aboutsummaryrefslogtreecommitdiff
path: root/builtin-mailinfo.c
blob: b99a5b6f9679061d75e9c48e2fa5877e27920dc3 (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
/*
 * Another stupid program, this one parsing the headers of an
 * email to figure out authorship and subject
 */
#include "cache.h"
#include "builtin.h"
#include "utf8.h"
#include "strbuf.h"

static FILE *cmitmsg, *patchfile, *fin, *fout;

static int keep_subject;
static const char *metainfo_charset;
static struct strbuf line = STRBUF_INIT;
static struct strbuf name = STRBUF_INIT;
static struct strbuf email = STRBUF_INIT;

static enum  {
	TE_DONTCARE, TE_QP, TE_BASE64,
} transfer_encoding;
static enum  {
	TYPE_TEXT, TYPE_OTHER,
} message_type;

static struct strbuf charset = STRBUF_INIT;
static int patch_lines;
static struct strbuf **p_hdr_data, **s_hdr_data;

#define MAX_HDR_PARSED 10
#define MAX_BOUNDARIES 5

static void get_sane_name(struct strbuf *out, struct strbuf *name, struct strbuf *email)
{
	struct strbuf *src = name;
	if (name->len < 3 || 60 < name->len || strchr(name->buf, '@') ||
		strchr(name->buf, '<') || strchr(name->buf, '>'))
		src = email;
	else if (name == out)
		return;
	strbuf_reset(out);
	strbuf_addbuf(out, src);
}

static void parse_bogus_from(const struct strbuf *line)
{
	/* John Doe <johndoe> */

	char *bra, *ket;
	/* This is fallback, so do not bother if we already have an
	 * e-mail address.
	 */
	if (email.len)
		return;

	bra = strchr(line->buf, '<');
	if (!bra)
		return;
	ket = strchr(bra, '>');
	if (!ket)
		return;

	strbuf_reset(&email);
	strbuf_add(&email, bra + 1, ket - bra - 1);

	strbuf_reset(&name);
	strbuf_add(&name, line->buf, bra - line->buf);
	strbuf_trim(&name);
	get_sane_name(&name, &name, &email);
}

static void handle_from(const struct strbuf *from)
{
	char *at;
	size_t el;
	struct strbuf f;

	strbuf_init(&f, from->len);
	strbuf_addbuf(&f, from);

	at = strchr(f.buf, '@');
	if (!at) {
		parse_bogus_from(from);
		return;
	}

	/*
	 * If we already have one email, don't take any confusing lines
	 */
	if (email.len && strchr(at + 1, '@')) {
		strbuf_release(&f);
		return;
	}

	/* Pick up the string around '@', possibly delimited with <>
	 * pair; that is the email part.
	 */
	while (at > f.buf) {
		char c = at[-1];
		if (isspace(c))
			break;
		if (c == '<') {
			at[-1] = ' ';
			break;
		}
		at--;
	}
	el = strcspn(at, " \n\t\r\v\f>");
	strbuf_reset(&email);
	strbuf_add(&email, at, el);
	strbuf_remove(&f, at - f.buf, el + 1);

	/* The remainder is name.  It could be "John Doe <john.doe@xz>"
	 * or "john.doe@xz (John Doe)", but we have removed the
	 * email part, so trim from both ends, possibly removing
	 * the () pair at the end.
	 */
	strbuf_trim(&f);
	if (f.buf[0] == '(')
		strbuf_remove(&name, 0, 1);
	if (f.len && f.buf[f.len - 1] == ')')
		strbuf_setlen(&f, f.len - 1);

	get_sane_name(&name, &f, &email);
	strbuf_release(&f);
}

static void handle_header(struct strbuf **out, const struct strbuf *line)
{
	if (!*out) {
		*out = xmalloc(sizeof(struct strbuf));
		strbuf_init(*out, line->len);
	} else
		strbuf_reset(*out);

	strbuf_addbuf(*out, line);
}

/* NOTE NOTE NOTE.  We do not claim we do full MIME.  We just attempt
 * to have enough heuristics to grok MIME encoded patches often found
 * on our mailing lists.  For example, we do not even treat header lines
 * case insensitively.
 */

static int slurp_attr(const char *line, const char *name, struct strbuf *attr)
{
	const char *ends, *ap = strcasestr(line, name);
	size_t sz;

