_sha = list = last = NULL;
/* if last object's offset is >= 2^31 we should use index V2 */
index_version = (last_obj_offset >> 31) ? 2 : index_default_version;
/* index versions 2 and above need a header */
if (index_version >= 2) {
struct pack_idx_header hdr;
hdr.idx_signature = htonl(PACK_IDX_SIGNATURE);
hdr.idx_version = htonl(index_version);
sha1write(f, &hdr, sizeof(hdr));
}
/*
* Write the first-level table (the list is sorted,
* but we use a 256-entry lookup to be able to avoid
* having to do eight extra binary search iterations).
*/
for (i = 0; i < 256; i++) {
struct object_entry **next = list;
while (next < last) {
struct object_entry *entry = *next;
if (entry->sha1[0] != i)
break;
next++;
}
array[i] = htonl(next - sorted_by_sha);
list = next;
}
sha1write(f, array, 256 * 4);
/* Compute the SHA1 hash of sorted object names. */
SHA1_Init(&ctx);
/* Write the actual SHA1 entries. */
list = sorted_by_sha;
for (i = 0; i < nr_result; i++) {
struct object_entry *entry = *list++;
if (index_version < 2) {
uint32_t offset = htonl(entry->offset);
sha1write(f, &offset, 4);
}
sha1write(f, entry->sha1, 20);
SHA1_Update(&ctx, entry->sha1, 20);
}
if (index_version >= 2) {
unsigned int nr_large_offset = 0;
/* write the crc32 table */
list = sorted_by_sha;
for (i = 0; i < nr_objects; i++) {
struct object_entry *entry = *list++;
uint32_t crc32_val = htonl(entry->crc32);
sha1write(f, &crc32_val, 4);
}
/* write the 32-bit offset table */
list = sorted_by_sha;
for (i = 0; i < nr_objects; i++) {
struct object_entry *entry = *list++;
uint32_t offset = (entry->offset <= index_off32_limit) ?
entry->offset : (0x80000000 | nr_large_offset++);
offset = htonl(offset);
sha1write(f, &offset, 4);
}
/* write the large offset table */
list = sorted_by_sha;
while (nr_large_offset) {
struct object_entry *entry = *list++;
uint64_t offset = entry->offset;
if (offset > index_off32_limit) {
uint32_t split[2];
split[0] = htonl(offset >> 32);
split[1] = htonl(offset & 0xffffffff);
sha1write(f, split, 8);
nr_large_offset--;
}
}
}
sha1write(f, pack_file_sha1, 20);
sha1close(f, NULL, 1);
free(sorted_by_sha);
SHA1_Final(sha1, &ctx);
}
static int locate_object_entry_hash(const unsigned char *sha1)
{
int i;
unsigned int ui;
memcpy(&ui, sha1, sizeof(unsigned int));
i = ui % object_ix_hashsz;
while (0 < object_ix[i]) {
if (!hashcmp(sha1, objects[object_ix[i] - 1].sha1))
return i;
if (++i == object_ix_hashsz)
i = 0;
}
return -1 - i;
}
static struct object_entry *locate_object_entry(const unsigned char *sha1)
{
int i;
if (!object_ix_hashsz)
return NULL;
i = locate_object_entry_hash(sha1);
if (0 <= i)
return &objects[object_ix[i]-1];
return NULL;
}
static void rehash_objects(void)
{
uint32_t i;
struct object_entry *oe;
object_ix_hashsz = nr_objects * 3;
if (object_ix_hashsz < 1024)
object_ix_hashsz = 1024;
object_ix = xrealloc(object_ix, sizeof(int) * object_ix_hashsz);
memset(object_ix, 0, sizeof(int) * object_ix_hashsz);
for (i = 0, oe = objects; i < nr_objects; i++, oe++) {
int ix = locate_object_entry_hash(oe->sha1);
if (0 <= ix)
continue;
ix = -1 - ix;
object_ix[ix] = i + 1;
}
}
static unsigned name_hash(const char *name)
{
unsigned char c;
unsigned hash = 0;
/*
* This effectively just creates a sortable number from the
* last sixteen non-whitespace characters. Last characters
* count "most", so things that end in ".c" sort together.
*/
while ((c = *name++) != 0) {
if (isspace(c))
continue;
hash = (hash >> 2) + (c << 24);
}
return hash;
}
static int add_object_entry(const unsigned char *sha1, enum object_type type,
unsigned hash, int exclude)
{
struct object_entry *entry;
struct packed_git *p, *found_pack = NULL;
off_t found_offset = 0;
int ix;
ix = nr_objects ? locate_object_entry_hash(sha1) : -1;
if (ix >= 0) {
if (exclude) {
entry = objects + object_ix[ix] - 1;
if (!entry->preferred_base)
nr_result--;
entry->preferred_base = 1;
}
return 0;
}
for (p = packed_git; p; p = p->next) {
off_t offset = find_pack_entry_one(sha1, p);
if (offset) {
if (!found_pack) {
found_offset = offset;
found_pack = p;
}
if (exclude)
break;
if (incremental)
return 0;
if (local && !p->pack_local)
return 0;
}
}
if (nr_objects >= nr_alloc) {
nr_alloc = (nr_alloc + 1024) * 3 / 2;
objects = xrealloc(objects, nr_alloc * sizeof(*entry));
}
entry = objects + nr_objects++;
memset(entry, 0, sizeof(*entry));
hashcpy(entry->sha1, sha1);
entry->hash = hash;
if (type)
entry->type = type;
if (exclude)
entry->preferred_base = 1;
else
nr_result++;
if (found_pack) {
entry->in_pack = found_pack;
entry->in_pack_offset = found_offset;
}
if (object_ix_hashsz * 3 <= nr_objects * 4)
rehash_objects();
else
object_ix[-1 - ix] = nr_objects;
if (progress)
display_progress(&progress_state, nr_objects);
return 1;
}
struct pbase_tree_cache {
unsigned char sha1[20];
int ref;
int temporary;
void *tree_data;
unsigned long tree_size;
};
static struct pbase_tree_cache *(pbase_tree_cache[256]);
static int pbase_tree_cache_ix(const unsigned char *sha1)
{
return sha1[0] % ARRAY_SIZE(pbase_tree_cache);
}
static int pbase_tree_cache_ix_incr(int ix)
{
return (ix+1) % ARRAY_SIZE(pbase_tree_cache);
}
static struct pbase_tree {
struct pbase_tree *next;
/* This is a phony "cache" entry; we are not
* going to evict it nor find it through _get()
* mechanism -- this is for the toplevel node that
* would almost always change with any commit.
