[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;

	fd = open(path, O_RDONLY);
	if (fd < 0) {
		if (errno == ENOENT || errno == ENOTDIR) {
			if (allow_remove)
				return remove_file_from_cache(path);
		}
		return -1;
	}
	if (fstat(fd, &st) < 0) {
		close(fd);
		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);

	if (index_fd(ce->sha1, fd, &st) < 0)
		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 (stat(ce->name, &st) < 0)
		return ERR_PTR(-errno);

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

	/*
	 * If the mode has changed, there's no point in trying
	 * to refresh the entry - it's not going to match
	 */
	if (changed & MODE_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, "--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;
	60
	61	fd = open(path, O_RDONLY);
	62	if (fd < 0) {
e2a669bb	63	if (errno == ENOENT \|\| errno == ENOTDIR) {
121481ab LT	64	if (allow_remove)
	65	return remove_file_from_cache(path);
	66	}
e83c5163 LT	67	return -1;
	68	}
	69	if (fstat(fd, &st) < 0) {
	70	close(fd);
	71	return -1;
	72	}
	73	namelen = strlen(path);
	74	size = cache_entry_size(namelen);
812666c8	75	ce = xmalloc(size);
e83c5163 LT	76	memset(ce, 0, size);
e83c5163 LT	77	memcpy(ce->name, path, namelen);
711cf3a0	78	fill_stat_cache_info(ce, &st);
e4479470	79	ce->ce_mode = create_ce_mode(st.st_mode);
f5cabd13	80	ce->ce_flags = htons(namelen);
e83c5163	81
c747fc6f	82	if (index_fd(ce->sha1, fd, &st) < 0)
e83c5163 LT	83	return -1;
e83c5163 LT	84
121481ab LT	85	return add_cache_entry(ce, allow_add);
	86	}
	87
711cf3a0 LT	88	static int match_data(int fd, void *buffer, unsigned long size)
	89	{
	90	while (size) {
	91	char compare[1024];
	92	int ret = read(fd, compare, sizeof(compare));
	93
	94	if (ret <= 0 \|\| ret > size \|\| memcmp(buffer, compare, ret))
	95	return -1;
	96	size -= ret;
	97	buffer += ret;
	98	}
	99	return 0;
	100	}
	101
32d197f1	102	static int compare_data(struct cache_entry *ce, unsigned long expected_size)
121481ab	103	{
711cf3a0 LT	104	int match = -1;
	105	int fd = open(ce->name, O_RDONLY);
	106
	107	if (fd >= 0) {
	108	void *buffer;
	109	unsigned long size;
	110	char type[10];
	111
	112	buffer = read_sha1_file(ce->sha1, type, &size);
	113	if (buffer) {
32d197f1	114	if (size == expected_size && !strcmp(type, "blob"))
711cf3a0 LT	115	match = match_data(fd, buffer, size);
	116	free(buffer);
	117	}
	118	close(fd);
	119	}
	120	return match;
	121	}
	122
	123	/*
	124	* "refresh" does not calculate a new sha1 file or bring the
	125	* cache up-to-date for mode/content changes. But what it
	126	* _does_ do is to "re-match" the stat information of a file
	127	* with the cache, so that you can refresh the cache for a
	128	* file that hasn't been changed but where the stat entry is
	129	* out of date.
	130	*
	131	* For example, you'd want to do this after doing a "read-tree",
	132	* to link up the stat cache details with the proper files.
	133	*/
	134	static struct cache_entry refresh_entry(struct cache_entry ce)
	135	{
	136	struct stat st;
	137	struct cache_entry *updated;
	138	int changed, size;
	139
	140	if (stat(ce->name, &st) < 0)
c6e007b0	141	return ERR_PTR(-errno);
711cf3a0 LT	142
	143	changed = cache_match_stat(ce, &st);
	144	if (!changed)
	145	return ce;
	146
121481ab	147	/*
32d197f1	148	* If the mode has changed, there's no point in trying
711cf3a0	149	* to refresh the entry - it's not going to match
121481ab	150	*/
32d197f1	151	if (changed & MODE_CHANGED)
c6e007b0	152	return ERR_PTR(-EINVAL);
711cf3a0	153
32d197f1	154	if (compare_data(ce, st.st_size))
c6e007b0	155	return ERR_PTR(-EINVAL);
711cf3a0 LT	156
711cf3a0 LT	157	size = ce_size(ce);
812666c8	158	updated = xmalloc(size);
711cf3a0 LT	159	memcpy(updated, ce, size);
	160	fill_stat_cache_info(updated, &st);
	161	return updated;
121481ab LT	162	}
121481ab LT	163
90535218	164	static int refresh_cache(void)
121481ab LT	165	{
121481ab LT	166	int i;
90535218	167	int has_errors = 0;
121481ab	168
711cf3a0	169	for (i = 0; i < active_nr; i++) {
1bc992ac JH	170	struct cache_entry ce, new;
	171	ce = active_cache[i];
	172	if (ce_stage(ce)) {
	173	printf("%s: needs merge\n", ce->name);
90535218	174	has_errors = 1;
1bc992ac JH	175	while ((i < active_nr) &&
	176	! strcmp(active_cache[i]->name, ce->name))
	177	i++;
	178	i--;
	179	continue;
	180	}
