summaryrefslogtreecommitdiff
path: root/convert.c
blob: 21908b10398492c0b07f705ed3b1ce7a06ac6b44 (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
#include "cache.h"
#include "attr.h"
#include "run-command.h"
 
/*
 * convert.c - convert a file when checking it out and checking it in.
 *
 * This should use the pathname to decide on whether it wants to do some
 * more interesting conversions (automatic gzip/unzip, general format
 * conversions etc etc), but by default it just does automatic CRLF<->LF
 * translation when the "auto_crlf" option is set.
 */
 
#define CRLF_GUESS	(-1)
#define CRLF_BINARY	0
#define CRLF_TEXT	1
#define CRLF_INPUT	2
 
struct text_stat {
	/* CR, LF and CRLF counts */
	unsigned cr, lf, crlf;
 
	/* These are just approximations! */
	unsigned printable, nonprintable;
};
 
static void gather_stats(const char *buf, unsigned long size, struct text_stat *stats)
{
	unsigned long i;
 
	memset(stats, 0, sizeof(*stats));
 
	for (i = 0; i < size; i++) {
		unsigned char c = buf[i];
		if (c == '\r') {
			stats->cr++;
			if (i+1 < size && buf[i+1] == '\n')
				stats->crlf++;
			continue;
		}
		if (c == '\n') {
			stats->lf++;
			continue;
		}
		if (c == 127)
			/* DEL */
			stats->nonprintable++;
		else if (c < 32) {
			switch (c) {
				/* BS, HT, ESC and FF */
			case '\b': case '\t': case '\033': case '\014':
				stats->printable++;
				break;
			default:
				stats->nonprintable++;
			}
		}
		else
			stats->printable++;
	}
}
 
/*
 * The same heuristics as diff.c::mmfile_is_binary()
 */
static int is_binary(unsigned long size, struct text_stat *stats)
{
 
	if ((stats->printable >> 7) < stats->nonprintable)
		return 1;
	/*
	 * Other heuristics? Average line length might be relevant,
	 * as might LF vs CR vs CRLF counts..
	 *
	 * NOTE! It might be normal to have a low ratio of CRLF to LF
	 * (somebody starts with a LF-only file and edits it with an editor
	 * that adds CRLF only to lines that are added..). But do  we
	 * want to support CR-only? Probably not.
	 */
	return 0;
}
 
static char *crlf_to_git(const char *path, const char *src, unsigned long *sizep, int action)
{
	char *buffer, *dst;
	unsigned long size, nsize;
	struct text_stat stats;
 
	if ((action == CRLF_BINARY) || !auto_crlf)
		return NULL;
 
	size = *sizep;
	if (!size)
		return NULL;
 
	gather_stats(src, size, &stats);
 
	/* No CR? Nothing to convert, regardless. */
	if (!stats.cr)
		return NULL;
 
	if (action == CRLF_GUESS) {
		/*
		 * We're currently not going to even try to convert stuff
		 * that has bare CR characters. Does anybody do that crazy
		 * stuff?
		 */
		if (stats.cr != stats.crlf)
			return NULL;
 
		/*
		 * And add some heuristics for binary vs text, of course...
		 */
		if (is_binary(size, &stats))
			return NULL;
	}
 
	/*
	 * Ok, allocate a new buffer, fill it in, and return it
	 * to let the caller know that we switched buffers.
	 */
	nsize = size - stats.crlf;
	buffer = xmalloc(nsize);
	*sizep = nsize;
 
	dst = buffer;
	if (action == CRLF_GUESS) {
		/*
		 * If we guessed, we already know we rejected a file with
		 * lone CR, and we can strip a CR without looking at what
		 * follow it.
		 */
		do {
			unsigned char c = *src++;
			if (c != '\r')
				*dst++ = c;
		} while (--size);
	} else {
		do {
			unsigned char c = *src++;
			if (! (c == '\r' && (1 < size && *src == '\n')))
				*dst++ = c;
		} while (--size);
	}
 
	return buffer;
}
 
static char *crlf_to_worktree(const char *path, const char *src, unsigned long *sizep, int action)
{
	char *buffer, *dst;
	unsigned long size, nsize;
	struct text_stat stats;
	unsigned char last;
 
	if ((action == CRLF_BINARY) || (action == CRLF_INPUT) ||
	    auto_crlf <= 0)
		return NULL;
 
	size = *sizep;
	if (!size)
		return NULL;
 
	gather_stats(src, size, &stats);
 
	/* No LF? Nothing to convert, regardless. */
	if (!stats.lf)
		return NULL;
 