	if (!ap) {
		strbuf_setlen(attr, 0);
		return 0;
	}
	ap += strlen(name);
	if (*ap == '"') {
		ap++;
		ends = "\"";
	}
	else
		ends = "; \t";
	sz = strcspn(ap, ends);
	strbuf_add(attr, ap, sz);
	return 1;
}

static struct strbuf *content[MAX_BOUNDARIES];

static struct strbuf **content_top = content;

static void handle_content_type(struct strbuf *line)
{
	struct strbuf *boundary = xmalloc(sizeof(struct strbuf));
	strbuf_init(boundary, line->len);

	if (!strcasestr(line->buf, "text/"))
		 message_type = TYPE_OTHER;
	if (slurp_attr(line->buf, "boundary=", boundary)) {
		strbuf_insert(boundary, 0, "--", 2);
		if (content_top++ >= &content[MAX_BOUNDARIES]) {
			fprintf(stderr, "Too many boundaries to handle\n");
			exit(1);
		}
		*content_top = boundary;
		boundary = NULL;
	}
	if (slurp_attr(line->buf, "charset=", &charset))
		strbuf_tolower(&charset);

	if (boundary) {
		strbuf_release(boundary);
		free(boundary);
	}
}

static void handle_content_transfer_encoding(const struct strbuf *line)
{
	if (strcasestr(line->buf, "base64"))
		transfer_encoding = TE_BASE64;
	else if (strcasestr(line->buf, "quoted-printable"))
		transfer_encoding = TE_QP;
	else
		transfer_encoding = TE_DONTCARE;
}

static int is_multipart_boundary(const struct strbuf *line)
{
	return !strbuf_cmp(line, *content_top);
}

static void cleanup_subject(struct strbuf *subject)
{
	char *pos;
	size_t remove;
	while (subject->len) {
		switch (*subject->buf) {
		case 'r': case 'R':
			if (subject->len <= 3)
				break;
			if (!memcmp(subject->buf + 1, "e:", 2)) {
				strbuf_remove(subject, 0, 3);
				continue;
			}
			break;
		case ' ': case '\t': case ':':
			strbuf_remove(subject, 0, 1);
			continue;
		case '[':
			if ((pos = strchr(subject->buf, ']'))) {
				remove = pos - subject->buf;
				if (remove <= (subject->len - remove) * 2) {
					strbuf_remove(subject, 0, remove + 1);
					continue;
				}
			} else
				strbuf_remove(subject, 0, 1);
			break;
		}
		strbuf_trim(subject);
		return;
	}
}

static void cleanup_space(struct strbuf *sb)
{
	size_t pos, cnt;
	for (pos = 0; pos < sb->len; pos++) {
		if (isspace(sb->buf[pos])) {
			sb->buf[pos] = ' ';
			for (cnt = 0; isspace(sb->buf[pos + cnt + 1]); cnt++);
			strbuf_remove(sb, pos + 1, cnt);
		}
	}
}

static void decode_header(struct strbuf *line);
static const char *header[MAX_HDR_PARSED] = {
	"From","Subject","Date",
};

static inline int cmp_header(const struct strbuf *line, const char *hdr)
{
	int len = strlen(hdr);
	return !strncasecmp(line->buf, hdr, len) && line->len > len &&
			line->buf[len] == ':' && isspace(line->buf[len + 1]);
}

static int check_header(const struct strbuf *line,
				struct strbuf *hdr_data[], int overwrite)
{
	int i, ret = 0, len;
	struct strbuf sb = STRBUF_INIT;
	/* search for the interesting parts */
	for (i = 0; header[i]; i++) {
		int len = strlen(header[i]);
		if ((!hdr_data[i] || overwrite) && cmp_header(line, header[i])) {
			/* Unwrap inline B and Q encoding, and optionally
			 * normalize the meta information to utf8.
			 */
			strbuf_add(&sb, line->buf + len + 2, line->len - len - 2);
			decode_header(&sb);
			handle_header(&hdr_data[i], &sb);
			ret = 1;
			goto check_header_out;
		}
	}

	/* Content stuff */
	if (cmp_header(line, "Content-Type")) {
		len = strlen("Content-Type: ");
		strbuf_add(&sb, line->buf + len, line->len - len);
		decode_header(&sb);
		strbuf_insert(&sb, 0, "Content-Type: ", len);
		handle_content_type(&sb);
		ret = 1;
		goto check_header_out;
	}
	if (cmp_header(line, "Content-Transfer-Encoding")) {
		len = strlen("Content-Transfer-Encoding: ");
		strbuf_add(&sb, line->buf + len, line->len - len);
		decode_header(&sb);
		handle_content_transfer_encoding(&sb);
		ret = 1;
		goto check_header_out;
	}

