[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, max_size;
	unsigned long 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)) {
		*merge_score_p = (int)MAX_SCORE;
		return 1; /* even their types are different */
	}

	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 */

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

	if (diffcore_count_changes(src, dst,
				   &src->cnt_data, &dst->cnt_data,
				   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);
	if (*merge_score_p > break_score)
		return 1;

	/* Extent of damage, which counts both inserts and
	 * deletes.
	 */
	delta_size = src_removed + literal_added;
	if (delta_size * MAX_SCORE / max_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;

	DIFF_QUEUE_CLEAR(&outq);

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

		/*
		 * We deal only with in-place edit of blobs.
		 * We do not break anything else.
		 */
		if (DIFF_FILE_VALID(p->one) && DIFF_FILE_VALID(p->two) &&
		    object_type(p->one->mode) == OBJ_BLOB &&
		    object_type(p->two->mode) == OBJ_BLOB &&
		    !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;

				diff_free_filespec_blob(p->one);
				diff_free_filespec_blob(p->two);
				free(p); /* not diff_free_filepair(), we are
					  * reusing one and two here.
					  */
				continue;
			}
		}
		diff_free_filespec_data(p->one);
		diff_free_filespec_data(p->two);
		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;

	DIFF_QUEUE_CLEAR(&outq);

