[thirdparty/git.git] / diffcore-break.c

/*
 * Copyright (C) 2005 Junio C Hamano
 */
#include "cache.h"
#include "diff.h"
#include "diffcore.h"

static int should_break(struct diff_filespec *src,
			struct diff_filespec *dst,
			int break_score,
			int *merge_score_p)
{
	/* dst is recorded as a modification of src.  Are they so
	 * different that we are better off recording this as a pair
	 * of delete and create?
	 *
	 * There are two criteria used in this algorithm.  For the
	 * purposes of helping later rename/copy, we take both delete
	 * and insert into account and estimate the amount of "edit".
	 * If the edit is very large, we break this pair so that
	 * rename/copy can pick the pieces up to match with other
	 * files.
	 *
	 * On the other hand, we would want to ignore inserts for the
	 * pure "complete rewrite" detection.  As long as most of the
	 * existing contents were removed from the file, it is a
	 * complete rewrite, and if sizable chunk from the original
	 * still remains in the result, it is not a rewrite.  It does
	 * not matter how much or how little new material is added to
	 * the file.
	 *
	 * The score we leave for such a broken filepair uses the
	 * latter definition so that later clean-up stage can find the
	 * pieces that should not have been broken according to the
	 * latter definition after rename/copy runs, and merge the
	 * broken pair that have a score lower than given criteria
	 * back together.  The break operation itself happens
	 * according to the former definition.
	 *
	 * The minimum_edit parameter tells us when to break (the
	 * amount of "edit" required for us to consider breaking the
	 * pair).  We leave the amount of deletion in *merge_score_p
	 * when we return.
	 *
	 * The value we return is 1 if we want the pair to be broken,
	 * or 0 if we do not.
	 */
	unsigned long delta_size, base_size, src_copied, literal_added,
		src_removed;

	*merge_score_p = 0; /* assume no deletion --- "do not break"
			     * is the default.
			     */

	if (!S_ISREG(src->mode) || !S_ISREG(dst->mode))
		return 0; /* leave symlink rename alone */

	if (src->sha1_valid && dst->sha1_valid &&
	    !hashcmp(src->sha1, dst->sha1))
		return 0; /* they are the same */

	if (diff_populate_filespec(src, 0) || diff_populate_filespec(dst, 0))
		return 0; /* error but caught downstream */

	base_size = ((src->size < dst->size) ? src->size : dst->size);
	if (base_size < MINIMUM_BREAK_SIZE)
		return 0; /* we do not break too small filepair */

	if (diffcore_count_changes(src, dst,
				   NULL, NULL,
				   0,
				   &src_copied, &literal_added))
		return 0;

	/* sanity */
	if (src->size < src_copied)
		src_copied = src->size;
	if (dst->size < literal_added + src_copied) {
		if (src_copied < dst->size)
			literal_added = dst->size - src_copied;
		else
			literal_added = 0;
	}
	src_removed = src->size - src_copied;

	/* Compute merge-score, which is "how much is removed
	 * from the source material".  The clean-up stage will
	 * merge the surviving pair together if the score is
	 * less than the minimum, after rename/copy runs.
	 */
	*merge_score_p = (int)(src_removed * MAX_SCORE / src->size);

	/* Extent of damage, which counts both inserts and
	 * deletes.
	 */
	delta_size = src_removed + literal_added;
	if (delta_size * MAX_SCORE / base_size < break_score)
		return 0;

	/* If you removed a lot without adding new material, that is
	 * not really a rewrite.
	 */
	if ((src->size * break_score < src_removed * MAX_SCORE) &&
	    (literal_added * 20 < src_removed) &&
	    (literal_added * 20 < src_copied))
		return 0;

	return 1;
}

void diffcore_break(int break_score)
{
	struct diff_queue_struct *q = &diff_queued_diff;
	struct diff_queue_struct outq;

	/* When the filepair has this much edit (insert and delete),
	 * it is first considered to be a rewrite and broken into a
	 * create and delete filepair.  This is to help breaking a
	 * file that had too much new stuff added, possibly from
	 * moving contents from another file, so that rename/copy can
	 * match it with the other file.
	 *
	 * int break_score; we reuse incoming parameter for this.
	 */

