summaryrefslogtreecommitdiff
path: root/pretty.c
blob: 2e031e62fd98c02bfa6cc558fc49aef86c03ed09 (plain)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
#include "cache.h"
#include "commit.h"
#include "utf8.h"
#include "diff.h"
#include "revision.h"
#include "string-list.h"
#include "mailmap.h"
#include "log-tree.h"
#include "color.h"
#include "reflog-walk.h"

static char *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;
}

void get_commit_format(const char *arg, struct rev_info *rev)
{
	int i;
	static struct cmt_fmt_map {
		const char *n;
		size_t cmp_len;
		enum cmit_fmt v;
	} cmt_fmts[] = {
		{ "raw",	1,	CMIT_FMT_RAW },
		{ "medium",	1,	CMIT_FMT_MEDIUM },
		{ "short",	1,	CMIT_FMT_SHORT },
		{ "email",	1,	CMIT_FMT_EMAIL },
		{ "full",	5,	CMIT_FMT_FULL },
		{ "fuller",	5,	CMIT_FMT_FULLER },
		{ "oneline",	1,	CMIT_FMT_ONELINE },
	};

	rev->use_terminator = 0;
	if (!arg || !*arg) {
		rev->commit_format = CMIT_FMT_DEFAULT;
		return;
	}
	if (!prefixcmp(arg, "format:") || !prefixcmp(arg, "tformat:")) {
		save_user_format(rev, strchr(arg, ':') + 1, arg[0] == 't');
		return;
	}
	for (i = 0; i < ARRAY_SIZE(cmt_fmts); i++) {
		if (!strncmp(arg, cmt_fmts[i].n, cmt_fmts[i].cmp_len) &&
		    !strncmp(arg, cmt_fmts[i].n, strlen(arg))) {
			if (cmt_fmts[i].v == CMIT_FMT_ONELINE)
				rev->use_terminator = 1;
			rev->commit_format = cmt_fmts[i].v;
			return;
		}
	}
	if (strchr(arg, '%')) {
		save_user_format(rev, arg, 1);
		return;
	}

	die("invalid --pretty format: %s", arg);
}

/*
 * 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 */
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_rfc2047_special(char ch)
{
	return (non_ascii(ch) || (ch == '=') || (ch == '?') || (ch == '_'));
}

static void add_rfc2047(struct strbuf *sb, const char *line, int len,
		       const char *encoding)
{
	int i, last;

	for (i = 0; i < len; i++) {
		int ch = line[i];
		if (non_ascii(ch))
			goto needquote;
		if ((i + 1 < len) && (ch == '=' && line[i+1] == '?'))
			goto needquote;
	}
	strbuf_add(sb, line, len);
	return;

needquote:
	strbuf_grow(sb, len * 3 + strlen(encoding) + 100);
	strbuf_addf(sb, "=?%s?q?", encoding);
	for (i = last = 0; i < len; i++) {
		unsigned ch = line[i] & 0xFF;
		/*
		 * We encode ' ' using '=20' even though rfc2047
		 * allows using '_' for readability.  Unfortunately,
		 * many programs do not understand this and just
		 * leave the underscore in place.
		 */
		if (is_rfc2047_special(ch) || ch == ' ') {
			strbuf_add(sb, line + last, i - last);
			strbuf_addf(sb, "=%02X", ch);
			last = i + 1;
		}
	}
	strbuf_add(sb, line + last, len - last);
	strbuf_addstr(sb, "?=");
}

void pp_user_info(const char *what, enum cmit_fmt fmt, struct strbuf *sb,
		  const char *line, enum date_mode dmode,
		  const char *encoding)
{
	char *date;
	int namelen;
	unsigned long time;
	int tz;

	if (fmt == CMIT_FMT_ONELINE)
		return;
	date = strchr(line, '>');
	if (!date)
		return;
	namelen = ++date - line;
	time = strtoul(date, &date, 10);
	tz = strtol(date, NULL, 10);

