read-cache.c 61.2 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 "lockfile.h"
9
#include "cache-tree.h"
10
#include "refs.h"
11
#include "dir.h"
12 13
#include "tree.h"
#include "commit.h"
14
#include "blob.h"
15
#include "resolve-undo.h"
16 17
#include "strbuf.h"
#include "varint.h"
Duy Nguyen's avatar
Duy Nguyen committed
18
#include "split-index.h"
19
#include "sigchain.h"
20
#include "utf8.h"
21

22 23
static struct cache_entry *refresh_cache_entry(struct cache_entry *ce,
					       unsigned int options);
24

25 26 27 28
/* Mask for the name length in ce_flags in the on-disk index */

#define CE_NAMEMASK  (0x0fff)

29 30 31 32 33 34 35 36 37 38 39
/* 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" */
40
#define CACHE_EXT_RESOLVE_UNDO 0x52455543 /* "REUC" */
Duy Nguyen's avatar
Duy Nguyen committed
41 42 43
#define CACHE_EXT_LINK 0x6c696e6b	  /* "link" */

/* changes that can be kept in $GIT_DIR/index (basically all extensions) */
44
#define EXTMASK (RESOLVE_UNDO_CHANGED | CACHE_TREE_CHANGED | \
45 46
		 CE_ENTRY_ADDED | CE_ENTRY_REMOVED | CE_ENTRY_CHANGED | \
		 SPLIT_INDEX_ORDERED)
47

48
struct index_state the_index;
49
static const char *alternate_index_output;
50

Junio C Hamano's avatar
Junio C Hamano committed
51 52 53
static void set_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
{
	istate->cache[nr] = ce;
54
	add_name_hash(istate, ce);
Junio C Hamano's avatar
Junio C Hamano committed
55 56
}

57 58 59 60
static void replace_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
{
	struct cache_entry *old = istate->cache[nr];

61
	replace_index_entry_in_base(istate, old, ce);
62
	remove_name_hash(istate, old);
63
	free(old);
64
	set_index_entry(istate, nr, ce);
65
	ce->ce_flags |= CE_UPDATE_IN_BASE;
66
	istate->cache_changed |= CE_ENTRY_CHANGED;
67 68
}

69 70 71 72 73 74 75
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);
76
	new->ce_flags &= ~CE_HASHED;
77
	new->ce_namelen = namelen;
Duy Nguyen's avatar
Duy Nguyen committed
78
	new->index = 0;
79 80
	memcpy(new->name, new_name, namelen + 1);

81
	cache_tree_invalidate_path(istate, old->name);
82 83 84 85
	remove_index_entry_at(istate, nr);
	add_index_entry(istate, new, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE);
}

86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140
void fill_stat_data(struct stat_data *sd, struct stat *st)
{
	sd->sd_ctime.sec = (unsigned int)st->st_ctime;
	sd->sd_mtime.sec = (unsigned int)st->st_mtime;
	sd->sd_ctime.nsec = ST_CTIME_NSEC(*st);
	sd->sd_mtime.nsec = ST_MTIME_NSEC(*st);
	sd->sd_dev = st->st_dev;
	sd->sd_ino = st->st_ino;
	sd->sd_uid = st->st_uid;
	sd->sd_gid = st->st_gid;
	sd->sd_size = st->st_size;
}

int match_stat_data(const struct stat_data *sd, struct stat *st)
{
	int changed = 0;

	if (sd->sd_mtime.sec != (unsigned int)st->st_mtime)
		changed |= MTIME_CHANGED;
	if (trust_ctime && check_stat &&
	    sd->sd_ctime.sec != (unsigned int)st->st_ctime)
		changed |= CTIME_CHANGED;

#ifdef USE_NSEC
	if (check_stat && sd->sd_mtime.nsec != ST_MTIME_NSEC(*st))
		changed |= MTIME_CHANGED;
	if (trust_ctime && check_stat &&
	    sd->sd_ctime.nsec != ST_CTIME_NSEC(*st))
		changed |= CTIME_CHANGED;
#endif

	if (check_stat) {
		if (sd->sd_uid != (unsigned int) st->st_uid ||
			sd->sd_gid != (unsigned int) st->st_gid)
			changed |= OWNER_CHANGED;
		if (sd->sd_ino != (unsigned int) st->st_ino)
			changed |= INODE_CHANGED;
	}

