[git/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 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 (*arg == '-')
			usage("fsck-cache [--tags] [[--unreachable] <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 commit *commit = lookup_commit(head_sha1);
			struct object *obj;

			/* Error is printed by lookup_commit(). */
			if (!commit)
				continue;

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

	if (!heads) {
		if (show_unreachable) {
			fprintf(stderr, "unable to do reachability without a head\n");
			show_unreachable = 0; 
		}
		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;
d9839e03 LT	15	static unsigned char head_sha1[20];
d9839e03 LT	16
8ba0bbb2 LT	17	static void check_connectivity(void)
	18	{
	19	int i;
	20
8ba0bbb2	21	/* Look up all the requirements, warn about missing objects.. */
ff5ebe39 DB	22	for (i = 0; i < nr_objs; i++) {
ff5ebe39 DB	23	struct object *obj = objs[i];
c418eda4	24	struct object_list *refs;
8ba0bbb2	25
3a6a23e6 LT	26	if (!obj->parsed) {
	27	printf("missing %s %s\n", obj->type, sha1_to_hex(obj->sha1));
	28	continue;
	29	}
	30
	31	for (refs = obj->refs; refs; refs = refs->next) {
	32	if (refs->item->parsed)
	33	continue;
	34	printf("broken link from %7s %s\n",
	35	obj->type, sha1_to_hex(obj->sha1));
	36	printf(" to %7s %s\n",
aa034134	37	refs->item->type, sha1_to_hex(refs->item->sha1));
3a6a23e6 LT	38	}
	39
	40	/* Don't bother with tag reachability. */
	41	if (obj->type == tag_type)
	42	continue;
	43
ff5ebe39	44	if (show_unreachable && !(obj->flags & REACHABLE)) {
f43b8abc	45	printf("unreachable %s %s\n", obj->type, sha1_to_hex(obj->sha1));
8ba0bbb2	46	continue;
d9839e03	47	}
8ba0bbb2	48
ff5ebe39 DB	49	if (!obj->used) {
	50	printf("dangling %s %s\n", obj->type,
	51	sha1_to_hex(obj->sha1));
d9839e03	52	}
8ba0bbb2 LT	53	}
	54	}
	55
85003492 LT	56	/*
	57	* The entries in a tree are ordered in the _path_ order,
	58	* which means that a directory entry is ordered by adding
	59	* a slash to the end of it.
	60	*
	61	* So a directory called "a" is ordered _after_ a file
	62	* called "a.c", because "a/" sorts after "a.c".
	63	*/
	64	static int verify_ordered(struct tree_entry_list a, struct tree_entry_list b)
	65	{
	66	int len1 = strlen(a->name);
	67	int len2 = strlen(b->name);
	68	int len = len1 < len2 ? len1 : len2;
	69	unsigned char c1, c2;
	70	int cmp;
	71
	72	cmp = memcmp(a->name, b->name, len);
	73	if (cmp < 0)
	74	return 0;
	75	if (cmp > 0)
	76	return -1;
	77
	78	/*
	79	* Ok, the first <len> characters are the same.
	80	* Now we need to order the next one, but turn
	81	* a '\0' into a '/' for a directory entry.
