[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().
 */
static int tree_entry_pathcmp(struct tree_desc *t1, struct tree_desc *t2)
{
	struct name_entry *e1, *e2;
	int cmp;

	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);
	}
}

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

	/* 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) {
			if (!t2->size)
				break;
			show_path(&base, opt, /*t1=*/NULL, t2);
			update_tree_entry(t2);
			continue;
		}
		if (!t2->size) {
			show_path(&base, opt, t1, /*t2=*/NULL);
			update_tree_entry(t1);
			continue;
		}

		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);
	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(struct tree_desc *t1, struct tree_desc *t2, 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);
	diff_tree(t1, t2, 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)
{
	void *tree1, *tree2;
	struct tree_desc t1, t2;
	unsigned long size1, size2;
	int retval;

	tree1 = fill_tree_descriptor(&t1, old);
	tree2 = fill_tree_descriptor(&t2, new);
	size1 = t1.size;
	size2 = t2.size;
	retval = diff_tree(&t1, &t2, base, opt);
	if (!*base && DIFF_OPT_TST(opt, FOLLOW_RENAMES) && diff_might_be_rename()) {
		init_tree_desc(&t1, tree1, size1);
		init_tree_desc(&t2, tree2, size2);
		try_to_follow_renames(&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)
{
	return diff_tree_sha1(NULL, new, base, opt);
}
Commit	Line	Data
	1	/*
	2	* Helper functions for tree diff generation
	3	*/
	4	#include "cache.h"
	5	#include "diff.h"
	6	#include "diffcore.h"
	7	#include "tree.h"
	8
	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().
	15	*/
	16	static int tree_entry_pathcmp(struct tree_desc t1, struct tree_desc t2)
	17	{
	18	struct name_entry e1, e2;
	19	int cmp;
	20
	21	e1 = &t1->entry;
	22	e2 = &t2->entry;
	23	cmp = base_name_compare(e1->path, tree_entry_len(e1), e1->mode,
	24	e2->path, tree_entry_len(e2), e2->mode);
	25	return cmp;
	26	}
	27
	28
	29	/* convert path, t1/t2 -> opt->diff_() callbacks /
	30	static void emit_diff(struct diff_options opt, struct strbuf path,
	31	struct tree_desc t1, struct tree_desc t2)
	32	{
	33	unsigned int mode1 = t1 ? t1->entry.mode : 0;
	34	unsigned int mode2 = t2 ? t2->entry.mode : 0;
	35
	36	if (mode1 && mode2) {
	37	opt->change(opt, mode1, mode2, t1->entry.sha1, t2->entry.sha1,
	38	1, 1, path->buf, 0, 0);
	39	}
	40	else {
	41	const unsigned char *sha1;
	42	unsigned int mode;
	43	int addremove;
	44
	45	if (mode2) {
	46	addremove = '+';
	47	sha1 = t2->entry.sha1;
	48	mode = mode2;
	49	} else {
	50	addremove = '-';
	51	sha1 = t1->entry.sha1;
	52	mode = mode1;
	53	}
	54
	55	opt->add_remove(opt, addremove, mode, sha1, 1, path->buf, 0);
	56	}
	57	}
	58
	59
	60	/* new path should be added to diff
	61	*
	62	* 3 cases on how/when it should be called and behaves:
	63	*
	64	* !t1, t2 -> path added, parent lacks it
	65	* t1, !t2 -> path removed from parent
	66	* t1, t2 -> path modified
	67	*/
	68	static void show_path(struct strbuf base, struct diff_options opt,
	69	struct tree_desc t1, struct tree_desc t2)
	70	{
	71	unsigned mode;
	72	const char *path;
	73	int pathlen;
	74	int old_baselen = base->len;
	75	int isdir, recurse = 0, emitthis = 1;
	76
	77	/* at least something has to be valid */
	78	assert(t1 \|\| t2);
	79
	80	if (t2) {
	81	/* path present in resulting tree */
	82	tree_entry_extract(t2, &path, &mode);
	83	pathlen = tree_entry_len(&t2->entry);
	84	isdir = S_ISDIR(mode);
	85	} else {
	86	/*