	/* for inbody stuff */
	if (!prefixcmp(line->buf, ">From") && isspace(line->buf[5])) {
		ret = 1; /* Should this return 0? */
		goto check_header_out;
	}
	if (!prefixcmp(line->buf, "[PATCH]") && isspace(line->buf[7])) {
		for (i = 0; header[i]; i++) {
			if (!memcmp("Subject", header[i], 7)) {
				handle_header(&hdr_data[i], line);
				ret = 1;
				goto check_header_out;
			}
		}
	}

check_header_out:
	strbuf_release(&sb);
	return ret;
}

static int is_rfc2822_header(const struct strbuf *line)
{
	/*
	 * The section that defines the loosest possible
	 * field name is "3.6.8 Optional fields".
	 *
	 * optional-field = field-name ":" unstructured CRLF
	 * field-name = 1*ftext
	 * ftext = %d33-57 / %59-126
	 */
	int ch;
	char *cp = line->buf;

	/* Count mbox From headers as headers */
	if (!prefixcmp(cp, "From ") || !prefixcmp(cp, ">From "))
		return 1;

	while ((ch = *cp++)) {
		if (ch == ':')
			return 1;
		if ((33 <= ch && ch <= 57) ||
		    (59 <= ch && ch <= 126))
			continue;
		break;
	}
	return 0;
}

static int read_one_header_line(struct strbuf *line, FILE *in)
{
	/* Get the first part of the line. */
	if (strbuf_getline(line, in, '\n'))
		return 0;

	/*
	 * Is it an empty line or not a valid rfc2822 header?
	 * If so, stop here, and return false ("not a header")
	 */
	strbuf_rtrim(line);
	if (!line->len || !is_rfc2822_header(line)) {
		/* Re-add the newline */
		strbuf_addch(line, '\n');
		return 0;
	}

	/*
	 * Now we need to eat all the continuation lines..
	 * Yuck, 2822 header "folding"
	 */
	for (;;) {
		int peek;
		struct strbuf continuation = STRBUF_INIT;

		peek = fgetc(in); ungetc(peek, in);
		if (peek != ' ' && peek != '\t')
			break;
		if (strbuf_getline(&continuation, in, '\n'))
			break;
		continuation.buf[0] = '\n';
		strbuf_rtrim(&continuation);
		strbuf_addbuf(line, &continuation);
	}

	return 1;
}

static struct strbuf *decode_q_segment(const struct strbuf *q_seg, int rfc2047)
{
	const char *in = q_seg->buf;
	int c;
	struct strbuf *out = xmalloc(sizeof(struct strbuf));
	strbuf_init(out, q_seg->len);

	while ((c = *in++) != 0) {
		if (c == '=') {
			int d = *in++;
			if (d == '\n' || !d)
				break; /* drop trailing newline */
			strbuf_addch(out, (hexval(d) << 4) | hexval(*in++));
			continue;
		}
		if (rfc2047 && c == '_') /* rfc2047 4.2 (2) */
			c = 0x20;
		strbuf_addch(out, c);
	}
	return out;
}

static struct strbuf *decode_b_segment(const struct strbuf *b_seg)
{
	/* Decode in..ep, possibly in-place to ot */
	int c, pos = 0, acc = 0;
	const char *in = b_seg->buf;
	struct strbuf *out = xmalloc(sizeof(struct strbuf));
	strbuf_init(out, b_seg->len);

	while ((c = *in++) != 0) {
		if (c == '+')
			c = 62;
		else if (c == '/')
			c = 63;
		else if ('A' <= c && c <= 'Z')
			c -= 'A';
		else if ('a' <= c && c <= 'z')
			c -= 'a' - 26;
		else if ('0' <= c && c <= '9')
			c -= '0' - 52;
		else if (c == '=') {
			/* padding is almost like (c == 0), except we do
			 * not output NUL resulting only from it;
			 * for now we just trust the data.
			 */
			c = 0;
		}
		else
			continue; /* garbage */
		switch (pos++) {
		case 0:
			acc = (c << 2);
			break;
		case 1:
			strbuf_addch(out, (acc | (c >> 4)));
			acc = (c & 15) << 4;
			break;
		case 2:
			strbuf_addch(out, (acc | (c >> 2)));
			acc = (c & 3) << 6;
			break;
		case 3:
			strbuf_addch(out, (acc | c));
			acc = pos = 0;
			break;
		}
	}
	return out;
}