	if (fmt == CMIT_FMT_EMAIL) {
		char *name_tail = strchr(line, '<');
		int display_name_length;
		if (!name_tail)
			return;
		while (line < name_tail && isspace(name_tail[-1]))
			name_tail--;
		display_name_length = name_tail - line;
		strbuf_addstr(sb, "From: ");
		add_rfc2047(sb, line, display_name_length, encoding);
		strbuf_add(sb, name_tail, namelen - display_name_length);
		strbuf_addch(sb, '\n');
	} else {
		strbuf_addf(sb, "%s: %.*s%.*s\n", what,
			      (fmt == CMIT_FMT_FULLER) ? 4 : 0,
			      "    ", namelen, line);
	}
	switch (fmt) {
	case CMIT_FMT_MEDIUM:
		strbuf_addf(sb, "Date:   %s\n", show_date(time, tz, dmode));
		break;
	case CMIT_FMT_EMAIL:
		strbuf_addf(sb, "Date: %s\n", show_date(time, tz, DATE_RFC2822));
		break;
	case CMIT_FMT_FULLER:
		strbuf_addf(sb, "%sDate: %s\n", what, show_date(time, tz, dmode));
		break;
	default:
		/* notin' */
		break;
	}
}

static int is_empty_line(const char *line, int *len_p)
{
	int len = *len_p;
	while (len && isspace(line[len-1]))
		len--;
	*len_p = len;
	return !len;
}

static const char *skip_empty_lines(const char *msg)
{
	for (;;) {
		int linelen = get_one_line(msg);
		int ll = linelen;
		if (!linelen)
			break;
		if (!is_empty_line(msg, &ll))
			break;
		msg += linelen;
	}
	return msg;
}

static void add_merge_info(enum cmit_fmt fmt, struct strbuf *sb,
			const struct commit *commit, int abbrev)
{
	struct commit_list *parent = commit->parents;

	if ((fmt == CMIT_FMT_ONELINE) || (fmt == CMIT_FMT_EMAIL) ||
	    !parent || !parent->next)
		return;

	strbuf_addstr(sb, "Merge:");

	while (parent) {
		struct commit *p = parent->item;
		const char *hex = NULL;
		if (abbrev)
			hex = find_unique_abbrev(p->object.sha1, abbrev);
		if (!hex)
			hex = sha1_to_hex(p->object.sha1);
		parent = parent->next;

		strbuf_addf(sb, " %s", hex);
	}
	strbuf_addch(sb, '\n');
}

static char *get_header(const struct commit *commit, const char *key)
{
	int key_len = strlen(key);
	const char *line = commit->buffer;

	for (;;) {
		const char *eol = strchr(line, '\n'), *next;

		if (line == eol)
			return NULL;
		if (!eol) {
			eol = line + strlen(line);
			next = NULL;
		} else
			next = eol + 1;
		if (eol - line > key_len &&
		    !strncmp(line, key, key_len) &&
		    line[key_len] == ' ') {
			return xmemdupz(line + key_len + 1, eol - line - key_len - 1);
		}
		line = next;
	}
}

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 (strncmp(cp, "encoding ", strlen("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);
}

static char *logmsg_reencode(const struct commit *commit,
			     const char *output_encoding)
{
	static const char *utf8 = "UTF-8";
	const char *use_encoding;
	char *encoding;
	char *out;

	if (!*output_encoding)
		return NULL;
	encoding = get_header(commit, "encoding");
	use_encoding = encoding ? encoding : utf8;
	if (!strcmp(use_encoding, output_encoding))
		if (encoding) /* we'll strip encoding header later */
			out = xstrdup(commit->buffer);
		else
			return NULL; /* nothing to do */
	else
		out = reencode_string(commit->buffer,
				      output_encoding, use_encoding);
	if (out)
		out = replace_encoding_header(out, output_encoding);

	free(encoding);
	return out;
}

static int mailmap_name(char *email, int email_len, char *name, int name_len)
{
	static struct string_list *mail_map;
	if (!mail_map) {
		mail_map = xcalloc(1, sizeof(*mail_map));
		read_mailmap(mail_map, NULL);
	}
	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, enum date_mode dmode)
{
	/* currently all placeholders have same length */
	const int placeholder_len = 2;
	int start, end, tz = 0;
	unsigned long date = 0;
	char *ep;
	const char *name_start, *name_end, *mail_start, *mail_end, *msg_end = msg+len;
	char person_name[1024];
	char person_mail[1024];

