forked from git/git
-
Notifications
You must be signed in to change notification settings - Fork 142
/
Copy pathpretty.c
2372 lines (2096 loc) · 58 KB
/
pretty.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
#define USE_THE_REPOSITORY_VARIABLE
#define DISABLE_SIGN_COMPARE_WARNINGS
#include "git-compat-util.h"
#include "config.h"
#include "commit.h"
#include "environment.h"
#include "gettext.h"
#include "hash.h"
#include "hex.h"
#include "utf8.h"
#include "diff.h"
#include "pager.h"
#include "revision.h"
#include "string-list.h"
#include "mailmap.h"
#include "log-tree.h"
#include "notes.h"
#include "color.h"
#include "reflog-walk.h"
#include "gpg-interface.h"
#include "trailer.h"
#include "run-command.h"
#include "object-name.h"
/*
* The limit for formatting directives, which enable the caller to append
* arbitrarily many bytes to the formatted buffer. This includes padding
* and wrapping formatters.
*/
#define FORMATTING_LIMIT (16 * 1024)
static char *user_format;
static struct cmt_fmt_map {
const char *name;
enum cmit_fmt format;
int is_tformat;
int expand_tabs_in_log;
int is_alias;
enum date_mode_type default_date_mode_type;
const char *user_format;
} *commit_formats;
static size_t builtin_formats_len;
static size_t commit_formats_len;
static size_t commit_formats_alloc;
static struct cmt_fmt_map *find_commit_format(const char *sought);
int commit_format_is_empty(enum cmit_fmt fmt)
{
return fmt == CMIT_FMT_USERFORMAT && !*user_format;
}
static void save_user_format(struct rev_info *rev, const char *cp, int is_tformat)
{
free(user_format);
user_format = xstrdup(cp);
if (is_tformat)
rev->use_terminator = 1;
rev->commit_format = CMIT_FMT_USERFORMAT;
}
static int git_pretty_formats_config(const char *var, const char *value,
const struct config_context *ctx UNUSED,
void *cb UNUSED)
{
struct cmt_fmt_map *commit_format = NULL;
const char *name, *stripped;
char *fmt;
int i;
if (!skip_prefix(var, "pretty.", &name))
return 0;
for (i = 0; i < builtin_formats_len; i++) {
if (!strcmp(commit_formats[i].name, name))
return 0;
}
for (i = builtin_formats_len; i < commit_formats_len; i++) {
if (!strcmp(commit_formats[i].name, name)) {
commit_format = &commit_formats[i];
break;
}
}
if (!commit_format) {
ALLOC_GROW(commit_formats, commit_formats_len+1,
commit_formats_alloc);
commit_format = &commit_formats[commit_formats_len];
memset(commit_format, 0, sizeof(*commit_format));
commit_formats_len++;
}
free((char *)commit_format->name);
commit_format->name = xstrdup(name);
commit_format->format = CMIT_FMT_USERFORMAT;
if (git_config_string(&fmt, var, value))
return -1;
free((char *)commit_format->user_format);
if (skip_prefix(fmt, "format:", &stripped)) {
commit_format->is_tformat = 0;
commit_format->user_format = xstrdup(stripped);
free(fmt);
} else if (skip_prefix(fmt, "tformat:", &stripped)) {
commit_format->is_tformat = 1;
commit_format->user_format = xstrdup(stripped);
free(fmt);
} else if (strchr(fmt, '%')) {
commit_format->is_tformat = 1;
commit_format->user_format = fmt;
} else {
commit_format->is_alias = 1;
commit_format->user_format = fmt;
}
return 0;
}
static void setup_commit_formats(void)
{
struct cmt_fmt_map builtin_formats[] = {
{ "raw", CMIT_FMT_RAW, 0, 0 },
{ "medium", CMIT_FMT_MEDIUM, 0, 8 },
{ "short", CMIT_FMT_SHORT, 0, 0 },
{ "email", CMIT_FMT_EMAIL, 0, 0 },
{ "mboxrd", CMIT_FMT_MBOXRD, 0, 0 },
{ "fuller", CMIT_FMT_FULLER, 0, 8 },
{ "full", CMIT_FMT_FULL, 0, 8 },
{ "oneline", CMIT_FMT_ONELINE, 1, 0 },
{ "reference", CMIT_FMT_USERFORMAT, 1, 0,
0, DATE_SHORT, "%C(auto)%h (%s, %ad)" },
/*
* Please update $__git_log_pretty_formats in
* git-completion.bash when you add new formats.
