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

/*
 * GIT - The information manager from hell
 *
 * Copyright (C) Linus Torvalds, 2005
 */
#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;

static int index_fd(unsigned char *sha1, int fd, struct stat *st)
{
	z_stream stream;
	unsigned long size = st->st_size;
	int max_out_bytes = size + 200;
	void *out = malloc(max_out_bytes);
	void *metadata = malloc(200);
	void *in;
	SHA_CTX c;

	in = "";
	if (size)
		in = mmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
	close(fd);
	if (!out || (int)(long)in == -1)
		return -1;

	memset(&stream, 0, sizeof(stream));
	deflateInit(&stream, Z_BEST_COMPRESSION);

	/*
	 * ASCII size + nul byte
	 */	
	stream.next_in = metadata;
	stream.avail_in = 1+sprintf(metadata, "blob %lu", size);
	stream.next_out = out;
	stream.avail_out = max_out_bytes;
	while (deflate(&stream, 0) == Z_OK)
		/* nothing */;

	/*
	 * File content
	 */
	stream.next_in = in;
	stream.avail_in = size;
	while (deflate(&stream, Z_FINISH) == Z_OK)
		/*nothing */;

	deflateEnd(&stream);
	
	SHA1_Init(&c);
	SHA1_Update(&c, out, stream.total_out);
	SHA1_Final(sha1, &c);

	return write_sha1_buffer(sha1, out, stream.total_out);
}

/*
 * 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) {
			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 = malloc(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 NULL;

	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 NULL;

	if (compare_data(ce, st.st_size))
		return NULL;

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

static void refresh_cache(void)
{
	int i;

	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);
			while ((i < active_nr) &&
			       ! strcmp(active_cache[i]->name, ce->name))
				i++;
			i--;
			continue;
		}

		new = refresh_entry(ce);
		if (!new) {
			printf("%s: needs update\n", ce->name);
			continue;
		}
		active_cache[i] = new;
	}
}

/*
 * 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 = malloc(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 int remove_lock = 0;

static void remove_lock_file(void)
{
	if (remove_lock)
		unlink(".git/index.lock");
}

int main(int argc, char **argv)
{
	int i, newfd, entries;
	int allow_options = 1;

	newfd = open(".git/index.lock", O_RDWR | O_CREAT | O_EXCL, 0600);
	if (newfd < 0)
		die("unable to create new cachefile");

	atexit(remove_lock_file);
	remove_lock = 1;

	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")) {
				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;
			}
			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(".git/index.lock", ".git/index"))
		die("Unable to write new cachefile");

