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

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

/*
 * Compare two tree entries, taking into account only path/S_ISDIR(mode),
 * but not their sha1's.
 *
 * NOTE files and directories *always* compare differently, even when having
 *      the same name - thanks to base_name_compare().
 *
 * NOTE empty (=invalid) descriptor(s) take part in comparison as +infty,
 *      so that they sort *after* valid tree entries.
 *
 *      Due to this convention, if trees are scanned in sorted order, all
 *      non-empty descriptors will be processed first.
 */
static int tree_entry_pathcmp(struct tree_desc *t1, struct tree_desc *t2)
{
	struct name_entry *e1, *e2;
	int cmp;

	/* empty descriptors sort after valid tree entries */
	if (!t1->size)
		return t2->size ? 1 : 0;
	else if (!t2->size)
		return -1;

	e1 = &t1->entry;
	e2 = &t2->entry;
	cmp = base_name_compare(e1->path, tree_entry_len(e1), e1->mode,
				e2->path, tree_entry_len(e2), e2->mode);
	return cmp;
}


/* convert path, t1/t2 -> opt->diff_*() callbacks */
static void emit_diff(struct diff_options *opt, struct strbuf *path,
		      struct tree_desc *t1, struct tree_desc *t2)
{
	unsigned int mode1 = t1 ? t1->entry.mode : 0;
	unsigned int mode2 = t2 ? t2->entry.mode : 0;

	if (mode1 && mode2) {
		opt->change(opt, mode1, mode2, t1->entry.sha1, t2->entry.sha1,
			1, 1, path->buf, 0, 0);
	}
	else {
		const unsigned char *sha1;
		unsigned int mode;
		int addremove;

		if (mode2) {
			addremove = '+';
			sha1 = t2->entry.sha1;
			mode = mode2;
		} else {
			addremove = '-';
			sha1 = t1->entry.sha1;
			mode = mode1;
		}

		opt->add_remove(opt, addremove, mode, sha1, 1, path->buf, 0);
	}
}


/* new path should be added to diff
 *
 * 3 cases on how/when it should be called and behaves:
 *
 *	!t1,  t2	-> path added, parent lacks it
 *	 t1, !t2	-> path removed from parent
 *	 t1,  t2	-> path modified
 */
static void show_path(struct strbuf *base, struct diff_options *opt,
		      struct tree_desc *t1, struct tree_desc *t2)
{
	unsigned mode;
	const char *path;
	int pathlen;
	int old_baselen = base->len;
	int isdir, recurse = 0, emitthis = 1;

	/* at least something has to be valid */
	assert(t1 || t2);

	if (t2) {
		/* path present in resulting tree */
		tree_entry_extract(t2, &path, &mode);
		pathlen = tree_entry_len(&t2->entry);
		isdir = S_ISDIR(mode);
	} else {
		/*
		 * a path was removed - take path from parent. Also take
		 * mode from parent, to decide on recursion.
		 */
		tree_entry_extract(t1, &path, &mode);
		pathlen = tree_entry_len(&t1->entry);

		isdir = S_ISDIR(mode);
		mode = 0;
	}

	if (DIFF_OPT_TST(opt, RECURSIVE) && isdir) {
		recurse = 1;
		emitthis = DIFF_OPT_TST(opt, TREE_IN_RECURSIVE);
	}

	strbuf_add(base, path, pathlen);

	if (emitthis)
		emit_diff(opt, base, t1, t2);

	if (recurse) {
		strbuf_addch(base, '/');
		diff_tree_sha1(t1 ? t1->entry.sha1 : NULL,
			       t2 ? t2->entry.sha1 : NULL, base->buf, opt);
	}

	strbuf_setlen(base, old_baselen);
}

static void skip_uninteresting(struct tree_desc *t, struct strbuf *base,
			       struct diff_options *opt)
{
	enum interesting match;

	while (t->size) {
		match = tree_entry_interesting(&t->entry, base, 0, &opt->pathspec);
		if (match) {
			if (match == all_entries_not_interesting)
				t->size = 0;
			break;
		}
		update_tree_entry(t);
	}
}

static int ll_diff_tree_sha1(const unsigned char *old, const unsigned char *new,
			     const char *base_str, struct diff_options *opt)
{
	struct tree_desc t1, t2;
	void *t1tree, *t2tree;
	struct strbuf base;
	int baselen = strlen(base_str);

	t1tree = fill_tree_descriptor(&t1, old);
	t2tree = fill_tree_descriptor(&t2, new);

