[thirdparty/git.git] / fsck.c

#include "cache.h"
#include "object.h"
#include "blob.h"
#include "tree.h"
#include "tree-walk.h"
#include "commit.h"
#include "tag.h"
#include "fsck.h"

static int fsck_walk_tree(struct tree *tree, fsck_walk_func walk, void *data)
{
	struct tree_desc desc;
	struct name_entry entry;
	int res = 0;

	if (parse_tree(tree))
		return -1;

	init_tree_desc(&desc, tree->buffer, tree->size);
	while (tree_entry(&desc, &entry)) {
		int result;

		if (S_ISGITLINK(entry.mode))
			continue;
		if (S_ISDIR(entry.mode))
			result = walk(&lookup_tree(entry.sha1)->object, OBJ_TREE, data);
		else if (S_ISREG(entry.mode) || S_ISLNK(entry.mode))
			result = walk(&lookup_blob(entry.sha1)->object, OBJ_BLOB, data);
		else {
			result = error("in tree %s: entry %s has bad mode %.6o\n",
					sha1_to_hex(tree->object.sha1), entry.path, entry.mode);
		}
		if (result < 0)
			return result;
		if (!res)
			res = result;
	}
	return res;
}

static int fsck_walk_commit(struct commit *commit, fsck_walk_func walk, void *data)
{
	struct commit_list *parents;
	int res;
	int result;

	if (parse_commit(commit))
		return -1;

	result = walk((struct object *)commit->tree, OBJ_TREE, data);
	if (result < 0)
		return result;
	res = result;

	parents = commit->parents;
	while (parents) {
		result = walk((struct object *)parents->item, OBJ_COMMIT, data);
		if (result < 0)
			return result;
		if (!res)
			res = result;
		parents = parents->next;
	}
	return res;
}

static int fsck_walk_tag(struct tag *tag, fsck_walk_func walk, void *data)
{
	if (parse_tag(tag))
		return -1;
	return walk(tag->tagged, OBJ_ANY, data);
}

int fsck_walk(struct object *obj, fsck_walk_func walk, void *data)
{
	if (!obj)
		return -1;
	switch (obj->type) {
	case OBJ_BLOB:
		return 0;
	case OBJ_TREE:
		return fsck_walk_tree((struct tree *)obj, walk, data);
	case OBJ_COMMIT:
		return fsck_walk_commit((struct commit *)obj, walk, data);
	case OBJ_TAG:
		return fsck_walk_tag((struct tag *)obj, walk, data);
	default:
		error("Unknown object type for %s", sha1_to_hex(obj->sha1));
		return -1;
	}
}

/*
 * 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(unsigned mode1, const char *name1, unsigned mode2, const char *name2)
{
	int len1 = strlen(name1);
	int len2 = strlen(name2);
	int len = len1 < len2 ? len1 : len2;
	unsigned char c1, c2;
	int cmp;

	cmp = memcmp(name1, name2, 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 = name1[len];
	c2 = name2[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 && S_ISDIR(mode1))
		c1 = '/';
	if (!c2 && S_ISDIR(mode2))
		c2 = '/';
	return c1 < c2 ? 0 : TREE_UNORDERED;
}

static int fsck_tree(struct tree *item, int strict, fsck_error error_func)
{
	int retval;
	int has_full_path = 0;
	int has_empty_name = 0;
	int has_zero_pad = 0;
	int has_bad_modes = 0;
	int has_dup_entries = 0;
	int not_properly_sorted = 0;
	struct tree_desc desc;
	unsigned o_mode;
	const char *o_name;
	const unsigned char *o_sha1;

	init_tree_desc(&desc, item->buffer, item->size);

	o_mode = 0;
	o_name = NULL;
	o_sha1 = NULL;
	if (!desc.size)
		return error_func(&item->object, FSCK_ERROR, "empty tree");

	while (desc.size) {
		unsigned mode;
		const char *name;
		const unsigned char *sha1;

		sha1 = tree_entry_extract(&desc, &name, &mode);

		if (strchr(name, '/'))
			has_full_path = 1;
		if (!*name)
			has_empty_name = 1;
		has_zero_pad |= *(char *)desc.buffer == '0';
		update_tree_entry(&desc);

		switch (mode) {
		/*
		 * Standard modes..
		 */
		case S_IFREG | 0755:
		case S_IFREG | 0644:
		case S_IFLNK:
		case S_IFDIR:
		case S_IFGITLINK:
			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 (!strict)
				break;
		default:
			has_bad_modes = 1;
		}

