dir.c 42.7 KB
Newer Older
1 2 3 4
/*
 * This handles recursive filename detection with exclude
 * files, index knowledge etc..
 *
5 6
 * See Documentation/technical/api-directory-listing.txt
 *
7 8 9 10 11
 * Copyright (C) Linus Torvalds, 2005-2006
 *		 Junio Hamano, 2005-2006
 */
#include "cache.h"
#include "dir.h"
12
#include "refs.h"
13
#include "wildmatch.h"
14
#include "pathspec.h"
15
#include "utf8.h"
16

17 18 19 20 21
struct path_simplify {
	int len;
	const char *path;
};

22 23 24 25 26 27 28 29 30 31 32 33 34 35 36
/*
 * Tells read_directory_recursive how a file or directory should be treated.
 * Values are ordered by significance, e.g. if a directory contains both
 * excluded and untracked files, it is listed as untracked because
 * path_untracked > path_excluded.
 */
enum path_treatment {
	path_none = 0,
	path_recurse,
	path_excluded,
	path_untracked
};

static enum path_treatment read_directory_recursive(struct dir_struct *dir,
	const char *path, int len,
37
	int check_only, const struct path_simplify *simplify);
38
static int get_dtype(struct dirent *de, const char *path, int len);
39

40 41 42 43 44 45 46 47 48 49 50 51 52
/* helper string functions with support for the ignore_case flag */
int strcmp_icase(const char *a, const char *b)
{
	return ignore_case ? strcasecmp(a, b) : strcmp(a, b);
}

int strncmp_icase(const char *a, const char *b, size_t count)
{
	return ignore_case ? strncasecmp(a, b, count) : strncmp(a, b, count);
}

int fnmatch_icase(const char *pattern, const char *string, int flags)
{
53 54 55
	return wildmatch(pattern, string,
			 flags | (ignore_case ? WM_CASEFOLD : 0),
			 NULL);
56 57
}

58 59 60
int git_fnmatch(const struct pathspec_item *item,
		const char *pattern, const char *string,
		int prefix)
61 62
{
	if (prefix > 0) {
63
		if (ps_strncmp(item, pattern, string, prefix))
64
			return WM_NOMATCH;
65 66 67
		pattern += prefix;
		string += prefix;
	}
68
	if (item->flags & PATHSPEC_ONESTAR) {
69 70 71
		int pattern_len = strlen(++pattern);
		int string_len = strlen(string);
		return string_len < pattern_len ||
72 73
			ps_strcmp(item, pattern,
				  string + string_len - pattern_len);
74
	}
75
	if (item->magic & PATHSPEC_GLOB)
76 77 78 79
		return wildmatch(pattern, string,
				 WM_PATHNAME |
				 (item->magic & PATHSPEC_ICASE ? WM_CASEFOLD : 0),
				 NULL);
80 81
	else
		/* wildmatch has not learned no FNM_PATHNAME mode yet */
82 83 84
		return wildmatch(pattern, string,
				 item->magic & PATHSPEC_ICASE ? WM_CASEFOLD : 0,
				 NULL);
85 86
}

87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105
static int fnmatch_icase_mem(const char *pattern, int patternlen,
			     const char *string, int stringlen,
			     int flags)
{
	int match_status;
	struct strbuf pat_buf = STRBUF_INIT;
	struct strbuf str_buf = STRBUF_INIT;
	const char *use_pat = pattern;
	const char *use_str = string;

	if (pattern[patternlen]) {
		strbuf_add(&pat_buf, pattern, patternlen);
		use_pat = pat_buf.buf;
	}
	if (string[stringlen]) {
		strbuf_add(&str_buf, string, stringlen);
		use_str = str_buf.buf;
	}

106 107 108
	if (ignore_case)
		flags |= WM_CASEFOLD;
	match_status = wildmatch(use_pat, use_str, flags, NULL);
109 110 111 112 113 114 115

	strbuf_release(&pat_buf);
	strbuf_release(&str_buf);

	return match_status;
}

116
static size_t common_prefix_len(const struct pathspec *pathspec)
117
{
118
	int n;
119
	size_t max = 0;
120

121 122 123 124 125 126 127
	/*
	 * ":(icase)path" is treated as a pathspec full of
	 * wildcard. In other words, only prefix is considered common
	 * prefix. If the pathspec is abc/foo abc/bar, running in
	 * subdir xyz, the common prefix is still xyz, not xuz/abc as
	 * in non-:(icase).
	 */
128 129 130
	GUARD_PATHSPEC(pathspec,
		       PATHSPEC_FROMTOP |
		       PATHSPEC_MAXDEPTH |
131
		       PATHSPEC_LITERAL |
132
		       PATHSPEC_GLOB |
133 134
		       PATHSPEC_ICASE |
		       PATHSPEC_EXCLUDE);
135

136
	for (n = 0; n < pathspec->nr; n++) {
137
		size_t i = 0, len = 0, item_len;
138 139
		if (pathspec->items[n].magic & PATHSPEC_EXCLUDE)
			continue;
140 141 142 143 144
		if (pathspec->items[n].magic & PATHSPEC_ICASE)
			item_len = pathspec->items[n].prefix;
		else
			item_len = pathspec->items[n].nowildcard_len;
		while (i < item_len && (n == 0 || i < max)) {
145 146
			char c = pathspec->items[n].match[i];
			if (c != pathspec->items[0].match[i])
147 148 149
				break;
			if (c == '/')
				len = i + 1;
150
			i++;
151
		}
152
		if (n == 0 || len < max) {
153 154 155 156
			max = len;
			if (!max)
				break;
		}
157
	}
158
	return max;
159 160
}

161 162 163 164
/*
 * Returns a copy of the longest leading path common among all
 * pathspecs.
 */
165
char *common_prefix(const struct pathspec *pathspec)
166 167 168
{
	unsigned long len = common_prefix_len(pathspec);

169
	return len ? xmemdupz(pathspec->items[0].match, len) : NULL;
170 171
}

172
int fill_directory(struct dir_struct *dir, const struct pathspec *pathspec)
173
{
174
	size_t len;
175 176 177 178 179

	/*
	 * Calculate common prefix for the pathspec, and
	 * use that to optimize the directory walk
	 */
180
	len = common_prefix_len(pathspec);
181 182

	/* Read the directory and prune it */
183
	read_directory(dir, pathspec->nr ? pathspec->_raw[0] : "", len, pathspec);
184
	return len;
185 186
}

187 188 189 190 191 192 193 194 195 196 197 198 199 200 201
int within_depth(const char *name, int namelen,
			int depth, int max_depth)
{
	const char *cp = name, *cpe = name + namelen;

	while (cp < cpe) {
		if (*cp++ != '/')
			continue;
		depth++;
		if (depth > max_depth)
			return 0;
	}
	return 1;
}

202
#define DO_MATCH_EXCLUDE   1
203
#define DO_MATCH_DIRECTORY 2
204

205 206 207 208 209 210 211 212 213 214 215 216 217
/*
 * Does 'match' match the given name?
 * A match is found if
 *
 * (1) the 'match' string is leading directory of 'name', or
 * (2) the 'match' string is a wildcard and matches 'name', or
 * (3) the 'match' string is exactly the same as 'name'.
 *
 * and the return value tells which case it was.
 *
 * It returns 0 when there is no match.
 */
static int match_pathspec_item(const struct pathspec_item *item, int prefix,
218
			       const char *name, int namelen, unsigned flags)
219 220 221 222 223
{
	/* name/namelen has prefix cut off by caller */
	const char *match = item->match + prefix;
	int matchlen = item->len - prefix;