/*
 * When there is no known charset, guess.
 *
 * Right now we assume that if the target is UTF-8 (the default),
 * and it already looks like UTF-8 (which includes US-ASCII as its
 * subset, of course) then that is what it is and there is nothing
 * to do.
 *
 * Otherwise, we default to assuming it is Latin1 for historical
 * reasons.
 */
static const char *guess_charset(const struct strbuf *line, const char *target_charset)
{
	if (is_encoding_utf8(target_charset)) {
		if (is_utf8(line->buf))
			return NULL;
	}
	return "latin1";
}

static void convert_to_utf8(struct strbuf *line, const char *charset)
{
	char *out;

	if (!charset || !*charset) {
		charset = guess_charset(line, metainfo_charset);
		if (!charset)
			return;
	}

	if (!strcmp(metainfo_charset, charset))
		return;
	out = reencode_string(line->buf, metainfo_charset, charset);
	if (!out)
		die("cannot convert from %s to %s\n",
		    charset, metainfo_charset);
	strbuf_attach(line, out, strlen(out), strlen(out));
}

static int decode_header_bq(struct strbuf *it)
{
	char *in, *ep, *cp;
	struct strbuf outbuf = STRBUF_INIT, *dec;
	struct strbuf charset_q = STRBUF_INIT, piecebuf = STRBUF_INIT;
	int rfc2047 = 0;

	in = it->buf;
	while (in - it->buf <= it->len && (ep = strstr(in, "=?")) != NULL) {
		int encoding;
		strbuf_reset(&charset_q);
		strbuf_reset(&piecebuf);
		rfc2047 = 1;

		if (in != ep) {
			strbuf_add(&outbuf, in, ep - in);
			in = ep;
		}
		/* E.g.
		 * ep : "=?iso-2022-jp?B?GyR...?= foo"
		 * ep : "=?ISO-8859-1?Q?Foo=FCbar?= baz"
		 */
		ep += 2;

		if (ep - it->buf >= it->len || !(cp = strchr(ep, '?')))
			goto decode_header_bq_out;

		if (cp + 3 - it->buf > it->len)
			goto decode_header_bq_out;
		strbuf_add(&charset_q, ep, cp - ep);
		strbuf_tolower(&charset_q);

		encoding = cp[1];
		if (!encoding || cp[2] != '?')
			goto decode_header_bq_out;
		ep = strstr(cp + 3, "?=");
		if (!ep)
			goto decode_header_bq_out;
		strbuf_add(&piecebuf, cp + 3, ep - cp - 3);
		switch (tolower(encoding)) {
		default:
			goto decode_header_bq_out;
		case 'b':
			dec = decode_b_segment(&piecebuf);
			break;
		case 'q':
			dec = decode_q_segment(&piecebuf, 1);
			break;
		}
		if (metainfo_charset)
			convert_to_utf8(dec, charset_q.buf);

		strbuf_addbuf(&outbuf, dec);
		strbuf_release(dec);
		free(dec);
		in = ep + 2;
	}
	strbuf_addstr(&outbuf, in);
	strbuf_reset(it);
	strbuf_addbuf(it, &outbuf);
decode_header_bq_out:
	strbuf_release(&outbuf);
	strbuf_release(&charset_q);
	strbuf_release(&piecebuf);
	return rfc2047;
}

static void decode_header(struct strbuf *it)
{
	if (decode_header_bq(it))
		return;
	/* otherwise "it" is a straight copy of the input.
	 * This can be binary guck but there is no charset specified.
	 */
	if (metainfo_charset)
		convert_to_utf8(it, "");
}

static void decode_transfer_encoding(struct strbuf *line)
{
	struct strbuf *ret;

	switch (transfer_encoding) {
	case TE_QP:
		ret = decode_q_segment(line, 0);
		break;
	case TE_BASE64:
		ret = decode_b_segment(line);
		break;
	case TE_DONTCARE:
	default:
		return;
	}
	strbuf_reset(line);
	strbuf_addbuf(line, ret);
	strbuf_release(ret);
	free(ret);
}

static void handle_filter(struct strbuf *line);

static int find_boundary(void)
{
	while (!strbuf_getline(&line, fin, '\n')) {
		if (is_multipart_boundary(&line))
			return 1;
	}
	return 0;
}

static int handle_boundary(void)
{
	struct strbuf newline = STRBUF_INIT;

	strbuf_addch(&newline, '\n');
again:
	if (line.len >= (*content_top)->len + 2 &&
	    !memcmp(line.buf + (*content_top)->len, "--", 2)) {
		/* we hit an end boundary */
		/* pop the current boundary off the stack */
		strbuf_release(*content_top);
		free(*content_top);
		*content_top = NULL;