	/* advance 'end' to point to email start delimiter */
	for (end = 0; end < len && msg[end] != '<'; end++)
		; /* do nothing */

	/*
	 * When end points at the '<' that we found, it should have
	 * matching '>' later, which means 'end' must be strictly
	 * below len - 1.
	 */
	if (end >= len - 2)
		goto skip;

	/* Seek for both name and email part */
	name_start = msg;
	name_end = msg+end;
	while (name_end > name_start && isspace(*(name_end-1)))
		name_end--;
	mail_start = msg+end+1;
	mail_end = mail_start;
	while (mail_end < msg_end && *mail_end != '>')
		mail_end++;
	if (mail_end == msg_end)
		goto skip;
	end = mail_end-msg;

	if (part == 'N' || part == 'E') { /* mailmap lookup */
		strlcpy(person_name, name_start, name_end-name_start+1);
		strlcpy(person_mail, mail_start, mail_end-mail_start+1);
		mailmap_name(person_mail, sizeof(person_mail), person_name, sizeof(person_name));
		name_start = person_name;
		name_end = name_start + strlen(person_name);
		mail_start = person_mail;
		mail_end = mail_start +  strlen(person_mail);
	}
	if (part == 'n' || part == 'N') {	/* name */
		strbuf_add(sb, name_start, name_end-name_start);
		return placeholder_len;
	}
	if (part == 'e' || part == 'E') {	/* email */
		strbuf_add(sb, mail_start, mail_end-mail_start);
		return placeholder_len;
	}

	/* advance 'start' to point to date start delimiter */
	for (start = end + 1; start < len && isspace(msg[start]); start++)
		; /* do nothing */
	if (start >= len)
		goto skip;
	date = strtoul(msg + start, &ep, 10);
	if (msg + start == ep)
		goto skip;

	if (part == 't') {	/* date, UNIX timestamp */
		strbuf_add(sb, msg + start, ep - (msg + start));
		return placeholder_len;
	}

	/* parse tz */
	for (start = ep - msg + 1; start < len && isspace(msg[start]); start++)
		; /* do nothing */
	if (start + 1 < len) {
		tz = strtoul(msg + start + 1, NULL, 10);
		if (msg[start] == '-')
			tz = -tz;
	}

	switch (part) {
	case 'd':	/* date */
		strbuf_addstr(sb, show_date(date, tz, dmode));
		return placeholder_len;
	case 'D':	/* date, RFC2822 style */
		strbuf_addstr(sb, show_date(date, tz, DATE_RFC2822));
		return placeholder_len;
	case 'r':	/* date, relative */
		strbuf_addstr(sb, show_date(date, tz, DATE_RELATIVE));
		return placeholder_len;
	case 'i':	/* date, ISO 8601 */
		strbuf_addstr(sb, show_date(date, tz, DATE_ISO8601));
		return placeholder_len;
	}

skip:
	/*
	 * bogus commit, '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;
};

struct format_commit_context {
	const struct commit *commit;
	const struct pretty_print_context *pretty_ctx;
	unsigned commit_header_parsed:1;
	unsigned commit_message_parsed:1;
	size_t width, indent1, indent2;

	/* These offsets are relative to the start of the commit message. */
	struct chunk author;
	struct chunk committer;
	struct chunk encoding;
	size_t message_off;
	size_t subject_off;
	size_t body_off;

	/* The following ones are relative to the result struct strbuf. */
	struct chunk abbrev_commit_hash;
	struct chunk abbrev_tree_hash;
	struct chunk abbrev_parent_hashes;
	size_t wrap_start;
};

static int add_again(struct strbuf *sb, struct chunk *chunk)
{
	if (chunk->len) {
		strbuf_adddup(sb, chunk->off, chunk->len);
		return 1;
	}