224 225 226 227
	/*
	 * The normal call pattern is:
	 * 1. prefix = common_prefix_len(ps);
	 * 2. prune something, or fill_directory
228
	 * 3. match_pathspec()
229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256
	 *
	 * 'prefix' at #1 may be shorter than the command's prefix and
	 * it's ok for #2 to match extra files. Those extras will be
	 * trimmed at #3.
	 *
	 * Suppose the pathspec is 'foo' and '../bar' running from
	 * subdir 'xyz'. The common prefix at #1 will be empty, thanks
	 * to "../". We may have xyz/foo _and_ XYZ/foo after #2. The
	 * user does not want XYZ/foo, only the "foo" part should be
	 * case-insensitive. We need to filter out XYZ/foo here. In
	 * other words, we do not trust the caller on comparing the
	 * prefix part when :(icase) is involved. We do exact
	 * comparison ourselves.
	 *
	 * Normally the caller (common_prefix_len() in fact) does
	 * _exact_ matching on name[-prefix+1..-1] and we do not need
	 * to check that part. Be defensive and check it anyway, in
	 * case common_prefix_len is changed, or a new caller is
	 * introduced that does not use common_prefix_len.
	 *
	 * If the penalty turns out too high when prefix is really
	 * long, maybe change it to
	 * strncmp(match, name, item->prefix - prefix)
	 */
	if (item->prefix && (item->magic & PATHSPEC_ICASE) &&
	    strncmp(item->match, name - prefix, item->prefix))
		return 0;

257 258 259 260
	/* If the match was just the prefix, we matched */
	if (!*match)
		return MATCHED_RECURSIVELY;

261
	if (matchlen <= namelen && !ps_strncmp(item, match, name, matchlen)) {
262 263 264 265 266
		if (matchlen == namelen)
			return MATCHED_EXACTLY;

		if (match[matchlen-1] == '/' || name[matchlen] == '/')
			return MATCHED_RECURSIVELY;
267 268 269 270 271
	} else if ((flags & DO_MATCH_DIRECTORY) &&
		   match[matchlen - 1] == '/' &&
		   namelen == matchlen - 1 &&
		   !ps_strncmp(item, match, name, namelen))
		return MATCHED_EXACTLY;
272

273
	if (item->nowildcard_len < item->len &&
274
	    !git_fnmatch(item, match, name,
275
			 item->nowildcard_len - prefix))
276 277 278 279 280 281
		return MATCHED_FNMATCH;

	return 0;
}

/*
282 283 284 285 286 287 288 289 290 291 292 293 294
 * Given a name and a list of pathspecs, returns the nature of the
 * closest (i.e. most specific) match of the name to any of the
 * pathspecs.
 *
 * The caller typically calls this multiple times with the same
 * pathspec and seen[] array but with different name/namelen
 * (e.g. entries from the index) and is interested in seeing if and
 * how each pathspec matches all the names it calls this function
 * with.  A mark is left in the seen[] array for each pathspec element
 * indicating the closest type of match that element achieved, so if
 * seen[n] remains zero after multiple invocations, that means the nth
 * pathspec did not match any names, which could indicate that the
 * user mistyped the nth pathspec.
295
 */
296 297 298
static int do_match_pathspec(const struct pathspec *ps,
			     const char *name, int namelen,
			     int prefix, char *seen,
299
			     unsigned flags)
300
{
301
	int i, retval = 0, exclude = flags & DO_MATCH_EXCLUDE;
302

303 304 305
	GUARD_PATHSPEC(ps,
		       PATHSPEC_FROMTOP |
		       PATHSPEC_MAXDEPTH |
306
		       PATHSPEC_LITERAL |
307
		       PATHSPEC_GLOB |
308 309
		       PATHSPEC_ICASE |
		       PATHSPEC_EXCLUDE);
310

311
	if (!ps->nr) {
312 313 314
		if (!ps->recursive ||
		    !(ps->magic & PATHSPEC_MAXDEPTH) ||
		    ps->max_depth == -1)
315 316 317 318 319 320 321 322 323 324 325 326 327
			return MATCHED_RECURSIVELY;

		if (within_depth(name, namelen, 0, ps->max_depth))
			return MATCHED_EXACTLY;
		else
			return 0;
	}

	name += prefix;
	namelen -= prefix;

	for (i = ps->nr - 1; i >= 0; i--) {
		int how;
328 329 330 331 332

		if ((!exclude &&   ps->items[i].magic & PATHSPEC_EXCLUDE) ||
		    ( exclude && !(ps->items[i].magic & PATHSPEC_EXCLUDE)))
			continue;

333 334
		if (seen && seen[i] == MATCHED_EXACTLY)
			continue;
335 336 337 338 339 340
		/*
		 * Make exclude patterns optional and never report
		 * "pathspec ':(exclude)foo' matches no files"
		 */
		if (seen && ps->items[i].magic & PATHSPEC_EXCLUDE)
			seen[i] = MATCHED_FNMATCH;
341 342
		how = match_pathspec_item(ps->items+i, prefix, name,
					  namelen, flags);
343 344 345
		if (ps->recursive &&
		    (ps->magic & PATHSPEC_MAXDEPTH) &&
		    ps->max_depth != -1 &&
346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364
		    how && how != MATCHED_FNMATCH) {
			int len = ps->items[i].len;
			if (name[len] == '/')
				len++;
			if (within_depth(name+len, namelen-len, 0, ps->max_depth))
				how = MATCHED_EXACTLY;
			else
				how = 0;
		}
		if (how) {
			if (retval < how)
				retval = how;
			if (seen && seen[i] < how)
				seen[i] = how;
		}
	}
	return retval;
}

365 366
int match_pathspec(const struct pathspec *ps,
		   const char *name, int namelen,
367
		   int prefix, char *seen, int is_dir)
368 369
{
	int positive, negative;
370
	unsigned flags = is_dir ? DO_MATCH_DIRECTORY : 0;
371 372
	positive = do_match_pathspec(ps, name, namelen,
				     prefix, seen, flags);
373 374
	if (!(ps->magic & PATHSPEC_EXCLUDE) || !positive)
		return positive;
375 376 377
	negative = do_match_pathspec(ps, name, namelen,
				     prefix, seen,
				     flags | DO_MATCH_EXCLUDE);
378 379 380
	return negative ? 0 : positive;
}

381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423
int report_path_error(const char *ps_matched,
		      const struct pathspec *pathspec,
		      const char *prefix)
{
	/*
	 * Make sure all pathspec matched; otherwise it is an error.
	 */
	struct strbuf sb = STRBUF_INIT;
	int num, errors = 0;
	for (num = 0; num < pathspec->nr; num++) {
		int other, found_dup;

		if (ps_matched[num])
			continue;
		/*
		 * The caller might have fed identical pathspec
		 * twice.  Do not barf on such a mistake.
		 * FIXME: parse_pathspec should have eliminated
		 * duplicate pathspec.
		 */
		for (found_dup = other = 0;
		     !found_dup && other < pathspec->nr;
		     other++) {
			if (other == num || !ps_matched[other])
				continue;
			if (!strcmp(pathspec->items[other].original,
				    pathspec->items[num].original))
				/*
				 * Ok, we have a match already.
				 */
				found_dup = 1;
		}
		if (found_dup)
			continue;

		error("pathspec '%s' did not match any file(s) known to git.",
		      pathspec->items[num].original);
		errors++;
	}
	strbuf_release(&sb);
	return errors;
}

424 425 426
/*
 * Return the length of the "simple" part of a path match limiter.
 */
427
int simple_length(const char *match)
428 429 430 431 432 433 434 435 436 437 438
{
	int len = -1;

	for (;;) {
		unsigned char c = *match++;
		len++;
		if (c == '\0' || is_glob_special(c))
			return len;
	}
}

