[thirdparty/git.git] / tree-diff.c

/*
 * Helper functions for tree diff generation
 */
#include "cache.h"
#include "diff.h"
#include "tree.h"

static char *malloc_base(const char *base, int baselen, const char *path, int pathlen)
{
	char *newbase = xmalloc(baselen + pathlen + 2);
	memcpy(newbase, base, baselen);
	memcpy(newbase + baselen, path, pathlen);
	memcpy(newbase + baselen + pathlen, "/", 2);
	return newbase;
}

static void show_entry(struct diff_options *opt, const char *prefix, struct tree_desc *desc,
		       const char *base, int baselen);

static int compare_tree_entry(struct tree_desc *t1, struct tree_desc *t2, const char *base, int baselen, struct diff_options *opt)
{
	unsigned mode1, mode2;
	const char *path1, *path2;
	const unsigned char *sha1, *sha2;
	int cmp, pathlen1, pathlen2;

	sha1 = tree_entry_extract(t1, &path1, &mode1);
	sha2 = tree_entry_extract(t2, &path2, &mode2);

	pathlen1 = tree_entry_len(path1, sha1);
	pathlen2 = tree_entry_len(path2, sha2);
	cmp = base_name_compare(path1, pathlen1, mode1, path2, pathlen2, mode2);
	if (cmp < 0) {
		show_entry(opt, "-", t1, base, baselen);
		return -1;
	}
	if (cmp > 0) {
		show_entry(opt, "+", t2, base, baselen);
		return 1;
	}
	if (!opt->find_copies_harder && !hashcmp(sha1, sha2) && mode1 == mode2)
		return 0;

	/*
	 * If the filemode has changed to/from a directory from/to a regular
	 * file, we need to consider it a remove and an add.
	 */
	if (S_ISDIR(mode1) != S_ISDIR(mode2)) {
		show_entry(opt, "-", t1, base, baselen);
		show_entry(opt, "+", t2, base, baselen);
		return 0;
	}

	if (opt->recursive && S_ISDIR(mode1)) {
		int retval;
		char *newbase = malloc_base(base, baselen, path1, pathlen1);
		if (opt->tree_in_recursive)
			opt->change(opt, mode1, mode2,
				    sha1, sha2, base, path1);
		retval = diff_tree_sha1(sha1, sha2, newbase, opt);
		free(newbase);
		return retval;
	}

	opt->change(opt, mode1, mode2, sha1, sha2, base, path1);
	return 0;
}

/*
 * Is a tree entry interesting given the pathspec we have?
 *
 * Return:
 *  - positive for yes
 *  - zero for no
 *  - negative for "no, and no subsequent entries will be either"
 */
static int tree_entry_interesting(struct tree_desc *desc, const char *base, int baselen, struct diff_options *opt)
{
	const char *path;
	const unsigned char *sha1;
	unsigned mode;
	int i;
	int pathlen;
	int never_interesting = -1;

	if (!opt->nr_paths)
		return 1;

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

	pathlen = tree_entry_len(path, sha1);

	for (i = 0; i < opt->nr_paths; i++) {
		const char *match = opt->paths[i];
		int matchlen = opt->pathlens[i];
		int m;

		if (baselen >= matchlen) {
			/* If it doesn't match, move along... */
			if (strncmp(base, match, matchlen))
				continue;

			/* The base is a subdirectory of a path which was specified. */
			return 1;
		}

		/* Does the base match? */
		if (strncmp(base, match, baselen))
			continue;

		match += baselen;
		matchlen -= baselen;

		/*
		 * Does match sort strictly earlier than path with their
		 * common parts?
		 */
		m = strncmp(match, path,
			    (matchlen < pathlen) ? matchlen : pathlen);
		if (m < 0)
			continue;

