diff.c 88.6 KB
Newer Older
J
Junio C Hamano 已提交
1 2 3 4 5 6 7
/*
 * Copyright (C) 2005 Junio C Hamano
 */
#include "cache.h"
#include "quote.h"
#include "diff.h"
#include "diffcore.h"
J
Junio C Hamano 已提交
8
#include "delta.h"
J
Junio C Hamano 已提交
9
#include "xdiff-interface.h"
10
#include "color.h"
11
#include "attr.h"
12
#include "run-command.h"
13
#include "utf8.h"
J
Junio C Hamano 已提交
14

15 16 17 18 19 20
#ifdef NO_FAST_WORKING_DIRECTORY
#define FAST_WORKING_DIRECTORY 0
#else
#define FAST_WORKING_DIRECTORY 1
#endif

21
static int diff_detect_rename_default;
J
Jeff King 已提交
22
static int diff_rename_limit_default = 200;
23
int diff_use_color_default = -1;
24
static const char *external_diff_cmd_cfg;
25
int diff_auto_refresh_index = 1;
J
Junio C Hamano 已提交
26

27
static char diff_colors[][COLOR_MAXLEN] = {
28
	"\033[m",	/* reset */
29 30 31 32 33 34 35
	"",		/* PLAIN (normal) */
	"\033[1m",	/* METAINFO (bold) */
	"\033[36m",	/* FRAGINFO (cyan) */
	"\033[31m",	/* OLD (red) */
	"\033[32m",	/* NEW (green) */
	"\033[33m",	/* COMMIT (yellow) */
	"\033[41m",	/* WHITESPACE (red background) */
J
Johannes Schindelin 已提交
36 37
};

38 39 40 41 42 43 44 45 46 47 48 49
static int parse_diff_color_slot(const char *var, int ofs)
{
	if (!strcasecmp(var+ofs, "plain"))
		return DIFF_PLAIN;
	if (!strcasecmp(var+ofs, "meta"))
		return DIFF_METAINFO;
	if (!strcasecmp(var+ofs, "frag"))
		return DIFF_FRAGINFO;
	if (!strcasecmp(var+ofs, "old"))
		return DIFF_FILE_OLD;
	if (!strcasecmp(var+ofs, "new"))
		return DIFF_FILE_NEW;
J
Jeff King 已提交
50 51
	if (!strcasecmp(var+ofs, "commit"))
		return DIFF_COMMIT;
52 53
	if (!strcasecmp(var+ofs, "whitespace"))
		return DIFF_WHITESPACE;
54 55 56
	die("bad config variable '%s'", var);
}

J
Junio C Hamano 已提交
57 58 59
static struct ll_diff_driver {
	const char *name;
	struct ll_diff_driver *next;
60
	const char *cmd;
J
Junio C Hamano 已提交
61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81
} *user_diff, **user_diff_tail;

/*
 * Currently there is only "diff.<drivername>.command" variable;
 * because there are "diff.color.<slot>" variables, we are parsing
 * this in a bit convoluted way to allow low level diff driver
 * called "color".
 */
static int parse_lldiff_command(const char *var, const char *ep, const char *value)
{
	const char *name;
	int namelen;
	struct ll_diff_driver *drv;

	name = var + 5;
	namelen = ep - name;
	for (drv = user_diff; drv; drv = drv->next)
		if (!strncmp(drv->name, name, namelen) && !drv->name[namelen])
			break;
	if (!drv) {
		drv = xcalloc(1, sizeof(struct ll_diff_driver));
P
Pierre Habouzit 已提交
82
		drv->name = xmemdupz(name, namelen);
J
Junio C Hamano 已提交
83 84 85 86 87 88
		if (!user_diff_tail)
			user_diff_tail = &user_diff;
		*user_diff_tail = drv;
		user_diff_tail = &(drv->next);
	}

89
	return git_config_string(&(drv->cmd), var, value);
J
Junio C Hamano 已提交
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
/*
 * 'diff.<what>.funcname' attribute can be specified in the configuration
 * to define a customized regexp to find the beginning of a function to
 * be used for hunk header lines of "diff -p" style output.
 */
static struct funcname_pattern {
	char *name;
	char *pattern;
	struct funcname_pattern *next;
} *funcname_pattern_list;

static int parse_funcname_pattern(const char *var, const char *ep, const char *value)
{
	const char *name;
	int namelen;
	struct funcname_pattern *pp;

	name = var + 5; /* "diff." */
	namelen = ep - name;

	for (pp = funcname_pattern_list; pp; pp = pp->next)
		if (!strncmp(pp->name, name, namelen) && !pp->name[namelen])
			break;
	if (!pp) {
		pp = xcalloc(1, sizeof(*pp));
P
Pierre Habouzit 已提交
117
		pp->name = xmemdupz(name, namelen);
118 119 120
		pp->next = funcname_pattern_list;
		funcname_pattern_list = pp;
	}
121
	free(pp->pattern);
122 123 124 125
	pp->pattern = xstrdup(value);
	return 0;
}

126 127 128 129 130 131
/*
 * These are to give UI layer defaults.
 * The core-level commands such as git-diff-files should
 * never be affected by the setting of diff.renames
 * the user happens to have in the configuration file.
 */
132
int git_diff_ui_config(const char *var, const char *value, void *cb)
133
{
134
	if (!strcmp(var, "diff.color") || !strcmp(var, "color.diff")) {
J
Junio C Hamano 已提交
135
		diff_use_color_default = git_config_colorbool(var, value, -1);
136 137
		return 0;
	}
138 139 140 141 142 143 144 145 146 147
	if (!strcmp(var, "diff.renames")) {
		if (!value)
			diff_detect_rename_default = DIFF_DETECT_RENAME;
		else if (!strcasecmp(value, "copies") ||
			 !strcasecmp(value, "copy"))
			diff_detect_rename_default = DIFF_DETECT_COPY;
		else if (git_config_bool(var,value))
			diff_detect_rename_default = DIFF_DETECT_RENAME;
		return 0;
	}
148 149 150 151
	if (!strcmp(var, "diff.autorefreshindex")) {
		diff_auto_refresh_index = git_config_bool(var, value);
		return 0;
	}
152 153
	if (!strcmp(var, "diff.external"))
		return git_config_string(&external_diff_cmd_cfg, var, value);
J
Junio C Hamano 已提交
154 155 156
	if (!prefixcmp(var, "diff.")) {
		const char *ep = strrchr(var, '.');

157 158
		if (ep != var + 4 && !strcmp(ep, ".command"))
			return parse_lldiff_command(var, ep, value);
J
Junio C Hamano 已提交
159
	}
J
Jeff King 已提交
160

161
	return git_diff_basic_config(var, value, cb);
J
Jeff King 已提交
162 163
}

164
int git_diff_basic_config(const char *var, const char *value, void *cb)
J
Jeff King 已提交
165
{
166 167 168 169 170
	if (!strcmp(var, "diff.renamelimit")) {
		diff_rename_limit_default = git_config_int(var, value);
		return 0;
	}

171
	if (!prefixcmp(var, "diff.color.") || !prefixcmp(var, "color.diff.")) {
172
		int slot = parse_diff_color_slot(var, 11);
173 174
		if (!value)
			return config_error_nonbool(var);
175
		color_parse(value, var, diff_colors[slot]);
176 177
		return 0;
	}
J
Junio C Hamano 已提交
178

179 180 181
	if (!prefixcmp(var, "diff.")) {
		const char *ep = strrchr(var, '.');
		if (ep != var + 4) {
182 183 184
			if (!strcmp(ep, ".funcname")) {
				if (!value)
					return config_error_nonbool(var);
185
				return parse_funcname_pattern(var, ep, value);
186
			}
187 188 189
		}
	}

190
	return git_color_default_config(var, value, cb);
191 192
}

J
Junio C Hamano 已提交
193 194 195 196
static char *quote_two(const char *one, const char *two)
{
	int need_one = quote_c_style(one, NULL, NULL, 1);
	int need_two = quote_c_style(two, NULL, NULL, 1);
197
	struct strbuf res;
J
Junio C Hamano 已提交
198

199
	strbuf_init(&res, 0);
J
Junio C Hamano 已提交
200
	if (need_one + need_two) {
201 202 203 204 205 206 207
		strbuf_addch(&res, '"');
		quote_c_style(one, &res, NULL, 1);
		quote_c_style(two, &res, NULL, 1);
		strbuf_addch(&res, '"');
	} else {
		strbuf_addstr(&res, one);
		strbuf_addstr(&res, two);
J
Junio C Hamano 已提交
208
	}
209
	return strbuf_detach(&res, NULL);
J
Junio C Hamano 已提交
210 211 212 213 214 215 216 217 218 219
}

static const char *external_diff(void)
{
	static const char *external_diff_cmd = NULL;
	static int done_preparing = 0;

	if (done_preparing)
		return external_diff_cmd;
	external_diff_cmd = getenv("GIT_EXTERNAL_DIFF");
220 221
	if (!external_diff_cmd)
		external_diff_cmd = external_diff_cmd_cfg;
J
Junio C Hamano 已提交
222 223 224 225 226 227 228 229
	done_preparing = 1;
	return external_diff_cmd;
}

static struct diff_tempfile {
	const char *name; /* filename external diff should read from */
	char hex[41];
	char mode[10];
230
	char tmp_path[PATH_MAX];
J
Junio C Hamano 已提交
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
} diff_temp[2];

static int count_lines(const char *data, int size)
{
	int count, ch, completely_empty = 1, nl_just_seen = 0;
	count = 0;
	while (0 < size--) {
		ch = *data++;
		if (ch == '\n') {
			count++;
			nl_just_seen = 1;
			completely_empty = 0;
		}
		else {
			nl_just_seen = 0;
			completely_empty = 0;
		}
	}
	if (completely_empty)
		return 0;
	if (!nl_just_seen)
		count++; /* no trailing newline */
	return count;
}

256
static void print_line_count(FILE *file, int count)
J
Junio C Hamano 已提交
257 258 259
{
	switch (count) {
	case 0:
260
		fprintf(file, "0,0");
J
Junio C Hamano 已提交
261 262
		break;
	case 1:
263
		fprintf(file, "1");
J
Junio C Hamano 已提交
264 265
		break;
	default:
266
		fprintf(file, "1,%d", count);
J
Junio C Hamano 已提交
267 268 269 270
		break;
	}
}

271 272
static void copy_file_with_prefix(FILE *file,
				  int prefix, const char *data, int size,
273
				  const char *set, const char *reset)
J
Junio C Hamano 已提交
274 275 276 277
{
	int ch, nl_just_seen = 1;
	while (0 < size--) {
		ch = *data++;
278
		if (nl_just_seen) {
279 280
			fputs(set, file);
			putc(prefix, file);
281 282
		}
		if (ch == '\n') {
J
Junio C Hamano 已提交
283
			nl_just_seen = 1;
284
			fputs(reset, file);
285
		} else
J
Junio C Hamano 已提交
286
			nl_just_seen = 0;
287
		putc(ch, file);
J
Junio C Hamano 已提交
288 289
	}
	if (!nl_just_seen)
290
		fprintf(file, "%s\n\\ No newline at end of file\n", reset);
J
Junio C Hamano 已提交
291 292 293 294 295
}

static void emit_rewrite_diff(const char *name_a,
			      const char *name_b,
			      struct diff_filespec *one,
296
			      struct diff_filespec *two,
297
			      struct diff_options *o)
J
Junio C Hamano 已提交
298 299
{
	int lc_a, lc_b;
300
	int color_diff = DIFF_OPT_TST(o, COLOR_DIFF);
301
	const char *name_a_tab, *name_b_tab;
302 303 304 305 306
	const char *metainfo = diff_get_color(color_diff, DIFF_METAINFO);
	const char *fraginfo = diff_get_color(color_diff, DIFF_FRAGINFO);
	const char *old = diff_get_color(color_diff, DIFF_FILE_OLD);
	const char *new = diff_get_color(color_diff, DIFF_FILE_NEW);
	const char *reset = diff_get_color(color_diff, DIFF_RESET);
J
Junio C Hamano 已提交
307
	static struct strbuf a_name = STRBUF_INIT, b_name = STRBUF_INIT;
308

J
Junio C Hamano 已提交
309 310
	name_a += (*name_a == '/');
	name_b += (*name_b == '/');
311 312 313
	name_a_tab = strchr(name_a, ' ') ? "\t" : "";
	name_b_tab = strchr(name_b, ' ') ? "\t" : "";

J
Junio C Hamano 已提交
314 315 316 317 318
	strbuf_reset(&a_name);
	strbuf_reset(&b_name);
	quote_two_c_style(&a_name, o->a_prefix, name_a, 0);
	quote_two_c_style(&b_name, o->b_prefix, name_b, 0);

J
Junio C Hamano 已提交
319 320 321 322
	diff_populate_filespec(one, 0);
	diff_populate_filespec(two, 0);
	lc_a = count_lines(one->data, one->size);
	lc_b = count_lines(two->data, two->size);
323 324 325 326 327 328 329 330
	fprintf(o->file,
		"%s--- %s%s%s\n%s+++ %s%s%s\n%s@@ -",
		metainfo, a_name.buf, name_a_tab, reset,
		metainfo, b_name.buf, name_b_tab, reset, fraginfo);
	print_line_count(o->file, lc_a);
	fprintf(o->file, " +");
	print_line_count(o->file, lc_b);
	fprintf(o->file, " @@%s\n", reset);
J
Junio C Hamano 已提交
331
	if (lc_a)
332
		copy_file_with_prefix(o->file, '-', one->data, one->size, old, reset);
J
Junio C Hamano 已提交
333
	if (lc_b)
334
		copy_file_with_prefix(o->file, '+', two->data, two->size, new, reset);
J
Junio C Hamano 已提交
335 336 337 338 339
}

static int fill_mmfile(mmfile_t *mf, struct diff_filespec *one)
{
	if (!DIFF_FILE_VALID(one)) {
T
Timo Hirvonen 已提交
340
		mf->ptr = (char *)""; /* does not matter */
J
Junio C Hamano 已提交
341 342 343 344 345 346 347 348 349 350
		mf->size = 0;
		return 0;
	}
	else if (diff_populate_filespec(one, 0))
		return -1;
	mf->ptr = one->data;
	mf->size = one->size;
	return 0;
}

351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373
struct diff_words_buffer {
	mmfile_t text;
	long alloc;
	long current; /* output pointer */
	int suppressed_newline;
};

static void diff_words_append(char *line, unsigned long len,
		struct diff_words_buffer *buffer)
{
	if (buffer->text.size + len > buffer->alloc) {
		buffer->alloc = (buffer->text.size + len) * 3 / 2;
		buffer->text.ptr = xrealloc(buffer->text.ptr, buffer->alloc);
	}
	line++;
	len--;
	memcpy(buffer->text.ptr + buffer->text.size, line, len);
	buffer->text.size += len;
}

struct diff_words_data {
	struct xdiff_emit_state xm;
	struct diff_words_buffer minus, plus;
374
	FILE *file;
375 376
};

377
static void print_word(FILE *file, struct diff_words_buffer *buffer, int len, int color,
378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393
		int suppress_newline)
{
	const char *ptr;
	int eol = 0;

	if (len == 0)
		return;

	ptr  = buffer->text.ptr + buffer->current;
	buffer->current += len;

	if (ptr[len - 1] == '\n') {
		eol = 1;
		len--;
	}

394 395 396
	fputs(diff_get_color(1, color), file);
	fwrite(ptr, len, 1, file);
	fputs(diff_get_color(1, DIFF_RESET), file);
397 398 399 400 401

	if (eol) {
		if (suppress_newline)
			buffer->suppressed_newline = 1;
		else
402
			putc('\n', file);
403 404 405 406 407 408 409 410 411
	}
}

static void fn_out_diff_words_aux(void *priv, char *line, unsigned long len)
{
	struct diff_words_data *diff_words = priv;

	if (diff_words->minus.suppressed_newline) {
		if (line[0] != '+')
412
			putc('\n', diff_words->file);
413 414 415 416 417 418
		diff_words->minus.suppressed_newline = 0;
	}

	len--;
	switch (line[0]) {
		case '-':
419 420
			print_word(diff_words->file,
				   &diff_words->minus, len, DIFF_FILE_OLD, 1);
421 422
			break;
		case '+':
423 424
			print_word(diff_words->file,
				   &diff_words->plus, len, DIFF_FILE_NEW, 0);
425 426
			break;
		case ' ':
427 428
			print_word(diff_words->file,
				   &diff_words->plus, len, DIFF_PLAIN, 0);
429 430 431 432 433 434 435 436 437 438 439 440 441 442
			diff_words->minus.current += len;
			break;
	}
}

/* this executes the word diff on the accumulated buffers */
static void diff_words_show(struct diff_words_data *diff_words)
{
	xpparam_t xpp;
	xdemitconf_t xecfg;
	xdemitcb_t ecb;
	mmfile_t minus, plus;
	int i;

