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

#include "builtin.h"
#include "cache.h"
#include "commit.h"
#include "tree.h"
#include "blob.h"
#include "tag.h"
#include "refs.h"
#include "pack.h"
#include "cache-tree.h"
#include "tree-walk.h"
#include "fsck.h"
#include "parse-options.h"

#define REACHABLE 0x0001
#define SEEN      0x0002

static int show_root;
static int show_tags;
static int show_unreachable;
static int include_reflogs = 1;
static int check_full;
static int check_strict;
static int keep_cache_objects;
static unsigned char head_sha1[20];
static int errors_found;
static int write_lost_and_found;
static int verbose;
#define ERROR_OBJECT 01
#define ERROR_REACHABLE 02

#ifdef NO_D_INO_IN_DIRENT
#define SORT_DIRENT 0
#define DIRENT_SORT_HINT(de) 0
#else
#define SORT_DIRENT 1
#define DIRENT_SORT_HINT(de) ((de)->d_ino)
#endif

static void objreport(struct object *obj, const char *severity,
                      const char *err, va_list params)
{
	fprintf(stderr, "%s in %s %s: ",
	        severity, typename(obj->type), sha1_to_hex(obj->sha1));
	vfprintf(stderr, err, params);
	fputs("\n", stderr);
}

static int objerror(struct object *obj, const char *err, ...)
{
	va_list params;
	va_start(params, err);
	errors_found |= ERROR_OBJECT;
	objreport(obj, "error", err, params);
	va_end(params);
	return -1;
}

static int fsck_error_func(struct object *obj, int type, const char *err, ...)
{
	va_list params;
	va_start(params, err);
	objreport(obj, (type == FSCK_WARN) ? "warning" : "error", err, params);
	va_end(params);
	return (type == FSCK_WARN) ? 0 : 1;
}

static int mark_object(struct object *obj, int type, void *data)
{
	struct tree *tree = NULL;
	struct object *parent = data;
	int result;

	if (!obj) {
		printf("broken link from %7s %s\n",
			   typename(parent->type), sha1_to_hex(parent->sha1));
		printf("broken link from %7s %s\n",
			   (type == OBJ_ANY ? "unknown" : typename(type)), "unknown");
		errors_found |= ERROR_REACHABLE;
		return 1;
	}

	if (type != OBJ_ANY && obj->type != type)
		objerror(parent, "wrong object type in link");

	if (obj->flags & REACHABLE)
		return 0;
	obj->flags |= REACHABLE;
	if (!obj->parsed) {
		if (parent && !has_sha1_file(obj->sha1)) {
			printf("broken link from %7s %s\n",
				 typename(parent->type), sha1_to_hex(parent->sha1));
			printf("              to %7s %s\n",
				 typename(obj->type), sha1_to_hex(obj->sha1));
			errors_found |= ERROR_REACHABLE;
		}
		return 1;
	}

	if (obj->type == OBJ_TREE) {
		obj->parsed = 0;
		tree = (struct tree *)obj;
		if (parse_tree(tree) < 0)
			return 1; /* error already displayed */
	}
	result = fsck_walk(obj, mark_object, obj);
	if (tree) {
		free(tree->buffer);
		tree->buffer = NULL;
	}
	if (result < 0)
		result = 1;

	return result;
}

static void mark_object_reachable(struct object *obj)
{
	mark_object(obj, OBJ_ANY, 0);
}

static int mark_used(struct object *obj, int type, void *data)
{
	if (!obj)
		return 1;
	obj->used = 1;
	return 0;
}

/*
 * Check a single reachable object
 */
static void check_reachable_object(struct object *obj)
{
	/*
	 * We obviously want the object to be parsed,
	 * except if it was in a pack-file and we didn't
	 * do a full fsck
	 */
	if (!obj->parsed) {
		if (has_sha1_pack(obj->sha1, NULL))
			return; /* it is in pack - forget about it */
		printf("missing %s %s\n", typename(obj->type), sha1_to_hex(obj->sha1));
		errors_found |= ERROR_REACHABLE;
		return;
	}
}

/*
 * Check a single unreachable object
 */
static void check_unreachable_object(struct object *obj)
{
	/*
	 * Missing unreachable object? Ignore it. It's not like
	 * we miss it (since it can't be reached), nor do we want
	 * to complain about it being unreachable (since it does
	 * not exist).
	 */
	if (!obj->parsed)
		return;

	/*
	 * Unreachable object that exists? Show it if asked to,
	 * since this is something that is prunable.
	 */
	if (show_unreachable) {
		printf("unreachable %s %s\n", typename(obj->type), sha1_to_hex(obj->sha1));
		return;
	}

	/*
	 * "!used" means that nothing at all points to it, including
	 * other unreachable objects. In other words, it's the "tip"
	 * of some set of unreachable objects, usually a commit that
	 * got dropped.
	 *
	 * Such starting points are more interesting than some random
	 * set of unreachable objects, so we show them even if the user
	 * hasn't asked for _all_ unreachable objects. If you have
	 * deleted a branch by mistake, this is a prime candidate to
	 * start looking at, for example.
	 */
	if (!obj->used) {
		printf("dangling %s %s\n", typename(obj->type),
		       sha1_to_hex(obj->sha1));
		if (write_lost_and_found) {
			char *filename = git_path("lost-found/%s/%s",
				obj->type == OBJ_COMMIT ? "commit" : "other",
				sha1_to_hex(obj->sha1));
			FILE *f;

			if (safe_create_leading_directories(filename)) {
				error("Could not create lost-found");
				return;
			}
			if (!(f = fopen(filename, "w")))
				die("Could not open %s", filename);
			if (obj->type == OBJ_BLOB) {
				enum object_type type;
				unsigned long size;
				char *buf = read_sha1_file(obj->sha1,
						&type, &size);
				if (buf) {
					fwrite(buf, size, 1, f);
					free(buf);
				}
			} else
				fprintf(f, "%s\n", sha1_to_hex(obj->sha1));
			fclose(f);
		}
		return;
	}