	/* Enable recursion indefinitely */
	opt->pathspec.recursive = DIFF_OPT_TST(opt, RECURSIVE);

	strbuf_init(&base, PATH_MAX);
	strbuf_add(&base, base_str, baselen);

	for (;;) {
		int cmp;

		if (diff_can_quit_early(opt))
			break;
		if (opt->pathspec.nr) {
			skip_uninteresting(&t1, &base, opt);
			skip_uninteresting(&t2, &base, opt);
		}
		if (!t1.size && !t2.size)
			break;

		cmp = tree_entry_pathcmp(&t1, &t2);

		/* t1 = t2 */
		if (cmp == 0) {
			if (DIFF_OPT_TST(opt, FIND_COPIES_HARDER) ||
			    hashcmp(t1.entry.sha1, t2.entry.sha1) ||
			    (t1.entry.mode != t2.entry.mode))
				show_path(&base, opt, &t1, &t2);

			update_tree_entry(&t1);
			update_tree_entry(&t2);
		}

		/* t1 < t2 */
		else if (cmp < 0) {
			show_path(&base, opt, &t1, /*t2=*/NULL);
			update_tree_entry(&t1);
		}

		/* t1 > t2 */
		else {
			show_path(&base, opt, /*t1=*/NULL, &t2);
			update_tree_entry(&t2);
		}
	}

	strbuf_release(&base);
	free(t2tree);
	free(t1tree);
	return 0;
}

/*
 * Does it look like the resulting diff might be due to a rename?
 *  - single entry
 *  - not a valid previous file
 */
static inline int diff_might_be_rename(void)
{
	return diff_queued_diff.nr == 1 &&
		!DIFF_FILE_VALID(diff_queued_diff.queue[0]->one);
}

static void try_to_follow_renames(const unsigned char *old, const unsigned char *new, const char *base, struct diff_options *opt)
{
	struct diff_options diff_opts;
	struct diff_queue_struct *q = &diff_queued_diff;
	struct diff_filepair *choice;
	int i;

	/*
	 * follow-rename code is very specific, we need exactly one
	 * path. Magic that matches more than one path is not
	 * supported.
	 */
	GUARD_PATHSPEC(&opt->pathspec, PATHSPEC_FROMTOP | PATHSPEC_LITERAL);
#if 0
	/*
	 * We should reject wildcards as well. Unfortunately we
	 * haven't got a reliable way to detect that 'foo\*bar' in
	 * fact has no wildcards. nowildcard_len is merely a hint for
	 * optimization. Let it slip for now until wildmatch is taught
	 * about dry-run mode and returns wildcard info.
	 */
	if (opt->pathspec.has_wildcard)
		die("BUG:%s:%d: wildcards are not supported",
		    __FILE__, __LINE__);
#endif

	/* Remove the file creation entry from the diff queue, and remember it */
	choice = q->queue[0];
	q->nr = 0;

	diff_setup(&diff_opts);
	DIFF_OPT_SET(&diff_opts, RECURSIVE);
	DIFF_OPT_SET(&diff_opts, FIND_COPIES_HARDER);
	diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT;
	diff_opts.single_follow = opt->pathspec.items[0].match;
	diff_opts.break_opt = opt->break_opt;
	diff_opts.rename_score = opt->rename_score;
	diff_setup_done(&diff_opts);
	ll_diff_tree_sha1(old, new, base, &diff_opts);
	diffcore_std(&diff_opts);
	free_pathspec(&diff_opts.pathspec);

	/* Go through the new set of filepairing, and see if we find a more interesting one */
	opt->found_follow = 0;
	for (i = 0; i < q->nr; i++) {
		struct diff_filepair *p = q->queue[i];