443
	memset(&xecfg, 0, sizeof(xecfg));
444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464
	minus.size = diff_words->minus.text.size;
	minus.ptr = xmalloc(minus.size);
	memcpy(minus.ptr, diff_words->minus.text.ptr, minus.size);
	for (i = 0; i < minus.size; i++)
		if (isspace(minus.ptr[i]))
			minus.ptr[i] = '\n';
	diff_words->minus.current = 0;

	plus.size = diff_words->plus.text.size;
	plus.ptr = xmalloc(plus.size);
	memcpy(plus.ptr, diff_words->plus.text.ptr, plus.size);
	for (i = 0; i < plus.size; i++)
		if (isspace(plus.ptr[i]))
			plus.ptr[i] = '\n';
	diff_words->plus.current = 0;

	xpp.flags = XDF_NEED_MINIMAL;
	xecfg.ctxlen = diff_words->minus.alloc + diff_words->plus.alloc;
	ecb.outf = xdiff_outf;
	ecb.priv = diff_words;
	diff_words->xm.consume = fn_out_diff_words_aux;
J
Junio C Hamano 已提交
465
	xdi_diff(&minus, &plus, &xpp, &xecfg, &ecb);
466 467 468 469 470 471

	free(minus.ptr);
	free(plus.ptr);
	diff_words->minus.text.size = diff_words->plus.text.size = 0;

	if (diff_words->minus.suppressed_newline) {
472
		putc('\n', diff_words->file);
473 474 475 476
		diff_words->minus.suppressed_newline = 0;
	}
}

477 478
typedef unsigned long (*sane_truncate_fn)(char *line, unsigned long len);

J
Junio C Hamano 已提交
479
struct emit_callback {
J
Johannes Schindelin 已提交
480 481
	struct xdiff_emit_state xm;
	int nparents, color_diff;
482
	unsigned ws_rule;
483
	sane_truncate_fn truncate;
J
Junio C Hamano 已提交
484
	const char **label_path;
485
	struct diff_words_data *diff_words;
486
	int *found_changesp;
487
	FILE *file;
J
Junio C Hamano 已提交
488 489
};

490 491 492 493 494 495 496 497
static void free_diff_words_data(struct emit_callback *ecbdata)
{
	if (ecbdata->diff_words) {
		/* flush buffers */
		if (ecbdata->diff_words->minus.text.size ||
				ecbdata->diff_words->plus.text.size)
			diff_words_show(ecbdata->diff_words);

498 499
		free (ecbdata->diff_words->minus.text.ptr);
		free (ecbdata->diff_words->plus.text.ptr);
500 501 502 503 504
		free(ecbdata->diff_words);
		ecbdata->diff_words = NULL;
	}
}

J
Jeff King 已提交
505
const char *diff_get_color(int diff_use_color, enum color_diff ix)
J
Johannes Schindelin 已提交
506 507
{
	if (diff_use_color)
L
Linus Torvalds 已提交
508 509
		return diff_colors[ix];
	return "";
J
Johannes Schindelin 已提交
510 511
}

512
static void emit_line(FILE *file, const char *set, const char *reset, const char *line, int len)
513
{
514 515
	int has_trailing_newline = (len > 0 && line[len-1] == '\n');
	if (has_trailing_newline)
516 517
		len--;

518 519 520
	fputs(set, file);
	fwrite(line, len, 1, file);
	fputs(reset, file);
521 522
	if (has_trailing_newline)
		fputc('\n', file);
523 524
}

J
Johannes Schindelin 已提交
525 526 527 528 529 530
static void emit_add_line(const char *reset, struct emit_callback *ecbdata, const char *line, int len)
{
	const char *ws = diff_get_color(ecbdata->color_diff, DIFF_WHITESPACE);
	const char *set = diff_get_color(ecbdata->color_diff, DIFF_FILE_NEW);

	if (!*ws)
531
		emit_line(ecbdata->file, set, reset, line, len);
W
Wincent Colaiuta 已提交
532 533
	else {
		/* Emit just the prefix, then the rest. */
534
		emit_line(ecbdata->file, set, reset, line, ecbdata->nparents);
535 536 537
		ws_check_emit(line + ecbdata->nparents,
			      len - ecbdata->nparents, ecbdata->ws_rule,
			      ecbdata->file, set, reset, ws);
W
Wincent Colaiuta 已提交
538
	}
J
Johannes Schindelin 已提交
539 540
}

541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558
static unsigned long sane_truncate_line(struct emit_callback *ecb, char *line, unsigned long len)
{
	const char *cp;
	unsigned long allot;
	size_t l = len;

	if (ecb->truncate)
		return ecb->truncate(line, len);
	cp = line;
	allot = l;
	while (0 < l) {
		(void) utf8_width(&cp, &l);
		if (!cp)
			break; /* truncated in the middle? */
	}
	return allot - l;
}

J
Johannes Schindelin 已提交
559
static void fn_out_consume(void *priv, char *line, unsigned long len)
J
Junio C Hamano 已提交
560 561
{
	int i;
562
	int color;
J
Junio C Hamano 已提交
563
	struct emit_callback *ecbdata = priv;
564 565
	const char *meta = diff_get_color(ecbdata->color_diff, DIFF_METAINFO);
	const char *plain = diff_get_color(ecbdata->color_diff, DIFF_PLAIN);
J
Jeff King 已提交
566
	const char *reset = diff_get_color(ecbdata->color_diff, DIFF_RESET);
J
Junio C Hamano 已提交
567

568 569
	*(ecbdata->found_changesp) = 1;

J
Junio C Hamano 已提交
570
	if (ecbdata->label_path[0]) {
571 572 573 574 575
		const char *name_a_tab, *name_b_tab;

		name_a_tab = strchr(ecbdata->label_path[0], ' ') ? "\t" : "";
		name_b_tab = strchr(ecbdata->label_path[1], ' ') ? "\t" : "";

576 577 578 579
		fprintf(ecbdata->file, "%s--- %s%s%s\n",
			meta, ecbdata->label_path[0], reset, name_a_tab);
		fprintf(ecbdata->file, "%s+++ %s%s%s\n",
			meta, ecbdata->label_path[1], reset, name_b_tab);
J
Junio C Hamano 已提交
580 581
		ecbdata->label_path[0] = ecbdata->label_path[1] = NULL;
	}
J
Johannes Schindelin 已提交
582 583 584 585 586 587 588 589

	/* This is not really necessary for now because
	 * this codepath only deals with two-way diffs.
	 */
	for (i = 0; i < len && line[i] == '@'; i++)
		;
	if (2 <= i && i < len && line[i] == ' ') {
		ecbdata->nparents = i - 1;
590
		len = sane_truncate_line(ecbdata, line, len);
591 592
		emit_line(ecbdata->file,
			  diff_get_color(ecbdata->color_diff, DIFF_FRAGINFO),
593
			  reset, line, len);
594
		if (line[len-1] != '\n')
595
			putc('\n', ecbdata->file);
596
		return;
J
Johannes Schindelin 已提交
597
	}
598 599

	if (len < ecbdata->nparents) {
600
		emit_line(ecbdata->file, reset, reset, line, len);
601
		return;
J
Johannes Schindelin 已提交
602
	}
603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621

	color = DIFF_PLAIN;
	if (ecbdata->diff_words && ecbdata->nparents != 1)
		/* fall back to normal diff */
		free_diff_words_data(ecbdata);
	if (ecbdata->diff_words) {
		if (line[0] == '-') {
			diff_words_append(line, len,
					  &ecbdata->diff_words->minus);
			return;
		} else if (line[0] == '+') {
			diff_words_append(line, len,
					  &ecbdata->diff_words->plus);
			return;
		}
		if (ecbdata->diff_words->minus.text.size ||
		    ecbdata->diff_words->plus.text.size)
			diff_words_show(ecbdata->diff_words);
		line++;
L
Linus Torvalds 已提交
622
		len--;
623
		emit_line(ecbdata->file, plain, reset, line, len);
624 625 626 627 628 629 630 631 632 633
		return;
	}
	for (i = 0; i < ecbdata->nparents && len; i++) {
		if (line[i] == '-')
			color = DIFF_FILE_OLD;
		else if (line[i] == '+')
			color = DIFF_FILE_NEW;
	}

	if (color != DIFF_FILE_NEW) {
634 635
		emit_line(ecbdata->file,
			  diff_get_color(ecbdata->color_diff, color),
636 637 638 639
			  reset, line, len);
		return;
	}
	emit_add_line(reset, ecbdata, line, len);
J
Junio C Hamano 已提交
640 641 642 643 644 645
}

static char *pprint_rename(const char *a, const char *b)
{
	const char *old = a;
	const char *new = b;
646
	struct strbuf name;
J
Junio C Hamano 已提交
647 648 649
	int pfx_length, sfx_length;
	int len_a = strlen(a);
	int len_b = strlen(b);
650
	int a_midlen, b_midlen;
651 652 653
	int qlen_a = quote_c_style(a, NULL, NULL, 0);
	int qlen_b = quote_c_style(b, NULL, NULL, 0);

654
	strbuf_init(&name, 0);
655
	if (qlen_a || qlen_b) {
656 657 658
		quote_c_style(a, &name, NULL, 0);
		strbuf_addstr(&name, " => ");
		quote_c_style(b, &name, NULL, 0);
659
		return strbuf_detach(&name, NULL);
660
	}
J
Junio C Hamano 已提交
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

	/* Find common prefix */
	pfx_length = 0;
	while (*old && *new && *old == *new) {
		if (*old == '/')
			pfx_length = old - a + 1;
		old++;
		new++;
	}

	/* Find common suffix */
	old = a + len_a;
	new = b + len_b;
	sfx_length = 0;
	while (a <= old && b <= new && *old == *new) {
		if (*old == '/')
			sfx_length = len_a - (old - a);
		old--;
		new--;
	}

	/*
	 * pfx{mid-a => mid-b}sfx
	 * {pfx-a => pfx-b}sfx
	 * pfx{sfx-a => sfx-b}
	 * name-a => name-b
	 */
688 689 690 691 692 693 694 695
	a_midlen = len_a - pfx_length - sfx_length;
	b_midlen = len_b - pfx_length - sfx_length;
	if (a_midlen < 0)
		a_midlen = 0;
	if (b_midlen < 0)
		b_midlen = 0;

	strbuf_grow(&name, pfx_length + a_midlen + b_midlen + sfx_length + 7);
J
Junio C Hamano 已提交
696
	if (pfx_length + sfx_length) {
697 698
		strbuf_add(&name, a, pfx_length);
		strbuf_addch(&name, '{');
J
Junio C Hamano 已提交
699
	}
700 701 702 703 704 705
	strbuf_add(&name, a + pfx_length, a_midlen);
	strbuf_addstr(&name, " => ");
	strbuf_add(&name, b + pfx_length, b_midlen);
	if (pfx_length + sfx_length) {
		strbuf_addch(&name, '}');
		strbuf_add(&name, a + len_a - sfx_length, sfx_length);
J
Junio C Hamano 已提交
706
	}
707
	return strbuf_detach(&name, NULL);
J
Junio C Hamano 已提交
708 709 710 711 712 713 714 715
}

struct diffstat_t {
	struct xdiff_emit_state xm;

	int nr;
	int alloc;
	struct diffstat_file {
716
		char *from_name;
J
Junio C Hamano 已提交
717
		char *name;
718
		char *print_name;
J
Junio C Hamano 已提交
719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738
		unsigned is_unmerged:1;
		unsigned is_binary:1;
		unsigned is_renamed:1;
		unsigned int added, deleted;
	} **files;
};

static struct diffstat_file *diffstat_add(struct diffstat_t *diffstat,
					  const char *name_a,
					  const char *name_b)
{
	struct diffstat_file *x;
	x = xcalloc(sizeof (*x), 1);
	if (diffstat->nr == diffstat->alloc) {
		diffstat->alloc = alloc_nr(diffstat->alloc);
		diffstat->files = xrealloc(diffstat->files,
				diffstat->alloc * sizeof(x));
	}
	diffstat->files[diffstat->nr++] = x;
	if (name_b) {
739 740
		x->from_name = xstrdup(name_a);
		x->name = xstrdup(name_b);
J
Junio C Hamano 已提交
741 742
		x->is_renamed = 1;
	}
743 744
	else {
		x->from_name = NULL;
745
		x->name = xstrdup(name_a);
746
	}
J
Junio C Hamano 已提交
747 748 749 750 751 752 753 754 755 756 757 758 759 760
	return x;
}

static void diffstat_consume(void *priv, char *line, unsigned long len)
{
	struct diffstat_t *diffstat = priv;
	struct diffstat_file *x = diffstat->files[diffstat->nr - 1];

	if (line[0] == '+')
		x->added++;
	else if (line[0] == '-')
		x->deleted++;
}

761
const char mime_boundary_leader[] = "------------";
J
Junio C Hamano 已提交
762

763 764 765
static int scale_linear(int it, int width, int max_change)
{
	/*
766 767
	 * make sure that at least one '-' is printed if there were deletions,
	 * and likewise for '+'.
768
	 */
769 770 771
	if (max_change < 2)
		return it;
	return ((it - 1) * (width - 1) + max_change - 1) / (max_change - 1);
772 773
}

774 775
static void show_name(FILE *file,
		      const char *prefix, const char *name, int len,
J
Junio C Hamano 已提交
776
		      const char *reset, const char *set)
777
{
778
	fprintf(file, " %s%s%-*s%s |", set, prefix, len, name, reset);
779 780
}

781
static void show_graph(FILE *file, char ch, int cnt, const char *set, const char *reset)
782 783 784
{
	if (cnt <= 0)
		return;
785
	fprintf(file, "%s", set);
786
	while (cnt--)
787 788
		putc(ch, file);
	fprintf(file, "%s", reset);
789 790
}

791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812
static void fill_print_name(struct diffstat_file *file)
{
	char *pname;

	if (file->print_name)
		return;

	if (!file->is_renamed) {
		struct strbuf buf;
		strbuf_init(&buf, 0);
		if (quote_c_style(file->name, &buf, NULL, 0)) {
			pname = strbuf_detach(&buf, NULL);
		} else {
			pname = file->name;
			strbuf_release(&buf);
		}
	} else {
		pname = pprint_rename(file->from_name, file->name);
	}
	file->print_name = pname;
}

813
static void show_stats(struct diffstat_t* data, struct diff_options *options)
J
Junio C Hamano 已提交
814 815
{
	int i, len, add, del, total, adds = 0, dels = 0;
816
	int max_change = 0, max_len = 0;
J
Junio C Hamano 已提交
817
	int total_files = data->nr;
818
	int width, name_width;
J
Junio C Hamano 已提交
819
	const char *reset, *set, *add_c, *del_c;
J
Junio C Hamano 已提交
820 821 822 823

	if (data->nr == 0)
		return;

824 825 826 827 828 829
	width = options->stat_width ? options->stat_width : 80;
	name_width = options->stat_name_width ? options->stat_name_width : 50;

	/* Sanity: give at least 5 columns to the graph,
	 * but leave at least 10 columns for the name.
	 */
830 831 832 833 834 835
	if (width < 25)
		width = 25;
	if (name_width < 10)
		name_width = 10;
	else if (width < name_width + 15)
		name_width = width - 15;
836 837

	/* Find the longest filename and max number of changes */
838 839 840 841
	reset = diff_get_color_opt(options, DIFF_RESET);
	set   = diff_get_color_opt(options, DIFF_PLAIN);
	add_c = diff_get_color_opt(options, DIFF_FILE_NEW);
	del_c = diff_get_color_opt(options, DIFF_FILE_OLD);
J
Junio C Hamano 已提交
842

J
Junio C Hamano 已提交
843 844
	for (i = 0; i < data->nr; i++) {
		struct diffstat_file *file = data->files[i];
845
		int change = file->added + file->deleted;
846 847
		fill_print_name(file);
		len = strlen(file->print_name);
J
Junio C Hamano 已提交
848 849 850 851 852
		if (max_len < len)
			max_len = len;

		if (file->is_binary || file->is_unmerged)
			continue;
853 854
		if (max_change < change)
			max_change = change;
J
Junio C Hamano 已提交
855 856
	}

857 858 859 860 861 862 863 864 865 866 867 868 869
	/* Compute the width of the graph part;
	 * 10 is for one blank at the beginning of the line plus
	 * " | count " between the name and the graph.
	 *
	 * From here on, name_width is the width of the name area,
	 * and width is the width of the graph area.
	 */
	name_width = (name_width < max_len) ? name_width : max_len;
	if (width < (name_width + 10) + max_change)
		width = width - (name_width + 10);
	else
		width = max_change;

J
Junio C Hamano 已提交
870
	for (i = 0; i < data->nr; i++) {
T
Timo Hirvonen 已提交
871
		const char *prefix = "";
872
		char *name = data->files[i]->print_name;
J
Junio C Hamano 已提交
873 874
		int added = data->files[i]->added;
		int deleted = data->files[i]->deleted;
875
		int name_len;
J
Junio C Hamano 已提交
876 877 878 879

		/*
		 * "scale" the filename
		 */
880 881 882
		len = name_width;
		name_len = strlen(name);
		if (name_width < name_len) {
J
Junio C Hamano 已提交
883 884
			char *slash;
			prefix = "...";
885 886
			len -= 3;
			name += name_len - len;
J
Junio C Hamano 已提交
887 888 889 890 891 892
			slash = strchr(name, '/');
			if (slash)
				name = slash;
		}

		if (data->files[i]->is_binary) {
893 894 895 896 897 898 899
			show_name(options->file, prefix, name, len, reset, set);
			fprintf(options->file, "  Bin ");
			fprintf(options->file, "%s%d%s", del_c, deleted, reset);
			fprintf(options->file, " -> ");
			fprintf(options->file, "%s%d%s", add_c, added, reset);
			fprintf(options->file, " bytes");
			fprintf(options->file, "\n");
900
			continue;
J
Junio C Hamano 已提交
901 902
		}
		else if (data->files[i]->is_unmerged) {
903 904
			show_name(options->file, prefix, name, len, reset, set);
			fprintf(options->file, "  Unmerged\n");
905
			continue;
J
Junio C Hamano 已提交
906 907 908 909
		}
		else if (!data->files[i]->is_renamed &&
			 (added + deleted == 0)) {
			total_files--;
910
			continue;
J
Junio C Hamano 已提交
911 912
		}