439
int no_wildcard(const char *string)
L
Lars Knoll 已提交
440
{
441
	return string[simple_length(string)] == '\0';
L
Lars Knoll 已提交
442 443
}

444 445 446 447
void parse_exclude_pattern(const char **pattern,
			   int *patternlen,
			   int *flags,
			   int *nowildcardlen)
448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481
{
	const char *p = *pattern;
	size_t i, len;

	*flags = 0;
	if (*p == '!') {
		*flags |= EXC_FLAG_NEGATIVE;
		p++;
	}
	len = strlen(p);
	if (len && p[len - 1] == '/') {
		len--;
		*flags |= EXC_FLAG_MUSTBEDIR;
	}
	for (i = 0; i < len; i++) {
		if (p[i] == '/')
			break;
	}
	if (i == len)
		*flags |= EXC_FLAG_NODIR;
	*nowildcardlen = simple_length(p);
	/*
	 * we should have excluded the trailing slash from 'p' too,
	 * but that's one more allocation. Instead just make sure
	 * nowildcardlen does not exceed real patternlen
	 */
	if (*nowildcardlen > len)
		*nowildcardlen = len;
	if (*p == '*' && no_wildcard(p + 1))
		*flags |= EXC_FLAG_ENDSWITH;
	*pattern = p;
	*patternlen = len;
}

482
void add_exclude(const char *string, const char *base,
483
		 int baselen, struct exclude_list *el, int srcpos)
484
{
485
	struct exclude *x;
486 487 488
	int patternlen;
	int flags;
	int nowildcardlen;
489

490 491
	parse_exclude_pattern(&string, &patternlen, &flags, &nowildcardlen);
	if (flags & EXC_FLAG_MUSTBEDIR) {
492
		char *s;
493
		x = xmalloc(sizeof(*x) + patternlen + 1);
494
		s = (char *)(x+1);
495 496
		memcpy(s, string, patternlen);
		s[patternlen] = '\0';
497 498 499 500 501
		x->pattern = s;
	} else {
		x = xmalloc(sizeof(*x));
		x->pattern = string;
	}
502 503
	x->patternlen = patternlen;
	x->nowildcardlen = nowildcardlen;
504 505
	x->base = base;
	x->baselen = baselen;
506
	x->flags = flags;
507
	x->srcpos = srcpos;
508 509
	ALLOC_GROW(el->excludes, el->nr + 1, el->alloc);
	el->excludes[el->nr++] = x;
510
	x->el = el;
511 512
}

513 514 515 516 517 518 519 520
static void *read_skip_worktree_file_from_index(const char *path, size_t *size)
{
	int pos, len;
	unsigned long sz;
	enum object_type type;
	void *data;

	len = strlen(path);
521
	pos = cache_name_pos(path, len);
522 523
	if (pos < 0)
		return NULL;
524
	if (!ce_skip_worktree(active_cache[pos]))
525
		return NULL;
526
	data = read_sha1_file(active_cache[pos]->sha1, &type, &sz);
527 528 529 530 531 532 533 534
	if (!data || type != OBJ_BLOB) {
		free(data);
		return NULL;
	}
	*size = xsize_t(sz);
	return data;
}

535 536 537 538 539
/*
 * Frees memory within el which was allocated for exclude patterns and
 * the file buffer.  Does not free el itself.
 */
void clear_exclude_list(struct exclude_list *el)
540 541 542 543 544 545
{
	int i;

	for (i = 0; i < el->nr; i++)
		free(el->excludes[i]);
	free(el->excludes);
546
	free(el->filebuf);
547 548 549

	el->nr = 0;
	el->excludes = NULL;
550
	el->filebuf = NULL;
551 552
}

553
static void trim_trailing_spaces(char *buf)
554
{
555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573
	char *p, *last_space = NULL;

	for (p = buf; *p; p++)
		switch (*p) {
		case ' ':
			if (!last_space)
				last_space = p;
			break;
		case '\\':
			p++;
			if (!*p)
				return;
			/* fallthrough */
		default:
			last_space = NULL;
		}

	if (last_space)
		*last_space = '\0';
574 575
}

576 577 578
int add_excludes_from_file_to_list(const char *fname,
				   const char *base,
				   int baselen,
579
				   struct exclude_list *el,
580
				   int check_index)
581
{
J
Jonas Fonseca 已提交
582
	struct stat st;
583
	int fd, i, lineno = 1;
584
	size_t size = 0;
585 586 587
	char *buf, *entry;

	fd = open(fname, O_RDONLY);
588
	if (fd < 0 || fstat(fd, &st) < 0) {
589
		if (errno != ENOENT)
590
			warn_on_inaccessible(fname);
591 592 593 594 595
		if (0 <= fd)
			close(fd);
		if (!check_index ||
		    (buf = read_skip_worktree_file_from_index(fname, &size)) == NULL)
			return -1;
596 597 598 599 600 601 602 603
		if (size == 0) {
			free(buf);
			return 0;
		}
		if (buf[size-1] != '\n') {
			buf = xrealloc(buf, size+1);
			buf[size++] = '\n';
		}
604
	} else {
605 606 607 608 609
		size = xsize_t(st.st_size);
		if (size == 0) {
			close(fd);
			return 0;
		}
610
		buf = xmalloc(size+1);
611
		if (read_in_full(fd, buf, size) != size) {
612
			free(buf);
613 614 615
			close(fd);
			return -1;
		}
616
		buf[size++] = '\n';
617
		close(fd);
李鸿 已提交
618
	}
619

620
	el->filebuf = buf;
621

622 623 624
	if (skip_utf8_bom(&buf, size))
		size -= buf - el->filebuf;

625
	entry = buf;
626

627 628
	for (i = 0; i < size; i++) {
		if (buf[i] == '\n') {
629 630
			if (entry != buf + i && entry[0] != '#') {
				buf[i - (i && buf[i-1] == '\r')] = 0;
631
				trim_trailing_spaces(entry);
632
				add_exclude(entry, base, baselen, el, lineno);
633
			}
634
			lineno++;
635 636 637 638 639 640
			entry = buf + i + 1;
		}
	}
	return 0;
}

641 642
struct exclude_list *add_exclude_list(struct dir_struct *dir,
				      int group_type, const char *src)
643 644 645 646 647 648 649 650
{
	struct exclude_list *el;
	struct exclude_list_group *group;

	group = &dir->exclude_list_group[group_type];
	ALLOC_GROW(group->el, group->nr + 1, group->alloc);
	el = &group->el[group->nr++];
	memset(el, 0, sizeof(*el));
651
	el->src = src;
652 653 654 655 656 657
	return el;
}

/*
 * Used to set up core.excludesfile and .git/info/exclude lists.
 */
658 659
void add_excludes_from_file(struct dir_struct *dir, const char *fname)
{
660
	struct exclude_list *el;
661
	el = add_exclude_list(dir, EXC_FILE, fname);
662
	if (add_excludes_from_file_to_list(fname, "", 0, el, 0) < 0)
663 664 665
		die("cannot use %s as an exclude file", fname);
}

666 667 668
int match_basename(const char *basename, int basenamelen,
		   const char *pattern, int prefix, int patternlen,
		   int flags)
669 670
{
	if (prefix == patternlen) {
671 672
		if (patternlen == basenamelen &&
		    !strncmp_icase(pattern, basename, basenamelen))
673 674
			return 1;
	} else if (flags & EXC_FLAG_ENDSWITH) {
675
		/* "*literal" matching against "fooliteral" */
676
		if (patternlen - 1 <= basenamelen &&
677 678 679
		    !strncmp_icase(pattern + 1,
				   basename + basenamelen - (patternlen - 1),
				   patternlen - 1))
680 681
			return 1;
	} else {
682 683 684
		if (fnmatch_icase_mem(pattern, patternlen,
				      basename, basenamelen,
				      0) == 0)
685 686 687 688 689
			return 1;
	}
	return 0;
}

