read-cache.c 38.2 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1 2 3 4 5
/*
 * GIT - The information manager from hell
 *
 * Copyright (C) Linus Torvalds, 2005
 */
6
#define NO_THE_INDEX_COMPATIBILITY_MACROS
7
#include "cache.h"
8
#include "cache-tree.h"
9
#include "refs.h"
10
#include "dir.h"
11 12 13 14 15 16 17 18 19 20 21 22

/* Index extensions.
 *
 * The first letter should be 'A'..'Z' for extensions that are not
 * necessary for a correct operation (i.e. optimization data).
 * When new extensions are added that _needs_ to be understood in
 * order to correctly interpret the index file, pick character that
 * is outside the range, to cause the reader to abort.
 */

#define CACHE_EXT(s) ( (s[0]<<24)|(s[1]<<16)|(s[2]<<8)|(s[3]) )
#define CACHE_EXT_TREE 0x54524545	/* "TREE" */
23

24
struct index_state the_index;
25

Junio C Hamano's avatar
Junio C Hamano committed
26 27 28
static void set_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
{
	istate->cache[nr] = ce;
29
	add_name_hash(istate, ce);
Junio C Hamano's avatar
Junio C Hamano committed
30 31
}

32 33 34 35
static void replace_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
{
	struct cache_entry *old = istate->cache[nr];

36
	remove_name_hash(old);
37
	set_index_entry(istate, nr, ce);
38 39 40
	istate->cache_changed = 1;
}

41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56
void rename_index_entry_at(struct index_state *istate, int nr, const char *new_name)
{
	struct cache_entry *old = istate->cache[nr], *new;
	int namelen = strlen(new_name);

	new = xmalloc(cache_entry_size(namelen));
	copy_cache_entry(new, old);
	new->ce_flags &= ~(CE_STATE_MASK | CE_NAMEMASK);
	new->ce_flags |= (namelen >= CE_NAMEMASK ? CE_NAMEMASK : namelen);
	memcpy(new->name, new_name, namelen + 1);

	cache_tree_invalidate_path(istate->cache_tree, old->name);
	remove_index_entry_at(istate, nr);
	add_index_entry(istate, new, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE);
}

57 58 59 60 61 62 63
/*
 * This only updates the "non-critical" parts of the directory
 * cache, ie the parts that aren't tracked by GIT, and only used
 * to validate the cache.
 */
void fill_stat_cache_info(struct cache_entry *ce, struct stat *st)
{
64 65 66 67 68 69 70
	ce->ce_ctime = st->st_ctime;
	ce->ce_mtime = st->st_mtime;
	ce->ce_dev = st->st_dev;
	ce->ce_ino = st->st_ino;
	ce->ce_uid = st->st_uid;
	ce->ce_gid = st->st_gid;
	ce->ce_size = st->st_size;
Junio C Hamano's avatar
Junio C Hamano committed
71 72

	if (assume_unchanged)
73
		ce->ce_flags |= CE_VALID;
74 75 76

	if (S_ISREG(st->st_mode))
		ce_mark_uptodate(ce);
77 78
}

Junio C Hamano's avatar
Junio C Hamano committed
79 80 81 82 83 84 85
static int ce_compare_data(struct cache_entry *ce, struct stat *st)
{
	int match = -1;
	int fd = open(ce->name, O_RDONLY);

	if (fd >= 0) {
		unsigned char sha1[20];
86
		if (!index_fd(sha1, fd, st, 0, OBJ_BLOB, ce->name))
87
			match = hashcmp(sha1, ce->sha1);
88
		/* index_fd() closed the file descriptor already */
Junio C Hamano's avatar
Junio C Hamano committed
89 90 91 92
	}
	return match;
}

93
static int ce_compare_link(struct cache_entry *ce, size_t expected_size)
Junio C Hamano's avatar
Junio C Hamano committed
94 95 96 97 98
{
	int match = -1;
	char *target;
	void *buffer;
	unsigned long size;
99
	enum object_type type;
Junio C Hamano's avatar
Junio C Hamano committed
100 101 102 103 104 105 106 107
	int len;

	target = xmalloc(expected_size);
	len = readlink(ce->name, target, expected_size);
	if (len != expected_size) {
		free(target);
		return -1;
	}
108
	buffer = read_sha1_file(ce->sha1, &type, &size);
Junio C Hamano's avatar
Junio C Hamano committed
109 110 111 112 113 114 115 116 117 118 119
	if (!buffer) {
		free(target);
		return -1;
	}
	if (size == expected_size)
		match = memcmp(buffer, target, size);
	free(buffer);
	free(target);
	return match;
}

120 121 122 123 124 125
static int ce_compare_gitlink(struct cache_entry *ce)
{
	unsigned char sha1[20];

	/*
	 * We don't actually require that the .git directory
Martin Waitz's avatar
Martin Waitz committed
126
	 * under GITLINK directory be a valid git directory. It
127 128 129 130 131 132 133 134 135 136
	 * might even be missing (in case nobody populated that
	 * sub-project).
	 *
	 * If so, we consider it always to match.
	 */
	if (resolve_gitlink_ref(ce->name, "HEAD", sha1) < 0)
		return 0;
	return hashcmp(sha1, ce->sha1);
}