	/* After a pair is broken according to break_score and
	 * subjected to rename/copy, both of them may survive intact,
	 * due to lack of suitable rename/copy peer.  Or, the caller
	 * may be calling us without using rename/copy.  When that
	 * happens, we merge the broken pieces back into one
	 * modification together if the pair did not have more than
	 * this much delete.  For this computation, we do not take
	 * insert into account at all.  If you start from a 100-line
	 * file and delete 97 lines of it, it does not matter if you
	 * add 27 lines to it to make a new 30-line file or if you add
	 * 997 lines to it to make a 1000-line file.  Either way what
	 * you did was a rewrite of 97%.  On the other hand, if you
	 * delete 3 lines, keeping 97 lines intact, it does not matter
	 * if you add 3 lines to it to make a new 100-line file or if
	 * you add 903 lines to it to make a new 1000-line file.
	 * Either way you did a lot of additions and not a rewrite.
	 * This merge happens to catch the latter case.  A merge_score
	 * of 80% would be a good default value (a broken pair that
	 * has score lower than merge_score will be merged back
	 * together).
	 */
	int merge_score;
	int i;

	/* See comment on DEFAULT_BREAK_SCORE and
	 * DEFAULT_MERGE_SCORE in diffcore.h
	 */
	merge_score = (break_score >> 16) & 0xFFFF;
	break_score = (break_score & 0xFFFF);

	if (!break_score)
		break_score = DEFAULT_BREAK_SCORE;
	if (!merge_score)
		merge_score = DEFAULT_MERGE_SCORE;

	outq.nr = outq.alloc = 0;
	outq.queue = NULL;

	for (i = 0; i < q->nr; i++) {
		struct diff_filepair *p = q->queue[i];
		int score;

		/* We deal only with in-place edit of non directory.
		 * We do not break anything else.
		 */
		if (DIFF_FILE_VALID(p->one) && DIFF_FILE_VALID(p->two) &&
		    !S_ISDIR(p->one->mode) && !S_ISDIR(p->two->mode) &&
		    !strcmp(p->one->path, p->two->path)) {
			if (should_break(p->one, p->two,
					 break_score, &score)) {
				/* Split this into delete and create */
				struct diff_filespec *null_one, *null_two;
				struct diff_filepair *dp;

				/* Set score to 0 for the pair that
				 * needs to be merged back together
				 * should they survive rename/copy.
				 * Also we do not want to break very
				 * small files.
				 */
				if (score < merge_score)
					score = 0;

				/* deletion of one */
				null_one = alloc_filespec(p->one->path);
				dp = diff_queue(&outq, p->one, null_one);
				dp->score = score;
				dp->broken_pair = 1;

				/* creation of two */
				null_two = alloc_filespec(p->two->path);
				dp = diff_queue(&outq, null_two, p->two);
				dp->score = score;
				dp->broken_pair = 1;

				free(p); /* not diff_free_filepair(), we are
					  * reusing one and two here.
					  */
				continue;
			}
		}
		diff_q(&outq, p);
	}
	free(q->queue);
	*q = outq;

	return;
}

static void merge_broken(struct diff_filepair *p,
			 struct diff_filepair *pp,
			 struct diff_queue_struct *outq)
{
	/* p and pp are broken pairs we want to merge */
	struct diff_filepair *c = p, *d = pp, *dp;
	if (DIFF_FILE_VALID(p->one)) {
		/* this must be a delete half */
		d = p; c = pp;
	}
	/* Sanity check */
	if (!DIFF_FILE_VALID(d->one))
		die("internal error in merge #1");
	if (DIFF_FILE_VALID(d->two))
		die("internal error in merge #2");
	if (DIFF_FILE_VALID(c->one))
		die("internal error in merge #3");
	if (!DIFF_FILE_VALID(c->two))
		die("internal error in merge #4");

	dp = diff_queue(outq, d->one, c->two);
	dp->score = p->score;
	diff_free_filespec_data(d->two);
	diff_free_filespec_data(c->one);
	free(d);
	free(c);
}

void diffcore_merge_broken(void)
{
	struct diff_queue_struct *q = &diff_queued_diff;
	struct diff_queue_struct outq;
	int i, j;

	outq.nr = outq.alloc = 0;
	outq.queue = NULL;

