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

#include <sys/types.h>
#include <dirent.h>

#include "cache.h"
#include "commit.h"
#include "tree.h"
#include "blob.h"
#include "tag.h"

#define REACHABLE 0x0001

static int show_root = 0;
static int show_tags = 0;
static int show_unreachable = 0;
static int keep_cache_objects = 0; 
static unsigned char head_sha1[20];

static void check_connectivity(void)
{
	int i;

	/* Look up all the requirements, warn about missing objects.. */
	for (i = 0; i < nr_objs; i++) {
		struct object *obj = objs[i];
		struct object_list *refs;

		if (!obj->parsed) {
			printf("missing %s %s\n", obj->type, sha1_to_hex(obj->sha1));
			continue;
		}

		for (refs = obj->refs; refs; refs = refs->next) {
			if (refs->item->parsed)
				continue;
			printf("broken link from %7s %s\n",
			       obj->type, sha1_to_hex(obj->sha1));
			printf("              to %7s %s\n",
			       refs->item->type, sha1_to_hex(refs->item->sha1));
		}

		/* Don't bother with tag reachability. */
		if (obj->type == tag_type)
			continue;

		if (show_unreachable && !(obj->flags & REACHABLE)) {
			printf("unreachable %s %s\n", obj->type, sha1_to_hex(obj->sha1));
			continue;
		}

		if (!obj->used) {
			printf("dangling %s %s\n", obj->type, 
			       sha1_to_hex(obj->sha1));
		}
	}
}

/*
 * The entries in a tree are ordered in the _path_ order,
 * which means that a directory entry is ordered by adding
 * a slash to the end of it.
 *
 * So a directory called "a" is ordered _after_ a file
 * called "a.c", because "a/" sorts after "a.c".
 */
static int verify_ordered(struct tree_entry_list *a, struct tree_entry_list *b)
{
	int len1 = strlen(a->name);
	int len2 = strlen(b->name);
	int len = len1 < len2 ? len1 : len2;
	unsigned char c1, c2;
	int cmp;

	cmp = memcmp(a->name, b->name, len);
	if (cmp < 0)
		return 0;
	if (cmp > 0)
		return -1;

	/*
	 * Ok, the first <len> characters are the same.
	 * Now we need to order the next one, but turn
	 * a '\0' into a '/' for a directory entry.
	 */
	c1 = a->name[len];
	c2 = b->name[len];
	if (!c1 && a->directory)
		c1 = '/';
	if (!c2 && b->directory)
		c2 = '/';
	return c1 < c2 ? 0 : -1;
}

static int fsck_tree(struct tree *item)
{
	int has_full_path = 0;
	struct tree_entry_list *entry, *last;

	last = NULL;
	for (entry = item->entries; entry; entry = entry->next) {
		if (strchr(entry->name, '/'))
			has_full_path = 1;

		if (last) {
			if (verify_ordered(last, entry) < 0) {
				fprintf(stderr, "tree %s not ordered\n",
					sha1_to_hex(item->object.sha1));
				return -1;
			}
		}

		last = entry;
	}

	if (has_full_path) {
		fprintf(stderr, "warning: fsck-cache: tree %s "
			"has full pathnames in it\n", 
			sha1_to_hex(item->object.sha1));
	}

	return 0;
}

static int fsck_commit(struct commit *commit)
{
	if (!commit->tree)
		return -1;
	if (!commit->parents && show_root)
		printf("root %s\n", sha1_to_hex(commit->object.sha1));
	if (!commit->date)
		printf("bad commit date in %s\n", 
		       sha1_to_hex(commit->object.sha1));
	return 0;
}

static int fsck_tag(struct tag *tag)
{
	struct object *tagged = tag->tagged;

	if (!tagged) {
		printf("bad object in tag %s\n", sha1_to_hex(tag->object.sha1));
		return -1;
	}
	if (!show_tags)
		return 0;

	printf("tagged %s %s", tagged->type, sha1_to_hex(tagged->sha1));
	printf(" (%s) in %s\n", tag->tag, sha1_to_hex(tag->object.sha1));
	return 0;
}

static int fsck_sha1(unsigned char *sha1)
{
	struct object *obj = parse_object(sha1);
	if (!obj)
		return -1;
	if (obj->type == blob_type)
		return 0;
	if (obj->type == tree_type)
		return fsck_tree((struct tree *) obj);
	if (obj->type == commit_type)
		return fsck_commit((struct commit *) obj);
	if (obj->type == tag_type)
		return fsck_tag((struct tag *) obj);
	return -1;
}

