-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathfast-export.c
1260 lines (1112 loc) · 33.2 KB
/
fast-export.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
/*
* "git fast-export" builtin command
*
* Copyright (C) 2007 Johannes E. Schindelin
*/
#include "builtin.h"
#include "cache.h"
#include "config.h"
#include "refs.h"
#include "refspec.h"
#include "object-store.h"
#include "commit.h"
#include "object.h"
#include "tag.h"
#include "diff.h"
#include "diffcore.h"
#include "log-tree.h"
#include "revision.h"
#include "decorate.h"
#include "string-list.h"
#include "utf8.h"
#include "parse-options.h"
#include "quote.h"
#include "remote.h"
#include "blob.h"
#include "commit-slab.h"
static const char *fast_export_usage[] = {
N_("git fast-export [rev-list-opts]"),
NULL
};
static int progress;
static enum { SIGNED_TAG_ABORT, VERBATIM, WARN, WARN_STRIP, STRIP } signed_tag_mode = SIGNED_TAG_ABORT;
static enum { TAG_FILTERING_ABORT, DROP, REWRITE } tag_of_filtered_mode = TAG_FILTERING_ABORT;
static enum { REENCODE_ABORT, REENCODE_YES, REENCODE_NO } reencode_mode = REENCODE_ABORT;
static int fake_missing_tagger;
static int use_done_feature;
static int no_data;
static int full_tree;
static int reference_excluded_commits;
static int show_original_ids;
static int mark_tags;
static struct string_list extra_refs = STRING_LIST_INIT_NODUP;
static struct string_list tag_refs = STRING_LIST_INIT_NODUP;
static struct refspec refspecs = REFSPEC_INIT_FETCH;
static int anonymize;
static struct revision_sources revision_sources;
static int parse_opt_signed_tag_mode(const struct option *opt,
const char *arg, int unset)
{
if (unset || !strcmp(arg, "abort"))
signed_tag_mode = SIGNED_TAG_ABORT;
else if (!strcmp(arg, "verbatim") || !strcmp(arg, "ignore"))
signed_tag_mode = VERBATIM;
else if (!strcmp(arg, "warn"))
signed_tag_mode = WARN;
else if (!strcmp(arg, "warn-strip"))
signed_tag_mode = WARN_STRIP;
else if (!strcmp(arg, "strip"))
signed_tag_mode = STRIP;
else
return error("Unknown signed-tags mode: %s", arg);
return 0;
}
static int parse_opt_tag_of_filtered_mode(const struct option *opt,
const char *arg, int unset)
{
if (unset || !strcmp(arg, "abort"))
tag_of_filtered_mode = TAG_FILTERING_ABORT;
else if (!strcmp(arg, "drop"))
tag_of_filtered_mode = DROP;
else if (!strcmp(arg, "rewrite"))
tag_of_filtered_mode = REWRITE;
else
return error("Unknown tag-of-filtered mode: %s", arg);
return 0;
}
static int parse_opt_reencode_mode(const struct option *opt,
const char *arg, int unset)
{
if (unset) {
reencode_mode = REENCODE_ABORT;
return 0;
}
switch (git_parse_maybe_bool(arg)) {
case 0:
reencode_mode = REENCODE_NO;
break;
case 1:
reencode_mode = REENCODE_YES;
break;
default:
if (!strcasecmp(arg, "abort"))
reencode_mode = REENCODE_ABORT;
else
return error("Unknown reencoding mode: %s", arg);
}
return 0;
}
static struct decoration idnums;
static uint32_t last_idnum;
static int has_unshown_parent(struct commit *commit)
{
struct commit_list *parent;
for (parent = commit->parents; parent; parent = parent->next)
if (!(parent->item->object.flags & SHOWN) &&
!(parent->item->object.flags & UNINTERESTING))
return 1;
return 0;
}
struct anonymized_entry {
struct hashmap_entry hash;
const char *orig;
size_t orig_len;
const char *anon;
size_t anon_len;
};
static int anonymized_entry_cmp(const void *unused_cmp_data,
const struct hashmap_entry *eptr,
const struct hashmap_entry *entry_or_key,
const void *unused_keydata)
{
const struct anonymized_entry *a, *b;
a = container_of(eptr, const struct anonymized_entry, hash);
b = container_of(entry_or_key, const struct anonymized_entry, hash);
return a->orig_len != b->orig_len ||
memcmp(a->orig, b->orig, a->orig_len);
}
/*
* Basically keep a cache of X->Y so that we can repeatedly replace
* the same anonymized string with another. The actual generation
* is farmed out to the generate function.