913 914 915
		/*
		 * scale the add/delete
		 */
J
Junio C Hamano 已提交
916 917 918 919 920 921
		add = added;
		del = deleted;
		total = add + del;
		adds += add;
		dels += del;

922 923
		if (width <= max_change) {
			add = scale_linear(add, width, max_change);
924 925
			del = scale_linear(del, width, max_change);
			total = add + del;
J
Junio C Hamano 已提交
926
		}
927
		show_name(options->file, prefix, name, len, reset, set);
928 929
		fprintf(options->file, "%5d%s", added + deleted,
				added + deleted ? " " : "");
930 931 932 933 934 935
		show_graph(options->file, '+', add, add_c, reset);
		show_graph(options->file, '-', del, del_c, reset);
		fprintf(options->file, "\n");
	}
	fprintf(options->file,
	       "%s %d files changed, %d insertions(+), %d deletions(-)%s\n",
J
Junio C Hamano 已提交
936
	       set, total_files, adds, dels, reset);
J
Junio C Hamano 已提交
937 938
}

939
static void show_shortstats(struct diffstat_t* data, struct diff_options *options)
940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959
{
	int i, adds = 0, dels = 0, total_files = data->nr;

	if (data->nr == 0)
		return;

	for (i = 0; i < data->nr; i++) {
		if (!data->files[i]->is_binary &&
		    !data->files[i]->is_unmerged) {
			int added = data->files[i]->added;
			int deleted= data->files[i]->deleted;
			if (!data->files[i]->is_renamed &&
			    (added + deleted == 0)) {
				total_files--;
			} else {
				adds += added;
				dels += deleted;
			}
		}
	}
960
	fprintf(options->file, " %d files changed, %d insertions(+), %d deletions(-)\n",
961 962 963
	       total_files, adds, dels);
}

J
Junio C Hamano 已提交
964 965 966 967
static void show_numstat(struct diffstat_t* data, struct diff_options *options)
{
	int i;

968 969 970
	if (data->nr == 0)
		return;

J
Junio C Hamano 已提交
971 972 973
	for (i = 0; i < data->nr; i++) {
		struct diffstat_file *file = data->files[i];

974
		if (file->is_binary)
975
			fprintf(options->file, "-\t-\t");
976
		else
977 978
			fprintf(options->file,
				"%d\t%d\t", file->added, file->deleted);
979 980 981
		if (options->line_termination) {
			fill_print_name(file);
			if (!file->is_renamed)
982
				write_name_quoted(file->name, options->file,
983 984
						  options->line_termination);
			else {
985 986
				fputs(file->print_name, options->file);
				putc(options->line_termination, options->file);
987
			}
988
		} else {
989
			if (file->is_renamed) {
990 991
				putc('\0', options->file);
				write_name_quoted(file->from_name, options->file, '\0');
992
			}
993
			write_name_quoted(file->name, options->file, '\0');
994
		}
J
Junio C Hamano 已提交
995 996 997
	}
}

998 999 1000
struct dirstat_file {
	const char *name;
	unsigned long changed;
1001 1002
};

1003 1004 1005 1006 1007 1008
struct dirstat_dir {
	struct dirstat_file *files;
	int alloc, nr, percent, cumulative;
};

static long gather_dirstat(FILE *file, struct dirstat_dir *dir, unsigned long changed, const char *base, int baselen)
1009 1010 1011 1012 1013
{
	unsigned long this_dir = 0;
	unsigned int sources = 0;

	while (dir->nr) {
1014
		struct dirstat_file *f = dir->files;
1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025
		int namelen = strlen(f->name);
		unsigned long this;
		char *slash;

		if (namelen < baselen)
			break;
		if (memcmp(f->name, base, baselen))
			break;
		slash = strchr(f->name + baselen, '/');
		if (slash) {
			int newbaselen = slash + 1 - f->name;
1026
			this = gather_dirstat(file, dir, changed, f->name, newbaselen);
1027 1028
			sources++;
		} else {
1029
			this = f->changed;
1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047
			dir->files++;
			dir->nr--;
			sources += 2;
		}
		this_dir += this;
	}

	/*
	 * We don't report dirstat's for
	 *  - the top level
	 *  - or cases where everything came from a single directory
	 *    under this directory (sources == 1).
	 */
	if (baselen && sources != 1) {
		int permille = this_dir * 1000 / changed;
		if (permille) {
			int percent = permille / 10;
			if (percent >= dir->percent) {
1048
				fprintf(file, "%4d.%01d%% %.*s\n", percent, permille % 10, baselen, base);
1049 1050 1051 1052 1053 1054 1055 1056
				if (!dir->cumulative)
					return 0;
			}
		}
	}
	return this_dir;
}

1057
static void show_dirstat(struct diff_options *options)
1058 1059 1060
{
	int i;
	unsigned long changed;
1061 1062 1063 1064 1065 1066 1067 1068
	struct dirstat_dir dir;
	struct diff_queue_struct *q = &diff_queued_diff;

	dir.files = NULL;
	dir.alloc = 0;
	dir.nr = 0;
	dir.percent = options->dirstat_percent;
	dir.cumulative = options->output_format & DIFF_FORMAT_CUMULATIVE;
1069 1070

	changed = 0;
1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094
	for (i = 0; i < q->nr; i++) {
		struct diff_filepair *p = q->queue[i];
		const char *name;
		unsigned long copied, added, damage;

		name = p->one->path ? p->one->path : p->two->path;

		if (DIFF_FILE_VALID(p->one) && DIFF_FILE_VALID(p->two)) {
			diff_populate_filespec(p->one, 0);
			diff_populate_filespec(p->two, 0);
			diffcore_count_changes(p->one, p->two, NULL, NULL, 0,
					       &copied, &added);
			diff_free_filespec_data(p->one);
			diff_free_filespec_data(p->two);
		} else if (DIFF_FILE_VALID(p->one)) {
			diff_populate_filespec(p->one, 1);
			copied = added = 0;
			diff_free_filespec_data(p->one);
		} else if (DIFF_FILE_VALID(p->two)) {
			diff_populate_filespec(p->two, 1);
			copied = 0;
			added = p->two->size;
			diff_free_filespec_data(p->two);
		} else
1095
			continue;
1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108

		/*
		 * Original minus copied is the removed material,
		 * added is the new material.  They are both damages
		 * made to the preimage.
		 */
		damage = (p->one->size - copied) + added;

		ALLOC_GROW(dir.files, dir.nr + 1, dir.alloc);
		dir.files[dir.nr].name = name;
		dir.files[dir.nr].changed = damage;
		changed += damage;
		dir.nr++;
1109 1110 1111 1112 1113 1114 1115
	}

	/* This can happen even with many files, if everything was renames */
	if (!changed)
		return;

	/* Show all directories with more than x% of the changes */
1116
	gather_dirstat(options->file, &dir, changed, "", 0);
1117 1118
}

1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132
static void free_diffstat_info(struct diffstat_t *diffstat)
{
	int i;
	for (i = 0; i < diffstat->nr; i++) {
		struct diffstat_file *f = diffstat->files[i];
		if (f->name != f->print_name)
			free(f->print_name);
		free(f->name);
		free(f->from_name);
		free(f);
	}
	free(diffstat->files);
}

1133 1134 1135
struct checkdiff_t {
	struct xdiff_emit_state xm;
	const char *filename;
1136 1137
	int lineno;
	struct diff_options *o;
1138
	unsigned ws_rule;
1139
	unsigned status;
1140
	int trailing_blanks_start;
1141 1142
};

1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171
static int is_conflict_marker(const char *line, unsigned long len)
{
	char firstchar;
	int cnt;

	if (len < 8)
		return 0;
	firstchar = line[0];
	switch (firstchar) {
	case '=': case '>': case '<':
		break;
	default:
		return 0;
	}
	for (cnt = 1; cnt < 7; cnt++)
		if (line[cnt] != firstchar)
			return 0;
	/* line[0] thru line[6] are same as firstchar */
	if (firstchar == '=') {
		/* divider between ours and theirs? */
		if (len != 8 || line[7] != '\n')
			return 0;
	} else if (len < 8 || !isspace(line[7])) {
		/* not divider before ours nor after theirs */
		return 0;
	}
	return 1;
}

1172 1173 1174
static void checkdiff_consume(void *priv, char *line, unsigned long len)
{
	struct checkdiff_t *data = priv;
1175 1176 1177 1178
	int color_diff = DIFF_OPT_TST(data->o, COLOR_DIFF);
	const char *ws = diff_get_color(color_diff, DIFF_WHITESPACE);
	const char *reset = diff_get_color(color_diff, DIFF_RESET);
	const char *set = diff_get_color(color_diff, DIFF_FILE_NEW);
W
Wincent Colaiuta 已提交
1179
	char *err;
1180 1181

	if (line[0] == '+') {
1182
		unsigned bad;
1183
		data->lineno++;
1184 1185 1186 1187
		if (!ws_blank_line(line + 1, len - 1, data->ws_rule))
			data->trailing_blanks_start = 0;
		else if (!data->trailing_blanks_start)
			data->trailing_blanks_start = data->lineno;
1188 1189 1190 1191 1192 1193
		if (is_conflict_marker(line + 1, len - 1)) {
			data->status |= 1;
			fprintf(data->o->file,
				"%s:%d: leftover conflict marker\n",
				data->filename, data->lineno);
		}
1194
		bad = ws_check(line + 1, len - 1, data->ws_rule);
1195
		if (!bad)
W
Wincent Colaiuta 已提交
1196
			return;
1197 1198
		data->status |= bad;
		err = whitespace_error_string(bad);
1199 1200
		fprintf(data->o->file, "%s:%d: %s.\n",
			data->filename, data->lineno, err);
W
Wincent Colaiuta 已提交
1201
		free(err);
1202
		emit_line(data->o->file, set, reset, line, 1);
1203
		ws_check_emit(line + 1, len - 1, data->ws_rule,
1204
			      data->o->file, set, reset, ws);
1205
	} else if (line[0] == ' ') {
1206
		data->lineno++;
1207 1208
		data->trailing_blanks_start = 0;
	} else if (line[0] == '@') {
1209 1210
		char *plus = strchr(line, '+');
		if (plus)
1211
			data->lineno = strtol(plus, NULL, 10) - 1;
1212 1213
		else
			die("invalid diff");
1214
		data->trailing_blanks_start = 0;
1215 1216 1217
	}
}

J
Junio C Hamano 已提交
1218 1219 1220
static unsigned char *deflate_it(char *data,
				 unsigned long size,
				 unsigned long *result_size)
J
Junio C Hamano 已提交
1221
{
J
Junio C Hamano 已提交
1222 1223 1224 1225 1226
	int bound;
	unsigned char *deflated;
	z_stream stream;

	memset(&stream, 0, sizeof(stream));
1227
	deflateInit(&stream, zlib_compression_level);
J
Junio C Hamano 已提交
1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239
	bound = deflateBound(&stream, size);
	deflated = xmalloc(bound);
	stream.next_out = deflated;
	stream.avail_out = bound;

	stream.next_in = (unsigned char *)data;
	stream.avail_in = size;
	while (deflate(&stream, Z_FINISH) == Z_OK)
		; /* nothing */
	deflateEnd(&stream);
	*result_size = stream.total_out;
	return deflated;
J
Junio C Hamano 已提交
1240 1241
}

1242
static void emit_binary_diff_body(FILE *file, mmfile_t *one, mmfile_t *two)
J
Junio C Hamano 已提交
1243
{
J
Junio C Hamano 已提交
1244 1245 1246 1247 1248 1249 1250 1251
	void *cp;
	void *delta;
	void *deflated;
	void *data;
	unsigned long orig_size;
	unsigned long delta_size;
	unsigned long deflate_size;
	unsigned long data_size;
J
Junio C Hamano 已提交
1252

J
Junio C Hamano 已提交
1253 1254
	/* We could do deflated delta, or we could do just deflated two,
	 * whichever is smaller.
J
Junio C Hamano 已提交
1255
	 */
J
Junio C Hamano 已提交
1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266
	delta = NULL;
	deflated = deflate_it(two->ptr, two->size, &deflate_size);
	if (one->size && two->size) {
		delta = diff_delta(one->ptr, one->size,
				   two->ptr, two->size,
				   &delta_size, deflate_size);
		if (delta) {
			void *to_free = delta;
			orig_size = delta_size;
			delta = deflate_it(delta, delta_size, &delta_size);
			free(to_free);
J
Junio C Hamano 已提交
1267 1268 1269
		}
	}

J
Junio C Hamano 已提交
1270
	if (delta && delta_size < deflate_size) {
1271
		fprintf(file, "delta %lu\n", orig_size);
J
Junio C Hamano 已提交
1272 1273 1274 1275 1276
		free(deflated);
		data = delta;
		data_size = delta_size;
	}
	else {
1277
		fprintf(file, "literal %lu\n", two->size);
J
Junio C Hamano 已提交
1278 1279 1280 1281
		free(delta);
		data = deflated;
		data_size = deflate_size;
	}
J
Junio C Hamano 已提交
1282

J
Junio C Hamano 已提交
1283 1284 1285 1286
	/* emit data encoded in base85 */
	cp = data;
	while (data_size) {
		int bytes = (52 < data_size) ? 52 : data_size;
J
Junio C Hamano 已提交
1287
		char line[70];
J
Junio C Hamano 已提交
1288
		data_size -= bytes;
J
Junio C Hamano 已提交
1289 1290 1291 1292 1293
		if (bytes <= 26)
			line[0] = bytes + 'A' - 1;
		else
			line[0] = bytes - 26 + 'a' - 1;
		encode_85(line + 1, cp, bytes);
1294
		cp = (char *) cp + bytes;
1295 1296
		fputs(line, file);
		fputc('\n', file);
J
Junio C Hamano 已提交
1297
	}
1298
	fprintf(file, "\n");
J
Junio C Hamano 已提交
1299
	free(data);
J
Junio C Hamano 已提交
1300 1301
}

1302
static void emit_binary_diff(FILE *file, mmfile_t *one, mmfile_t *two)
1303
{
1304 1305 1306
	fprintf(file, "GIT binary patch\n");
	emit_binary_diff_body(file, one, two);
	emit_binary_diff_body(file, two, one);
1307 1308
}

1309 1310 1311 1312
static void setup_diff_attr_check(struct git_attr_check *check)
{
	static struct git_attr *attr_diff;

1313
	if (!attr_diff) {
1314
		attr_diff = git_attr("diff", 4);
1315 1316
	}
	check[0].attr = attr_diff;
1317 1318
}

1319
static void diff_filespec_check_attr(struct diff_filespec *one)
J
Junio C Hamano 已提交
1320
{
1321
	struct git_attr_check attr_diff_check;
1322
	int check_from_data = 0;
1323

1324 1325 1326
	if (one->checked_attr)
		return;

1327
	setup_diff_attr_check(&attr_diff_check);
1328
	one->is_binary = 0;
1329
	one->funcname_pattern_ident = NULL;
1330

1331
	if (!git_checkattr(one->path, 1, &attr_diff_check)) {
1332 1333 1334
		const char *value;

		/* binaryness */
1335
		value = attr_diff_check.value;
1336
		if (ATTR_TRUE(value))
1337
			;
1338
		else if (ATTR_FALSE(value))
1339
			one->is_binary = 1;
1340 1341
		else
			check_from_data = 1;
1342

1343
		/* funcname pattern ident */
1344 1345 1346
		if (ATTR_TRUE(value) || ATTR_FALSE(value) || ATTR_UNSET(value))
			;
		else
1347
			one->funcname_pattern_ident = value;
1348
	}
J
Junio C Hamano 已提交
1349

1350 1351 1352
	if (check_from_data) {
		if (!one->data && DIFF_FILE_VALID(one))
			diff_populate_filespec(one, 0);
1353

1354 1355 1356
		if (one->data)
			one->is_binary = buffer_is_binary(one->data, one->size);
	}
1357 1358 1359 1360 1361 1362
}

int diff_filespec_is_binary(struct diff_filespec *one)
{
	diff_filespec_check_attr(one);
	return one->is_binary;
J
Junio C Hamano 已提交
1363 1364
}

1365
static const char *funcname_pattern(const char *ident)
1366
{
1367
	struct funcname_pattern *pp;
1368

1369 1370 1371
	for (pp = funcname_pattern_list; pp; pp = pp->next)
		if (!strcmp(ident, pp->name))
			return pp->pattern;
1372 1373 1374
	return NULL;
}

1375 1376 1377 1378 1379 1380 1381 1382
static struct builtin_funcname_pattern {
	const char *name;
	const char *pattern;
} builtin_funcname_pattern[] = {
	{ "java", "!^[ 	]*\\(catch\\|do\\|for\\|if\\|instanceof\\|"
			"new\\|return\\|switch\\|throw\\|while\\)\n"
			"^[ 	]*\\(\\([ 	]*"
			"[A-Za-z_][A-Za-z_0-9]*\\)\\{2,\\}"
1383
			"[ 	]*([^;]*\\)$" },
1384 1385 1386 1387 1388 1389
	{ "pascal", "^\\(\\(procedure\\|function\\|constructor\\|"
			"destructor\\|interface\\|implementation\\|"
			"initialization\\|finalization\\)[ \t]*.*\\)$"
			"\\|"
			"^\\(.*=[ \t]*\\(class\\|record\\).*\\)$"
			},
1390
	{ "tex", "^\\(\\\\\\(\\(sub\\)*section\\|chapter\\|part\\)\\*\\{0,1\\}{.*\\)$" },
1391
	{ "ruby", "^\\s*\\(\\(class\\|module\\|def\\)\\s.*\\)$" },
1392 1393
};