*/
};
commit_formats_len = ARRAY_SIZE(builtin_formats);
builtin_formats_len = commit_formats_len;
ALLOC_GROW(commit_formats, commit_formats_len, commit_formats_alloc);
COPY_ARRAY(commit_formats, builtin_formats,
ARRAY_SIZE(builtin_formats));
git_config(git_pretty_formats_config, NULL);
}
static struct cmt_fmt_map *find_commit_format_recursive(const char *sought,
const char *original,
int num_redirections)
{
struct cmt_fmt_map *found = NULL;
size_t found_match_len = 0;
int i;
if (num_redirections >= commit_formats_len)
die("invalid --pretty format: "
"'%s' references an alias which points to itself",
original);
for (i = 0; i < commit_formats_len; i++) {
size_t match_len;
if (!istarts_with(commit_formats[i].name, sought))
continue;
match_len = strlen(commit_formats[i].name);
if (found == NULL || found_match_len > match_len) {
found = &commit_formats[i];
found_match_len = match_len;
}
}
if (found && found->is_alias) {
found = find_commit_format_recursive(found->user_format,
original,
num_redirections+1);
}
return found;
}
static struct cmt_fmt_map *find_commit_format(const char *sought)
{
if (!commit_formats)
setup_commit_formats();
return find_commit_format_recursive(sought, sought, 0);
}
void get_commit_format(const char *arg, struct rev_info *rev)
{
struct cmt_fmt_map *commit_format;
rev->use_terminator = 0;
if (!arg) {
rev->commit_format = CMIT_FMT_DEFAULT;
return;
}
if (skip_prefix(arg, "format:", &arg)) {
save_user_format(rev, arg, 0);
return;
}
if (!*arg || skip_prefix(arg, "tformat:", &arg) || strchr(arg, '%')) {
save_user_format(rev, arg, 1);
return;
}
commit_format = find_commit_format(arg);
if (!commit_format)
die("invalid --pretty format: %s", arg);
rev->commit_format = commit_format->format;
rev->use_terminator = commit_format->is_tformat;
rev->expand_tabs_in_log_default = commit_format->expand_tabs_in_log;
if (!rev->date_mode_explicit && commit_format->default_date_mode_type)
rev->date_mode.type = commit_format->default_date_mode_type;
if (commit_format->format == CMIT_FMT_USERFORMAT) {
save_user_format(rev, commit_format->user_format,
commit_format->is_tformat);
}
}
/*
* Generic support for pretty-printing the header
*/
static int get_one_line(const char *msg)
{
int ret = 0;
for (;;) {
char c = *msg++;
if (!c)
break;
ret++;
if (c == '\n')
break;
}
return ret;
}
/* High bit set, or ISO-2022-INT */
static int non_ascii(int ch)
{
return !isascii(ch) || ch == '\033';
}
int has_non_ascii(const char *s)
{
int ch;
if (!s)
return 0;
while ((ch = *s++) != '\0') {
if (non_ascii(ch))
return 1;
}
return 0;
}
static int is_rfc822_special(char ch)
{
switch (ch) {
case '(':
case ')':
case '<':
case '>':
case '[':
case ']':
case ':':
case ';':
case '@':
case ',':
case '.':
case '"':
case '\\':
return 1;
default:
return 0;
}
}
static int needs_rfc822_quoting(const char *s, int len)
{
int i;
for (i = 0; i < len; i++)
if (is_rfc822_special(s[i]))
return 1;
return 0;
}
static int last_line_length(struct strbuf *sb)
{
int i;
/* How many bytes are already used on the last line? */
for (i = sb->len - 1; i >= 0; i--)
if (sb->buf[i] == '\n')
break;
return sb->len - (i + 1);
}
static void add_rfc822_quoted(struct strbuf *out, const char *s, int len)
{
int i;
/* just a guess, we may have to also backslash-quote */
strbuf_grow(out, len + 2);
strbuf_addch(out, '"');
for (i = 0; i < len; i++) {
switch (s[i]) {
case '"':
case '\\':
strbuf_addch(out, '\\');
/* fall through */
default:
strbuf_addch(out, s[i]);
}
}
strbuf_addch(out, '"');
}
enum rfc2047_type {
RFC2047_SUBJECT,
RFC2047_ADDRESS
};
static int is_rfc2047_special(char ch, enum rfc2047_type type)
{
/*
* rfc2047, section 4.2:
*
* 8-bit values which correspond to printable ASCII characters other
* than "=", "?", and "_" (underscore), MAY be represented as those
* characters. (But see section 5 for restrictions.) In
* particular, SPACE and TAB MUST NOT be represented as themselves
* within encoded words.