*/
static const void *anonymize_mem(struct hashmap *map,
void *(*generate)(const void *, size_t *),
const void *orig, size_t *len)
{
struct anonymized_entry key, *ret;
if (!map->cmpfn)
hashmap_init(map, anonymized_entry_cmp, NULL, 0);
hashmap_entry_init(&key.hash, memhash(orig, *len));
key.orig = orig;
key.orig_len = *len;
ret = hashmap_get_entry(map, &key, hash, NULL);
if (!ret) {
ret = xmalloc(sizeof(*ret));
hashmap_entry_init(&ret->hash, key.hash.hash);
ret->orig = xstrdup(orig);
ret->orig_len = *len;
ret->anon = generate(orig, len);
ret->anon_len = *len;
hashmap_put(map, &ret->hash);
}
*len = ret->anon_len;
return ret->anon;
}
/*
* We anonymize each component of a path individually,
* so that paths a/b and a/c will share a common root.
* The paths are cached via anonymize_mem so that repeated
* lookups for "a" will yield the same value.
*/
static void anonymize_path(struct strbuf *out, const char *path,
struct hashmap *map,
void *(*generate)(const void *, size_t *))
{
while (*path) {
const char *end_of_component = strchrnul(path, '/');
size_t len = end_of_component - path;
const char *c = anonymize_mem(map, generate, path, &len);
strbuf_add(out, c, len);
path = end_of_component;
if (*path)
strbuf_addch(out, *path++);
}
}
static inline void *mark_to_ptr(uint32_t mark)
{
return (void *)(uintptr_t)mark;
}
static inline uint32_t ptr_to_mark(void * mark)
{
return (uint32_t)(uintptr_t)mark;
}
static inline void mark_object(struct object *object, uint32_t mark)
{
add_decoration(&idnums, object, mark_to_ptr(mark));
}
static inline void mark_next_object(struct object *object)
{
mark_object(object, ++last_idnum);
}
static int get_object_mark(struct object *object)
{
void *decoration = lookup_decoration(&idnums, object);
if (!decoration)
return 0;
return ptr_to_mark(decoration);
}
static struct commit *rewrite_commit(struct commit *p)
{
for (;;) {
if (p->parents && p->parents->next)
break;
if (p->object.flags & UNINTERESTING)
break;
if (!(p->object.flags & TREESAME))
break;
if (!p->parents)
return NULL;
p = p->parents->item;
}
return p;
}
static void show_progress(void)
{
static int counter = 0;
if (!progress)
return;
if ((++counter % progress) == 0)
printf("progress %d objects\n", counter);
}
/*
* Ideally we would want some transformation of the blob data here
* that is unreversible, but would still be the same size and have
* the same data relationship to other blobs (so that we get the same
* delta and packing behavior as the original). But the first and last
* requirements there are probably mutually exclusive, so let's take
* the easy way out for now, and just generate arbitrary content.
*
* There's no need to cache this result with anonymize_mem, since
* we already handle blob content caching with marks.
