[thirdparty/git.git] / update-cache.c

/*
 * GIT - The information manager from hell
 *
 * Copyright (C) Linus Torvalds, 2005
 */
#include <signal.h>
#include "cache.h"

/*
 * Default to not allowing changes to the list of files. The
 * tool doesn't actually care, but this makes it harder to add
 * files to the revision control by mistake by doing something
 * like "update-cache *" and suddenly having all the object
 * files be revision controlled.
 */
static int allow_add = 0, allow_remove = 0, not_new = 0;

/* Three functions to allow overloaded pointer return; see linux/err.h */
static inline void *ERR_PTR(long error)
{
	return (void *) error;
}

static inline long PTR_ERR(const void *ptr)
{
	return (long) ptr;
}

static inline long IS_ERR(const void *ptr)
{
	return (unsigned long)ptr > (unsigned long)-1000L;
}

/*
 * 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.
 */
static void fill_stat_cache_info(struct cache_entry *ce, struct stat *st)
{
	ce->ce_ctime.sec = htonl(st->st_ctime);
	ce->ce_mtime.sec = htonl(st->st_mtime);
#ifdef NSEC
	ce->ce_ctime.nsec = htonl(st->st_ctim.tv_nsec);
	ce->ce_mtime.nsec = htonl(st->st_mtim.tv_nsec);
#endif
	ce->ce_dev = htonl(st->st_dev);
	ce->ce_ino = htonl(st->st_ino);
	ce->ce_uid = htonl(st->st_uid);
	ce->ce_gid = htonl(st->st_gid);
	ce->ce_size = htonl(st->st_size);
}

static int add_file_to_cache(char *path)
{
	int size, namelen;
	struct cache_entry *ce;
	struct stat st;
	int fd;
	unsigned int len;
	char target[1024];

	if (lstat(path, &st) < 0) {
		if (errno == ENOENT || errno == ENOTDIR) {
			if (allow_remove)
				return remove_file_from_cache(path);
		}
		return -1;
	}
	namelen = strlen(path);
	size = cache_entry_size(namelen);
	ce = xmalloc(size);
	memset(ce, 0, size);
	memcpy(ce->name, path, namelen);
	fill_stat_cache_info(ce, &st);
	ce->ce_mode = create_ce_mode(st.st_mode);
	ce->ce_flags = htons(namelen);
	switch (st.st_mode & S_IFMT) {
	case S_IFREG:
		fd = open(path, O_RDONLY);
		if (fd < 0)
			return -1;
		if (index_fd(ce->sha1, fd, &st) < 0)
			return -1;
		break;
	case S_IFLNK:
		len = readlink(path, target, sizeof(target));
		if (len == -1 || len+1 > sizeof(target))
			return -1;
		if (write_sha1_file(target, len, "blob", ce->sha1))
			return -1;
		break;
	default:
		return -1;
	}
	return add_cache_entry(ce, allow_add);
}

static int match_data(int fd, void *buffer, unsigned long size)
{
	while (size) {
		char compare[1024];
		int ret = read(fd, compare, sizeof(compare));

		if (ret <= 0 || ret > size || memcmp(buffer, compare, ret))
			return -1;
		size -= ret;
		buffer += ret;
	}
	return 0;
}

static int compare_data(struct cache_entry *ce, unsigned long expected_size)
{
	int match = -1;
	int fd = open(ce->name, O_RDONLY);

	if (fd >= 0) {
		void *buffer;
		unsigned long size;
		char type[10];

		buffer = read_sha1_file(ce->sha1, type, &size);
		if (buffer) {
			if (size == expected_size && !strcmp(type, "blob"))
				match = match_data(fd, buffer, size);
			free(buffer);
		}
		close(fd);
	}
	return match;
}

/*
 * "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 "read-tree",
 * to link up the stat cache details with the proper files.
 */
static struct cache_entry *refresh_entry(struct cache_entry *ce)
{
	struct stat st;
	struct cache_entry *updated;
	int changed, size;

	if (lstat(ce->name, &st) < 0)
		return ERR_PTR(-errno);

	changed = cache_match_stat(ce, &st);
	if (!changed)
		return ce;