		/*
		 * If we come here even once, that means there is at
		 * least one pathspec that would sort equal to or
		 * later than the path we are currently looking at.
		 * In other words, if we have never reached this point
		 * after iterating all pathspecs, it means all
		 * pathspecs are either outside of base, or inside the
		 * base but sorts strictly earlier than the current
		 * one.  In either case, they will never match the
		 * subsequent entries.  In such a case, we initialized
		 * the variable to -1 and that is what will be
		 * returned, allowing the caller to terminate early.
		 */
		never_interesting = 0;

		if (pathlen > matchlen)
			continue;

		if (matchlen > pathlen) {
			if (match[pathlen] != '/')
				continue;
			if (!S_ISDIR(mode))
				continue;
		}

		/*
		 * If common part matched earlier then it is a hit,
		 * because we rejected the case where path is not a
		 * leading directory and is shorter than match.
		 */
		if (!m)
			return 1;
	}
	return never_interesting; /* No matches */
}

/* A whole sub-tree went away or appeared */
static void show_tree(struct diff_options *opt, const char *prefix, struct tree_desc *desc, const char *base, int baselen)
{
	while (desc->size) {
		int show = tree_entry_interesting(desc, base, baselen, opt);
		if (show < 0)
			break;
		if (show)
			show_entry(opt, prefix, desc, base, baselen);
		update_tree_entry(desc);
	}
}

/* A file entry went away or appeared */
static void show_entry(struct diff_options *opt, const char *prefix, struct tree_desc *desc,
		       const char *base, int baselen)
{
	unsigned mode;
	const char *path;
	const unsigned char *sha1 = tree_entry_extract(desc, &path, &mode);

	if (opt->recursive && S_ISDIR(mode)) {
		enum object_type type;
		int pathlen = tree_entry_len(path, sha1);
		char *newbase = malloc_base(base, baselen, path, pathlen);
		struct tree_desc inner;
		void *tree;
		unsigned long size;

		tree = read_sha1_file(sha1, &type, &size);
		if (!tree || type != OBJ_TREE)
			die("corrupt tree sha %s", sha1_to_hex(sha1));

		init_tree_desc(&inner, tree, size);
		show_tree(opt, prefix, &inner, newbase, baselen + 1 + pathlen);

		free(tree);
		free(newbase);
	} else {
		opt->add_remove(opt, prefix[0], mode, sha1, base, path);
	}
}

static void skip_uninteresting(struct tree_desc *t, const char *base, int baselen, struct diff_options *opt)
{
	while (t->size) {
		int show = tree_entry_interesting(t, base, baselen, opt);
		if (!show) {
			update_tree_entry(t);
			continue;
		}
		/* Skip it all? */
		if (show < 0)
			t->size = 0;
		return;
	}
}

int diff_tree(struct tree_desc *t1, struct tree_desc *t2, const char *base, struct diff_options *opt)
{
	int baselen = strlen(base);

	for (;;) {
		if (opt->quiet && opt->has_changes)
			break;
		if (opt->nr_paths) {
			skip_uninteresting(t1, base, baselen, opt);
			skip_uninteresting(t2, base, baselen, opt);
		}
		if (!t1->size) {
			if (!t2->size)
				break;
			show_entry(opt, "+", t2, base, baselen);
			update_tree_entry(t2);
			continue;
		}
		if (!t2->size) {
			show_entry(opt, "-", t1, base, baselen);
			update_tree_entry(t1);
			continue;
		}
		switch (compare_tree_entry(t1, t2, base, baselen, opt)) {
		case -1:
			update_tree_entry(t1);
			continue;
		case 0:
			update_tree_entry(t1);
			/* Fallthrough */
		case 1:
			update_tree_entry(t2);
			continue;
		}
		die("git-diff-tree: internal error");
	}
	return 0;
}

int diff_tree_sha1(const unsigned char *old, const unsigned char *new, const char *base, struct diff_options *opt)
{
	void *tree1, *tree2;
	struct tree_desc t1, t2;
	unsigned long size1, size2;
	int retval;