#ifdef USE_STDEV
	/*
	 * st_dev breaks on network filesystems where different
	 * clients will have different views of what "device"
	 * the filesystem is on
	 */
	if (check_stat && sd->sd_dev != (unsigned int) st->st_dev)
			changed |= INODE_CHANGED;
#endif

	if (sd->sd_size != (unsigned int) st->st_size)
		changed |= DATA_CHANGED;

	return changed;
}

141 142 143 144 145 146 147
/*
 * 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)
{
148
	fill_stat_data(&ce->ce_stat_data, st);
Junio C Hamano's avatar
Junio C Hamano committed
149 150

	if (assume_unchanged)
151
		ce->ce_flags |= CE_VALID;
152 153 154

	if (S_ISREG(st->st_mode))
		ce_mark_uptodate(ce);
155 156
}

157
static int ce_compare_data(const struct cache_entry *ce, struct stat *st)
Junio C Hamano's avatar
Junio C Hamano committed
158 159 160 161 162 163
{
	int match = -1;
	int fd = open(ce->name, O_RDONLY);

	if (fd >= 0) {
		unsigned char sha1[20];
164
		if (!index_fd(sha1, fd, st, OBJ_BLOB, ce->name, 0))
165
			match = hashcmp(sha1, ce->sha1);
166
		/* index_fd() closed the file descriptor already */
Junio C Hamano's avatar
Junio C Hamano committed
167 168 169 170
	}
	return match;
}

171
static int ce_compare_link(const struct cache_entry *ce, size_t expected_size)
Junio C Hamano's avatar
Junio C Hamano committed
172 173 174 175
{
	int match = -1;
	void *buffer;
	unsigned long size;
176
	enum object_type type;
177
	struct strbuf sb = STRBUF_INIT;
Junio C Hamano's avatar
Junio C Hamano committed
178

179
	if (strbuf_readlink(&sb, ce->name, expected_size))
Junio C Hamano's avatar
Junio C Hamano committed
180
		return -1;
181

182
	buffer = read_sha1_file(ce->sha1, &type, &size);
183 184 185 186
	if (buffer) {
		if (size == sb.len)
			match = memcmp(buffer, sb.buf, size);
		free(buffer);
Junio C Hamano's avatar
Junio C Hamano committed
187
	}
188
	strbuf_release(&sb);
Junio C Hamano's avatar
Junio C Hamano committed
189 190 191
	return match;
}

192
static int ce_compare_gitlink(const struct cache_entry *ce)
193 194 195 196 197
{
	unsigned char sha1[20];

	/*
	 * We don't actually require that the .git directory
Martin Waitz's avatar
Martin Waitz committed
198
	 * under GITLINK directory be a valid git directory. It
199 200 201 202 203 204 205 206 207 208
	 * 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);
}

209
static int ce_modified_check_fs(const struct cache_entry *ce, struct stat *st)
Junio C Hamano's avatar
Junio C Hamano committed
210 211 212 213 214 215 216
{
	switch (st->st_mode & S_IFMT) {
	case S_IFREG:
		if (ce_compare_data(ce, st))
			return DATA_CHANGED;
		break;
	case S_IFLNK:
217
		if (ce_compare_link(ce, xsize_t(st->st_size)))
Junio C Hamano's avatar
Junio C Hamano committed
218 219
			return DATA_CHANGED;
		break;
220
	case S_IFDIR:
221
		if (S_ISGITLINK(ce->ce_mode))
222
			return ce_compare_gitlink(ce) ? DATA_CHANGED : 0;
Junio C Hamano's avatar
Junio C Hamano committed
223 224 225 226 227 228
	default:
		return TYPE_CHANGED;
	}
	return 0;
}

229
static int ce_match_stat_basic(const struct cache_entry *ce, struct stat *st)
230 231 232
{
	unsigned int changed = 0;

