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

/*
 * Copyright (C) 2005 Junio C Hamano
 */
#include "cache.h"
#include "diff.h"
#include "diffcore.h"
#include "delta.h"
#include "count-delta.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.
	 */
	void *delta;
	unsigned long delta_size, base_size, src_copied, literal_added;
	int to_break = 0;

	*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 (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);

	delta = diff_delta(src->data, src->size,
			   dst->data, dst->size,
			   &delta_size, 0);
	if (!delta)
		return 0; /* error but caught downstream */

	/* Estimate the edit size by interpreting delta. */
	if (count_delta(delta, delta_size,
			&src_copied, &literal_added)) {
		free(delta);
		return 0; /* we cannot tell */
	}
	free(delta);

	/* 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.
	 */
	if (src->size <= src_copied)
		; /* all copied, nothing removed */
	else {
		delta_size = src->size - src_copied;
		*merge_score_p = delta_size * MAX_SCORE / src->size;
	}
	
	/* Extent of damage, which counts both inserts and
	 * deletes.
	 */
	if (src->size + literal_added <= src_copied)
		delta_size = 0; /* avoid wrapping around */
	else
		delta_size = (src->size - src_copied) + literal_added;
	
	/* We break if the edit exceeds the minimum.
	 * i.e. (break_score / MAX_SCORE < delta_size / base_size)
	 */
	if (break_score * base_size < delta_size * MAX_SCORE)
		to_break = 1;