	/* Was it already in CRLF format? */
	if (stats.lf == stats.crlf)
		return NULL;
 
	if (action == CRLF_GUESS) {
		/* If we have any bare CR characters, we're not going to touch it */
		if (stats.cr != stats.crlf)
			return NULL;
 
		if (is_binary(size, &stats))
			return NULL;
	}
 
	/*
	 * Ok, allocate a new buffer, fill it in, and return it
	 * to let the caller know that we switched buffers.
	 */
	nsize = size + stats.lf - stats.crlf;
	buffer = xmalloc(nsize);
	*sizep = nsize;
	last = 0;
 
	dst = buffer;
	do {
		unsigned char c = *src++;
		if (c == '\n' && last != '\r')
			*dst++ = '\r';
		*dst++ = c;
		last = c;
	} while (--size);
 
	return buffer;
}
 
static int filter_buffer(const char *path, const char *src,
			 unsigned long size, const char *cmd)
{
	/*
	 * Spawn cmd and feed the buffer contents through its stdin.
	 */
	struct child_process child_process;
	int pipe_feed[2];
	int write_err, status;
 
	memset(&child_process, 0, sizeof(child_process));
 
	if (pipe(pipe_feed) < 0) {
		error("cannot create pipe to run external filter %s", cmd);
		return 1;
	}
 
	child_process.pid = fork();
	if (child_process.pid < 0) {
		error("cannot fork to run external filter %s", cmd);
		close(pipe_feed[0]);
		close(pipe_feed[1]);
		return 1;
	}
	if (!child_process.pid) {
		dup2(pipe_feed[0], 0);
		close(pipe_feed[0]);
		close(pipe_feed[1]);
		execlp("sh", "sh", "-c", cmd, NULL);
		return 1;
	}
	close(pipe_feed[0]);
 
	write_err = (write_in_full(pipe_feed[1], src, size) < 0);
	if (close(pipe_feed[1]))
		write_err = 1;
	if (write_err)
		error("cannot feed the input to external filter %s", cmd);
 
	status = finish_command(&child_process);
	if (status)
		error("external filter %s failed %d", cmd, -status);
	return (write_err || status);
}
 
static char *apply_filter(const char *path, const char *src,
			  unsigned long *sizep, const char *cmd)
{
	/*
	 * Create a pipeline to have the command filter the buffer's
	 * contents.
	 *
	 * (child --> cmd) --> us
	 */
	const int SLOP = 4096;
	int pipe_feed[2];
	int status;
	char *dst;
	unsigned long dstsize, dstalloc;
	struct child_process child_process;
 
	if (!cmd)
		return NULL;
 
	memset(&child_process, 0, sizeof(child_process));
 
	if (pipe(pipe_feed) < 0) {
		error("cannot create pipe to run external filter %s", cmd);
		return NULL;
	}
 
	fflush(NULL);
	child_process.pid = fork();
	if (child_process.pid < 0) {
		error("cannot fork to run external filter %s", cmd);
		close(pipe_feed[0]);
		close(pipe_feed[1]);
		return NULL;
	}
	if (!child_process.pid) {
		dup2(pipe_feed[1], 1);
		close(pipe_feed[0]);
		close(pipe_feed[1]);
		exit(filter_buffer(path, src, *sizep, cmd));
	}
	close(pipe_feed[1]);
 
	dstalloc = *sizep;
	dst = xmalloc(dstalloc);
	dstsize = 0;
 
	while (1) {
		ssize_t numread = xread(pipe_feed[0], dst + dstsize,
					dstalloc - dstsize);
 
		if (numread <= 0) {
			if (!numread)
				break;
			error("read from external filter %s failed", cmd);
			free(dst);
			dst = NULL;
			break;
		}
		dstsize += numread;
		if (dstalloc <= dstsize + SLOP) {
			dstalloc = dstsize + SLOP;
			dst = xrealloc(dst, dstalloc);
		}
	}
	if (close(pipe_feed[0])) {
		error("read from external filter %s failed", cmd);
		free(dst);
		dst = NULL;
	}
 
	status = finish_command(&child_process);
	if (status) {
		error("external filter %s failed %d", cmd, -status);
		free(dst);
		dst = NULL;
	}
 
	if (dst)
		*sizep = dstsize;
	return dst;
}
 
static struct convert_driver {
	const char *name;
	struct convert_driver *next;
	char *smudge;
	char *clean;
} *user_convert, **user_convert_tail;
 
static int read_convert_config(const char *var, const char *value)
{
	const char *ep, *name;
	int namelen;
	struct convert_driver *drv;
 