		/* technically won't happen as is_multipart_boundary()
		   will fail first.  But just in case..
		 */
		if (content_top-- < content) {
			fprintf(stderr, "Detected mismatched boundaries, "
					"can't recover\n");
			exit(1);
		}
		handle_filter(&newline);
		strbuf_release(&newline);

		/* skip to the next boundary */
		if (!find_boundary())
			return 0;
		goto again;
	}

	/* set some defaults */
	transfer_encoding = TE_DONTCARE;
	strbuf_reset(&charset);
	message_type = TYPE_TEXT;

	/* slurp in this section's info */
	while (read_one_header_line(&line, fin))
		check_header(&line, p_hdr_data, 0);

	strbuf_release(&newline);
	/* eat the blank line after section info */
	return (strbuf_getline(&line, fin, '\n') == 0);
}

static inline int patchbreak(const struct strbuf *line)
{
	size_t i;

	/* Beginning of a "diff -" header? */
	if (!prefixcmp(line->buf, "diff -"))
		return 1;

	/* CVS "Index: " line? */
	if (!prefixcmp(line->buf, "Index: "))
		return 1;

	/*
	 * "--- <filename>" starts patches without headers
	 * "---<sp>*" is a manual separator
	 */
	if (line->len < 4)
		return 0;

	if (!prefixcmp(line->buf, "---")) {
		/* space followed by a filename? */
		if (line->buf[3] == ' ' && !isspace(line->buf[4]))
			return 1;
		/* Just whitespace? */
		for (i = 3; i < line->len; i++) {
			unsigned char c = line->buf[i];
			if (c == '\n')
				return 1;
			if (!isspace(c))
				break;
		}
		return 0;
	}
	return 0;
}

static int handle_commit_msg(struct strbuf *line)
{
	static int still_looking = 1;

	if (!cmitmsg)
		return 0;

	if (still_looking) {
		strbuf_ltrim(line);
		if (!line->len)
			return 0;
		if ((still_looking = check_header(line, s_hdr_data, 0)) != 0)
			return 0;
	}

	/* normalize the log message to UTF-8. */
	if (metainfo_charset)
		convert_to_utf8(line, charset.buf);

	if (patchbreak(line)) {
		fclose(cmitmsg);
		cmitmsg = NULL;
		return 1;
	}

	fputs(line->buf, cmitmsg);
	return 0;
}

static void handle_patch(const struct strbuf *line)
{
	fwrite(line->buf, 1, line->len, patchfile);
	patch_lines++;
}

static void handle_filter(struct strbuf *line)
{
	static int filter = 0;

	/* filter tells us which part we left off on */
	switch (filter) {
	case 0:
		if (!handle_commit_msg(line))
			break;
		filter++;
	case 1:
		handle_patch(line);
		break;
	}
}

static void handle_body(void)
{
	int len = 0;
	struct strbuf prev = STRBUF_INIT;

	/* Skip up to the first boundary */
	if (*content_top) {
		if (!find_boundary())
			goto handle_body_out;
	}

	do {
		strbuf_setlen(&line, line.len + len);

		/* process any boundary lines */
		if (*content_top && is_multipart_boundary(&line)) {
			/* flush any leftover */
			if (line.len)
				handle_filter(&line);

			if (!handle_boundary())
				goto handle_body_out;
		}

		/* Unwrap transfer encoding */
		decode_transfer_encoding(&line);

		switch (transfer_encoding) {
		case TE_BASE64:
		case TE_QP:
		{
			struct strbuf **lines, **it, *sb;

			/* Prepend any previous partial lines */
			strbuf_insert(&line, 0, prev.buf, prev.len);
			strbuf_reset(&prev);