	/*
	 * We haven't seen this chunk before.  Our caller is surely
	 * going to add it the hard way now.  Remember the most likely
	 * start of the to-be-added chunk: the current end of the
	 * struct strbuf.
	 */
	chunk->off = sb->len;
	return 0;
}

static void parse_commit_header(struct format_commit_context *context)
{
	const char *msg = context->commit->buffer;
	int i;

	for (i = 0; msg[i]; i++) {
		int eol;
		for (eol = i; msg[eol] && msg[eol] != '\n'; eol++)
			; /* do nothing */

		if (i == eol) {
			break;
		} else if (!prefixcmp(msg + i, "author ")) {
			context->author.off = i + 7;
			context->author.len = eol - i - 7;
		} else if (!prefixcmp(msg + i, "committer ")) {
			context->committer.off = i + 10;
			context->committer.len = eol - i - 10;
		} else if (!prefixcmp(msg + i, "encoding ")) {
			context->encoding.off = i + 9;
			context->encoding.len = eol - i - 9;
		}
		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 == '_';
}

static void format_sanitized_subject(struct strbuf *sb, const char *msg)
{
	size_t trimlen;
	size_t start_len = sb->len;
	int space = 2;

	for (; *msg && *msg != '\n'; msg++) {
		if (istitlechar(*msg)) {
			if (space == 1)
				strbuf_addch(sb, '-');
			space = 0;
			strbuf_addch(sb, *msg);
			if (*msg == '.')
				while (*(msg+1) == '.')
					msg++;
		} 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_empty_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;
}

static void parse_commit_message(struct format_commit_context *c)
{
	const char *msg = c->commit->buffer + c->message_off;
	const char *start = c->commit->buffer;

	msg = skip_empty_lines(msg);
	c->subject_off = msg - start;

	msg = format_subject(NULL, msg, NULL);
	msg = skip_empty_lines(msg);
	c->body_off = msg - start;

	c->commit_message_parsed = 1;
}

static void format_decoration(struct strbuf *sb, const struct commit *commit)
{
	struct name_decoration *d;
	const char *prefix = " (";

	load_ref_decorations(DECORATE_SHORT_REFS);
	d = lookup_decoration(&name_decoration, &commit->object);
	while (d) {
		strbuf_addstr(sb, prefix);
		prefix = ", ";
		strbuf_addstr(sb, d->name);
		d = d->next;
	}
	if (prefix[0] == ',')
		strbuf_addch(sb, ')');
}

static void strbuf_wrap(struct strbuf *sb, size_t pos,
			size_t width, size_t indent1, size_t indent2)
{
	struct strbuf tmp = STRBUF_INIT;

	if (pos)
		strbuf_add(&tmp, sb->buf, pos);
	strbuf_add_wrapped_text(&tmp, sb->buf + pos,
				(int) indent1, (int) indent2, (int) width);
	strbuf_swap(&tmp, sb);
	strbuf_release(&tmp);
}

static void rewrap_message_tail(struct strbuf *sb,
				struct format_commit_context *c,
				size_t new_width, size_t new_indent1,
				size_t new_indent2)
{
	if (c->width == new_width && c->indent1 == new_indent1 &&
	    c->indent2 == new_indent2)
		return;
	if (c->wrap_start < sb->len)
		strbuf_wrap(sb, c->wrap_start, c->width, c->indent1, c->indent2);
	c->wrap_start = sb->len;
	c->width = new_width;
	c->indent1 = new_indent1;
	c->indent2 = new_indent2;
}

static size_t format_commit_item(struct strbuf *sb, const char *placeholder,
                               void *context)
{
	struct format_commit_context *c = context;
	const struct commit *commit = c->commit;
	const char *msg = commit->buffer;
	struct commit_list *p;
	int h1, h2;