1394
static const char *diff_funcname_pattern(struct diff_filespec *one)
1395
{
1396
	const char *ident, *pattern;
1397
	int i;
1398 1399

	diff_filespec_check_attr(one);
1400
	ident = one->funcname_pattern_ident;
1401 1402 1403 1404 1405 1406 1407

	if (!ident)
		/*
		 * If the config file has "funcname.default" defined, that
		 * regexp is used; otherwise NULL is returned and xemit uses
		 * the built-in default.
		 */
1408
		return funcname_pattern("default");
1409 1410

	/* Look up custom "funcname.$ident" regexp from config. */
1411 1412 1413
	pattern = funcname_pattern(ident);
	if (pattern)
		return pattern;
1414 1415 1416

	/*
	 * And define built-in fallback patterns here.  Note that
B
Bill Lear 已提交
1417
	 * these can be overridden by the user's config settings.
1418
	 */
1419 1420 1421
	for (i = 0; i < ARRAY_SIZE(builtin_funcname_pattern); i++)
		if (!strcmp(ident, builtin_funcname_pattern[i].name))
			return builtin_funcname_pattern[i].pattern;
1422 1423 1424 1425

	return NULL;
}

J
Junio C Hamano 已提交
1426 1427 1428 1429 1430
static void builtin_diff(const char *name_a,
			 const char *name_b,
			 struct diff_filespec *one,
			 struct diff_filespec *two,
			 const char *xfrm_msg,
J
Junio C Hamano 已提交
1431
			 struct diff_options *o,
J
Junio C Hamano 已提交
1432 1433 1434 1435 1436
			 int complete_rewrite)
{
	mmfile_t mf1, mf2;
	const char *lbl[2];
	char *a_one, *b_two;
1437 1438
	const char *set = diff_get_color_opt(o, DIFF_METAINFO);
	const char *reset = diff_get_color_opt(o, DIFF_RESET);
J
Junio C Hamano 已提交
1439

1440 1441
	a_one = quote_two(o->a_prefix, name_a + (*name_a == '/'));
	b_two = quote_two(o->b_prefix, name_b + (*name_b == '/'));
J
Junio C Hamano 已提交
1442 1443
	lbl[0] = DIFF_FILE_VALID(one) ? a_one : "/dev/null";
	lbl[1] = DIFF_FILE_VALID(two) ? b_two : "/dev/null";
1444
	fprintf(o->file, "%sdiff --git %s %s%s\n", set, a_one, b_two, reset);
J
Junio C Hamano 已提交
1445 1446
	if (lbl[0][0] == '/') {
		/* /dev/null */
1447
		fprintf(o->file, "%snew file mode %06o%s\n", set, two->mode, reset);
L
Linus Torvalds 已提交
1448
		if (xfrm_msg && xfrm_msg[0])
1449
			fprintf(o->file, "%s%s%s\n", set, xfrm_msg, reset);
J
Junio C Hamano 已提交
1450 1451
	}
	else if (lbl[1][0] == '/') {
1452
		fprintf(o->file, "%sdeleted file mode %06o%s\n", set, one->mode, reset);
L
Linus Torvalds 已提交
1453
		if (xfrm_msg && xfrm_msg[0])
1454
			fprintf(o->file, "%s%s%s\n", set, xfrm_msg, reset);
J
Junio C Hamano 已提交
1455 1456 1457
	}
	else {
		if (one->mode != two->mode) {
1458 1459
			fprintf(o->file, "%sold mode %06o%s\n", set, one->mode, reset);
			fprintf(o->file, "%snew mode %06o%s\n", set, two->mode, reset);
J
Johannes Schindelin 已提交
1460
		}
L
Linus Torvalds 已提交
1461
		if (xfrm_msg && xfrm_msg[0])
1462
			fprintf(o->file, "%s%s%s\n", set, xfrm_msg, reset);
J
Junio C Hamano 已提交
1463 1464 1465 1466 1467 1468 1469
		/*
		 * we do not run diff between different kind
		 * of objects.
		 */
		if ((one->mode ^ two->mode) & S_IFMT)
			goto free_ab_and_return;
		if (complete_rewrite) {
1470
			emit_rewrite_diff(name_a, name_b, one, two, o);
1471
			o->found_changes = 1;
J
Junio C Hamano 已提交
1472 1473 1474 1475 1476 1477 1478
			goto free_ab_and_return;
		}
	}

	if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
		die("unable to read files to diff");

1479
	if (!DIFF_OPT_TST(o, TEXT) &&
1480
	    (diff_filespec_is_binary(one) || diff_filespec_is_binary(two))) {
J
Junio C Hamano 已提交
1481 1482 1483 1484
		/* Quite common confusing case */
		if (mf1.size == mf2.size &&
		    !memcmp(mf1.ptr, mf2.ptr, mf1.size))
			goto free_ab_and_return;
1485
		if (DIFF_OPT_TST(o, BINARY))
1486
			emit_binary_diff(o->file, &mf1, &mf2);
J
Junio C Hamano 已提交
1487
		else
1488 1489
			fprintf(o->file, "Binary files %s and %s differ\n",
				lbl[0], lbl[1]);
1490
		o->found_changes = 1;
J
Junio C Hamano 已提交
1491
	}
J
Junio C Hamano 已提交
1492 1493 1494 1495 1496 1497 1498
	else {
		/* Crazy xdl interfaces.. */
		const char *diffopts = getenv("GIT_DIFF_OPTS");
		xpparam_t xpp;
		xdemitconf_t xecfg;
		xdemitcb_t ecb;
		struct emit_callback ecbdata;
1499
		const char *funcname_pattern;
1500

1501 1502 1503
		funcname_pattern = diff_funcname_pattern(one);
		if (!funcname_pattern)
			funcname_pattern = diff_funcname_pattern(two);
J
Junio C Hamano 已提交
1504

1505
		memset(&xecfg, 0, sizeof(xecfg));
J
Johannes Schindelin 已提交
1506
		memset(&ecbdata, 0, sizeof(ecbdata));
J
Junio C Hamano 已提交
1507
		ecbdata.label_path = lbl;
1508
		ecbdata.color_diff = DIFF_OPT_TST(o, COLOR_DIFF);
1509
		ecbdata.found_changesp = &o->found_changes;
1510
		ecbdata.ws_rule = whitespace_rule(name_b ? name_b : name_a);
1511
		ecbdata.file = o->file;
1512
		xpp.flags = XDF_NEED_MINIMAL | o->xdl_opts;
1513
		xecfg.ctxlen = o->context;
J
Junio C Hamano 已提交
1514
		xecfg.flags = XDL_EMIT_FUNCNAMES;
1515 1516
		if (funcname_pattern)
			xdiff_set_find_func(&xecfg, funcname_pattern);
J
Junio C Hamano 已提交
1517 1518
		if (!diffopts)
			;
1519
		else if (!prefixcmp(diffopts, "--unified="))
J
Junio C Hamano 已提交
1520
			xecfg.ctxlen = strtoul(diffopts + 10, NULL, 10);
1521
		else if (!prefixcmp(diffopts, "-u"))
J
Junio C Hamano 已提交
1522
			xecfg.ctxlen = strtoul(diffopts + 2, NULL, 10);
J
Johannes Schindelin 已提交
1523
		ecb.outf = xdiff_outf;
J
Junio C Hamano 已提交
1524
		ecb.priv = &ecbdata;
J
Johannes Schindelin 已提交
1525
		ecbdata.xm.consume = fn_out_consume;
1526
		if (DIFF_OPT_TST(o, COLOR_DIFF_WORDS)) {
1527 1528
			ecbdata.diff_words =
				xcalloc(1, sizeof(struct diff_words_data));
1529 1530
			ecbdata.diff_words->file = o->file;
		}
J
Junio C Hamano 已提交
1531
		xdi_diff(&mf1, &mf2, &xpp, &xecfg, &ecb);
1532
		if (DIFF_OPT_TST(o, COLOR_DIFF_WORDS))
1533
			free_diff_words_data(&ecbdata);
J
Junio C Hamano 已提交
1534 1535 1536
	}

 free_ab_and_return:
1537 1538
	diff_free_filespec_data(one);
	diff_free_filespec_data(two);
J
Junio C Hamano 已提交
1539 1540 1541 1542 1543 1544 1545 1546
	free(a_one);
	free(b_two);
	return;
}

static void builtin_diffstat(const char *name_a, const char *name_b,
			     struct diff_filespec *one,
			     struct diff_filespec *two,
1547
			     struct diffstat_t *diffstat,
1548
			     struct diff_options *o,
1549
			     int complete_rewrite)
J
Junio C Hamano 已提交
1550 1551 1552 1553 1554 1555 1556 1557 1558 1559
{
	mmfile_t mf1, mf2;
	struct diffstat_file *data;

	data = diffstat_add(diffstat, name_a, name_b);

	if (!one || !two) {
		data->is_unmerged = 1;
		return;
	}
1560 1561 1562 1563 1564
	if (complete_rewrite) {
		diff_populate_filespec(one, 0);
		diff_populate_filespec(two, 0);
		data->deleted = count_lines(one->data, one->size);
		data->added = count_lines(two->data, two->size);
1565
		goto free_and_return;
1566
	}
J
Junio C Hamano 已提交
1567 1568 1569
	if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
		die("unable to read files to diff");

1570
	if (diff_filespec_is_binary(one) || diff_filespec_is_binary(two)) {
J
Junio C Hamano 已提交
1571
		data->is_binary = 1;
1572 1573 1574
		data->added = mf2.size;
		data->deleted = mf1.size;
	} else {
J
Junio C Hamano 已提交
1575 1576 1577 1578 1579
		/* Crazy xdl interfaces.. */
		xpparam_t xpp;
		xdemitconf_t xecfg;
		xdemitcb_t ecb;

1580
		memset(&xecfg, 0, sizeof(xecfg));
1581
		xpp.flags = XDF_NEED_MINIMAL | o->xdl_opts;
J
Junio C Hamano 已提交
1582 1583
		ecb.outf = xdiff_outf;
		ecb.priv = diffstat;
J
Junio C Hamano 已提交
1584
		xdi_diff(&mf1, &mf2, &xpp, &xecfg, &ecb);
J
Junio C Hamano 已提交
1585
	}
1586 1587 1588 1589

 free_and_return:
	diff_free_filespec_data(one);
	diff_free_filespec_data(two);
J
Junio C Hamano 已提交
1590 1591
}

1592
static void builtin_checkdiff(const char *name_a, const char *name_b,
1593
			      const char *attr_path,
1594 1595 1596
			      struct diff_filespec *one,
			      struct diff_filespec *two,
			      struct diff_options *o)
1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607
{
	mmfile_t mf1, mf2;
	struct checkdiff_t data;

	if (!two)
		return;

	memset(&data, 0, sizeof(data));
	data.xm.consume = checkdiff_consume;
	data.filename = name_b ? name_b : name_a;
	data.lineno = 0;
1608
	data.o = o;
1609
	data.ws_rule = whitespace_rule(attr_path);
1610 1611 1612 1613

	if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
		die("unable to read files to diff");

1614 1615 1616 1617 1618 1619
	/*
	 * All the other codepaths check both sides, but not checking
	 * the "old" side here is deliberate.  We are checking the newly
	 * introduced changes, and as long as the "new" side is text, we
	 * can and should check what it introduces.
	 */
1620
	if (diff_filespec_is_binary(two))
1621
		goto free_and_return;
1622 1623 1624 1625 1626 1627
	else {
		/* Crazy xdl interfaces.. */
		xpparam_t xpp;
		xdemitconf_t xecfg;
		xdemitcb_t ecb;

1628
		memset(&xecfg, 0, sizeof(xecfg));
1629 1630 1631
		xpp.flags = XDF_NEED_MINIMAL;
		ecb.outf = xdiff_outf;
		ecb.priv = &data;
J
Junio C Hamano 已提交
1632
		xdi_diff(&mf1, &mf2, &xpp, &xecfg, &ecb);
1633 1634 1635 1636 1637 1638

		if (data.trailing_blanks_start) {
			fprintf(o->file, "%s:%d: ends with blank lines.\n",
				data.filename, data.trailing_blanks_start);
			data.status = 1; /* report errors */
		}
1639
	}
1640 1641 1642
 free_and_return:
	diff_free_filespec_data(one);
	diff_free_filespec_data(two);
1643 1644
	if (data.status)
		DIFF_OPT_SET(o, CHECK_FAILED);
1645 1646
}

J
Junio C Hamano 已提交
1647 1648 1649 1650 1651 1652 1653 1654
struct diff_filespec *alloc_filespec(const char *path)
{
	int namelen = strlen(path);
	struct diff_filespec *spec = xmalloc(sizeof(*spec) + namelen + 1);

	memset(spec, 0, sizeof(*spec));
	spec->path = (char *)(spec + 1);
	memcpy(spec->path, path, namelen+1);
1655
	spec->count = 1;
J
Junio C Hamano 已提交
1656 1657 1658
	return spec;
}

1659 1660 1661 1662 1663 1664 1665 1666
void free_filespec(struct diff_filespec *spec)
{
	if (!--spec->count) {
		diff_free_filespec_data(spec);
		free(spec);
	}
}

J
Junio C Hamano 已提交
1667 1668 1669 1670 1671
void fill_filespec(struct diff_filespec *spec, const unsigned char *sha1,
		   unsigned short mode)
{
	if (mode) {
		spec->mode = canon_mode(mode);
1672
		hashcpy(spec->sha1, sha1);
D
David Rientjes 已提交
1673
		spec->sha1_valid = !is_null_sha1(sha1);
J
Junio C Hamano 已提交
1674 1675 1676 1677
	}
}

/*
1678
 * Given a name and sha1 pair, if the index tells us the file in
J
Junio C Hamano 已提交
1679 1680 1681
 * the work tree has that object contents, return true, so that
 * prepare_temp_file() does not have to inflate and extract.
 */
1682
static int reuse_worktree_file(const char *name, const unsigned char *sha1, int want_file)
J
Junio C Hamano 已提交
1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702
{
	struct cache_entry *ce;
	struct stat st;
	int pos, len;

	/* We do not read the cache ourselves here, because the
	 * benchmark with my previous version that always reads cache
	 * shows that it makes things worse for diff-tree comparing
	 * two linux-2.6 kernel trees in an already checked out work
	 * tree.  This is because most diff-tree comparisons deal with
	 * only a small number of files, while reading the cache is
	 * expensive for a large project, and its cost outweighs the
	 * savings we get by not inflating the object to a temporary
	 * file.  Practically, this code only helps when we are used
	 * by diff-cache --cached, which does read the cache before
	 * calling us.
	 */
	if (!active_cache)
		return 0;

1703 1704 1705 1706 1707 1708 1709 1710 1711
	/* We want to avoid the working directory if our caller
	 * doesn't need the data in a normal file, this system
	 * is rather slow with its stat/open/mmap/close syscalls,
	 * and the object is contained in a pack file.  The pack
	 * is probably already open and will be faster to obtain
	 * the data through than the working directory.  Loose
	 * objects however would tend to be slower as they need
	 * to be individually opened and inflated.
	 */
J
Junio C Hamano 已提交
1712
	if (!FAST_WORKING_DIRECTORY && !want_file && has_sha1_pack(sha1, NULL))
1713 1714
		return 0;

J
Junio C Hamano 已提交
1715 1716 1717 1718 1719
	len = strlen(name);
	pos = cache_name_pos(name, len);
	if (pos < 0)
		return 0;
	ce = active_cache[pos];
1720 1721 1722 1723 1724 1725

	/*
	 * This is not the sha1 we are looking for, or
	 * unreusable because it is not a regular file.
	 */
	if (hashcmp(sha1, ce->sha1) || !S_ISREG(ce->ce_mode))
J
Junio C Hamano 已提交
1726
		return 0;
1727 1728 1729

	/*
	 * If ce matches the file in the work tree, we can reuse it.
J
Junio C Hamano 已提交
1730
	 */
1731 1732 1733 1734 1735
	if (ce_uptodate(ce) ||
	    (!lstat(name, &st) && !ce_match_stat(ce, &st, 0)))
		return 1;

	return 0;
J
Junio C Hamano 已提交
1736 1737
}

1738 1739
static int populate_from_stdin(struct diff_filespec *s)
{
1740
	struct strbuf buf;
1741
	size_t size = 0;
1742

1743 1744
	strbuf_init(&buf, 0);
	if (strbuf_read(&buf, 0, 0) < 0)
1745
		return error("error while reading from stdin %s",
1746
				     strerror(errno));
1747

1748
	s->should_munmap = 0;
1749 1750
	s->data = strbuf_detach(&buf, &size);
	s->size = size;
1751 1752 1753 1754
	s->should_free = 1;
	return 0;
}

1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770
static int diff_populate_gitlink(struct diff_filespec *s, int size_only)
{
	int len;
	char *data = xmalloc(100);
	len = snprintf(data, 100,
		"Subproject commit %s\n", sha1_to_hex(s->sha1));
	s->data = data;
	s->size = len;
	s->should_free = 1;
	if (size_only) {
		s->data = NULL;
		free(data);
	}
	return 0;
}