	for (i = 0; i < q->nr; i++) {
		struct diff_filepair *p = q->queue[i];
		if (!p)
			/* we already merged this with its peer */
			continue;
		else if (p->broken_pair &&
			 !strcmp(p->one->path, p->two->path)) {
			/* If the peer also survived rename/copy, then
			 * we merge them back together.
			 */
			for (j = i + 1; j < q->nr; j++) {
				struct diff_filepair *pp = q->queue[j];
				if (pp->broken_pair &&
				    !strcmp(pp->one->path, pp->two->path) &&
				    !strcmp(p->one->path, pp->two->path)) {
					/* Peer survived.  Merge them */
					merge_broken(p, pp, &outq);
					q->queue[j] = NULL;
					break;
				}
			}
			if (q->nr <= j)
				/* The peer did not survive, so we keep
				 * it in the output.
				 */
				diff_q(&outq, p);
		}
		else
			diff_q(&outq, p);
	}
	free(q->queue);
	*q = outq;

	return;
}
Commit	Line	Data
f345b0a0 JH	1	/*
	2	* Copyright (C) 2005 Junio C Hamano
	3	*/
	4	#include "cache.h"
	5	#include "diff.h"
	6	#include "diffcore.h"
f345b0a0	7
eeaa4603 JH	8	static int should_break(struct diff_filespec *src,
	9	struct diff_filespec *dst,
	10	int break_score,
	11	int *merge_score_p)
f345b0a0 JH	12	{
	13	/* dst is recorded as a modification of src. Are they so
	14	* different that we are better off recording this as a pair
eeaa4603	15	* of delete and create?
f345b0a0	16	*
eeaa4603 JH	17	* There are two criteria used in this algorithm. For the
	18	* purposes of helping later rename/copy, we take both delete
	19	* and insert into account and estimate the amount of "edit".
	20	* If the edit is very large, we break this pair so that
	21	* rename/copy can pick the pieces up to match with other
	22	* files.
	23	*
	24	* On the other hand, we would want to ignore inserts for the
	25	* pure "complete rewrite" detection. As long as most of the
	26	* existing contents were removed from the file, it is a
	27	* complete rewrite, and if sizable chunk from the original
	28	* still remains in the result, it is not a rewrite. It does
	29	* not matter how much or how little new material is added to
	30	* the file.
	31	*
	32	* The score we leave for such a broken filepair uses the
	33	* latter definition so that later clean-up stage can find the
	34	* pieces that should not have been broken according to the
	35	* latter definition after rename/copy runs, and merge the
	36	* broken pair that have a score lower than given criteria
	37	* back together. The break operation itself happens
	38	* according to the former definition.
	39	*
	40	* The minimum_edit parameter tells us when to break (the
	41	* amount of "edit" required for us to consider breaking the
	42	* pair). We leave the amount of deletion in *merge_score_p
	43	* when we return.
	44	*
	45	* The value we return is 1 if we want the pair to be broken,
	46	* or 0 if we do not.
f345b0a0	47	*/
4d0f39ce JH	48	unsigned long delta_size, base_size, src_copied, literal_added,
4d0f39ce JH	49	src_removed;
eeaa4603 JH	50
	51	merge_score_p = 0; / assume no deletion --- "do not break"
	52	* is the default.
	53	*/
f345b0a0 JH	54
	55	if (!S_ISREG(src->mode) \|\| !S_ISREG(dst->mode))
	56	return 0; /* leave symlink rename alone */
	57
aeecd23a	58	if (src->sha1_valid && dst->sha1_valid &&
a89fccd2	59	!hashcmp(src->sha1, dst->sha1))
aeecd23a JH	60	return 0; /* they are the same */
aeecd23a JH	61
eeaa4603	62	if (diff_populate_filespec(src, 0) \|\| diff_populate_filespec(dst, 0))
f345b0a0 JH	63	return 0; /* error but caught downstream */
f345b0a0 JH	64
f78c79c5	65	base_size = ((src->size < dst->size) ? src->size : dst->size);
0532a5e4 JH	66	if (base_size < MINIMUM_BREAK_SIZE)