/*
 * This is the sorting chunk size: make it reasonably
 * big so that we can sort well..
 */
#define MAX_SHA1_ENTRIES (1024)

struct sha1_entry {
	unsigned long ino;
	unsigned char sha1[20];
};

static struct {
	unsigned long nr;
	struct sha1_entry *entry[MAX_SHA1_ENTRIES];
} sha1_list;

static int ino_compare(const void *_a, const void *_b)
{
	const struct sha1_entry *a = _a, *b = _b;
	unsigned long ino1 = a->ino, ino2 = b->ino;
	return ino1 < ino2 ? -1 : ino1 > ino2 ? 1 : 0;
}

static void fsck_sha1_list(void)
{
	int i, nr = sha1_list.nr;

	qsort(sha1_list.entry, nr, sizeof(struct sha1_entry *), ino_compare);
	for (i = 0; i < nr; i++) {
		struct sha1_entry *entry = sha1_list.entry[i];
		unsigned char *sha1 = entry->sha1;

		sha1_list.entry[i] = NULL;
		if (fsck_sha1(sha1) < 0)
			fprintf(stderr, "bad sha1 entry '%s'\n", sha1_to_hex(sha1));
		free(entry);
	}
	sha1_list.nr = 0;
}

static void add_sha1_list(unsigned char *sha1, unsigned long ino)
{
	struct sha1_entry *entry = xmalloc(sizeof(*entry));
	int nr;

	entry->ino = ino;
	memcpy(entry->sha1, sha1, 20);
	nr = sha1_list.nr;
	if (nr == MAX_SHA1_ENTRIES) {
		fsck_sha1_list();
		nr = 0;
	}
	sha1_list.entry[nr] = entry;
	sha1_list.nr = ++nr;
}

static int fsck_dir(int i, char *path)
{
	DIR *dir = opendir(path);
	struct dirent *de;

	if (!dir) {
		return error("missing sha1 directory '%s'", path);
	}

	while ((de = readdir(dir)) != NULL) {
		char name[100];
		unsigned char sha1[20];
		int len = strlen(de->d_name);

		switch (len) {
		case 2:
			if (de->d_name[1] != '.')
				break;
		case 1:
			if (de->d_name[0] != '.')
				break;
			continue;
		case 38:
			sprintf(name, "%02x", i);
			memcpy(name+2, de->d_name, len+1);
			if (get_sha1_hex(name, sha1) < 0)
				break;
			add_sha1_list(sha1, de->d_ino);
			continue;
		}
		fprintf(stderr, "bad sha1 file: %s/%s\n", path, de->d_name);
	}
	closedir(dir);
	return 0;
}

int main(int argc, char **argv)
{
	int i, heads;
	char *sha1_dir;

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

		if (!strcmp(arg, "--unreachable")) {
			show_unreachable = 1;
			continue;
		}
		if (!strcmp(arg, "--tags")) {
			show_tags = 1;
			continue;
		}
		if (!strcmp(arg, "--root")) {
			show_root = 1;
			continue;
		}
		if (!strcmp(arg, "--cache")) {
			keep_cache_objects = 1;
			continue;
		}
		if (*arg == '-')
			usage("fsck-cache [--tags] [[--unreachable] [--cache] <head-sha1>*]");
	}

	sha1_dir = getenv(DB_ENVIRONMENT) ? : DEFAULT_DB_ENVIRONMENT;
	for (i = 0; i < 256; i++) {
		static char dir[4096];
		sprintf(dir, "%s/%02x", sha1_dir, i);
		fsck_dir(i, dir);
	}
	fsck_sha1_list();

	heads = 0;
	for (i = 1; i < argc; i++) {
		const char *arg = argv[i]; 

		if (*arg == '-')
			continue;

		if (!get_sha1(arg, head_sha1)) {
			struct object *obj = lookup_object(head_sha1);

			/* Error is printed by lookup_object(). */
			if (!obj)
				continue;

			obj->used = 1;
			mark_reachable(obj, REACHABLE);
			heads++;
			continue;
		}
		error("expected sha1, got %s", arg);
	}

	if (keep_cache_objects) {
		int i;
		read_cache();
		for (i = 0; i < active_nr; i++) {
			struct blob *blob = lookup_blob(active_cache[i]->sha1);
			struct object *obj;
			if (!blob)
				continue;
			obj = &blob->object;
			obj->used = 1;
			mark_reachable(obj, REACHABLE);
		}
	}

