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

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

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

#define REACHABLE 0x0001

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


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

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

int objwarning(struct object *obj, const char *err, ...)
{
	va_list params;
	va_start(params, err);
	objreport(obj, "warning", err, params);
	va_end(params);
	return -1;
}


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) {
			if (!standalone && has_sha1_file(obj->sha1))
				; /* it is in pack */
			else
				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 ||
			    (!standalone && has_sha1_file(refs->item->sha1)))
				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));
		}

		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".
 */
#define TREE_UNORDERED (-1)
#define TREE_HAS_DUPS  (-2)

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 TREE_UNORDERED;

	/*
	 * 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 && !c2)
		/*
		 * git-write-tree used to write out a nonsense tree that has
		 * entries with the same name, one blob and one tree.  Make
		 * sure we do not have duplicate entries.
		 */
		return TREE_HAS_DUPS;
	if (!c1 && a->directory)
		c1 = '/';
	if (!c2 && b->directory)
		c2 = '/';
	return c1 < c2 ? 0 : TREE_UNORDERED;
}

static int fsck_tree(struct tree *item)
{
	int retval;
	int has_full_path = 0;
	int has_zero_pad = 0;
	int has_bad_modes = 0;
	int has_dup_entries = 0;
	int not_properly_sorted = 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;
		has_zero_pad |= entry->zeropad;

		switch (entry->mode) {
		/*
		 * Standard modes.. 
		 */
		case S_IFREG | 0755:
		case S_IFREG | 0644:
		case S_IFLNK:
		case S_IFDIR:
			break;
		/*
		 * This is nonstandard, but we had a few of these
		 * early on when we honored the full set of mode
		 * bits..
		 */
		case S_IFREG | 0664:
			if (!check_strict)
				break;
		default:
			has_bad_modes = 1;
		}

		if (last) {
			switch (verify_ordered(last, entry)) {
			case TREE_UNORDERED:
				not_properly_sorted = 1;
				break;
			case TREE_HAS_DUPS:
				has_dup_entries = 1;
				break;
			default:
				break;
			}
		}

		last = entry;
	}

	retval = 0;
	if (has_full_path) {
		objwarning(&item->object, "contains full pathnames");
	}
	if (has_zero_pad) {
		objwarning(&item->object, "contains zero-padded file modes");
	}
	if (has_bad_modes) {
		objwarning(&item->object, "contains bad file modes");
	}
	if (has_dup_entries) {
		retval = objerror(&item->object, "contains duplicate file entries");
	}
	if (not_properly_sorted) {
		retval = objerror(&item->object, "not properly sorted");
	}
	return retval;
}

static int fsck_commit(struct commit *commit)
{
	char *buffer = commit->buffer;
	unsigned char tree_sha1[20], sha1[20];

	if (memcmp(buffer, "tree ", 5))
		return objerror(&commit->object, "invalid format - expected 'tree' line");
	if (get_sha1_hex(buffer+5, tree_sha1) || buffer[45] != '\n')
		return objerror(&commit->object, "invalid 'tree' line format - bad sha1");
	buffer += 46;
	while (!memcmp(buffer, "parent ", 7)) {
		if (get_sha1_hex(buffer+7, sha1) || buffer[47] != '\n')
			return objerror(&commit->object, "invalid 'parent' line format - bad sha1");
		buffer += 48;
	}
	if (memcmp(buffer, "author ", 7))
		return objerror(&commit->object, "invalid format - expected 'author' line");
	free(commit->buffer);
	commit->buffer = NULL;
	if (!commit->tree)
		return objerror(&commit->object, "could not load commit's tree %s", tree_sha1);
	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) {
		return objerror(&tag->object, "could not load tagged object");
	}
	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 error("%s: object not found", sha1_to_hex(sha1));
	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);
	/* By now, parse_object() would've returned NULL instead. */
	return objerror(obj, "unknown type '%s' (internal fsck error)", obj->type);
}

/*
 * 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;
		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;
	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;
}

static int default_refs = 0;