0532a5e4 JH	67	return 0; /* we do not break too small filepair */
f345b0a0	68
d8c3d03a	69	if (diffcore_count_changes(src, dst,
c06c7966	70	NULL, NULL,
65416758 JH	71	0,
	72	&src_copied, &literal_added))
	73	return 0;
355e76a4	74
4d0f39ce JH	75	/* sanity */
	76	if (src->size < src_copied)
	77	src_copied = src->size;
	78	if (dst->size < literal_added + src_copied) {
	79	if (src_copied < dst->size)
	80	literal_added = dst->size - src_copied;
	81	else
	82	literal_added = 0;
	83	}
	84	src_removed = src->size - src_copied;
	85
eeaa4603 JH	86	/* Compute merge-score, which is "how much is removed
	87	* from the source material". The clean-up stage will
	88	* merge the surviving pair together if the score is
	89	* less than the minimum, after rename/copy runs.
	90	*/
dc49cd76	91	merge_score_p = (int)(src_removed MAX_SCORE / src->size);
4d0f39ce	92
eeaa4603 JH	93	/* Extent of damage, which counts both inserts and
	94	* deletes.
	95	*/
4d0f39ce JH	96	delta_size = src_removed + literal_added;
	97	if (delta_size * MAX_SCORE / base_size < break_score)
	98	return 0;
	99
	100	/* If you removed a lot without adding new material, that is
	101	* not really a rewrite.
eeaa4603	102	*/
4d0f39ce JH	103	if ((src->size * break_score < src_removed * MAX_SCORE) &&
	104	(literal_added * 20 < src_removed) &&
	105	(literal_added * 20 < src_copied))
	106	return 0;
f345b0a0	107
4d0f39ce	108	return 1;
f345b0a0 JH	109	}
f345b0a0 JH	110
eeaa4603	111	void diffcore_break(int break_score)
f345b0a0 JH	112	{
	113	struct diff_queue_struct *q = &diff_queued_diff;
	114	struct diff_queue_struct outq;
eeaa4603 JH	115
	116	/* When the filepair has this much edit (insert and delete),
	117	* it is first considered to be a rewrite and broken into a
	118	* create and delete filepair. This is to help breaking a
	119	* file that had too much new stuff added, possibly from
	120	* moving contents from another file, so that rename/copy can
	121	* match it with the other file.
	122	*
	123	* int break_score; we reuse incoming parameter for this.
	124	*/
	125
	126	/* After a pair is broken according to break_score and
	127	* subjected to rename/copy, both of them may survive intact,
	128	* due to lack of suitable rename/copy peer. Or, the caller
	129	* may be calling us without using rename/copy. When that
	130	* happens, we merge the broken pieces back into one
	131	* modification together if the pair did not have more than
	132	* this much delete. For this computation, we do not take
	133	* insert into account at all. If you start from a 100-line
	134	* file and delete 97 lines of it, it does not matter if you
	135	* add 27 lines to it to make a new 30-line file or if you add
	136	* 997 lines to it to make a 1000-line file. Either way what
	137	* you did was a rewrite of 97%. On the other hand, if you
	138	* delete 3 lines, keeping 97 lines intact, it does not matter
	139	* if you add 3 lines to it to make a new 100-line file or if
	140	* you add 903 lines to it to make a new 1000-line file.
	141	* Either way you did a lot of additions and not a rewrite.
	142	* This merge happens to catch the latter case. A merge_score
	143	* of 80% would be a good default value (a broken pair that
	144	* has score lower than merge_score will be merged back
	145	* together).
	146	*/
	147	int merge_score;
f345b0a0 JH	148	int i;
f345b0a0 JH	149
eeaa4603 JH	150	/* See comment on DEFAULT_BREAK_SCORE and
	151	* DEFAULT_MERGE_SCORE in diffcore.h
	152	*/
	153	merge_score = (break_score >> 16) & 0xFFFF;
	154	break_score = (break_score & 0xFFFF);
	155
	156	if (!break_score)
	157	break_score = DEFAULT_BREAK_SCORE;
	158	if (!merge_score)