		if (o_name) {
			switch (verify_ordered(o_mode, o_name, mode, name)) {
			case TREE_UNORDERED:
				not_properly_sorted = 1;
				break;
			case TREE_HAS_DUPS:
				has_dup_entries = 1;
				break;
			default:
				break;
			}
		}

		o_mode = mode;
		o_name = name;
		o_sha1 = sha1;
	}

	retval = 0;
	if (has_full_path)
		retval += error_func(&item->object, FSCK_WARN, "contains full pathnames");
	if (has_empty_name)
		retval += error_func(&item->object, FSCK_WARN, "contains empty pathname");
	if (has_zero_pad)
		retval += error_func(&item->object, FSCK_WARN, "contains zero-padded file modes");
	if (has_bad_modes)
		retval += error_func(&item->object, FSCK_WARN, "contains bad file modes");
	if (has_dup_entries)
		retval += error_func(&item->object, FSCK_ERROR, "contains duplicate file entries");
	if (not_properly_sorted)
		retval += error_func(&item->object, FSCK_ERROR, "not properly sorted");
	return retval;
}

static int fsck_commit(struct commit *commit, fsck_error error_func)
{
	char *buffer = commit->buffer;
	unsigned char tree_sha1[20], sha1[20];
	struct commit_graft *graft;
	int parents = 0;

	if (!commit->date)
		return error_func(&commit->object, FSCK_ERROR, "invalid author/committer line");

	if (memcmp(buffer, "tree ", 5))
		return error_func(&commit->object, FSCK_ERROR, "invalid format - expected 'tree' line");
	if (get_sha1_hex(buffer+5, tree_sha1) || buffer[45] != '\n')
		return error_func(&commit->object, FSCK_ERROR, "invalid 'tree' line format - bad sha1");
	buffer += 46;
	while (!memcmp(buffer, "parent ", 7)) {
		if (get_sha1_hex(buffer+7, sha1) || buffer[47] != '\n')
			return error_func(&commit->object, FSCK_ERROR, "invalid 'parent' line format - bad sha1");
		buffer += 48;
		parents++;
	}
	graft = lookup_commit_graft(commit->object.sha1);
	if (graft) {
		struct commit_list *p = commit->parents;
		parents = 0;
		while (p) {
			p = p->next;
			parents++;
		}
		if (graft->nr_parent == -1 && !parents)
			; /* shallow commit */
		else if (graft->nr_parent != parents)
			return error_func(&commit->object, FSCK_ERROR, "graft objects missing");
	} else {
		struct commit_list *p = commit->parents;
		while (p && parents) {
			p = p->next;
			parents--;
		}
		if (p || parents)
			return error_func(&commit->object, FSCK_ERROR, "parent objects missing");
	}
	if (memcmp(buffer, "author ", 7))
		return error_func(&commit->object, FSCK_ERROR, "invalid format - expected 'author' line");
	if (!commit->tree)
		return error_func(&commit->object, FSCK_ERROR, "could not load commit's tree %s", sha1_to_hex(tree_sha1));

	return 0;
}

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

	if (!tagged)
		return error_func(&tag->object, FSCK_ERROR, "could not load tagged object");
	return 0;
}

int fsck_object(struct object *obj, int strict, fsck_error error_func)
{
	if (!obj)
		return error_func(obj, FSCK_ERROR, "no valid object to fsck");

	if (obj->type == OBJ_BLOB)
		return 0;
	if (obj->type == OBJ_TREE)
		return fsck_tree((struct tree *) obj, strict, error_func);
	if (obj->type == OBJ_COMMIT)
		return fsck_commit((struct commit *) obj, error_func);
	if (obj->type == OBJ_TAG)
		return fsck_tag((struct tag *) obj, error_func);