Junio C Hamano's avatar
Junio C Hamano committed
137 138 139 140 141 142 143 144
static int ce_modified_check_fs(struct cache_entry *ce, struct stat *st)
{
	switch (st->st_mode & S_IFMT) {
	case S_IFREG:
		if (ce_compare_data(ce, st))
			return DATA_CHANGED;
		break;
	case S_IFLNK:
145
		if (ce_compare_link(ce, xsize_t(st->st_size)))
Junio C Hamano's avatar
Junio C Hamano committed
146 147
			return DATA_CHANGED;
		break;
148
	case S_IFDIR:
149
		if (S_ISGITLINK(ce->ce_mode))
150
			return ce_compare_gitlink(ce) ? DATA_CHANGED : 0;
Junio C Hamano's avatar
Junio C Hamano committed
151 152 153 154 155 156
	default:
		return TYPE_CHANGED;
	}
	return 0;
}

157 158 159 160 161 162 163 164 165 166
static int is_empty_blob_sha1(const unsigned char *sha1)
{
	static const unsigned char empty_blob_sha1[20] = {
		0xe6,0x9d,0xe2,0x9b,0xb2,0xd1,0xd6,0x43,0x4b,0x8b,
		0x29,0xae,0x77,0x5a,0xd8,0xc2,0xe4,0x8c,0x53,0x91
	};

	return !hashcmp(sha1, empty_blob_sha1);
}

Junio C Hamano's avatar
Junio C Hamano committed
167
static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st)
168 169 170
{
	unsigned int changed = 0;

171 172 173 174
	if (ce->ce_flags & CE_REMOVE)
		return MODE_CHANGED | DATA_CHANGED | TYPE_CHANGED;

	switch (ce->ce_mode & S_IFMT) {
175 176
	case S_IFREG:
		changed |= !S_ISREG(st->st_mode) ? TYPE_CHANGED : 0;
Junio C Hamano's avatar
Junio C Hamano committed
177 178 179 180
		/* We consider only the owner x bit to be relevant for
		 * "mode changes"
		 */
		if (trust_executable_bit &&
181
		    (0100 & (ce->ce_mode ^ st->st_mode)))
182
			changed |= MODE_CHANGED;
183 184
		break;
	case S_IFLNK:
185 186 187
		if (!S_ISLNK(st->st_mode) &&
		    (has_symlinks || !S_ISREG(st->st_mode)))
			changed |= TYPE_CHANGED;
188
		break;
Martin Waitz's avatar
Martin Waitz committed
189
	case S_IFGITLINK:
190
		/* We ignore most of the st_xxx fields for gitlinks */
191 192 193 194
		if (!S_ISDIR(st->st_mode))
			changed |= TYPE_CHANGED;
		else if (ce_compare_gitlink(ce))
			changed |= DATA_CHANGED;
195
		return changed;
196
	default:
197
		die("internal error: ce_mode is %o", ce->ce_mode);
198
	}
199
	if (ce->ce_mtime != (unsigned int) st->st_mtime)
200
		changed |= MTIME_CHANGED;
201
	if (trust_ctime && ce->ce_ctime != (unsigned int) st->st_ctime)
202
		changed |= CTIME_CHANGED;
203

204 205
	if (ce->ce_uid != (unsigned int) st->st_uid ||
	    ce->ce_gid != (unsigned int) st->st_gid)
206
		changed |= OWNER_CHANGED;
207
	if (ce->ce_ino != (unsigned int) st->st_ino)
208
		changed |= INODE_CHANGED;
209 210 211 212 213 214 215

#ifdef USE_STDEV
	/*
	 * st_dev breaks on network filesystems where different
	 * clients will have different views of what "device"
	 * the filesystem is on
	 */
216
	if (ce->ce_dev != (unsigned int) st->st_dev)
217 218 219
		changed |= INODE_CHANGED;
#endif

220
	if (ce->ce_size != (unsigned int) st->st_size)
221
		changed |= DATA_CHANGED;
222

223 224 225 226 227 228
	/* Racily smudged entry? */
	if (!ce->ce_size) {
		if (!is_empty_blob_sha1(ce->sha1))
			changed |= DATA_CHANGED;
	}

Junio C Hamano's avatar
Junio C Hamano committed
229 230 231
	return changed;
}

232
static int is_racy_timestamp(const struct index_state *istate, struct cache_entry *ce)
233
{
234 235
	return (!S_ISGITLINK(ce->ce_mode) &&
		istate->timestamp &&
236 237 238
		((unsigned int)istate->timestamp) <= ce->ce_mtime);
}

239
int ie_match_stat(const struct index_state *istate,
240 241
		  struct cache_entry *ce, struct stat *st,
		  unsigned int options)
Junio C Hamano's avatar
Junio C Hamano committed
242
{
Junio C Hamano's avatar
Junio C Hamano committed
243
	unsigned int changed;
244 245
	int ignore_valid = options & CE_MATCH_IGNORE_VALID;
	int assume_racy_is_modified = options & CE_MATCH_RACY_IS_DIRTY;
Junio C Hamano's avatar
Junio C Hamano committed
246 247 248 249 250

	/*
	 * If it's marked as always valid in the index, it's
	 * valid whatever the checked-out copy says.
	 */
251
	if (!ignore_valid && (ce->ce_flags & CE_VALID))
Junio C Hamano's avatar
Junio C Hamano committed
252 253 254
		return 0;

	changed = ce_match_stat_basic(ce, st);
Junio C Hamano's avatar
Junio C Hamano committed
255