	/*
	 * 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 ERR_PTR(-EINVAL);

	if (compare_data(ce, st.st_size))
		return ERR_PTR(-EINVAL);

	size = ce_size(ce);
	updated = xmalloc(size);
	memcpy(updated, ce, size);
	fill_stat_cache_info(updated, &st);
	return updated;
}

static int refresh_cache(void)
{
	int i;
	int has_errors = 0;

	for (i = 0; i < active_nr; i++) {
		struct cache_entry *ce, *new;
		ce = active_cache[i];
		if (ce_stage(ce)) {
			printf("%s: needs merge\n", ce->name);
			has_errors = 1;
			while ((i < active_nr) &&
			       ! strcmp(active_cache[i]->name, ce->name))
				i++;
			i--;
			continue;
		}

		new = refresh_entry(ce);
		if (IS_ERR(new)) {
			if (!(not_new && PTR_ERR(new) == -ENOENT)) {
				printf("%s: needs update\n", ce->name);
				has_errors = 1;
			}
			continue;
		}
		active_cache[i] = new;
	}
	return has_errors;
}

/*
 * We fundamentally don't like some paths: we don't want
 * dot or dot-dot anywhere, and in fact, we don't even want
 * any other dot-files (.git or anything else). They
 * are hidden, for chist sake.
 *
 * Also, we don't want double slashes or slashes at the
 * end that can make pathnames ambiguous.
 */
static int verify_path(char *path)
{
	char c;

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

static int add_cacheinfo(char *arg1, char *arg2, char *arg3)
{
	int size, len;
	unsigned int mode;
	unsigned char sha1[20];
	struct cache_entry *ce;

	if (sscanf(arg1, "%o", &mode) != 1)
		return -1;
	if (get_sha1_hex(arg2, sha1))
		return -1;
	if (!verify_path(arg3))
		return -1;

	len = strlen(arg3);
	size = cache_entry_size(len);
	ce = xmalloc(size);
	memset(ce, 0, size);

	memcpy(ce->sha1, sha1, 20);
	memcpy(ce->name, arg3, len);
	ce->ce_flags = htons(len);
	ce->ce_mode = create_ce_mode(mode);
	return add_cache_entry(ce, allow_add);
}

static const char *lockfile_name = NULL;

static void remove_lock_file(void)
{
	if (lockfile_name)
		unlink(lockfile_name);
}

static void remove_lock_file_on_signal(int signo)
{
	remove_lock_file();
}

int main(int argc, char **argv)
{
	int i, newfd, entries, has_errors = 0;
	int allow_options = 1;
	static char lockfile[MAXPATHLEN+1];
	const char *indexfile = get_index_file();

	snprintf(lockfile, sizeof(lockfile), "%s.lock", indexfile);

	newfd = open(lockfile, O_RDWR | O_CREAT | O_EXCL, 0600);
	if (newfd < 0)
		die("unable to create new cachefile");

	signal(SIGINT, remove_lock_file_on_signal);
	atexit(remove_lock_file);
	lockfile_name = lockfile;

	entries = read_cache();
	if (entries < 0)
		die("cache corrupted");

	for (i = 1 ; i < argc; i++) {
		char *path = argv[i];

		if (allow_options && *path == '-') {
			if (!strcmp(path, "--")) {
				allow_options = 0;
				continue;
			}
			if (!strcmp(path, "--add")) {
				allow_add = 1;
				continue;
			}
			if (!strcmp(path, "--remove")) {
				allow_remove = 1;
				continue;
			}
			if (!strcmp(path, "--refresh")) {
				has_errors |= refresh_cache();
				continue;
			}
			if (!strcmp(path, "--cacheinfo")) {
				if (i+3 >= argc || add_cacheinfo(argv[i+1], argv[i+2], argv[i+3]))
					die("update-cache: --cacheinfo <mode> <sha1> <path>");
				i += 3;
				continue;
			}
			if (!strcmp(path, "--force-remove")) {
				if (argc <= i + 1)
					die("update-cache: --force-remove <path>");
				if (remove_file_from_cache(argv[i+1]))
					die("update-cache: --force-remove cannot remove %s", argv[i+1]);
				i++;
				continue;
			}

			if (!strcmp(path, "--ignore-missing")) {
				not_new = 1;
				continue;
			}
			die("unknown option %s", path);
		}
		if (!verify_path(path)) {
			fprintf(stderr, "Ignoring path %s\n", argv[i]);
			continue;
		}
		if (add_file_to_cache(path))
			die("Unable to add %s to database", path);
	}
	if (write_cache(newfd, active_cache, active_nr) || rename(lockfile, indexfile))
		die("Unable to write new cachefile");