	tree1 = read_object_with_reference(old, tree_type, &size1, NULL);
	if (!tree1)
		die("unable to read source tree (%s)", sha1_to_hex(old));
	tree2 = read_object_with_reference(new, tree_type, &size2, NULL);
	if (!tree2)
		die("unable to read destination tree (%s)", sha1_to_hex(new));
	init_tree_desc(&t1, tree1, size1);
	init_tree_desc(&t2, tree2, size2);
	retval = diff_tree(&t1, &t2, base, opt);
	free(tree1);
	free(tree2);
	return retval;
}

int diff_root_tree_sha1(const unsigned char *new, const char *base, struct diff_options *opt)
{
	int retval;
	void *tree;
	unsigned long size;
	struct tree_desc empty, real;

	tree = read_object_with_reference(new, tree_type, &size, NULL);
	if (!tree)
		die("unable to read root tree (%s)", sha1_to_hex(new));
	init_tree_desc(&real, tree, size);

	init_tree_desc(&empty, "", 0);
	retval = diff_tree(&empty, &real, base, opt);
	free(tree);
	return retval;
}

static int count_paths(const char **paths)
{
	int i = 0;
	while (*paths++)
		i++;
	return i;
}

void diff_tree_release_paths(struct diff_options *opt)
{
	free(opt->pathlens);
}

void diff_tree_setup_paths(const char **p, struct diff_options *opt)
{
	opt->nr_paths = 0;
	opt->pathlens = NULL;
	opt->paths = NULL;

	if (p) {
		int i;