	/* these are independent of the commit */
	switch (placeholder[0]) {
	case 'C':
		if (placeholder[1] == '(') {
			const char *end = strchr(placeholder + 2, ')');
			char color[COLOR_MAXLEN];
			if (!end)
				return 0;
			color_parse_mem(placeholder + 2,
					end - (placeholder + 2),
					"--pretty format", color);
			strbuf_addstr(sb, color);
			return end - placeholder + 1;
		}
		if (!prefixcmp(placeholder + 1, "red")) {
			strbuf_addstr(sb, GIT_COLOR_RED);
			return 4;
		} else if (!prefixcmp(placeholder + 1, "green")) {
			strbuf_addstr(sb, GIT_COLOR_GREEN);
			return 6;
		} else if (!prefixcmp(placeholder + 1, "blue")) {
			strbuf_addstr(sb, GIT_COLOR_BLUE);
			return 5;
		} else if (!prefixcmp(placeholder + 1, "reset")) {
			strbuf_addstr(sb, GIT_COLOR_RESET);
			return 6;
		} else
			return 0;
	case 'n':		/* newline */
		strbuf_addch(sb, '\n');
		return 1;
	case 'x':
		/* %x00 == NUL, %x0a == LF, etc. */
		if (0 <= (h1 = hexval_table[0xff & placeholder[1]]) &&
		    h1 <= 16 &&
		    0 <= (h2 = hexval_table[0xff & placeholder[2]]) &&
		    h2 <= 16) {
			strbuf_addch(sb, (h1<<4)|h2);
			return 3;
		} else
			return 0;
	case 'w':
		if (placeholder[1] == '(') {
			unsigned long width = 0, indent1 = 0, indent2 = 0;
			char *next;
			const char *start = placeholder + 2;
			const char *end = strchr(start, ')');
			if (!end)
				return 0;
			if (end > start) {
				width = strtoul(start, &next, 10);
				if (*next == ',') {
					indent1 = strtoul(next + 1, &next, 10);
					if (*next == ',') {
						indent2 = strtoul(next + 1,
								 &next, 10);
					}
				}
				if (*next != ')')
					return 0;
			}
			rewrap_message_tail(sb, c, width, indent1, indent2);
			return end - placeholder + 1;
		} else
			return 0;
	}

	/* these depend on the commit */
	if (!commit->object.parsed)
		parse_object(commit->object.sha1);

	switch (placeholder[0]) {
	case 'H':		/* commit hash */
		strbuf_addstr(sb, sha1_to_hex(commit->object.sha1));
		return 1;
	case 'h':		/* abbreviated commit hash */
		if (add_again(sb, &c->abbrev_commit_hash))
			return 1;
		strbuf_addstr(sb, find_unique_abbrev(commit->object.sha1,
		                                     DEFAULT_ABBREV));
		c->abbrev_commit_hash.len = sb->len - c->abbrev_commit_hash.off;
		return 1;
	case 'T':		/* tree hash */
		strbuf_addstr(sb, sha1_to_hex(commit->tree->object.sha1));
		return 1;
	case 't':		/* abbreviated tree hash */
		if (add_again(sb, &c->abbrev_tree_hash))
			return 1;
		strbuf_addstr(sb, find_unique_abbrev(commit->tree->object.sha1,
		                                     DEFAULT_ABBREV));
		c->abbrev_tree_hash.len = sb->len - c->abbrev_tree_hash.off;
		return 1;
	case 'P':		/* parent hashes */
		for (p = commit->parents; p; p = p->next) {
			if (p != commit->parents)
				strbuf_addch(sb, ' ');
			strbuf_addstr(sb, sha1_to_hex(p->item->object.sha1));
		}
		return 1;
	case 'p':		/* abbreviated parent hashes */
		if (add_again(sb, &c->abbrev_parent_hashes))
			return 1;
		for (p = commit->parents; p; p = p->next) {
			if (p != commit->parents)
				strbuf_addch(sb, ' ');
			strbuf_addstr(sb, find_unique_abbrev(
					p->item->object.sha1, DEFAULT_ABBREV));
		}
		c->abbrev_parent_hashes.len = sb->len -
		                              c->abbrev_parent_hashes.off;
		return 1;
	case 'm':		/* left/right/bottom */
		strbuf_addch(sb, (commit->object.flags & BOUNDARY)
		                 ? '-'
		                 : (commit->object.flags & SYMMETRIC_LEFT)
		                 ? '<'
		                 : '>');
		return 1;
	case 'd':
		format_decoration(sb, commit);
		return 1;
	case 'g':		/* reflog info */
		switch(placeholder[1]) {
		case 'd':	/* reflog selector */
		case 'D':
			if (c->pretty_ctx->reflog_info)
				get_reflog_selector(sb,
						    c->pretty_ctx->reflog_info,
						    c->pretty_ctx->date_mode,
						    (placeholder[1] == 'd'));
			return 2;
		case 's':	/* reflog message */
			if (c->pretty_ctx->reflog_info)
				get_reflog_message(sb, c->pretty_ctx->reflog_info);
			return 2;
		}
		return 0;	/* unknown %g placeholder */
	}