Junio C Hamano's avatar
Junio C Hamano committed
256 257 258 259 260 261 262 263 264 265 266 267 268 269
	/*
	 * Within 1 second of this sequence:
	 * 	echo xyzzy >file && git-update-index --add file
	 * running this command:
	 * 	echo frotz >file
	 * would give a falsely clean cache entry.  The mtime and
	 * length match the cache, and other stat fields do not change.
	 *
	 * We could detect this at update-index time (the cache entry
	 * being registered/updated records the same time as "now")
	 * and delay the return from git-update-index, but that would
	 * effectively mean we can make at most one commit per second,
	 * which is not acceptable.  Instead, we check cache entries
	 * whose mtime are the same as the index file timestamp more
Junio C Hamano's avatar
Junio C Hamano committed
270
	 * carefully than others.
Junio C Hamano's avatar
Junio C Hamano committed
271
	 */
272
	if (!changed && is_racy_timestamp(istate, ce)) {
273 274 275 276 277
		if (assume_racy_is_modified)
			changed |= DATA_CHANGED;
		else
			changed |= ce_modified_check_fs(ce, st);
	}
278

Junio C Hamano's avatar
Junio C Hamano committed
279
	return changed;
280 281
}

282
int ie_modified(const struct index_state *istate,
283
		struct cache_entry *ce, struct stat *st, unsigned int options)
284
{
Junio C Hamano's avatar
Junio C Hamano committed
285
	int changed, changed_fs;
286 287

	changed = ie_match_stat(istate, ce, st, options);
288 289 290 291 292 293 294 295 296
	if (!changed)
		return 0;
	/*
	 * If the mode or type has changed, there's no point in trying
	 * to refresh the entry - it's not going to match
	 */
	if (changed & (MODE_CHANGED | TYPE_CHANGED))
		return changed;

297 298 299 300 301 302 303 304 305 306 307 308 309
	/*
	 * Immediately after read-tree or update-index --cacheinfo,
	 * the length field is zero, as we have never even read the
	 * lstat(2) information once, and we cannot trust DATA_CHANGED
	 * returned by ie_match_stat() which in turn was returned by
	 * ce_match_stat_basic() to signal that the filesize of the
	 * blob changed.  We have to actually go to the filesystem to
	 * see if the contents match, and if so, should answer "unchanged".
	 *
	 * The logic does not apply to gitlinks, as ce_match_stat_basic()
	 * already has checked the actual HEAD from the filesystem in the
	 * subproject.  If ie_match_stat() already said it is different,
	 * then we know it is.
310
	 */
311 312
	if ((changed & DATA_CHANGED) &&
	    (S_ISGITLINK(ce->ce_mode) || ce->ce_size != 0))
313 314
		return changed;

Junio C Hamano's avatar
Junio C Hamano committed
315 316 317
	changed_fs = ce_modified_check_fs(ce, st);
	if (changed_fs)
		return changed | changed_fs;
318 319 320
	return 0;
}

321 322 323 324 325 326 327 328 329 330 331 332
int base_name_compare(const char *name1, int len1, int mode1,
		      const char *name2, int len2, int mode2)
{
	unsigned char c1, c2;
	int len = len1 < len2 ? len1 : len2;
	int cmp;

	cmp = memcmp(name1, name2, len);
	if (cmp)
		return cmp;
	c1 = name1[len];
	c2 = name2[len];
333
	if (!c1 && S_ISDIR(mode1))
334
		c1 = '/';
335
	if (!c2 && S_ISDIR(mode2))
336 337 338 339
		c2 = '/';
	return (c1 < c2) ? -1 : (c1 > c2) ? 1 : 0;
}

340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374
/*
 * df_name_compare() is identical to base_name_compare(), except it
 * compares conflicting directory/file entries as equal. Note that
 * while a directory name compares as equal to a regular file, they
 * then individually compare _differently_ to a filename that has
 * a dot after the basename (because '\0' < '.' < '/').
 *
 * This is used by routines that want to traverse the git namespace
 * but then handle conflicting entries together when possible.
 */
int df_name_compare(const char *name1, int len1, int mode1,
		    const char *name2, int len2, int mode2)
{
	int len = len1 < len2 ? len1 : len2, cmp;
	unsigned char c1, c2;

	cmp = memcmp(name1, name2, len);
	if (cmp)
		return cmp;
	/* Directories and files compare equal (same length, same name) */
	if (len1 == len2)
		return 0;
	c1 = name1[len];
	if (!c1 && S_ISDIR(mode1))
		c1 = '/';
	c2 = name2[len];
	if (!c2 && S_ISDIR(mode2))
		c2 = '/';
	if (c1 == '/' && !c2)
		return 0;
	if (c2 == '/' && !c1)
		return 0;
	return c1 - c2;
}

375
int cache_name_compare(const char *name1, int flags1, const char *name2, int flags2)
376
{
377 378
	int len1 = flags1 & CE_NAMEMASK;
	int len2 = flags2 & CE_NAMEMASK;
379 380 381 382 383 384 385 386 387 388
	int len = len1 < len2 ? len1 : len2;
	int cmp;

	cmp = memcmp(name1, name2, len);
	if (cmp)
		return cmp;
	if (len1 < len2)
		return -1;
	if (len1 > len2)
		return 1;
Junio C Hamano's avatar
Junio C Hamano committed
389

390 391 392
	/* Compare stages  */
	flags1 &= CE_STAGEMASK;
	flags2 &= CE_STAGEMASK;
Junio C Hamano's avatar
Junio C Hamano committed
393