	/*
	 * Otherwise? It's there, it's unreachable, and some other unreachable
	 * object points to it. Ignore it - it's not interesting, and we showed
	 * all the interesting cases above.
	 */
}

static void check_object(struct object *obj)
{
	if (verbose)
		fprintf(stderr, "Checking %s\n", sha1_to_hex(obj->sha1));

	if (obj->flags & REACHABLE)
		check_reachable_object(obj);
	else
		check_unreachable_object(obj);
}

static void check_connectivity(void)
{
	int i, max;

	/* Look up all the requirements, warn about missing objects.. */
	max = get_max_object_index();
	if (verbose)
		fprintf(stderr, "Checking connectivity (%d objects)\n", max);

	for (i = 0; i < max; i++) {
		struct object *obj = get_indexed_object(i);

		if (obj)
			check_object(obj);
	}
}

static int fsck_sha1(const unsigned char *sha1)
{
	struct object *obj = parse_object(sha1);
	if (!obj) {
		errors_found |= ERROR_OBJECT;
		return error("%s: object corrupt or missing",
			     sha1_to_hex(sha1));
	}
	if (obj->flags & SEEN)
		return 0;
	obj->flags |= SEEN;

	if (verbose)
		fprintf(stderr, "Checking %s %s\n",
			typename(obj->type), sha1_to_hex(obj->sha1));

	if (fsck_walk(obj, mark_used, 0))
		objerror(obj, "broken links");
	if (fsck_object(obj, check_strict, fsck_error_func))
		return -1;

	if (obj->type == OBJ_TREE) {
		struct tree *item = (struct tree *) obj;

		free(item->buffer);
		item->buffer = NULL;
	}

	if (obj->type == OBJ_COMMIT) {
		struct commit *commit = (struct commit *) obj;

		free(commit->buffer);
		commit->buffer = NULL;

		if (!commit->parents && show_root)
			printf("root %s\n", sha1_to_hex(commit->object.sha1));
	}

	if (obj->type == OBJ_TAG) {
		struct tag *tag = (struct tag *) obj;

		if (show_tags && tag->tagged) {
			printf("tagged %s %s", typename(tag->tagged->type), sha1_to_hex(tag->tagged->sha1));
			printf(" (%s) in %s\n", tag->tag, sha1_to_hex(tag->object.sha1));
		}
	}

	return 0;
}

/*
 * 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;

	if (SORT_DIRENT)
		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;
		fsck_sha1(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;
	hashcpy(entry->sha1, sha1);
	nr = sha1_list.nr;
	if (nr == MAX_SHA1_ENTRIES) {
		fsck_sha1_list();
		nr = 0;
	}
	sha1_list.entry[nr] = entry;
	sha1_list.nr = ++nr;
}

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

	if (!dir)
		return;

	if (verbose)
		fprintf(stderr, "Checking directory %s\n", 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, DIRENT_SORT_HINT(de));
			continue;
		}
		if (!prefixcmp(de->d_name, "tmp_obj_"))
			continue;
		fprintf(stderr, "bad sha1 file: %s/%s\n", path, de->d_name);
	}
	closedir(dir);
}

static int default_refs;

static int fsck_handle_reflog_ent(unsigned char *osha1, unsigned char *nsha1,
		const char *email, unsigned long timestamp, int tz,
		const char *message, void *cb_data)
{
	struct object *obj;

	if (verbose)
		fprintf(stderr, "Checking reflog %s->%s\n",
			sha1_to_hex(osha1), sha1_to_hex(nsha1));

	if (!is_null_sha1(osha1)) {
		obj = lookup_object(osha1);
		if (obj) {
			obj->used = 1;
			mark_object_reachable(obj);
		}
	}
	obj = lookup_object(nsha1);
	if (obj) {
		obj->used = 1;
		mark_object_reachable(obj);
	}
	return 0;
}

static int fsck_handle_reflog(const char *logname, const unsigned char *sha1, int flag, void *cb_data)
{
	for_each_reflog_ent(logname, fsck_handle_reflog_ent, NULL);
	return 0;
}

static int is_branch(const char *refname)
{
	return !strcmp(refname, "HEAD") || !prefixcmp(refname, "refs/heads/");
}

static int fsck_handle_ref(const char *refname, const unsigned char *sha1, int flag, void *cb_data)
{
	struct object *obj;

	obj = parse_object(sha1);
	if (!obj) {
		error("%s: invalid sha1 pointer %s", refname, sha1_to_hex(sha1));
		/* We'll continue with the rest despite the error.. */
		return 0;
	}
	if (obj->type != OBJ_COMMIT && is_branch(refname))
		error("%s: not a commit", refname);
	default_refs++;
	obj->used = 1;
	mark_object_reachable(obj);

	return 0;
}

static void get_default_heads(void)
{
	for_each_ref(fsck_handle_ref, NULL);
	if (include_reflogs)
		for_each_reflog(fsck_handle_reflog, NULL);