		/*
		 * Found a source? Not only do we use that for the new
		 * diff_queued_diff, we will also use that as the path in
		 * the future!
		 */
		if ((p->status == 'R' || p->status == 'C') &&
		    !strcmp(p->two->path, opt->pathspec.items[0].match)) {
			const char *path[2];

			/* Switch the file-pairs around */
			q->queue[i] = choice;
			choice = p;

			/* Update the path we use from now on.. */
			path[0] = p->one->path;
			path[1] = NULL;
			free_pathspec(&opt->pathspec);
			parse_pathspec(&opt->pathspec,
				       PATHSPEC_ALL_MAGIC & ~PATHSPEC_LITERAL,
				       PATHSPEC_LITERAL_PATH, "", path);

			/*
			 * The caller expects us to return a set of vanilla
			 * filepairs to let a later call to diffcore_std()
			 * it makes to sort the renames out (among other
			 * things), but we already have found renames
			 * ourselves; signal diffcore_std() not to muck with
			 * rename information.
			 */
			opt->found_follow = 1;
			break;
		}
	}

	/*
	 * Then, discard all the non-relevant file pairs...
	 */
	for (i = 0; i < q->nr; i++) {
		struct diff_filepair *p = q->queue[i];
		diff_free_filepair(p);
	}

	/*
	 * .. and re-instate the one we want (which might be either the
	 * original one, or the rename/copy we found)
	 */
	q->queue[0] = choice;
	q->nr = 1;
}

int diff_tree_sha1(const unsigned char *old, const unsigned char *new, const char *base, struct diff_options *opt)
{
	int retval;

	retval = ll_diff_tree_sha1(old, new, base, opt);
	if (!*base && DIFF_OPT_TST(opt, FOLLOW_RENAMES) && diff_might_be_rename())
		try_to_follow_renames(old, new, base, opt);

