[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(const char *path, int namelen, struct cache_entry *ce, int fd, struct stat *st)
{
	z_stream stream;
	unsigned long size = st->st_size;
	int max_out_bytes = namelen + size + 200;
	void *out = malloc(max_out_bytes);
	void *metadata = malloc(namelen + 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(ce->sha1, &c);

	return write_sha1_buffer(ce->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->ctime.sec = st->st_ctime;
	ce->ctime.nsec = st->st_ctim.tv_nsec;
	ce->mtime.sec = st->st_mtime;
	ce->mtime.nsec = st->st_mtim.tv_nsec;
	ce->st_dev = st->st_dev;
	ce->st_ino = st->st_ino;
	ce->st_uid = st->st_uid;
	ce->st_gid = st->st_gid;
}

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->st_mode = st.st_mode;
	ce->st_size = st.st_size;
	ce->namelen = namelen;

	if (index_fd(path, namelen, ce, 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);
	updated->st_size = st.st_size;
	return updated;
}

static void refresh_cache(void)
{
	int i;

	for (i = 0; i < active_nr; i++) {
		struct cache_entry *ce = active_cache[i];
		struct cache_entry *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 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)
		usage("unable to create new cachefile");

	atexit(remove_lock_file);
	remove_lock = 1;

	entries = read_cache();
	if (entries < 0)
		usage("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;
			}
			usage("unknown option %s", path);
		}
		if (!verify_path(path)) {
			fprintf(stderr, "Ignoring path %s\n", argv[i]);
			continue;
		}
		if (add_file_to_cache(path))
			usage("Unable to add %s to database", path);
	}
	if (write_cache(newfd, active_cache, active_nr) ||
	    rename(".git/index.lock", ".git/index"))
		usage("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
e83c5163 LT	17	static int index_fd(const char path, int namelen, struct cache_entry ce, int fd, struct stat *st)
	18	{
	19	z_stream stream;
3607c27f LT	20	unsigned long size = st->st_size;
3607c27f LT	21	int max_out_bytes = namelen + size + 200;
e83c5163 LT	22	void *out = malloc(max_out_bytes);
e83c5163 LT	23	void *metadata = malloc(namelen + 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);
	59	SHA1_Final(ce->sha1, &c);
	60
	61	return write_sha1_buffer(ce->sha1, out, stream.total_out);
	62	}
	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	{
	71	ce->ctime.sec = st->st_ctime;
	72	ce->ctime.nsec = st->st_ctim.tv_nsec;
	73	ce->mtime.sec = st->st_mtime;
	74	ce->mtime.nsec = st->st_mtim.tv_nsec;
	75	ce->st_dev = st->st_dev;
	76	ce->st_ino = st->st_ino;
	77	ce->st_uid = st->st_uid;
	78	ce->st_gid = st->st_gid;
	79	}
	80
e83c5163 LT	81	static int add_file_to_cache(char *path)
	82	{
	83	int size, namelen;
	84	struct cache_entry *ce;
	85	struct stat st;
	86	int fd;
	87
	88	fd = open(path, O_RDONLY);
	89	if (fd < 0) {
121481ab LT	90	if (errno == ENOENT) {
	91	if (allow_remove)
	92	return remove_file_from_cache(path);
	93	}
e83c5163 LT	94	return -1;
	95	}
	96	if (fstat(fd, &st) < 0) {
	97	close(fd);
	98	return -1;
	99	}
	100	namelen = strlen(path);
	101	size = cache_entry_size(namelen);
	102	ce = malloc(size);
	103	memset(ce, 0, size);
	104	memcpy(ce->name, path, namelen);
711cf3a0	105	fill_stat_cache_info(ce, &st);
e83c5163	106	ce->st_mode = st.st_mode;
e83c5163 LT	107	ce->st_size = st.st_size;
	108	ce->namelen = namelen;
	109
	110	if (index_fd(path, namelen, ce, fd, &st) < 0)
	111	return -1;
	112
121481ab LT	113	return add_cache_entry(ce, allow_add);
	114	}
	115
711cf3a0 LT	116	static int match_data(int fd, void *buffer, unsigned long size)
	117	{
	118	while (size) {
	119	char compare[1024];
	120	int ret = read(fd, compare, sizeof(compare));
	121
	122	if (ret <= 0 \|\| ret > size \|\| memcmp(buffer, compare, ret))
	123	return -1;
	124	size -= ret;
	125	buffer += ret;
	126	}
	127	return 0;
	128	}
	129
32d197f1	130	static int compare_data(struct cache_entry *ce, unsigned long expected_size)
121481ab	131	{
711cf3a0 LT	132	int match = -1;
	133	int fd = open(ce->name, O_RDONLY);
	134
	135	if (fd >= 0) {
	136	void *buffer;
	137	unsigned long size;
	138	char type[10];
	139
	140	buffer = read_sha1_file(ce->sha1, type, &size);
	141	if (buffer) {