	return error_func(obj, FSCK_ERROR, "unknown type '%d' (internal fsck error)",
			  obj->type);
}
Commit	Line	Data
355885d5 MK	1	#include "cache.h"
	2	#include "object.h"
	3	#include "blob.h"
	4	#include "tree.h"
	5	#include "tree-walk.h"
	6	#include "commit.h"
	7	#include "tag.h"
	8	#include "fsck.h"
	9
	10	static int fsck_walk_tree(struct tree tree, fsck_walk_func walk, void data)
	11	{
	12	struct tree_desc desc;
	13	struct name_entry entry;
	14	int res = 0;
	15
	16	if (parse_tree(tree))
	17	return -1;
	18
	19	init_tree_desc(&desc, tree->buffer, tree->size);
	20	while (tree_entry(&desc, &entry)) {
	21	int result;
	22
	23	if (S_ISGITLINK(entry.mode))
	24	continue;
	25	if (S_ISDIR(entry.mode))
	26	result = walk(&lookup_tree(entry.sha1)->object, OBJ_TREE, data);
	27	else if (S_ISREG(entry.mode) \|\| S_ISLNK(entry.mode))
	28	result = walk(&lookup_blob(entry.sha1)->object, OBJ_BLOB, data);
	29	else {
	30	result = error("in tree %s: entry %s has bad mode %.6o\n",
	31	sha1_to_hex(tree->object.sha1), entry.path, entry.mode);
	32	}
	33	if (result < 0)
	34	return result;
	35	if (!res)
	36	res = result;
	37	}
	38	return res;
	39	}
	40
	41	static int fsck_walk_commit(struct commit commit, fsck_walk_func walk, void data)
	42	{
	43	struct commit_list *parents;
	44	int res;
	45	int result;
	46
	47	if (parse_commit(commit))
	48	return -1;
	49
	50	result = walk((struct object *)commit->tree, OBJ_TREE, data);
	51	if (result < 0)
	52	return result;
	53	res = result;
	54
	55	parents = commit->parents;
	56	while (parents) {
	57	result = walk((struct object *)parents->item, OBJ_COMMIT, data);
	58	if (result < 0)
	59	return result;
	60	if (!res)
	61	res = result;
	62	parents = parents->next;
	63	}
	64	return res;
65	}
66
67	static int fsck_walk_tag(struct tag tag, fsck_walk_func walk, void data)
68	{
69	if (parse_tag(tag))
70	return -1;
71	return walk(tag->tagged, OBJ_ANY, data);
72	}
73
74	int fsck_walk(struct object obj, fsck_walk_func walk, void data)
75	{
76	if (!obj)
77	return -1;
78	switch (obj->type) {
79	case OBJ_BLOB:
80	return 0;
81	case OBJ_TREE:
82	return fsck_walk_tree((struct tree *)obj, walk, data);
83	case OBJ_COMMIT:
84	return fsck_walk_commit((struct commit *)obj, walk, data);
85	case OBJ_TAG:
86	return fsck_walk_tag((struct tag *)obj, walk, data);
87	default:
88	error("Unknown object type for %s", sha1_to_hex(obj->sha1));
89	return -1;
90	}
91	}
ba002f3b MK	92
	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	*/
	101	#define TREE_UNORDERED (-1)
	102	#define TREE_HAS_DUPS (-2)
	103
	104	static int verify_ordered(unsigned mode1, const char name1, unsigned mode2, const char name2)
	105	{
	106	int len1 = strlen(name1);
	107	int len2 = strlen(name2);
	108	int len = len1 < len2 ? len1 : len2;
	109	unsigned char c1, c2;
	110	int cmp;
	111
	112	cmp = memcmp(name1, name2, len);
	113	if (cmp < 0)
	114	return 0;
	115	if (cmp > 0)
	116	return TREE_UNORDERED;
	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 = name1[len];
	124	c2 = name2[len];
	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;
	132	if (!c1 && S_ISDIR(mode1))
	133	c1 = '/';
	134	if (!c2 && S_ISDIR(mode2))
	135	c2 = '/';
	136	return c1 < c2 ? 0 : TREE_UNORDERED;
	137	}
	138
	139	static int fsck_tree(struct tree *item, int strict, fsck_error error_func)
	140	{
	141	int retval;
	142	int has_full_path = 0;
	143	int has_empty_name = 0;
	144	int has_zero_pad = 0;
	145	int has_bad_modes = 0;
	146	int has_dup_entries = 0;
	147	int not_properly_sorted = 0;
	148	struct tree_desc desc;
	149	unsigned o_mode;
	150	const char *o_name;
	151	const unsigned char *o_sha1;
	152
	153	init_tree_desc(&desc, item->buffer, item->size);
	154
	155	o_mode = 0;
156	o_name = NULL;
157	o_sha1 = NULL;
158	if (!desc.size)
159	return error_func(&item->object, FSCK_ERROR, "empty tree");
160
161	while (desc.size) {
162	unsigned mode;
163	const char *name;
164	const unsigned char *sha1;
165
166	sha1 = tree_entry_extract(&desc, &name, &mode);
167
168	if (strchr(name, '/'))
169	has_full_path = 1;
170	if (!*name)
171	has_empty_name = 1;