	/*
	 * Not having any default heads isn't really fatal, but
	 * it does mean that "--unreachable" no longer makes any
	 * sense (since in this case everything will obviously
	 * be unreachable by definition.
	 *
	 * Showing dangling objects is valid, though (as those
	 * dangling objects are likely lost heads).
	 *
	 * So we just print a warning about it, and clear the
	 * "show_unreachable" flag.
	 */
	if (!default_refs) {
		fprintf(stderr, "notice: No default references\n");
		show_unreachable = 0;
	}
}

static void fsck_object_dir(const char *path)
{
	int i;

	if (verbose)
		fprintf(stderr, "Checking object directory\n");

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

static int fsck_head_link(void)
{
	unsigned char sha1[20];
	int flag;
	int null_is_error = 0;
	const char *head_points_at = resolve_ref("HEAD", sha1, 0, &flag);

	if (verbose)
		fprintf(stderr, "Checking HEAD link\n");

	if (!head_points_at)
		return error("Invalid HEAD");
	if (!strcmp(head_points_at, "HEAD"))
		/* detached HEAD */
		null_is_error = 1;
	else if (prefixcmp(head_points_at, "refs/heads/"))
		return error("HEAD points to something strange (%s)",
			     head_points_at);
	if (is_null_sha1(sha1)) {
		if (null_is_error)
			return error("HEAD: detached HEAD points at nothing");
		fprintf(stderr, "notice: HEAD points to an unborn branch (%s)\n",
			head_points_at + 11);
	}
	return 0;
}

static int fsck_cache_tree(struct cache_tree *it)
{
	int i;
	int err = 0;

	if (verbose)
		fprintf(stderr, "Checking cache tree\n");

	if (0 <= it->entry_count) {
		struct object *obj = parse_object(it->sha1);
		if (!obj) {
			error("%s: invalid sha1 pointer in cache-tree",
			      sha1_to_hex(it->sha1));
			return 1;
		}
		mark_object_reachable(obj);
		obj->used = 1;
		if (obj->type != OBJ_TREE)
			err |= objerror(obj, "non-tree in cache-tree");
	}
	for (i = 0; i < it->subtree_nr; i++)
		err |= fsck_cache_tree(it->down[i]->cache_tree);
	return err;
}

static char const * const fsck_usage[] = {
	"git fsck [options] [<object>...]",
	NULL
};

static struct option fsck_opts[] = {
	OPT__VERBOSE(&verbose),
	OPT_BOOLEAN(0, "unreachable", &show_unreachable, "show unreachable objects"),
	OPT_BOOLEAN(0, "tags", &show_tags, "report tags"),
	OPT_BOOLEAN(0, "root", &show_root, "report root nodes"),
	OPT_BOOLEAN(0, "cache", &keep_cache_objects, "make index objects head nodes"),
	OPT_BOOLEAN(0, "reflogs", &include_reflogs, "make reflogs head nodes (default)"),
	OPT_BOOLEAN(0, "full", &check_full, "also consider alternate objects"),
	OPT_BOOLEAN(0, "strict", &check_strict, "enable more strict checking"),
	OPT_BOOLEAN(0, "lost-found", &write_lost_and_found,
				"write dangling objects in .git/lost-found"),
	OPT_END(),
};

int cmd_fsck(int argc, const char **argv, const char *prefix)
{
	int i, heads;

	errors_found = 0;

	argc = parse_options(argc, argv, fsck_opts, fsck_usage, 0);
	if (write_lost_and_found) {
		check_full = 1;
		include_reflogs = 0;
	}

	fsck_head_link();
	fsck_object_dir(get_object_directory());
	if (check_full) {
		struct alternate_object_database *alt;
		struct packed_git *p;
		prepare_alt_odb();
		for (alt = alt_odb_list; alt; alt = alt->next) {
			char namebuf[PATH_MAX];
			int namelen = alt->name - alt->base;
			memcpy(namebuf, alt->base, namelen);
			namebuf[namelen - 1] = 0;
			fsck_object_dir(namebuf);
		}
		prepare_packed_git();
		for (p = packed_git; p; p = p->next)
			/* verify gives error messages itself */
			verify_pack(p);

		for (p = packed_git; p; p = p->next) {
			uint32_t j, num;
			if (open_pack_index(p))
				continue;
			num = p->num_objects;
			for (j = 0; j < num; j++)
				fsck_sha1(nth_packed_object_sha1(p, j));
		}
	}

	heads = 0;
	for (i = 1; i < argc; i++) {
		const char *arg = argv[i];
		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_object_reachable(obj);
			heads++;
			continue;
		}
		error("invalid parameter: expected sha1, got '%s'", arg);
	}

	/*
	 * If we've not been given any explicit head information, do the
	 * default ones from .git/refs. We also consider the index file
	 * in this case (ie this implies --cache).
	 */
	if (!heads) {
		get_default_heads();
		keep_cache_objects = 1;
	}

	if (keep_cache_objects) {
		read_cache();
		for (i = 0; i < active_nr; i++) {
			unsigned int mode;
			struct blob *blob;
			struct object *obj;

			mode = active_cache[i]->ce_mode;
			if (S_ISGITLINK(mode))
				continue;
			blob = lookup_blob(active_cache[i]->sha1);
			if (!blob)
				continue;
			obj = &blob->object;
			obj->used = 1;
			mark_object_reachable(obj);
		}
		if (active_cache_tree)
			fsck_cache_tree(active_cache_tree);
	}