*/
/*
* rule out non-ASCII characters and non-printable characters (the
* non-ASCII check should be redundant as isprint() is not localized
* and only knows about ASCII, but be defensive about that)
*/
if (non_ascii(ch) || !isprint(ch))
return 1;
/*
* rule out special printable characters (' ' should be the only
* whitespace character considered printable, but be defensive and use
* isspace())
*/
if (isspace(ch) || ch == '=' || ch == '?' || ch == '_')
return 1;
/*
* rfc2047, section 5.3:
*
* As a replacement for a 'word' entity within a 'phrase', for example,
* one that precedes an address in a From, To, or Cc header. The ABNF
* definition for 'phrase' from RFC 822 thus becomes:
*
* phrase = 1*( encoded-word / word )
*
* In this case the set of characters that may be used in a "Q"-encoded
* 'encoded-word' is restricted to: <upper and lower case ASCII
* letters, decimal digits, "!", "*", "+", "-", "/", "=", and "_"
* (underscore, ASCII 95.)>. An 'encoded-word' that appears within a
* 'phrase' MUST be separated from any adjacent 'word', 'text' or
* 'special' by 'linear-white-space'.
*/
if (type != RFC2047_ADDRESS)
return 0;
/* '=' and '_' are special cases and have been checked above */
return !(isalnum(ch) || ch == '!' || ch == '*' || ch == '+' || ch == '-' || ch == '/');
}
static int needs_rfc2047_encoding(const char *line, int len)
{
int i;
for (i = 0; i < len; i++) {
int ch = line[i];
if (non_ascii(ch) || ch == '\n')
return 1;
if ((i + 1 < len) && (ch == '=' && line[i+1] == '?'))
return 1;
}
return 0;
}
static void add_rfc2047(struct strbuf *sb, const char *line, size_t len,
const char *encoding, enum rfc2047_type type)
{
static const int max_encoded_length = 76; /* per rfc2047 */
int i;
int line_len = last_line_length(sb);
strbuf_grow(sb, len * 3 + strlen(encoding) + 100);
strbuf_addf(sb, "=?%s?q?", encoding);
line_len += strlen(encoding) + 5; /* 5 for =??q? */
while (len) {
/*
* RFC 2047, section 5 (3):
*
* Each 'encoded-word' MUST represent an integral number of
* characters. A multi-octet character may not be split across
* adjacent 'encoded- word's.
*/
const unsigned char *p = (const unsigned char *)line;
int chrlen = mbs_chrlen(&line, &len, encoding);
int is_special = (chrlen > 1) || is_rfc2047_special(*p, type);
/* "=%02X" * chrlen, or the byte itself */
const char *encoded_fmt = is_special ? "=%02X" : "%c";
int encoded_len = is_special ? 3 * chrlen : 1;
/*
* According to RFC 2047, we could encode the special character
* ' ' (space) with '_' (underscore) for readability. But many
* programs do not understand this and just leave the
* underscore in place. Thus, we do nothing special here, which
* causes ' ' to be encoded as '=20', avoiding this problem.