233 234 235 236
	if (ce->ce_flags & CE_REMOVE)
		return MODE_CHANGED | DATA_CHANGED | TYPE_CHANGED;

	switch (ce->ce_mode & S_IFMT) {
237 238
	case S_IFREG:
		changed |= !S_ISREG(st->st_mode) ? TYPE_CHANGED : 0;
Junio C Hamano's avatar
Junio C Hamano committed
239 240 241 242
		/* We consider only the owner x bit to be relevant for
		 * "mode changes"
		 */
		if (trust_executable_bit &&
243
		    (0100 & (ce->ce_mode ^ st->st_mode)))
244
			changed |= MODE_CHANGED;
245 246
		break;
	case S_IFLNK:
247 248 249
		if (!S_ISLNK(st->st_mode) &&
		    (has_symlinks || !S_ISREG(st->st_mode)))
			changed |= TYPE_CHANGED;
250
		break;
Martin Waitz's avatar
Martin Waitz committed
251
	case S_IFGITLINK:
252
		/* We ignore most of the st_xxx fields for gitlinks */
253 254 255 256
		if (!S_ISDIR(st->st_mode))
			changed |= TYPE_CHANGED;
		else if (ce_compare_gitlink(ce))
			changed |= DATA_CHANGED;
257
		return changed;
258
	default:
259
		die("internal error: ce_mode is %o", ce->ce_mode);
260
	}
261

262
	changed |= match_stat_data(&ce->ce_stat_data, st);
263

264
	/* Racily smudged entry? */
265
	if (!ce->ce_stat_data.sd_size) {
266 267 268 269
		if (!is_empty_blob_sha1(ce->sha1))
			changed |= DATA_CHANGED;
	}

Junio C Hamano's avatar
Junio C Hamano committed
270 271 272
	return changed;
}

273 274
static int is_racy_timestamp(const struct index_state *istate,
			     const struct cache_entry *ce)
275
{
276
	return (!S_ISGITLINK(ce->ce_mode) &&
277 278 279
		istate->timestamp.sec &&
#ifdef USE_NSEC
		 /* nanosecond timestamped files can also be racy! */
280 281 282
		(istate->timestamp.sec < ce->ce_stat_data.sd_mtime.sec ||
		 (istate->timestamp.sec == ce->ce_stat_data.sd_mtime.sec &&
		  istate->timestamp.nsec <= ce->ce_stat_data.sd_mtime.nsec))
283
#else
284
		istate->timestamp.sec <= ce->ce_stat_data.sd_mtime.sec
285 286
#endif
		 );
287 288
}

289
int ie_match_stat(const struct index_state *istate,
290
		  const struct cache_entry *ce, struct stat *st,
291
		  unsigned int options)
Junio C Hamano's avatar
Junio C Hamano committed
292
{
Junio C Hamano's avatar
Junio C Hamano committed
293
	unsigned int changed;
294
	int ignore_valid = options & CE_MATCH_IGNORE_VALID;
295
	int ignore_skip_worktree = options & CE_MATCH_IGNORE_SKIP_WORKTREE;
296
	int assume_racy_is_modified = options & CE_MATCH_RACY_IS_DIRTY;
Junio C Hamano's avatar
Junio C Hamano committed
297 298 299 300

	/*
	 * If it's marked as always valid in the index, it's
	 * valid whatever the checked-out copy says.
301 302
	 *
	 * skip-worktree has the same effect with higher precedence
Junio C Hamano's avatar
Junio C Hamano committed
303
	 */
304 305
	if (!ignore_skip_worktree && ce_skip_worktree(ce))
		return 0;
306
	if (!ignore_valid && (ce->ce_flags & CE_VALID))
Junio C Hamano's avatar
Junio C Hamano committed
307 308
		return 0;

309 310 311 312 313 314 315 316
	/*
	 * Intent-to-add entries have not been added, so the index entry
	 * by definition never matches what is in the work tree until it
	 * actually gets added.
	 */
	if (ce->ce_flags & CE_INTENT_TO_ADD)
		return DATA_CHANGED | TYPE_CHANGED | MODE_CHANGED;

Junio C Hamano's avatar
Junio C Hamano committed
317
	changed = ce_match_stat_basic(ce, st);
Junio C Hamano's avatar
Junio C Hamano committed
318