*/
static char *anonymize_blob(unsigned long *size)
{
static int counter;
struct strbuf out = STRBUF_INIT;
strbuf_addf(&out, "anonymous blob %d", counter++);
*size = out.len;
return strbuf_detach(&out, NULL);
}
static void export_blob(const struct object_id *oid)
{
unsigned long size;
enum object_type type;
char *buf;
struct object *object;
int eaten;
if (no_data)
return;
if (is_null_oid(oid))
return;
object = lookup_object(the_repository, oid);
if (object && object->flags & SHOWN)
return;
if (anonymize) {
buf = anonymize_blob(&size);
object = (struct object *)lookup_blob(the_repository, oid);
eaten = 0;
} else {
buf = read_object_file(oid, &type, &size);
if (!buf)
die("could not read blob %s", oid_to_hex(oid));
if (check_object_signature(the_repository, oid, buf, size,
type_name(type)) < 0)
die("oid mismatch in blob %s", oid_to_hex(oid));
object = parse_object_buffer(the_repository, oid, type,
size, buf, &eaten);
}
if (!object)
die("Could not read blob %s", oid_to_hex(oid));
mark_next_object(object);
printf("blob\nmark :%"PRIu32"\n", last_idnum);
if (show_original_ids)
printf("original-oid %s\n", oid_to_hex(oid));
printf("data %"PRIuMAX"\n", (uintmax_t)size);
if (size && fwrite(buf, size, 1, stdout) != 1)
die_errno("could not write blob '%s'", oid_to_hex(oid));
printf("\n");
show_progress();
object->flags |= SHOWN;
if (!eaten)
free(buf);
}
static int depth_first(const void *a_, const void *b_)
{
const struct diff_filepair *a = *((const struct diff_filepair **)a_);
const struct diff_filepair *b = *((const struct diff_filepair **)b_);
const char *name_a, *name_b;
int len_a, len_b, len;
int cmp;
name_a = a->one ? a->one->path : a->two->path;
name_b = b->one ? b->one->path : b->two->path;
len_a = strlen(name_a);
len_b = strlen(name_b);
len = (len_a < len_b) ? len_a : len_b;
/* strcmp will sort 'd' before 'd/e', we want 'd/e' before 'd' */
cmp = memcmp(name_a, name_b, len);
if (cmp)
return cmp;
cmp = len_b - len_a;
if (cmp)
return cmp;
/*
* Move 'R'ename entries last so that all references of the file
* appear in the output before it is renamed (e.g., when a file
* was copied and renamed in the same commit).
*/
return (a->status == 'R') - (b->status == 'R');
}
static void print_path_1(const char *path)
{
int need_quote = quote_c_style(path, NULL, NULL, 0);
if (need_quote)
quote_c_style(path, NULL, stdout, 0);
else if (strchr(path, ' '))
printf("\"%s\"", path);
else
printf("%s", path);
}
static void *anonymize_path_component(const void *path, size_t *len)
{
static int counter;
struct strbuf out = STRBUF_INIT;
strbuf_addf(&out, "path%d", counter++);
return strbuf_detach(&out, len);
}
static void print_path(const char *path)
{
if (!anonymize)
print_path_1(path);
else {
static struct hashmap paths;
static struct strbuf anon = STRBUF_INIT;
anonymize_path(&anon, path, &paths, anonymize_path_component);
print_path_1(anon.buf);
strbuf_reset(&anon);
}
}
static void *generate_fake_oid(const void *old, size_t *len)
{
static uint32_t counter = 1; /* avoid null oid */
const unsigned hashsz = the_hash_algo->rawsz;
unsigned char *out = xcalloc(hashsz, 1);
put_be32(out + hashsz - 4, counter++);
return out;
}
static const struct object_id *anonymize_oid(const struct object_id *oid)
{
static struct hashmap objs;
size_t len = the_hash_algo->rawsz;
return anonymize_mem(&objs, generate_fake_oid, oid, &len);
}
static void show_filemodify(struct diff_queue_struct *q,
struct diff_options *options, void *data)
{
int i;
struct string_list *changed = data;
/*
* Handle files below a directory first, in case they are all deleted
* and the directory changes to a file or symlink.
*/
QSORT(q->queue, q->nr, depth_first);
for (i = 0; i < q->nr; i++) {
struct diff_filespec *ospec = q->queue[i]->one;
struct diff_filespec *spec = q->queue[i]->two;
switch (q->queue[i]->status) {
case DIFF_STATUS_DELETED:
printf("D ");
print_path(spec->path);
string_list_insert(changed, spec->path);
putchar('\n');
break;
case DIFF_STATUS_COPIED:
case DIFF_STATUS_RENAMED:
/*
* If a change in the file corresponding to ospec->path
* has been observed, we cannot trust its contents
* because the diff is calculated based on the prior
* contents, not the current contents. So, declare a
* copy or rename only if there was no change observed.