	159	merge_score = DEFAULT_MERGE_SCORE;
f345b0a0 JH	160
	161	outq.nr = outq.alloc = 0;
	162	outq.queue = NULL;
	163
	164	for (i = 0; i < q->nr; i++) {
	165	struct diff_filepair *p = q->queue[i];
	166	int score;
	167
	168	/* We deal only with in-place edit of non directory.
	169	* We do not break anything else.
	170	*/
	171	if (DIFF_FILE_VALID(p->one) && DIFF_FILE_VALID(p->two) &&
	172	!S_ISDIR(p->one->mode) && !S_ISDIR(p->two->mode) &&
	173	!strcmp(p->one->path, p->two->path)) {
eeaa4603	174	if (should_break(p->one, p->two,
0532a5e4	175	break_score, &score)) {
f345b0a0 JH	176	/* Split this into delete and create */
	177	struct diff_filespec null_one, null_two;
	178	struct diff_filepair *dp;
	179
eeaa4603 JH	180	/* Set score to 0 for the pair that
	181	* needs to be merged back together
	182	* should they survive rename/copy.
	183	* Also we do not want to break very
	184	* small files.
	185	*/
f78c79c5	186	if (score < merge_score)
eeaa4603 JH	187	score = 0;
eeaa4603 JH	188
f345b0a0 JH	189	/* deletion of one */
	190	null_one = alloc_filespec(p->one->path);
	191	dp = diff_queue(&outq, p->one, null_one);
	192	dp->score = score;
	193	dp->broken_pair = 1;
	194
	195	/* creation of two */
	196	null_two = alloc_filespec(p->two->path);
	197	dp = diff_queue(&outq, null_two, p->two);
	198	dp->score = score;
	199	dp->broken_pair = 1;
	200
	201	free(p); /* not diff_free_filepair(), we are
	202	* reusing one and two here.
	203	*/
	204	continue;
	205	}
	206	}
	207	diff_q(&outq, p);
	208	}
	209	free(q->queue);
	210	*q = outq;
	211
	212	return;
	213	}
eeaa4603 JH	214
	215	static void merge_broken(struct diff_filepair *p,
	216	struct diff_filepair *pp,
	217	struct diff_queue_struct *outq)
	218	{
	219	/* p and pp are broken pairs we want to merge */
366175ef	220	struct diff_filepair c = p, d = pp, *dp;
eeaa4603 JH	221	if (DIFF_FILE_VALID(p->one)) {
	222	/* this must be a delete half */
	223	d = p; c = pp;
	224	}
	225	/* Sanity check */
	226	if (!DIFF_FILE_VALID(d->one))
	227	die("internal error in merge #1");
	228	if (DIFF_FILE_VALID(d->two))
	229	die("internal error in merge #2");
	230	if (DIFF_FILE_VALID(c->one))
	231	die("internal error in merge #3");
	232	if (!DIFF_FILE_VALID(c->two))
	233	die("internal error in merge #4");
	234
366175ef JH	235	dp = diff_queue(outq, d->one, c->two);
366175ef JH	236	dp->score = p->score;
19397b45 JH	237	diff_free_filespec_data(d->two);
19397b45 JH	238	diff_free_filespec_data(c->one);
eeaa4603 JH	239	free(d);
	240	free(c);
	241	}
	242
	243	void diffcore_merge_broken(void)
	244	{
	245	struct diff_queue_struct *q = &diff_queued_diff;
	246	struct diff_queue_struct outq;
	247	int i, j;
	248
	249	outq.nr = outq.alloc = 0;
	250	outq.queue = NULL;
	251
	252	for (i = 0; i < q->nr; i++) {
	253	struct diff_filepair *p = q->queue[i];
	254	if (!p)
	255	/* we already merged this with its peer */
	256	continue;
	257	else if (p->broken_pair &&
eeaa4603 JH	258	!strcmp(p->one->path, p->two->path)) {
	259	/* If the peer also survived rename/copy, then
	260	* we merge them back together.
	261	*/
	262	for (j = i + 1; j < q->nr; j++) {
	263	struct diff_filepair *pp = q->queue[j];
	264	if (pp->broken_pair &&
eeaa4603 JH	265	!strcmp(pp->one->path, pp->two->path) &&
	266	!strcmp(p->one->path, pp->two->path)) {
	267	/* Peer survived. Merge them */
	268	merge_broken(p, pp, &outq);
	269	q->queue[j] = NULL;
	270	break;
	271	}
	272	}
	273	if (q->nr <= j)
	274	/* The peer did not survive, so we keep
	275	* it in the output.
	276	*/
	277	diff_q(&outq, p);
	278	}
	279	else
	280	diff_q(&outq, p);
	281	}
	282	free(q->queue);
	283	*q = outq;
	284
	285	return;
	286	}