*/
struct pbase_tree_cache pcache;
} *pbase_tree;
static struct pbase_tree_cache *pbase_tree_get(const unsigned char *sha1)
{
struct pbase_tree_cache *ent, *nent;
void *data;
unsigned long size;
enum object_type type;
int neigh;
int my_ix = pbase_tree_cache_ix(sha1);
int available_ix = -1;
/* pbase-tree-cache acts as a limited hashtable.
* your object will be found at your index or within a few
* slots after that slot if it is cached.
*/
for (neigh = 0; neigh < 8; neigh++) {
ent = pbase_tree_cache[my_ix];
if (ent && !hashcmp(ent->sha1, sha1)) {
ent->ref++;
return ent;
}
else if (((available_ix < 0) && (!ent || !ent->ref)) ||
((0 <= available_ix) &&
(!ent && pbase_tree_cache[available_ix])))
available_ix = my_ix;
if (!ent)
break;
my_ix = pbase_tree_cache_ix_incr(my_ix);
}
/* Did not find one. Either we got a bogus request or
* we need to read and perhaps cache.
*/
data = read_sha1_file(sha1, &type, &size);
if (!data)
return NULL;
if (type != OBJ_TREE) {
free(data);
return NULL;
}
/* We need to either cache or return a throwaway copy */
if (available_ix < 0)
ent = NULL;
else {
ent = pbase_tree_cache[available_ix];
my_ix = available_ix;
}
if (!ent) {
nent = xmalloc(sizeof(*nent));
nent->temporary = (available_ix < 0);
}
else {
/* evict and reuse */
free(ent->tree_data);
nent = ent;
}
hashcpy(nent->sha1, sha1);
nent->tree_data = data;
nent->tree_size = size;
nent->ref = 1;
if (!nent->temporary)
pbase_tree_cache[my_ix] = nent;
return nent;
}
static void pbase_tree_put(struct pbase_tree_cache *cache)
{
if (!cache->temporary) {
cache->ref--;
return;
}
free(cache->tree_data);
free(cache);
}
static int name_cmp_len(const char *name)
{
int i;
for (i = 0; name[i] && name[i] != '\n' && name[i] != '/'; i++)
;
return i;
}
static void add_pbase_object(struct tree_desc *tree,
const char *name,
int cmplen,
const char *fullname)
{
struct name_entry entry;
int cmp;
while (tree_entry(tree,&entry)) {
cmp = tree_entry_len(entry.path, entry.sha1) != cmplen ? 1 :
memcmp(name, entry.path, cmplen);
if (cmp > 0)
continue;
if (cmp < 0)
return;
if (name[cmplen] != '/') {
unsigned hash = name_hash(fullname);
add_object_entry(entry.sha1,
S_ISDIR(entry.mode) ? OBJ_TREE : OBJ_BLOB,
hash, 1);
return;
}
if (S_ISDIR(entry.mode)) {
struct tree_desc sub;
struct pbase_tree_cache *tree;
const char *down = name+cmplen+1;
int downlen = name_cmp_len(down);
tree = pbase_tree_get(entry.sha1);
if (!tree)
return;
init_tree_desc(&sub, tree->tree_data, tree->tree_size);
add_pbase_object(&sub, down, downlen, fullname);
pbase_tree_put(tree);
}
}
}
static unsigned *done_pbase_paths;
static int done_pbase_paths_num;
static int done_pbase_paths_alloc;
static int done_pbase_path_pos(unsigned hash)
{
int lo = 0;
int hi = done_pbase_paths_num;
while (lo < hi) {
int mi = (hi + lo) / 2;
if (done_pbase_paths[mi] == hash)
return mi;
if (done_pbase_paths[mi] < hash)
hi = mi;
else
lo = mi + 1;
}
return -lo-1;
}
static int check_pbase_path(unsigned hash)
{
int pos = (!done_pbase_paths) ? -1 : done_pbase_path_pos(hash);
if (0 <= pos)
return 1;
pos = -pos - 1;
if (done_pbase_paths_alloc <= done_pbase_paths_num) {
done_pbase_paths_alloc = alloc_nr(done_pbase_paths_alloc);
done_pbase_paths = xrealloc(done_pbase_paths,
done_pbase_paths_alloc *
sizeof(unsigned));
}
done_pbase_paths_num++;
if (pos < done_pbase_paths_num)
memmove(done_pbase_paths + pos + 1,
done_pbase_paths + pos,
(done_pbase_paths_num - pos - 1) * sizeof(unsigned));
done_pbase_paths[pos] = hash;
return 0;
}
static void add_preferred_base_object(const char *name, unsigned hash)
{
struct pbase_tree *it;
int cmplen;