*/
if (!string_list_has_string(changed, ospec->path)) {
printf("%c ", q->queue[i]->status);
print_path(ospec->path);
putchar(' ');
print_path(spec->path);
string_list_insert(changed, spec->path);
putchar('\n');
if (oideq(&ospec->oid, &spec->oid) &&
ospec->mode == spec->mode)
break;
}
/* fallthrough */
case DIFF_STATUS_TYPE_CHANGED:
case DIFF_STATUS_MODIFIED:
case DIFF_STATUS_ADDED:
/*
* Links refer to objects in another repositories;
* output the SHA-1 verbatim.
*/
if (no_data || S_ISGITLINK(spec->mode))
printf("M %06o %s ", spec->mode,
oid_to_hex(anonymize ?
anonymize_oid(&spec->oid) :
&spec->oid));
else {
struct object *object = lookup_object(the_repository,
&spec->oid);
printf("M %06o :%d ", spec->mode,
get_object_mark(object));
}
print_path(spec->path);
string_list_insert(changed, spec->path);
putchar('\n');
break;
default:
die("Unexpected comparison status '%c' for %s, %s",
q->queue[i]->status,
ospec->path ? ospec->path : "none",
spec->path ? spec->path : "none");
}
}
}
static const char *find_encoding(const char *begin, const char *end)
{
const char *needle = "\nencoding ";
char *bol, *eol;
bol = memmem(begin, end ? end - begin : strlen(begin),
needle, strlen(needle));
if (!bol)
return NULL;
bol += strlen(needle);
eol = strchrnul(bol, '\n');
*eol = '\0';
return bol;
}
static void *anonymize_ref_component(const void *old, size_t *len)
{
static int counter;
struct strbuf out = STRBUF_INIT;
strbuf_addf(&out, "ref%d", counter++);
return strbuf_detach(&out, len);
}
static const char *anonymize_refname(const char *refname)
{
/*
* If any of these prefixes is found, we will leave it intact
* so that tags remain tags and so forth.
*/
static const char *prefixes[] = {
"refs/heads/",
"refs/tags/",
"refs/remotes/",
"refs/"
};
static struct hashmap refs;
static struct strbuf anon = STRBUF_INIT;
int i;
/*
* We also leave "master" as a special case, since it does not reveal
* anything interesting.
*/
if (!strcmp(refname, "refs/heads/master"))
return refname;
strbuf_reset(&anon);
for (i = 0; i < ARRAY_SIZE(prefixes); i++) {
if (skip_prefix(refname, prefixes[i], &refname)) {
strbuf_addstr(&anon, prefixes[i]);
break;
}
}
anonymize_path(&anon, refname, &refs, anonymize_ref_component);
return anon.buf;
}
/*
* We do not even bother to cache commit messages, as they are unlikely
* to be repeated verbatim, and it is not that interesting when they are.
*/
static char *anonymize_commit_message(const char *old)
{
static int counter;
return xstrfmt("subject %d\n\nbody\n", counter++);
}
static struct hashmap idents;
static void *anonymize_ident(const void *old, size_t *len)
{
static int counter;
struct strbuf out = STRBUF_INIT;
strbuf_addf(&out, "User %d <user%[email protected]>", counter, counter);
counter++;
return strbuf_detach(&out, len);
}
/*
* Our strategy here is to anonymize the names and email addresses,
* but keep timestamps intact, as they influence things like traversal
* order (and by themselves should not be too revealing).