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

	obj = lookup_object(sha1);
	if (!obj) {
		if (!standalone && has_sha1_file(sha1)) {
			default_refs++;
			return 0; /* it is in a pack */
		}
		error("%s: invalid sha1 pointer %s", refname, sha1_to_hex(sha1));
		/* We'll continue with the rest despite the error.. */
		return 0;
	}
	default_refs++;
	obj->used = 1;
	mark_reachable(obj, REACHABLE);
	return 0;
}

static void get_default_heads(void)
{
	for_each_ref(fsck_handle_ref);
	if (!default_refs)
		die("No default references");
}

static void fsck_object_dir(const char *path)
{
	int i;
	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)
{
	int fd, count;
	char hex[40];
	unsigned char sha1[20];
	static char path[PATH_MAX], link[PATH_MAX];
	const char *git_dir = get_git_dir();

	snprintf(path, sizeof(path), "%s/HEAD", git_dir);
	if (readlink(path, link, sizeof(link)) < 0)
		return error("HEAD is not a symlink");
	if (strncmp("refs/heads/", link, 11))
		return error("HEAD points to something strange (%s)", link);
	fd = open(path, O_RDONLY);
	if (fd < 0)
		return error("HEAD: %s", strerror(errno));
	count = read(fd, hex, sizeof(hex));
	close(fd);
	if (count < 0)
		return error("HEAD: %s", strerror(errno));
	if (count < 40 || get_sha1_hex(hex, sha1))
		return error("HEAD: not a valid git pointer");
	return 0;
}

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

	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 (!strcmp(arg, "--standalone")) {
			standalone = 1;
			continue;
		}
		if (!strcmp(arg, "--full")) {
			check_full = 1;
			continue;
		}
		if (!strcmp(arg, "--strict")) {
			check_strict = 1;
			continue;
		}
		if (*arg == '-')
			usage("git-fsck-objects [--tags] [--root] [[--unreachable] [--cache] [--standalone | --full] [--strict] <head-sha1>*]");
	}

	if (standalone && check_full)
		die("Only one of --standalone or --full can be used.");
	if (standalone)
		putenv("GIT_ALTERNATE_OBJECT_DIRECTORIES=");

	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, 0);

		for (p = packed_git; p; p = p->next) {
			int num = num_packed_objects(p);
			for (i = 0; i < num; i++) {
				unsigned char sha1[20];
				nth_packed_object_sha1(p, i, sha1);
				fsck_sha1(sha1);
			}
		}
	}

	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("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) {
		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);
		}
	}