	87	* a path was removed - take path from parent. Also take
	88	* mode from parent, to decide on recursion.
	89	*/
	90	tree_entry_extract(t1, &path, &mode);
	91	pathlen = tree_entry_len(&t1->entry);
	92
	93	isdir = S_ISDIR(mode);
	94	mode = 0;
	95	}
	96
	97	if (DIFF_OPT_TST(opt, RECURSIVE) && isdir) {
	98	recurse = 1;
	99	emitthis = DIFF_OPT_TST(opt, TREE_IN_RECURSIVE);
	100	}
	101
	102	strbuf_add(base, path, pathlen);
	103
	104	if (emitthis)
	105	emit_diff(opt, base, t1, t2);
	106
	107	if (recurse) {
	108	strbuf_addch(base, '/');
	109	diff_tree_sha1(t1 ? t1->entry.sha1 : NULL,
	110	t2 ? t2->entry.sha1 : NULL, base->buf, opt);
	111	}
	112
	113	strbuf_setlen(base, old_baselen);
	114	}
	115
	116	static void skip_uninteresting(struct tree_desc t, struct strbuf base,
	117	struct diff_options *opt)
	118	{
	119	enum interesting match;
	120
	121	while (t->size) {
	122	match = tree_entry_interesting(&t->entry, base, 0, &opt->pathspec);
	123	if (match) {
	124	if (match == all_entries_not_interesting)
	125	t->size = 0;
	126	break;
	127	}
	128	update_tree_entry(t);
	129	}
	130	}
	131
	132	int diff_tree(struct tree_desc t1, struct tree_desc t2,
	133	const char base_str, struct diff_options opt)
	134	{
	135	struct strbuf base;
	136	int baselen = strlen(base_str);
	137
	138	/* Enable recursion indefinitely */
	139	opt->pathspec.recursive = DIFF_OPT_TST(opt, RECURSIVE);
	140
	141	strbuf_init(&base, PATH_MAX);
	142	strbuf_add(&base, base_str, baselen);
	143
	144	for (;;) {
	145	int cmp;
	146
	147	if (diff_can_quit_early(opt))
	148	break;
	149	if (opt->pathspec.nr) {
	150	skip_uninteresting(t1, &base, opt);
	151	skip_uninteresting(t2, &base, opt);
	152	}
	153	if (!t1->size) {
	154	if (!t2->size)
	155	break;
	156	show_path(&base, opt, /t1=/NULL, t2);
	157	update_tree_entry(t2);
	158	continue;
	159	}
	160	if (!t2->size) {
	161	show_path(&base, opt, t1, /t2=/NULL);
	162	update_tree_entry(t1);
	163	continue;
	164	}
	165
	166	cmp = tree_entry_pathcmp(t1, t2);
	167
	168	/* t1 = t2 */
	169	if (cmp == 0) {
	170	if (DIFF_OPT_TST(opt, FIND_COPIES_HARDER) \|\|
	171	hashcmp(t1->entry.sha1, t2->entry.sha1) \|\|
	172	(t1->entry.mode != t2->entry.mode))
	173	show_path(&base, opt, t1, t2);
	174
	175	update_tree_entry(t1);
	176	update_tree_entry(t2);
	177	}
	178
	179	/* t1 < t2 */
	180	else if (cmp < 0) {
	181	show_path(&base, opt, t1, /t2=/NULL);
	182	update_tree_entry(t1);
	183	}
	184
	185	/* t1 > t2 */
	186	else {
	187	show_path(&base, opt, /t1=/NULL, t2);
	188	update_tree_entry(t2);
	189	}
	190	}
	191
	192	strbuf_release(&base);
	193	return 0;
	194	}
	195
	196	/*
	197	* Does it look like the resulting diff might be due to a rename?
	198	* - single entry
	199	* - not a valid previous file
	200	*/
	201	static inline int diff_might_be_rename(void)
	202	{
	203	return diff_queued_diff.nr == 1 &&
	204	!DIFF_FILE_VALID(diff_queued_diff.queue[0]->one);
	205	}
	206
	207	static void try_to_follow_renames(struct tree_desc t1, struct tree_desc t2, const char base, struct diff_options opt)
	208	{
	209	struct diff_options diff_opts;
	210	struct diff_queue_struct *q = &diff_queued_diff;
	211	struct diff_filepair *choice;
	212	int i;
	213
	214	/*
	215	* follow-rename code is very specific, we need exactly one
	216	* path. Magic that matches more than one path is not
	217	* supported.
	218	*/
	219	GUARD_PATHSPEC(&opt->pathspec, PATHSPEC_FROMTOP \| PATHSPEC_LITERAL);
	220	#if 0
	221	/*
	222	* We should reject wildcards as well. Unfortunately we