*/
if (line_len + encoded_len + 2 > max_encoded_length) {
/* It won't fit with trailing "?=" --- break the line */
strbuf_addf(sb, "?=\n =?%s?q?", encoding);
line_len = strlen(encoding) + 5 + 1; /* =??q? plus SP */
}
for (i = 0; i < chrlen; i++)
strbuf_addf(sb, encoded_fmt, p[i]);
line_len += encoded_len;
}
strbuf_addstr(sb, "?=");
}
const char *show_ident_date(const struct ident_split *ident,
struct date_mode mode)
{
timestamp_t date = 0;
long tz = 0;
if (ident->date_begin && ident->date_end)
date = parse_timestamp(ident->date_begin, NULL, 10);
if (date_overflows(date))
date = 0;
else {
if (ident->tz_begin && ident->tz_end)
tz = strtol(ident->tz_begin, NULL, 10);
if (tz >= INT_MAX || tz <= INT_MIN)
tz = 0;
}
return show_date(date, tz, mode);
}
static inline void strbuf_add_with_color(struct strbuf *sb, const char *color,
const char *buf, size_t buflen)
{
strbuf_addstr(sb, color);
strbuf_add(sb, buf, buflen);
if (*color)
strbuf_addstr(sb, GIT_COLOR_RESET);
}
static void append_line_with_color(struct strbuf *sb, struct grep_opt *opt,
const char *line, size_t linelen,
int color, enum grep_context ctx,
enum grep_header_field field)
{
const char *buf, *eol, *line_color, *match_color;
regmatch_t match;
int eflags = 0;
buf = line;
eol = buf + linelen;
if (!opt || !want_color(color) || opt->invert)
goto end;
line_color = opt->colors[GREP_COLOR_SELECTED];
match_color = opt->colors[GREP_COLOR_MATCH_SELECTED];
while (grep_next_match(opt, buf, eol, ctx, &match, field, eflags)) {
if (match.rm_so == match.rm_eo)
break;
strbuf_add_with_color(sb, line_color, buf, match.rm_so);
strbuf_add_with_color(sb, match_color, buf + match.rm_so,
match.rm_eo - match.rm_so);
buf += match.rm_eo;
eflags = REG_NOTBOL;
}
if (eflags)
strbuf_add_with_color(sb, line_color, buf, eol - buf);
else {
end:
strbuf_add(sb, buf, eol - buf);
}
}
static int use_in_body_from(const struct pretty_print_context *pp,
const struct ident_split *ident)
{
if (pp->rev && pp->rev->force_in_body_from)
return 1;
if (ident_cmp(pp->from_ident, ident))
return 1;
return 0;
}
void pp_user_info(struct pretty_print_context *pp,
const char *what, struct strbuf *sb,
const char *line, const char *encoding)
{
struct ident_split ident;
char *line_end;
const char *mailbuf, *namebuf;
size_t namelen, maillen;
int max_length = 78; /* per rfc2822 */
if (pp->fmt == CMIT_FMT_ONELINE)
return;
line_end = strchrnul(line, '\n');
if (split_ident_line(&ident, line, line_end - line))
return;
mailbuf = ident.mail_begin;
maillen = ident.mail_end - ident.mail_begin;
namebuf = ident.name_begin;
namelen = ident.name_end - ident.name_begin;
if (pp->mailmap)
map_user(pp->mailmap, &mailbuf, &maillen, &namebuf, &namelen);
if (cmit_fmt_is_mail(pp->fmt)) {
if (pp->from_ident && use_in_body_from(pp, &ident)) {
struct strbuf buf = STRBUF_INIT;
strbuf_addstr(&buf, "From: ");
strbuf_add(&buf, namebuf, namelen);
strbuf_addstr(&buf, " <");
strbuf_add(&buf, mailbuf, maillen);
strbuf_addstr(&buf, ">\n");
string_list_append(&pp->in_body_headers,
strbuf_detach(&buf, NULL));
mailbuf = pp->from_ident->mail_begin;
maillen = pp->from_ident->mail_end - mailbuf;
namebuf = pp->from_ident->name_begin;
namelen = pp->from_ident->name_end - namebuf;
}
strbuf_addstr(sb, "From: ");
if (pp->encode_email_headers &&
needs_rfc2047_encoding(namebuf, namelen)) {
add_rfc2047(sb, namebuf, namelen,
encoding, RFC2047_ADDRESS);
max_length = 76; /* per rfc2047 */
} else if (needs_rfc822_quoting(namebuf, namelen)) {
struct strbuf quoted = STRBUF_INIT;
add_rfc822_quoted("ed, namebuf, namelen);
strbuf_add_wrapped_bytes(sb, quoted.buf, quoted.len,
-6, 1, max_length);
strbuf_release("ed);
} else {
strbuf_add_wrapped_bytes(sb, namebuf, namelen,
-6, 1, max_length);
}
if (max_length <