	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	*/
eb3a9dd3	48	unsigned long delta_size, max_size;
6dd4b66f	49	unsigned long src_copied, literal_added, src_removed;
eeaa4603 JH	50
	51	merge_score_p = 0; / assume no deletion --- "do not break"
	52	* is the default.
	53	*/
f345b0a0	54
b45563a2 JH	55	if (S_ISREG(src->mode) != S_ISREG(dst->mode)) {
	56	*merge_score_p = (int)MAX_SCORE;
	57	return 1; /* even their types are different */
	58	}
f345b0a0	59
aeecd23a	60	if (src->sha1_valid && dst->sha1_valid &&
a89fccd2	61	!hashcmp(src->sha1, dst->sha1))
aeecd23a JH	62	return 0; /* they are the same */
aeecd23a JH	63
eeaa4603	64	if (diff_populate_filespec(src, 0) \|\| diff_populate_filespec(dst, 0))
f345b0a0 JH	65	return 0; /* error but caught downstream */
f345b0a0 JH	66
6dd4b66f LT	67	max_size = ((src->size > dst->size) ? src->size : dst->size);
6dd4b66f LT	68	if (max_size < MINIMUM_BREAK_SIZE)
0532a5e4	69	return 0; /* we do not break too small filepair */
f345b0a0	70
d8c3d03a	71	if (diffcore_count_changes(src, dst,
8282de94	72	&src->cnt_data, &dst->cnt_data,
65416758 JH	73	0,
	74	&src_copied, &literal_added))
	75	return 0;
355e76a4	76
4d0f39ce JH	77	/* sanity */
	78	if (src->size < src_copied)
	79	src_copied = src->size;
	80	if (dst->size < literal_added + src_copied) {
	81	if (src_copied < dst->size)
	82	literal_added = dst->size - src_copied;
	83	else
	84	literal_added = 0;
	85	}
	86	src_removed = src->size - src_copied;
	87
eeaa4603 JH	88	/* Compute merge-score, which is "how much is removed
	89	* from the source material". The clean-up stage will
	90	* merge the surviving pair together if the score is
	91	* less than the minimum, after rename/copy runs.
	92	*/
dc49cd76	93	merge_score_p = (int)(src_removed MAX_SCORE / src->size);
6dd4b66f LT	94	if (*merge_score_p > break_score)
6dd4b66f LT	95	return 1;
4d0f39ce	96
eeaa4603 JH	97	/* Extent of damage, which counts both inserts and
	98	* deletes.
	99	*/
4d0f39ce	100	delta_size = src_removed + literal_added;
6dd4b66f	101	if (delta_size * MAX_SCORE / max_size < break_score)
4d0f39ce JH	102	return 0;
	103
	104	/* If you removed a lot without adding new material, that is
	105	* not really a rewrite.
eeaa4603	106	*/
4d0f39ce JH	107	if ((src->size * break_score < src_removed * MAX_SCORE) &&
	108	(literal_added * 20 < src_removed) &&
	109	(literal_added * 20 < src_copied))
	110	return 0;
f345b0a0	111
4d0f39ce	112	return 1;
f345b0a0 JH	113	}
f345b0a0 JH	114
eeaa4603	115	void diffcore_break(int break_score)
f345b0a0 JH	116	{
	117	struct diff_queue_struct *q = &diff_queued_diff;
	118	struct diff_queue_struct outq;
eeaa4603 JH	119
	120	/* When the filepair has this much edit (insert and delete),
	121	* it is first considered to be a rewrite and broken into a
	122	* create and delete filepair. This is to help breaking a
	123	* file that had too much new stuff added, possibly from
	124	* moving contents from another file, so that rename/copy can
	125	* match it with the other file.
	126	*
	127	* int break_score; we reuse incoming parameter for this.
	128	*/
	129
	130	/* After a pair is broken according to break_score and
	131	* subjected to rename/copy, both of them may survive intact,
	132	* due to lack of suitable rename/copy peer. Or, the caller
	133	* may be calling us without using rename/copy. When that
	134	* happens, we merge the broken pieces back into one
	135	* modification together if the pair did not have more than
	136	* this much delete. For this computation, we do not take
	137	* insert into account at all. If you start from a 100-line
	138	* file and delete 97 lines of it, it does not matter if you
	139	* add 27 lines to it to make a new 30-line file or if you add
	140	* 997 lines to it to make a 1000-line file. Either way what
	141	* you did was a rewrite of 97%. On the other hand, if you
	142	* delete 3 lines, keeping 97 lines intact, it does not matter
	143	* if you add 3 lines to it to make a new 100-line file or if
	144	* you add 903 lines to it to make a new 1000-line file.
	145	* Either way you did a lot of additions and not a rewrite.
	146	* This merge happens to catch the latter case. A merge_score
	147	* of 80% would be a good default value (a broken pair that
	148	* has score lower than merge_score will be merged back
	149	* together).