	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"
944d8589	9	#include "refs.h"
f9253394	10	#include "pack.h"
ff5ebe39 DB	11
ff5ebe39 DB	12	#define REACHABLE 0x0001
d9839e03	13
ab7df187	14	static int show_root = 0;
889262ea	15	static int show_tags = 0;
d9839e03	16	static int show_unreachable = 0;
8a498a05 JH	17	static int standalone = 0;
8a498a05 JH	18	static int check_full = 0;
de2eb7f6	19	static int check_strict = 0;
ae7c0c92	20	static int keep_cache_objects = 0;
d9839e03 LT	21	static unsigned char head_sha1[20];
d9839e03 LT	22
f1f0d088 PB	23
	24	static void objreport(struct object obj, const char severity,
	25	const char *err, va_list params)
	26	{
	27	fprintf(stderr, "%s in %s %s: ",
	28	severity, obj->type, sha1_to_hex(obj->sha1));
	29	vfprintf(stderr, err, params);
	30	fputs("\n", stderr);
	31	}
	32
	33	int objerror(struct object obj, const char err, ...)
	34	{
	35	va_list params;
	36	va_start(params, err);
	37	objreport(obj, "error", err, params);
	38	va_end(params);
	39	return -1;
	40	}
	41
	42	int objwarning(struct object obj, const char err, ...)
	43	{
	44	va_list params;
	45	va_start(params, err);
	46	objreport(obj, "warning", err, params);
	47	va_end(params);
	48	return -1;
	49	}
	50
	51
8ba0bbb2 LT	52	static void check_connectivity(void)
	53	{
	54	int i;
	55
8ba0bbb2	56	/* Look up all the requirements, warn about missing objects.. */
ff5ebe39 DB	57	for (i = 0; i < nr_objs; i++) {
ff5ebe39 DB	58	struct object *obj = objs[i];
c418eda4	59	struct object_list *refs;
8ba0bbb2	60
3a6a23e6	61	if (!obj->parsed) {
8a498a05 JH	62	if (!standalone && has_sha1_file(obj->sha1))
	63	; /* it is in pack */
	64	else
	65	printf("missing %s %s\n",
	66	obj->type, sha1_to_hex(obj->sha1));
3a6a23e6 LT	67	continue;
	68	}
	69
	70	for (refs = obj->refs; refs; refs = refs->next) {
8a498a05 JH	71	if (refs->item->parsed \|\|
8a498a05 JH	72	(!standalone && has_sha1_file(refs->item->sha1)))
3a6a23e6 LT	73	continue;
	74	printf("broken link from %7s %s\n",
	75	obj->type, sha1_to_hex(obj->sha1));
	76	printf(" to %7s %s\n",
aa034134	77	refs->item->type, sha1_to_hex(refs->item->sha1));
3a6a23e6 LT	78	}
3a6a23e6 LT	79
ff5ebe39	80	if (show_unreachable && !(obj->flags & REACHABLE)) {
c4584ae3 JH	81	printf("unreachable %s %s\n",
c4584ae3 JH	82	obj->type, sha1_to_hex(obj->sha1));
8ba0bbb2	83	continue;
d9839e03	84	}
8ba0bbb2	85
ff5ebe39 DB	86	if (!obj->used) {
	87	printf("dangling %s %s\n", obj->type,
	88	sha1_to_hex(obj->sha1));
d9839e03	89	}
8ba0bbb2 LT	90	}
	91	}
	92
85003492 LT	93	/*
	94	* The entries in a tree are ordered in the _path_ order,
	95	* which means that a directory entry is ordered by adding
	96	* a slash to the end of it.
	97	*
	98	* So a directory called "a" is ordered _after_ a file
	99	* called "a.c", because "a/" sorts after "a.c".
	100	*/
a4f35a2d JH	101	#define TREE_UNORDERED (-1)
	102	#define TREE_HAS_DUPS (-2)
	103
85003492 LT	104	static int verify_ordered(struct tree_entry_list a, struct tree_entry_list b)
	105	{
	106	int len1 = strlen(a->name);
	107	int len2 = strlen(b->name);
	108	int len = len1 < len2 ? len1 : len2;
	109	unsigned char c1, c2;
	110	int cmp;
	111
	112	cmp = memcmp(a->name, b->name, len);
	113	if (cmp < 0)
	114	return 0;
	115	if (cmp > 0)
a4f35a2d	116	return TREE_UNORDERED;
85003492 LT	117
	118	/*
	119	* Ok, the first <len> characters are the same.