*/
static void anonymize_ident_line(const char **beg, const char **end)
{
static struct strbuf buffers[] = { STRBUF_INIT, STRBUF_INIT };
static unsigned which_buffer;
struct strbuf *out;
struct ident_split split;
const char *end_of_header;
out = &buffers[which_buffer++];
which_buffer %= ARRAY_SIZE(buffers);
strbuf_reset(out);
/* skip "committer", "author", "tagger", etc */
end_of_header = strchr(*beg, ' ');
if (!end_of_header)
BUG("malformed line fed to anonymize_ident_line: %.*s",
(int)(*end - *beg), *beg);
end_of_header++;
strbuf_add(out, *beg, end_of_header - *beg);
if (!split_ident_line(&split, end_of_header, *end - end_of_header) &&
split.date_begin) {
const char *ident;
size_t len;
len = split.mail_end - split.name_begin;
ident = anonymize_mem(&idents, anonymize_ident,
split.name_begin, &len);
strbuf_add(out, ident, len);
strbuf_addch(out, ' ');
strbuf_add(out, split.date_begin, split.tz_end - split.date_begin);
} else {
strbuf_addstr(out, "Malformed Ident <[email protected]> 0 -0000");
}
*beg = out->buf;
*end = out->buf + out->len;
}
static void handle_commit(struct commit *commit, struct rev_info *rev,
struct string_list *paths_of_changed_objects)
{
int saved_output_format = rev->diffopt.output_format;
const char *commit_buffer;
const char *author, *author_end, *committer, *committer_end;
const char *encoding, *message;
char *reencoded = NULL;
struct commit_list *p;
const char *refname;
int i;
rev->diffopt.output_format = DIFF_FORMAT_CALLBACK;
parse_commit_or_die(commit);
commit_buffer = get_commit_buffer(commit, NULL);
author = strstr(commit_buffer, "\nauthor ");
if (!author)
die("could not find author in commit %s",
oid_to_hex(&commit->object.oid));
author++;
author_end = strchrnul(author, '\n');
committer = strstr(author_end, "\ncommitter ");
if (!committer)
die("could not find committer in commit %s",
oid_to_hex(&commit->object.oid));
committer++;
committer_end = strchrnul(committer, '\n');
message = strstr(committer_end, "\n\n");
encoding = find_encoding(committer_end, message);
if (message)
message += 2;
if (commit->parents &&
(get_object_mark(&commit->parents->item->object) != 0 ||
reference_excluded_commits) &&
!full_tree) {
parse_commit_or_die(commit->parents->item);
diff_tree_oid(get_commit_tree_oid(commit->parents->item),
get_commit_tree_oid(commit), "", &rev->diffopt);
}
else
diff_root_tree_oid(get_commit_tree_oid(commit),
"", &rev->diffopt);
/* Export the referenced blobs, and remember the marks. */
for (i = 0; i < diff_queued_diff.nr; i++)
if (!S_ISGITLINK(diff_queued_diff.queue[i]->two->mode))
export_blob(&diff_queued_diff.queue[i]->two->oid);
refname = *revision_sources_at(&revision_sources, commit);
/*
* FIXME: string_list_remove() below for each ref is overall
* O(N^2). Compared to a history walk and diffing trees, this is
* just lost in the noise in practice. However, theoretically a
* repo may have enough refs for this to become slow.
*/
string_list_remove(&extra_refs, refname, 0);
if (anonymize) {
refname = anonymize_refname(refname);
anonymize_ident_line(&committer, &committer_end);
anonymize_ident_line(&author, &author_end);
}
mark_next_object(&commit->object);
if (anonymize) {
reencoded = anonymize_commit_message(message);
} else if (encoding) {
switch(reencode_mode) {
case REENCODE_YES:
reencoded = reencode_string(message, "UTF-8", encoding);
break;
case REENCODE_NO:
break;
case REENCODE_ABORT:
die("Encountered commit-specific encoding %s in commit "
"%s; use --reencode=[yes|no] to handle it",
encoding, oid_to_hex(&commit->object.oid));
}
}
if (!commit->parents)
printf("reset %s\n", refname);
printf("commit %s\nmark :%"PRIu32"\n", refname, last_idnum);
if (show_original_ids)
printf("original-oid %s\n", oid_to_hex(&commit->object.oid));
printf("%.*s\n%.*s\n",
(int)(author_end - author), author,
(int)(committer_end - committer), committer);
if (!reencoded && encoding)
printf("encoding %s\n", encoding);
printf("data %u\n%s",
(unsigned)(reencoded
? strlen(reencoded) : message
? strlen(message) : 0),
reencoded ? reencoded : message ? message : "");
free(reencoded);
unuse_commit_buffer(commit, commit_buffer);
for (i = 0, p = commit->parents; p; p = p->next) {
struct object *obj = &p->item->object;
int mark = get_object_mark(obj);
if (!mark && !reference_excluded_commits)
continue;
if (i == 0)
printf("from ");
else
printf("merge ");
if (mark)
printf(":%d\n", mark);
else
printf("%s\n", oid_to_hex(anonymize ?