Junio C Hamano's avatar
Junio C Hamano committed
319 320 321 322 323 324 325 326 327 328 329 330 331 332
	/*
	 * 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
333
	 * carefully than others.
Junio C Hamano's avatar
Junio C Hamano committed
334
	 */
335
	if (!changed && is_racy_timestamp(istate, ce)) {
336 337 338 339 340
		if (assume_racy_is_modified)
			changed |= DATA_CHANGED;
		else
			changed |= ce_modified_check_fs(ce, st);
	}
341

Junio C Hamano's avatar
Junio C Hamano committed
342
	return changed;
343 344
}

345
int ie_modified(const struct index_state *istate,
346 347
		const struct cache_entry *ce,
		struct stat *st, unsigned int options)
348
{
Junio C Hamano's avatar
Junio C Hamano committed
349
	int changed, changed_fs;
350 351

	changed = ie_match_stat(istate, ce, st, options);
352 353 354 355 356 357 358 359 360
	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;

361 362 363 364 365 366 367 368 369 370 371 372 373
	/*
	 * 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.
374
	 */
375
	if ((changed & DATA_CHANGED) &&
376
	    (S_ISGITLINK(ce->ce_mode) || ce->ce_stat_data.sd_size != 0))
377 378
		return changed;

Junio C Hamano's avatar
Junio C Hamano committed
379 380 381
	changed_fs = ce_modified_check_fs(ce, st);
	if (changed_fs)
		return changed | changed_fs;
382 383 384
	return 0;
}

385 386 387 388 389 390 391 392 393 394 395 396
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];
397
	if (!c1 && S_ISDIR(mode1))
398
		c1 = '/';
399
	if (!c2 && S_ISDIR(mode2))
400 401 402 403
		c2 = '/';
	return (c1 < c2) ? -1 : (c1 > c2) ? 1 : 0;
}

404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438
/*
 * 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;
}

439
int name_compare(const char *name1, size_t len1, const char *name2, size_t len2)
440
{
441 442
	size_t min_len = (len1 < len2) ? len1 : len2;
	int cmp = memcmp(name1, name2, min_len);
443 444 445 446 447 448
	if (cmp)
		return cmp;
	if (len1 < len2)
		return -1;
	if (len1 > len2)
		return 1;
449 450 451 452 453 454 455 456 457 458
	return 0;
}

int cache_name_stage_compare(const char *name1, int len1, int stage1, const char *name2, int len2, int stage2)
{
	int cmp;

	cmp = name_compare(name1, len1, name2, len2);
	if (cmp)
		return cmp;
Junio C Hamano's avatar
Junio C Hamano committed
459

460
	if (stage1 < stage2)
461
		return -1;
462
	if (stage1 > stage2)
463
		return 1;
464 465 466
	return 0;
}

467
static int index_name_stage_pos(const struct index_state *istate, const char *name, int namelen, int stage)
468 469 470 471
{
	int first, last;

	first = 0;
472
	last = istate->cache_nr;
473 474
	while (last > first) {
		int next = (last + first) >> 1;
475
		struct cache_entry *ce = istate->cache[next];
476
		int cmp = cache_name_stage_compare(name, namelen, stage, ce->name, ce_namelen(ce), ce_stage(ce));
477
		if (!cmp)
478
			return next;
479 480 481 482 483 484
		if (cmp < 0) {
			last = next;
			continue;
		}
		first = next+1;
	}
485
	return -first-1;
486 487
}

488 489 490 491 492
int index_name_pos(const struct index_state *istate, const char *name, int namelen)
{
	return index_name_stage_pos(istate, name, namelen, 0);
}

493
/* Remove entry, return true if there are more entries to go.. */
494
int remove_index_entry_at(struct index_state *istate, int pos)
495
{
496 497
	struct cache_entry *ce = istate->cache[pos];

498
	record_resolve_undo(istate, ce);
499
	remove_name_hash(istate, ce);
500
	save_or_free_index_entry(istate, ce);
501
	istate->cache_changed |= CE_ENTRY_REMOVED;
502 503
	istate->cache_nr--;
	if (pos >= istate->cache_nr)
504
		return 0;
505 506 507
	memmove(istate->cache + pos,
		istate->cache + pos + 1,
		(istate->cache_nr - pos) * sizeof(struct cache_entry *));
508 509 510
	return 1;
}