last_line_length(sb) + strlen(" <") + maillen + strlen(">"))
strbuf_addch(sb, '\n');
strbuf_addf(sb, " <%.*s>\n", (int)maillen, mailbuf);
} else {
struct strbuf id = STRBUF_INIT;
enum grep_header_field field = GREP_HEADER_FIELD_MAX;
struct grep_opt *opt = pp->rev ? &pp->rev->grep_filter : NULL;
if (!strcmp(what, "Author"))
field = GREP_HEADER_AUTHOR;
else if (!strcmp(what, "Commit"))
field = GREP_HEADER_COMMITTER;
strbuf_addf(sb, "%s: ", what);
if (pp->fmt == CMIT_FMT_FULLER)
strbuf_addchars(sb, ' ', 4);
strbuf_addf(&id, "%.*s <%.*s>", (int)namelen, namebuf,
(int)maillen, mailbuf);
append_line_with_color(sb, opt, id.buf, id.len, pp->color,
GREP_CONTEXT_HEAD, field);
strbuf_addch(sb, '\n');
strbuf_release(&id);
}
switch (pp->fmt) {
case CMIT_FMT_MEDIUM:
strbuf_addf(sb, "Date: %s\n",
show_ident_date(&ident, pp->date_mode));
break;
case CMIT_FMT_EMAIL:
case CMIT_FMT_MBOXRD:
strbuf_addf(sb, "Date: %s\n",
show_ident_date(&ident, DATE_MODE(RFC2822)));
break;
case CMIT_FMT_FULLER:
strbuf_addf(sb, "%sDate: %s\n", what,
show_ident_date(&ident, pp->date_mode));
break;
default:
/* notin' */
break;
}
}
static int is_blank_line(const char *line, int *len_p)
{
int len = *len_p;
while (len && isspace(line[len - 1]))
len--;
*len_p = len;
return !len;
}
const char *skip_blank_lines(const char *msg)
{
for (;;) {
int linelen = get_one_line(msg);
int ll = linelen;
if (!linelen)
break;
if (!is_blank_line(msg, &ll))
break;
msg += linelen;
}
return msg;
}
static void add_merge_info(const struct pretty_print_context *pp,
struct strbuf *sb, const struct commit *commit)
{
struct commit_list *parent = commit->parents;
if ((pp->fmt == CMIT_FMT_ONELINE) || (cmit_fmt_is_mail(pp->fmt)) ||
!parent || !parent->next)
return;
strbuf_addstr(sb, "Merge:");
while (parent) {
struct object_id *oidp = &parent->item->object.oid;
strbuf_addch(sb, ' ');
if (pp->abbrev)
strbuf_add_unique_abbrev(sb, oidp, pp->abbrev);
else
strbuf_addstr(sb, oid_to_hex(oidp));
parent = parent->next;
}
strbuf_addch(sb, '\n');
}
static char *get_header(const char *msg, const char *key)
{
size_t len;
const char *v = find_commit_header(msg, key, &len);
return v ? xmemdupz(v, len) : NULL;
}
static char *replace_encoding_header(char *buf, const char *encoding)
{
struct strbuf tmp = STRBUF_INIT;
size_t start, len;
char *cp = buf;
/* guess if there is an encoding header before a \n\n */
while (!starts_with(cp, "encoding ")) {
cp = strchr(cp, '\n');
if (!cp || *++cp == '\n')
return buf;
}
start = cp - buf;
cp = strchr(cp, '\n');
if (!cp)
return buf; /* should not happen but be defensive */
len = cp + 1 - (buf + start);
strbuf_attach(&tmp, buf, strlen(buf), strlen(buf) + 1);
if (is_encoding_utf8(encoding)) {
/* we have re-coded to UTF-8; drop the header */
strbuf_remove(&tmp, start, len);
} else {
/* just replaces XXXX in 'encoding XXXX\n' */
strbuf_splice(&tmp, start + strlen("encoding "),
len - strlen("encoding \n"),
encoding, strlen(encoding));
}
return strbuf_detach(&tmp, NULL);
}
const char *repo_logmsg_reencode(struct repository *r,
const struct commit *commit,
char **commit_encoding,
const char *output_encoding)
{
static const char *utf8 = "UTF-8";
const char *use_encoding;
char *encoding;
const char *msg = repo_get_commit_buffer(r, commit, NULL);
char *out;
if (!output_encoding || !*output_encoding) {
if (commit_encoding)
*commit_encoding = get_header(msg, "encoding");
return msg;
}
encoding = get_header(msg, "encoding");
if (commit_encoding)
*commit_encoding = encoding;
use_encoding = encoding ? encoding : utf8;
if (same_encoding(use_encoding, output_encoding)) {
/*
* No encoding work to be done. If we have no encoding header
* at all, then there's nothing to do, and we can return the
* message verbatim (whether newly allocated or not).