	return retval;
}

int diff_root_tree_sha1(const unsigned char *new, const char *base, struct diff_options *opt)
{
	return diff_tree_sha1(NULL, new, base, opt);
}
Commit	Line	Data
ac1b3d12 LT	1	/*
	2	* Helper functions for tree diff generation
	3	*/
	4	#include "cache.h"
	5	#include "diff.h"
750f7b66	6	#include "diffcore.h"
8e440259	7	#include "tree.h"
ac1b3d12	8
9bc06196 KS	9	/*
	10	* Compare two tree entries, taking into account only path/S_ISDIR(mode),
	11	* but not their sha1's.
	12	*
	13	* NOTE files and directories always compare differently, even when having
	14	* the same name - thanks to base_name_compare().
6ca844e9 KS	15	*
	16	* NOTE empty (=invalid) descriptor(s) take part in comparison as +infty,
	17	* so that they sort after valid tree entries.
	18	*
	19	* Due to this convention, if trees are scanned in sorted order, all
	20	* non-empty descriptors will be processed first.
9bc06196 KS	21	*/
9bc06196 KS	22	static int tree_entry_pathcmp(struct tree_desc t1, struct tree_desc t2)
ac1b3d12	23	{
1a27a154 KS	24	struct name_entry e1, e2;
1a27a154 KS	25	int cmp;
ac1b3d12	26
6ca844e9 KS	27	/* empty descriptors sort after valid tree entries */
	28	if (!t1->size)
	29	return t2->size ? 1 : 0;
	30	else if (!t2->size)
	31	return -1;
	32
1a27a154 KS	33	e1 = &t1->entry;
	34	e2 = &t2->entry;
	35	cmp = base_name_compare(e1->path, tree_entry_len(e1), e1->mode,
	36	e2->path, tree_entry_len(e2), e2->mode);
903bba68	37	return cmp;
d00e980c KS	38	}
	39
	40
	41	/* convert path, t1/t2 -> opt->diff_() callbacks /
	42	static void emit_diff(struct diff_options opt, struct strbuf path,
	43	struct tree_desc t1, struct tree_desc t2)
	44	{
	45	unsigned int mode1 = t1 ? t1->entry.mode : 0;
	46	unsigned int mode2 = t2 ? t2->entry.mode : 0;
	47
	48	if (mode1 && mode2) {
	49	opt->change(opt, mode1, mode2, t1->entry.sha1, t2->entry.sha1,
	50	1, 1, path->buf, 0, 0);
	51	}
	52	else {
	53	const unsigned char *sha1;
	54	unsigned int mode;
	55	int addremove;
	56
	57	if (mode2) {
	58	addremove = '+';
	59	sha1 = t2->entry.sha1;
	60	mode = mode2;
	61	} else {
	62	addremove = '-';
	63	sha1 = t1->entry.sha1;
	64	mode = mode1;
fd55a19e	65	}
d00e980c KS	66
d00e980c KS	67	opt->add_remove(opt, addremove, mode, sha1, 1, path->buf, 0);
ac1b3d12	68	}
ac1b3d12 LT	69	}
ac1b3d12 LT	70
d00e980c KS	71
	72	/* new path should be added to diff
	73	*
	74	* 3 cases on how/when it should be called and behaves:
	75	*
	76	* !t1, t2 -> path added, parent lacks it
	77	* t1, !t2 -> path removed from parent
	78	* t1, t2 -> path modified
	79	*/
	80	static void show_path(struct strbuf base, struct diff_options opt,
	81	struct tree_desc t1, struct tree_desc t2)
ac1b3d12 LT	82	{
	83	unsigned mode;
	84	const char *path;
d00e980c	85	int pathlen;
48932677	86	int old_baselen = base->len;
d00e980c KS	87	int isdir, recurse = 0, emitthis = 1;
	88
	89	/* at least something has to be valid */
	90	assert(t1 \|\| t2);
	91
	92	if (t2) {
	93	/* path present in resulting tree */
	94	tree_entry_extract(t2, &path, &mode);
	95	pathlen = tree_entry_len(&t2->entry);
	96	isdir = S_ISDIR(mode);
	97	} else {
	98	/*
	99	* a path was removed - take path from parent. Also take
	100	* mode from parent, to decide on recursion.
	101	*/
	102	tree_entry_extract(t1, &path, &mode);
	103	pathlen = tree_entry_len(&t1->entry);
	104
	105	isdir = S_ISDIR(mode);
	106	mode = 0;
	107	}
	108
	109	if (DIFF_OPT_TST(opt, RECURSIVE) && isdir) {
	110	recurse = 1;
	111	emitthis = DIFF_OPT_TST(opt, TREE_IN_RECURSIVE);
	112	}
ac1b3d12	113
48932677	114	strbuf_add(base, path, pathlen);
df533f34	115
d00e980c KS	116	if (emitthis)
	117	emit_diff(opt, base, t1, t2);
	118
	119	if (recurse) {
48932677	120	strbuf_addch(base, '/');