	223	* haven't got a reliable way to detect that 'foo\*bar' in
	224	* fact has no wildcards. nowildcard_len is merely a hint for
	225	* optimization. Let it slip for now until wildmatch is taught
	226	* about dry-run mode and returns wildcard info.
	227	*/
	228	if (opt->pathspec.has_wildcard)
	229	die("BUG:%s:%d: wildcards are not supported",
	230	__FILE__, __LINE__);
	231	#endif
	232
	233	/* Remove the file creation entry from the diff queue, and remember it */
	234	choice = q->queue[0];
	235	q->nr = 0;
	236
	237	diff_setup(&diff_opts);
	238	DIFF_OPT_SET(&diff_opts, RECURSIVE);
	239	DIFF_OPT_SET(&diff_opts, FIND_COPIES_HARDER);
	240	diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT;
	241	diff_opts.single_follow = opt->pathspec.items[0].match;
	242	diff_opts.break_opt = opt->break_opt;
	243	diff_opts.rename_score = opt->rename_score;
	244	diff_setup_done(&diff_opts);
	245	diff_tree(t1, t2, base, &diff_opts);
	246	diffcore_std(&diff_opts);
	247	free_pathspec(&diff_opts.pathspec);
	248
	249	/* Go through the new set of filepairing, and see if we find a more interesting one */
	250	opt->found_follow = 0;
	251	for (i = 0; i < q->nr; i++) {
	252	struct diff_filepair *p = q->queue[i];
	253
	254	/*
	255	* Found a source? Not only do we use that for the new
	256	* diff_queued_diff, we will also use that as the path in
	257	* the future!
	258	*/
	259	if ((p->status == 'R' \|\| p->status == 'C') &&
	260	!strcmp(p->two->path, opt->pathspec.items[0].match)) {
	261	const char *path[2];
	262
	263	/* Switch the file-pairs around */
	264	q->queue[i] = choice;
	265	choice = p;
	266
	267	/* Update the path we use from now on.. */
	268	path[0] = p->one->path;
	269	path[1] = NULL;
	270	free_pathspec(&opt->pathspec);
	271	parse_pathspec(&opt->pathspec,
	272	PATHSPEC_ALL_MAGIC & ~PATHSPEC_LITERAL,
	273	PATHSPEC_LITERAL_PATH, "", path);
	274
	275	/*
	276	* The caller expects us to return a set of vanilla
	277	* filepairs to let a later call to diffcore_std()
	278	* it makes to sort the renames out (among other
	279	* things), but we already have found renames
	280	* ourselves; signal diffcore_std() not to muck with
	281	* rename information.
	282	*/
	283	opt->found_follow = 1;
	284	break;
	285	}
	286	}
	287
	288	/*
	289	* Then, discard all the non-relevant file pairs...
	290	*/
	291	for (i = 0; i < q->nr; i++) {
	292	struct diff_filepair *p = q->queue[i];
	293	diff_free_filepair(p);
	294	}
	295
	296	/*
	297	* .. and re-instate the one we want (which might be either the
	298	* original one, or the rename/copy we found)
	299	*/
	300	q->queue[0] = choice;
	301	q->nr = 1;
	302	}
	303
	304	int diff_tree_sha1(const unsigned char old, const unsigned char new, const char base, struct diff_options opt)
	305	{
	306	void tree1, tree2;
	307	struct tree_desc t1, t2;
	308	unsigned long size1, size2;
	309	int retval;
	310
	311	tree1 = fill_tree_descriptor(&t1, old);
	312	tree2 = fill_tree_descriptor(&t2, new);
	313	size1 = t1.size;
	314	size2 = t2.size;
	315	retval = diff_tree(&t1, &t2, base, opt);
	316	if (!*base && DIFF_OPT_TST(opt, FOLLOW_RENAMES) && diff_might_be_rename()) {
	317	init_tree_desc(&t1, tree1, size1);
	318	init_tree_desc(&t2, tree2, size2);
	319	try_to_follow_renames(&t1, &t2, base, opt);
	320	}
	321	free(tree1);
	322	free(tree2);
	323	return retval;
	324	}
	325
	326	int diff_root_tree_sha1(const unsigned char new, const char base, struct diff_options *opt)
	327	{
	328	return diff_tree_sha1(NULL, new, base, opt);
	329	}