690 691 692 693
int match_pathname(const char *pathname, int pathlen,
		   const char *base, int baselen,
		   const char *pattern, int prefix, int patternlen,
		   int flags)
694 695 696 697 698 699 700 701 702 703
{
	const char *name;
	int namelen;

	/*
	 * match with FNM_PATHNAME; the pattern has base implicitly
	 * in front of it.
	 */
	if (*pattern == '/') {
		pattern++;
704
		patternlen--;
705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730
		prefix--;
	}

	/*
	 * baselen does not count the trailing slash. base[] may or
	 * may not end with a trailing slash though.
	 */
	if (pathlen < baselen + 1 ||
	    (baselen && pathname[baselen] != '/') ||
	    strncmp_icase(pathname, base, baselen))
		return 0;

	namelen = baselen ? pathlen - baselen - 1 : pathlen;
	name = pathname + pathlen - namelen;

	if (prefix) {
		/*
		 * if the non-wildcard part is longer than the
		 * remaining pathname, surely it cannot match.
		 */
		if (prefix > namelen)
			return 0;

		if (strncmp_icase(pattern, name, prefix))
			return 0;
		pattern += prefix;
731
		patternlen -= prefix;
732 733
		name    += prefix;
		namelen -= prefix;
734 735 736 737 738 739 740 741

		/*
		 * If the whole pattern did not have a wildcard,
		 * then our prefix match is all we need; we
		 * do not need to call fnmatch at all.
		 */
		if (!patternlen && !namelen)
			return 1;
742 743
	}

744 745
	return fnmatch_icase_mem(pattern, patternlen,
				 name, namelen,
746
				 WM_PATHNAME) == 0;
747 748
}

749 750 751 752 753
/*
 * Scan the given exclude list in reverse to see whether pathname
 * should be ignored.  The first match (i.e. the last on the list), if
 * any, determines the fate.  Returns the exclude_list element which
 * matched, or NULL for undecided.
754
 */
755 756 757 758 759
static struct exclude *last_exclude_matching_from_list(const char *pathname,
						       int pathlen,
						       const char *basename,
						       int *dtype,
						       struct exclude_list *el)
760 761 762
{
	int i;

763
	if (!el->nr)
764
		return NULL;	/* undefined */
765

766 767
	for (i = el->nr - 1; 0 <= i; i--) {
		struct exclude *x = el->excludes[i];
768 769
		const char *exclude = x->pattern;
		int prefix = x->nowildcardlen;
770 771 772 773 774 775 776

		if (x->flags & EXC_FLAG_MUSTBEDIR) {
			if (*dtype == DT_UNKNOWN)
				*dtype = get_dtype(NULL, pathname, pathlen);
			if (*dtype != DT_DIR)
				continue;
		}
777

778
		if (x->flags & EXC_FLAG_NODIR) {
779 780 781 782
			if (match_basename(basename,
					   pathlen - (basename - pathname),
					   exclude, prefix, x->patternlen,
					   x->flags))
783
				return x;
784 785 786
			continue;
		}

787 788 789 790
		assert(x->baselen == 0 || x->base[x->baselen - 1] == '/');
		if (match_pathname(pathname, pathlen,
				   x->base, x->baselen ? x->baselen - 1 : 0,
				   exclude, prefix, x->patternlen, x->flags))
791
			return x;
792
	}
793 794 795 796 797 798 799 800 801 802 803 804 805 806 807
	return NULL; /* undecided */
}

/*
 * Scan the list and let the last match determine the fate.
 * Return 1 for exclude, 0 for include and -1 for undecided.
 */
int is_excluded_from_list(const char *pathname,
			  int pathlen, const char *basename, int *dtype,
			  struct exclude_list *el)
{
	struct exclude *exclude;
	exclude = last_exclude_matching_from_list(pathname, pathlen, basename, dtype, el);
	if (exclude)
		return exclude->flags & EXC_FLAG_NEGATIVE ? 0 : 1;
808 809 810
	return -1; /* undecided */
}

811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830
static struct exclude *last_exclude_matching_from_lists(struct dir_struct *dir,
		const char *pathname, int pathlen, const char *basename,
		int *dtype_p)
{
	int i, j;
	struct exclude_list_group *group;
	struct exclude *exclude;
	for (i = EXC_CMDL; i <= EXC_FILE; i++) {
		group = &dir->exclude_list_group[i];
		for (j = group->nr - 1; j >= 0; j--) {
			exclude = last_exclude_matching_from_list(
				pathname, pathlen, basename, dtype_p,
				&group->el[j]);
			if (exclude)
				return exclude;
		}
	}
	return NULL;
}

K
Karsten Blees 已提交
831 832 833 834 835 836 837 838 839 840 841 842 843
/*
 * Loads the per-directory exclude list for the substring of base
 * which has a char length of baselen.
 */
static void prep_exclude(struct dir_struct *dir, const char *base, int baselen)
{
	struct exclude_list_group *group;
	struct exclude_list *el;
	struct exclude_stack *stk = NULL;
	int current;

	group = &dir->exclude_list_group[EXC_DIRS];

844 845
	/*
	 * Pop the exclude lists from the EXCL_DIRS exclude_list_group
K
Karsten Blees 已提交
846
	 * which originate from directories not in the prefix of the
847 848
	 * path being checked.
	 */
K
Karsten Blees 已提交
849 850
	while ((stk = dir->exclude_stack) != NULL) {
		if (stk->baselen <= baselen &&
851
		    !strncmp(dir->basebuf.buf, base, stk->baselen))
K
Karsten Blees 已提交
852 853 854
			break;
		el = &group->el[dir->exclude_stack->exclude_ix];
		dir->exclude_stack = stk->prev;
855
		dir->exclude = NULL;
856
		free((char *)el->src); /* see strbuf_detach() below */
K
Karsten Blees 已提交
857 858 859 860 861
		clear_exclude_list(el);
		free(stk);
		group->nr--;
	}

862 863 864 865
	/* Skip traversing into sub directories if the parent is excluded */
	if (dir->exclude)
		return;

866 867 868 869 870 871 872 873
	/*
	 * Lazy initialization. All call sites currently just
	 * memset(dir, 0, sizeof(*dir)) before use. Changing all of
	 * them seems lots of work for little benefit.
	 */
	if (!dir->basebuf.buf)
		strbuf_init(&dir->basebuf, PATH_MAX);

K
Karsten Blees 已提交
874 875
	/* Read from the parent directories and push them down. */
	current = stk ? stk->baselen : -1;
876
	strbuf_setlen(&dir->basebuf, current < 0 ? 0 : current);
K
Karsten Blees 已提交
877 878 879
	while (current < baselen) {
		const char *cp;

880
		stk = xcalloc(1, sizeof(*stk));
K
Karsten Blees 已提交
881 882 883
		if (current < 0) {
			cp = base;
			current = 0;
884
		} else {
K
Karsten Blees 已提交
885 886 887 888 889 890 891
			cp = strchr(base + current + 1, '/');
			if (!cp)
				die("oops in prep_exclude");
			cp++;
		}
		stk->prev = dir->exclude_stack;
		stk->baselen = cp - base;
892 893
		stk->exclude_ix = group->nr;
		el = add_exclude_list(dir, EXC_DIRS, NULL);
894 895
		strbuf_add(&dir->basebuf, base + current, stk->baselen - current);
		assert(stk->baselen == dir->basebuf.len);
896 897 898 899