anonymize_oid(&obj->oid) :
&obj->oid));
i++;
}
if (full_tree)
printf("deleteall\n");
log_tree_diff_flush(rev);
string_list_clear(paths_of_changed_objects, 0);
rev->diffopt.output_format = saved_output_format;
printf("\n");
show_progress();
}
static void *anonymize_tag(const void *old, size_t *len)
{
static int counter;
struct strbuf out = STRBUF_INIT;
strbuf_addf(&out, "tag message %d", counter++);
return strbuf_detach(&out, len);
}
static void handle_tail(struct object_array *commits, struct rev_info *revs,
struct string_list *paths_of_changed_objects)
{
struct commit *commit;
while (commits->nr) {
commit = (struct commit *)object_array_pop(commits);
if (has_unshown_parent(commit)) {
/* Queue again, to be handled later */
add_object_array(&commit->object, NULL, commits);
return;
}
handle_commit(commit, revs, paths_of_changed_objects);
}
}
static void handle_tag(const char *name, struct tag *tag)
{
unsigned long size;
enum object_type type;
char *buf;
const char *tagger, *tagger_end, *message;
size_t message_size = 0;
struct object *tagged;
int tagged_mark;
struct commit *p;
/* Trees have no identifier in fast-export output, thus we have no way
* to output tags of trees, tags of tags of trees, etc. Simply omit
* such tags.
*/
tagged = tag->tagged;
while (tagged->type == OBJ_TAG) {
tagged = ((struct tag *)tagged)->tagged;
}
if (tagged->type == OBJ_TREE) {
warning("Omitting tag %s,\nsince tags of trees (or tags of tags of trees, etc.) are not supported.",
oid_to_hex(&tag->object.oid));
return;
}
buf = read_object_file(&tag->object.oid, &type, &size);
if (!buf)
die("could not read tag %s", oid_to_hex(&tag->object.oid));
message = memmem(buf, size, "\n\n", 2);
if (message) {
message += 2;
message_size = strlen(message);
}
tagger = memmem(buf, message ? message - buf : size, "\ntagger ", 8);
if (!tagger) {
if (fake_missing_tagger)
tagger = "tagger Unspecified Tagger "
"<unspecified-tagger> 0 +0000";
else
tagger = "";
tagger_end = tagger + strlen(tagger);
} else {
tagger++;
tagger_end = strchrnul(tagger, '\n');
if (anonymize)
anonymize_ident_line(&tagger, &tagger_end);
}
if (anonymize) {
name = anonymize_refname(name);
if (message) {
static struct hashmap tags;
message = anonymize_mem(&tags, anonymize_tag,
message, &message_size);
}
}
/* handle signed tags */
if (message) {
const char *signature = strstr(message,
"\n-----BEGIN PGP SIGNATURE-----\n");
if (signature)
switch(signed_tag_mode) {
case SIGNED_TAG_ABORT:
die("encountered signed tag %s; use "
"--signed-tags=<mode> to handle it",
oid_to_hex(&tag->object.oid));
case WARN:
warning("exporting signed tag %s",
oid_to_hex(&tag->object.oid));
/* fallthru */
case VERBATIM:
break;
case WARN_STRIP:
warning("stripping signature from tag %s",
oid_to_hex(&tag->object.oid));
/* fallthru */
case STRIP:
message_size = signature + 1 - message;
break;
}
}
/* handle tag->tagged having been filtered out due to paths specified */
tagged = tag->tagged;
tagged_mark = get_object_mark(tagged);
if (!tagged_mark) {
switch(tag_of_filtered_mode) {
case TAG_FILTERING_ABORT:
die("tag %s tags unexported object; use "
"--tag-of-filtered-object=<mode> to handle it",
oid_to_hex(&tag->object.oid));
case DROP:
/* Ignore this tag altogether */
free(buf);
return;
case REWRITE:
if (tagged->type == OBJ_TAG && !mark_tags) {
die(_("Error: Cannot export nested tags unless --mark-tags is specified."));