	check_connectivity();
	return errors_found;
}
Commit	Line	Data
baffc0e7	1	#include "builtin.h"
4b182421	2	#include "cache.h"
ff5ebe39 DB	3	#include "commit.h"
	4	#include "tree.h"
	5	#include "blob.h"
c418eda4	6	#include "tag.h"
944d8589	7	#include "refs.h"
f9253394	8	#include "pack.h"
53dc3f3e	9	#include "cache-tree.h"
e9a95bef	10	#include "tree-walk.h"
271b8d25	11	#include "fsck.h"
5ac0a206	12	#include "parse-options.h"
ff5ebe39 DB	13
ff5ebe39 DB	14	#define REACHABLE 0x0001
2d9c58c6	15	#define SEEN 0x0002
d9839e03	16
96f1e58f DR	17	static int show_root;
	18	static int show_tags;
	19	static int show_unreachable;
566842f6	20	static int include_reflogs = 1;
96f1e58f DR	21	static int check_full;
	22	static int check_strict;
	23	static int keep_cache_objects;
d9839e03	24	static unsigned char head_sha1[20];
e2b4f635	25	static int errors_found;
68f6c019	26	static int write_lost_and_found;
20f1eb6b	27	static int verbose;
e2b4f635 JH	28	#define ERROR_OBJECT 01
e2b4f635 JH	29	#define ERROR_REACHABLE 02
d9839e03	30
962554c6	31	#ifdef NO_D_INO_IN_DIRENT
35a730f0 JH	32	#define SORT_DIRENT 0
	33	#define DIRENT_SORT_HINT(de) 0
	34	#else
	35	#define SORT_DIRENT 1
	36	#define DIRENT_SORT_HINT(de) ((de)->d_ino)
	37	#endif
f1f0d088 PB	38
	39	static void objreport(struct object obj, const char severity,
	40	const char *err, va_list params)
	41	{
	42	fprintf(stderr, "%s in %s %s: ",
885a86ab	43	severity, typename(obj->type), sha1_to_hex(obj->sha1));
f1f0d088 PB	44	vfprintf(stderr, err, params);
	45	fputs("\n", stderr);
	46	}
	47
a7928f8e	48	static int objerror(struct object obj, const char err, ...)
f1f0d088 PB	49	{
	50	va_list params;
	51	va_start(params, err);
e2b4f635	52	errors_found \|= ERROR_OBJECT;
f1f0d088 PB	53	objreport(obj, "error", err, params);
	54	va_end(params);
	55	return -1;
	56	}
	57
ba002f3b	58	static int fsck_error_func(struct object obj, int type, const char err, ...)
f1f0d088 PB	59	{
	60	va_list params;
	61	va_start(params, err);
ba002f3b	62	objreport(obj, (type == FSCK_WARN) ? "warning" : "error", err, params);
f1f0d088	63	va_end(params);
ba002f3b	64	return (type == FSCK_WARN) ? 0 : 1;
f1f0d088 PB	65	}
f1f0d088 PB	66
271b8d25 MK	67	static int mark_object(struct object obj, int type, void data)
	68	{
	69	struct tree *tree = NULL;
	70	struct object *parent = data;
	71	int result;
	72
	73	if (!obj) {
	74	printf("broken link from %7s %s\n",
	75	typename(parent->type), sha1_to_hex(parent->sha1));
	76	printf("broken link from %7s %s\n",
	77	(type == OBJ_ANY ? "unknown" : typename(type)), "unknown");
	78	errors_found \|= ERROR_REACHABLE;
	79	return 1;
	80	}
	81
	82	if (type != OBJ_ANY && obj->type != type)
	83	objerror(parent, "wrong object type in link");
	84
	85	if (obj->flags & REACHABLE)
	86	return 0;
	87	obj->flags \|= REACHABLE;
	88	if (!obj->parsed) {
	89	if (parent && !has_sha1_file(obj->sha1)) {
	90	printf("broken link from %7s %s\n",
	91	typename(parent->type), sha1_to_hex(parent->sha1));
	92	printf(" to %7s %s\n",
	93	typename(obj->type), sha1_to_hex(obj->sha1));
	94	errors_found \|= ERROR_REACHABLE;
	95	}
	96	return 1;
	97	}
	98
	99	if (obj->type == OBJ_TREE) {
	100	obj->parsed = 0;
	101	tree = (struct tree *)obj;
	102	if (parse_tree(tree) < 0)
	103	return 1; /* error already displayed */
	104	}
	105	result = fsck_walk(obj, mark_object, obj);
	106	if (tree) {
	107	free(tree->buffer);
	108	tree->buffer = NULL;
	109	}
	110	if (result < 0)
	111	result = 1;
	112
	113	return result;
	114	}
	115
	116	static void mark_object_reachable(struct object *obj)
	117	{
	118	mark_object(obj, OBJ_ANY, 0);
	119	}
	120
	121	static int mark_used(struct object obj, int type, void data)
	122	{
	123	if (!obj)
	124	return 1;
	125	obj->used = 1;
	126	return 0;
f1f0d088 PB	127	}
f1f0d088 PB	128
18af29f2 LT	129	/*
	130	* Check a single reachable object
	131	*/
	132	static void check_reachable_object(struct object *obj)
	133	{
18af29f2 LT	134	/*
	135	* We obviously want the object to be parsed,
	136	* except if it was in a pack-file and we didn't
	137	* do a full fsck
	138	*/
	139	if (!obj->parsed) {