	remove_lock = 0;
	return 0;
}
Commit	Line	Data
8bc9a0c7 LT	1	/*
	2	* GIT - The information manager from hell
	3	*
	4	* Copyright (C) Linus Torvalds, 2005
	5	*/
e83c5163 LT	6	#include "cache.h"
e83c5163 LT	7
121481ab LT	8	/*
	9	* Default to not allowing changes to the list of files. The
	10	* tool doesn't actually care, but this makes it harder to add
	11	* files to the revision control by mistake by doing something
	12	* like "update-cache *" and suddenly having all the object
	13	* files be revision controlled.
	14	*/
	15	static int allow_add = 0, allow_remove = 0;
	16
c747fc6f	17	static int index_fd(unsigned char sha1, int fd, struct stat st)
e83c5163 LT	18	{
e83c5163 LT	19	z_stream stream;
3607c27f	20	unsigned long size = st->st_size;
c747fc6f	21	int max_out_bytes = size + 200;
e83c5163	22	void *out = malloc(max_out_bytes);
c747fc6f	23	void *metadata = malloc(200);
3607c27f	24	void *in;
e83c5163 LT	25	SHA_CTX c;
e83c5163 LT	26
3607c27f LT	27	in = "";
	28	if (size)
	29	in = mmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
e83c5163 LT	30	close(fd);
	31	if (!out \|\| (int)(long)in == -1)
	32	return -1;
	33
	34	memset(&stream, 0, sizeof(stream));
	35	deflateInit(&stream, Z_BEST_COMPRESSION);
	36
	37	/*
	38	* ASCII size + nul byte
	39	*/
	40	stream.next_in = metadata;
3607c27f	41	stream.avail_in = 1+sprintf(metadata, "blob %lu", size);
e83c5163 LT	42	stream.next_out = out;
	43	stream.avail_out = max_out_bytes;
	44	while (deflate(&stream, 0) == Z_OK)
	45	/* nothing */;
	46
	47	/*
	48	* File content
	49	*/
	50	stream.next_in = in;
3607c27f	51	stream.avail_in = size;
e83c5163 LT	52	while (deflate(&stream, Z_FINISH) == Z_OK)
	53	/nothing /;
	54
	55	deflateEnd(&stream);
	56
	57	SHA1_Init(&c);
	58	SHA1_Update(&c, out, stream.total_out);
c747fc6f	59	SHA1_Final(sha1, &c);
e83c5163	60
c747fc6f	61	return write_sha1_buffer(sha1, out, stream.total_out);
e83c5163 LT	62	}
e83c5163 LT	63
711cf3a0 LT	64	/*
	65	* This only updates the "non-critical" parts of the directory
	66	* cache, ie the parts that aren't tracked by GIT, and only used
	67	* to validate the cache.
	68	*/
	69	static void fill_stat_cache_info(struct cache_entry ce, struct stat st)
	70	{
ccc4feb5 LT	71	ce->ce_ctime.sec = htonl(st->st_ctime);
ccc4feb5 LT	72	ce->ce_mtime.sec = htonl(st->st_mtime);
5ade8628	73	#ifdef NSEC
ccc4feb5 LT	74	ce->ce_ctime.nsec = htonl(st->st_ctim.tv_nsec);
ccc4feb5 LT	75	ce->ce_mtime.nsec = htonl(st->st_mtim.tv_nsec);
5ade8628	76	#endif
ccc4feb5 LT	77	ce->ce_dev = htonl(st->st_dev);
	78	ce->ce_ino = htonl(st->st_ino);
	79	ce->ce_uid = htonl(st->st_uid);
	80	ce->ce_gid = htonl(st->st_gid);
	81	ce->ce_size = htonl(st->st_size);
711cf3a0 LT	82	}
711cf3a0 LT	83
e83c5163 LT	84	static int add_file_to_cache(char *path)
	85	{
	86	int size, namelen;
	87	struct cache_entry *ce;
	88	struct stat st;
	89	int fd;
	90
	91	fd = open(path, O_RDONLY);
	92	if (fd < 0) {
121481ab LT	93	if (errno == ENOENT) {
	94	if (allow_remove)
	95	return remove_file_from_cache(path);
	96	}
e83c5163 LT	97	return -1;
	98	}
	99	if (fstat(fd, &st) < 0) {
	100	close(fd);
	101	return -1;
	102	}
	103	namelen = strlen(path);
	104	size = cache_entry_size(namelen);
	105	ce = malloc(size);
	106	memset(ce, 0, size);
