Repository navigation
Expand file tree
/
Copy pathblame.c
More file actions
2957 lines (2655 loc) · 84.4 KB
/
Copy pathblame.c
File metadata and controls
2957 lines (2655 loc) · 84.4 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
#define USE_THE_REPOSITORY_VARIABLE
#define DISABLE_SIGN_COMPARE_WARNINGS
#include "git-compat-util.h"
#include "refs.h"
#include "odb.h"
#include "cache-tree.h"
#include "mergesort.h"
#include "commit.h"
#include "convert.h"
#include "diff.h"
#include "diffcore.h"
#include "gettext.h"
#include "hex.h"
#include "path.h"
#include "read-cache.h"
#include "revision.h"
#include "setup.h"
#include "tag.h"
#include "trace2.h"
#include "blame.h"
#include "alloc.h"
#include "commit-slab.h"
#include "bloom.h"
#include "commit-graph.h"
define_commit_slab(blame_suspects, struct blame_origin *);
static struct blame_suspects blame_suspects;
struct blame_origin *get_blame_suspects(struct commit *commit)
{
struct blame_origin **result;
result = blame_suspects_peek(&blame_suspects, commit);
return result ? *result : NULL;
}
static void set_blame_suspects(struct commit *commit, struct blame_origin *origin)
{
*blame_suspects_at(&blame_suspects, commit) = origin;
}
void blame_origin_decref(struct blame_origin *o)
{
if (o && --o->refcnt <= 0) {
struct blame_origin *p, *l = NULL;
if (o->previous)
blame_origin_decref(o->previous);
free(o->file.ptr);
/* Should be present exactly once in commit chain */
for (p = get_blame_suspects(o->commit); p; l = p, p = p->next) {
if (p == o) {
if (l)
l->next = p->next;
else
set_blame_suspects(o->commit, p->next);
free(o);
return;
}
}
die("internal error in blame_origin_decref");
}
}
/*
* Given a commit and a path in it, create a new origin structure.
* The callers that add blame to the scoreboard should use
* get_origin() to obtain shared, refcounted copy instead of calling
* this function directly.
*/
static struct blame_origin *make_origin(struct commit *commit, const char *path)
{
struct blame_origin *o;
FLEX_ALLOC_STR(o, path, path);
o->commit = commit;
o->refcnt = 1;
o->next = get_blame_suspects(commit);
set_blame_suspects(commit, o);
return o;
}
/*
* Locate an existing origin or create a new one.
* This moves the origin to front position in the commit util list.
*/
static struct blame_origin *get_origin(struct commit *commit, const char *path)
{
struct blame_origin *o, *l;
for (o = get_blame_suspects(commit), l = NULL; o; l = o, o = o->next) {
if (!strcmp(o->path, path)) {
/* bump to front */
if (l) {
l->next = o->next;
o->next = get_blame_suspects(commit);
set_blame_suspects(commit, o);
}
return blame_origin_incref(o);
}
}
return make_origin(commit, path);
}
static void verify_working_tree_path(struct repository *r,
struct commit *work_tree, const char *path)
{
struct commit_list *parents;
int pos;
for (parents = work_tree->parents; parents; parents = parents->next) {
const struct object_id *commit_oid = &parents->item->object.oid;
struct object_id blob_oid;
unsigned short mode;
if (!get_tree_entry(r, commit_oid, path, &blob_oid, &mode) &&
odb_read_object_info(r->objects, &blob_oid, NULL) == OBJ_BLOB)
return;
}
pos = index_name_pos(r->index, path, strlen(path));
if (pos >= 0)
; /* path is in the index */
else if (-1 - pos < r->index->cache_nr &&
!strcmp(r->index->cache[-1 - pos]->name, path))
; /* path is in the index, unmerged */
else
die("no such path '%s' in HEAD", path);
}
static struct commit_list **append_parent(struct repository *r,
struct commit_list **tail,
const struct object_id *oid)
{
struct commit *parent;
parent = lookup_commit_reference(r, oid);
if (!parent)
die("no such commit %s", oid_to_hex(oid));
return &commit_list_insert(parent, tail)->next;
}
static void append_merge_parents(struct repository *r,
struct commit_list **tail)
{
int merge_head;
struct strbuf line = STRBUF_INIT;
merge_head = open(git_path_merge_head(r), O_RDONLY);
if (merge_head < 0) {
if (errno == ENOENT)
return;
die("cannot open '%s' for reading",
git_path_merge_head(r));
}
while (!strbuf_getwholeline_fd(&line, merge_head, '\n')) {
struct object_id oid;
if (get_oid_hex(line.buf, &oid))
die("unknown line in '%s': %s",
git_path_merge_head(r), line.buf);
tail = append_parent(r, tail, &oid);
}
close(merge_head);
strbuf_release(&line);
}
/*
* This isn't as simple as passing sb->buf and sb->len, because we
* want to transfer ownership of the buffer to the commit (so we
* must use detach).