	82	*/
	83	c1 = a->name[len];
	84	c2 = b->name[len];
	85	if (!c1 && a->directory)
	86	c1 = '/';
	87	if (!c2 && b->directory)
	88	c2 = '/';
	89	return c1 < c2 ? 0 : -1;
	90	}
	91
c418eda4	92	static int fsck_tree(struct tree *item)
20222118	93	{
85003492 LT	94	int has_full_path = 0;
	95	struct tree_entry_list entry, last;
	96
	97	last = NULL;
	98	for (entry = item->entries; entry; entry = entry->next) {
	99	if (strchr(entry->name, '/'))
	100	has_full_path = 1;
	101
	102	if (last) {
	103	if (verify_ordered(last, entry) < 0) {
	104	fprintf(stderr, "tree %s not ordered\n",
	105	sha1_to_hex(item->object.sha1));
	106	return -1;
	107	}
	108	}
	109
	110	last = entry;
	111	}
	112
	113	if (has_full_path) {
ff5ebe39	114	fprintf(stderr, "warning: fsck-cache: tree %s "
c418eda4 DB	115	"has full pathnames in it\n",
c418eda4 DB	116	sha1_to_hex(item->object.sha1));
1ea34e36	117	}
85003492	118
59c1e249	119	return 0;
1ea34e36 LT	120	}
1ea34e36 LT	121
c418eda4	122	static int fsck_commit(struct commit *commit)
1ea34e36	123	{
ff5ebe39	124	if (!commit->tree)
1ea34e36	125	return -1;
ab7df187	126	if (!commit->parents && show_root)
c418eda4	127	printf("root %s\n", sha1_to_hex(commit->object.sha1));
e6948b6d	128	if (!commit->date)
c418eda4 DB	129	printf("bad commit date in %s\n",
c418eda4 DB	130	sha1_to_hex(commit->object.sha1));
4728b861 LT	131	return 0;
	132	}
	133
c418eda4	134	static int fsck_tag(struct tag *tag)
ec4465ad	135	{
92d4c85d LT	136	struct object *tagged = tag->tagged;
	137
	138	if (!tagged) {
	139	printf("bad object in tag %s\n", sha1_to_hex(tag->object.sha1));
	140	return -1;
	141	}
889262ea LT	142	if (!show_tags)
	143	return 0;
	144
92d4c85d LT	145	printf("tagged %s %s", tagged->type, sha1_to_hex(tagged->sha1));
92d4c85d LT	146	printf(" (%s) in %s\n", tag->tag, sha1_to_hex(tag->object.sha1));
ff5ebe39	147	return 0;
20222118 LT	148	}
20222118 LT	149
7e8c174a	150	static int fsck_sha1(unsigned char *sha1)
20222118	151	{
7e8c174a LT	152	struct object *obj = parse_object(sha1);
	153	if (!obj)
	154	return -1;
	155	if (obj->type == blob_type)
	156	return 0;
	157	if (obj->type == tree_type)
	158	return fsck_tree((struct tree *) obj);
	159	if (obj->type == commit_type)
	160	return fsck_commit((struct commit *) obj);
	161	if (obj->type == tag_type)
	162	return fsck_tag((struct tag *) obj);
	163	return -1;
	164	}
	165
	166	/*
	167	* This is the sorting chunk size: make it reasonably
	168	* big so that we can sort well..
	169	*/
	170	#define MAX_SHA1_ENTRIES (1024)
	171
	172	struct sha1_entry {
	173	unsigned long ino;
20222118	174	unsigned char sha1[20];
7e8c174a LT	175	};
	176
	177	static struct {
	178	unsigned long nr;
	179	struct sha1_entry *entry[MAX_SHA1_ENTRIES];
	180	} sha1_list;
	181
	182	static int ino_compare(const void _a, const void _b)
	183	{
	184	const struct sha1_entry a = _a, b = _b;
	185	unsigned long ino1 = a->ino, ino2 = b->ino;
	186	return ino1 < ino2 ? -1 : ino1 > ino2 ? 1 : 0;
	187	}
	188
	189	static void fsck_sha1_list(void)
	190	{
	191	int i, nr = sha1_list.nr;
	192
	193	qsort(sha1_list.entry, nr, sizeof(struct sha1_entry *), ino_compare);
	194	for (i = 0; i < nr; i++) {
	195	struct sha1_entry *entry = sha1_list.entry[i];
	196	unsigned char *sha1 = entry->sha1;
	197
	198	sha1_list.entry[i] = NULL;
	199	if (fsck_sha1(sha1) < 0)
	200	fprintf(stderr, "bad sha1 entry '%s'\n", sha1_to_hex(sha1));
	201	free(entry);
20222118	202	}
7e8c174a LT	203	sha1_list.nr = 0;
	204	}
	205
	206	static void add_sha1_list(unsigned char *sha1, unsigned long ino)
	207	{
	208	struct sha1_entry entry = xmalloc(sizeof(entry));
	209	int nr;
	210
	211	entry->ino = ino;
	212	memcpy(entry->sha1, sha1, 20);
	213	nr = sha1_list.nr;
	214	if (nr == MAX_SHA1_ENTRIES) {
	215	fsck_sha1_list();
	216	nr = 0;
	217	}
	218	sha1_list.entry[nr] = entry;
	219	sha1_list.nr = ++nr;
20222118 LT	220	}
	221
	222	static int fsck_dir(int i, char *path)
	223	{
	224	DIR *dir = opendir(path);
	225	struct dirent *de;
	226
	227	if (!dir) {
2de381f9	228	return error("missing sha1 directory '%s'", path);
20222118 LT	229	}
	230
	231	while ((de = readdir(dir)) != NULL) {
	232	char name[100];
7e8c174a	233	unsigned char sha1[20];
20222118 LT	234	int len = strlen(de->d_name);
	235
	236	switch (len) {
	237	case 2:
	238	if (de->d_name[1] != '.')