efec43c0	140	if (has_sha1_pack(obj->sha1, NULL))
18af29f2 LT	141	return; /* it is in pack - forget about it */
18af29f2 LT	142	printf("missing %s %s\n", typename(obj->type), sha1_to_hex(obj->sha1));
e2b4f635	143	errors_found \|= ERROR_REACHABLE;
18af29f2 LT	144	return;
18af29f2 LT	145	}
18af29f2 LT	146	}
	147
	148	/*
	149	* Check a single unreachable object
	150	*/
	151	static void check_unreachable_object(struct object *obj)
	152	{
	153	/*
	154	* Missing unreachable object? Ignore it. It's not like
	155	* we miss it (since it can't be reached), nor do we want
	156	* to complain about it being unreachable (since it does
	157	* not exist).
	158	*/
	159	if (!obj->parsed)
	160	return;
	161
	162	/*
	163	* Unreachable object that exists? Show it if asked to,
	164	* since this is something that is prunable.
	165	*/
	166	if (show_unreachable) {
	167	printf("unreachable %s %s\n", typename(obj->type), sha1_to_hex(obj->sha1));
	168	return;
	169	}
	170
	171	/*
	172	* "!used" means that nothing at all points to it, including
3dff5379	173	* other unreachable objects. In other words, it's the "tip"
18af29f2 LT	174	* of some set of unreachable objects, usually a commit that
	175	* got dropped.
	176	*
	177	* Such starting points are more interesting than some random
	178	* set of unreachable objects, so we show them even if the user
	179	* hasn't asked for _all_ unreachable objects. If you have
	180	* deleted a branch by mistake, this is a prime candidate to
	181	* start looking at, for example.
	182	*/
	183	if (!obj->used) {
	184	printf("dangling %s %s\n", typename(obj->type),
	185	sha1_to_hex(obj->sha1));
68f6c019 JS	186	if (write_lost_and_found) {
	187	char *filename = git_path("lost-found/%s/%s",
	188	obj->type == OBJ_COMMIT ? "commit" : "other",
	189	sha1_to_hex(obj->sha1));
	190	FILE *f;
	191
	192	if (safe_create_leading_directories(filename)) {
	193	error("Could not create lost-found");
	194	return;
	195	}
	196	if (!(f = fopen(filename, "w")))
	197	die("Could not open %s", filename);
16a7fcfe JS	198	if (obj->type == OBJ_BLOB) {
	199	enum object_type type;
	200	unsigned long size;
	201	char *buf = read_sha1_file(obj->sha1,
	202	&type, &size);
	203	if (buf) {
	204	fwrite(buf, size, 1, f);
	205	free(buf);
	206	}
	207	} else
	208	fprintf(f, "%s\n", sha1_to_hex(obj->sha1));
68f6c019 JS	209	fclose(f);
68f6c019 JS	210	}
18af29f2 LT	211	return;
	212	}
	213
	214	/*
	215	* Otherwise? It's there, it's unreachable, and some other unreachable
	216	* object points to it. Ignore it - it's not interesting, and we showed
	217	* all the interesting cases above.
	218	*/
	219	}
	220
	221	static void check_object(struct object *obj)
	222	{
20f1eb6b JS	223	if (verbose)
	224	fprintf(stderr, "Checking %s\n", sha1_to_hex(obj->sha1));
	225
18af29f2 LT	226	if (obj->flags & REACHABLE)
	227	check_reachable_object(obj);
	228	else
	229	check_unreachable_object(obj);
	230	}
f1f0d088	231
8ba0bbb2 LT	232	static void check_connectivity(void)
8ba0bbb2 LT	233	{
fc046a75	234	int i, max;
8ba0bbb2	235
8ba0bbb2	236	/* Look up all the requirements, warn about missing objects.. */
fc046a75	237	max = get_max_object_index();
20f1eb6b JS	238	if (verbose)
	239	fprintf(stderr, "Checking connectivity (%d objects)\n", max);
	240
fc046a75	241	for (i = 0; i < max; i++) {
fc046a75	242	struct object *obj = get_indexed_object(i);
8ba0bbb2	243
18af29f2 LT	244	if (obj)
18af29f2 LT	245	check_object(obj);
8ba0bbb2 LT	246	}
	247	}
	248
ba002f3b	249	static int fsck_sha1(const unsigned char *sha1)
85003492	250	{
ba002f3b MK	251	struct object *obj = parse_object(sha1);
	252	if (!obj) {
	253	errors_found \|= ERROR_OBJECT;
	254	return error("%s: object corrupt or missing",
	255	sha1_to_hex(sha1));
	256	}
	257	if (obj->flags & SEEN)
85003492	258	return 0;
ba002f3b	259	obj->flags \|= SEEN;
85003492	260
20f1eb6b	261	if (verbose)
ba002f3b MK	262	fprintf(stderr, "Checking %s %s\n",
ba002f3b MK	263	typename(obj->type), sha1_to_hex(obj->sha1));
42ea9cb2	264
ba002f3b MK	265	if (fsck_walk(obj, mark_used, 0))
	266	objerror(obj, "broken links");
	267	if (fsck_object(obj, check_strict, fsck_error_func))