511
/*
Ondřej Bílka's avatar
Ondřej Bílka committed
512
 * Remove all cache entries marked for removal, that is where
513 514 515 516 517 518 519 520 521
 * CE_REMOVE is set in ce_flags.  This is much more effective than
 * calling remove_index_entry_at() for each entry to be removed.
 */
void remove_marked_cache_entries(struct index_state *istate)
{
	struct cache_entry **ce_array = istate->cache;
	unsigned int i, j;

	for (i = j = 0; i < istate->cache_nr; i++) {
522
		if (ce_array[i]->ce_flags & CE_REMOVE) {
523
			remove_name_hash(istate, ce_array[i]);
524
			save_or_free_index_entry(istate, ce_array[i]);
525
		}
526 527 528
		else
			ce_array[j++] = ce_array[i];
	}
529 530
	if (j == istate->cache_nr)
		return;
531
	istate->cache_changed |= CE_ENTRY_REMOVED;
532 533 534
	istate->cache_nr = j;
}

535
int remove_file_from_index(struct index_state *istate, const char *path)
536
{
537
	int pos = index_name_pos(istate, path, strlen(path));
538 539
	if (pos < 0)
		pos = -pos-1;
540
	cache_tree_invalidate_path(istate, path);
541 542
	while (pos < istate->cache_nr && !strcmp(istate->cache[pos]->name, path))
		remove_index_entry_at(istate, pos);
543 544 545
	return 0;
}

546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573
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;
}

574 575 576 577 578 579 580 581 582 583 584 585 586 587 588
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
 */
589 590 591
static struct cache_entry *create_alias_ce(struct index_state *istate,
					   struct cache_entry *ce,
					   struct cache_entry *alias)
592 593 594 595 596 597 598 599 600 601 602 603
{
	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);
604
	save_or_free_index_entry(istate, ce);
605 606 607
	return new;
}

608
void set_object_name_for_intent_to_add_entry(struct cache_entry *ce)
609 610 611 612 613 614 615
{
	unsigned char sha1[20];
	if (write_sha1_file("", 0, blob_type, sha1))
		die("cannot create an empty blob in the object database");
	hashcpy(ce->sha1, sha1);
}

616
int add_to_index(struct index_state *istate, const char *path, struct stat *st, int flags)
Johannes Schindelin's avatar
Johannes Schindelin committed
617
{
618
	int size, namelen, was_same;
619
	mode_t st_mode = st->st_mode;
620
	struct cache_entry *ce, *alias;
621
	unsigned ce_option = CE_MATCH_IGNORE_VALID|CE_MATCH_IGNORE_SKIP_WORKTREE|CE_MATCH_RACY_IS_DIRTY;
622 623
	int verbose = flags & (ADD_CACHE_VERBOSE | ADD_CACHE_PRETEND);
	int pretend = flags & ADD_CACHE_PRETEND;
624 625 626
	int intent_only = flags & ADD_CACHE_INTENT;
	int add_option = (ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE|
			  (intent_only ? ADD_CACHE_NEW_ONLY : 0));
Johannes Schindelin's avatar
Johannes Schindelin committed
627

628
	if (!S_ISREG(st_mode) && !S_ISLNK(st_mode) && !S_ISDIR(st_mode))
629
		return error("%s: can only add regular files, symbolic links or git-directories", path);
Johannes Schindelin's avatar
Johannes Schindelin committed
630 631

	namelen = strlen(path);
632
	if (S_ISDIR(st_mode)) {
633 634 635
		while (namelen && path[namelen-1] == '/')
			namelen--;
	}
Johannes Schindelin's avatar
Johannes Schindelin committed
636 637 638
	size = cache_entry_size(namelen);
	ce = xcalloc(1, size);
	memcpy(ce->name, path, namelen);
639
	ce->ce_namelen = namelen;
640 641
	if (!intent_only)
		fill_stat_cache_info(ce, st);
642 643
	else
		ce->ce_flags |= CE_INTENT_TO_ADD;
Johannes Schindelin's avatar
Johannes Schindelin committed
644

645
	if (trust_executable_bit && has_symlinks)
646
		ce->ce_mode = create_ce_mode(st_mode);
647
	else {
648 649
		/* 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
650
		 */
651
		struct cache_entry *ent;
652
		int pos = index_name_pos_also_unmerged(istate, path, namelen);
653