*/
if (!encoding)
return msg;
/*
* Otherwise, we still want to munge the encoding header in the
* result, which will be done by modifying the buffer. If we
* are using a fresh copy, we can reuse it. But if we are using
* the cached copy from repo_get_commit_buffer, we need to duplicate it
* to avoid munging the cached copy.
*/
if (msg == get_cached_commit_buffer(r, commit, NULL))
out = xstrdup(msg);
else
out = (char *)msg;
}
else {
/*
* There's actual encoding work to do. Do the reencoding, which
* still leaves the header to be replaced in the next step. At
* this point, we are done with msg. If we allocated a fresh
* copy, we can free it.
*/
out = reencode_string(msg, output_encoding, use_encoding);
if (out)
repo_unuse_commit_buffer(r, commit, msg);
}
/*
* This replacement actually consumes the buffer we hand it, so we do
* not have to worry about freeing the old "out" here.
*/
if (out)
out = replace_encoding_header(out, output_encoding);
if (!commit_encoding)
free(encoding);
/*
* If the re-encoding failed, out might be NULL here; in that
* case we just return the commit message verbatim.
*/
return out ? out : msg;
}
static int mailmap_name(const char **email, size_t *email_len,
const char **name, size_t *name_len)
{
static struct string_list *mail_map;
if (!mail_map) {
CALLOC_ARRAY(mail_map, 1);
read_mailmap(mail_map);
}
return mail_map->nr && map_user(mail_map, email, email_len, name, name_len);
}
static size_t format_person_part(struct strbuf *sb, char part,
const char *msg, int len,
struct date_mode dmode)
{
/* currently all placeholders have same length */
const int placeholder_len = 2;
struct ident_split s;
const char *name, *mail;
size_t maillen, namelen;
if (split_ident_line(&s, msg, len) < 0)
goto skip;
name = s.name_begin;
namelen = s.name_end - s.name_begin;
mail = s.mail_begin;
maillen = s.mail_end - s.mail_begin;
if (part == 'N' || part == 'E' || part == 'L') /* mailmap lookup */
mailmap_name(&mail, &maillen, &name, &namelen);
if (part == 'n' || part == 'N') { /* name */
strbuf_add(sb, name, namelen);
return placeholder_len;
}
if (part == 'e' || part == 'E') { /* email */
strbuf_add(sb, mail, maillen);
return placeholder_len;
}
if (part == 'l' || part == 'L') { /* local-part */
const char *at = memchr(mail, '@', maillen);
if (at)
maillen = at - mail;
strbuf_add(sb, mail, maillen);
return placeholder_len;
}
if (!s.date_begin)
goto skip;
if (part == 't') { /* date, UNIX timestamp */
strbuf_add(sb, s.date_begin, s.date_end - s.date_begin);
return placeholder_len;
}
switch (part) {
case 'd': /* date */
strbuf_addstr(sb, show_ident_date(&s, dmode));
return placeholder_len;
case 'D': /* date, RFC2822 style */
strbuf_addstr(sb, show_ident_date(&s, DATE_MODE(RFC2822)));
return placeholder_len;
case 'r': /* date, relative */
strbuf_addstr(sb, show_ident_date(&s, DATE_MODE(RELATIVE)));
return placeholder_len;
case 'i': /* date, ISO 8601-like */
strbuf_addstr(sb, show_ident_date(&s, DATE_MODE(ISO8601)));
return placeholder_len;
case 'I': /* date, ISO 8601 strict */
strbuf_addstr(sb, show_ident_date(&s, DATE_MODE(ISO8601_STRICT)));
return placeholder_len;
case 'h': /* date, human */
strbuf_addstr(sb, show_ident_date(&s, DATE_MODE(HUMAN)));
return placeholder_len;
case 's':
strbuf_addstr(sb, show_ident_date(&s, DATE_MODE(SHORT)));
return placeholder_len;
}
skip:
/*
* reading from either a bogus commit, or a reflog entry with
* %gn, %ge, etc.; 'sb' cannot be updated, but we still need
* to compute a valid return value.