} else if (tagged->type == OBJ_COMMIT) {
p = rewrite_commit((struct commit *)tagged);
if (!p) {
printf("reset %s\nfrom %s\n\n",
name, oid_to_hex(&null_oid));
free(buf);
return;
}
tagged_mark = get_object_mark(&p->object);
} else {
/* tagged->type is either OBJ_BLOB or OBJ_TAG */
tagged_mark = get_object_mark(tagged);
}
}
}
if (tagged->type == OBJ_TAG) {
printf("reset %s\nfrom %s\n\n",
name, oid_to_hex(&null_oid));
}
skip_prefix(name, "refs/tags/", &name);
printf("tag %s\n", name);
if (mark_tags) {
mark_next_object(&tag->object);
printf("mark :%"PRIu32"\n", last_idnum);
}
if (tagged_mark)
printf("from :%d\n", tagged_mark);
else
printf("from %s\n", oid_to_hex(&tagged->oid));
if (show_original_ids)
printf("original-oid %s\n", oid_to_hex(&tag->object.oid));
printf("%.*s%sdata %d\n%.*s\n",
(int)(tagger_end - tagger), tagger,
tagger == tagger_end ? "" : "\n",
(int)message_size, (int)message_size, message ? message : "");
free(buf);
}
static struct commit *get_commit(struct rev_cmdline_entry *e, char *full_name)
{
switch (e->item->type) {
case OBJ_COMMIT:
return (struct commit *)e->item;
case OBJ_TAG: {
struct tag *tag = (struct tag *)e->item;
/* handle nested tags */
while (tag && tag->object.type == OBJ_TAG) {
parse_object(the_repository, &tag->object.oid);
string_list_append(&tag_refs, full_name)->util = tag;
tag = (struct tag *)tag->tagged;
}
if (!tag)
die("Tag %s points nowhere?", e->name);
return (struct commit *)tag;
break;
}
default:
return NULL;
}
}
static void get_tags_and_duplicates(struct rev_cmdline_info *info)
{
int i;
for (i = 0; i < info->nr; i++) {
struct rev_cmdline_entry *e = info->rev + i;
struct object_id oid;
struct commit *commit;
char *full_name;
if (e->flags & UNINTERESTING)
continue;
if (dwim_ref(e->name, strlen(e->name), &oid, &full_name) != 1)
continue;
if (refspecs.nr) {
char *private;
private = apply_refspecs(&refspecs, full_name);
if (private) {
free(full_name);
full_name = private;
}
}
commit = get_commit(e, full_name);
if (!commit) {
warning("%s: Unexpected object of type %s, skipping.",
e->name,
type_name(e->item->type));
continue;
}
switch(commit->object.type) {
case OBJ_COMMIT:
break;
case OBJ_BLOB:
export_blob(&commit->object.oid);
continue;
default: /* OBJ_TAG (nested tags) is already handled */
warning("Tag points to object of unexpected type %s, skipping.",
type_name(commit->object.type));
continue;
}
/*
* Make sure this ref gets properly updated eventually, whether
* through a commit or manually at the end.
*/
if (e->item->type != OBJ_TAG)
string_list_append(&extra_refs, full_name)->util = commit;
if (!*revision_sources_at(&revision_sources, commit))
*revision_sources_at(&revision_sources, commit) = full_name;
}
string_list_sort(&extra_refs);
string_list_remove_duplicates(&extra_refs, 0);
}
static void handle_tags_and_duplicates(struct string_list *extras)
{
struct commit *commit;
int i;
for (i = extras->nr - 1; i >= 0; i--) {
const char *name = extras->items[i].string;
struct object *object = extras->items[i].util;
int mark;
switch (object->type) {
case OBJ_TAG:
handle_tag(name, (struct tag *)object);
break;
case OBJ_COMMIT:
if (anonymize)
name = anonymize_refname(name);
/* create refs pointing to already seen commits */
commit = rewrite_commit((struct commit *)object);
if (!commit) {
/*
* Neither this object nor any of its
* ancestors touch any relevant paths, so