	if (!heads && !keep_cache_objects) {
		if (show_unreachable) {
			fprintf(stderr, "unable to do reachability without a head nor --cache\n");
			show_unreachable = 0; 
		}
		if (!heads)
			fprintf(stderr, "expect dangling commits - potential heads - due to lack of head information\n");
	}

	check_connectivity();
	return 0;
}
Commit	Line	Data
20222118 LT	1	#include <sys/types.h>
	2	#include <dirent.h>
	3
4b182421	4	#include "cache.h"
ff5ebe39 DB	5	#include "commit.h"
	6	#include "tree.h"
	7	#include "blob.h"
c418eda4	8	#include "tag.h"
ff5ebe39 DB	9
ff5ebe39 DB	10	#define REACHABLE 0x0001
d9839e03	11
ab7df187	12	static int show_root = 0;
889262ea	13	static int show_tags = 0;
d9839e03	14	static int show_unreachable = 0;
ae7c0c92	15	static int keep_cache_objects = 0;
d9839e03 LT	16	static unsigned char head_sha1[20];
d9839e03 LT	17
8ba0bbb2 LT	18	static void check_connectivity(void)
	19	{
	20	int i;
	21
8ba0bbb2	22	/* Look up all the requirements, warn about missing objects.. */
ff5ebe39 DB	23	for (i = 0; i < nr_objs; i++) {
ff5ebe39 DB	24	struct object *obj = objs[i];
c418eda4	25	struct object_list *refs;
8ba0bbb2	26
3a6a23e6 LT	27	if (!obj->parsed) {
	28	printf("missing %s %s\n", obj->type, sha1_to_hex(obj->sha1));
	29	continue;
	30	}
	31
	32	for (refs = obj->refs; refs; refs = refs->next) {
	33	if (refs->item->parsed)
	34	continue;
	35	printf("broken link from %7s %s\n",
	36	obj->type, sha1_to_hex(obj->sha1));
	37	printf(" to %7s %s\n",
aa034134	38	refs->item->type, sha1_to_hex(refs->item->sha1));
3a6a23e6 LT	39	}
	40
	41	/* Don't bother with tag reachability. */
	42	if (obj->type == tag_type)
	43	continue;
	44
ff5ebe39	45	if (show_unreachable && !(obj->flags & REACHABLE)) {
f43b8abc	46	printf("unreachable %s %s\n", obj->type, sha1_to_hex(obj->sha1));
8ba0bbb2	47	continue;
d9839e03	48	}
8ba0bbb2	49
ff5ebe39 DB	50	if (!obj->used) {
	51	printf("dangling %s %s\n", obj->type,
	52	sha1_to_hex(obj->sha1));
d9839e03	53	}
8ba0bbb2 LT	54	}
	55	}
	56
85003492 LT	57	/*
	58	* The entries in a tree are ordered in the _path_ order,
	59	* which means that a directory entry is ordered by adding
	60	* a slash to the end of it.
	61	*
	62	* So a directory called "a" is ordered _after_ a file
	63	* called "a.c", because "a/" sorts after "a.c".
	64	*/
	65	static int verify_ordered(struct tree_entry_list a, struct tree_entry_list b)
	66	{
	67	int len1 = strlen(a->name);
	68	int len2 = strlen(b->name);
	69	int len = len1 < len2 ? len1 : len2;
	70	unsigned char c1, c2;
	71	int cmp;
	72
	73	cmp = memcmp(a->name, b->name, len);
	74	if (cmp < 0)
	75	return 0;
	76	if (cmp > 0)
	77	return -1;
	78
	79	/*
	80	* Ok, the first <len> characters are the same.
	81	* Now we need to order the next one, but turn
	82	* a '\0' into a '/' for a directory entry.
	83	*/
	84	c1 = a->name[len];
	85	c2 = b->name[len];
	86	if (!c1 && a->directory)
	87	c1 = '/';
	88	if (!c2 && b->directory)
	89	c2 = '/';
	90	return c1 < c2 ? 0 : -1;
	91	}
	92
c418eda4	93	static int fsck_tree(struct tree *item)
20222118	94	{
85003492 LT	95	int has_full_path = 0;
	96	struct tree_entry_list entry, last;
	97
	98	last = NULL;
	99	for (entry = item->entries; entry; entry = entry->next) {
	100	if (strchr(entry->name, '/'))
	101	has_full_path = 1;
	102
	103	if (last) {
	104	if (verify_ordered(last, entry) < 0) {