172	has_zero_pad \|= (char )desc.buffer == '0';
173	update_tree_entry(&desc);
174
175	switch (mode) {
176	/*
177	* Standard modes..
178	*/
179	case S_IFREG \| 0755:
180	case S_IFREG \| 0644:
181	case S_IFLNK:
182	case S_IFDIR:
183	case S_IFGITLINK:
184	break;
185	/*
186	* This is nonstandard, but we had a few of these
187	* early on when we honored the full set of mode
188	* bits..
189	*/
190	case S_IFREG \| 0664:
191	if (!strict)
192	break;
193	default:
194	has_bad_modes = 1;
195	}
196
197	if (o_name) {
198	switch (verify_ordered(o_mode, o_name, mode, name)) {
199	case TREE_UNORDERED:
200	not_properly_sorted = 1;
201	break;
202	case TREE_HAS_DUPS:
203	has_dup_entries = 1;
204	break;
205	default:
206	break;
207	}
208	}
209
210	o_mode = mode;
211	o_name = name;
212	o_sha1 = sha1;
213	}
214
215	retval = 0;
216	if (has_full_path)
217	retval += error_func(&item->object, FSCK_WARN, "contains full pathnames");
218	if (has_empty_name)
219	retval += error_func(&item->object, FSCK_WARN, "contains empty pathname");
220	if (has_zero_pad)
221	retval += error_func(&item->object, FSCK_WARN, "contains zero-padded file modes");
222	if (has_bad_modes)
223	retval += error_func(&item->object, FSCK_WARN, "contains bad file modes");
224	if (has_dup_entries)
225	retval += error_func(&item->object, FSCK_ERROR, "contains duplicate file entries");
226	if (not_properly_sorted)
227	retval += error_func(&item->object, FSCK_ERROR, "not properly sorted");
228	return retval;
229	}
230
231	static int fsck_commit(struct commit *commit, fsck_error error_func)
232	{
233	char *buffer = commit->buffer;
234	unsigned char tree_sha1[20], sha1[20];
235	struct commit_graft *graft;
236	int parents = 0;
237
238	if (!commit->date)
239	return error_func(&commit->object, FSCK_ERROR, "invalid author/committer line");
240
241	if (memcmp(buffer, "tree ", 5))
242	return error_func(&commit->object, FSCK_ERROR, "invalid format - expected 'tree' line");
243	if (get_sha1_hex(buffer+5, tree_sha1) \|\| buffer[45] != '\n')
244	return error_func(&commit->object, FSCK_ERROR, "invalid 'tree' line format - bad sha1");
245	buffer += 46;
246	while (!memcmp(buffer, "parent ", 7)) {
247	if (get_sha1_hex(buffer+7, sha1) \|\| buffer[47] != '\n')
248	return error_func(&commit->object, FSCK_ERROR, "invalid 'parent' line format - bad sha1");
249	buffer += 48;
250	parents++;
251	}
252	graft = lookup_commit_graft(commit->object.sha1);
253	if (graft) {
254	struct commit_list *p = commit->parents;
255	parents = 0;
256	while (p) {
257	p = p->next;
258	parents++;
259	}
260	if (graft->nr_parent == -1 && !parents)
261	; /* shallow commit */
262	else if (graft->nr_parent != parents)
263	return error_func(&commit->object, FSCK_ERROR, "graft objects missing");
264	} else {
265	struct commit_list *p = commit->parents;
266	while (p && parents) {
267	p = p->next;
268	parents--;
269	}
270	if (p \|\| parents)
271	return error_func(&commit->object, FSCK_ERROR, "parent objects missing");
272	}
273	if (memcmp(buffer, "author ", 7))
274	return error_func(&commit->object, FSCK_ERROR, "invalid format - expected 'author' line");
275	if (!commit->tree)
276	return error_func(&commit->object, FSCK_ERROR, "could not load commit's tree %s", sha1_to_hex(tree_sha1));
277
278	return 0;
279	}
280
281	static int fsck_tag(struct tag *tag, fsck_error error_func)
282	{
283	struct object *tagged = tag->tagged;
284
285	if (!tagged)
286	return error_func(&tag->object, FSCK_ERROR, "could not load tagged object");
287	return 0;
288	}
289
290	int fsck_object(struct object *obj, int strict, fsck_error error_func)
291	{
292	if (!obj)
293	return error_func(obj, FSCK_ERROR, "no valid object to fsck");
294
295	if (obj->type == OBJ_BLOB)
296	return 0;
297	if (obj->type == OBJ_TREE)
298	return fsck_tree((struct tree *) obj, strict, error_func);
299	if (obj->type == OBJ_COMMIT)
300	return fsck_commit((struct commit *) obj, error_func);
301	if (obj->type == OBJ_TAG)
302	return fsck_tag((struct tag *) obj, error_func);
303
304	return error_func(obj, FSCK_ERROR, "unknown type '%d' (internal fsck error)",
305	obj->type);
306	}