394 395 396 397
	if (flags1 < flags2)
		return -1;
	if (flags1 > flags2)
		return 1;
398 399 400
	return 0;
}

401
int index_name_pos(const struct index_state *istate, const char *name, int namelen)
402 403 404 405
{
	int first, last;

	first = 0;
406
	last = istate->cache_nr;
407 408
	while (last > first) {
		int next = (last + first) >> 1;
409
		struct cache_entry *ce = istate->cache[next];
410
		int cmp = cache_name_compare(name, namelen, ce->name, ce->ce_flags);
411
		if (!cmp)
412
			return next;
413 414 415 416 417 418
		if (cmp < 0) {
			last = next;
			continue;
		}
		first = next+1;
	}
419
	return -first-1;
420 421
}

422
/* Remove entry, return true if there are more entries to go.. */
423
int remove_index_entry_at(struct index_state *istate, int pos)
424
{
425 426
	struct cache_entry *ce = istate->cache[pos];

427
	remove_name_hash(ce);
428 429 430
	istate->cache_changed = 1;
	istate->cache_nr--;
	if (pos >= istate->cache_nr)
431
		return 0;
432 433 434
	memmove(istate->cache + pos,
		istate->cache + pos + 1,
		(istate->cache_nr - pos) * sizeof(struct cache_entry *));
435 436 437
	return 1;
}

438
int remove_file_from_index(struct index_state *istate, const char *path)
439
{
440
	int pos = index_name_pos(istate, path, strlen(path));
441 442
	if (pos < 0)
		pos = -pos-1;
Junio C Hamano's avatar
Junio C Hamano committed
443
	cache_tree_invalidate_path(istate->cache_tree, path);
444 445
	while (pos < istate->cache_nr && !strcmp(istate->cache[pos]->name, path))
		remove_index_entry_at(istate, pos);
446 447 448
	return 0;
}

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
static int compare_name(struct cache_entry *ce, const char *path, int namelen)
{
	return namelen != ce_namelen(ce) || memcmp(path, ce->name, namelen);
}

static int index_name_pos_also_unmerged(struct index_state *istate,
	const char *path, int namelen)
{
	int pos = index_name_pos(istate, path, namelen);
	struct cache_entry *ce;

	if (pos >= 0)
		return pos;

	/* maybe unmerged? */
	pos = -1 - pos;
	if (pos >= istate->cache_nr ||
			compare_name((ce = istate->cache[pos]), path, namelen))
		return -1;

	/* order of preference: stage 2, 1, 3 */
	if (ce_stage(ce) == 1 && pos + 1 < istate->cache_nr &&
			ce_stage((ce = istate->cache[pos + 1])) == 2 &&
			!compare_name(ce, path, namelen))
		pos++;
	return pos;
}

477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508
static int different_name(struct cache_entry *ce, struct cache_entry *alias)
{
	int len = ce_namelen(ce);
	return ce_namelen(alias) != len || memcmp(ce->name, alias->name, len);
}

/*
 * If we add a filename that aliases in the cache, we will use the
 * name that we already have - but we don't want to update the same
 * alias twice, because that implies that there were actually two
 * different files with aliasing names!
 *
 * So we use the CE_ADDED flag to verify that the alias was an old
 * one before we accept it as
 */
static struct cache_entry *create_alias_ce(struct cache_entry *ce, struct cache_entry *alias)
{
	int len;
	struct cache_entry *new;

	if (alias->ce_flags & CE_ADDED)
		die("Will not add file alias '%s' ('%s' already exists in index)", ce->name, alias->name);

	/* Ok, create the new entry using the name of the existing alias */
	len = ce_namelen(alias);
	new = xcalloc(1, cache_entry_size(len));
	memcpy(new->name, alias->name, len);
	copy_cache_entry(new, ce);
	free(ce);
	return new;
}

509
int add_to_index(struct index_state *istate, const char *path, struct stat *st, int flags)
Johannes Schindelin's avatar
Johannes Schindelin committed
510
{
511
	int size, namelen, was_same;
512
	mode_t st_mode = st->st_mode;
513
	struct cache_entry *ce, *alias;
514
	unsigned ce_option = CE_MATCH_IGNORE_VALID|CE_MATCH_RACY_IS_DIRTY;
515 516
	int verbose = flags & (ADD_CACHE_VERBOSE | ADD_CACHE_PRETEND);
	int pretend = flags & ADD_CACHE_PRETEND;
Johannes Schindelin's avatar
Johannes Schindelin committed
517

518
	if (!S_ISREG(st_mode) && !S_ISLNK(st_mode) && !S_ISDIR(st_mode))
519
		return error("%s: can only add regular files, symbolic links or git-directories", path);
Johannes Schindelin's avatar
Johannes Schindelin committed
520 521

	namelen = strlen(path);
522
	if (S_ISDIR(st_mode)) {
523 524 525
		while (namelen && path[namelen-1] == '/')
			namelen--;
	}
Johannes Schindelin's avatar
Johannes Schindelin committed
526 527 528
	size = cache_entry_size(namelen);
	ce = xcalloc(1, size);
	memcpy(ce->name, path, namelen);
529
	ce->ce_flags = namelen;
530
	fill_stat_cache_info(ce, st);
Johannes Schindelin's avatar
Johannes Schindelin committed
531