*/
static void set_commit_buffer_from_strbuf(struct repository *r,
struct commit *c,
struct strbuf *sb)
{
size_t len;
void *buf = strbuf_detach(sb, &len);
set_commit_buffer(r, c, buf, len);
}
/*
* Prepare a dummy commit that represents the work tree (or staged) item.
* Note that annotating work tree item never works in the reverse.
*/
static struct commit *fake_working_tree_commit(struct repository *r,
struct diff_options *opt,
const char *path,
const char *contents_from,
struct object_id *oid)
{
struct commit *commit;
struct blame_origin *origin;
struct commit_list **parent_tail, *parent;
struct strbuf buf = STRBUF_INIT;
const char *ident;
time_t now;
int len;
struct cache_entry *ce;
unsigned mode;
struct strbuf msg = STRBUF_INIT;
repo_read_index(r);
time(&now);
commit = alloc_commit_node(r);
commit->object.parsed = 1;
commit->date = now;
parent_tail = &commit->parents;
parent_tail = append_parent(r, parent_tail, oid);
append_merge_parents(r, parent_tail);
verify_working_tree_path(r, commit, path);
origin = make_origin(commit, path);
if (contents_from)
ident = fmt_ident("External file (--contents)", "external.file",
WANT_BLANK_IDENT, NULL, 0);
else
ident = fmt_ident("Not Committed Yet", "not.committed.yet",
WANT_BLANK_IDENT, NULL, 0);
strbuf_addstr(&msg, "tree 0000000000000000000000000000000000000000\n");
for (parent = commit->parents; parent; parent = parent->next)
strbuf_addf(&msg, "parent %s\n",
oid_to_hex(&parent->item->object.oid));
strbuf_addf(&msg,
"author %s\n"
"committer %s\n\n"
"Version of %s from %s\n",
ident, ident, path,
(!contents_from ? path :
(!strcmp(contents_from, "-") ? "standard input" : contents_from)));
set_commit_buffer_from_strbuf(r, commit, &msg);
if (!contents_from || strcmp("-", contents_from)) {
struct stat st;
const char *read_from;
char *buf_ptr;
unsigned long buf_len;
if (contents_from) {
if (stat(contents_from, &st) < 0)
die_errno("Cannot stat '%s'", contents_from);
read_from = contents_from;
}
else {
if (lstat(path, &st) < 0)
die_errno("Cannot lstat '%s'", path);
read_from = path;
}
mode = canon_mode(st.st_mode);
switch (st.st_mode & S_IFMT) {
case S_IFREG:
if (textconv_object(r, opt, read_from, mode,
null_oid(the_hash_algo), 0,
&buf_ptr, &buf_len))
strbuf_attach(&buf, buf_ptr, buf_len, buf_len + 1);
else if (strbuf_read_file(&buf, read_from, st.st_size) != st.st_size)
die_errno("cannot open or read '%s'", read_from);
break;
case S_IFLNK:
if (strbuf_readlink(&buf, read_from, st.st_size) < 0)
die_errno("cannot readlink '%s'", read_from);
break;
default:
die("unsupported file type %s", read_from);
}
}
else {
/* Reading from stdin */
mode = 0;
if (strbuf_read(&buf, 0, 0) < 0)
die_errno("failed to read from stdin");
}
convert_to_git(r->index, path, buf.buf, buf.len, &buf, 0);
origin->file.ptr = buf.buf;
origin->file.size = buf.len;
odb_pretend_object(the_repository->objects, buf.buf, buf.len,
OBJ_BLOB, &origin->blob_oid);
/*
* Read the current index, replace the path entry with
* origin->blob_sha1 without mucking with its mode or type
* bits; we are not going to write this index out -- we just
* want to run "diff-index --cached".