		/* Abort if the directory is excluded */
		if (stk->baselen) {
			int dt = DT_DIR;
900
			dir->basebuf.buf[stk->baselen - 1] = 0;
901
			dir->exclude = last_exclude_matching_from_lists(dir,
902 903 904
				dir->basebuf.buf, stk->baselen - 1,
				dir->basebuf.buf + current, &dt);
			dir->basebuf.buf[stk->baselen - 1] = '/';
905 906 907
			if (dir->exclude &&
			    dir->exclude->flags & EXC_FLAG_NEGATIVE)
				dir->exclude = NULL;
908 909 910 911 912 913
			if (dir->exclude) {
				dir->exclude_stack = stk;
				return;
			}
		}

914 915
		/* Try to read per-directory file */
		if (dir->exclude_per_dir) {
916 917 918 919 920 921
			/*
			 * dir->basebuf gets reused by the traversal, but we
			 * need fname to remain unchanged to ensure the src
			 * member of each struct exclude correctly
			 * back-references its source file.  Other invocations
			 * of add_exclude_list provide stable strings, so we
922
			 * strbuf_detach() and free() here in the caller.
923
			 */
924 925 926 927 928 929
			struct strbuf sb = STRBUF_INIT;
			strbuf_addbuf(&sb, &dir->basebuf);
			strbuf_addstr(&sb, dir->exclude_per_dir);
			el->src = strbuf_detach(&sb, NULL);
			add_excludes_from_file_to_list(el->src, el->src,
						       stk->baselen, el, 1);
930
		}
K
Karsten Blees 已提交
931 932 933
		dir->exclude_stack = stk;
		current = stk->baselen;
	}
934
	strbuf_setlen(&dir->basebuf, baselen);
K
Karsten Blees 已提交
935 936
}

A
Adam Spiers 已提交
937 938 939 940 941 942
/*
 * Loads the exclude lists for the directory containing pathname, then
 * scans all exclude lists to determine whether pathname is excluded.
 * Returns the exclude_list element which matched, or NULL for
 * undecided.
 */
943
struct exclude *last_exclude_matching(struct dir_struct *dir,
A
Adam Spiers 已提交
944 945
					     const char *pathname,
					     int *dtype_p)
946 947
{
	int pathlen = strlen(pathname);
L
Lars Knoll 已提交
948 949
	const char *basename = strrchr(pathname, '/');
	basename = (basename) ? basename+1 : pathname;
950

951
	prep_exclude(dir, pathname, basename-pathname);
952

953 954 955
	if (dir->exclude)
		return dir->exclude;

956 957
	return last_exclude_matching_from_lists(dir, pathname, pathlen,
			basename, dtype_p);
A
Adam Spiers 已提交
958 959 960 961 962 963 964
}

/*
 * Loads the exclude lists for the directory containing pathname, then
 * scans all exclude lists to determine whether pathname is excluded.
 * Returns 1 if true, otherwise 0.
 */
965
int is_excluded(struct dir_struct *dir, const char *pathname, int *dtype_p)
A
Adam Spiers 已提交
966 967 968 969 970
{
	struct exclude *exclude =
		last_exclude_matching(dir, pathname, dtype_p);
	if (exclude)
		return exclude->flags & EXC_FLAG_NEGATIVE ? 0 : 1;
971 972 973
	return 0;
}

974 975
static struct dir_entry *dir_entry_new(const char *pathname, int len)
{
976 977 978 979 980 981
	struct dir_entry *ent;

	ent = xmalloc(sizeof(*ent) + len + 1);
	ent->len = len;
	memcpy(ent->name, pathname, len);
	ent->name[len] = 0;
J
Junio C Hamano 已提交
982
	return ent;
983 984
}

985
static struct dir_entry *dir_add_name(struct dir_struct *dir, const char *pathname, int len)
J
Jeff King 已提交
986
{
987
	if (cache_file_exists(pathname, len, ignore_case))
J
Jeff King 已提交
988 989
		return NULL;

990
	ALLOC_GROW(dir->entries, dir->nr+1, dir->alloc);
J
Jeff King 已提交
991 992 993
	return dir->entries[dir->nr++] = dir_entry_new(pathname, len);
}

994
struct dir_entry *dir_add_ignored(struct dir_struct *dir, const char *pathname, int len)
995
{
996
	if (!cache_name_is_other(pathname, len))
997 998
		return NULL;

999
	ALLOC_GROW(dir->ignored, dir->ignored_nr+1, dir->ignored_alloc);
1000 1001 1002
	return dir->ignored[dir->ignored_nr++] = dir_entry_new(pathname, len);
}

1003 1004 1005
enum exist_status {
	index_nonexistent = 0,
	index_directory,
1006
	index_gitdir
1007 1008
};

1009
/*
1010
 * Do not use the alphabetically sorted index to look up
1011
 * the directory name; instead, use the case insensitive
1012
 * directory hash.
1013 1014 1015
 */
static enum exist_status directory_exists_in_index_icase(const char *dirname, int len)
{
1016
	const struct cache_entry *ce = cache_dir_exists(dirname, len);
1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041
	unsigned char endchar;

	if (!ce)
		return index_nonexistent;
	endchar = ce->name[len];

	/*
	 * The cache_entry structure returned will contain this dirname
	 * and possibly additional path components.
	 */
	if (endchar == '/')
		return index_directory;

	/*
	 * If there are no additional path components, then this cache_entry
	 * represents a submodule.  Submodules, despite being directories,
	 * are stored in the cache without a closing slash.
	 */
	if (!endchar && S_ISGITLINK(ce->ce_mode))
		return index_gitdir;

	/* This should never be hit, but it exists just in case. */
	return index_nonexistent;
}

1042 1043 1044 1045 1046 1047 1048 1049
/*
 * The index sorts alphabetically by entry name, which
 * means that a gitlink sorts as '\0' at the end, while
 * a directory (which is defined not as an entry, but as
 * the files it contains) will sort with the '/' at the
 * end.
 */
static enum exist_status directory_exists_in_index(const char *dirname, int len)
1050
{
1051 1052 1053 1054 1055 1056
	int pos;

	if (ignore_case)
		return directory_exists_in_index_icase(dirname, len);

	pos = cache_name_pos(dirname, len);
1057 1058 1059
	if (pos < 0)
		pos = -pos-1;
	while (pos < active_nr) {
1060
		const struct cache_entry *ce = active_cache[pos++];
1061 1062 1063 1064 1065 1066 1067 1068 1069
		unsigned char endchar;

		if (strncmp(ce->name, dirname, len))
			break;
		endchar = ce->name[len];
		if (endchar > '/')
			break;
		if (endchar == '/')
			return index_directory;
1070
		if (!endchar && S_ISGITLINK(ce->ce_mode))
1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088
			return index_gitdir;
	}
	return index_nonexistent;
}