532
	if (trust_executable_bit && has_symlinks)
533
		ce->ce_mode = create_ce_mode(st_mode);
534
	else {
535 536
		/* If there is an existing entry, pick the mode bits and type
		 * from it, otherwise assume unexecutable regular file.
Johannes Schindelin's avatar
Johannes Schindelin committed
537
		 */
538
		struct cache_entry *ent;
539
		int pos = index_name_pos_also_unmerged(istate, path, namelen);
540

541
		ent = (0 <= pos) ? istate->cache[pos] : NULL;
542
		ce->ce_mode = ce_mode_from_stat(ent, st_mode);
Johannes Schindelin's avatar
Johannes Schindelin committed
543 544
	}

545
	alias = index_name_exists(istate, ce->name, ce_namelen(ce), ignore_case);
546
	if (alias && !ce_stage(alias) && !ie_match_stat(istate, alias, st, ce_option)) {
547 548
		/* Nothing changed, really */
		free(ce);
549
		ce_mark_uptodate(alias);
550
		alias->ce_flags |= CE_ADDED;
551 552
		return 0;
	}
553
	if (index_path(ce->sha1, path, st, 1))
554
		return error("unable to index file %s", path);
555 556 557
	if (ignore_case && alias && different_name(ce, alias))
		ce = create_alias_ce(ce, alias);
	ce->ce_flags |= CE_ADDED;
558

Junio C Hamano's avatar
Junio C Hamano committed
559
	/* It was suspected to be racily clean, but it turns out to be Ok */
560 561 562 563 564 565 566 567
	was_same = (alias &&
		    !ce_stage(alias) &&
		    !hashcmp(alias->sha1, ce->sha1) &&
		    ce->ce_mode == alias->ce_mode);

	if (pretend)
		;
	else if (add_index_entry(istate, ce, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE))
568
		return error("unable to add %s to index",path);
569
	if (verbose && !was_same)
Johannes Schindelin's avatar
Johannes Schindelin committed
570 571 572 573
		printf("add '%s'\n", path);
	return 0;
}

574
int add_file_to_index(struct index_state *istate, const char *path, int flags)
575 576 577 578
{
	struct stat st;
	if (lstat(path, &st))
		die("%s: unable to stat (%s)", path, strerror(errno));
579
	return add_to_index(istate, path, &st, flags);
580 581
}

582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606
struct cache_entry *make_cache_entry(unsigned int mode,
		const unsigned char *sha1, const char *path, int stage,
		int refresh)
{
	int size, len;
	struct cache_entry *ce;

	if (!verify_path(path))
		return NULL;

	len = strlen(path);
	size = cache_entry_size(len);
	ce = xcalloc(1, size);

	hashcpy(ce->sha1, sha1);
	memcpy(ce->name, path, len);
	ce->ce_flags = create_ce_flags(len, stage);
	ce->ce_mode = create_ce_mode(mode);

	if (refresh)
		return refresh_cache_entry(ce, 0);

	return ce;
}

607
int ce_same_name(struct cache_entry *a, struct cache_entry *b)
608 609 610 611 612
{
	int len = ce_namelen(a);
	return ce_namelen(b) == len && !memcmp(a->name, b->name, len);
}

613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632
int ce_path_match(const struct cache_entry *ce, const char **pathspec)
{
	const char *match, *name;
	int len;

	if (!pathspec)
		return 1;

	len = ce_namelen(ce);
	name = ce->name;
	while ((match = *pathspec++) != NULL) {
		int matchlen = strlen(match);
		if (matchlen > len)
			continue;
		if (memcmp(name, match, matchlen))
			continue;
		if (matchlen && name[matchlen-1] == '/')
			return 1;
		if (name[matchlen] == '/' || !name[matchlen])
			return 1;
633 634
		if (!matchlen)
			return 1;
635 636 637 638
	}
	return 0;
}

639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702
/*
 * We fundamentally don't like some paths: we don't want
 * dot or dot-dot anywhere, and for obvious reasons don't
 * want to recurse into ".git" either.
 *
 * Also, we don't want double slashes or slashes at the
 * end that can make pathnames ambiguous.
 */
static int verify_dotfile(const char *rest)
{
	/*
	 * The first character was '.', but that
	 * has already been discarded, we now test
	 * the rest.
	 */
	switch (*rest) {
	/* "." is not allowed */
	case '\0': case '/':
		return 0;

	/*
	 * ".git" followed by  NUL or slash is bad. This
	 * shares the path end test with the ".." case.
	 */
	case 'g':
		if (rest[1] != 'i')
			break;
		if (rest[2] != 't')
			break;
		rest += 2;
	/* fallthrough */
	case '.':
		if (rest[1] == '\0' || rest[1] == '/')
			return 0;
	}
	return 1;
}

int verify_path(const char *path)
{
	char c;

	goto inside;
	for (;;) {
		if (!c)
			return 1;
		if (c == '/') {
inside:
			c = *path++;
			switch (c) {
			default:
				continue;
			case '/': case '\0':
				break;
			case '.':
				if (verify_dotfile(path))
					continue;
			}
			return 0;
		}
		c = *path++;
	}
}

703 704 705
/*
 * Do we have another file that has the beginning components being a
 * proper superset of the name we're trying to add?
706
 */
707 708
static int has_file_name(struct index_state *istate,
			 const struct cache_entry *ce, int pos, int ok_to_replace)
709
{
710 711
	int retval = 0;
	int len = ce_namelen(ce);
712
	int stage = ce_stage(ce);
713
	const char *name = ce->name;
714