	lockfile_name = NULL;
	return has_errors;
}
Commit	Line	Data
8bc9a0c7 LT	1	/*
	2	* GIT - The information manager from hell
	3	*
	4	* Copyright (C) Linus Torvalds, 2005
	5	*/
f2a19340	6	#include <signal.h>
e83c5163 LT	7	#include "cache.h"
e83c5163 LT	8
121481ab LT	9	/*
	10	* Default to not allowing changes to the list of files. The
	11	* tool doesn't actually care, but this makes it harder to add
	12	* files to the revision control by mistake by doing something
	13	* like "update-cache *" and suddenly having all the object
	14	* files be revision controlled.
	15	*/
c6e007b0 JB	16	static int allow_add = 0, allow_remove = 0, not_new = 0;
	17
	18	/* Three functions to allow overloaded pointer return; see linux/err.h */
	19	static inline void *ERR_PTR(long error)
	20	{
	21	return (void *) error;
	22	}
	23
	24	static inline long PTR_ERR(const void *ptr)
	25	{
	26	return (long) ptr;
	27	}
	28
	29	static inline long IS_ERR(const void *ptr)
	30	{
	31	return (unsigned long)ptr > (unsigned long)-1000L;
	32	}
121481ab	33
711cf3a0 LT	34	/*
	35	* This only updates the "non-critical" parts of the directory
	36	* cache, ie the parts that aren't tracked by GIT, and only used
	37	* to validate the cache.
	38	*/
	39	static void fill_stat_cache_info(struct cache_entry ce, struct stat st)
	40	{
ccc4feb5 LT	41	ce->ce_ctime.sec = htonl(st->st_ctime);
ccc4feb5 LT	42	ce->ce_mtime.sec = htonl(st->st_mtime);
5ade8628	43	#ifdef NSEC
ccc4feb5 LT	44	ce->ce_ctime.nsec = htonl(st->st_ctim.tv_nsec);
ccc4feb5 LT	45	ce->ce_mtime.nsec = htonl(st->st_mtim.tv_nsec);
5ade8628	46	#endif
ccc4feb5 LT	47	ce->ce_dev = htonl(st->st_dev);
	48	ce->ce_ino = htonl(st->st_ino);
	49	ce->ce_uid = htonl(st->st_uid);
	50	ce->ce_gid = htonl(st->st_gid);
	51	ce->ce_size = htonl(st->st_size);
711cf3a0 LT	52	}
711cf3a0 LT	53
e83c5163 LT	54	static int add_file_to_cache(char *path)
	55	{
	56	int size, namelen;
	57	struct cache_entry *ce;
	58	struct stat st;
	59	int fd;
8ae0a8c5 KS	60	unsigned int len;
8ae0a8c5 KS	61	char target[1024];
e83c5163	62
8ae0a8c5	63	if (lstat(path, &st) < 0) {
e2a669bb	64	if (errno == ENOENT \|\| errno == ENOTDIR) {
121481ab LT	65	if (allow_remove)
	66	return remove_file_from_cache(path);
	67	}
e83c5163 LT	68	return -1;
e83c5163 LT	69	}
e83c5163 LT	70	namelen = strlen(path);
e83c5163 LT	71	size = cache_entry_size(namelen);
812666c8	72	ce = xmalloc(size);
e83c5163 LT	73	memset(ce, 0, size);
e83c5163 LT	74	memcpy(ce->name, path, namelen);
711cf3a0	75	fill_stat_cache_info(ce, &st);
e4479470	76	ce->ce_mode = create_ce_mode(st.st_mode);
f5cabd13	77	ce->ce_flags = htons(namelen);
8ae0a8c5 KS	78	switch (st.st_mode & S_IFMT) {
	79	case S_IFREG:
	80	fd = open(path, O_RDONLY);
	81	if (fd < 0)
	82	return -1;
	83	if (index_fd(ce->sha1, fd, &st) < 0)
	84	return -1;
	85	break;
	86	case S_IFLNK:
	87	len = readlink(path, target, sizeof(target));
	88	if (len == -1 \|\| len+1 > sizeof(target))
	89	return -1;
	90	if (write_sha1_file(target, len, "blob", ce->sha1))
	91	return -1;
	92	break;
	93	default:
e83c5163	94	return -1;
8ae0a8c5	95	}
121481ab LT	96	return add_cache_entry(ce, allow_add);
	97	}
	98
711cf3a0 LT	99	static int match_data(int fd, void *buffer, unsigned long size)
	100	{
	101	while (size) {
	102	char compare[1024];
	103	int ret = read(fd, compare, sizeof(compare));
	104
	105	if (ret <= 0 \|\| ret > size \|\| memcmp(buffer, compare, ret))
	106	return -1;
	107	size -= ret;
	108	buffer += ret;
	109	}
	110	return 0;
	111	}
	112