		opt->paths = p;
		opt->nr_paths = count_paths(p);
		if (opt->nr_paths == 0) {
			opt->pathlens = NULL;
			return;
		}
		opt->pathlens = xmalloc(opt->nr_paths * sizeof(int));
		for (i=0; i < opt->nr_paths; i++)
			opt->pathlens[i] = strlen(p[i]);
	}
}
Commit	Line	Data
ac1b3d12 LT	1	/*
	2	* Helper functions for tree diff generation
	3	*/
	4	#include "cache.h"
	5	#include "diff.h"
8e440259	6	#include "tree.h"
ac1b3d12	7
304de2d2	8	static char malloc_base(const char base, int baselen, const char *path, int pathlen)
ac1b3d12	9	{
ac1b3d12 LT	10	char *newbase = xmalloc(baselen + pathlen + 2);
	11	memcpy(newbase, base, baselen);
	12	memcpy(newbase + baselen, path, pathlen);
	13	memcpy(newbase + baselen + pathlen, "/", 2);
	14	return newbase;
	15	}
	16
cf995ede	17	static void show_entry(struct diff_options opt, const char prefix, struct tree_desc *desc,
304de2d2	18	const char *base, int baselen);
ac1b3d12	19
304de2d2	20	static int compare_tree_entry(struct tree_desc t1, struct tree_desc t2, const char base, int baselen, struct diff_options opt)
ac1b3d12 LT	21	{
	22	unsigned mode1, mode2;
	23	const char path1, path2;
	24	const unsigned char sha1, sha2;
	25	int cmp, pathlen1, pathlen2;
	26
50f9a858 LT	27	sha1 = tree_entry_extract(t1, &path1, &mode1);
50f9a858 LT	28	sha2 = tree_entry_extract(t2, &path2, &mode2);
ac1b3d12	29
304de2d2 LT	30	pathlen1 = tree_entry_len(path1, sha1);
304de2d2 LT	31	pathlen2 = tree_entry_len(path2, sha2);
ac1b3d12 LT	32	cmp = base_name_compare(path1, pathlen1, mode1, path2, pathlen2, mode2);
ac1b3d12 LT	33	if (cmp < 0) {
304de2d2	34	show_entry(opt, "-", t1, base, baselen);
ac1b3d12 LT	35	return -1;
	36	}
	37	if (cmp > 0) {
304de2d2	38	show_entry(opt, "+", t2, base, baselen);
ac1b3d12 LT	39	return 1;
ac1b3d12 LT	40	}
a89fccd2	41	if (!opt->find_copies_harder && !hashcmp(sha1, sha2) && mode1 == mode2)
ac1b3d12 LT	42	return 0;
	43
	44	/*
	45	* If the filemode has changed to/from a directory from/to a regular
	46	* file, we need to consider it a remove and an add.
	47	*/
	48	if (S_ISDIR(mode1) != S_ISDIR(mode2)) {
304de2d2 LT	49	show_entry(opt, "-", t1, base, baselen);
304de2d2 LT	50	show_entry(opt, "+", t2, base, baselen);
ac1b3d12 LT	51	return 0;
	52	}
	53
	54	if (opt->recursive && S_ISDIR(mode1)) {
	55	int retval;
304de2d2	56	char *newbase = malloc_base(base, baselen, path1, pathlen1);
ac1b3d12 LT	57	if (opt->tree_in_recursive)
	58	opt->change(opt, mode1, mode2,
	59	sha1, sha2, base, path1);
	60	retval = diff_tree_sha1(sha1, sha2, newbase, opt);
	61	free(newbase);
	62	return retval;
	63	}
	64
	65	opt->change(opt, mode1, mode2, sha1, sha2, base, path1);
	66	return 0;
	67	}
	68
5d865017 LT	69	/*
	70	* Is a tree entry interesting given the pathspec we have?
	71	*
	72	* Return:
	73	* - positive for yes
	74	* - zero for no
	75	* - negative for "no, and no subsequent entries will be either"
	76	*/
	77	static int tree_entry_interesting(struct tree_desc desc, const char base, int baselen, struct diff_options *opt)
ac1b3d12 LT	78	{
ac1b3d12 LT	79	const char *path;
304de2d2	80	const unsigned char *sha1;
ac1b3d12 LT	81	unsigned mode;
ac1b3d12 LT	82	int i;
304de2d2	83	int pathlen;
7d2f667b	84	int never_interesting = -1;
ac1b3d12	85
a8baa7b9	86	if (!opt->nr_paths)
ac1b3d12 LT	87	return 1;
ac1b3d12 LT	88
304de2d2	89	sha1 = tree_entry_extract(desc, &path, &mode);
ac1b3d12	90
304de2d2	91	pathlen = tree_entry_len(path, sha1);
ac1b3d12	92
7d2f667b	93	for (i = 0; i < opt->nr_paths; i++) {
a8baa7b9 JH	94	const char *match = opt->paths[i];
a8baa7b9 JH	95	int matchlen = opt->pathlens[i];
7d2f667b	96	int m;
ac1b3d12 LT	97
	98	if (baselen >= matchlen) {