715 716
	while (pos < istate->cache_nr) {
		struct cache_entry *p = istate->cache[pos++];
717

718
		if (len >= ce_namelen(p))
719
			break;
720 721
		if (memcmp(name, p->name, len))
			break;
722 723
		if (ce_stage(p) != stage)
			continue;
724 725
		if (p->name[len] != '/')
			continue;
726
		if (p->ce_flags & CE_REMOVE)
727
			continue;
728 729 730
		retval = -1;
		if (!ok_to_replace)
			break;
731
		remove_index_entry_at(istate, --pos);
732
	}
733 734
	return retval;
}
735

736 737 738 739
/*
 * Do we have another file with a pathname that is a proper
 * subset of the name we're trying to add?
 */
740 741
static int has_dir_name(struct index_state *istate,
			const struct cache_entry *ce, int pos, int ok_to_replace)
742 743
{
	int retval = 0;
744
	int stage = ce_stage(ce);
745 746
	const char *name = ce->name;
	const char *slash = name + ce_namelen(ce);
747

748 749
	for (;;) {
		int len;
750

751 752 753 754 755 756 757
		for (;;) {
			if (*--slash == '/')
				break;
			if (slash <= ce->name)
				return retval;
		}
		len = slash - name;
758

759
		pos = index_name_pos(istate, name, create_ce_flags(len, stage));
760
		if (pos >= 0) {
761 762 763 764 765 766 767 768
			/*
			 * Found one, but not so fast.  This could
			 * be a marker that says "I was here, but
			 * I am being removed".  Such an entry is
			 * not a part of the resulting tree, and
			 * it is Ok to have a directory at the same
			 * path.
			 */
769
			if (!(istate->cache[pos]->ce_flags & CE_REMOVE)) {
770 771 772
				retval = -1;
				if (!ok_to_replace)
					break;
773
				remove_index_entry_at(istate, pos);
774 775
				continue;
			}
776
		}
777 778
		else
			pos = -pos-1;
779 780 781 782

		/*
		 * Trivial optimization: if we find an entry that
		 * already matches the sub-directory, then we know
783
		 * we're ok, and we can exit.
784
		 */
785 786
		while (pos < istate->cache_nr) {
			struct cache_entry *p = istate->cache[pos];
787 788 789 790
			if ((ce_namelen(p) <= len) ||
			    (p->name[len] != '/') ||
			    memcmp(p->name, name, len))
				break; /* not our subdirectory */
791 792 793
			if (ce_stage(p) == stage && !(p->ce_flags & CE_REMOVE))
				/*
				 * p is at the same stage as our entry, and
794 795 796 797 798 799
				 * is a subdirectory of what we are looking
				 * at, so we cannot have conflicts at our
				 * level or anything shorter.
				 */
				return retval;
			pos++;
800
		}
801
	}
802 803 804 805 806 807 808
	return retval;
}

/* We may be in a situation where we already have path/file and path
 * is being added, or we already have path and path/file is being
 * added.  Either one would result in a nonsense tree that has path
 * twice when git-write-tree tries to write it out.  Prevent it.
Junio C Hamano's avatar
Junio C Hamano committed
809
 *
810 811 812 813
 * If ok-to-replace is specified, we remove the conflicting entries
 * from the cache so the caller should recompute the insert position.
 * When this happens, we return non-zero.
 */
814 815 816
static int check_file_directory_conflict(struct index_state *istate,
					 const struct cache_entry *ce,
					 int pos, int ok_to_replace)
817
{
818 819 820 821 822
	int retval;

	/*
	 * When ce is an "I am going away" entry, we allow it to be added
	 */
823
	if (ce->ce_flags & CE_REMOVE)
824 825
		return 0;

826 827 828
	/*
	 * We check if the path is a sub-path of a subsequent pathname
	 * first, since removing those will not change the position
829
	 * in the array.
830
	 */
831
	retval = has_file_name(istate, ce, pos, ok_to_replace);
832

833 834 835 836
	/*
	 * Then check if the path might have a clashing sub-directory
	 * before it.
	 */
837
	return retval + has_dir_name(istate, ce, pos, ok_to_replace);
838 839
}

840
static int add_index_entry_with_check(struct index_state *istate, struct cache_entry *ce, int option)
841 842
{
	int pos;
843 844
	int ok_to_add = option & ADD_CACHE_OK_TO_ADD;
	int ok_to_replace = option & ADD_CACHE_OK_TO_REPLACE;
845
	int skip_df_check = option & ADD_CACHE_SKIP_DFCHECK;
Junio C Hamano's avatar
Junio C Hamano committed
846

Junio C Hamano's avatar
Junio C Hamano committed
847
	cache_tree_invalidate_path(istate->cache_tree, ce->name);
848
	pos = index_name_pos(istate, ce->name, ce->ce_flags);
849

Junio C Hamano's avatar
Junio C Hamano committed
850
	/* existing match? Just replace it. */
851
	if (pos >= 0) {
852
		replace_index_entry(istate, pos, ce);
853 854
		return 0;
	}
855
	pos = -pos-1;
856

857 858 859 860
	/*
	 * Inserting a merged entry ("stage 0") into the index
	 * will always replace all non-merged entries..
	 */
861 862
	if (pos < istate->cache_nr && ce_stage(ce) == 0) {
		while (ce_same_name(istate->cache[pos], ce)) {
863
			ok_to_add = 1;
864
			if (!remove_index_entry_at(istate, pos))
865 866 867 868
				break;
		}
	}