d00e980c KS	121	diff_tree_sha1(t1 ? t1->entry.sha1 : NULL,
	122	t2 ? t2->entry.sha1 : NULL, base->buf, opt);
	123	}
48932677 NTND	124
48932677 NTND	125	strbuf_setlen(base, old_baselen);
ac1b3d12 LT	126	}
ac1b3d12 LT	127
48932677	128	static void skip_uninteresting(struct tree_desc t, struct strbuf base,
e9066121	129	struct diff_options *opt)
5d865017	130	{
e9066121 KS	131	enum interesting match;
e9066121 KS	132
5d865017	133	while (t->size) {
e9066121 KS	134	match = tree_entry_interesting(&t->entry, base, 0, &opt->pathspec);
	135	if (match) {
	136	if (match == all_entries_not_interesting)
97d0b74a NTND	137	t->size = 0;
97d0b74a NTND	138	break;
5d865017	139	}
97d0b74a	140	update_tree_entry(t);
5d865017 LT	141	}
	142	}
	143
52894e70 KS	144	static int ll_diff_tree_sha1(const unsigned char old, const unsigned char new,
52894e70 KS	145	const char base_str, struct diff_options opt)
ac1b3d12	146	{
52894e70 KS	147	struct tree_desc t1, t2;
52894e70 KS	148	void t1tree, t2tree;
48932677 NTND	149	struct strbuf base;
48932677 NTND	150	int baselen = strlen(base_str);
304de2d2	151
52894e70 KS	152	t1tree = fill_tree_descriptor(&t1, old);
	153	t2tree = fill_tree_descriptor(&t2, new);
	154
bc96cc87 NTND	155	/* Enable recursion indefinitely */
bc96cc87 NTND	156	opt->pathspec.recursive = DIFF_OPT_TST(opt, RECURSIVE);
bc96cc87	157
48932677 NTND	158	strbuf_init(&base, PATH_MAX);
	159	strbuf_add(&base, base_str, baselen);
	160
5d865017	161	for (;;) {
903bba68 KS	162	int cmp;
903bba68 KS	163
28b9264d	164	if (diff_can_quit_early(opt))
822cac01	165	break;
66f13625	166	if (opt->pathspec.nr) {
52894e70 KS	167	skip_uninteresting(&t1, &base, opt);
52894e70 KS	168	skip_uninteresting(&t2, &base, opt);
ac1b3d12	169	}
52894e70	170	if (!t1.size && !t2.size)
6ca844e9	171	break;
5dfb2bbd	172
52894e70	173	cmp = tree_entry_pathcmp(&t1, &t2);
5dfb2bbd KS	174
	175	/* t1 = t2 */
	176	if (cmp == 0) {
903bba68	177	if (DIFF_OPT_TST(opt, FIND_COPIES_HARDER) \|\|
52894e70 KS	178	hashcmp(t1.entry.sha1, t2.entry.sha1) \|\|
	179	(t1.entry.mode != t2.entry.mode))
	180	show_path(&base, opt, &t1, &t2);
903bba68	181
52894e70 KS	182	update_tree_entry(&t1);
52894e70 KS	183	update_tree_entry(&t2);
5dfb2bbd KS	184	}
	185
	186	/* t1 < t2 */
	187	else if (cmp < 0) {
52894e70 KS	188	show_path(&base, opt, &t1, /t2=/NULL);
52894e70 KS	189	update_tree_entry(&t1);
5dfb2bbd KS	190	}
	191
	192	/* t1 > t2 */
	193	else {
52894e70 KS	194	show_path(&base, opt, /t1=/NULL, &t2);
52894e70 KS	195	update_tree_entry(&t2);
ac1b3d12	196	}
ac1b3d12	197	}
48932677 NTND	198
48932677 NTND	199	strbuf_release(&base);
52894e70 KS	200	free(t2tree);
52894e70 KS	201	free(t1tree);
ac1b3d12 LT	202	return 0;
	203	}
	204
750f7b66 LT	205	/*
	206	* Does it look like the resulting diff might be due to a rename?
	207	* - single entry
	208	* - not a valid previous file
	209	*/
	210	static inline int diff_might_be_rename(void)
	211	{
	212	return diff_queued_diff.nr == 1 &&
	213	!DIFF_FILE_VALID(diff_queued_diff.queue[0]->one);
	214	}
	215
52894e70	216	static void try_to_follow_renames(const unsigned char old, const unsigned char new, const char base, struct diff_options opt)
750f7b66 LT	217	{
750f7b66 LT	218	struct diff_options diff_opts;
9f38e1ef LT	219	struct diff_queue_struct *q = &diff_queued_diff;
9f38e1ef LT	220	struct diff_filepair *choice;
750f7b66 LT	221	int i;
750f7b66 LT	222
8f4f8f45 NTND	223	/*
	224	* follow-rename code is very specific, we need exactly one
	225	* path. Magic that matches more than one path is not
	226	* supported.
	227	*/
5c6933d2	228	GUARD_PATHSPEC(&opt->pathspec, PATHSPEC_FROMTOP \| PATHSPEC_LITERAL);
8f4f8f45 NTND	229	#if 0
	230	/*