32d197f1	113	static int compare_data(struct cache_entry *ce, unsigned long expected_size)
121481ab	114	{
711cf3a0 LT	115	int match = -1;
	116	int fd = open(ce->name, O_RDONLY);
	117
	118	if (fd >= 0) {
	119	void *buffer;
	120	unsigned long size;
	121	char type[10];
	122
	123	buffer = read_sha1_file(ce->sha1, type, &size);
	124	if (buffer) {
32d197f1	125	if (size == expected_size && !strcmp(type, "blob"))
711cf3a0 LT	126	match = match_data(fd, buffer, size);
	127	free(buffer);
	128	}
	129	close(fd);
	130	}
	131	return match;
	132	}
	133
	134	/*
	135	* "refresh" does not calculate a new sha1 file or bring the
	136	* cache up-to-date for mode/content changes. But what it
	137	* _does_ do is to "re-match" the stat information of a file
	138	* with the cache, so that you can refresh the cache for a
	139	* file that hasn't been changed but where the stat entry is
	140	* out of date.
	141	*
	142	* For example, you'd want to do this after doing a "read-tree",
	143	* to link up the stat cache details with the proper files.
	144	*/
	145	static struct cache_entry refresh_entry(struct cache_entry ce)
	146	{
	147	struct stat st;
	148	struct cache_entry *updated;
	149	int changed, size;
	150
8ae0a8c5	151	if (lstat(ce->name, &st) < 0)
c6e007b0	152	return ERR_PTR(-errno);
711cf3a0 LT	153
	154	changed = cache_match_stat(ce, &st);
	155	if (!changed)
	156	return ce;
	157
121481ab	158	/*
8ae0a8c5	159	* If the mode or type has changed, there's no point in trying
711cf3a0	160	* to refresh the entry - it's not going to match
121481ab	161	*/
8ae0a8c5	162	if (changed & (MODE_CHANGED \| TYPE_CHANGED))
c6e007b0	163	return ERR_PTR(-EINVAL);
711cf3a0	164
32d197f1	165	if (compare_data(ce, st.st_size))
c6e007b0	166	return ERR_PTR(-EINVAL);
711cf3a0 LT	167
711cf3a0 LT	168	size = ce_size(ce);
812666c8	169	updated = xmalloc(size);
711cf3a0 LT	170	memcpy(updated, ce, size);
	171	fill_stat_cache_info(updated, &st);
	172	return updated;
121481ab LT	173	}
121481ab LT	174
90535218	175	static int refresh_cache(void)
121481ab LT	176	{
121481ab LT	177	int i;
90535218	178	int has_errors = 0;
121481ab	179
711cf3a0	180	for (i = 0; i < active_nr; i++) {
1bc992ac JH	181	struct cache_entry ce, new;
	182	ce = active_cache[i];
	183	if (ce_stage(ce)) {
	184	printf("%s: needs merge\n", ce->name);
90535218	185	has_errors = 1;
1bc992ac JH	186	while ((i < active_nr) &&
	187	! strcmp(active_cache[i]->name, ce->name))
	188	i++;
	189	i--;
	190	continue;
	191	}
711cf3a0	192
1bc992ac	193	new = refresh_entry(ce);
c6e007b0	194	if (IS_ERR(new)) {
90535218	195	if (!(not_new && PTR_ERR(new) == -ENOENT)) {
c6e007b0	196	printf("%s: needs update\n", ce->name);
90535218 JH	197	has_errors = 1;
90535218 JH	198	}
711cf3a0 LT	199	continue;
	200	}
	201	active_cache[i] = new;
	202	}
90535218	203	return has_errors;
e83c5163 LT	204	}
e83c5163 LT	205
e83c5163 LT	206	/*
	207	* We fundamentally don't like some paths: we don't want
	208	* dot or dot-dot anywhere, and in fact, we don't even want
4bb04f21	209	* any other dot-files (.git or anything else). They
e83c5163 LT	210	* are hidden, for chist sake.
	211	*
	212	* Also, we don't want double slashes or slashes at the
aebb2679	213	* end that can make pathnames ambiguous.
e83c5163 LT	214	*/
	215	static int verify_path(char *path)
	216	{
	217	char c;
	218
	219	goto inside;
	220	for (;;) {
	221	if (!c)
	222	return 1;
	223	if (c == '/') {
	224	inside:
	225	c = *path++;
	226	if (c != '/' && c != '.' && c != '\0')
	227	continue;
	228	return 0;
	229	}
	230	c = *path++;
	231	}
	232	}
	233