*/
discard_index(r->index);
repo_read_index(r);
len = strlen(path);
if (!mode) {
int pos = index_name_pos(r->index, path, len);
if (0 <= pos)
mode = r->index->cache[pos]->ce_mode;
else
/* Let's not bother reading from HEAD tree */
mode = S_IFREG | 0644;
}
ce = make_empty_cache_entry(r->index, len);
oidcpy(&ce->oid, &origin->blob_oid);
memcpy(ce->name, path, len);
ce->ce_flags = create_ce_flags(0);
ce->ce_namelen = len;
ce->ce_mode = create_ce_mode(mode);
add_index_entry(r->index, ce,
ADD_CACHE_OK_TO_ADD | ADD_CACHE_OK_TO_REPLACE);
cache_tree_invalidate_path(r->index, path);
return commit;
}
static int diff_hunks(mmfile_t *file_a, mmfile_t *file_b,
xdl_emit_hunk_consume_func_t hunk_func, void *cb_data, int xdl_opts)
{
xpparam_t xpp = {0};
xdemitconf_t xecfg = {0};
xdemitcb_t ecb = {NULL};
xpp.flags = xdl_opts;
xecfg.hunk_func = hunk_func;
ecb.priv = cb_data;
return xdi_diff(file_a, file_b, &xpp, &xecfg, &ecb);
}
static const char *get_next_line(const char *start, const char *end)
{
const char *nl = memchr(start, '\n', end - start);
return nl ? nl + 1 : end;
}
static int find_line_starts(int **line_starts, const char *buf,
unsigned long len)
{
const char *end = buf + len;
const char *p;
int *lineno;
int num = 0;
for (p = buf; p < end; p = get_next_line(p, end))
num++;
ALLOC_ARRAY(*line_starts, num + 1);
lineno = *line_starts;
for (p = buf; p < end; p = get_next_line(p, end))
*lineno++ = p - buf;
*lineno = len;
return num;
}
struct fingerprint_entry;
/* A fingerprint is intended to loosely represent a string, such that two
* fingerprints can be quickly compared to give an indication of the similarity
* of the strings that they represent.
*
* A fingerprint is represented as a multiset of the lower-cased byte pairs in
* the string that it represents. Whitespace is added at each end of the
* string. Whitespace pairs are ignored. Whitespace is converted to '\0'.
* For example, the string "Darth Radar" will be converted to the following
* fingerprint:
* {"\0d", "da", "da", "ar", "ar", "rt", "th", "h\0", "\0r", "ra", "ad", "r\0"}
*
* The similarity between two fingerprints is the size of the intersection of
* their multisets, including repeated elements. See fingerprint_similarity for
* examples.
*
* For ease of implementation, the fingerprint is implemented as a map
* of byte pairs to the count of that byte pair in the string, instead of
* allowing repeated elements in a set.
*/
struct fingerprint {
struct hashmap map;
/* As we know the maximum number of entries in advance, it's
* convenient to store the entries in a single array instead of having
* the hashmap manage the memory.
*/
struct fingerprint_entry *entries;
};
/* A byte pair in a fingerprint. Stores the number of times the byte pair
* occurs in the string that the fingerprint represents.
*/
struct fingerprint_entry {
/* The hashmap entry - the hash represents the byte pair in its
* entirety so we don't need to store the byte pair separately.