	120	* Now we need to order the next one, but turn
	121	* a '\0' into a '/' for a directory entry.
	122	*/
	123	c1 = a->name[len];
	124	c2 = b->name[len];
a4f35a2d JH	125	if (!c1 && !c2)
	126	/*
	127	* git-write-tree used to write out a nonsense tree that has
	128	* entries with the same name, one blob and one tree. Make
	129	* sure we do not have duplicate entries.
	130	*/
	131	return TREE_HAS_DUPS;
85003492 LT	132	if (!c1 && a->directory)
	133	c1 = '/';
	134	if (!c2 && b->directory)
	135	c2 = '/';
a4f35a2d	136	return c1 < c2 ? 0 : TREE_UNORDERED;
85003492 LT	137	}
85003492 LT	138
c418eda4	139	static int fsck_tree(struct tree *item)
20222118	140	{
64071805	141	int retval;
85003492	142	int has_full_path = 0;
64071805 LT	143	int has_zero_pad = 0;
	144	int has_bad_modes = 0;
	145	int has_dup_entries = 0;
	146	int not_properly_sorted = 0;
85003492 LT	147	struct tree_entry_list entry, last;
	148
	149	last = NULL;
	150	for (entry = item->entries; entry; entry = entry->next) {
	151	if (strchr(entry->name, '/'))
	152	has_full_path = 1;
64071805	153	has_zero_pad \|= entry->zeropad;
85003492	154
42ea9cb2 LT	155	switch (entry->mode) {
	156	/*
	157	* Standard modes..
	158	*/
	159	case S_IFREG \| 0755:
	160	case S_IFREG \| 0644:
	161	case S_IFLNK:
	162	case S_IFDIR:
	163	break;
	164	/*
	165	* This is nonstandard, but we had a few of these
	166	* early on when we honored the full set of mode
	167	* bits..
	168	*/
	169	case S_IFREG \| 0664:
de2eb7f6 LT	170	if (!check_strict)
de2eb7f6 LT	171	break;
42ea9cb2	172	default:
64071805	173	has_bad_modes = 1;
42ea9cb2 LT	174	}
42ea9cb2 LT	175
85003492	176	if (last) {
a4f35a2d JH	177	switch (verify_ordered(last, entry)) {
a4f35a2d JH	178	case TREE_UNORDERED:
64071805 LT	179	not_properly_sorted = 1;
64071805 LT	180	break;
a4f35a2d	181	case TREE_HAS_DUPS:
64071805 LT	182	has_dup_entries = 1;
64071805 LT	183	break;
a4f35a2d JH	184	default:
a4f35a2d JH	185	break;
85003492 LT	186	}
	187	}
	188
	189	last = entry;
	190	}
	191
64071805	192	retval = 0;
85003492	193	if (has_full_path) {
f1f0d088	194	objwarning(&item->object, "contains full pathnames");
1ea34e36	195	}
64071805	196	if (has_zero_pad) {
f1f0d088	197	objwarning(&item->object, "contains zero-padded file modes");
64071805 LT	198	}
64071805 LT	199	if (has_bad_modes) {
f1f0d088	200	objwarning(&item->object, "contains bad file modes");
64071805 LT	201	}
64071805 LT	202	if (has_dup_entries) {
f1f0d088	203	retval = objerror(&item->object, "contains duplicate file entries");
64071805 LT	204	}
64071805 LT	205	if (not_properly_sorted) {
f1f0d088	206	retval = objerror(&item->object, "not properly sorted");
64071805 LT	207	}
64071805 LT	208	return retval;
1ea34e36 LT	209	}
1ea34e36 LT	210
c418eda4	211	static int fsck_commit(struct commit *commit)
1ea34e36	212	{
de2eb7f6	213	char *buffer = commit->buffer;
f1f0d088	214	unsigned char tree_sha1[20], sha1[20];
de2eb7f6 LT	215
de2eb7f6 LT	216	if (memcmp(buffer, "tree ", 5))
f1f0d088 PB	217	return objerror(&commit->object, "invalid format - expected 'tree' line");
	218	if (get_sha1_hex(buffer+5, tree_sha1) \|\| buffer[45] != '\n')
	219	return objerror(&commit->object, "invalid 'tree' line format - bad sha1");
de2eb7f6 LT	220	buffer += 46;
	221	while (!memcmp(buffer, "parent ", 7)) {
	222	if (get_sha1_hex(buffer+7, sha1) \|\| buffer[47] != '\n')