	268	return -1;
85003492	269
ba002f3b MK	270	if (obj->type == OBJ_TREE) {
ba002f3b MK	271	struct tree item = (struct tree ) obj;
85003492	272
ba002f3b MK	273	free(item->buffer);
ba002f3b MK	274	item->buffer = NULL;
1ea34e36	275	}
1ea34e36	276
ba002f3b MK	277	if (obj->type == OBJ_COMMIT) {
ba002f3b MK	278	struct commit commit = (struct commit ) obj;
de2eb7f6	279
ba002f3b MK	280	free(commit->buffer);
ba002f3b MK	281	commit->buffer = NULL;
4728b861	282
ba002f3b MK	283	if (!commit->parents && show_root)
	284	printf("root %s\n", sha1_to_hex(commit->object.sha1));
	285	}
92d4c85d	286
ba002f3b MK	287	if (obj->type == OBJ_TAG) {
ba002f3b MK	288	struct tag tag = (struct tag ) obj;
20f1eb6b	289
ba002f3b MK	290	if (show_tags && tag->tagged) {
	291	printf("tagged %s %s", typename(tag->tagged->type), sha1_to_hex(tag->tagged->sha1));
	292	printf(" (%s) in %s\n", tag->tag, sha1_to_hex(tag->object.sha1));
	293	}
92d4c85d	294	}
889262ea	295
ff5ebe39	296	return 0;
20222118 LT	297	}
20222118 LT	298
7e8c174a LT	299	/*
	300	* This is the sorting chunk size: make it reasonably
	301	* big so that we can sort well..
	302	*/
	303	#define MAX_SHA1_ENTRIES (1024)
	304
	305	struct sha1_entry {
	306	unsigned long ino;
20222118	307	unsigned char sha1[20];
7e8c174a LT	308	};
	309
	310	static struct {
	311	unsigned long nr;
	312	struct sha1_entry *entry[MAX_SHA1_ENTRIES];
	313	} sha1_list;
	314
	315	static int ino_compare(const void _a, const void _b)
	316	{
	317	const struct sha1_entry a = _a, b = _b;
	318	unsigned long ino1 = a->ino, ino2 = b->ino;
	319	return ino1 < ino2 ? -1 : ino1 > ino2 ? 1 : 0;
	320	}
	321
	322	static void fsck_sha1_list(void)
	323	{
	324	int i, nr = sha1_list.nr;
	325
35a730f0 JH	326	if (SORT_DIRENT)
	327	qsort(sha1_list.entry, nr,
	328	sizeof(struct sha1_entry *), ino_compare);
7e8c174a LT	329	for (i = 0; i < nr; i++) {
	330	struct sha1_entry *entry = sha1_list.entry[i];
	331	unsigned char *sha1 = entry->sha1;
	332
	333	sha1_list.entry[i] = NULL;
f1f0d088	334	fsck_sha1(sha1);
7e8c174a	335	free(entry);
20222118	336	}
7e8c174a LT	337	sha1_list.nr = 0;
	338	}
	339
	340	static void add_sha1_list(unsigned char *sha1, unsigned long ino)
	341	{
	342	struct sha1_entry entry = xmalloc(sizeof(entry));
	343	int nr;
	344
	345	entry->ino = ino;
e702496e	346	hashcpy(entry->sha1, sha1);
7e8c174a LT	347	nr = sha1_list.nr;
	348	if (nr == MAX_SHA1_ENTRIES) {
	349	fsck_sha1_list();
	350	nr = 0;
	351	}
	352	sha1_list.entry[nr] = entry;
	353	sha1_list.nr = ++nr;
20222118 LT	354	}
20222118 LT	355
b5524c82	356	static void fsck_dir(int i, char *path)
20222118 LT	357	{
	358	DIR *dir = opendir(path);
	359	struct dirent *de;
	360
230f1322	361	if (!dir)
b5524c82	362	return;
20222118	363
20f1eb6b JS	364	if (verbose)
	365	fprintf(stderr, "Checking directory %s\n", path);
	366
20222118 LT	367	while ((de = readdir(dir)) != NULL) {
20222118 LT	368	char name[100];
7e8c174a	369	unsigned char sha1[20];
20222118 LT	370	int len = strlen(de->d_name);
	371
	372	switch (len) {
	373	case 2:
	374	if (de->d_name[1] != '.')
	375	break;
	376	case 1:
	377	if (de->d_name[0] != '.')
	378	break;
	379	continue;
	380	case 38:
	381	sprintf(name, "%02x", i);
	382	memcpy(name+2, de->d_name, len+1);
7e8c174a LT	383	if (get_sha1_hex(name, sha1) < 0)
7e8c174a LT	384	break;
35a730f0	385	add_sha1_list(sha1, DIRENT_SORT_HINT(de));
7e8c174a	386	continue;
20222118	387	}
3d32a46b	388	if (!prefixcmp(de->d_name, "tmp_obj_"))
a08c53a1	389	continue;
20222118 LT	390	fprintf(stderr, "bad sha1 file: %s/%s\n", path, de->d_name);
	391	}
	392	closedir(dir);
20222118 LT	393	}
20222118 LT	394
96f1e58f	395	static int default_refs;
944d8589	396
883d60fa JS	397	static int fsck_handle_reflog_ent(unsigned char osha1, unsigned char nsha1,
	398	const char *email, unsigned long timestamp, int tz,
	399	const char message, void cb_data)
55dd5526 JH	400	{
	401	struct object *obj;
	402
20f1eb6b JS	403	if (verbose)
	404	fprintf(stderr, "Checking reflog %s->%s\n",
	405	sha1_to_hex(osha1), sha1_to_hex(nsha1));
	406
55dd5526 JH	407	if (!is_null_sha1(osha1)) {
	408	obj = lookup_object(osha1);
	409	if (obj) {