J
Junio C Hamano 已提交
1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784
/*
 * While doing rename detection and pickaxe operation, we may need to
 * grab the data for the blob (or file) for our own in-core comparison.
 * diff_filespec has data and size fields for this purpose.
 */
int diff_populate_filespec(struct diff_filespec *s, int size_only)
{
	int err = 0;
	if (!DIFF_FILE_VALID(s))
		die("internal error: asking to populate invalid file.");
	if (S_ISDIR(s->mode))
		return -1;

	if (s->data)
1785
		return 0;
1786

1787 1788 1789
	if (size_only && 0 < s->size)
		return 0;

M
Martin Waitz 已提交
1790
	if (S_ISGITLINK(s->mode))
1791 1792
		return diff_populate_gitlink(s, size_only);

J
Junio C Hamano 已提交
1793
	if (!s->sha1_valid ||
1794
	    reuse_worktree_file(s->path, s->sha1, 0)) {
1795
		struct strbuf buf;
J
Junio C Hamano 已提交
1796 1797
		struct stat st;
		int fd;
L
Linus Torvalds 已提交
1798

1799 1800 1801
		if (!strcmp(s->path, "-"))
			return populate_from_stdin(s);

J
Junio C Hamano 已提交
1802 1803 1804 1805 1806
		if (lstat(s->path, &st) < 0) {
			if (errno == ENOENT) {
			err_empty:
				err = -1;
			empty:
T
Timo Hirvonen 已提交
1807
				s->data = (char *)"";
J
Junio C Hamano 已提交
1808 1809 1810 1811
				s->size = 0;
				return err;
			}
		}
1812
		s->size = xsize_t(st.st_size);
J
Junio C Hamano 已提交
1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830
		if (!s->size)
			goto empty;
		if (size_only)
			return 0;
		if (S_ISLNK(st.st_mode)) {
			int ret;
			s->data = xmalloc(s->size);
			s->should_free = 1;
			ret = readlink(s->path, s->data, s->size);
			if (ret < 0) {
				free(s->data);
				goto err_empty;
			}
			return 0;
		}
		fd = open(s->path, O_RDONLY);
		if (fd < 0)
			goto err_empty;
1831
		s->data = xmmap(NULL, s->size, PROT_READ, MAP_PRIVATE, fd, 0);
J
Junio C Hamano 已提交
1832 1833
		close(fd);
		s->should_munmap = 1;
L
Linus Torvalds 已提交
1834 1835 1836 1837

		/*
		 * Convert from working tree format to canonical git format
		 */
1838
		strbuf_init(&buf, 0);
1839
		if (convert_to_git(s->path, s->data, s->size, &buf, safe_crlf)) {
1840
			size_t size = 0;
L
Linus Torvalds 已提交
1841 1842
			munmap(s->data, s->size);
			s->should_munmap = 0;
1843 1844
			s->data = strbuf_detach(&buf, &size);
			s->size = size;
L
Linus Torvalds 已提交
1845 1846
			s->should_free = 1;
		}
J
Junio C Hamano 已提交
1847 1848
	}
	else {
1849
		enum object_type type;
1850
		if (size_only)
1851
			type = sha1_object_info(s->sha1, &s->size);
J
Junio C Hamano 已提交
1852
		else {
1853
			s->data = read_sha1_file(s->sha1, &type, &s->size);
J
Junio C Hamano 已提交
1854 1855 1856 1857 1858 1859
			s->should_free = 1;
		}
	}
	return 0;
}

1860
void diff_free_filespec_blob(struct diff_filespec *s)
J
Junio C Hamano 已提交
1861 1862 1863 1864 1865
{
	if (s->should_free)
		free(s->data);
	else if (s->should_munmap)
		munmap(s->data, s->size);
1866 1867 1868 1869 1870

	if (s->should_free || s->should_munmap) {
		s->should_free = s->should_munmap = 0;
		s->data = NULL;
	}
J
Jeff King 已提交
1871 1872 1873 1874
}

void diff_free_filespec_data(struct diff_filespec *s)
{
1875
	diff_free_filespec_blob(s);
J
Junio C Hamano 已提交
1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887
	free(s->cnt_data);
	s->cnt_data = NULL;
}

static void prep_temp_blob(struct diff_tempfile *temp,
			   void *blob,
			   unsigned long size,
			   const unsigned char *sha1,
			   int mode)
{
	int fd;

1888
	fd = git_mkstemp(temp->tmp_path, PATH_MAX, ".diff_XXXXXX");
J
Junio C Hamano 已提交
1889
	if (fd < 0)
1890
		die("unable to create temp-file: %s", strerror(errno));
1891
	if (write_in_full(fd, blob, size) != size)
J
Junio C Hamano 已提交
1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915
		die("unable to write temp-file");
	close(fd);
	temp->name = temp->tmp_path;
	strcpy(temp->hex, sha1_to_hex(sha1));
	temp->hex[40] = 0;
	sprintf(temp->mode, "%06o", mode);
}

static void prepare_temp_file(const char *name,
			      struct diff_tempfile *temp,
			      struct diff_filespec *one)
{
	if (!DIFF_FILE_VALID(one)) {
	not_a_valid_file:
		/* A '-' entry produces this for file-2, and
		 * a '+' entry produces this for file-1.
		 */
		temp->name = "/dev/null";
		strcpy(temp->hex, ".");
		strcpy(temp->mode, ".");
		return;
	}

	if (!one->sha1_valid ||
1916
	    reuse_worktree_file(name, one->sha1, 1)) {
J
Junio C Hamano 已提交
1917 1918 1919 1920 1921 1922 1923 1924 1925
		struct stat st;
		if (lstat(name, &st) < 0) {
			if (errno == ENOENT)
				goto not_a_valid_file;
			die("stat(%s): %s", name, strerror(errno));
		}
		if (S_ISLNK(st.st_mode)) {
			int ret;
			char buf[PATH_MAX + 1]; /* ought to be SYMLINK_MAX */
1926
			size_t sz = xsize_t(st.st_size);
J
Junio C Hamano 已提交
1927 1928
			if (sizeof(buf) <= st.st_size)
				die("symlink too long: %s", name);
1929
			ret = readlink(name, buf, sz);
J
Junio C Hamano 已提交
1930 1931
			if (ret < 0)
				die("readlink(%s)", name);
1932
			prep_temp_blob(temp, buf, sz,
J
Junio C Hamano 已提交
1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032
				       (one->sha1_valid ?
					one->sha1 : null_sha1),
				       (one->sha1_valid ?
					one->mode : S_IFLNK));
		}
		else {
			/* we can borrow from the file in the work tree */
			temp->name = name;
			if (!one->sha1_valid)
				strcpy(temp->hex, sha1_to_hex(null_sha1));
			else
				strcpy(temp->hex, sha1_to_hex(one->sha1));
			/* Even though we may sometimes borrow the
			 * contents from the work tree, we always want
			 * one->mode.  mode is trustworthy even when
			 * !(one->sha1_valid), as long as
			 * DIFF_FILE_VALID(one).
			 */
			sprintf(temp->mode, "%06o", one->mode);
		}
		return;
	}
	else {
		if (diff_populate_filespec(one, 0))
			die("cannot read data blob for %s", one->path);
		prep_temp_blob(temp, one->data, one->size,
			       one->sha1, one->mode);
	}
}

static void remove_tempfile(void)
{
	int i;

	for (i = 0; i < 2; i++)
		if (diff_temp[i].name == diff_temp[i].tmp_path) {
			unlink(diff_temp[i].name);
			diff_temp[i].name = NULL;
		}
}

static void remove_tempfile_on_signal(int signo)
{
	remove_tempfile();
	signal(SIGINT, SIG_DFL);
	raise(signo);
}

/* An external diff command takes:
 *
 * diff-cmd name infile1 infile1-sha1 infile1-mode \
 *               infile2 infile2-sha1 infile2-mode [ rename-to ]
 *
 */
static void run_external_diff(const char *pgm,
			      const char *name,
			      const char *other,
			      struct diff_filespec *one,
			      struct diff_filespec *two,
			      const char *xfrm_msg,
			      int complete_rewrite)
{
	const char *spawn_arg[10];
	struct diff_tempfile *temp = diff_temp;
	int retval;
	static int atexit_asked = 0;
	const char *othername;
	const char **arg = &spawn_arg[0];

	othername = (other? other : name);
	if (one && two) {
		prepare_temp_file(name, &temp[0], one);
		prepare_temp_file(othername, &temp[1], two);
		if (! atexit_asked &&
		    (temp[0].name == temp[0].tmp_path ||
		     temp[1].name == temp[1].tmp_path)) {
			atexit_asked = 1;
			atexit(remove_tempfile);
		}
		signal(SIGINT, remove_tempfile_on_signal);
	}

	if (one && two) {
		*arg++ = pgm;
		*arg++ = name;
		*arg++ = temp[0].name;
		*arg++ = temp[0].hex;
		*arg++ = temp[0].mode;
		*arg++ = temp[1].name;
		*arg++ = temp[1].hex;
		*arg++ = temp[1].mode;
		if (other) {
			*arg++ = other;
			*arg++ = xfrm_msg;
		}
	} else {
		*arg++ = pgm;
		*arg++ = name;
	}
	*arg = NULL;
2033 2034
	fflush(NULL);
	retval = run_command_v_opt(spawn_arg, 0);
J
Junio C Hamano 已提交
2035 2036 2037 2038 2039 2040 2041
	remove_tempfile();
	if (retval) {
		fprintf(stderr, "external diff died, stopping at %s.\n", name);
		exit(1);
	}
}

J
Junio C Hamano 已提交
2042 2043 2044 2045
static const char *external_diff_attr(const char *name)
{
	struct git_attr_check attr_diff_check;

2046 2047 2048
	if (!name)
		return NULL;

J
Junio C Hamano 已提交
2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064
	setup_diff_attr_check(&attr_diff_check);
	if (!git_checkattr(name, 1, &attr_diff_check)) {
		const char *value = attr_diff_check.value;
		if (!ATTR_TRUE(value) &&
		    !ATTR_FALSE(value) &&
		    !ATTR_UNSET(value)) {
			struct ll_diff_driver *drv;

			for (drv = user_diff; drv; drv = drv->next)
				if (!strcmp(drv->name, value))
					return drv->cmd;
		}
	}
	return NULL;
}

J
Junio C Hamano 已提交
2065 2066 2067
static void run_diff_cmd(const char *pgm,
			 const char *name,
			 const char *other,
2068
			 const char *attr_path,
J
Junio C Hamano 已提交
2069 2070 2071
			 struct diff_filespec *one,
			 struct diff_filespec *two,
			 const char *xfrm_msg,
J
Junio C Hamano 已提交
2072
			 struct diff_options *o,
J
Junio C Hamano 已提交
2073 2074
			 int complete_rewrite)
{
2075
	if (!DIFF_OPT_TST(o, ALLOW_EXTERNAL))
J
Junio C Hamano 已提交
2076 2077
		pgm = NULL;
	else {
2078
		const char *cmd = external_diff_attr(attr_path);
J
Junio C Hamano 已提交
2079 2080 2081 2082
		if (cmd)
			pgm = cmd;
	}

J
Junio C Hamano 已提交
2083 2084 2085 2086 2087 2088 2089
	if (pgm) {
		run_external_diff(pgm, name, other, one, two, xfrm_msg,
				  complete_rewrite);
		return;
	}
	if (one && two)
		builtin_diff(name, other ? other : name,
J
Junio C Hamano 已提交
2090
			     one, two, xfrm_msg, o, complete_rewrite);
J
Junio C Hamano 已提交
2091
	else
2092
		fprintf(o->file, "* Unmerged path %s\n", name);
J
Junio C Hamano 已提交
2093 2094 2095 2096 2097 2098 2099
}

static void diff_fill_sha1_info(struct diff_filespec *one)
{
	if (DIFF_FILE_VALID(one)) {
		if (!one->sha1_valid) {
			struct stat st;
2100 2101 2102 2103
			if (!strcmp(one->path, "-")) {
				hashcpy(one->sha1, null_sha1);
				return;
			}
J
Junio C Hamano 已提交
2104 2105 2106 2107 2108 2109 2110
			if (lstat(one->path, &st) < 0)
				die("stat %s", one->path);
			if (index_path(one->sha1, one->path, &st, 0))
				die("cannot hash %s\n", one->path);
		}
	}
	else
2111
		hashclr(one->sha1);
J
Junio C Hamano 已提交
2112 2113
}

2114 2115 2116 2117 2118
static int similarity_index(struct diff_filepair *p)
{
	return p->score * 100 / MAX_SCORE;
}

2119 2120 2121 2122 2123 2124 2125 2126 2127
static void strip_prefix(int prefix_length, const char **namep, const char **otherp)
{
	/* Strip the prefix but do not molest /dev/null and absolute paths */
	if (*namep && **namep != '/')
		*namep += prefix_length;
	if (*otherp && **otherp != '/')
		*otherp += prefix_length;
}

J
Junio C Hamano 已提交
2128 2129 2130
static void run_diff(struct diff_filepair *p, struct diff_options *o)
{
	const char *pgm = external_diff();
2131 2132 2133 2134
	struct strbuf msg;
	char *xfrm_msg;
	struct diff_filespec *one = p->one;
	struct diff_filespec *two = p->two;
J
Junio C Hamano 已提交
2135 2136
	const char *name;
	const char *other;
2137
	const char *attr_path;
J
Junio C Hamano 已提交
2138
	int complete_rewrite = 0;
2139

2140 2141 2142 2143 2144
	name  = p->one->path;
	other = (strcmp(name, p->two->path) ? p->two->path : NULL);
	attr_path = name;
	if (o->prefix_length)
		strip_prefix(o->prefix_length, &name, &other);
J
Junio C Hamano 已提交
2145 2146

	if (DIFF_PAIR_UNMERGED(p)) {
2147 2148
		run_diff_cmd(pgm, name, NULL, attr_path,
			     NULL, NULL, NULL, o, 0);
J
Junio C Hamano 已提交
2149 2150 2151 2152 2153 2154
		return;
	}

	diff_fill_sha1_info(one);
	diff_fill_sha1_info(two);

2155
	strbuf_init(&msg, PATH_MAX * 2 + 300);
J
Junio C Hamano 已提交
2156 2157
	switch (p->status) {
	case DIFF_STATUS_COPIED:
2158 2159 2160 2161 2162 2163
		strbuf_addf(&msg, "similarity index %d%%", similarity_index(p));
		strbuf_addstr(&msg, "\ncopy from ");
		quote_c_style(name, &msg, NULL, 0);
		strbuf_addstr(&msg, "\ncopy to ");
		quote_c_style(other, &msg, NULL, 0);
		strbuf_addch(&msg, '\n');
J
Junio C Hamano 已提交
2164 2165
		break;
	case DIFF_STATUS_RENAMED:
2166 2167 2168 2169 2170 2171
		strbuf_addf(&msg, "similarity index %d%%", similarity_index(p));
		strbuf_addstr(&msg, "\nrename from ");
		quote_c_style(name, &msg, NULL, 0);
		strbuf_addstr(&msg, "\nrename to ");
		quote_c_style(other, &msg, NULL, 0);
		strbuf_addch(&msg, '\n');
J
Junio C Hamano 已提交
2172 2173 2174
		break;
	case DIFF_STATUS_MODIFIED:
		if (p->score) {
2175
			strbuf_addf(&msg, "dissimilarity index %d%%\n",
2176
					similarity_index(p));
J
Junio C Hamano 已提交
2177 2178 2179 2180 2181 2182 2183 2184 2185
			complete_rewrite = 1;
			break;
		}
		/* fallthru */
	default:
		/* nothing */
		;
	}

2186
	if (hashcmp(one->sha1, two->sha1)) {
2187
		int abbrev = DIFF_OPT_TST(o, FULL_INDEX) ? 40 : DEFAULT_ABBREV;
J
Junio C Hamano 已提交
2188

2189
		if (DIFF_OPT_TST(o, BINARY)) {
2190
			mmfile_t mf;
2191 2192
			if ((!fill_mmfile(&mf, one) && diff_filespec_is_binary(one)) ||
			    (!fill_mmfile(&mf, two) && diff_filespec_is_binary(two)))
2193 2194
				abbrev = 40;
		}
2195
		strbuf_addf(&msg, "index %.*s..%.*s",
L
Linus Torvalds 已提交
2196 2197
				abbrev, sha1_to_hex(one->sha1),
				abbrev, sha1_to_hex(two->sha1));
J
Junio C Hamano 已提交
2198
		if (one->mode == two->mode)
2199 2200
			strbuf_addf(&msg, " %06o", one->mode);
		strbuf_addch(&msg, '\n');
J
Junio C Hamano 已提交
2201 2202
	}

2203 2204 2205
	if (msg.len)
		strbuf_setlen(&msg, msg.len - 1);
	xfrm_msg = msg.len ? msg.buf : NULL;
J
Junio C Hamano 已提交
2206 2207 2208 2209 2210 2211 2212 2213

	if (!pgm &&
	    DIFF_FILE_VALID(one) && DIFF_FILE_VALID(two) &&
	    (S_IFMT & one->mode) != (S_IFMT & two->mode)) {
		/* a filepair that changes between file and symlink
		 * needs to be split into deletion and creation.
		 */
		struct diff_filespec *null = alloc_filespec(two->path);
2214 2215
		run_diff_cmd(NULL, name, other, attr_path,
			     one, null, xfrm_msg, o, 0);
J
Junio C Hamano 已提交
2216 2217
		free(null);
		null = alloc_filespec(one->path);
2218 2219
		run_diff_cmd(NULL, name, other, attr_path,
			     null, two, xfrm_msg, o, 0);
J
Junio C Hamano 已提交
2220 2221 2222
		free(null);
	}
	else
2223 2224
		run_diff_cmd(pgm, name, other, attr_path,
			     one, two, xfrm_msg, o, complete_rewrite);
J
Junio C Hamano 已提交
2225