*/
struct hashmap_entry entry;
/* The number of times the byte pair occurs in the string that the
* fingerprint represents.
*/
int count;
};
/* See `struct fingerprint` for an explanation of what a fingerprint is.
* \param result the fingerprint of the string is stored here. This must be
* freed later using free_fingerprint.
* \param line_begin the start of the string
* \param line_end the end of the string
*/
static void get_fingerprint(struct fingerprint *result,
const char *line_begin,
const char *line_end)
{
unsigned int hash, c0 = 0, c1;
const char *p;
int max_map_entry_count = 1 + line_end - line_begin;
struct fingerprint_entry *entry = xcalloc(max_map_entry_count,
sizeof(struct fingerprint_entry));
struct fingerprint_entry *found_entry;
hashmap_init(&result->map, NULL, NULL, max_map_entry_count);
result->entries = entry;
for (p = line_begin; p <= line_end; ++p, c0 = c1) {
/* Always terminate the string with whitespace.
* Normalise whitespace to 0, and normalise letters to
* lower case. This won't work for multibyte characters but at
* worst will match some unrelated characters.
*/
if ((p == line_end) || isspace(*p))
c1 = 0;
else
c1 = tolower(*p);
hash = c0 | (c1 << 8);
/* Ignore whitespace pairs */
if (hash == 0)
continue;
hashmap_entry_init(&entry->entry, hash);
found_entry = hashmap_get_entry(&result->map, entry,
/* member name */ entry, NULL);
if (found_entry) {
found_entry->count += 1;
} else {
entry->count = 1;
hashmap_add(&result->map, &entry->entry);
++entry;
}
}
}
static void free_fingerprint(struct fingerprint *f)
{
hashmap_clear(&f->map);
free(f->entries);
}
/* Calculates the similarity between two fingerprints as the size of the
* intersection of their multisets, including repeated elements. See
* `struct fingerprint` for an explanation of the fingerprint representation.
* The similarity between "cat mat" and "father rather" is 2 because "at" is
* present twice in both strings while the similarity between "tim" and "mit"
* is 0.
*/
static int fingerprint_similarity(struct fingerprint *a, struct fingerprint *b)
{
int intersection = 0;
struct hashmap_iter iter;
const struct fingerprint_entry *entry_a, *entry_b;
hashmap_for_each_entry(&b->map, &iter, entry_b,
entry /* member name */) {
entry_a = hashmap_get_entry(&a->map, entry_b, entry, NULL);
if (entry_a) {
intersection += entry_a->count < entry_b->count ?
entry_a->count : entry_b->count;
}
}
return intersection;
}
/* Subtracts byte-pair elements in B from A, modifying A in place.
*/
static void fingerprint_subtract(struct fingerprint *a, struct fingerprint *b)
{
struct hashmap_iter iter;
struct fingerprint_entry *entry_a;
const struct fingerprint_entry *entry_b;
hashmap_iter_init(&b->map, &iter);
hashmap_for_each_entry(&b->map, &iter, entry_b,
entry /* member name */) {
entry_a = hashmap_get_entry(&a->map, entry_b, entry, NULL);
if (entry_a) {
if (entry_a->count <= entry_b->count)
hashmap_remove(&a->map, &entry_b->entry, NULL);
else
entry_a->count -= entry_b->count;
}
}
}
/* Calculate fingerprints for a series of lines.
* Puts the fingerprints in the fingerprints array, which must have been
* preallocated to allow storing line_count elements.
*/
static void get_line_fingerprints(struct fingerprint *fingerprints,
const char *content, const int *line_starts,
long first_line, long line_count)
{
int i;
const char *linestart, *lineend;
line_starts += first_line;
for (i = 0; i < line_count; ++i) {
linestart = content + line_starts[i];
lineend = content + line_starts[i + 1];
get_fingerprint(fingerprints + i, linestart, lineend);
}
}
static void free_line_fingerprints(struct fingerprint *fingerprints,
int nr_fingerprints)
{
int i;
for (i = 0; i < nr_fingerprints; i++)
free_fingerprint(&fingerprints[i]);
}
/* This contains the data necessary to linearly map a line number in one half
* of a diff chunk to the line in the other half of the diff chunk that is
* closest in terms of its position as a fraction of the length of the chunk.