	150	*/
	151	int merge_score;
f345b0a0 JH	152	int i;
f345b0a0 JH	153
eeaa4603 JH	154	/* See comment on DEFAULT_BREAK_SCORE and
	155	* DEFAULT_MERGE_SCORE in diffcore.h
	156	*/
	157	merge_score = (break_score >> 16) & 0xFFFF;
	158	break_score = (break_score & 0xFFFF);
	159
	160	if (!break_score)
	161	break_score = DEFAULT_BREAK_SCORE;
	162	if (!merge_score)
	163	merge_score = DEFAULT_MERGE_SCORE;
f345b0a0	164
9ca5df90	165	DIFF_QUEUE_CLEAR(&outq);
f345b0a0 JH	166
	167	for (i = 0; i < q->nr; i++) {
	168	struct diff_filepair *p = q->queue[i];
	169	int score;
	170
b45563a2 JH	171	/*
b45563a2 JH	172	* We deal only with in-place edit of blobs.
f345b0a0 JH	173	* We do not break anything else.
	174	*/
	175	if (DIFF_FILE_VALID(p->one) && DIFF_FILE_VALID(p->two) &&
b45563a2 JH	176	object_type(p->one->mode) == OBJ_BLOB &&
b45563a2 JH	177	object_type(p->two->mode) == OBJ_BLOB &&
f345b0a0	178	!strcmp(p->one->path, p->two->path)) {
eeaa4603	179	if (should_break(p->one, p->two,
0532a5e4	180	break_score, &score)) {
f345b0a0 JH	181	/* Split this into delete and create */
	182	struct diff_filespec null_one, null_two;
	183	struct diff_filepair *dp;
	184
eeaa4603 JH	185	/* Set score to 0 for the pair that
	186	* needs to be merged back together
	187	* should they survive rename/copy.
	188	* Also we do not want to break very
	189	* small files.
	190	*/
f78c79c5	191	if (score < merge_score)
eeaa4603 JH	192	score = 0;
eeaa4603 JH	193
f345b0a0 JH	194	/* deletion of one */
	195	null_one = alloc_filespec(p->one->path);
	196	dp = diff_queue(&outq, p->one, null_one);
	197	dp->score = score;
	198	dp->broken_pair = 1;
	199
	200	/* creation of two */
	201	null_two = alloc_filespec(p->two->path);
	202	dp = diff_queue(&outq, null_two, p->two);
	203	dp->score = score;
	204	dp->broken_pair = 1;
	205
8282de94 JK	206	diff_free_filespec_blob(p->one);
8282de94 JK	207	diff_free_filespec_blob(p->two);
f345b0a0 JH	208	free(p); /* not diff_free_filepair(), we are
	209	* reusing one and two here.
	210	*/
	211	continue;
	212	}
	213	}
f4f19fb6 JK	214	diff_free_filespec_data(p->one);
f4f19fb6 JK	215	diff_free_filespec_data(p->two);
f345b0a0 JH	216	diff_q(&outq, p);
	217	}
	218	free(q->queue);
	219	*q = outq;
	220
	221	return;
	222	}
eeaa4603 JH	223
	224	static void merge_broken(struct diff_filepair *p,
	225	struct diff_filepair *pp,
	226	struct diff_queue_struct *outq)
	227	{
	228	/* p and pp are broken pairs we want to merge */
366175ef	229	struct diff_filepair c = p, d = pp, *dp;
eeaa4603 JH	230	if (DIFF_FILE_VALID(p->one)) {
	231	/* this must be a delete half */
	232	d = p; c = pp;
	233	}
	234	/* Sanity check */
	235	if (!DIFF_FILE_VALID(d->one))
	236	die("internal error in merge #1");
	237	if (DIFF_FILE_VALID(d->two))
	238	die("internal error in merge #2");
	239	if (DIFF_FILE_VALID(c->one))
	240	die("internal error in merge #3");
	241	if (!DIFF_FILE_VALID(c->two))
	242	die("internal error in merge #4");
	243
366175ef JH	244	dp = diff_queue(outq, d->one, c->two);
366175ef JH	245	dp->score = p->score;
19397b45 JH	246	diff_free_filespec_data(d->two);
19397b45 JH	247	diff_free_filespec_data(c->one);
eeaa4603 JH	248	free(d);
	249	free(c);
	250	}
	251
	252	void diffcore_merge_broken(void)
	253	{
	254	struct diff_queue_struct *q = &diff_queued_diff;
	255	struct diff_queue_struct outq;
	256	int i, j;
	257
9ca5df90	258	DIFF_QUEUE_CLEAR(&outq);
eeaa4603 JH	259
	260	for (i = 0; i < q->nr; i++) {
	261	struct diff_filepair *p = q->queue[i];
	262	if (!p)
	263	/* we already merged this with its peer */
	264	continue;
	265	else if (p->broken_pair &&
eeaa4603 JH	266	!strcmp(p->one->path, p->two->path)) {
	267	/* If the peer also survived rename/copy, then
	268	* we merge them back together.
	269	*/
	270	for (j = i + 1; j < q->nr; j++) {
	271	struct diff_filepair *pp = q->queue[j];
	272	if (pp->broken_pair &&
eeaa4603 JH	273	!strcmp(pp->one->path, pp->two->path) &&
	274	!strcmp(p->one->path, pp->two->path)) {
	275	/* Peer survived. Merge them */
	276	merge_broken(p, pp, &outq);
	277	q->queue[j] = NULL;
	278	break;
	279	}
	280	}
	281	if (q->nr <= j)
	282	/* The peer did not survive, so we keep
	283	* it in the output.
	284	*/
	285	diff_q(&outq, p);
	286	}
	287	else
	288	diff_q(&outq, p);
	289	}
	290	free(q->queue);
	291	*q = outq;
	292
	293	return;
	294	}