869 870
	if (!ok_to_add)
		return -1;
871 872
	if (!verify_path(ce->name))
		return -1;
873

Junio C Hamano's avatar
Junio C Hamano committed
874
	if (!skip_df_check &&
875
	    check_file_directory_conflict(istate, ce, pos, ok_to_replace)) {
876
		if (!ok_to_replace)
877 878
			return error("'%s' appears as both a file and as a directory",
				     ce->name);
879
		pos = index_name_pos(istate, ce->name, ce->ce_flags);
880 881
		pos = -pos-1;
	}
882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897
	return pos + 1;
}

int add_index_entry(struct index_state *istate, struct cache_entry *ce, int option)
{
	int pos;

	if (option & ADD_CACHE_JUST_APPEND)
		pos = istate->cache_nr;
	else {
		int ret;
		ret = add_index_entry_with_check(istate, ce, option);
		if (ret <= 0)
			return ret;
		pos = ret - 1;
	}
898

899
	/* Make sure the array is big enough .. */
900 901 902 903
	if (istate->cache_nr == istate->cache_alloc) {
		istate->cache_alloc = alloc_nr(istate->cache_alloc);
		istate->cache = xrealloc(istate->cache,
					istate->cache_alloc * sizeof(struct cache_entry *));
904 905 906
	}

	/* Add it in.. */
907
	istate->cache_nr++;
908
	if (istate->cache_nr > pos + 1)
909 910 911
		memmove(istate->cache + pos + 1,
			istate->cache + pos,
			(istate->cache_nr - pos - 1) * sizeof(ce));
912
	set_index_entry(istate, pos, ce);
913
	istate->cache_changed = 1;
914 915 916
	return 0;
}

917 918 919 920 921 922 923 924 925 926 927
/*
 * "refresh" does not calculate a new sha1 file or bring the
 * cache up-to-date for mode/content changes. But what it
 * _does_ do is to "re-match" the stat information of a file
 * with the cache, so that you can refresh the cache for a
 * file that hasn't been changed but where the stat entry is
 * out of date.
 *
 * For example, you'd want to do this after doing a "git-read-tree",
 * to link up the stat cache details with the proper files.
 */
928
static struct cache_entry *refresh_cache_ent(struct index_state *istate,
929 930
					     struct cache_entry *ce,
					     unsigned int options, int *err)
931 932 933 934
{
	struct stat st;
	struct cache_entry *updated;
	int changed, size;
935
	int ignore_valid = options & CE_MATCH_IGNORE_VALID;
936

937 938 939
	if (ce_uptodate(ce))
		return ce;

940 941 942 943 944 945 946 947 948
	/*
	 * CE_VALID means the user promised us that the change to
	 * the work tree does not matter and told us not to worry.
	 */
	if (!ignore_valid && (ce->ce_flags & CE_VALID)) {
		ce_mark_uptodate(ce);
		return ce;
	}

949
	if (lstat(ce->name, &st) < 0) {
950 951
		if (err)
			*err = errno;
952 953
		return NULL;
	}
954

955
	changed = ie_match_stat(istate, ce, &st, options);
956
	if (!changed) {
957 958 959 960 961 962 963 964
		/*
		 * The path is unchanged.  If we were told to ignore
		 * valid bit, then we did the actual stat check and
		 * found that the entry is unmodified.  If the entry
		 * is not marked VALID, this is the place to mark it
		 * valid again, under "assume unchanged" mode.
		 */
		if (ignore_valid && assume_unchanged &&
965
		    !(ce->ce_flags & CE_VALID))
966
			; /* mark this one VALID again */
967 968 969 970 971 972 973
		else {
			/*
			 * We do not mark the index itself "modified"
			 * because CE_UPTODATE flag is in-core only;
			 * we are not going to write this change out.
			 */
			ce_mark_uptodate(ce);
974
			return ce;
975
		}
976 977
	}

978
	if (ie_modified(istate, ce, &st, options)) {
979 980
		if (err)
			*err = EINVAL;
981 982
		return NULL;
	}
983 984 985 986 987

	size = ce_size(ce);
	updated = xmalloc(size);
	memcpy(updated, ce, size);
	fill_stat_cache_info(updated, &st);
988 989 990 991 992
	/*
	 * If ignore_valid is not set, we should leave CE_VALID bit
	 * alone.  Otherwise, paths marked with --no-assume-unchanged
	 * (i.e. things to be edited) will reacquire CE_VALID bit
	 * automatically, which is not really what we want.
993
	 */
994
	if (!ignore_valid && assume_unchanged &&
995 996
	    !(ce->ce_flags & CE_VALID))
		updated->ce_flags &= ~CE_VALID;
997 998 999 1000

	return updated;
}

1001
int refresh_index(struct index_state *istate, unsigned int flags, const char **pathspec, char *seen)
1002 1003 1004 1005 1006 1007 1008
{
	int i;
	int has_errors = 0;
	int really = (flags & REFRESH_REALLY) != 0;
	int allow_unmerged = (flags & REFRESH_UNMERGED) != 0;
	int quiet = (flags & REFRESH_QUIET) != 0;
	int not_new = (flags & REFRESH_IGNORE_MISSING) != 0;
1009
	int ignore_submodules = (flags & REFRESH_IGNORE_SUBMODULES) != 0;
1010
	unsigned int options = really ? CE_MATCH_IGNORE_VALID : 0;
1011
	const char *needs_update_message;
1012