9945d980 LT	234	static int add_cacheinfo(char arg1, char arg2, char *arg3)
	235	{
	236	int size, len;
	237	unsigned int mode;
	238	unsigned char sha1[20];
	239	struct cache_entry *ce;
	240
	241	if (sscanf(arg1, "%o", &mode) != 1)
	242	return -1;
9945d980 LT	243	if (get_sha1_hex(arg2, sha1))
9945d980 LT	244	return -1;
9945d980 LT	245	if (!verify_path(arg3))
9945d980 LT	246	return -1;
9945d980 LT	247
	248	len = strlen(arg3);
	249	size = cache_entry_size(len);
812666c8	250	ce = xmalloc(size);
9945d980 LT	251	memset(ce, 0, size);
	252
	253	memcpy(ce->sha1, sha1, 20);
	254	memcpy(ce->name, arg3, len);
f5cabd13	255	ce->ce_flags = htons(len);
e4479470	256	ce->ce_mode = create_ce_mode(mode);
9945d980 LT	257	return add_cache_entry(ce, allow_add);
	258	}
	259
bb233d69	260	static const char *lockfile_name = NULL;
9614b8dc LT	261
	262	static void remove_lock_file(void)
	263	{
bb233d69 LT	264	if (lockfile_name)
bb233d69 LT	265	unlink(lockfile_name);
9614b8dc LT	266	}
9614b8dc LT	267
f2a19340 LT	268	static void remove_lock_file_on_signal(int signo)
	269	{
	270	remove_lock_file();
	271	}
	272
e83c5163 LT	273	int main(int argc, char **argv)
e83c5163 LT	274	{
90535218	275	int i, newfd, entries, has_errors = 0;
121481ab	276	int allow_options = 1;
bb233d69 LT	277	static char lockfile[MAXPATHLEN+1];
bb233d69 LT	278	const char *indexfile = get_index_file();
e83c5163	279
bb233d69 LT	280	snprintf(lockfile, sizeof(lockfile), "%s.lock", indexfile);
	281
	282	newfd = open(lockfile, O_RDWR \| O_CREAT \| O_EXCL, 0600);
9614b8dc	283	if (newfd < 0)
2de381f9	284	die("unable to create new cachefile");
9614b8dc	285
f2a19340	286	signal(SIGINT, remove_lock_file_on_signal);
9614b8dc	287	atexit(remove_lock_file);
bb233d69	288	lockfile_name = lockfile;
9614b8dc	289
e83c5163	290	entries = read_cache();
9614b8dc	291	if (entries < 0)
2de381f9	292	die("cache corrupted");
e83c5163	293
e83c5163 LT	294	for (i = 1 ; i < argc; i++) {
e83c5163 LT	295	char *path = argv[i];
121481ab LT	296
	297	if (allow_options && *path == '-') {
	298	if (!strcmp(path, "--")) {
	299	allow_options = 0;
	300	continue;
	301	}
	302	if (!strcmp(path, "--add")) {
	303	allow_add = 1;
	304	continue;
	305	}
	306	if (!strcmp(path, "--remove")) {
	307	allow_remove = 1;
	308	continue;
	309	}
	310	if (!strcmp(path, "--refresh")) {
90535218	311	has_errors \|= refresh_cache();
121481ab LT	312	continue;
121481ab LT	313	}
9945d980 LT	314	if (!strcmp(path, "--cacheinfo")) {
	315	if (i+3 >= argc \|\| add_cacheinfo(argv[i+1], argv[i+2], argv[i+3]))
	316	die("update-cache: --cacheinfo <mode> <sha1> <path>");
	317	i += 3;
	318	continue;
	319	}
0ff5bf7c JH	320	if (!strcmp(path, "--force-remove")) {
	321	if (argc <= i + 1)
	322	die("update-cache: --force-remove <path>");
	323	if (remove_file_from_cache(argv[i+1]))
	324	die("update-cache: --force-remove cannot remove %s", argv[i+1]);
	325	i++;
	326	continue;
	327	}
	328
c6e007b0 JB	329	if (!strcmp(path, "--ignore-missing")) {
	330	not_new = 1;
	331	continue;
	332	}
2de381f9	333	die("unknown option %s", path);
121481ab	334	}
e83c5163 LT	335	if (!verify_path(path)) {
	336	fprintf(stderr, "Ignoring path %s\n", argv[i]);
	337	continue;
	338	}
9614b8dc	339	if (add_file_to_cache(path))
2de381f9	340	die("Unable to add %s to database", path);
e83c5163	341	}
bb233d69	342	if (write_cache(newfd, active_cache, active_nr) \|\| rename(lockfile, indexfile))
2de381f9	343	die("Unable to write new cachefile");
9614b8dc	344
bb233d69	345	lockfile_name = NULL;
90535218	346	return has_errors;
e83c5163	347	}