2226
	strbuf_release(&msg);
J
Junio C Hamano 已提交
2227 2228 2229 2230 2231 2232 2233
}

static void run_diffstat(struct diff_filepair *p, struct diff_options *o,
			 struct diffstat_t *diffstat)
{
	const char *name;
	const char *other;
2234
	int complete_rewrite = 0;
J
Junio C Hamano 已提交
2235 2236 2237

	if (DIFF_PAIR_UNMERGED(p)) {
		/* unmerged */
2238
		builtin_diffstat(p->one->path, NULL, NULL, NULL, diffstat, o, 0);
J
Junio C Hamano 已提交
2239 2240 2241 2242 2243 2244
		return;
	}

	name = p->one->path;
	other = (strcmp(name, p->two->path) ? p->two->path : NULL);

2245 2246 2247
	if (o->prefix_length)
		strip_prefix(o->prefix_length, &name, &other);

J
Junio C Hamano 已提交
2248 2249 2250
	diff_fill_sha1_info(p->one);
	diff_fill_sha1_info(p->two);

2251 2252
	if (p->status == DIFF_STATUS_MODIFIED && p->score)
		complete_rewrite = 1;
2253
	builtin_diffstat(name, other, p->one, p->two, diffstat, o, complete_rewrite);
J
Junio C Hamano 已提交
2254 2255
}

2256 2257 2258 2259
static void run_checkdiff(struct diff_filepair *p, struct diff_options *o)
{
	const char *name;
	const char *other;
2260
	const char *attr_path;
2261 2262 2263 2264 2265 2266 2267 2268

	if (DIFF_PAIR_UNMERGED(p)) {
		/* unmerged */
		return;
	}

	name = p->one->path;
	other = (strcmp(name, p->two->path) ? p->two->path : NULL);
2269 2270 2271 2272
	attr_path = other ? other : name;

	if (o->prefix_length)
		strip_prefix(o->prefix_length, &name, &other);
2273 2274 2275 2276

	diff_fill_sha1_info(p->one);
	diff_fill_sha1_info(p->two);

2277
	builtin_checkdiff(name, other, attr_path, p->one, p->two, o);
2278 2279
}

J
Junio C Hamano 已提交
2280 2281 2282
void diff_setup(struct diff_options *options)
{
	memset(options, 0, sizeof(*options));
2283 2284 2285

	options->file = stdout;

J
Junio C Hamano 已提交
2286 2287 2288
	options->line_termination = '\n';
	options->break_opt = -1;
	options->rename_limit = -1;
2289
	options->dirstat_percent = 3;
2290
	options->context = 3;
J
Junio C Hamano 已提交
2291 2292 2293

	options->change = diff_change;
	options->add_remove = diff_addremove;
2294
	if (diff_use_color_default > 0)
2295 2296 2297
		DIFF_OPT_SET(options, COLOR_DIFF);
	else
		DIFF_OPT_CLR(options, COLOR_DIFF);
2298
	options->detect_rename = diff_detect_rename_default;
2299 2300 2301

	options->a_prefix = "a/";
	options->b_prefix = "b/";
J
Junio C Hamano 已提交
2302 2303 2304 2305
}

int diff_setup_done(struct diff_options *options)
{
2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318
	int count = 0;

	if (options->output_format & DIFF_FORMAT_NAME)
		count++;
	if (options->output_format & DIFF_FORMAT_NAME_STATUS)
		count++;
	if (options->output_format & DIFF_FORMAT_CHECKDIFF)
		count++;
	if (options->output_format & DIFF_FORMAT_NO_OUTPUT)
		count++;
	if (count > 1)
		die("--name-only, --name-status, --check and -s are mutually exclusive");

2319
	if (DIFF_OPT_TST(options, FIND_COPIES_HARDER))
2320 2321
		options->detect_rename = DIFF_DETECT_COPY;

2322 2323 2324 2325 2326 2327 2328
	if (!DIFF_OPT_TST(options, RELATIVE_NAME))
		options->prefix = NULL;
	if (options->prefix)
		options->prefix_length = strlen(options->prefix);
	else
		options->prefix_length = 0;

2329 2330 2331 2332 2333
	if (options->output_format & (DIFF_FORMAT_NAME |
				      DIFF_FORMAT_NAME_STATUS |
				      DIFF_FORMAT_CHECKDIFF |
				      DIFF_FORMAT_NO_OUTPUT))
		options->output_format &= ~(DIFF_FORMAT_RAW |
J
Junio C Hamano 已提交
2334
					    DIFF_FORMAT_NUMSTAT |
2335
					    DIFF_FORMAT_DIFFSTAT |
2336
					    DIFF_FORMAT_SHORTSTAT |
2337
					    DIFF_FORMAT_DIRSTAT |
2338 2339 2340
					    DIFF_FORMAT_SUMMARY |
					    DIFF_FORMAT_PATCH);

J
Junio C Hamano 已提交
2341 2342 2343 2344
	/*
	 * These cases always need recursive; we do not drop caller-supplied
	 * recursive bits for other formats here.
	 */
2345
	if (options->output_format & (DIFF_FORMAT_PATCH |
J
Junio C Hamano 已提交
2346
				      DIFF_FORMAT_NUMSTAT |
2347
				      DIFF_FORMAT_DIFFSTAT |
2348
				      DIFF_FORMAT_SHORTSTAT |
2349
				      DIFF_FORMAT_DIRSTAT |
2350
				      DIFF_FORMAT_SUMMARY |
2351
				      DIFF_FORMAT_CHECKDIFF))
2352
		DIFF_OPT_SET(options, RECURSIVE);
2353
	/*
2354
	 * Also pickaxe would not work very well if you do not say recursive
2355
	 */
2356
	if (options->pickaxe)
2357
		DIFF_OPT_SET(options, RECURSIVE);
2358

J
Junio C Hamano 已提交
2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373
	if (options->detect_rename && options->rename_limit < 0)
		options->rename_limit = diff_rename_limit_default;
	if (options->setup & DIFF_SETUP_USE_CACHE) {
		if (!active_cache)
			/* read-cache does not die even when it fails
			 * so it is safe for us to do this here.  Also
			 * it does not smudge active_cache or active_nr
			 * when it fails, so we do not have to worry about
			 * cleaning it up ourselves either.
			 */
			read_cache();
	}
	if (options->abbrev <= 0 || 40 < options->abbrev)
		options->abbrev = 40; /* full */

J
Junio C Hamano 已提交
2374 2375 2376 2377 2378
	/*
	 * It does not make sense to show the first hit we happened
	 * to have found.  It does not make sense not to return with
	 * exit code in such a case either.
	 */
2379
	if (DIFF_OPT_TST(options, QUIET)) {
J
Junio C Hamano 已提交
2380
		options->output_format = DIFF_FORMAT_NO_OUTPUT;
2381
		DIFF_OPT_SET(options, EXIT_WITH_STATUS);
J
Junio C Hamano 已提交
2382 2383 2384 2385 2386 2387 2388
	}

	/*
	 * If we postprocess in diffcore, we cannot simply return
	 * upon the first hit.  We need to run diff as usual.
	 */
	if (options->pickaxe || options->filter)
2389
		DIFF_OPT_CLR(options, QUIET);
J
Junio C Hamano 已提交
2390

J
Junio C Hamano 已提交
2391 2392 2393
	return 0;
}

T
Timo Hirvonen 已提交
2394
static int opt_arg(const char *arg, int arg_short, const char *arg_long, int *val)
2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440
{
	char c, *eq;
	int len;

	if (*arg != '-')
		return 0;
	c = *++arg;
	if (!c)
		return 0;
	if (c == arg_short) {
		c = *++arg;
		if (!c)
			return 1;
		if (val && isdigit(c)) {
			char *end;
			int n = strtoul(arg, &end, 10);
			if (*end)
				return 0;
			*val = n;
			return 1;
		}
		return 0;
	}
	if (c != '-')
		return 0;
	arg++;
	eq = strchr(arg, '=');
	if (eq)
		len = eq - arg;
	else
		len = strlen(arg);
	if (!len || strncmp(arg, arg_long, len))
		return 0;
	if (eq) {
		int n;
		char *end;
		if (!isdigit(*++eq))
			return 0;
		n = strtoul(eq, &end, 10);
		if (*end)
			return 0;
		*val = n;
	}
	return 1;
}

J
Junio C Hamano 已提交
2441 2442
static int diff_scoreopt_parse(const char *opt);

J
Junio C Hamano 已提交
2443 2444 2445
int diff_opt_parse(struct diff_options *options, const char **av, int ac)
{
	const char *arg = av[0];
2446 2447

	/* Output format options */
J
Junio C Hamano 已提交
2448
	if (!strcmp(arg, "-p") || !strcmp(arg, "-u"))
2449
		options->output_format |= DIFF_FORMAT_PATCH;
2450
	else if (opt_arg(arg, 'U', "unified", &options->context))
2451
		options->output_format |= DIFF_FORMAT_PATCH;
2452 2453
	else if (!strcmp(arg, "--raw"))
		options->output_format |= DIFF_FORMAT_RAW;
2454
	else if (!strcmp(arg, "--patch-with-raw"))
2455
		options->output_format |= DIFF_FORMAT_PATCH | DIFF_FORMAT_RAW;
2456
	else if (!strcmp(arg, "--numstat"))
J
Junio C Hamano 已提交
2457
		options->output_format |= DIFF_FORMAT_NUMSTAT;
2458
	else if (!strcmp(arg, "--shortstat"))
2459
		options->output_format |= DIFF_FORMAT_SHORTSTAT;
2460 2461 2462 2463
	else if (opt_arg(arg, 'X', "dirstat", &options->dirstat_percent))
		options->output_format |= DIFF_FORMAT_DIRSTAT;
	else if (!strcmp(arg, "--cumulative"))
		options->output_format |= DIFF_FORMAT_CUMULATIVE;
2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475
	else if (!strcmp(arg, "--check"))
		options->output_format |= DIFF_FORMAT_CHECKDIFF;
	else if (!strcmp(arg, "--summary"))
		options->output_format |= DIFF_FORMAT_SUMMARY;
	else if (!strcmp(arg, "--patch-with-stat"))
		options->output_format |= DIFF_FORMAT_PATCH | DIFF_FORMAT_DIFFSTAT;
	else if (!strcmp(arg, "--name-only"))
		options->output_format |= DIFF_FORMAT_NAME;
	else if (!strcmp(arg, "--name-status"))
		options->output_format |= DIFF_FORMAT_NAME_STATUS;
	else if (!strcmp(arg, "-s"))
		options->output_format |= DIFF_FORMAT_NO_OUTPUT;
2476
	else if (!prefixcmp(arg, "--stat")) {
2477 2478 2479 2480 2481 2482 2483 2484
		char *end;
		int width = options->stat_width;
		int name_width = options->stat_name_width;
		arg += 6;
		end = (char *)arg;

		switch (*arg) {
		case '-':
2485
			if (!prefixcmp(arg, "-width="))
2486
				width = strtoul(arg + 7, &end, 10);
2487
			else if (!prefixcmp(arg, "-name-width="))
2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498
				name_width = strtoul(arg + 12, &end, 10);
			break;
		case '=':
			width = strtoul(arg+1, &end, 10);
			if (*end == ',')
				name_width = strtoul(end+1, &end, 10);
		}

		/* Important! This checks all the error cases! */
		if (*end)
			return 0;
2499
		options->output_format |= DIFF_FORMAT_DIFFSTAT;
2500 2501
		options->stat_name_width = name_width;
		options->stat_width = width;
2502
	}
2503 2504

	/* renames options */
2505
	else if (!prefixcmp(arg, "-B")) {
2506
		if ((options->break_opt = diff_scoreopt_parse(arg)) == -1)
J
Junio C Hamano 已提交
2507 2508
			return -1;
	}
2509
	else if (!prefixcmp(arg, "-M")) {
2510
		if ((options->rename_score = diff_scoreopt_parse(arg)) == -1)
J
Junio C Hamano 已提交
2511 2512 2513
			return -1;
		options->detect_rename = DIFF_DETECT_RENAME;
	}
2514
	else if (!prefixcmp(arg, "-C")) {
2515
		if (options->detect_rename == DIFF_DETECT_COPY)
2516 2517
			DIFF_OPT_SET(options, FIND_COPIES_HARDER);
		if ((options->rename_score = diff_scoreopt_parse(arg)) == -1)
J
Junio C Hamano 已提交
2518 2519 2520
			return -1;
		options->detect_rename = DIFF_DETECT_COPY;
	}
2521 2522
	else if (!strcmp(arg, "--no-renames"))
		options->detect_rename = 0;
2523 2524
	else if (!strcmp(arg, "--relative"))
		DIFF_OPT_SET(options, RELATIVE_NAME);
2525 2526 2527 2528
	else if (!prefixcmp(arg, "--relative=")) {
		DIFF_OPT_SET(options, RELATIVE_NAME);
		options->prefix = arg + 11;
	}
2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548

	/* xdiff options */
	else if (!strcmp(arg, "-w") || !strcmp(arg, "--ignore-all-space"))
		options->xdl_opts |= XDF_IGNORE_WHITESPACE;
	else if (!strcmp(arg, "-b") || !strcmp(arg, "--ignore-space-change"))
		options->xdl_opts |= XDF_IGNORE_WHITESPACE_CHANGE;
	else if (!strcmp(arg, "--ignore-space-at-eol"))
		options->xdl_opts |= XDF_IGNORE_WHITESPACE_AT_EOL;

	/* flags options */
	else if (!strcmp(arg, "--binary")) {
		options->output_format |= DIFF_FORMAT_PATCH;
		DIFF_OPT_SET(options, BINARY);
	}
	else if (!strcmp(arg, "--full-index"))
		DIFF_OPT_SET(options, FULL_INDEX);
	else if (!strcmp(arg, "-a") || !strcmp(arg, "--text"))
		DIFF_OPT_SET(options, TEXT);
	else if (!strcmp(arg, "-R"))
		DIFF_OPT_SET(options, REVERSE_DIFF);
J
Junio C Hamano 已提交
2549
	else if (!strcmp(arg, "--find-copies-harder"))
2550
		DIFF_OPT_SET(options, FIND_COPIES_HARDER);
2551
	else if (!strcmp(arg, "--follow"))
2552
		DIFF_OPT_SET(options, FOLLOW_RENAMES);
J
Johannes Schindelin 已提交
2553
	else if (!strcmp(arg, "--color"))
2554
		DIFF_OPT_SET(options, COLOR_DIFF);
2555
	else if (!strcmp(arg, "--no-color"))
2556
		DIFF_OPT_CLR(options, COLOR_DIFF);
2557
	else if (!strcmp(arg, "--color-words"))
2558
		options->flags |= DIFF_OPT_COLOR_DIFF | DIFF_OPT_COLOR_DIFF_WORDS;
2559
	else if (!strcmp(arg, "--exit-code"))
2560
		DIFF_OPT_SET(options, EXIT_WITH_STATUS);
J
Junio C Hamano 已提交
2561
	else if (!strcmp(arg, "--quiet"))
2562
		DIFF_OPT_SET(options, QUIET);
J
Johannes Schindelin 已提交
2563
	else if (!strcmp(arg, "--ext-diff"))
2564
		DIFF_OPT_SET(options, ALLOW_EXTERNAL);
J
Johannes Schindelin 已提交
2565
	else if (!strcmp(arg, "--no-ext-diff"))
2566
		DIFF_OPT_CLR(options, ALLOW_EXTERNAL);
2567 2568
	else if (!strcmp(arg, "--ignore-submodules"))
		DIFF_OPT_SET(options, IGNORE_SUBMODULES);
2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593

	/* misc options */
	else if (!strcmp(arg, "-z"))
		options->line_termination = 0;
	else if (!prefixcmp(arg, "-l"))
		options->rename_limit = strtoul(arg+2, NULL, 10);
	else if (!prefixcmp(arg, "-S"))
		options->pickaxe = arg + 2;
	else if (!strcmp(arg, "--pickaxe-all"))
		options->pickaxe_opts = DIFF_PICKAXE_ALL;
	else if (!strcmp(arg, "--pickaxe-regex"))
		options->pickaxe_opts = DIFF_PICKAXE_REGEX;
	else if (!prefixcmp(arg, "-O"))
		options->orderfile = arg + 2;
	else if (!prefixcmp(arg, "--diff-filter="))
		options->filter = arg + 14;
	else if (!strcmp(arg, "--abbrev"))
		options->abbrev = DEFAULT_ABBREV;
	else if (!prefixcmp(arg, "--abbrev=")) {
		options->abbrev = strtoul(arg + 9, NULL, 10);
		if (options->abbrev < MINIMUM_ABBREV)
			options->abbrev = MINIMUM_ABBREV;
		else if (40 < options->abbrev)
			options->abbrev = 40;
	}
2594 2595 2596 2597 2598 2599
	else if (!prefixcmp(arg, "--src-prefix="))
		options->a_prefix = arg + 13;
	else if (!prefixcmp(arg, "--dst-prefix="))
		options->b_prefix = arg + 13;
	else if (!strcmp(arg, "--no-prefix"))
		options->a_prefix = options->b_prefix = "";
2600 2601 2602 2603
	else if (!prefixcmp(arg, "--output=")) {
		options->file = fopen(arg + strlen("--output="), "w");
		options->close_file = 1;
	} else
J
Junio C Hamano 已提交
2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640
		return 0;
	return 1;
}

static int parse_num(const char **cp_p)
{
	unsigned long num, scale;
	int ch, dot;
	const char *cp = *cp_p;

	num = 0;
	scale = 1;
	dot = 0;
	for(;;) {
		ch = *cp;
		if ( !dot && ch == '.' ) {
			scale = 1;
			dot = 1;
		} else if ( ch == '%' ) {
			scale = dot ? scale*100 : 100;
			cp++;	/* % is always at the end */
			break;
		} else if ( ch >= '0' && ch <= '9' ) {
			if ( scale < 100000 ) {
				scale *= 10;
				num = (num*10) + (ch-'0');
			}
		} else {
			break;
		}
		cp++;
	}
	*cp_p = cp;