	105	fprintf(stderr, "tree %s not ordered\n",
	106	sha1_to_hex(item->object.sha1));
	107	return -1;
	108	}
	109	}
	110
	111	last = entry;
	112	}
	113
	114	if (has_full_path) {
ff5ebe39	115	fprintf(stderr, "warning: fsck-cache: tree %s "
c418eda4 DB	116	"has full pathnames in it\n",
c418eda4 DB	117	sha1_to_hex(item->object.sha1));
1ea34e36	118	}
85003492	119
59c1e249	120	return 0;
1ea34e36 LT	121	}
1ea34e36 LT	122
c418eda4	123	static int fsck_commit(struct commit *commit)
1ea34e36	124	{
ff5ebe39	125	if (!commit->tree)
1ea34e36	126	return -1;
ab7df187	127	if (!commit->parents && show_root)
c418eda4	128	printf("root %s\n", sha1_to_hex(commit->object.sha1));
e6948b6d	129	if (!commit->date)
c418eda4 DB	130	printf("bad commit date in %s\n",
c418eda4 DB	131	sha1_to_hex(commit->object.sha1));
4728b861 LT	132	return 0;
	133	}
	134
c418eda4	135	static int fsck_tag(struct tag *tag)
ec4465ad	136	{
92d4c85d LT	137	struct object *tagged = tag->tagged;
	138
	139	if (!tagged) {
	140	printf("bad object in tag %s\n", sha1_to_hex(tag->object.sha1));
	141	return -1;
	142	}
889262ea LT	143	if (!show_tags)
	144	return 0;
	145
92d4c85d LT	146	printf("tagged %s %s", tagged->type, sha1_to_hex(tagged->sha1));
92d4c85d LT	147	printf(" (%s) in %s\n", tag->tag, sha1_to_hex(tag->object.sha1));
ff5ebe39	148	return 0;
20222118 LT	149	}
20222118 LT	150
7e8c174a	151	static int fsck_sha1(unsigned char *sha1)
20222118	152	{
7e8c174a LT	153	struct object *obj = parse_object(sha1);
	154	if (!obj)
	155	return -1;
	156	if (obj->type == blob_type)
	157	return 0;
	158	if (obj->type == tree_type)
	159	return fsck_tree((struct tree *) obj);
	160	if (obj->type == commit_type)
	161	return fsck_commit((struct commit *) obj);
	162	if (obj->type == tag_type)
	163	return fsck_tag((struct tag *) obj);
	164	return -1;
	165	}
	166
	167	/*
	168	* This is the sorting chunk size: make it reasonably
	169	* big so that we can sort well..
	170	*/
	171	#define MAX_SHA1_ENTRIES (1024)
	172
	173	struct sha1_entry {
	174	unsigned long ino;
20222118	175	unsigned char sha1[20];
7e8c174a LT	176	};
	177
	178	static struct {
	179	unsigned long nr;
	180	struct sha1_entry *entry[MAX_SHA1_ENTRIES];
	181	} sha1_list;
	182
	183	static int ino_compare(const void _a, const void _b)
	184	{
	185	const struct sha1_entry a = _a, b = _b;
	186	unsigned long ino1 = a->ino, ino2 = b->ino;
	187	return ino1 < ino2 ? -1 : ino1 > ino2 ? 1 : 0;
	188	}
	189
	190	static void fsck_sha1_list(void)
	191	{
	192	int i, nr = sha1_list.nr;
	193
	194	qsort(sha1_list.entry, nr, sizeof(struct sha1_entry *), ino_compare);
	195	for (i = 0; i < nr; i++) {
	196	struct sha1_entry *entry = sha1_list.entry[i];
	197	unsigned char *sha1 = entry->sha1;
	198
	199	sha1_list.entry[i] = NULL;
	200	if (fsck_sha1(sha1) < 0)
	201	fprintf(stderr, "bad sha1 entry '%s'\n", sha1_to_hex(sha1));
	202	free(entry);
20222118	203	}
7e8c174a LT	204	sha1_list.nr = 0;
	205	}
	206
	207	static void add_sha1_list(unsigned char *sha1, unsigned long ino)
	208	{
	209	struct sha1_entry entry = xmalloc(sizeof(entry));
	210	int nr;
	211
	212	entry->ino = ino;
	213	memcpy(entry->sha1, sha1, 20);
	214	nr = sha1_list.nr;
	215	if (nr == MAX_SHA1_ENTRIES) {
	216	fsck_sha1_list();
	217	nr = 0;
	218	}
	219	sha1_list.entry[nr] = entry;
	220	sha1_list.nr = ++nr;