	/*
	 * External conversion drivers are configured using
	 * "filter.<name>.variable".
	 */
	if (prefixcmp(var, "filter.") || (ep = strrchr(var, '.')) == var + 6)
		return 0;
	name = var + 7;
	namelen = ep - name;
	for (drv = user_convert; drv; drv = drv->next)
		if (!strncmp(drv->name, name, namelen) && !drv->name[namelen])
			break;
	if (!drv) {
		char *namebuf;
		drv = xcalloc(1, sizeof(struct convert_driver));
		namebuf = xmalloc(namelen + 1);
		memcpy(namebuf, name, namelen);
		namebuf[namelen] = 0;
		drv->name = namebuf;
		drv->next = NULL;
		*user_convert_tail = drv;
		user_convert_tail = &(drv->next);
	}
 
	ep++;
 
	/*
	 * filter.<name>.smudge and filter.<name>.clean specifies
	 * the command line:
	 *
	 *	command-line
	 *
	 * The command-line will not be interpolated in any way.
	 */
 
	if (!strcmp("smudge", ep)) {
		if (!value)
			return error("%s: lacks value", var);
		drv->smudge = strdup(value);
		return 0;
	}
 
	if (!strcmp("clean", ep)) {
		if (!value)
			return error("%s: lacks value", var);
		drv->clean = strdup(value);
		return 0;
	}
	return 0;
}
 
static void setup_convert_check(struct git_attr_check *check)
{
	static struct git_attr *attr_crlf;
	static struct git_attr *attr_ident;
	static struct git_attr *attr_filter;
 
	if (!attr_crlf) {
		attr_crlf = git_attr("crlf", 4);
		attr_ident = git_attr("ident", 5);
		attr_filter = git_attr("filter", 6);
		user_convert_tail = &user_convert;
		git_config(read_convert_config);
	}
	check[0].attr = attr_crlf;
	check[1].attr = attr_ident;
	check[2].attr = attr_filter;
}
 
static int count_ident(const char *cp, unsigned long size)
{
	/*
	 * "$Id: 0000000000000000000000000000000000000000 $" <=> "$Id$"
	 */
	int cnt = 0;
	char ch;
 
	while (size) {
		ch = *cp++;
		size--;
		if (ch != '$')
			continue;
		if (size < 3)
			break;
		if (memcmp("Id", cp, 2))
			continue;
		ch = cp[2];
		cp += 3;
		size -= 3;
		if (ch == '$')
			cnt++; /* $Id$ */
		if (ch != ':')
			continue;
 
		/*
		 * "$Id: ... "; scan up to the closing dollar sign and discard.
		 */
		while (size) {
			ch = *cp++;
			size--;
			if (ch == '$') {
				cnt++;
				break;
			}
		}
	}
	return cnt;
}
 
static char *ident_to_git(const char *path, const char *src, unsigned long *sizep, int ident)
{
	int cnt;
	unsigned long size;
	char *dst, *buf;
 
	if (!ident)
		return NULL;
	size = *sizep;
	cnt = count_ident(src, size);
	if (!cnt)
		return NULL;
	buf = xmalloc(size);
 
	for (dst = buf; size; size--) {
		char ch = *src++;
		*dst++ = ch;
		if ((ch == '$') && (3 <= size) &&
		    !memcmp("Id:", src, 3)) {
			unsigned long rem = size - 3;
			const char *cp = src + 3;
			do {
				ch = *cp++;
				if (ch == '$')
					break;
				rem--;
			} while (rem);
			if (!rem)
				continue;
			memcpy(dst, "Id$", 3);
			dst += 3;
			size -= (cp - src);
			src = cp;
		}
	}
 
	*sizep = dst - buf;
	return buf;
}
 
static char *ident_to_worktree(const char *path, const char *src, unsigned long *sizep, int ident)
{
	int cnt;
	unsigned long size;
	char *dst, *buf;
	unsigned char sha1[20];
 
	if (!ident)
		return NULL;
 
	size = *sizep;
	cnt = count_ident(src, size);
	if (!cnt)
		return NULL;
 
	hash_sha1_file(src, size, "blob", sha1);
	buf = xmalloc(size + cnt * 43);
 
	for (dst = buf; size; size--) {
		const char *cp;
		/* Fetch next source character, move the pointer on */
		char ch = *src++;
		/* Copy the current character to the destination */
		*dst++ = ch;
		/* If the current character is "$" or there are less than three
		 * remaining bytes or the two bytes following this one are not
		 * "Id", then simply read the next character */
		if ((ch != '$') || (size < 3) || memcmp("Id", src, 2))
			continue;
		/*
		 * Here when
		 *  - There are more than 2 bytes remaining
		 *  - The current three bytes are "$Id"
		 * with
		 *  - ch == "$"
		 *  - src[0] == "I"
		 */
 
		/*
		 * It's possible that an expanded Id has crept its way into the
		 * repository, we cope with that by stripping the expansion out
		 */
		if (src[2] == ':') {
			/* Expanded keywords have "$Id:" at the front */
 