*/
struct line_number_mapping {
int destination_start, destination_length,
source_start, source_length;
};
/* Given a line number in one range, offset and scale it to map it onto the
* other range.
* Essentially this mapping is a simple linear equation but the calculation is
* more complicated to allow performing it with integer operations.
* Another complication is that if a line could map onto many lines in the
* destination range then we want to choose the line at the center of those
* possibilities.
* Example: if the chunk is 2 lines long in A and 10 lines long in B then the
* first 5 lines in B will map onto the first line in the A chunk, while the
* last 5 lines will all map onto the second line in the A chunk.
* Example: if the chunk is 10 lines long in A and 2 lines long in B then line
* 0 in B will map onto line 2 in A, and line 1 in B will map onto line 7 in A.
*/
static int map_line_number(int line_number,
const struct line_number_mapping *mapping)
{
return ((line_number - mapping->source_start) * 2 + 1) *
mapping->destination_length /
(mapping->source_length * 2) +
mapping->destination_start;
}
/* Get a pointer to the element storing the similarity between a line in A
* and a line in B.
*
* The similarities are stored in a 2-dimensional array. Each "row" in the
* array contains the similarities for a line in B. The similarities stored in
* a row are the similarities between the line in B and the nearby lines in A.
* To keep the length of each row the same, it is padded out with values of -1
* where the search range extends beyond the lines in A.
* For example, if max_search_distance_a is 2 and the two sides of a diff chunk
* look like this:
* a | m
* b | n
* c | o
* d | p
* e | q
* Then the similarity array will contain:
* [-1, -1, am, bm, cm,
* -1, an, bn, cn, dn,
* ao, bo, co, do, eo,
* bp, cp, dp, ep, -1,
* cq, dq, eq, -1, -1]
* Where similarities are denoted either by -1 for invalid, or the
* concatenation of the two lines in the diff being compared.
*
* \param similarities array of similarities between lines in A and B
* \param line_a the index of the line in A, in the same frame of reference as
* closest_line_a.
* \param local_line_b the index of the line in B, relative to the first line
* in B that similarities represents.
* \param closest_line_a the index of the line in A that is deemed to be
* closest to local_line_b. This must be in the same
* frame of reference as line_a. This value defines
* where similarities is centered for the line in B.
* \param max_search_distance_a maximum distance in lines from the closest line
* in A for other lines in A for which
* similarities may be calculated.
*/
static int *get_similarity(int *similarities,
int line_a, int local_line_b,
int closest_line_a, int max_search_distance_a)
{
assert(abs(line_a - closest_line_a) <=
max_search_distance_a);
return similarities + line_a - closest_line_a +
max_search_distance_a +
local_line_b * (max_search_distance_a * 2 + 1);
}
#define CERTAIN_NOTHING_MATCHES -2
#define CERTAINTY_NOT_CALCULATED -1
/* Given a line in B, first calculate its similarities with nearby lines in A
* if not already calculated, then identify the most similar and second most
* similar lines. The "certainty" is calculated based on those two
* similarities.
*
* \param start_a the index of the first line of the chunk in A
* \param length_a the length in lines of the chunk in A
* \param local_line_b the index of the line in B, relative to the first line
* in the chunk.
* \param fingerprints_a array of fingerprints for the chunk in A
* \param fingerprints_b array of fingerprints for the chunk in B
* \param similarities 2-dimensional array of similarities between lines in A
* and B. See get_similarity() for more details.
* \param certainties array of values indicating how strongly a line in B is
* matched with some line in A.
* \param second_best_result array of absolute indices in A for the second
* closest match of a line in B.
* \param result array of absolute indices in A for the closest match of a line
* in B.
* \param max_search_distance_a maximum distance in lines from the closest line
* in A for other lines in A for which
* similarities may be calculated.