	231	* We should reject wildcards as well. Unfortunately we
	232	* haven't got a reliable way to detect that 'foo\*bar' in
	233	* fact has no wildcards. nowildcard_len is merely a hint for
	234	* optimization. Let it slip for now until wildmatch is taught
	235	* about dry-run mode and returns wildcard info.
	236	*/
	237	if (opt->pathspec.has_wildcard)
	238	die("BUG:%s:%d: wildcards are not supported",
	239	__FILE__, __LINE__);
	240	#endif
	241
9f38e1ef LT	242	/* Remove the file creation entry from the diff queue, and remember it */
	243	choice = q->queue[0];
	244	q->nr = 0;
	245
750f7b66	246	diff_setup(&diff_opts);
8f67f8ae	247	DIFF_OPT_SET(&diff_opts, RECURSIVE);
0cdca133	248	DIFF_OPT_SET(&diff_opts, FIND_COPIES_HARDER);
750f7b66	249	diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT;
61588ccf	250	diff_opts.single_follow = opt->pathspec.items[0].match;
6dd4b66f	251	diff_opts.break_opt = opt->break_opt;
dd98d88b	252	diff_opts.rename_score = opt->rename_score;
28452655	253	diff_setup_done(&diff_opts);
52894e70	254	ll_diff_tree_sha1(old, new, base, &diff_opts);
750f7b66	255	diffcore_std(&diff_opts);
bd1928df	256	free_pathspec(&diff_opts.pathspec);
750f7b66	257
9f38e1ef	258	/* Go through the new set of filepairing, and see if we find a more interesting one */
44c48a90	259	opt->found_follow = 0;
9f38e1ef LT	260	for (i = 0; i < q->nr; i++) {
9f38e1ef LT	261	struct diff_filepair *p = q->queue[i];
750f7b66 LT	262
	263	/*
	264	* Found a source? Not only do we use that for the new
9f38e1ef	265	* diff_queued_diff, we will also use that as the path in
750f7b66 LT	266	* the future!
750f7b66 LT	267	*/
66f13625	268	if ((p->status == 'R' \|\| p->status == 'C') &&
61588ccf	269	!strcmp(p->two->path, opt->pathspec.items[0].match)) {
9a087274 NTND	270	const char *path[2];
9a087274 NTND	271
9f38e1ef LT	272	/* Switch the file-pairs around */
	273	q->queue[i] = choice;
	274	choice = p;
	275
	276	/* Update the path we use from now on.. */
9a087274 NTND	277	path[0] = p->one->path;
9a087274 NTND	278	path[1] = NULL;
bd1928df	279	free_pathspec(&opt->pathspec);
4a2d5ae2 NTND	280	parse_pathspec(&opt->pathspec,
	281	PATHSPEC_ALL_MAGIC & ~PATHSPEC_LITERAL,
	282	PATHSPEC_LITERAL_PATH, "", path);
44c48a90 JH	283
	284	/*
	285	* The caller expects us to return a set of vanilla
	286	* filepairs to let a later call to diffcore_std()
	287	* it makes to sort the renames out (among other
	288	* things), but we already have found renames
	289	* ourselves; signal diffcore_std() not to muck with
	290	* rename information.
	291	*/
	292	opt->found_follow = 1;
750f7b66 LT	293	break;
	294	}
	295	}
	296
	297	/*
3ea3c215	298	* Then, discard all the non-relevant file pairs...
9f38e1ef LT	299	*/
	300	for (i = 0; i < q->nr; i++) {
	301	struct diff_filepair *p = q->queue[i];
	302	diff_free_filepair(p);
	303	}
	304
	305	/*
	306	* .. and re-instate the one we want (which might be either the
	307	* original one, or the rename/copy we found)
750f7b66	308	*/
9f38e1ef LT	309	q->queue[0] = choice;
9f38e1ef LT	310	q->nr = 1;
750f7b66 LT	311	}
750f7b66 LT	312
ac1b3d12 LT	313	int diff_tree_sha1(const unsigned char old, const unsigned char new, const char base, struct diff_options opt)
ac1b3d12 LT	314	{
ac1b3d12 LT	315	int retval;
ac1b3d12 LT	316
52894e70 KS	317	retval = ll_diff_tree_sha1(old, new, base, opt);
	318	if (!*base && DIFF_OPT_TST(opt, FOLLOW_RENAMES) && diff_might_be_rename())
	319	try_to_follow_renames(old, new, base, opt);
	320
ac1b3d12 LT	321	return retval;
	322	}
	323
2b60356d RS	324	int diff_root_tree_sha1(const unsigned char new, const char base, struct diff_options *opt)
2b60356d RS	325	{
0b707c33	326	return diff_tree_sha1(NULL, new, base, opt);
2b60356d	327	}