	/* user says num divided by scale and we say internally that
	 * is MAX_SCORE * num / scale.
	 */
2641
	return (int)((num >= scale) ? MAX_SCORE : (MAX_SCORE * num / scale));
J
Junio C Hamano 已提交
2642 2643
}

J
Junio C Hamano 已提交
2644
static int diff_scoreopt_parse(const char *opt)
J
Junio C Hamano 已提交
2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687
{
	int opt1, opt2, cmd;

	if (*opt++ != '-')
		return -1;
	cmd = *opt++;
	if (cmd != 'M' && cmd != 'C' && cmd != 'B')
		return -1; /* that is not a -M, -C nor -B option */

	opt1 = parse_num(&opt);
	if (cmd != 'B')
		opt2 = 0;
	else {
		if (*opt == 0)
			opt2 = 0;
		else if (*opt != '/')
			return -1; /* we expect -B80/99 or -B80 */
		else {
			opt++;
			opt2 = parse_num(&opt);
		}
	}
	if (*opt != 0)
		return -1;
	return opt1 | (opt2 << 16);
}

struct diff_queue_struct diff_queued_diff;

void diff_q(struct diff_queue_struct *queue, struct diff_filepair *dp)
{
	if (queue->alloc <= queue->nr) {
		queue->alloc = alloc_nr(queue->alloc);
		queue->queue = xrealloc(queue->queue,
					sizeof(dp) * queue->alloc);
	}
	queue->queue[queue->nr++] = dp;
}

struct diff_filepair *diff_queue(struct diff_queue_struct *queue,
				 struct diff_filespec *one,
				 struct diff_filespec *two)
{
2688
	struct diff_filepair *dp = xcalloc(1, sizeof(*dp));
J
Junio C Hamano 已提交
2689 2690 2691 2692 2693 2694 2695 2696 2697
	dp->one = one;
	dp->two = two;
	if (queue)
		diff_q(queue, dp);
	return dp;
}

void diff_free_filepair(struct diff_filepair *p)
{
2698 2699
	free_filespec(p->one);
	free_filespec(p->two);
J
Junio C Hamano 已提交
2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725
	free(p);
}

/* This is different from find_unique_abbrev() in that
 * it stuffs the result with dots for alignment.
 */
const char *diff_unique_abbrev(const unsigned char *sha1, int len)
{
	int abblen;
	const char *abbrev;
	if (len == 40)
		return sha1_to_hex(sha1);

	abbrev = find_unique_abbrev(sha1, len);
	abblen = strlen(abbrev);
	if (abblen < 37) {
		static char hex[41];
		if (len < abblen && abblen <= len + 2)
			sprintf(hex, "%s%.*s", abbrev, len+3-abblen, "..");
		else
			sprintf(hex, "%s...", abbrev);
		return hex;
	}
	return sha1_to_hex(sha1);
}

2726
static void diff_flush_raw(struct diff_filepair *p, struct diff_options *opt)
J
Junio C Hamano 已提交
2727
{
2728 2729
	int line_termination = opt->line_termination;
	int inter_name_termination = line_termination ? '\t' : '\0';
J
Junio C Hamano 已提交
2730

2731
	if (!(opt->output_format & DIFF_FORMAT_NAME_STATUS)) {
2732 2733 2734
		fprintf(opt->file, ":%06o %06o %s ", p->one->mode, p->two->mode,
			diff_unique_abbrev(p->one->sha1, opt->abbrev));
		fprintf(opt->file, "%s ", diff_unique_abbrev(p->two->sha1, opt->abbrev));
J
Junio C Hamano 已提交
2735
	}
2736
	if (p->score) {
2737 2738
		fprintf(opt->file, "%c%03d%c", p->status, similarity_index(p),
			inter_name_termination);
2739
	} else {
2740
		fprintf(opt->file, "%c%c", p->status, inter_name_termination);
J
Junio C Hamano 已提交
2741 2742
	}

2743 2744 2745 2746 2747 2748
	if (p->status == DIFF_STATUS_COPIED ||
	    p->status == DIFF_STATUS_RENAMED) {
		const char *name_a, *name_b;
		name_a = p->one->path;
		name_b = p->two->path;
		strip_prefix(opt->prefix_length, &name_a, &name_b);
2749 2750
		write_name_quoted(name_a, opt->file, inter_name_termination);
		write_name_quoted(name_b, opt->file, line_termination);
2751
	} else {
2752 2753 2754 2755
		const char *name_a, *name_b;
		name_a = p->one->mode ? p->one->path : p->two->path;
		name_b = NULL;
		strip_prefix(opt->prefix_length, &name_a, &name_b);
2756
		write_name_quoted(name_a, opt->file, line_termination);
2757
	}
J
Junio C Hamano 已提交
2758 2759 2760 2761 2762 2763 2764 2765 2766
}

int diff_unmodified_pair(struct diff_filepair *p)
{
	/* This function is written stricter than necessary to support
	 * the currently implemented transformers, but the idea is to
	 * let transformers to produce diff_filepairs any way they want,
	 * and filter and clean them up here before producing the output.
	 */
2767
	struct diff_filespec *one = p->one, *two = p->two;
J
Junio C Hamano 已提交
2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783

	if (DIFF_PAIR_UNMERGED(p))
		return 0; /* unmerged is interesting */

	/* deletion, addition, mode or type change
	 * and rename are all interesting.
	 */
	if (DIFF_FILE_VALID(one) != DIFF_FILE_VALID(two) ||
	    DIFF_PAIR_MODE_CHANGED(p) ||
	    strcmp(one->path, two->path))
		return 0;

	/* both are valid and point at the same path.  that is, we are
	 * dealing with a change.
	 */
	if (one->sha1_valid && two->sha1_valid &&
2784
	    !hashcmp(one->sha1, two->sha1))
J
Junio C Hamano 已提交
2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815
		return 1; /* no change */
	if (!one->sha1_valid && !two->sha1_valid)
		return 1; /* both look at the same file on the filesystem. */
	return 0;
}

static void diff_flush_patch(struct diff_filepair *p, struct diff_options *o)
{
	if (diff_unmodified_pair(p))
		return;

	if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) ||
	    (DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode)))
		return; /* no tree diffs in patch format */

	run_diff(p, o);
}

static void diff_flush_stat(struct diff_filepair *p, struct diff_options *o,
			    struct diffstat_t *diffstat)
{
	if (diff_unmodified_pair(p))
		return;

	if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) ||
	    (DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode)))
		return; /* no tree diffs in patch format */

	run_diffstat(p, o, diffstat);
}

2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828
static void diff_flush_checkdiff(struct diff_filepair *p,
		struct diff_options *o)
{
	if (diff_unmodified_pair(p))
		return;

	if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) ||
	    (DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode)))
		return; /* no tree diffs in patch format */

	run_checkdiff(p, o);
}

J
Junio C Hamano 已提交
2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856
int diff_queue_is_empty(void)
{
	struct diff_queue_struct *q = &diff_queued_diff;
	int i;
	for (i = 0; i < q->nr; i++)
		if (!diff_unmodified_pair(q->queue[i]))
			return 0;
	return 1;
}

#if DIFF_DEBUG
void diff_debug_filespec(struct diff_filespec *s, int x, const char *one)
{
	fprintf(stderr, "queue[%d] %s (%s) %s %06o %s\n",
		x, one ? one : "",
		s->path,
		DIFF_FILE_VALID(s) ? "valid" : "invalid",
		s->mode,
		s->sha1_valid ? sha1_to_hex(s->sha1) : "");
	fprintf(stderr, "queue[%d] %s size %lu flags %d\n",
		x, one ? one : "",
		s->size, s->xfrm_flags);
}

void diff_debug_filepair(const struct diff_filepair *p, int i)
{
	diff_debug_filespec(p->one, i, "one");
	diff_debug_filespec(p->two, i, "two");
2857
	fprintf(stderr, "score %d, status %c rename_used %d broken %d\n",
J
Junio C Hamano 已提交
2858
		p->score, p->status ? p->status : '?',
2859
		p->one->rename_used, p->broken_pair);
J
Junio C Hamano 已提交
2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876
}

void diff_debug_queue(const char *msg, struct diff_queue_struct *q)
{
	int i;
	if (msg)
		fprintf(stderr, "%s\n", msg);
	fprintf(stderr, "q->nr = %d\n", q->nr);
	for (i = 0; i < q->nr; i++) {
		struct diff_filepair *p = q->queue[i];
		diff_debug_filepair(p, i);
	}
}
#endif

static void diff_resolve_rename_copy(void)
{
2877 2878
	int i;
	struct diff_filepair *p;
J
Junio C Hamano 已提交
2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899
	struct diff_queue_struct *q = &diff_queued_diff;

	diff_debug_queue("resolve-rename-copy", q);

	for (i = 0; i < q->nr; i++) {
		p = q->queue[i];
		p->status = 0; /* undecided */
		if (DIFF_PAIR_UNMERGED(p))
			p->status = DIFF_STATUS_UNMERGED;
		else if (!DIFF_FILE_VALID(p->one))
			p->status = DIFF_STATUS_ADDED;
		else if (!DIFF_FILE_VALID(p->two))
			p->status = DIFF_STATUS_DELETED;
		else if (DIFF_PAIR_TYPE_CHANGED(p))
			p->status = DIFF_STATUS_TYPE_CHANGED;

		/* from this point on, we are dealing with a pair
		 * whose both sides are valid and of the same type, i.e.
		 * either in-place edit or rename/copy edit.
		 */
		else if (DIFF_PAIR_RENAME(p)) {
2900 2901 2902 2903 2904 2905 2906 2907 2908
			/*
			 * A rename might have re-connected a broken
			 * pair up, causing the pathnames to be the
			 * same again. If so, that's not a rename at
			 * all, just a modification..
			 *
			 * Otherwise, see if this source was used for
			 * multiple renames, in which case we decrement
			 * the count, and call it a copy.
J
Junio C Hamano 已提交
2909
			 */
2910 2911 2912
			if (!strcmp(p->one->path, p->two->path))
				p->status = DIFF_STATUS_MODIFIED;
			else if (--p->one->rename_used > 0)
J
Junio C Hamano 已提交
2913
				p->status = DIFF_STATUS_COPIED;
2914
			else
J
Junio C Hamano 已提交
2915 2916
				p->status = DIFF_STATUS_RENAMED;
		}
2917
		else if (hashcmp(p->one->sha1, p->two->sha1) ||
2918 2919
			 p->one->mode != p->two->mode ||
			 is_null_sha1(p->one->sha1))
J
Junio C Hamano 已提交
2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932
			p->status = DIFF_STATUS_MODIFIED;
		else {
			/* This is a "no-change" entry and should not
			 * happen anymore, but prepare for broken callers.
			 */
			error("feeding unmodified %s to diffcore",
			      p->one->path);
			p->status = DIFF_STATUS_UNKNOWN;
		}
	}
	diff_debug_queue("resolve-rename-copy done", q);
}

2933
static int check_pair_status(struct diff_filepair *p)
J
Junio C Hamano 已提交
2934 2935 2936
{
	switch (p->status) {
	case DIFF_STATUS_UNKNOWN:
2937
		return 0;
J
Junio C Hamano 已提交
2938 2939 2940
	case 0:
		die("internal error in diff-resolve-rename-copy");
	default:
2941
		return 1;
J
Junio C Hamano 已提交
2942 2943 2944
	}
}

2945 2946 2947 2948 2949 2950 2951 2952
static void flush_one_pair(struct diff_filepair *p, struct diff_options *opt)
{
	int fmt = opt->output_format;

	if (fmt & DIFF_FORMAT_CHECKDIFF)
		diff_flush_checkdiff(p, opt);
	else if (fmt & (DIFF_FORMAT_RAW | DIFF_FORMAT_NAME_STATUS))
		diff_flush_raw(p, opt);
2953 2954 2955 2956 2957
	else if (fmt & DIFF_FORMAT_NAME) {
		const char *name_a, *name_b;
		name_a = p->two->path;
		name_b = NULL;
		strip_prefix(opt->prefix_length, &name_a, &name_b);
2958
		write_name_quoted(name_a, opt->file, opt->line_termination);
2959
	}
2960 2961
}

2962
static void show_file_mode_name(FILE *file, const char *newdelete, struct diff_filespec *fs)
S
Sean 已提交
2963 2964
{
	if (fs->mode)
2965
		fprintf(file, " %s mode %06o ", newdelete, fs->mode);
S
Sean 已提交
2966
	else
2967 2968
		fprintf(file, " %s ", newdelete);
	write_name_quoted(fs->path, file, '\n');
S
Sean 已提交
2969 2970 2971
}


2972
static void show_mode_change(FILE *file, struct diff_filepair *p, int show_name)
S
Sean 已提交
2973 2974
{
	if (p->one->mode && p->two->mode && p->one->mode != p->two->mode) {
2975
		fprintf(file, " mode change %06o => %06o%c", p->one->mode, p->two->mode,
2976
			show_name ? ' ' : '\n');
2977
		if (show_name) {
2978
			write_name_quoted(p->two->path, file, '\n');
2979
		}
S
Sean 已提交
2980 2981 2982
	}
}

2983
static void show_rename_copy(FILE *file, const char *renamecopy, struct diff_filepair *p)
S
Sean 已提交
2984
{
2985
	char *names = pprint_rename(p->one->path, p->two->path);
S
Sean 已提交
2986

2987
	fprintf(file, " %s %s (%d%%)\n", renamecopy, names, similarity_index(p));
2988
	free(names);
2989
	show_mode_change(file, p, 0);
S
Sean 已提交
2990 2991
}

2992
static void diff_summary(FILE *file, struct diff_filepair *p)
S
Sean 已提交
2993 2994 2995
{
	switch(p->status) {
	case DIFF_STATUS_DELETED:
2996
		show_file_mode_name(file, "delete", p->one);
S
Sean 已提交
2997 2998
		break;
	case DIFF_STATUS_ADDED:
2999
		show_file_mode_name(file, "create", p->two);
S
Sean 已提交
3000 3001
		break;
	case DIFF_STATUS_COPIED:
3002
		show_rename_copy(file, "copy", p);
S
Sean 已提交
3003 3004
		break;
	case DIFF_STATUS_RENAMED:
3005
		show_rename_copy(file, "rename", p);
S
Sean 已提交
3006 3007 3008
		break;
	default:
		if (p->score) {
3009 3010 3011
			fputs(" rewrite ", file);
			write_name_quoted(p->two->path, file, ' ');
			fprintf(file, "(%d%%)\n", similarity_index(p));
3012
		}
3013
		show_mode_change(file, p, !p->score);
S
Sean 已提交
3014 3015 3016 3017
		break;
	}
}

3018 3019 3020 3021 3022 3023 3024 3025 3026
struct patch_id_t {
	struct xdiff_emit_state xm;
	SHA_CTX *ctx;
	int patchlen;
};

static int remove_space(char *line, int len)
{
	int i;
3027 3028
	char *dst = line;
	unsigned char c;
3029

3030 3031 3032
	for (i = 0; i < len; i++)
		if (!isspace((c = line[i])))
			*dst++ = c;
3033

3034
	return dst - line;
3035 3036 3037 3038 3039 3040 3041 3042
}

static void patch_id_consume(void *priv, char *line, unsigned long len)
{
	struct patch_id_t *data = priv;
	int new_len;

	/* Ignore line numbers when computing the SHA1 of the patch */
3043
	if (!prefixcmp(line, "@@ -"))
3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073
		return;

	new_len = remove_space(line, len);

	SHA1_Update(data->ctx, line, new_len);
	data->patchlen += new_len;
}

/* returns 0 upon success, and writes result into sha1 */
static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1)
{
	struct diff_queue_struct *q = &diff_queued_diff;
	int i;
	SHA_CTX ctx;
	struct patch_id_t data;
	char buffer[PATH_MAX * 4 + 20];

	SHA1_Init(&ctx);
	memset(&data, 0, sizeof(struct patch_id_t));
	data.ctx = &ctx;
	data.xm.consume = patch_id_consume;

	for (i = 0; i < q->nr; i++) {
		xpparam_t xpp;
		xdemitconf_t xecfg;
		xdemitcb_t ecb;
		mmfile_t mf1, mf2;
		struct diff_filepair *p = q->queue[i];
		int len1, len2;