32d197f1	142	if (size == expected_size && !strcmp(type, "blob"))
711cf3a0 LT	143	match = match_data(fd, buffer, size);
	144	free(buffer);
	145	}
	146	close(fd);
	147	}
	148	return match;
	149	}
	150
	151	/*
	152	* "refresh" does not calculate a new sha1 file or bring the
	153	* cache up-to-date for mode/content changes. But what it
	154	* _does_ do is to "re-match" the stat information of a file
	155	* with the cache, so that you can refresh the cache for a
	156	* file that hasn't been changed but where the stat entry is
	157	* out of date.
	158	*
	159	* For example, you'd want to do this after doing a "read-tree",
	160	* to link up the stat cache details with the proper files.
	161	*/
	162	static struct cache_entry refresh_entry(struct cache_entry ce)
	163	{
	164	struct stat st;
	165	struct cache_entry *updated;
	166	int changed, size;
	167
	168	if (stat(ce->name, &st) < 0)
	169	return NULL;
	170
	171	changed = cache_match_stat(ce, &st);
	172	if (!changed)
	173	return ce;
	174
121481ab	175	/*
32d197f1	176	* If the mode has changed, there's no point in trying
711cf3a0	177	* to refresh the entry - it's not going to match
121481ab	178	*/
32d197f1	179	if (changed & MODE_CHANGED)
711cf3a0 LT	180	return NULL;
711cf3a0 LT	181
32d197f1	182	if (compare_data(ce, st.st_size))
711cf3a0 LT	183	return NULL;
	184
	185	size = ce_size(ce);
	186	updated = malloc(size);
	187	memcpy(updated, ce, size);
	188	fill_stat_cache_info(updated, &st);
32d197f1	189	updated->st_size = st.st_size;
711cf3a0	190	return updated;
121481ab LT	191	}
	192
	193	static void refresh_cache(void)
	194	{
	195	int i;
	196
711cf3a0 LT	197	for (i = 0; i < active_nr; i++) {
	198	struct cache_entry *ce = active_cache[i];
	199	struct cache_entry *new = refresh_entry(ce);
	200
	201	if (!new) {
	202	printf("%s: needs update\n", ce->name);
	203	continue;
	204	}
	205	active_cache[i] = new;
	206	}
e83c5163 LT	207	}
e83c5163 LT	208
e83c5163 LT	209	/*
	210	* We fundamentally don't like some paths: we don't want
	211	* dot or dot-dot anywhere, and in fact, we don't even want
4bb04f21	212	* any other dot-files (.git or anything else). They
e83c5163 LT	213	* are hidden, for chist sake.
	214	*
	215	* Also, we don't want double slashes or slashes at the
	216	* end that can make pathnames ambiguous.
	217	*/
	218	static int verify_path(char *path)
	219	{
	220	char c;
	221
	222	goto inside;
	223	for (;;) {
	224	if (!c)
	225	return 1;
	226	if (c == '/') {
	227	inside:
	228	c = *path++;
	229	if (c != '/' && c != '.' && c != '\0')
	230	continue;
	231	return 0;
	232	}
	233	c = *path++;
	234	}
	235	}
	236
9614b8dc LT	237	static int remove_lock = 0;
	238
	239	static void remove_lock_file(void)
	240	{
	241	if (remove_lock)
4bb04f21	242	unlink(".git/index.lock");
9614b8dc LT	243	}
9614b8dc LT	244
e83c5163 LT	245	int main(int argc, char **argv)
	246	{
	247	int i, newfd, entries;
121481ab	248	int allow_options = 1;
e83c5163	249
4bb04f21	250	newfd = open(".git/index.lock", O_RDWR \| O_CREAT \| O_EXCL, 0600);
9614b8dc LT	251	if (newfd < 0)
	252	usage("unable to create new cachefile");
	253
	254	atexit(remove_lock_file);
	255	remove_lock = 1;
	256
e83c5163	257	entries = read_cache();
9614b8dc LT	258	if (entries < 0)
9614b8dc LT	259	usage("cache corrupted");
e83c5163	260
e83c5163 LT	261	for (i = 1 ; i < argc; i++) {
e83c5163 LT	262	char *path = argv[i];
121481ab LT	263
	264	if (allow_options && *path == '-') {
	265	if (!strcmp(path, "--")) {
	266	allow_options = 0;
	267	continue;
	268	}
	269	if (!strcmp(path, "--add")) {
	270	allow_add = 1;
	271	continue;
	272	}
	273	if (!strcmp(path, "--remove")) {
	274	allow_remove = 1;
	275	continue;
	276	}
	277	if (!strcmp(path, "--refresh")) {
	278	refresh_cache();
	279	continue;
	280	}
	281	usage("unknown option %s", path);
	282	}
e83c5163 LT	283	if (!verify_path(path)) {
	284	fprintf(stderr, "Ignoring path %s\n", argv[i]);
	285	continue;
	286	}
9614b8dc LT	287	if (add_file_to_cache(path))
9614b8dc LT	288	usage("Unable to add %s to database", path);
e83c5163	289	}
9614b8dc	290	if (write_cache(newfd, active_cache, active_nr) \|\|
4bb04f21	291	rename(".git/index.lock", ".git/index"))
9614b8dc LT	292	usage("Unable to write new cachefile");
	293
	294	remove_lock = 0;
19b2860c	295	return 0;
e83c5163	296	}