			/* binary data most likely doesn't have newlines */
			if (message_type != TYPE_TEXT) {
				handle_filter(&line);
				break;
			}
			/*
			 * This is a decoded line that may contain
			 * multiple new lines.  Pass only one chunk
			 * at a time to handle_filter()
			 */
			lines = strbuf_split(&line, '\n');
			for (it = lines; (sb = *it); it++) {
				if (*(it + 1) == NULL) /* The last line */
					if (sb->buf[sb->len - 1] != '\n') {
						/* Partial line, save it for later. */
						strbuf_addbuf(&prev, sb);
						break;
					}
				handle_filter(sb);
			}
			/*
			 * The partial chunk is saved in "prev" and will be
			 * appended by the next iteration of read_line_with_nul().
			 */
			strbuf_list_free(lines);
			break;
		}
		default:
			handle_filter(&line);
		}

		strbuf_reset(&line);
		if (strbuf_avail(&line) < 100)
			strbuf_grow(&line, 100);
	} while ((len = read_line_with_nul(line.buf, strbuf_avail(&line), fin)));

handle_body_out:
	strbuf_release(&prev);
}

static void output_header_lines(FILE *fout, const char *hdr, const struct strbuf *data)
{
	const char *sp = data->buf;
	while (1) {
		char *ep = strchr(sp, '\n');
		int len;
		if (!ep)
			len = strlen(sp);
		else
			len = ep - sp;
		fprintf(fout, "%s: %.*s\n", hdr, len, sp);
		if (!ep)
			break;
		sp = ep + 1;
	}
}

static void handle_info(void)
{
	struct strbuf *hdr;
	int i;

	for (i = 0; header[i]; i++) {
		/* only print inbody headers if we output a patch file */
		if (patch_lines && s_hdr_data[i])
			hdr = s_hdr_data[i];
		else if (p_hdr_data[i])
			hdr = p_hdr_data[i];
		else
			continue;

		if (!memcmp(header[i], "Subject", 7)) {
			if (!keep_subject) {
				cleanup_subject(hdr);
				cleanup_space(hdr);
			}
			output_header_lines(fout, "Subject", hdr);
		} else if (!memcmp(header[i], "From", 4)) {
			handle_from(hdr);
			fprintf(fout, "Author: %s\n", name.buf);
			fprintf(fout, "Email: %s\n", email.buf);
		} else {
			cleanup_space(hdr);
			fprintf(fout, "%s: %s\n", header[i], hdr->buf);
		}
	}
	fprintf(fout, "\n");
}

static int mailinfo(FILE *in, FILE *out, int ks, const char *encoding,
		    const char *msg, const char *patch)
{
	int peek;
	keep_subject = ks;
	metainfo_charset = encoding;
	fin = in;
	fout = out;

	cmitmsg = fopen(msg, "w");
	if (!cmitmsg) {
		perror(msg);
		return -1;
	}
	patchfile = fopen(patch, "w");
	if (!patchfile) {
		perror(patch);
		fclose(cmitmsg);
		return -1;
	}

	p_hdr_data = xcalloc(MAX_HDR_PARSED, sizeof(*p_hdr_data));
	s_hdr_data = xcalloc(MAX_HDR_PARSED, sizeof(*s_hdr_data));

	do {
		peek = fgetc(in);
	} while (isspace(peek));
	ungetc(peek, in);

	/* process the email header */
	while (read_one_header_line(&line, fin))
		check_header(&line, p_hdr_data, 1);

	handle_body();
	handle_info();

	return 0;
}

static const char mailinfo_usage[] =
	"git mailinfo [-k] [-u | --encoding=<encoding> | -n] msg patch <mail >info";

int cmd_mailinfo(int argc, const char **argv, const char *prefix)
{
	const char *def_charset;

	/* NEEDSWORK: might want to do the optional .git/ directory
	 * discovery
	 */
	git_config(git_default_config, NULL);

	def_charset = (git_commit_encoding ? git_commit_encoding : "utf-8");
	metainfo_charset = def_charset;

	while (1 < argc && argv[1][0] == '-') {
		if (!strcmp(argv[1], "-k"))
			keep_subject = 1;
		else if (!strcmp(argv[1], "-u"))
			metainfo_charset = def_charset;
		else if (!strcmp(argv[1], "-n"))
			metainfo_charset = NULL;
		else if (!prefixcmp(argv[1], "--encoding="))
			metainfo_charset = argv[1] + 11;
		else
			usage(mailinfo_usage);
		argc--; argv++;
	}

	if (argc != 3)
		usage(mailinfo_usage);

	return !!mailinfo(stdin, stdout, keep_subject, metainfo_charset, argv[1], argv[2]);
}