* \param map_line_number_in_b_to_a parameter to map_line_number().
*/
static void find_best_line_matches(
int start_a,
int length_a,
int start_b,
int local_line_b,
struct fingerprint *fingerprints_a,
struct fingerprint *fingerprints_b,
int *similarities,
int *certainties,
int *second_best_result,
int *result,
const int max_search_distance_a,
const struct line_number_mapping *map_line_number_in_b_to_a)
{
int i, search_start, search_end, closest_local_line_a, *similarity,
best_similarity = 0, second_best_similarity = 0,
best_similarity_index = 0, second_best_similarity_index = 0;
/* certainty has already been calculated so no need to redo the work */
if (certainties[local_line_b] != CERTAINTY_NOT_CALCULATED)
return;
closest_local_line_a = map_line_number(
local_line_b + start_b, map_line_number_in_b_to_a) - start_a;
search_start = closest_local_line_a - max_search_distance_a;
if (search_start < 0)
search_start = 0;
search_end = closest_local_line_a + max_search_distance_a + 1;
if (search_end > length_a)
search_end = length_a;
for (i = search_start; i < search_end; ++i) {
similarity = get_similarity(similarities,
i, local_line_b,
closest_local_line_a,
max_search_distance_a);
if (*similarity == -1) {
/* This value will never exceed 10 but assert just in
* case
*/
assert(abs(i - closest_local_line_a) < 1000);
/* scale the similarity by (1000 - distance from
* closest line) to act as a tie break between lines
* that otherwise are equally similar.
*/
*similarity = fingerprint_similarity(
fingerprints_b + local_line_b,
fingerprints_a + i) *
(1000 - abs(i - closest_local_line_a));
}
if (*similarity > best_similarity) {
second_best_similarity = best_similarity;
second_best_similarity_index = best_similarity_index;
best_similarity = *similarity;
best_similarity_index = i;
} else if (*similarity > second_best_similarity) {
second_best_similarity = *similarity;
second_best_similarity_index = i;
}
}
if (best_similarity == 0) {
/* this line definitely doesn't match with anything. Mark it
* with this special value so it doesn't get invalidated and
* won't be recalculated.
*/
certainties[local_line_b] = CERTAIN_NOTHING_MATCHES;
result[local_line_b] = -1;
} else {
/* Calculate the certainty with which this line matches.
* If the line matches well with two lines then that reduces
* the certainty. However we still want to prioritise matching
* a line that matches very well with two lines over matching a
* line that matches poorly with one line, hence doubling
* best_similarity.
* This means that if we have
* line X that matches only one line with a score of 3,
* line Y that matches two lines equally with a score of 5,
* and line Z that matches only one line with a score or 2,
* then the lines in order of certainty are X, Y, Z.
*/
certainties[local_line_b] = best_similarity * 2 -
second_best_similarity;
/* We keep both the best and second best results to allow us to
* check at a later stage of the matching process whether the
* result needs to be invalidated.
*/
result[local_line_b] = start_a + best_similarity_index;
second_best_result[local_line_b] =
start_a + second_best_similarity_index;
}
}
/*
* This finds the line that we can match with the most confidence, and
* uses it as a partition. It then calls itself on the lines on either side of
* that partition. In this way we avoid lines appearing out of order, and
* retain a sensible line ordering.
* \param start_a index of the first line in A with which lines in B may be
* compared.
* \param start_b index of the first line in B for which matching should be
* done.
* \param length_a number of lines in A with which lines in B may be compared.
* \param length_b number of lines in B for which matching should be done.
* \param fingerprints_a mutable array of fingerprints in A. The first element
* corresponds to the line at start_a.
* \param fingerprints_b array of fingerprints in B. The first element
* corresponds to the line at start_b.
* \param similarities 2-dimensional array of similarities between lines in A
* and B. See get_similarity() for more details.
* \param certainties array of values indicating how strongly a line in B is
* matched with some line in A.
* \param second_best_result array of absolute indices in A for the second
* closest match of a line in B.