/*
 * When we find a directory when traversing the filesystem, we
 * have three distinct cases:
 *
 *  - ignore it
 *  - see it as a directory
 *  - recurse into it
 *
 * and which one we choose depends on a combination of existing
 * git index contents and the flags passed into the directory
 * traversal routine.
 *
 * Case 1: If we *already* have entries in the index under that
1089 1090
 * directory name, we always recurse into the directory to see
 * all the files.
1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101
 *
 * Case 2: If we *already* have that directory name as a gitlink,
 * we always continue to see it as a gitlink, regardless of whether
 * there is an actual git directory there or not (it might not
 * be checked out as a subproject!)
 *
 * Case 3: if we didn't have it in the index previously, we
 * have a few sub-cases:
 *
 *  (a) if "show_other_directories" is true, we show it as
 *      just a directory, unless "hide_empty_directories" is
1102 1103
 *      also true, in which case we need to check if it contains any
 *      untracked and / or ignored files.
1104
 *  (b) if it looks like a git directory, and we don't have
M
Martin Waitz 已提交
1105
 *      'no_gitlinks' set we treat it as a gitlink, and show it
1106 1107 1108
 *      as a directory.
 *  (c) otherwise, we recurse into it.
 */
1109
static enum path_treatment treat_directory(struct dir_struct *dir,
1110
	const char *dirname, int len, int exclude,
1111 1112 1113 1114 1115
	const struct path_simplify *simplify)
{
	/* The "len-1" is to strip the final '/' */
	switch (directory_exists_in_index(dirname, len-1)) {
	case index_directory:
1116
		return path_recurse;
1117 1118

	case index_gitdir:
1119
		return path_none;
1120 1121

	case index_nonexistent:
1122
		if (dir->flags & DIR_SHOW_OTHER_DIRECTORIES)
1123
			break;
1124
		if (!(dir->flags & DIR_NO_GITLINKS)) {
1125 1126
			unsigned char sha1[20];
			if (resolve_gitlink_ref(dirname, "HEAD", sha1) == 0)
1127
				return path_untracked;
1128
		}
1129
		return path_recurse;
1130 1131 1132
	}

	/* This is the "show_other_directories" case */
1133

1134
	if (!(dir->flags & DIR_HIDE_EMPTY_DIRECTORIES))
1135 1136 1137
		return exclude ? path_excluded : path_untracked;

	return read_directory_recursive(dir, dirname, len, 1, simplify);
1138 1139
}

1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164
/*
 * This is an inexact early pruning of any recursive directory
 * reading - if the path cannot possibly be in the pathspec,
 * return true, and we'll skip it early.
 */
static int simplify_away(const char *path, int pathlen, const struct path_simplify *simplify)
{
	if (simplify) {
		for (;;) {
			const char *match = simplify->path;
			int len = simplify->len;

			if (!match)
				break;
			if (len > pathlen)
				len = pathlen;
			if (!memcmp(path, match, len))
				return 0;
			simplify++;
		}
		return 1;
	}
	return 0;
}

1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177
/*
 * This function tells us whether an excluded path matches a
 * list of "interesting" pathspecs. That is, whether a path matched
 * by any of the pathspecs could possibly be ignored by excluding
 * the specified path. This can happen if:
 *
 *   1. the path is mentioned explicitly in the pathspec
 *
 *   2. the path is a directory prefix of some element in the
 *      pathspec
 */
static int exclude_matches_pathspec(const char *path, int len,
		const struct path_simplify *simplify)
1178 1179 1180 1181 1182 1183
{
	if (simplify) {
		for (; simplify->path; simplify++) {
			if (len == simplify->len
			    && !memcmp(path, simplify->path, len))
				return 1;
1184 1185 1186 1187
			if (len < simplify->len
			    && simplify->path[len] == '/'
			    && !memcmp(path, simplify->path, len))
				return 1;
1188 1189 1190 1191 1192
		}
	}
	return 0;
}

1193 1194 1195
static int get_index_dtype(const char *path, int len)
{
	int pos;
1196
	const struct cache_entry *ce;
1197

1198
	ce = cache_file_exists(path, len, 0);
1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230
	if (ce) {
		if (!ce_uptodate(ce))
			return DT_UNKNOWN;
		if (S_ISGITLINK(ce->ce_mode))
			return DT_DIR;
		/*
		 * Nobody actually cares about the
		 * difference between DT_LNK and DT_REG
		 */
		return DT_REG;
	}

	/* Try to look it up as a directory */
	pos = cache_name_pos(path, len);
	if (pos >= 0)
		return DT_UNKNOWN;
	pos = -pos-1;
	while (pos < active_nr) {
		ce = active_cache[pos++];
		if (strncmp(ce->name, path, len))
			break;
		if (ce->name[len] > '/')
			break;
		if (ce->name[len] < '/')
			continue;
		if (!ce_uptodate(ce))
			break;	/* continue? */
		return DT_DIR;
	}
	return DT_UNKNOWN;
}

1231
static int get_dtype(struct dirent *de, const char *path, int len)
1232
{
J
Junio C Hamano 已提交
1233
	int dtype = de ? DTYPE(de) : DT_UNKNOWN;
1234 1235 1236 1237
	struct stat st;

	if (dtype != DT_UNKNOWN)
		return dtype;
1238 1239 1240 1241
	dtype = get_index_dtype(path, len);
	if (dtype != DT_UNKNOWN)
		return dtype;
	if (lstat(path, &st))
1242 1243 1244 1245 1246 1247 1248 1249 1250 1251
		return dtype;
	if (S_ISREG(st.st_mode))
		return DT_REG;
	if (S_ISDIR(st.st_mode))
		return DT_DIR;
	if (S_ISLNK(st.st_mode))
		return DT_LNK;
	return dtype;
}

1252
static enum path_treatment treat_one_path(struct dir_struct *dir,
R
René Scharfe 已提交
1253
					  struct strbuf *path,
1254 1255
					  const struct path_simplify *simplify,
					  int dtype, struct dirent *de)
1256
{
1257
	int exclude;
1258
	int has_path_in_index = !!cache_file_exists(path->buf, path->len, ignore_case);
1259

1260 1261 1262 1263
	if (dtype == DT_UNKNOWN)
		dtype = get_dtype(de, path->buf, path->len);

	/* Always exclude indexed files */
1264
	if (dtype != DT_DIR && has_path_in_index)
1265
		return path_none;
1266

1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286
	/*
	 * When we are looking at a directory P in the working tree,
	 * there are three cases:
	 *
	 * (1) P exists in the index.  Everything inside the directory P in
	 * the working tree needs to go when P is checked out from the
	 * index.
	 *
	 * (2) P does not exist in the index, but there is P/Q in the index.
	 * We know P will stay a directory when we check out the contents
	 * of the index, but we do not know yet if there is a directory
	 * P/Q in the working tree to be killed, so we need to recurse.
	 *
	 * (3) P does not exist in the index, and there is no P/Q in the index
	 * to require P to be a directory, either.  Only in this case, we
	 * know that everything inside P will not be killed without
	 * recursing.
	 */
	if ((dir->flags & DIR_COLLECT_KILLED_ONLY) &&
	    (dtype == DT_DIR) &&
1287 1288 1289
	    !has_path_in_index &&
	    (directory_exists_in_index(path->buf, path->len) == index_nonexistent))
		return path_none;
1290 1291

	exclude = is_excluded(dir, path->buf, &dtype);
1292 1293 1294 1295 1296

	/*
	 * Excluded? If we don't explicitly want to show
	 * ignored files, ignore it
	 */
1297
	if (exclude && !(dir->flags & (DIR_SHOW_IGNORED|DIR_SHOW_IGNORED_TOO)))
1298
		return path_excluded;
1299 1300 1301

	switch (dtype) {
	default:
1302
		return path_none;
1303
	case DT_DIR:
R
René Scharfe 已提交
1304
		strbuf_addch(path, '/');
1305 1306
		return treat_directory(dir, path->buf, path->len, exclude,
			simplify);
1307 1308
	case DT_REG:
	case DT_LNK:
1309
		return exclude ? path_excluded : path_untracked;
1310 1311 1312
	}
}