	99	/* If it doesn't match, move along... */
	100	if (strncmp(base, match, matchlen))
	101	continue;
	102
	103	/* The base is a subdirectory of a path which was specified. */
	104	return 1;
	105	}
	106
	107	/* Does the base match? */
	108	if (strncmp(base, match, baselen))
	109	continue;
	110
	111	match += baselen;
	112	matchlen -= baselen;
	113
7d2f667b JH	114	/*
	115	* Does match sort strictly earlier than path with their
	116	* common parts?
	117	*/
	118	m = strncmp(match, path,
	119	(matchlen < pathlen) ? matchlen : pathlen);
	120	if (m < 0)
	121	continue;
	122
	123	/*
	124	* If we come here even once, that means there is at
	125	* least one pathspec that would sort equal to or
	126	* later than the path we are currently looking at.
	127	* In other words, if we have never reached this point
	128	* after iterating all pathspecs, it means all
	129	* pathspecs are either outside of base, or inside the
	130	* base but sorts strictly earlier than the current
	131	* one. In either case, they will never match the
	132	* subsequent entries. In such a case, we initialized
	133	* the variable to -1 and that is what will be
	134	* returned, allowing the caller to terminate early.
	135	*/
	136	never_interesting = 0;
	137
ac1b3d12 LT	138	if (pathlen > matchlen)
	139	continue;
	140
	141	if (matchlen > pathlen) {
	142	if (match[pathlen] != '/')
	143	continue;
	144	if (!S_ISDIR(mode))
	145	continue;
	146	}
	147
7d2f667b JH	148	/*
	149	* If common part matched earlier then it is a hit,
	150	* because we rejected the case where path is not a
	151	* leading directory and is shorter than match.
	152	*/
	153	if (!m)
	154	return 1;
ac1b3d12	155	}
7d2f667b	156	return never_interesting; /* No matches */
ac1b3d12 LT	157	}
	158
	159	/* A whole sub-tree went away or appeared */
304de2d2	160	static void show_tree(struct diff_options opt, const char prefix, struct tree_desc desc, const char base, int baselen)
ac1b3d12 LT	161	{
ac1b3d12 LT	162	while (desc->size) {
5d865017 LT	163	int show = tree_entry_interesting(desc, base, baselen, opt);
	164	if (show < 0)
	165	break;
	166	if (show)
304de2d2	167	show_entry(opt, prefix, desc, base, baselen);
ac1b3d12 LT	168	update_tree_entry(desc);
	169	}
	170	}
	171
	172	/* A file entry went away or appeared */
cf995ede	173	static void show_entry(struct diff_options opt, const char prefix, struct tree_desc *desc,
304de2d2	174	const char *base, int baselen)
ac1b3d12 LT	175	{
	176	unsigned mode;
	177	const char *path;
50f9a858	178	const unsigned char *sha1 = tree_entry_extract(desc, &path, &mode);
ac1b3d12 LT	179
ac1b3d12 LT	180	if (opt->recursive && S_ISDIR(mode)) {
21666f1a	181	enum object_type type;
304de2d2 LT	182	int pathlen = tree_entry_len(path, sha1);
304de2d2 LT	183	char *newbase = malloc_base(base, baselen, path, pathlen);
ac1b3d12 LT	184	struct tree_desc inner;
ac1b3d12 LT	185	void *tree;
6fda5e51	186	unsigned long size;
ac1b3d12	187
6fda5e51	188	tree = read_sha1_file(sha1, &type, &size);
21666f1a	189	if (!tree \|\| type != OBJ_TREE)
ac1b3d12 LT	190	die("corrupt tree sha %s", sha1_to_hex(sha1));
ac1b3d12 LT	191
6fda5e51	192	init_tree_desc(&inner, tree, size);
304de2d2	193	show_tree(opt, prefix, &inner, newbase, baselen + 1 + pathlen);
ac1b3d12 LT	194
	195	free(tree);
	196	free(newbase);
cf995ede DR	197	} else {
cf995ede DR	198	opt->add_remove(opt, prefix[0], mode, sha1, base, path);
ac1b3d12	199	}
ac1b3d12 LT	200	}
ac1b3d12 LT	201
5d865017 LT	202	static void skip_uninteresting(struct tree_desc t, const char base, int baselen, struct diff_options *opt)
	203	{
	204	while (t->size) {
	205	int show = tree_entry_interesting(t, base, baselen, opt);