	107	memcpy(ce->name, path, namelen);
711cf3a0	108	fill_stat_cache_info(ce, &st);
e4479470	109	ce->ce_mode = create_ce_mode(st.st_mode);
f5cabd13	110	ce->ce_flags = htons(namelen);
e83c5163	111
c747fc6f	112	if (index_fd(ce->sha1, fd, &st) < 0)
e83c5163 LT	113	return -1;
e83c5163 LT	114
121481ab LT	115	return add_cache_entry(ce, allow_add);
	116	}
	117
711cf3a0 LT	118	static int match_data(int fd, void *buffer, unsigned long size)
	119	{
	120	while (size) {
	121	char compare[1024];
	122	int ret = read(fd, compare, sizeof(compare));
	123
	124	if (ret <= 0 \|\| ret > size \|\| memcmp(buffer, compare, ret))
	125	return -1;
	126	size -= ret;
	127	buffer += ret;
	128	}
	129	return 0;
	130	}
	131
32d197f1	132	static int compare_data(struct cache_entry *ce, unsigned long expected_size)
121481ab	133	{
711cf3a0 LT	134	int match = -1;
	135	int fd = open(ce->name, O_RDONLY);
	136
	137	if (fd >= 0) {
	138	void *buffer;
	139	unsigned long size;
	140	char type[10];
	141
	142	buffer = read_sha1_file(ce->sha1, type, &size);
	143	if (buffer) {
32d197f1	144	if (size == expected_size && !strcmp(type, "blob"))
711cf3a0 LT	145	match = match_data(fd, buffer, size);
	146	free(buffer);
	147	}
	148	close(fd);
	149	}
	150	return match;
	151	}
	152
	153	/*
	154	* "refresh" does not calculate a new sha1 file or bring the
	155	* cache up-to-date for mode/content changes. But what it
	156	* _does_ do is to "re-match" the stat information of a file
	157	* with the cache, so that you can refresh the cache for a
	158	* file that hasn't been changed but where the stat entry is
	159	* out of date.
	160	*
	161	* For example, you'd want to do this after doing a "read-tree",
	162	* to link up the stat cache details with the proper files.
	163	*/
	164	static struct cache_entry refresh_entry(struct cache_entry ce)
	165	{
	166	struct stat st;
	167	struct cache_entry *updated;
	168	int changed, size;
	169
	170	if (stat(ce->name, &st) < 0)
	171	return NULL;
	172
	173	changed = cache_match_stat(ce, &st);
	174	if (!changed)
	175	return ce;
	176
121481ab	177	/*
32d197f1	178	* If the mode has changed, there's no point in trying
711cf3a0	179	* to refresh the entry - it's not going to match
121481ab	180	*/
32d197f1	181	if (changed & MODE_CHANGED)
711cf3a0 LT	182	return NULL;
711cf3a0 LT	183
32d197f1	184	if (compare_data(ce, st.st_size))
711cf3a0 LT	185	return NULL;
	186
	187	size = ce_size(ce);
	188	updated = malloc(size);
	189	memcpy(updated, ce, size);
	190	fill_stat_cache_info(updated, &st);
	191	return updated;
121481ab LT	192	}
	193
	194	static void refresh_cache(void)
	195	{
	196	int i;
	197
711cf3a0	198	for (i = 0; i < active_nr; i++) {
1bc992ac JH	199	struct cache_entry ce, new;
	200	ce = active_cache[i];
	201	if (ce_stage(ce)) {
	202	printf("%s: needs merge\n", ce->name);
	203	while ((i < active_nr) &&
	204	! strcmp(active_cache[i]->name, ce->name))
	205	i++;
	206	i--;
	207	continue;
	208	}
711cf3a0	209
1bc992ac	210	new = refresh_entry(ce);
711cf3a0 LT	211	if (!new) {
	212	printf("%s: needs update\n", ce->name);
	213	continue;
	214	}
	215	active_cache[i] = new;
	216	}
e83c5163 LT	217	}
e83c5163 LT	218
e83c5163 LT	219	/*
	220	* We fundamentally don't like some paths: we don't want
	221	* dot or dot-dot anywhere, and in fact, we don't even want