1313 1314
static enum path_treatment treat_path(struct dir_struct *dir,
				      struct dirent *de,
R
René Scharfe 已提交
1315
				      struct strbuf *path,
1316
				      int baselen,
R
René Scharfe 已提交
1317
				      const struct path_simplify *simplify)
1318 1319 1320 1321
{
	int dtype;

	if (is_dot_or_dotdot(de->d_name) || !strcmp(de->d_name, ".git"))
1322
		return path_none;
R
René Scharfe 已提交
1323 1324 1325
	strbuf_setlen(path, baselen);
	strbuf_addstr(path, de->d_name);
	if (simplify_away(path->buf, path->len, simplify))
1326
		return path_none;
1327 1328

	dtype = DTYPE(de);
R
René Scharfe 已提交
1329
	return treat_one_path(dir, path, simplify, dtype, de);
1330 1331
}

1332 1333 1334 1335 1336 1337 1338 1339
/*
 * Read a directory tree. We currently ignore anything but
 * directories, regular files and symlinks. That's because git
 * doesn't handle them at all yet. Maybe that will change some
 * day.
 *
 * Also, we ignore the name ".git" (even if it is not a directory).
 * That likely will not change.
1340 1341
 *
 * Returns the most significant path_treatment value encountered in the scan.
1342
 */
1343
static enum path_treatment read_directory_recursive(struct dir_struct *dir,
1344 1345 1346
				    const char *base, int baselen,
				    int check_only,
				    const struct path_simplify *simplify)
1347
{
1348
	DIR *fdir;
1349
	enum path_treatment state, subdir_state, dir_state = path_none;
1350
	struct dirent *de;
1351
	struct strbuf path = STRBUF_INIT;
1352

1353
	strbuf_add(&path, base, baselen);
1354

1355 1356 1357 1358
	fdir = opendir(path.len ? path.buf : ".");
	if (!fdir)
		goto out;

1359
	while ((de = readdir(fdir)) != NULL) {
1360 1361 1362 1363 1364 1365 1366 1367
		/* check how the file or directory should be treated */
		state = treat_path(dir, de, &path, baselen, simplify);
		if (state > dir_state)
			dir_state = state;

		/* recurse into subdir if instructed by treat_path */
		if (state == path_recurse) {
			subdir_state = read_directory_recursive(dir, path.buf,
1368
				path.len, check_only, simplify);
1369 1370 1371 1372 1373 1374 1375 1376 1377
			if (subdir_state > dir_state)
				dir_state = subdir_state;
		}

		if (check_only) {
			/* abort early if maximum state has been reached */
			if (dir_state == path_untracked)
				break;
			/* skip the dir_add_* part */
1378
			continue;
1379
		}
1380 1381 1382 1383 1384 1385

		/* add the path to the appropriate result list */
		switch (state) {
		case path_excluded:
			if (dir->flags & DIR_SHOW_IGNORED)
				dir_add_name(dir, path.buf, path.len);
1386 1387 1388 1389 1390
			else if ((dir->flags & DIR_SHOW_IGNORED_TOO) ||
				((dir->flags & DIR_COLLECT_IGNORED) &&
				exclude_matches_pathspec(path.buf, path.len,
					simplify)))
				dir_add_ignored(dir, path.buf, path.len);
1391 1392 1393 1394 1395
			break;

		case path_untracked:
			if (!(dir->flags & DIR_SHOW_IGNORED))
				dir_add_name(dir, path.buf, path.len);
1396
			break;
1397 1398 1399 1400

		default:
			break;
		}
1401
	}
1402
	closedir(fdir);
1403
 out:
1404
	strbuf_release(&path);
1405

1406
	return dir_state;
1407 1408 1409 1410 1411 1412 1413
}

static int cmp_name(const void *p1, const void *p2)
{
	const struct dir_entry *e1 = *(const struct dir_entry **)p1;
	const struct dir_entry *e2 = *(const struct dir_entry **)p2;

1414
	return name_compare(e1->name, e1->len, e2->name, e2->len);
1415 1416
}

1417 1418 1419 1420 1421 1422 1423 1424 1425 1426
static struct path_simplify *create_simplify(const char **pathspec)
{
	int nr, alloc = 0;
	struct path_simplify *simplify = NULL;

	if (!pathspec)
		return NULL;

	for (nr = 0 ; ; nr++) {
		const char *match;
1427
		ALLOC_GROW(simplify, nr + 1, alloc);
1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440
		match = *pathspec++;
		if (!match)
			break;
		simplify[nr].path = match;
		simplify[nr].len = simple_length(match);
	}
	simplify[nr].path = NULL;
	simplify[nr].len = 0;
	return simplify;
}

static void free_simplify(struct path_simplify *simplify)
{
1441
	free(simplify);
1442 1443
}

1444 1445 1446 1447
static int treat_leading_path(struct dir_struct *dir,
			      const char *path, int len,
			      const struct path_simplify *simplify)
{
R
René Scharfe 已提交
1448 1449
	struct strbuf sb = STRBUF_INIT;
	int baselen, rc = 0;
1450
	const char *cp;
1451
	int old_flags = dir->flags;
1452 1453 1454 1455 1456 1457

	while (len && path[len - 1] == '/')
		len--;
	if (!len)
		return 1;
	baselen = 0;
1458
	dir->flags &= ~DIR_SHOW_OTHER_DIRECTORIES;
1459 1460 1461 1462 1463 1464 1465
	while (1) {
		cp = path + baselen + !!baselen;
		cp = memchr(cp, '/', path + len - cp);
		if (!cp)
			baselen = len;
		else
			baselen = cp - path;
R
René Scharfe 已提交
1466 1467 1468 1469 1470 1471 1472
		strbuf_setlen(&sb, 0);
		strbuf_add(&sb, path, baselen);
		if (!is_directory(sb.buf))
			break;
		if (simplify_away(sb.buf, sb.len, simplify))
			break;
		if (treat_one_path(dir, &sb, simplify,
1473
				   DT_DIR, NULL) == path_none)
R
René Scharfe 已提交
1474 1475 1476 1477 1478
			break; /* do not recurse into it */
		if (len <= baselen) {
			rc = 1;
			break; /* finished checking */
		}
1479
	}
R
René Scharfe 已提交
1480
	strbuf_release(&sb);
1481
	dir->flags = old_flags;
R
René Scharfe 已提交
1482
	return rc;
1483 1484
}

1485
int read_directory(struct dir_struct *dir, const char *path, int len, const struct pathspec *pathspec)
1486
{
1487
	struct path_simplify *simplify;
1488

1489 1490 1491 1492
	/*
	 * Check out create_simplify()
	 */
	if (pathspec)
1493 1494 1495
		GUARD_PATHSPEC(pathspec,
			       PATHSPEC_FROMTOP |
			       PATHSPEC_MAXDEPTH |
1496
			       PATHSPEC_LITERAL |
1497
			       PATHSPEC_GLOB |
1498 1499
			       PATHSPEC_ICASE |
			       PATHSPEC_EXCLUDE);
1500

1501
	if (has_symlink_leading_path(path, len))
1502 1503
		return dir->nr;

1504 1505 1506 1507 1508 1509
	/*
	 * exclude patterns are treated like positive ones in
	 * create_simplify. Usually exclude patterns should be a
	 * subset of positive ones, which has no impacts on
	 * create_simplify().
	 */
1510
	simplify = create_simplify(pathspec ? pathspec->_raw : NULL);
1511 1512
	if (!len || treat_leading_path(dir, path, len, simplify))
		read_directory_recursive(dir, path, len, 0, simplify);
1513
	free_simplify(simplify);
1514
	qsort(dir->entries, dir->nr, sizeof(struct dir_entry *), cmp_name);
1515
	qsort(dir->ignored, dir->ignored_nr, sizeof(struct dir_entry *), cmp_name);
1516 1517
	return dir->nr;
}
1518