711cf3a0	181
1bc992ac	182	new = refresh_entry(ce);
c6e007b0	183	if (IS_ERR(new)) {
90535218	184	if (!(not_new && PTR_ERR(new) == -ENOENT)) {
c6e007b0	185	printf("%s: needs update\n", ce->name);
90535218 JH	186	has_errors = 1;
90535218 JH	187	}
711cf3a0 LT	188	continue;
	189	}
	190	active_cache[i] = new;
	191	}
90535218	192	return has_errors;
e83c5163 LT	193	}
e83c5163 LT	194
e83c5163 LT	195	/*
	196	* We fundamentally don't like some paths: we don't want
	197	* dot or dot-dot anywhere, and in fact, we don't even want
4bb04f21	198	* any other dot-files (.git or anything else). They
e83c5163 LT	199	* are hidden, for chist sake.
	200	*
	201	* Also, we don't want double slashes or slashes at the
aebb2679	202	* end that can make pathnames ambiguous.
e83c5163 LT	203	*/
	204	static int verify_path(char *path)
	205	{
	206	char c;
	207
	208	goto inside;
	209	for (;;) {
	210	if (!c)
	211	return 1;
	212	if (c == '/') {
	213	inside:
	214	c = *path++;
	215	if (c != '/' && c != '.' && c != '\0')
	216	continue;
	217	return 0;
	218	}
	219	c = *path++;
	220	}
	221	}
	222
9945d980 LT	223	static int add_cacheinfo(char arg1, char arg2, char *arg3)
	224	{
	225	int size, len;
	226	unsigned int mode;
	227	unsigned char sha1[20];
	228	struct cache_entry *ce;
	229
	230	if (sscanf(arg1, "%o", &mode) != 1)
	231	return -1;
9945d980 LT	232	if (get_sha1_hex(arg2, sha1))
9945d980 LT	233	return -1;
9945d980 LT	234	if (!verify_path(arg3))
9945d980 LT	235	return -1;
9945d980 LT	236
	237	len = strlen(arg3);
	238	size = cache_entry_size(len);
812666c8	239	ce = xmalloc(size);
9945d980 LT	240	memset(ce, 0, size);
	241
	242	memcpy(ce->sha1, sha1, 20);
	243	memcpy(ce->name, arg3, len);
f5cabd13	244	ce->ce_flags = htons(len);
e4479470	245	ce->ce_mode = create_ce_mode(mode);
9945d980 LT	246	return add_cache_entry(ce, allow_add);
	247	}
	248
bb233d69	249	static const char *lockfile_name = NULL;
9614b8dc LT	250
	251	static void remove_lock_file(void)
	252	{
bb233d69 LT	253	if (lockfile_name)
bb233d69 LT	254	unlink(lockfile_name);
9614b8dc LT	255	}
9614b8dc LT	256
f2a19340 LT	257	static void remove_lock_file_on_signal(int signo)
	258	{
	259	remove_lock_file();
	260	}
	261
e83c5163 LT	262	int main(int argc, char **argv)
e83c5163 LT	263	{
90535218	264	int i, newfd, entries, has_errors = 0;
121481ab	265	int allow_options = 1;
bb233d69 LT	266	static char lockfile[MAXPATHLEN+1];
bb233d69 LT	267	const char *indexfile = get_index_file();
e83c5163	268
bb233d69 LT	269	snprintf(lockfile, sizeof(lockfile), "%s.lock", indexfile);
	270
	271	newfd = open(lockfile, O_RDWR \| O_CREAT \| O_EXCL, 0600);
9614b8dc	272	if (newfd < 0)
2de381f9	273	die("unable to create new cachefile");
9614b8dc	274
f2a19340	275	signal(SIGINT, remove_lock_file_on_signal);
9614b8dc	276	atexit(remove_lock_file);
bb233d69	277	lockfile_name = lockfile;
9614b8dc	278
e83c5163	279	entries = read_cache();
9614b8dc	280	if (entries < 0)
2de381f9	281	die("cache corrupted");
e83c5163	282
e83c5163 LT	283	for (i = 1 ; i < argc; i++) {
e83c5163 LT	284	char *path = argv[i];
121481ab LT	285
	286	if (allow_options && *path == '-') {
	287	if (!strcmp(path, "--")) {
	288	allow_options = 0;
	289	continue;
	290	}
	291	if (!strcmp(path, "--add")) {
	292	allow_add = 1;
	293	continue;
	294	}
	295	if (!strcmp(path, "--remove")) {
	296	allow_remove = 1;
	297	continue;
	298	}
	299	if (!strcmp(path, "--refresh")) {
90535218	300	has_errors \|= refresh_cache();
121481ab LT	301	continue;
121481ab LT	302	}
9945d980 LT	303	if (!strcmp(path, "--cacheinfo")) {
	304	if (i+3 >= argc \|\| add_cacheinfo(argv[i+1], argv[i+2], argv[i+3]))
	305	die("update-cache: --cacheinfo <mode> <sha1> <path>");
	306	i += 3;
	307	continue;
	308	}
c6e007b0 JB	309	if (!strcmp(path, "--ignore-missing")) {
	310	not_new = 1;
	311	continue;
	312	}
2de381f9	313	die("unknown option %s", path);
121481ab	314	}
e83c5163 LT	315	if (!verify_path(path)) {
	316	fprintf(stderr, "Ignoring path %s\n", argv[i]);
	317	continue;
	318	}
9614b8dc	319	if (add_file_to_cache(path))
2de381f9	320	die("Unable to add %s to database", path);
e83c5163	321	}
bb233d69	322	if (write_cache(newfd, active_cache, active_nr) \|\| rename(lockfile, indexfile))
2de381f9	323	die("Unable to write new cachefile");
9614b8dc	324
bb233d69	325	lockfile_name = NULL;
90535218	326	return has_errors;
e83c5163	327	}