*/
if (part == 'n' || part == 'e' || part == 't' || part == 'd'
|| part == 'D' || part == 'r' || part == 'i')
return placeholder_len;
return 0; /* unknown placeholder */
}
struct chunk {
size_t off;
size_t len;
};
enum flush_type {
no_flush,
flush_right,
flush_left,
flush_left_and_steal,
flush_both
};
enum trunc_type {
trunc_none,
trunc_left,
trunc_middle,
trunc_right
};
struct format_commit_context {
struct repository *repository;
const struct commit *commit;
const struct pretty_print_context *pretty_ctx;
unsigned commit_header_parsed:1;
unsigned commit_message_parsed:1;
struct signature_check signature_check;
enum flush_type flush_type;
enum trunc_type truncate;
const char *message;
char *commit_encoding;
size_t width, indent1, indent2;
int auto_color;
int padding;
/* These offsets are relative to the start of the commit message. */
struct chunk author;
struct chunk committer;
size_t message_off;
size_t subject_off;
size_t body_off;
/* The following ones are relative to the result struct strbuf. */
size_t wrap_start;
};
static void parse_commit_header(struct format_commit_context *context)
{
const char *msg = context->message;
int i;
for (i = 0; msg[i]; i++) {
const char *name;
int eol;
for (eol = i; msg[eol] && msg[eol] != '\n'; eol++)
; /* do nothing */
if (i == eol) {
break;
} else if (skip_prefix(msg + i, "author ", &name)) {
context->author.off = name - msg;
context->author.len = msg + eol - name;
} else if (skip_prefix(msg + i, "committer ", &name)) {
context->committer.off = name - msg;
context->committer.len = msg + eol - name;
}
i = eol;
}
context->message_off = i;
context->commit_header_parsed = 1;
}
static int istitlechar(char c)
{
return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') ||
(c >= '0' && c <= '9') || c == '.' || c == '_';
}
void format_sanitized_subject(struct strbuf *sb, const char *msg, size_t len)
{
size_t trimlen;
size_t start_len = sb->len;
int space = 2;
int i;
for (i = 0; i < len; i++) {
if (istitlechar(msg[i])) {
if (space == 1)
strbuf_addch(sb, '-');
space = 0;
strbuf_addch(sb, msg[i]);
if (msg[i] == '.')
while (msg[i+1] == '.')
i++;
} else
space |= 1;
}
/* trim any trailing '.' or '-' characters */
trimlen = 0;
while (sb->len - trimlen > start_len &&
(sb->buf[sb->len - 1 - trimlen] == '.'
|| sb->buf[sb->len - 1 - trimlen] == '-'))
trimlen++;
strbuf_remove(sb, sb->len - trimlen, trimlen);
}
const char *format_subject(struct strbuf *sb, const char *msg,
const char *line_separator)
{
int first = 1;
for (;;) {
const char *line = msg;
int linelen = get_one_line(line);
msg += linelen;
if (!linelen || is_blank_line(line, &linelen))
break;
if (!sb)
continue;
strbuf_grow(sb, linelen + 2);
if (!first)
strbuf_addstr(sb, line_separator);
strbuf_add(sb, line, linelen);
first = 0;
}
return msg;
}