	/* For the rest we have to parse the commit header. */
	if (!c->commit_header_parsed)
		parse_commit_header(c);

	switch (placeholder[0]) {
	case 'a':	/* author ... */
		return format_person_part(sb, placeholder[1],
				   msg + c->author.off, c->author.len,
				   c->pretty_ctx->date_mode);
	case 'c':	/* committer ... */
		return format_person_part(sb, placeholder[1],
				   msg + c->committer.off, c->committer.len,
				   c->pretty_ctx->date_mode);
	case 'e':	/* encoding */
		strbuf_add(sb, msg + c->encoding.off, c->encoding.len);
		return 1;
	}

	/* Now we need to parse the commit message. */
	if (!c->commit_message_parsed)
		parse_commit_message(c);

	switch (placeholder[0]) {
	case 's':	/* subject */
		format_subject(sb, msg + c->subject_off, " ");
		return 1;
	case 'f':	/* sanitized subject */
		format_sanitized_subject(sb, msg + c->subject_off);
		return 1;
	case 'b':	/* body */
		strbuf_addstr(sb, msg + c->body_off);
		return 1;
	}
	return 0;	/* unknown placeholder */
}

void format_commit_message(const struct commit *commit,
			   const char *format, struct strbuf *sb,
			   const struct pretty_print_context *pretty_ctx)
{
	struct format_commit_context context;

	memset(&context, 0, sizeof(context));
	context.commit = commit;
	context.pretty_ctx = pretty_ctx;
	context.wrap_start = sb->len;
	strbuf_expand(sb, format, format_commit_item, &context);
	rewrap_message_tail(sb, &context, 0, 0, 0);
}

static void pp_header(enum cmit_fmt fmt,
		      int abbrev,
		      enum date_mode dmode,
		      const char *encoding,
		      const struct commit *commit,
		      const char **msg_p,
		      struct strbuf *sb)
{
	int parents_shown = 0;

	for (;;) {
		const char *line = *msg_p;
		int linelen = get_one_line(*msg_p);

		if (!linelen)
			return;
		*msg_p += linelen;

		if (linelen == 1)
			/* End of header */
			return;

		if (fmt == CMIT_FMT_RAW) {
			strbuf_add(sb, line, linelen);
			continue;
		}

		if (!memcmp(line, "parent ", 7)) {
			if (linelen != 48)
				die("bad parent line in commit");
			continue;
		}

		if (!parents_shown) {
			struct commit_list *parent;
			int num;
			for (parent = commit->parents, num = 0;
			     parent;
			     parent = parent->next, num++)
				;
			/* with enough slop */
			strbuf_grow(sb, num * 50 + 20);
			add_merge_info(fmt, sb, commit, abbrev);
			parents_shown = 1;
		}

		/*
		 * MEDIUM == DEFAULT shows only author with dates.
		 * FULL shows both authors but not dates.
		 * FULLER shows both authors and dates.
		 */
		if (!memcmp(line, "author ", 7)) {
			strbuf_grow(sb, linelen + 80);
			pp_user_info("Author", fmt, sb, line + 7, dmode, encoding);
		}
		if (!memcmp(line, "committer ", 10) &&
		    (fmt == CMIT_FMT_FULL || fmt == CMIT_FMT_FULLER)) {
			strbuf_grow(sb, linelen + 80);
			pp_user_info("Commit", fmt, sb, line + 10, dmode, encoding);
		}
	}
}

void pp_title_line(enum cmit_fmt fmt,
		   const char **msg_p,
		   struct strbuf *sb,
		   const char *subject,
		   const char *after_subject,
		   const char *encoding,
		   int need_8bit_cte)
{
	const char *line_separator = (fmt == CMIT_FMT_EMAIL) ? "\n " : " ";
	struct strbuf title;

	strbuf_init(&title, 80);
	*msg_p = format_subject(&title, *msg_p, line_separator);

	strbuf_grow(sb, title.len + 1024);
	if (subject) {
		strbuf_addstr(sb, subject);
		add_rfc2047(sb, title.buf, title.len, encoding);
	} else {
		strbuf_addbuf(sb, &title);
	}
	strbuf_addch(sb, '\n');