			/* discard up to but not including the closing $ */
			unsigned long rem = size - 3;
			/* Point at first byte after the ":" */
			cp = src + 3;
			/*
			 * Throw away characters until either
			 *  - we reach a "$"
			 *  - we run out of bytes (rem == 0)
			 */
			do {
				ch = *cp;
				if (ch == '$')
					break;
				cp++;
				rem--;
			} while (rem);
			/* If the above finished because it ran out of characters, then
			 * this is an incomplete keyword, so don't run the expansion */
			if (!rem)
				continue;
		} else if (src[2] == '$')
			cp = src + 2;
		else
			/* Anything other than "$Id:XXX$" or $Id$ and we skip the
			 * expansion */
			continue;
 
		/* cp is now pointing at the last $ of the keyword */
 
		memcpy(dst, "Id: ", 4);
		dst += 4;
		memcpy(dst, sha1_to_hex(sha1), 40);
		dst += 40;
		*dst++ = ' ';
 
		/* Adjust for the characters we've discarded */
		size -= (cp - src);
		src = cp;
 
		/* Copy the final "$" */
		*dst++ = *src++;
		size--;
	}
 
	*sizep = dst - buf;
	return buf;
}
 
static int git_path_check_crlf(const char *path, struct git_attr_check *check)
{
	const char *value = check->value;
 
	if (ATTR_TRUE(value))
		return CRLF_TEXT;
	else if (ATTR_FALSE(value))
		return CRLF_BINARY;
	else if (ATTR_UNSET(value))
		;
	else if (!strcmp(value, "input"))
		return CRLF_INPUT;
	return CRLF_GUESS;
}
 
static struct convert_driver *git_path_check_convert(const char *path,
					     struct git_attr_check *check)
{
	const char *value = check->value;
	struct convert_driver *drv;
 
	if (ATTR_TRUE(value) || ATTR_FALSE(value) || ATTR_UNSET(value))
		return NULL;
	for (drv = user_convert; drv; drv = drv->next)
		if (!strcmp(value, drv->name))
			return drv;
	return NULL;
}
 
static int git_path_check_ident(const char *path, struct git_attr_check *check)
{
	const char *value = check->value;
 
	return !!ATTR_TRUE(value);
}
 
char *convert_to_git(const char *path, const char *src, unsigned long *sizep)
{
	struct git_attr_check check[3];
	int crlf = CRLF_GUESS;
	int ident = 0;
	char *filter = NULL;
	char *buf, *buf2;
 
	setup_convert_check(check);
	if (!git_checkattr(path, ARRAY_SIZE(check), check)) {
		struct convert_driver *drv;
		crlf = git_path_check_crlf(path, check + 0);
		ident = git_path_check_ident(path, check + 1);
		drv = git_path_check_convert(path, check + 2);
		if (drv && drv->clean)
			filter = drv->clean;
	}
 
	buf = apply_filter(path, src, sizep, filter);
 
	buf2 = crlf_to_git(path, buf ? buf : src, sizep, crlf);
	if (buf2) {
		free(buf);
		buf = buf2;
	}
 
	buf2 = ident_to_git(path, buf ? buf : src, sizep, ident);
	if (buf2) {
		free(buf);
		buf = buf2;
	}
 
	return buf;
}
 
char *convert_to_working_tree(const char *path, const char *src, unsigned long *sizep)
{
	struct git_attr_check check[3];
	int crlf = CRLF_GUESS;
	int ident = 0;
	char *filter = NULL;
	char *buf, *buf2;
 
	setup_convert_check(check);
	if (!git_checkattr(path, ARRAY_SIZE(check), check)) {
		struct convert_driver *drv;
		crlf = git_path_check_crlf(path, check + 0);
		ident = git_path_check_ident(path, check + 1);
		drv = git_path_check_convert(path, check + 2);
		if (drv && drv->smudge)
			filter = drv->smudge;
	}
 
	buf = ident_to_worktree(path, src, sizep, ident);
 
	buf2 = crlf_to_worktree(path, buf ? buf : src, sizep, crlf);
	if (buf2) {
		free(buf);
		buf = buf2;
	}
 
	buf2 = apply_filter(path, buf ? buf : src, sizep, filter);
	if (buf2) {
		free(buf);
		buf = buf2;
	}
 
	return buf;
}
 
void *convert_sha1_file(const char *path, const unsigned char *sha1,
                        unsigned int mode, enum object_type *type,
                        unsigned long *size)
{
	void *buffer = read_sha1_file(sha1, type, size);
	if (S_ISREG(mode) && buffer) {
		void *converted = convert_to_working_tree(path, buffer, size);
		if (converted) {
			free(buffer);
			buffer = converted;
		}
	}
	return buffer;
}