	239	break;
	240	case 1:
	241	if (de->d_name[0] != '.')
	242	break;
	243	continue;
	244	case 38:
	245	sprintf(name, "%02x", i);
	246	memcpy(name+2, de->d_name, len+1);
7e8c174a LT	247	if (get_sha1_hex(name, sha1) < 0)
	248	break;
	249	add_sha1_list(sha1, de->d_ino);
	250	continue;
20222118 LT	251	}
	252	fprintf(stderr, "bad sha1 file: %s/%s\n", path, de->d_name);
	253	}
	254	closedir(dir);
	255	return 0;
	256	}
	257
	258	int main(int argc, char **argv)
	259	{
bcee6fd8	260	int i, heads;
20222118 LT	261	char *sha1_dir;
20222118 LT	262
889262ea LT	263	for (i = 1; i < argc; i++) {
	264	const char *arg = argv[i];
	265
	266	if (!strcmp(arg, "--unreachable")) {
	267	show_unreachable = 1;
	268	continue;
	269	}
	270	if (!strcmp(arg, "--tags")) {
	271	show_tags = 1;
	272	continue;
	273	}
ab7df187 LT	274	if (!strcmp(arg, "--root")) {
	275	show_root = 1;
	276	continue;
	277	}
889262ea LT	278	if (*arg == '-')
	279	usage("fsck-cache [--tags] [[--unreachable] <head-sha1>*]");
	280	}
	281
bcee6fd8 LT	282	sha1_dir = getenv(DB_ENVIRONMENT) ? : DEFAULT_DB_ENVIRONMENT;
	283	for (i = 0; i < 256; i++) {
	284	static char dir[4096];
	285	sprintf(dir, "%s/%02x", sha1_dir, i);
	286	fsck_dir(i, dir);
	287	}
7e8c174a	288	fsck_sha1_list();
bcee6fd8 LT	289
bcee6fd8 LT	290	heads = 0;
d9839e03	291	for (i = 1; i < argc; i++) {
889262ea LT	292	const char *arg = argv[i];
	293
	294	if (*arg == '-')
d9839e03	295	continue;
889262ea	296
3c249c95	297	if (!get_sha1(arg, head_sha1)) {
e1a1388d JF	298	struct commit *commit = lookup_commit(head_sha1);
	299	struct object *obj;
	300
	301	/* Error is printed by lookup_commit(). */
	302	if (!commit)
	303	continue;
	304
	305	obj = &commit->object;
ff5ebe39 DB	306	obj->used = 1;
ff5ebe39 DB	307	mark_reachable(obj, REACHABLE);
bcee6fd8	308	heads++;
d9839e03 LT	309	continue;
d9839e03 LT	310	}
889262ea	311	error("expected sha1, got %s", arg);
d9839e03	312	}
d9839e03	313
bcee6fd8 LT	314	if (!heads) {
	315	if (show_unreachable) {
	316	fprintf(stderr, "unable to do reachability without a head\n");
	317	show_unreachable = 0;
	318	}
	319	fprintf(stderr, "expect dangling commits - potential heads - due to lack of head information\n");
20222118	320	}
bcee6fd8	321
8ba0bbb2	322	check_connectivity();
20222118 LT	323	return 0;
20222118 LT	324	}