	410	obj->used = 1;
271b8d25	411	mark_object_reachable(obj);
55dd5526 JH	412	}
	413	}
	414	obj = lookup_object(nsha1);
	415	if (obj) {
	416	obj->used = 1;
271b8d25	417	mark_object_reachable(obj);
55dd5526 JH	418	}
	419	return 0;
	420	}
	421
eb8381c8 NP	422	static int fsck_handle_reflog(const char logname, const unsigned char sha1, int flag, void *cb_data)
	423	{
	424	for_each_reflog_ent(logname, fsck_handle_reflog_ent, NULL);
	425	return 0;
	426	}
	427
6232f62b LT	428	static int is_branch(const char *refname)
	429	{
	430	return !strcmp(refname, "HEAD") \|\| !prefixcmp(refname, "refs/heads/");
	431	}
	432
8da19775	433	static int fsck_handle_ref(const char refname, const unsigned char sha1, int flag, void *cb_data)
1024932f	434	{
1024932f LT	435	struct object *obj;
1024932f LT	436
6232f62b	437	obj = parse_object(sha1);
8a498a05	438	if (!obj) {
944d8589 LT	439	error("%s: invalid sha1 pointer %s", refname, sha1_to_hex(sha1));
	440	/* We'll continue with the rest despite the error.. */
	441	return 0;
8a498a05	442	}
6232f62b LT	443	if (obj->type != OBJ_COMMIT && is_branch(refname))
6232f62b LT	444	error("%s: not a commit", refname);
944d8589	445	default_refs++;
1024932f	446	obj->used = 1;
271b8d25	447	mark_object_reachable(obj);
55dd5526	448
7c4d07c7	449	return 0;
1024932f LT	450	}
1024932f LT	451
1024932f LT	452	static void get_default_heads(void)
1024932f LT	453	{
cb5d709f	454	for_each_ref(fsck_handle_ref, NULL);
566842f6 SP	455	if (include_reflogs)
566842f6 SP	456	for_each_reflog(fsck_handle_reflog, NULL);
071fa89e LT	457
	458	/*
	459	* Not having any default heads isn't really fatal, but
	460	* it does mean that "--unreachable" no longer makes any
	461	* sense (since in this case everything will obviously
	462	* be unreachable by definition.
	463	*
	464	* Showing dangling objects is valid, though (as those
	465	* dangling objects are likely lost heads).
	466	*
	467	* So we just print a warning about it, and clear the
	468	* "show_unreachable" flag.
	469	*/
	470	if (!default_refs) {
8eb2d0be	471	fprintf(stderr, "notice: No default references\n");
071fa89e LT	472	show_unreachable = 0;
071fa89e LT	473	}
1024932f LT	474	}
1024932f LT	475
8a498a05 JH	476	static void fsck_object_dir(const char *path)
	477	{
	478	int i;
20f1eb6b JS	479
	480	if (verbose)
	481	fprintf(stderr, "Checking object directory\n");
	482
8a498a05 JH	483	for (i = 0; i < 256; i++) {
	484	static char dir[4096];
	485	sprintf(dir, "%s/%02x", path, i);
	486	fsck_dir(i, dir);
	487	}
	488	fsck_sha1_list();
	489	}
	490
c3330383 LT	491	static int fsck_head_link(void)
c3330383 LT	492	{
c3330383	493	unsigned char sha1[20];
8da19775	494	int flag;
8eb2d0be JH	495	int null_is_error = 0;
	496	const char *head_points_at = resolve_ref("HEAD", sha1, 0, &flag);
	497
20f1eb6b JS	498	if (verbose)
	499	fprintf(stderr, "Checking HEAD link\n");
	500
8eb2d0be JH	501	if (!head_points_at)
	502	return error("Invalid HEAD");
	503	if (!strcmp(head_points_at, "HEAD"))
	504	/* detached HEAD */
	505	null_is_error = 1;
	506	else if (prefixcmp(head_points_at, "refs/heads/"))
8098a178	507	return error("HEAD points to something strange (%s)",
5b10b091	508	head_points_at);
8eb2d0be JH	509	if (is_null_sha1(sha1)) {
	510	if (null_is_error)
	511	return error("HEAD: detached HEAD points at nothing");
	512	fprintf(stderr, "notice: HEAD points to an unborn branch (%s)\n",
	513	head_points_at + 11);
	514	}
c3330383 LT	515	return 0;
	516	}
	517
53dc3f3e JH	518	static int fsck_cache_tree(struct cache_tree *it)
	519	{
	520	int i;
	521	int err = 0;
	522
20f1eb6b JS	523	if (verbose)
	524	fprintf(stderr, "Checking cache tree\n");
	525
53dc3f3e JH	526	if (0 <= it->entry_count) {
53dc3f3e JH	527	struct object *obj = parse_object(it->sha1);
6d60bbef JH	528	if (!obj) {
	529	error("%s: invalid sha1 pointer in cache-tree",
	530	sha1_to_hex(it->sha1));
	531	return 1;
	532	}
271b8d25	533	mark_object_reachable(obj);
cdc08b33	534	obj->used = 1;
1974632c	535	if (obj->type != OBJ_TREE)
53dc3f3e JH	536	err \|= objerror(obj, "non-tree in cache-tree");
	537	}
	538	for (i = 0; i < it->subtree_nr; i++)