* \param result array of absolute indices in A for the closest match of a line
* in B.
* \param max_search_distance_a maximum distance in lines from the closest line
* in A for other lines in A for which
* similarities may be calculated.
* \param max_search_distance_b an upper bound on the greatest possible
* distance between lines in B such that they will
* both be compared with the same line in A
* according to max_search_distance_a.
* \param map_line_number_in_b_to_a parameter to map_line_number().
*/
static void fuzzy_find_matching_lines_recurse(
int start_a, int start_b,
int length_a, int length_b,
struct fingerprint *fingerprints_a,
struct fingerprint *fingerprints_b,
int *similarities,
int *certainties,
int *second_best_result,
int *result,
int max_search_distance_a,
int max_search_distance_b,
const struct line_number_mapping *map_line_number_in_b_to_a)
{
int i, invalidate_min, invalidate_max, offset_b,
second_half_start_a, second_half_start_b,
second_half_length_a, second_half_length_b,
most_certain_line_a, most_certain_local_line_b = -1,
most_certain_line_certainty = -1,
closest_local_line_a;
for (i = 0; i < length_b; ++i) {
find_best_line_matches(start_a,
length_a,
start_b,
i,
fingerprints_a,
fingerprints_b,
similarities,
certainties,
second_best_result,
result,
max_search_distance_a,
map_line_number_in_b_to_a);
if (certainties[i] > most_certain_line_certainty) {
most_certain_line_certainty = certainties[i];
most_certain_local_line_b = i;
}
}
/* No matches. */
if (most_certain_local_line_b == -1)
return;
most_certain_line_a = result[most_certain_local_line_b];
/*
* Subtract the most certain line's fingerprint in B from the matched
* fingerprint in A. This means that other lines in B can't also match
* the same parts of the line in A.
*/
fingerprint_subtract(fingerprints_a + most_certain_line_a - start_a,
fingerprints_b + most_certain_local_line_b);
/* Invalidate results that may be affected by the choice of most
* certain line.
*/
invalidate_min = most_certain_local_line_b - max_search_distance_b;
invalidate_max = most_certain_local_line_b + max_search_distance_b + 1;
if (invalidate_min < 0)
invalidate_min = 0;
if (invalidate_max > length_b)
invalidate_max = length_b;
/* As the fingerprint in A has changed, discard previously calculated
* similarity values with that fingerprint.
*/
for (i = invalidate_min; i < invalidate_max; ++i) {
closest_local_line_a = map_line_number(
i + start_b, map_line_number_in_b_to_a) - start_a;
/* Check that the lines in A and B are close enough that there
* is a similarity value for them.
*/
if (abs(most_certain_line_a - start_a - closest_local_line_a) >
max_search_distance_a) {
continue;
}
*get_similarity(similarities, most_certain_line_a - start_a,
i, closest_local_line_a,
max_search_distance_a) = -1;
}
/* More invalidating of results that may be affected by the choice of
* most certain line.
* Discard the matches for lines in B that are currently matched with a
* line in A such that their ordering contradicts the ordering imposed
* by the choice of most certain line.
*/
for (i = most_certain_local_line_b - 1; i >= invalidate_min; --i) {
/* In this loop we discard results for lines in B that are
* before most-certain-line-B but are matched with a line in A
* that is after most-certain-line-A.
*/
if (certainties[i] >= 0 &&
(result[i] >= most_certain_line_a ||
second_best_result[i] >= most_certain_line_a)) {
certainties[i] = CERTAINTY_NOT_CALCULATED;
}
}
for (i = most_certain_local_line_b + 1; i < invalidate_max; ++i) {
/* In this loop we discard results for lines in B that are
* after most-certain-line-B but are matched with a line in A
* that is before most-certain-line-A.
*/
if (certainties[i] >= 0 &&
(result[i] <= most_certain_line_a ||
second_best_result[i] <= most_certain_line_a)) {
certainties[i] = CERTAINTY_NOT_CALCULATED;
}
}
/* Repeat the matching process for lines before the most certain line.