J
Junio C Hamano 已提交
1519
int file_exists(const char *f)
1520
{
J
Junio C Hamano 已提交
1521
	struct stat sb;
1522
	return lstat(f, &sb) == 0;
1523
}
1524 1525

/*
1526 1527 1528
 * Given two normalized paths (a trailing slash is ok), if subdir is
 * outside dir, return -1.  Otherwise return the offset in subdir that
 * can be used as relative path to dir.
1529
 */
1530
int dir_inside_of(const char *subdir, const char *dir)
1531
{
1532
	int offset = 0;
1533

1534
	assert(dir && subdir && *dir && *subdir);
1535

1536
	while (*dir && *subdir && *dir == *subdir) {
1537
		dir++;
1538 1539
		subdir++;
		offset++;
1540
	}
1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554

	/* hel[p]/me vs hel[l]/yeah */
	if (*dir && *subdir)
		return -1;

	if (!*subdir)
		return !*dir ? offset : -1; /* same dir */

	/* foo/[b]ar vs foo/[] */
	if (is_dir_sep(dir[-1]))
		return is_dir_sep(subdir[-1]) ? offset : -1;

	/* foo[/]bar vs foo[] */
	return is_dir_sep(*subdir) ? offset + 1 : -1;
1555 1556 1557 1558
}

int is_inside_dir(const char *dir)
{
1559 1560 1561
	char *cwd;
	int rc;

1562 1563
	if (!dir)
		return 0;
1564 1565 1566 1567 1568

	cwd = xgetcwd();
	rc = (dir_inside_of(cwd, dir) >= 0);
	free(cwd);
	return rc;
1569
}
1570

1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589
int is_empty_dir(const char *path)
{
	DIR *dir = opendir(path);
	struct dirent *e;
	int ret = 1;

	if (!dir)
		return 0;

	while ((e = readdir(dir)) != NULL)
		if (!is_dot_or_dotdot(e->d_name)) {
			ret = 0;
			break;
		}

	closedir(dir);
	return ret;
}

1590
static int remove_dir_recurse(struct strbuf *path, int flag, int *kept_up)
1591
{
1592
	DIR *dir;
1593
	struct dirent *e;
1594
	int ret = 0, original_len = path->len, len, kept_down = 0;
1595
	int only_empty = (flag & REMOVE_DIR_EMPTY_ONLY);
1596
	int keep_toplevel = (flag & REMOVE_DIR_KEEP_TOPLEVEL);
1597
	unsigned char submodule_head[20];
1598

1599
	if ((flag & REMOVE_DIR_KEEP_NESTED_GIT) &&
1600
	    !resolve_gitlink_ref(path->buf, "HEAD", submodule_head)) {
1601
		/* Do not descend and nuke a nested git work tree. */
1602 1603
		if (kept_up)
			*kept_up = 1;
1604
		return 0;
1605
	}
1606

1607
	flag &= ~REMOVE_DIR_KEEP_TOPLEVEL;
1608
	dir = opendir(path->buf);
1609
	if (!dir) {
1610 1611 1612
		if (errno == ENOENT)
			return keep_toplevel ? -1 : 0;
		else if (errno == EACCES && !keep_toplevel)
1613 1614 1615 1616
			/*
			 * An empty dir could be removable even if it
			 * is unreadable:
			 */
1617 1618 1619 1620
			return rmdir(path->buf);
		else
			return -1;
	}
1621 1622 1623 1624 1625 1626
	if (path->buf[original_len - 1] != '/')
		strbuf_addch(path, '/');

	len = path->len;
	while ((e = readdir(dir)) != NULL) {
		struct stat st;
1627 1628
		if (is_dot_or_dotdot(e->d_name))
			continue;
1629 1630 1631

		strbuf_setlen(path, len);
		strbuf_addstr(path, e->d_name);
1632 1633 1634 1635 1636 1637 1638 1639 1640
		if (lstat(path->buf, &st)) {
			if (errno == ENOENT)
				/*
				 * file disappeared, which is what we
				 * wanted anyway
				 */
				continue;
			/* fall thru */
		} else if (S_ISDIR(st.st_mode)) {
1641
			if (!remove_dir_recurse(path, flag, &kept_down))
1642
				continue; /* happy */
1643 1644
		} else if (!only_empty &&
			   (!unlink(path->buf) || errno == ENOENT)) {
1645
			continue; /* happy, too */
1646
		}
1647 1648 1649 1650 1651 1652 1653 1654

		/* path too long, stat fails, or non-directory still exists */
		ret = -1;
		break;
	}
	closedir(dir);

	strbuf_setlen(path, original_len);
1655
	if (!ret && !keep_toplevel && !kept_down)
1656
		ret = (!rmdir(path->buf) || errno == ENOENT) ? 0 : -1;
1657 1658 1659 1660 1661 1662
	else if (kept_up)
		/*
		 * report the uplevel that it is not an error that we
		 * did not rmdir() our directory.
		 */
		*kept_up = !ret;
1663 1664
	return ret;
}
J
Junio C Hamano 已提交
1665

1666 1667 1668 1669 1670
int remove_dir_recursively(struct strbuf *path, int flag)
{
	return remove_dir_recurse(path, flag, NULL);
}

J
Junio C Hamano 已提交
1671 1672 1673
void setup_standard_excludes(struct dir_struct *dir)
{
	const char *path;
1674
	char *xdg_path;
J
Junio C Hamano 已提交
1675 1676 1677

	dir->exclude_per_dir = ".gitignore";
	path = git_path("info/exclude");
1678 1679 1680 1681
	if (!excludes_file) {
		home_config_paths(NULL, &xdg_path, "ignore");
		excludes_file = xdg_path;
	}
1682
	if (!access_or_warn(path, R_OK, 0))
J
Junio C Hamano 已提交
1683
		add_excludes_from_file(dir, path);
1684
	if (excludes_file && !access_or_warn(excludes_file, R_OK, 0))
J
Junio C Hamano 已提交
1685 1686
		add_excludes_from_file(dir, excludes_file);
}
1687 1688 1689 1690 1691

int remove_path(const char *name)
{
	char *slash;

1692
	if (unlink(name) && errno != ENOENT && errno != ENOTDIR)
1693 1694 1695 1696 1697 1698 1699 1700
		return -1;

	slash = strrchr(name, '/');
	if (slash) {
		char *dirs = xstrdup(name);
		slash = dirs + (slash - name);
		do {
			*slash = '\0';
1701
		} while (rmdir(dirs) == 0 && (slash = strrchr(dirs, '/')));
1702 1703 1704 1705 1706
		free(dirs);
	}
	return 0;
}

1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734
/*
 * Frees memory within dir which was allocated for exclude lists and
 * the exclude_stack.  Does not free dir itself.
 */
void clear_directory(struct dir_struct *dir)
{
	int i, j;
	struct exclude_list_group *group;
	struct exclude_list *el;
	struct exclude_stack *stk;

	for (i = EXC_CMDL; i <= EXC_FILE; i++) {
		group = &dir->exclude_list_group[i];
		for (j = 0; j < group->nr; j++) {
			el = &group->el[j];
			if (i == EXC_DIRS)
				free((char *)el->src);
			clear_exclude_list(el);
		}
		free(group->el);
	}

	stk = dir->exclude_stack;
	while (stk) {
		struct exclude_stack *prev = stk->prev;
		free(stk);
		stk = prev;
	}
1735
	strbuf_release(&dir->basebuf);
1736
}