654
		ent = (0 <= pos) ? istate->cache[pos] : NULL;
655
		ce->ce_mode = ce_mode_from_stat(ent, st_mode);
Johannes Schindelin's avatar
Johannes Schindelin committed
656 657
	}

658 659 660 661 662 663 664 665 666 667 668 669 670 671
	/* When core.ignorecase=true, determine if a directory of the same name but differing
	 * case already exists within the Git repository.  If it does, ensure the directory
	 * case of the file being added to the repository matches (is folded into) the existing
	 * entry's directory case.
	 */
	if (ignore_case) {
		const char *startPtr = ce->name;
		const char *ptr = startPtr;
		while (*ptr) {
			while (*ptr && *ptr != '/')
				++ptr;
			if (*ptr == '/') {
				struct cache_entry *foundce;
				++ptr;
672
				foundce = index_dir_exists(istate, ce->name, ptr - ce->name - 1);
673 674 675 676 677 678 679 680
				if (foundce) {
					memcpy((void *)startPtr, foundce->name + (startPtr - ce->name), ptr - startPtr);
					startPtr = ptr;
				}
			}
		}
	}

681
	alias = index_file_exists(istate, ce->name, ce_namelen(ce), ignore_case);
682
	if (alias && !ce_stage(alias) && !ie_match_stat(istate, alias, st, ce_option)) {
683
		/* Nothing changed, really */
684 685
		if (!S_ISGITLINK(alias->ce_mode))
			ce_mark_uptodate(alias);
686
		alias->ce_flags |= CE_ADDED;
687 688

		free(ce);
689 690
		return 0;
	}
691
	if (!intent_only) {
692 693
		if (index_path(ce->sha1, path, st, HASH_WRITE_OBJECT)) {
			free(ce);
694
			return error("unable to index file %s", path);
695
		}
696
	} else
697
		set_object_name_for_intent_to_add_entry(ce);
698

699
	if (ignore_case && alias && different_name(ce, alias))
700
		ce = create_alias_ce(istate, ce, alias);
701
	ce->ce_flags |= CE_ADDED;
702

Junio C Hamano's avatar
Junio C Hamano committed
703
	/* It was suspected to be racily clean, but it turns out to be Ok */
704 705 706 707 708 709
	was_same = (alias &&
		    !ce_stage(alias) &&
		    !hashcmp(alias->sha1, ce->sha1) &&
		    ce->ce_mode == alias->ce_mode);

	if (pretend)
710 711 712 713 714
		free(ce);
	else if (add_index_entry(istate, ce, add_option)) {
		free(ce);
		return error("unable to add %s to index", path);
	}
715
	if (verbose && !was_same)
Johannes Schindelin's avatar
Johannes Schindelin committed
716 717 718 719
		printf("add '%s'\n", path);
	return 0;
}

720
int add_file_to_index(struct index_state *istate, const char *path, int flags)
721 722 723
{
	struct stat st;
	if (lstat(path, &st))
724
		die_errno("unable to stat '%s'", path);
725
	return add_to_index(istate, path, &st, flags);
726 727
}

728 729
struct cache_entry *make_cache_entry(unsigned int mode,
		const unsigned char *sha1, const char *path, int stage,
730
		unsigned int refresh_options)
731 732
{
	int size, len;
733
	struct cache_entry *ce, *ret;
734

735 736
	if (!verify_path(path)) {
		error("Invalid path '%s'", path);
737
		return NULL;
738
	}
739 740 741 742 743 744 745

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

	hashcpy(ce->sha1, sha1);
	memcpy(ce->name, path, len);
746 747
	ce->ce_flags = create_ce_flags(stage);
	ce->ce_namelen = len;
748 749
	ce->ce_mode = create_ce_mode(mode);

750
	ret = refresh_cache_entry(ce, refresh_options);
Stefan Beller's avatar
Stefan Beller committed
751
	if (ret != ce)
752
		free(ce);
Stefan Beller's avatar
Stefan Beller committed
753
	return ret;
754 755
}