20222118 LT	221	}
	222
	223	static int fsck_dir(int i, char *path)
	224	{
	225	DIR *dir = opendir(path);
	226	struct dirent *de;
	227
	228	if (!dir) {
2de381f9	229	return error("missing sha1 directory '%s'", path);
20222118 LT	230	}
	231
	232	while ((de = readdir(dir)) != NULL) {
	233	char name[100];
7e8c174a	234	unsigned char sha1[20];
20222118 LT	235	int len = strlen(de->d_name);
	236
	237	switch (len) {
	238	case 2:
	239	if (de->d_name[1] != '.')
	240	break;
	241	case 1:
	242	if (de->d_name[0] != '.')
	243	break;
	244	continue;
	245	case 38:
	246	sprintf(name, "%02x", i);
	247	memcpy(name+2, de->d_name, len+1);
7e8c174a LT	248	if (get_sha1_hex(name, sha1) < 0)
	249	break;
	250	add_sha1_list(sha1, de->d_ino);
	251	continue;
20222118 LT	252	}
	253	fprintf(stderr, "bad sha1 file: %s/%s\n", path, de->d_name);
	254	}
	255	closedir(dir);
	256	return 0;
	257	}
	258
	259	int main(int argc, char **argv)
	260	{
bcee6fd8	261	int i, heads;
20222118 LT	262	char *sha1_dir;
20222118 LT	263
889262ea LT	264	for (i = 1; i < argc; i++) {
	265	const char *arg = argv[i];
	266
	267	if (!strcmp(arg, "--unreachable")) {
	268	show_unreachable = 1;
	269	continue;
	270	}
	271	if (!strcmp(arg, "--tags")) {
	272	show_tags = 1;
	273	continue;
	274	}
ab7df187 LT	275	if (!strcmp(arg, "--root")) {
	276	show_root = 1;
	277	continue;
	278	}
ae7c0c92 JH	279	if (!strcmp(arg, "--cache")) {
	280	keep_cache_objects = 1;
	281	continue;
	282	}
889262ea	283	if (*arg == '-')
ae7c0c92	284	usage("fsck-cache [--tags] [[--unreachable] [--cache] <head-sha1>*]");
889262ea LT	285	}
889262ea LT	286
bcee6fd8 LT	287	sha1_dir = getenv(DB_ENVIRONMENT) ? : DEFAULT_DB_ENVIRONMENT;
	288	for (i = 0; i < 256; i++) {
	289	static char dir[4096];
	290	sprintf(dir, "%s/%02x", sha1_dir, i);
	291	fsck_dir(i, dir);
	292	}
7e8c174a	293	fsck_sha1_list();
bcee6fd8 LT	294
bcee6fd8 LT	295	heads = 0;
d9839e03	296	for (i = 1; i < argc; i++) {
889262ea LT	297	const char *arg = argv[i];
	298
	299	if (*arg == '-')
d9839e03	300	continue;
889262ea	301
3c249c95	302	if (!get_sha1(arg, head_sha1)) {
770896e5	303	struct object *obj = lookup_object(head_sha1);
e1a1388d	304
770896e5 LT	305	/* Error is printed by lookup_object(). */
770896e5 LT	306	if (!obj)
e1a1388d JF	307	continue;
e1a1388d JF	308
ff5ebe39 DB	309	obj->used = 1;
ff5ebe39 DB	310	mark_reachable(obj, REACHABLE);
bcee6fd8	311	heads++;
d9839e03 LT	312	continue;
d9839e03 LT	313	}
889262ea	314	error("expected sha1, got %s", arg);
d9839e03	315	}
d9839e03	316
ae7c0c92 JH	317	if (keep_cache_objects) {
	318	int i;
	319	read_cache();
	320	for (i = 0; i < active_nr; i++) {
	321	struct blob *blob = lookup_blob(active_cache[i]->sha1);
	322	struct object *obj;
	323	if (!blob)
	324	continue;
	325	obj = &blob->object;
	326	obj->used = 1;
	327	mark_reachable(obj, REACHABLE);
	328	}
	329	}
	330
	331	if (!heads && !keep_cache_objects) {
bcee6fd8	332	if (show_unreachable) {
ae7c0c92	333	fprintf(stderr, "unable to do reachability without a head nor --cache\n");
bcee6fd8 LT	334	show_unreachable = 0;
bcee6fd8 LT	335	}
ae7c0c92 JH	336	if (!heads)
ae7c0c92 JH	337	fprintf(stderr, "expect dangling commits - potential heads - due to lack of head information\n");
20222118	338	}
bcee6fd8	339
8ba0bbb2	340	check_connectivity();
20222118 LT	341	return 0;
20222118 LT	342	}