	206	if (!show) {
	207	update_tree_entry(t);
	208	continue;
	209	}
	210	/* Skip it all? */
	211	if (show < 0)
	212	t->size = 0;
	213	return;
	214	}
	215	}
	216
ac1b3d12 LT	217	int diff_tree(struct tree_desc t1, struct tree_desc t2, const char base, struct diff_options opt)
ac1b3d12 LT	218	{
304de2d2 LT	219	int baselen = strlen(base);
304de2d2 LT	220
5d865017	221	for (;;) {
822cac01 JH	222	if (opt->quiet && opt->has_changes)
822cac01 JH	223	break;
5d865017 LT	224	if (opt->nr_paths) {
	225	skip_uninteresting(t1, base, baselen, opt);
	226	skip_uninteresting(t2, base, baselen, opt);
ac1b3d12 LT	227	}
ac1b3d12 LT	228	if (!t1->size) {
5d865017 LT	229	if (!t2->size)
5d865017 LT	230	break;
304de2d2	231	show_entry(opt, "+", t2, base, baselen);
ac1b3d12 LT	232	update_tree_entry(t2);
	233	continue;
	234	}
	235	if (!t2->size) {
304de2d2	236	show_entry(opt, "-", t1, base, baselen);
ac1b3d12 LT	237	update_tree_entry(t1);
	238	continue;
	239	}
304de2d2	240	switch (compare_tree_entry(t1, t2, base, baselen, opt)) {
ac1b3d12 LT	241	case -1:
	242	update_tree_entry(t1);
	243	continue;
	244	case 0:
	245	update_tree_entry(t1);
	246	/* Fallthrough */
	247	case 1:
	248	update_tree_entry(t2);
	249	continue;
	250	}
	251	die("git-diff-tree: internal error");
	252	}
	253	return 0;
	254	}
	255
	256	int diff_tree_sha1(const unsigned char old, const unsigned char new, const char base, struct diff_options opt)
	257	{
	258	void tree1, tree2;
	259	struct tree_desc t1, t2;
6fda5e51	260	unsigned long size1, size2;
ac1b3d12 LT	261	int retval;
ac1b3d12 LT	262
6fda5e51	263	tree1 = read_object_with_reference(old, tree_type, &size1, NULL);
ac1b3d12 LT	264	if (!tree1)
ac1b3d12 LT	265	die("unable to read source tree (%s)", sha1_to_hex(old));
6fda5e51	266	tree2 = read_object_with_reference(new, tree_type, &size2, NULL);
ac1b3d12 LT	267	if (!tree2)
ac1b3d12 LT	268	die("unable to read destination tree (%s)", sha1_to_hex(new));
6fda5e51 LT	269	init_tree_desc(&t1, tree1, size1);
6fda5e51 LT	270	init_tree_desc(&t2, tree2, size2);
ac1b3d12 LT	271	retval = diff_tree(&t1, &t2, base, opt);
	272	free(tree1);
	273	free(tree2);
	274	return retval;
	275	}
	276
2b60356d RS	277	int diff_root_tree_sha1(const unsigned char new, const char base, struct diff_options *opt)
	278	{
	279	int retval;
	280	void *tree;
6fda5e51	281	unsigned long size;
2b60356d RS	282	struct tree_desc empty, real;
2b60356d RS	283
6fda5e51	284	tree = read_object_with_reference(new, tree_type, &size, NULL);
2b60356d RS	285	if (!tree)
2b60356d RS	286	die("unable to read root tree (%s)", sha1_to_hex(new));
6fda5e51	287	init_tree_desc(&real, tree, size);
2b60356d	288
6fda5e51	289	init_tree_desc(&empty, "", 0);
2b60356d RS	290	retval = diff_tree(&empty, &real, base, opt);
	291	free(tree);
	292	return retval;
	293	}
	294
ac1b3d12 LT	295	static int count_paths(const char **paths)
	296	{
	297	int i = 0;
	298	while (*paths++)
	299	i++;
	300	return i;
	301	}
	302
a8baa7b9	303	void diff_tree_release_paths(struct diff_options *opt)
ac1b3d12	304	{
a8baa7b9 JH	305	free(opt->pathlens);
	306	}
	307
	308	void diff_tree_setup_paths(const char *p, struct diff_options opt)
	309	{
	310	opt->nr_paths = 0;
	311	opt->pathlens = NULL;
	312	opt->paths = NULL;
	313
ac1b3d12 LT	314	if (p) {
	315	int i;
	316
a8baa7b9 JH	317	opt->paths = p;
	318	opt->nr_paths = count_paths(p);
	319	if (opt->nr_paths == 0) {
	320	opt->pathlens = NULL;
7e4a2a84 JH	321	return;
7e4a2a84 JH	322	}
a8baa7b9 JH	323	opt->pathlens = xmalloc(opt->nr_paths * sizeof(int));
	324	for (i=0; i < opt->nr_paths; i++)
	325	opt->pathlens[i] = strlen(p[i]);
ac1b3d12 LT	326	}
ac1b3d12 LT	327	}