756
int ce_same_name(const struct cache_entry *a, const struct cache_entry *b)
757 758 759 760 761
{
	int len = ce_namelen(a);
	return ce_namelen(b) == len && !memcmp(a->name, b->name, len);
}

762 763 764 765 766 767 768 769 770 771 772 773 774 775 776
/*
 * 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.
	 */
777

778
	/* "." is not allowed */
779
	if (*rest == '\0' || is_dir_sep(*rest))
780 781
		return 0;

782
	switch (*rest) {
783 784 785 786 787
	/*
	 * ".git" followed by  NUL or slash is bad. This
	 * shares the path end test with the ".." case.
	 */
	case 'g':
788 789
	case 'G':
		if (rest[1] != 'i' && rest[1] != 'I')
790
			break;
791
		if (rest[2] != 't' && rest[2] != 'T')
792 793 794 795
			break;
		rest += 2;
	/* fallthrough */
	case '.':
796
		if (rest[1] == '\0' || is_dir_sep(rest[1]))
797 798 799 800 801 802 803 804 805
			return 0;
	}
	return 1;
}

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

806 807 808
	if (has_dos_drive_prefix(path))
		return 0;

809 810 811 812
	goto inside;
	for (;;) {
		if (!c)
			return 1;
813
		if (is_dir_sep(c)) {
814
inside:
815 816
			if (protect_hfs && is_hfs_dotgit(path))
				return 0;
817 818
			if (protect_ntfs && is_ntfs_dotgit(path))
				return 0;
819
			c = *path++;
820 821 822
			if ((c == '.' && !verify_dotfile(path)) ||
			    is_dir_sep(c) || c == '\0')
				return 0;
823 824 825 826 827
		}
		c = *path++;
	}
}

828 829 830
/*
 * Do we have another file that has the beginning components being a
 * proper superset of the name we're trying to add?
831
 */
832 833
static int has_file_name(struct index_state *istate,
			 const struct cache_entry *ce, int pos, int ok_to_replace)
834
{
835 836
	int retval = 0;
	int len = ce_namelen(ce);
837
	int stage = ce_stage(ce);
838
	const char *name = ce->name;
839

840 841
	while (pos < istate->cache_nr) {
		struct cache_entry *p = istate->cache[pos++];
842

843
		if (len >= ce_namelen(p))
844
			break;
845 846
		if (memcmp(name, p->name, len))
			break;
847 848
		if (ce_stage(p) != stage)
			continue;
849 850
		if (p->name[len] != '/')
			continue;
851
		if (p->ce_flags & CE_REMOVE)
852
			continue;
853 854 855
		retval = -1;
		if (!ok_to_replace)
			break;
856
		remove_index_entry_at(istate, --pos);
857
	}
858 859
	return retval;
}
860

861 862 863 864
/*
 * Do we have another file with a pathname that is a proper
 * subset of the name we're trying to add?
 */
865 866
static int has_dir_name(struct index_state *istate,
			const struct cache_entry *ce, int pos, int ok_to_replace)
867 868
{
	int retval = 0;
869
	int stage = ce_stage(ce);
870 871
	const char *name = ce->name;
	const char *slash = name + ce_namelen(ce);
872

873 874
	for (;;) {
		int len;
875

876 877 878 879 880 881 882
		for (;;) {
			if (*--slash == '/')
				break;
			if (slash <= ce->name)
				return retval;
		}
		len = slash - name;
883

884
		pos = index_name_stage_pos(istate, name, len, stage);
885
		if (pos >= 0) {
886 887 888 889 890 891 892 893
			/*
			 * 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.
			 */
894
			if (!(istate->cache[pos]->ce_flags & CE_REMOVE)) {
895 896 897
				retval = -1;
				if (!ok_to_replace)
					break;
898
				remove_index_entry_at(istate, pos);
899 900
				continue;
			}
901
		}
902 903
		else
			pos = -pos-1;
904 905 906 907