f1f0d088	223	return objerror(&commit->object, "invalid 'parent' line format - bad sha1");
de2eb7f6 LT	224	buffer += 48;
	225	}
	226	if (memcmp(buffer, "author ", 7))
f1f0d088	227	return objerror(&commit->object, "invalid format - expected 'author' line");
bd1e17e2 LT	228	free(commit->buffer);
bd1e17e2 LT	229	commit->buffer = NULL;
ff5ebe39	230	if (!commit->tree)
f1f0d088	231	return objerror(&commit->object, "could not load commit's tree %s", tree_sha1);
ab7df187	232	if (!commit->parents && show_root)
c418eda4	233	printf("root %s\n", sha1_to_hex(commit->object.sha1));
e6948b6d	234	if (!commit->date)
c418eda4 DB	235	printf("bad commit date in %s\n",
c418eda4 DB	236	sha1_to_hex(commit->object.sha1));
4728b861 LT	237	return 0;
	238	}
	239
c418eda4	240	static int fsck_tag(struct tag *tag)
ec4465ad	241	{
92d4c85d LT	242	struct object *tagged = tag->tagged;
	243
	244	if (!tagged) {
f1f0d088	245	return objerror(&tag->object, "could not load tagged object");
92d4c85d	246	}
889262ea LT	247	if (!show_tags)
	248	return 0;
	249
92d4c85d LT	250	printf("tagged %s %s", tagged->type, sha1_to_hex(tagged->sha1));
92d4c85d LT	251	printf(" (%s) in %s\n", tag->tag, sha1_to_hex(tag->object.sha1));
ff5ebe39	252	return 0;
20222118 LT	253	}
20222118 LT	254
7e8c174a	255	static int fsck_sha1(unsigned char *sha1)
20222118	256	{
7e8c174a LT	257	struct object *obj = parse_object(sha1);
7e8c174a LT	258	if (!obj)
f1f0d088	259	return error("%s: object not found", sha1_to_hex(sha1));
7e8c174a LT	260	if (obj->type == blob_type)
	261	return 0;
	262	if (obj->type == tree_type)
	263	return fsck_tree((struct tree *) obj);
	264	if (obj->type == commit_type)
	265	return fsck_commit((struct commit *) obj);
	266	if (obj->type == tag_type)
	267	return fsck_tag((struct tag *) obj);
f1f0d088 PB	268	/* By now, parse_object() would've returned NULL instead. */
f1f0d088 PB	269	return objerror(obj, "unknown type '%s' (internal fsck error)", obj->type);
7e8c174a LT	270	}
	271
	272	/*
	273	* This is the sorting chunk size: make it reasonably
	274	* big so that we can sort well..
	275	*/
	276	#define MAX_SHA1_ENTRIES (1024)
	277
	278	struct sha1_entry {
	279	unsigned long ino;
20222118	280	unsigned char sha1[20];
7e8c174a LT	281	};
	282
	283	static struct {
	284	unsigned long nr;
	285	struct sha1_entry *entry[MAX_SHA1_ENTRIES];
	286	} sha1_list;
	287
	288	static int ino_compare(const void _a, const void _b)
	289	{
	290	const struct sha1_entry a = _a, b = _b;
	291	unsigned long ino1 = a->ino, ino2 = b->ino;
	292	return ino1 < ino2 ? -1 : ino1 > ino2 ? 1 : 0;
	293	}
	294
	295	static void fsck_sha1_list(void)
	296	{
	297	int i, nr = sha1_list.nr;
	298
	299	qsort(sha1_list.entry, nr, sizeof(struct sha1_entry *), ino_compare);
	300	for (i = 0; i < nr; i++) {
	301	struct sha1_entry *entry = sha1_list.entry[i];
	302	unsigned char *sha1 = entry->sha1;
	303
	304	sha1_list.entry[i] = NULL;
f1f0d088	305	fsck_sha1(sha1);
7e8c174a	306	free(entry);
20222118	307	}
7e8c174a LT	308	sha1_list.nr = 0;
	309	}
	310
	311	static void add_sha1_list(unsigned char *sha1, unsigned long ino)
	312	{
	313	struct sha1_entry entry = xmalloc(sizeof(entry));
	314	int nr;
	315
	316	entry->ino = ino;
	317	memcpy(entry->sha1, sha1, 20);
	318	nr = sha1_list.nr;
	319	if (nr == MAX_SHA1_ENTRIES) {
	320	fsck_sha1_list();
	321	nr = 0;
	322	}