1013 1014
	needs_update_message = ((flags & REFRESH_SAY_CHANGED)
				? "locally modified" : "needs update");
1015
	for (i = 0; i < istate->cache_nr; i++) {
1016
		struct cache_entry *ce, *new;
1017 1018
		int cache_errno = 0;

1019
		ce = istate->cache[i];
1020 1021 1022
		if (ignore_submodules && S_ISGITLINK(ce->ce_mode))
			continue;

1023
		if (ce_stage(ce)) {
1024 1025
			while ((i < istate->cache_nr) &&
			       ! strcmp(istate->cache[i]->name, ce->name))
1026 1027 1028 1029 1030 1031 1032 1033 1034
				i++;
			i--;
			if (allow_unmerged)
				continue;
			printf("%s: needs merge\n", ce->name);
			has_errors = 1;
			continue;
		}

1035 1036 1037
		if (pathspec && !match_pathspec(pathspec, ce->name, strlen(ce->name), 0, seen))
			continue;

1038
		new = refresh_cache_ent(istate, ce, options, &cache_errno);
1039
		if (new == ce)
1040
			continue;
1041 1042
		if (!new) {
			if (not_new && cache_errno == ENOENT)
1043
				continue;
1044
			if (really && cache_errno == EINVAL) {
1045 1046 1047
				/* If we are doing --really-refresh that
				 * means the index is not valid anymore.
				 */
1048
				ce->ce_flags &= ~CE_VALID;
1049
				istate->cache_changed = 1;
1050 1051 1052
			}
			if (quiet)
				continue;
1053
			printf("%s: %s\n", ce->name, needs_update_message);
1054 1055 1056
			has_errors = 1;
			continue;
		}
1057 1058

		replace_index_entry(istate, i, new);
1059 1060 1061 1062
	}
	return has_errors;
}

1063 1064
struct cache_entry *refresh_cache_entry(struct cache_entry *ce, int really)
{
1065
	return refresh_cache_ent(&the_index, ce, really, NULL);
1066 1067
}

1068
static int verify_hdr(struct cache_header *hdr, unsigned long size)
1069 1070
{
	SHA_CTX c;
1071
	unsigned char sha1[20];
1072

1073
	if (hdr->hdr_signature != htonl(CACHE_SIGNATURE))
1074
		return error("bad signature");
1075 1076
	if (hdr->hdr_version != htonl(2))
		return error("bad index version");
1077
	SHA1_Init(&c);
1078
	SHA1_Update(&c, hdr, size - 20);
1079
	SHA1_Final(sha1, &c);
1080
	if (hashcmp(sha1, (unsigned char *)hdr + size - 20))
1081
		return error("bad index file sha1 signature");
1082 1083 1084
	return 0;
}

1085 1086
static int read_index_extension(struct index_state *istate,
				const char *ext, void *data, unsigned long sz)
1087 1088 1089
{
	switch (CACHE_EXT(ext)) {
	case CACHE_EXT_TREE:
1090
		istate->cache_tree = cache_tree_read(data, sz);
1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101
		break;
	default:
		if (*ext < 'A' || 'Z' < *ext)
			return error("index uses %.4s extension, which we do not understand",
				     ext);
		fprintf(stderr, "ignoring %.4s extension\n", ext);
		break;
	}
	return 0;
}

1102
int read_index(struct index_state *istate)
1103
{
1104
	return read_index_from(istate, get_index_file());
1105 1106
}

1107 1108
static void convert_from_disk(struct ondisk_cache_entry *ondisk, struct cache_entry *ce)
{
1109 1110
	size_t len;

1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121
	ce->ce_ctime = ntohl(ondisk->ctime.sec);
	ce->ce_mtime = ntohl(ondisk->mtime.sec);
	ce->ce_dev   = ntohl(ondisk->dev);
	ce->ce_ino   = ntohl(ondisk->ino);
	ce->ce_mode  = ntohl(ondisk->mode);
	ce->ce_uid   = ntohl(ondisk->uid);
	ce->ce_gid   = ntohl(ondisk->gid);
	ce->ce_size  = ntohl(ondisk->size);
	/* On-disk flags are just 16 bits */
	ce->ce_flags = ntohs(ondisk->flags);
	hashcpy(ce->sha1, ondisk->sha1);
1122 1123 1124 1125 1126 1127 1128 1129 1130

	len = ce->ce_flags & CE_NAMEMASK;
	if (len == CE_NAMEMASK)
		len = strlen(ondisk->name);
	/*
	 * NEEDSWORK: If the original index is crafted, this copy could
	 * go unchecked.
	 */
	memcpy(ce->name, ondisk->name, len + 1);
1131 1132
}

1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146
static inline size_t estimate_cache_size(size_t ondisk_size, unsigned int entries)
{
	long per_entry;

	per_entry = sizeof(struct cache_entry) - sizeof(struct ondisk_cache_entry);

	/*
	 * Alignment can cause differences. This should be "alignof", but
	 * since that's a gcc'ism, just use the size of a pointer.
	 */
	per_entry += sizeof(void *);
	return ondisk_size + entries*per_entry;
}

1147
/* remember to discard_cache() before reading a different cache! */
1148
int read_index_from(struct index_state *istate, const char *path)
1149 1150 1151
{
	int fd, i;
	struct stat st;
1152
	unsigned long src_offset, dst_offset;
1153
	struct cache_header *hdr;
1154