		/*
		 * Trivial optimization: if we find an entry that
		 * already matches the sub-directory, then we know
908
		 * we're ok, and we can exit.
909
		 */
910 911
		while (pos < istate->cache_nr) {
			struct cache_entry *p = istate->cache[pos];
912 913 914 915
			if ((ce_namelen(p) <= len) ||
			    (p->name[len] != '/') ||
			    memcmp(p->name, name, len))
				break; /* not our subdirectory */
916 917 918
			if (ce_stage(p) == stage && !(p->ce_flags & CE_REMOVE))
				/*
				 * p is at the same stage as our entry, and
919 920 921 922 923 924
				 * is a subdirectory of what we are looking
				 * at, so we cannot have conflicts at our
				 * level or anything shorter.
				 */
				return retval;
			pos++;
925
		}
926
	}
927 928 929 930 931 932 933
	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
934
 *
935 936 937 938
 * 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.
 */
939 940 941
static int check_file_directory_conflict(struct index_state *istate,
					 const struct cache_entry *ce,
					 int pos, int ok_to_replace)
942
{
943 944 945 946 947
	int retval;

	/*
	 * When ce is an "I am going away" entry, we allow it to be added
	 */
948
	if (ce->ce_flags & CE_REMOVE)
949 950
		return 0;

951 952 953
	/*
	 * We check if the path is a sub-path of a subsequent pathname
	 * first, since removing those will not change the position
954
	 * in the array.
955
	 */
956
	retval = has_file_name(istate, ce, pos, ok_to_replace);
957

958 959 960 961
	/*
	 * Then check if the path might have a clashing sub-directory
	 * before it.
	 */
962
	return retval + has_dir_name(istate, ce, pos, ok_to_replace);
963 964
}

965
static int add_index_entry_with_check(struct index_state *istate, struct cache_entry *ce, int option)
966 967
{
	int pos;
968 969
	int ok_to_add = option & ADD_CACHE_OK_TO_ADD;
	int ok_to_replace = option & ADD_CACHE_OK_TO_REPLACE;
970
	int skip_df_check = option & ADD_CACHE_SKIP_DFCHECK;
971
	int new_only = option & ADD_CACHE_NEW_ONLY;
Junio C Hamano's avatar
Junio C Hamano committed
972

973 974
	if (!(option & ADD_CACHE_KEEP_CACHE_TREE))
		cache_tree_invalidate_path(istate, ce->name);
975
	pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce));
976

Junio C Hamano's avatar
Junio C Hamano committed
977
	/* existing match? Just replace it. */
978
	if (pos >= 0) {
979 980
		if (!new_only)
			replace_index_entry(istate, pos, ce);
981 982
		return 0;
	}
983
	pos = -pos-1;
984

985 986 987 988
	/*
	 * Inserting a merged entry ("stage 0") into the index
	 * will always replace all non-merged entries..
	 */
989 990
	if (pos < istate->cache_nr && ce_stage(ce) == 0) {
		while (ce_same_name(istate->cache[pos], ce)) {
991
			ok_to_add = 1;
992
			if (!remove_index_entry_at(istate, pos))
993 994 995 996
				break;
		}
	}

997 998
	if (!ok_to_add)
		return -1;
999
	if (!verify_path(ce->name))
1000
		return error("Invalid path '%s'", ce->name);
1001

Junio C Hamano's avatar
Junio C Hamano committed
1002
	if (!skip_df_check &&
1003
	    check_file_directory_conflict(istate, ce, pos, ok_to_replace)) {
1004
		if (!ok_to_replace)
1005 1006
			return error("'%s' appears as both a file and as a directory",
				     ce->name);
1007
		pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce));
1008 1009
		pos = -pos-1;
	}
1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025
	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;
	}
1026

1027
	/* Make sure the array is big enough .. */
1028
	ALLOC_GROW(istate->cache, istate->cache_nr + 1, istate->cache_alloc);
1029 1030

	/* Add it in.. */
1031
	istate->cache_nr++;
1032
	if (istate->cache_nr > pos + 1)
1033 1034 1035
		memmove(istate->cache + pos + 1,
			istate->cache + pos,
			(istate->cache_nr - pos - 1) * sizeof(ce));
1036
	set_index_entry(istate, pos, ce);
1037
	istate->cache_changed |= CE_ENTRY_ADDED;
1038 1039 1040
	return 0;
}

1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051
/*
 * "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.
 */
1052
static struct cache_entry *refresh_cache_ent(struct index_state *istate,
1053
					     struct cache_entry *ce,
1054 1055
					     unsigned int options,