	323	sha1_list.entry[nr] = entry;
	324	sha1_list.nr = ++nr;
20222118 LT	325	}
	326
	327	static int fsck_dir(int i, char *path)
	328	{
	329	DIR *dir = opendir(path);
	330	struct dirent *de;
	331
	332	if (!dir) {
2de381f9	333	return error("missing sha1 directory '%s'", path);
20222118 LT	334	}
	335
	336	while ((de = readdir(dir)) != NULL) {
	337	char name[100];
7e8c174a	338	unsigned char sha1[20];
20222118 LT	339	int len = strlen(de->d_name);
	340
	341	switch (len) {
	342	case 2:
	343	if (de->d_name[1] != '.')
	344	break;
	345	case 1:
	346	if (de->d_name[0] != '.')
	347	break;
	348	continue;
	349	case 38:
	350	sprintf(name, "%02x", i);
	351	memcpy(name+2, de->d_name, len+1);
7e8c174a LT	352	if (get_sha1_hex(name, sha1) < 0)
	353	break;
	354	add_sha1_list(sha1, de->d_ino);
	355	continue;
20222118 LT	356	}
	357	fprintf(stderr, "bad sha1 file: %s/%s\n", path, de->d_name);
	358	}
	359	closedir(dir);
	360	return 0;
	361	}
	362
944d8589 LT	363	static int default_refs = 0;
	364
	365	static int fsck_handle_ref(const char refname, const unsigned char sha1)
1024932f	366	{
1024932f LT	367	struct object *obj;
1024932f LT	368
1024932f	369	obj = lookup_object(sha1);
8a498a05	370	if (!obj) {
659cacf5 LT	371	if (!standalone && has_sha1_file(sha1)) {
659cacf5 LT	372	default_refs++;
944d8589	373	return 0; /* it is in a pack */
659cacf5	374	}
944d8589 LT	375	error("%s: invalid sha1 pointer %s", refname, sha1_to_hex(sha1));
	376	/* We'll continue with the rest despite the error.. */
	377	return 0;
8a498a05	378	}
944d8589	379	default_refs++;
1024932f LT	380	obj->used = 1;
1024932f LT	381	mark_reachable(obj, REACHABLE);
7c4d07c7	382	return 0;
1024932f LT	383	}
1024932f LT	384
1024932f LT	385	static void get_default_heads(void)
1024932f LT	386	{
944d8589 LT	387	for_each_ref(fsck_handle_ref);
944d8589 LT	388	if (!default_refs)
477606f5	389	die("No default references");
1024932f LT	390	}
1024932f LT	391
8a498a05 JH	392	static void fsck_object_dir(const char *path)
	393	{
	394	int i;
	395	for (i = 0; i < 256; i++) {
	396	static char dir[4096];
	397	sprintf(dir, "%s/%02x", path, i);
	398	fsck_dir(i, dir);
	399	}
	400	fsck_sha1_list();
	401	}
	402
c3330383 LT	403	static int fsck_head_link(void)
	404	{
	405	int fd, count;
	406	char hex[40];
	407	unsigned char sha1[20];
	408	static char path[PATH_MAX], link[PATH_MAX];
5da1606d	409	const char *git_dir = get_git_dir();
c3330383 LT	410
	411	snprintf(path, sizeof(path), "%s/HEAD", git_dir);
	412	if (readlink(path, link, sizeof(link)) < 0)
	413	return error("HEAD is not a symlink");
	414	if (strncmp("refs/heads/", link, 11))
	415	return error("HEAD points to something strange (%s)", link);
	416	fd = open(path, O_RDONLY);
	417	if (fd < 0)
	418	return error("HEAD: %s", strerror(errno));
	419	count = read(fd, hex, sizeof(hex));
	420	close(fd);
	421	if (count < 0)
	422	return error("HEAD: %s", strerror(errno));
	423	if (count < 40 \|\| get_sha1_hex(hex, sha1))
	424	return error("HEAD: not a valid git pointer");
	425	return 0;
	426	}
	427
20222118 LT	428	int main(int argc, char **argv)
20222118 LT	429	{
bcee6fd8	430	int i, heads;
20222118	431
889262ea LT	432	for (i = 1; i < argc; i++) {
	433	const char *arg = argv[i];
	434
	435	if (!strcmp(arg, "--unreachable")) {
	436	show_unreachable = 1;
	437	continue;
	438	}
	439	if (!strcmp(arg, "--tags")) {
	440	show_tags = 1;