	if (need_8bit_cte > 0) {
		const char *header_fmt =
			"MIME-Version: 1.0\n"
			"Content-Type: text/plain; charset=%s\n"
			"Content-Transfer-Encoding: 8bit\n";
		strbuf_addf(sb, header_fmt, encoding);
	}
	if (after_subject) {
		strbuf_addstr(sb, after_subject);
	}
	if (fmt == CMIT_FMT_EMAIL) {
		strbuf_addch(sb, '\n');
	}
	strbuf_release(&title);
}

void pp_remainder(enum cmit_fmt fmt,
		  const char **msg_p,
		  struct strbuf *sb,
		  int indent)
{
	int first = 1;
	for (;;) {
		const char *line = *msg_p;
		int linelen = get_one_line(line);
		*msg_p += linelen;

		if (!linelen)
			break;

		if (is_empty_line(line, &linelen)) {
			if (first)
				continue;
			if (fmt == CMIT_FMT_SHORT)
				break;
		}
		first = 0;

		strbuf_grow(sb, linelen + indent + 20);
		if (indent) {
			memset(sb->buf + sb->len, ' ', indent);
			strbuf_setlen(sb, sb->len + indent);
		}
		strbuf_add(sb, line, linelen);
		strbuf_addch(sb, '\n');
	}
}

char *reencode_commit_message(const struct commit *commit, const char **encoding_p)
{
	const char *encoding;

	encoding = (git_log_output_encoding
		    ? git_log_output_encoding
		    : git_commit_encoding);
	if (!encoding)
		encoding = "UTF-8";
	if (encoding_p)
		*encoding_p = encoding;
	return logmsg_reencode(commit, encoding);
}

void pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit,
			 struct strbuf *sb,
			 const struct pretty_print_context *context)
{
	unsigned long beginning_of_body;
	int indent = 4;
	const char *msg = commit->buffer;
	char *reencoded;
	const char *encoding;
	int need_8bit_cte = context->need_8bit_cte;

	if (fmt == CMIT_FMT_USERFORMAT) {
		format_commit_message(commit, user_format, sb, context);
		return;
	}

	reencoded = reencode_commit_message(commit, &encoding);
	if (reencoded) {
		msg = reencoded;
	}

	if (fmt == CMIT_FMT_ONELINE || fmt == CMIT_FMT_EMAIL)
		indent = 0;

	/*
	 * We need to check and emit Content-type: to mark it
	 * as 8-bit if we haven't done so.
	 */
	if (fmt == CMIT_FMT_EMAIL && need_8bit_cte == 0) {
		int i, ch, in_body;

		for (in_body = i = 0; (ch = msg[i]); i++) {
			if (!in_body) {
				/* author could be non 7-bit ASCII but
				 * the log may be so; skip over the
				 * header part first.
				 */
				if (ch == '\n' && msg[i+1] == '\n')
					in_body = 1;
			}
			else if (non_ascii(ch)) {
				need_8bit_cte = 1;
				break;
			}
		}
	}

	pp_header(fmt, context->abbrev, context->date_mode, encoding,
		  commit, &msg, sb);
	if (fmt != CMIT_FMT_ONELINE && !context->subject) {
		strbuf_addch(sb, '\n');
	}

	/* Skip excess blank lines at the beginning of body, if any... */
	msg = skip_empty_lines(msg);

	/* These formats treat the title line specially. */
	if (fmt == CMIT_FMT_ONELINE || fmt == CMIT_FMT_EMAIL)
		pp_title_line(fmt, &msg, sb, context->subject,
			      context->after_subject, encoding, need_8bit_cte);

	beginning_of_body = sb->len;
	if (fmt != CMIT_FMT_ONELINE)
		pp_remainder(fmt, &msg, sb, indent);
	strbuf_rtrim(sb);

	/* Make sure there is an EOLN for the non-oneline case */
	if (fmt != CMIT_FMT_ONELINE)
		strbuf_addch(sb, '\n');

	/*
	 * The caller may append additional body text in e-mail
	 * format.  Make sure we did not strip the blank line
	 * between the header and the body.
	 */
	if (fmt == CMIT_FMT_EMAIL && sb->len <= beginning_of_body)
		strbuf_addch(sb, '\n');
	free(reencoded);
}