4bb04f21	222	* any other dot-files (.git or anything else). They
e83c5163 LT	223	* are hidden, for chist sake.
	224	*
	225	* Also, we don't want double slashes or slashes at the
aebb2679	226	* end that can make pathnames ambiguous.
e83c5163 LT	227	*/
	228	static int verify_path(char *path)
	229	{
	230	char c;
	231
	232	goto inside;
	233	for (;;) {
	234	if (!c)
	235	return 1;
	236	if (c == '/') {
	237	inside:
	238	c = *path++;
	239	if (c != '/' && c != '.' && c != '\0')
	240	continue;
	241	return 0;
	242	}
	243	c = *path++;
	244	}
	245	}
	246
9945d980 LT	247	static int add_cacheinfo(char arg1, char arg2, char *arg3)
	248	{
	249	int size, len;
	250	unsigned int mode;
	251	unsigned char sha1[20];
	252	struct cache_entry *ce;
	253
	254	if (sscanf(arg1, "%o", &mode) != 1)
	255	return -1;
9945d980 LT	256	if (get_sha1_hex(arg2, sha1))
9945d980 LT	257	return -1;
9945d980 LT	258	if (!verify_path(arg3))
9945d980 LT	259	return -1;
9945d980 LT	260
	261	len = strlen(arg3);
	262	size = cache_entry_size(len);
	263	ce = malloc(size);
	264	memset(ce, 0, size);
	265
	266	memcpy(ce->sha1, sha1, 20);
	267	memcpy(ce->name, arg3, len);
f5cabd13	268	ce->ce_flags = htons(len);
e4479470	269	ce->ce_mode = create_ce_mode(mode);
9945d980 LT	270	return add_cache_entry(ce, allow_add);
	271	}
	272
9614b8dc LT	273	static int remove_lock = 0;
	274
	275	static void remove_lock_file(void)
	276	{
	277	if (remove_lock)
4bb04f21	278	unlink(".git/index.lock");
9614b8dc LT	279	}
9614b8dc LT	280
e83c5163 LT	281	int main(int argc, char **argv)
	282	{
	283	int i, newfd, entries;
121481ab	284	int allow_options = 1;
e83c5163	285
4bb04f21	286	newfd = open(".git/index.lock", O_RDWR \| O_CREAT \| O_EXCL, 0600);
9614b8dc	287	if (newfd < 0)
2de381f9	288	die("unable to create new cachefile");
9614b8dc LT	289
	290	atexit(remove_lock_file);
	291	remove_lock = 1;
	292
e83c5163	293	entries = read_cache();
9614b8dc	294	if (entries < 0)
2de381f9	295	die("cache corrupted");
e83c5163	296
e83c5163 LT	297	for (i = 1 ; i < argc; i++) {
e83c5163 LT	298	char *path = argv[i];
121481ab LT	299
	300	if (allow_options && *path == '-') {
	301	if (!strcmp(path, "--")) {
	302	allow_options = 0;
	303	continue;
	304	}
	305	if (!strcmp(path, "--add")) {
	306	allow_add = 1;
	307	continue;
	308	}
	309	if (!strcmp(path, "--remove")) {
	310	allow_remove = 1;
	311	continue;
	312	}
	313	if (!strcmp(path, "--refresh")) {
	314	refresh_cache();
	315	continue;
	316	}
9945d980 LT	317	if (!strcmp(path, "--cacheinfo")) {
	318	if (i+3 >= argc \|\| add_cacheinfo(argv[i+1], argv[i+2], argv[i+3]))
	319	die("update-cache: --cacheinfo <mode> <sha1> <path>");
	320	i += 3;
	321	continue;
	322	}
2de381f9	323	die("unknown option %s", path);
121481ab	324	}
e83c5163 LT	325	if (!verify_path(path)) {
	326	fprintf(stderr, "Ignoring path %s\n", argv[i]);
	327	continue;
	328	}
9614b8dc	329	if (add_file_to_cache(path))
2de381f9	330	die("Unable to add %s to database", path);
e83c5163	331	}
9614b8dc	332	if (write_cache(newfd, active_cache, active_nr) \|\|
4bb04f21	333	rename(".git/index.lock", ".git/index"))
2de381f9	334	die("Unable to write new cachefile");
9614b8dc LT	335
9614b8dc LT	336	remove_lock = 0;
19b2860c	337	return 0;
e83c5163	338	}