	441	continue;
	442	}
ab7df187 LT	443	if (!strcmp(arg, "--root")) {
	444	show_root = 1;
	445	continue;
	446	}
ae7c0c92 JH	447	if (!strcmp(arg, "--cache")) {
	448	keep_cache_objects = 1;
	449	continue;
	450	}
8a498a05 JH	451	if (!strcmp(arg, "--standalone")) {
	452	standalone = 1;
	453	continue;
	454	}
	455	if (!strcmp(arg, "--full")) {
	456	check_full = 1;
	457	continue;
	458	}
de2eb7f6 LT	459	if (!strcmp(arg, "--strict")) {
	460	check_strict = 1;
	461	continue;
	462	}
889262ea	463	if (*arg == '-')
215a7ad1	464	usage("git-fsck-objects [--tags] [--root] [[--unreachable] [--cache] [--standalone \| --full] [--strict] <head-sha1>*]");
889262ea LT	465	}
889262ea LT	466
8a498a05 JH	467	if (standalone && check_full)
	468	die("Only one of --standalone or --full can be used.");
	469	if (standalone)
e72a7d45	470	putenv("GIT_ALTERNATE_OBJECT_DIRECTORIES=");
8a498a05	471
c3330383	472	fsck_head_link();
8a498a05 JH	473	fsck_object_dir(get_object_directory());
8a498a05 JH	474	if (check_full) {
d5a63b99	475	struct alternate_object_database *alt;
8a498a05 JH	476	struct packed_git *p;
8a498a05 JH	477	prepare_alt_odb();
d5a63b99	478	for (alt = alt_odb_list; alt; alt = alt->next) {
a3eb250f	479	char namebuf[PATH_MAX];
d5a63b99 JH	480	int namelen = alt->name - alt->base;
d5a63b99 JH	481	memcpy(namebuf, alt->base, namelen);
a3eb250f JH	482	namebuf[namelen - 1] = 0;
a3eb250f JH	483	fsck_object_dir(namebuf);
8a498a05 JH	484	}
8a498a05 JH	485	prepare_packed_git();
f9253394 JH	486	for (p = packed_git; p; p = p->next)
f9253394 JH	487	/* verify gives error messages itself */
f3bf9224	488	verify_pack(p, 0);
f9253394	489
8a498a05 JH	490	for (p = packed_git; p; p = p->next) {
	491	int num = num_packed_objects(p);
	492	for (i = 0; i < num; i++) {
	493	unsigned char sha1[20];
	494	nth_packed_object_sha1(p, i, sha1);
f1f0d088	495	fsck_sha1(sha1);
8a498a05 JH	496	}
8a498a05 JH	497	}
bcee6fd8 LT	498	}
	499
	500	heads = 0;
d9839e03	501	for (i = 1; i < argc; i++) {
889262ea LT	502	const char *arg = argv[i];
	503
	504	if (*arg == '-')
d9839e03	505	continue;
889262ea	506
3c249c95	507	if (!get_sha1(arg, head_sha1)) {
770896e5	508	struct object *obj = lookup_object(head_sha1);
e1a1388d	509
770896e5 LT	510	/* Error is printed by lookup_object(). */
770896e5 LT	511	if (!obj)
e1a1388d JF	512	continue;
e1a1388d JF	513
ff5ebe39 DB	514	obj->used = 1;
ff5ebe39 DB	515	mark_reachable(obj, REACHABLE);
bcee6fd8	516	heads++;
d9839e03 LT	517	continue;
d9839e03 LT	518	}
f1f0d088	519	error("invalid parameter: expected sha1, got '%s'", arg);
d9839e03	520	}
d9839e03	521
1024932f	522	/*
d1af002d	523	* If we've not been given any explicit head information, do the
e7bd907d LT	524	* default ones from .git/refs. We also consider the index file
e7bd907d LT	525	* in this case (ie this implies --cache).
1024932f	526	*/
e7bd907d	527	if (!heads) {
1024932f LT	528	get_default_heads();
	529	keep_cache_objects = 1;
	530	}
	531
ae7c0c92 JH	532	if (keep_cache_objects) {
	533	int i;
	534	read_cache();
	535	for (i = 0; i < active_nr; i++) {
	536	struct blob *blob = lookup_blob(active_cache[i]->sha1);
	537	struct object *obj;
	538	if (!blob)
	539	continue;
	540	obj = &blob->object;
	541	obj->used = 1;
	542	mark_reachable(obj, REACHABLE);
	543	}
	544	}
	545
8ba0bbb2	546	check_connectivity();
20222118 LT	547	return 0;
20222118 LT	548	}