3074
		memset(&xecfg, 0, sizeof(xecfg));
3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127
		if (p->status == 0)
			return error("internal diff status error");
		if (p->status == DIFF_STATUS_UNKNOWN)
			continue;
		if (diff_unmodified_pair(p))
			continue;
		if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) ||
		    (DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode)))
			continue;
		if (DIFF_PAIR_UNMERGED(p))
			continue;

		diff_fill_sha1_info(p->one);
		diff_fill_sha1_info(p->two);
		if (fill_mmfile(&mf1, p->one) < 0 ||
				fill_mmfile(&mf2, p->two) < 0)
			return error("unable to read files to diff");

		len1 = remove_space(p->one->path, strlen(p->one->path));
		len2 = remove_space(p->two->path, strlen(p->two->path));
		if (p->one->mode == 0)
			len1 = snprintf(buffer, sizeof(buffer),
					"diff--gita/%.*sb/%.*s"
					"newfilemode%06o"
					"---/dev/null"
					"+++b/%.*s",
					len1, p->one->path,
					len2, p->two->path,
					p->two->mode,
					len2, p->two->path);
		else if (p->two->mode == 0)
			len1 = snprintf(buffer, sizeof(buffer),
					"diff--gita/%.*sb/%.*s"
					"deletedfilemode%06o"
					"---a/%.*s"
					"+++/dev/null",
					len1, p->one->path,
					len2, p->two->path,
					p->one->mode,
					len1, p->one->path);
		else
			len1 = snprintf(buffer, sizeof(buffer),
					"diff--gita/%.*sb/%.*s"
					"---a/%.*s"
					"+++b/%.*s",
					len1, p->one->path,
					len2, p->two->path,
					len1, p->one->path,
					len2, p->two->path);
		SHA1_Update(&ctx, buffer, len1);

		xpp.flags = XDF_NEED_MINIMAL;
		xecfg.ctxlen = 3;
J
Junio C Hamano 已提交
3128
		xecfg.flags = XDL_EMIT_FUNCNAMES;
3129 3130
		ecb.outf = xdiff_outf;
		ecb.priv = &data;
J
Junio C Hamano 已提交
3131
		xdi_diff(&mf1, &mf2, &xpp, &xecfg, &ecb);
3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153
	}

	SHA1_Final(sha1, &ctx);
	return 0;
}

int diff_flush_patch_id(struct diff_options *options, unsigned char *sha1)
{
	struct diff_queue_struct *q = &diff_queued_diff;
	int i;
	int result = diff_get_patch_id(options, sha1);

	for (i = 0; i < q->nr; i++)
		diff_free_filepair(q->queue[i]);

	free(q->queue);
	q->queue = NULL;
	q->nr = q->alloc = 0;

	return result;
}

3154
static int is_summary_empty(const struct diff_queue_struct *q)
J
Junio C Hamano 已提交
3155 3156 3157
{
	int i;

3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174
	for (i = 0; i < q->nr; i++) {
		const struct diff_filepair *p = q->queue[i];

		switch (p->status) {
		case DIFF_STATUS_DELETED:
		case DIFF_STATUS_ADDED:
		case DIFF_STATUS_COPIED:
		case DIFF_STATUS_RENAMED:
			return 0;
		default:
			if (p->score)
				return 0;
			if (p->one->mode && p->two->mode &&
			    p->one->mode != p->two->mode)
				return 0;
			break;
		}
J
Junio C Hamano 已提交
3175
	}
3176 3177 3178
	return 1;
}

J
Junio C Hamano 已提交
3179 3180 3181
void diff_flush(struct diff_options *options)
{
	struct diff_queue_struct *q = &diff_queued_diff;
3182
	int i, output_format = options->output_format;
3183
	int separator = 0;
J
Junio C Hamano 已提交
3184

3185 3186 3187 3188
	/*
	 * Order: raw, stat, summary, patch
	 * or:    name/name-status/checkdiff (other bits clear)
	 */
3189 3190
	if (!q->nr)
		goto free_queue;
J
Junio C Hamano 已提交
3191

3192 3193 3194 3195
	if (output_format & (DIFF_FORMAT_RAW |
			     DIFF_FORMAT_NAME |
			     DIFF_FORMAT_NAME_STATUS |
			     DIFF_FORMAT_CHECKDIFF)) {
J
Junio C Hamano 已提交
3196 3197
		for (i = 0; i < q->nr; i++) {
			struct diff_filepair *p = q->queue[i];
3198 3199
			if (check_pair_status(p))
				flush_one_pair(p, options);
J
Junio C Hamano 已提交
3200
		}
3201
		separator++;
J
Junio C Hamano 已提交
3202
	}
3203

3204
	if (output_format & (DIFF_FORMAT_DIFFSTAT|DIFF_FORMAT_SHORTSTAT|DIFF_FORMAT_NUMSTAT)) {
3205
		struct diffstat_t diffstat;
3206

3207 3208
		memset(&diffstat, 0, sizeof(struct diffstat_t));
		diffstat.xm.consume = diffstat_consume;
J
Junio C Hamano 已提交
3209 3210
		for (i = 0; i < q->nr; i++) {
			struct diff_filepair *p = q->queue[i];
3211
			if (check_pair_status(p))
3212
				diff_flush_stat(p, options, &diffstat);
J
Junio C Hamano 已提交
3213
		}
J
Junio C Hamano 已提交
3214 3215 3216 3217
		if (output_format & DIFF_FORMAT_NUMSTAT)
			show_numstat(&diffstat, options);
		if (output_format & DIFF_FORMAT_DIFFSTAT)
			show_stats(&diffstat, options);
3218
		if (output_format & DIFF_FORMAT_SHORTSTAT)
3219
			show_shortstats(&diffstat, options);
3220
		free_diffstat_info(&diffstat);
3221
		separator++;
J
Junio C Hamano 已提交
3222
	}
3223 3224
	if (output_format & DIFF_FORMAT_DIRSTAT)
		show_dirstat(options);
J
Junio C Hamano 已提交
3225

3226
	if (output_format & DIFF_FORMAT_SUMMARY && !is_summary_empty(q)) {
3227
		for (i = 0; i < q->nr; i++)
3228
			diff_summary(options->file, q->queue[i]);
3229
		separator++;
J
Junio C Hamano 已提交
3230 3231
	}

3232
	if (output_format & DIFF_FORMAT_PATCH) {
3233
		if (separator) {
3234
			putc(options->line_termination, options->file);
3235 3236
			if (options->stat_sep) {
				/* attach patch instead of inline */
3237
				fputs(options->stat_sep, options->file);
3238
			}
3239 3240 3241 3242 3243 3244 3245
		}

		for (i = 0; i < q->nr; i++) {
			struct diff_filepair *p = q->queue[i];
			if (check_pair_status(p))
				diff_flush_patch(p, options);
		}
S
Sean 已提交
3246 3247
	}

3248 3249 3250
	if (output_format & DIFF_FORMAT_CALLBACK)
		options->format_callback(q, options, options->format_callback_data);

3251 3252
	for (i = 0; i < q->nr; i++)
		diff_free_filepair(q->queue[i]);
3253
free_queue:
J
Junio C Hamano 已提交
3254 3255 3256
	free(q->queue);
	q->queue = NULL;
	q->nr = q->alloc = 0;
3257 3258
	if (options->close_file)
		fclose(options->file);
J
Junio C Hamano 已提交
3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316
}

static void diffcore_apply_filter(const char *filter)
{
	int i;
	struct diff_queue_struct *q = &diff_queued_diff;
	struct diff_queue_struct outq;
	outq.queue = NULL;
	outq.nr = outq.alloc = 0;

	if (!filter)
		return;

	if (strchr(filter, DIFF_STATUS_FILTER_AON)) {
		int found;
		for (i = found = 0; !found && i < q->nr; i++) {
			struct diff_filepair *p = q->queue[i];
			if (((p->status == DIFF_STATUS_MODIFIED) &&
			     ((p->score &&
			       strchr(filter, DIFF_STATUS_FILTER_BROKEN)) ||
			      (!p->score &&
			       strchr(filter, DIFF_STATUS_MODIFIED)))) ||
			    ((p->status != DIFF_STATUS_MODIFIED) &&
			     strchr(filter, p->status)))
				found++;
		}
		if (found)
			return;

		/* otherwise we will clear the whole queue
		 * by copying the empty outq at the end of this
		 * function, but first clear the current entries
		 * in the queue.
		 */
		for (i = 0; i < q->nr; i++)
			diff_free_filepair(q->queue[i]);
	}
	else {
		/* Only the matching ones */
		for (i = 0; i < q->nr; i++) {
			struct diff_filepair *p = q->queue[i];

			if (((p->status == DIFF_STATUS_MODIFIED) &&
			     ((p->score &&
			       strchr(filter, DIFF_STATUS_FILTER_BROKEN)) ||
			      (!p->score &&
			       strchr(filter, DIFF_STATUS_MODIFIED)))) ||
			    ((p->status != DIFF_STATUS_MODIFIED) &&
			     strchr(filter, p->status)))
				diff_q(&outq, p);
			else
				diff_free_filepair(p);
		}
	}
	free(q->queue);
	*q = outq;
}

3317 3318 3319 3320
/* Check whether two filespecs with the same mode and size are identical */
static int diff_filespec_is_identical(struct diff_filespec *one,
				      struct diff_filespec *two)
{
3321 3322
	if (S_ISGITLINK(one->mode))
		return 0;
3323 3324 3325 3326 3327 3328 3329
	if (diff_populate_filespec(one, 0))
		return 0;
	if (diff_populate_filespec(two, 0))
		return 0;
	return !memcmp(one->data, two->data, one->size);
}

J
Junio C Hamano 已提交
3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360
static void diffcore_skip_stat_unmatch(struct diff_options *diffopt)
{
	int i;
	struct diff_queue_struct *q = &diff_queued_diff;
	struct diff_queue_struct outq;
	outq.queue = NULL;
	outq.nr = outq.alloc = 0;

	for (i = 0; i < q->nr; i++) {
		struct diff_filepair *p = q->queue[i];

		/*
		 * 1. Entries that come from stat info dirtyness
		 *    always have both sides (iow, not create/delete),
		 *    one side of the object name is unknown, with
		 *    the same mode and size.  Keep the ones that
		 *    do not match these criteria.  They have real
		 *    differences.
		 *
		 * 2. At this point, the file is known to be modified,
		 *    with the same mode and size, and the object
		 *    name of one side is unknown.  Need to inspect
		 *    the identical contents.
		 */
		if (!DIFF_FILE_VALID(p->one) || /* (1) */
		    !DIFF_FILE_VALID(p->two) ||
		    (p->one->sha1_valid && p->two->sha1_valid) ||
		    (p->one->mode != p->two->mode) ||
		    diff_populate_filespec(p->one, 1) ||
		    diff_populate_filespec(p->two, 1) ||
		    (p->one->size != p->two->size) ||
3361
		    !diff_filespec_is_identical(p->one, p->two)) /* (2) */
J
Junio C Hamano 已提交
3362 3363 3364 3365 3366 3367 3368
			diff_q(&outq, p);
		else {
			/*
			 * The caller can subtract 1 from skip_stat_unmatch
			 * to determine how many paths were dirty only
			 * due to stat info mismatch.
			 */
3369
			if (!DIFF_OPT_TST(diffopt, NO_INDEX))
3370
				diffopt->skip_stat_unmatch++;
J
Junio C Hamano 已提交
3371 3372 3373 3374 3375 3376 3377
			diff_free_filepair(p);
		}
	}
	free(q->queue);
	*q = outq;
}

J
Junio C Hamano 已提交
3378 3379
void diffcore_std(struct diff_options *options)
{
3380
	if (DIFF_OPT_TST(options, QUIET))
J
Junio C Hamano 已提交
3381
		return;
3382

3383
	if (options->skip_stat_unmatch && !DIFF_OPT_TST(options, FIND_COPIES_HARDER))
J
Junio C Hamano 已提交
3384
		diffcore_skip_stat_unmatch(options);
J
Junio C Hamano 已提交
3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396
	if (options->break_opt != -1)
		diffcore_break(options->break_opt);
	if (options->detect_rename)
		diffcore_rename(options);
	if (options->break_opt != -1)
		diffcore_merge_broken();
	if (options->pickaxe)
		diffcore_pickaxe(options->pickaxe, options->pickaxe_opts);
	if (options->orderfile)
		diffcore_order(options->orderfile);
	diff_resolve_rename_copy();
	diffcore_apply_filter(options->filter);
J
Junio C Hamano 已提交
3397

3398 3399 3400 3401
	if (diff_queued_diff.nr)
		DIFF_OPT_SET(options, HAS_CHANGES);
	else
		DIFF_OPT_CLR(options, HAS_CHANGES);
J
Junio C Hamano 已提交
3402 3403
}

J
Junio C Hamano 已提交
3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417
int diff_result_code(struct diff_options *opt, int status)
{
	int result = 0;
	if (!DIFF_OPT_TST(opt, EXIT_WITH_STATUS) &&
	    !(opt->output_format & DIFF_FORMAT_CHECKDIFF))
		return status;
	if (DIFF_OPT_TST(opt, EXIT_WITH_STATUS) &&
	    DIFF_OPT_TST(opt, HAS_CHANGES))
		result |= 01;
	if ((opt->output_format & DIFF_FORMAT_CHECKDIFF) &&
	    DIFF_OPT_TST(opt, CHECK_FAILED))
		result |= 02;
	return result;
}
J
Junio C Hamano 已提交
3418 3419 3420 3421

void diff_addremove(struct diff_options *options,
		    int addremove, unsigned mode,
		    const unsigned char *sha1,
D
Dmitry Potapov 已提交
3422
		    const char *concatpath)
J
Junio C Hamano 已提交
3423 3424 3425
{
	struct diff_filespec *one, *two;

3426 3427 3428
	if (DIFF_OPT_TST(options, IGNORE_SUBMODULES) && S_ISGITLINK(mode))
		return;

J
Junio C Hamano 已提交
3429 3430 3431 3432 3433 3434 3435
	/* This may look odd, but it is a preparation for
	 * feeding "there are unchanged files which should
	 * not produce diffs, but when you are doing copy
	 * detection you would need them, so here they are"
	 * entries to the diff-core.  They will be prefixed
	 * with something like '=' or '*' (I haven't decided
	 * which but should not make any difference).
J
Junio C Hamano 已提交
3436
	 * Feeding the same new and old to diff_change()
J
Junio C Hamano 已提交
3437 3438 3439 3440
	 * also has the same effect.
	 * Before the final output happens, they are pruned after
	 * merged into rename/copy pairs as appropriate.
	 */
3441
	if (DIFF_OPT_TST(options, REVERSE_DIFF))
J
Junio C Hamano 已提交
3442 3443 3444
		addremove = (addremove == '+' ? '-' :
			     addremove == '-' ? '+' : addremove);

3445 3446 3447 3448
	if (options->prefix &&
	    strncmp(concatpath, options->prefix, options->prefix_length))
		return;

J
Junio C Hamano 已提交
3449 3450 3451 3452 3453 3454 3455 3456 3457
	one = alloc_filespec(concatpath);
	two = alloc_filespec(concatpath);

	if (addremove != '+')
		fill_filespec(one, sha1, mode);
	if (addremove != '-')
		fill_filespec(two, sha1, mode);

	diff_queue(&diff_queued_diff, one, two);
3458
	DIFF_OPT_SET(options, HAS_CHANGES);
J
Junio C Hamano 已提交
3459 3460 3461 3462 3463 3464
}

void diff_change(struct diff_options *options,
		 unsigned old_mode, unsigned new_mode,
		 const unsigned char *old_sha1,
		 const unsigned char *new_sha1,
D
Dmitry Potapov 已提交
3465
		 const char *concatpath)
J
Junio C Hamano 已提交
3466 3467 3468
{
	struct diff_filespec *one, *two;

3469 3470 3471 3472
	if (DIFF_OPT_TST(options, IGNORE_SUBMODULES) && S_ISGITLINK(old_mode)
			&& S_ISGITLINK(new_mode))
		return;

3473
	if (DIFF_OPT_TST(options, REVERSE_DIFF)) {
J
Junio C Hamano 已提交
3474 3475 3476 3477 3478
		unsigned tmp;
		const unsigned char *tmp_c;
		tmp = old_mode; old_mode = new_mode; new_mode = tmp;
		tmp_c = old_sha1; old_sha1 = new_sha1; new_sha1 = tmp_c;
	}
3479 3480 3481 3482 3483

	if (options->prefix &&
	    strncmp(concatpath, options->prefix, options->prefix_length))
		return;

J
Junio C Hamano 已提交
3484 3485 3486 3487 3488 3489
	one = alloc_filespec(concatpath);
	two = alloc_filespec(concatpath);
	fill_filespec(one, old_sha1, old_mode);
	fill_filespec(two, new_sha1, new_mode);

	diff_queue(&diff_queued_diff, one, two);
3490
	DIFF_OPT_SET(options, HAS_CHANGES);
J
Junio C Hamano 已提交
3491 3492 3493
}

void diff_unmerge(struct diff_options *options,
3494 3495
		  const char *path,
		  unsigned mode, const unsigned char *sha1)
J
Junio C Hamano 已提交
3496 3497
{
	struct diff_filespec *one, *two;
3498 3499 3500 3501 3502

	if (options->prefix &&
	    strncmp(path, options->prefix, options->prefix_length))
		return;

J
Junio C Hamano 已提交
3503 3504
	one = alloc_filespec(path);
	two = alloc_filespec(path);
3505 3506
	fill_filespec(one, sha1, mode);
	diff_queue(&diff_queued_diff, one, two)->is_unmerged = 1;
J
Junio C Hamano 已提交
3507
}