*/
if (most_certain_local_line_b > 0) {
fuzzy_find_matching_lines_recurse(
start_a, start_b,
most_certain_line_a + 1 - start_a,
most_certain_local_line_b,
fingerprints_a, fingerprints_b, similarities,
certainties, second_best_result, result,
max_search_distance_a,
max_search_distance_b,
map_line_number_in_b_to_a);
}
/* Repeat the matching process for lines after the most certain line.
*/
if (most_certain_local_line_b + 1 < length_b) {
second_half_start_a = most_certain_line_a;
offset_b = most_certain_local_line_b + 1;
second_half_start_b = start_b + offset_b;
second_half_length_a =
length_a + start_a - second_half_start_a;
second_half_length_b =
length_b + start_b - second_half_start_b;
fuzzy_find_matching_lines_recurse(
second_half_start_a, second_half_start_b,
second_half_length_a, second_half_length_b,
fingerprints_a + second_half_start_a - start_a,
fingerprints_b + offset_b,
similarities +
offset_b * (max_search_distance_a * 2 + 1),
certainties + offset_b,
second_best_result + offset_b, result + offset_b,
max_search_distance_a,
max_search_distance_b,
map_line_number_in_b_to_a);
}
}
/* Find the lines in the parent line range that most closely match the lines in
* the target line range. This is accomplished by matching fingerprints in each
* blame_origin, and choosing the best matches that preserve the line ordering.
* See struct fingerprint for details of fingerprint matching, and
* fuzzy_find_matching_lines_recurse for details of preserving line ordering.
*
* The performance is believed to be O(n log n) in the typical case and O(n^2)
* in a pathological case, where n is the number of lines in the target range.
*/
static int *fuzzy_find_matching_lines(struct blame_origin *parent,
struct blame_origin *target,
int tlno, int parent_slno, int same,
int parent_len)
{
/* We use the terminology "A" for the left hand side of the diff AKA
* parent, and "B" for the right hand side of the diff AKA target. */
int start_a = parent_slno;
int length_a = parent_len;
int start_b = tlno;
int length_b = same - tlno;
struct line_number_mapping map_line_number_in_b_to_a = {
start_a, length_a, start_b, length_b
};
struct fingerprint *fingerprints_a = parent->fingerprints;
struct fingerprint *fingerprints_b = target->fingerprints;
int i, *result, *second_best_result,
*certainties, *similarities, similarity_count;
/*
* max_search_distance_a means that given a line in B, compare it to
* the line in A that is closest to its position, and the lines in A
* that are no greater than max_search_distance_a lines away from the
* closest line in A.
*
* max_search_distance_b is an upper bound on the greatest possible
* distance between lines in B such that they will both be compared
* with the same line in A according to max_search_distance_a.
*/
int max_search_distance_a = 10, max_search_distance_b;
if (length_a <= 0)
return NULL;
if (max_search_distance_a >= length_a)
max_search_distance_a = length_a ? length_a - 1 : 0;
max_search_distance_b = ((2 * max_search_distance_a + 1) * length_b
- 1) / length_a;
CALLOC_ARRAY(result, length_b);
CALLOC_ARRAY(second_best_result, length_b);
CALLOC_ARRAY(certainties, length_b);
/* See get_similarity() for details of similarities. */
similarity_count = length_b * (max_search_distance_a * 2 + 1);
CALLOC_ARRAY(similarities, similarity_count);
for (i = 0; i < length_b; ++i) {
result[i] = -1;
second_best_result[i] = -1;
certainties[i] = CERTAINTY_NOT_CALCULATED;
}
for (i = 0; i < similarity_count; ++i)
similarities[i] = -1;
fuzzy_find_matching_lines_recurse(start_a, start_b,
length_a, length_b,
fingerprints_a + start_a,
fingerprints_b + start_b,
similarities,
certainties,
second_best_result,
result,
max_search_distance_a,
max_search_distance_b,
&map_line_number_in_b_to_a);
free(similarities);
free(certainties);
free(second_best_result);