	539	err \|= fsck_cache_tree(it->down[i]->cache_tree);
	540	return err;
	541	}
	542
5ac0a206	543	static char const * const fsck_usage[] = {
1b1dd23f	544	"git fsck [options] [<object>...]",
5ac0a206 PH	545	NULL
	546	};
	547
	548	static struct option fsck_opts[] = {
	549	OPT__VERBOSE(&verbose),
	550	OPT_BOOLEAN(0, "unreachable", &show_unreachable, "show unreachable objects"),
	551	OPT_BOOLEAN(0, "tags", &show_tags, "report tags"),
	552	OPT_BOOLEAN(0, "root", &show_root, "report root nodes"),
	553	OPT_BOOLEAN(0, "cache", &keep_cache_objects, "make index objects head nodes"),
	554	OPT_BOOLEAN(0, "reflogs", &include_reflogs, "make reflogs head nodes (default)"),
	555	OPT_BOOLEAN(0, "full", &check_full, "also consider alternate objects"),
dd46b9b9	556	OPT_BOOLEAN(0, "strict", &check_strict, "enable more strict checking"),
5ac0a206 PH	557	OPT_BOOLEAN(0, "lost-found", &write_lost_and_found,
	558	"write dangling objects in .git/lost-found"),
	559	OPT_END(),
	560	};
e2b4f635	561
baffc0e7	562	int cmd_fsck(int argc, const char *argv, const char prefix)
20222118	563	{
bcee6fd8	564	int i, heads;
20222118	565
e2b4f635	566	errors_found = 0;
61e2b015	567
5ac0a206 PH	568	argc = parse_options(argc, argv, fsck_opts, fsck_usage, 0);
	569	if (write_lost_and_found) {
	570	check_full = 1;
	571	include_reflogs = 0;
889262ea LT	572	}
889262ea LT	573
c3330383	574	fsck_head_link();
8a498a05 JH	575	fsck_object_dir(get_object_directory());
8a498a05 JH	576	if (check_full) {
d5a63b99	577	struct alternate_object_database *alt;
8a498a05 JH	578	struct packed_git *p;
8a498a05 JH	579	prepare_alt_odb();
d5a63b99	580	for (alt = alt_odb_list; alt; alt = alt->next) {
a3eb250f	581	char namebuf[PATH_MAX];
d5a63b99 JH	582	int namelen = alt->name - alt->base;
d5a63b99 JH	583	memcpy(namebuf, alt->base, namelen);
a3eb250f JH	584	namebuf[namelen - 1] = 0;
a3eb250f JH	585	fsck_object_dir(namebuf);
8a498a05 JH	586	}
8a498a05 JH	587	prepare_packed_git();
f9253394 JH	588	for (p = packed_git; p; p = p->next)
f9253394 JH	589	/* verify gives error messages itself */
77d3ecee	590	verify_pack(p);
f9253394	591
8a498a05	592	for (p = packed_git; p; p = p->next) {
5ac0a206	593	uint32_t j, num;
b77ffe8a SP	594	if (open_pack_index(p))
	595	continue;
	596	num = p->num_objects;
5ac0a206 PH	597	for (j = 0; j < num; j++)
5ac0a206 PH	598	fsck_sha1(nth_packed_object_sha1(p, j));
8a498a05	599	}
bcee6fd8 LT	600	}
	601
	602	heads = 0;
d9839e03	603	for (i = 1; i < argc; i++) {
a6080a0a	604	const char *arg = argv[i];
3c249c95	605	if (!get_sha1(arg, head_sha1)) {
770896e5	606	struct object *obj = lookup_object(head_sha1);
e1a1388d	607
770896e5 LT	608	/* Error is printed by lookup_object(). */
770896e5 LT	609	if (!obj)
e1a1388d JF	610	continue;
e1a1388d JF	611
ff5ebe39	612	obj->used = 1;
271b8d25	613	mark_object_reachable(obj);
bcee6fd8	614	heads++;
d9839e03 LT	615	continue;
d9839e03 LT	616	}
f1f0d088	617	error("invalid parameter: expected sha1, got '%s'", arg);
d9839e03	618	}
d9839e03	619
1024932f	620	/*
d1af002d	621	* If we've not been given any explicit head information, do the
e7bd907d LT	622	* default ones from .git/refs. We also consider the index file
e7bd907d LT	623	* in this case (ie this implies --cache).
1024932f	624	*/
e7bd907d	625	if (!heads) {
1024932f LT	626	get_default_heads();
	627	keep_cache_objects = 1;
	628	}
	629
ae7c0c92	630	if (keep_cache_objects) {
ae7c0c92 JH	631	read_cache();
ae7c0c92 JH	632	for (i = 0; i < active_nr; i++) {
8d9721c8 LT	633	unsigned int mode;
8d9721c8 LT	634	struct blob *blob;
ae7c0c92	635	struct object *obj;
8d9721c8	636
7a51ed66	637	mode = active_cache[i]->ce_mode;
302b9282	638	if (S_ISGITLINK(mode))
8d9721c8 LT	639	continue;
8d9721c8 LT	640	blob = lookup_blob(active_cache[i]->sha1);
ae7c0c92 JH	641	if (!blob)
	642	continue;
	643	obj = &blob->object;
	644	obj->used = 1;
271b8d25	645	mark_object_reachable(obj);
ae7c0c92	646	}
53dc3f3e JH	647	if (active_cache_tree)
53dc3f3e JH	648	fsck_cache_tree(active_cache_tree);
ae7c0c92 JH	649	}
ae7c0c92 JH	650
8ba0bbb2	651	check_connectivity();
e2b4f635	652	return errors_found;
20222118	653	}