	return to_break;
}

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) &&
			    MINIMUM_BREAK_SIZE <= p->one->size) {
				/* 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"
	7	#include "delta.h"
	8	#include "count-delta.h"
	9
eeaa4603 JH	10	static int should_break(struct diff_filespec *src,
	11	struct diff_filespec *dst,
	12	int break_score,
	13	int *merge_score_p)
f345b0a0 JH	14	{
	15	/* dst is recorded as a modification of src. Are they so
	16	* different that we are better off recording this as a pair
eeaa4603	17	* of delete and create?
f345b0a0	18	*
eeaa4603 JH	19	* There are two criteria used in this algorithm. For the
	20	* purposes of helping later rename/copy, we take both delete
	21	* and insert into account and estimate the amount of "edit".
	22	* If the edit is very large, we break this pair so that
	23	* rename/copy can pick the pieces up to match with other
	24	* files.
	25	*
	26	* On the other hand, we would want to ignore inserts for the
	27	* pure "complete rewrite" detection. As long as most of the
	28	* existing contents were removed from the file, it is a
	29	* complete rewrite, and if sizable chunk from the original
	30	* still remains in the result, it is not a rewrite. It does
	31	* not matter how much or how little new material is added to
	32	* the file.
	33	*
	34	* The score we leave for such a broken filepair uses the
	35	* latter definition so that later clean-up stage can find the
	36	* pieces that should not have been broken according to the
	37	* latter definition after rename/copy runs, and merge the
	38	* broken pair that have a score lower than given criteria
	39	* back together. The break operation itself happens
	40	* according to the former definition.
	41	*
	42	* The minimum_edit parameter tells us when to break (the
	43	* amount of "edit" required for us to consider breaking the
	44	* pair). We leave the amount of deletion in *merge_score_p
	45	* when we return.
	46	*
	47	* The value we return is 1 if we want the pair to be broken,
	48	* or 0 if we do not.
f345b0a0 JH	49	*/
f345b0a0 JH	50	void *delta;
355e76a4	51	unsigned long delta_size, base_size, src_copied, literal_added;
eeaa4603 JH	52	int to_break = 0;
	53
	54	merge_score_p = 0; / assume no deletion --- "do not break"
	55	* is the default.
	56	*/
f345b0a0 JH	57
	58	if (!S_ISREG(src->mode) \|\| !S_ISREG(dst->mode))
	59	return 0; /* leave symlink rename alone */
	60
eeaa4603	61	if (diff_populate_filespec(src, 0) \|\| diff_populate_filespec(dst, 0))
f345b0a0 JH	62	return 0; /* error but caught downstream */
f345b0a0 JH	63
f78c79c5	64	base_size = ((src->size < dst->size) ? src->size : dst->size);
f345b0a0	65
f345b0a0 JH	66	delta = diff_delta(src->data, src->size,
f345b0a0 JH	67	dst->data, dst->size,
3c849742	68	&delta_size, 0);
d28c8af6 JH	69	if (!delta)
d28c8af6 JH	70	return 0; /* error but caught downstream */
f345b0a0	71
f345b0a0	72	/* Estimate the edit size by interpreting delta. */
eeaa4603 JH	73	if (count_delta(delta, delta_size,
eeaa4603 JH	74	&src_copied, &literal_added)) {
355e76a4	75	free(delta);
eeaa4603	76	return 0; /* we cannot tell */
355e76a4	77	}
f345b0a0	78	free(delta);
355e76a4	79
eeaa4603 JH	80	/* Compute merge-score, which is "how much is removed
	81	* from the source material". The clean-up stage will
	82	* merge the surviving pair together if the score is
	83	* less than the minimum, after rename/copy runs.
	84	*/
	85	if (src->size <= src_copied)
f78c79c5 JH	86	; /* all copied, nothing removed */
f78c79c5 JH	87	else {
eeaa4603	88	delta_size = src->size - src_copied;
f78c79c5 JH	89	merge_score_p = delta_size MAX_SCORE / src->size;
f78c79c5 JH	90	}
eeaa4603 JH	91
	92	/* Extent of damage, which counts both inserts and
	93	* deletes.
	94	*/
	95	if (src->size + literal_added <= src_copied)
	96	delta_size = 0; /* avoid wrapping around */
355e76a4 JH	97	else
355e76a4 JH	98	delta_size = (src->size - src_copied) + literal_added;
eeaa4603 JH	99
	100	/* We break if the edit exceeds the minimum.
	101	* i.e. (break_score / MAX_SCORE < delta_size / base_size)
	102	*/
	103	if (break_score * base_size < delta_size * MAX_SCORE)
	104	to_break = 1;
f345b0a0	105
eeaa4603	106	return to_break;
f345b0a0 JH	107	}
f345b0a0 JH	108
eeaa4603	109	void diffcore_break(int break_score)
f345b0a0 JH	110	{
	111	struct diff_queue_struct *q = &diff_queued_diff;
	112	struct diff_queue_struct outq;
eeaa4603 JH	113
	114	/* When the filepair has this much edit (insert and delete),
	115	* it is first considered to be a rewrite and broken into a
	116	* create and delete filepair. This is to help breaking a
	117	* file that had too much new stuff added, possibly from
	118	* moving contents from another file, so that rename/copy can
	119	* match it with the other file.
	120	*
	121	* int break_score; we reuse incoming parameter for this.
	122	*/
	123
	124	/* After a pair is broken according to break_score and
	125	* subjected to rename/copy, both of them may survive intact,
	126	* due to lack of suitable rename/copy peer. Or, the caller
	127	* may be calling us without using rename/copy. When that
	128	* happens, we merge the broken pieces back into one
	129	* modification together if the pair did not have more than
	130	* this much delete. For this computation, we do not take
	131	* insert into account at all. If you start from a 100-line
	132	* file and delete 97 lines of it, it does not matter if you
	133	* add 27 lines to it to make a new 30-line file or if you add
	134	* 997 lines to it to make a 1000-line file. Either way what
	135	* you did was a rewrite of 97%. On the other hand, if you
	136	* delete 3 lines, keeping 97 lines intact, it does not matter
	137	* if you add 3 lines to it to make a new 100-line file or if
	138	* you add 903 lines to it to make a new 1000-line file.
	139	* Either way you did a lot of additions and not a rewrite.
	140	* This merge happens to catch the latter case. A merge_score
	141	* of 80% would be a good default value (a broken pair that
	142	* has score lower than merge_score will be merged back
	143	* together).
	144	*/
	145	int merge_score;
f345b0a0 JH	146	int i;
f345b0a0 JH	147
eeaa4603 JH	148	/* See comment on DEFAULT_BREAK_SCORE and
	149	* DEFAULT_MERGE_SCORE in diffcore.h
	150	*/
	151	merge_score = (break_score >> 16) & 0xFFFF;
	152	break_score = (break_score & 0xFFFF);
	153
	154	if (!break_score)
	155	break_score = DEFAULT_BREAK_SCORE;
	156	if (!merge_score)
	157	merge_score = DEFAULT_MERGE_SCORE;
f345b0a0 JH	158
	159	outq.nr = outq.alloc = 0;
	160	outq.queue = NULL;
	161
	162	for (i = 0; i < q->nr; i++) {
	163	struct diff_filepair *p = q->queue[i];
	164	int score;
	165
	166	/* We deal only with in-place edit of non directory.
	167	* We do not break anything else.
	168	*/
	169	if (DIFF_FILE_VALID(p->one) && DIFF_FILE_VALID(p->two) &&
	170	!S_ISDIR(p->one->mode) && !S_ISDIR(p->two->mode) &&
	171	!strcmp(p->one->path, p->two->path)) {
eeaa4603	172	if (should_break(p->one, p->two,
f78c79c5 JH	173	break_score, &score) &&
f78c79c5 JH	174	MINIMUM_BREAK_SIZE <= p->one->size) {
f345b0a0 JH	175	/* Split this into delete and create */
	176	struct diff_filespec null_one, null_two;
	177	struct diff_filepair *dp;
	178
eeaa4603 JH	179	/* Set score to 0 for the pair that
	180	* needs to be merged back together
	181	* should they survive rename/copy.
	182	* Also we do not want to break very
	183	* small files.
	184	*/
f78c79c5	185	if (score < merge_score)
eeaa4603 JH	186	score = 0;
eeaa4603 JH	187
f345b0a0 JH	188	/* deletion of one */
	189	null_one = alloc_filespec(p->one->path);
	190	dp = diff_queue(&outq, p->one, null_one);
	191	dp->score = score;
	192	dp->broken_pair = 1;
	193
	194	/* creation of two */
	195	null_two = alloc_filespec(p->two->path);
	196	dp = diff_queue(&outq, null_two, p->two);
	197	dp->score = score;
	198	dp->broken_pair = 1;
	199
	200	free(p); /* not diff_free_filepair(), we are
	201	* reusing one and two here.
	202	*/
	203	continue;
	204	}
	205	}
	206	diff_q(&outq, p);
	207	}
	208	free(q->queue);
	209	*q = outq;
	210
	211	return;
	212	}
eeaa4603 JH	213
	214	static void merge_broken(struct diff_filepair *p,
	215	struct diff_filepair *pp,
	216	struct diff_queue_struct *outq)
	217	{
	218	/* p and pp are broken pairs we want to merge */
366175ef	219	struct diff_filepair c = p, d = pp, *dp;
eeaa4603 JH	220	if (DIFF_FILE_VALID(p->one)) {
	221	/* this must be a delete half */
	222	d = p; c = pp;
	223	}
	224	/* Sanity check */
	225	if (!DIFF_FILE_VALID(d->one))
	226	die("internal error in merge #1");
	227	if (DIFF_FILE_VALID(d->two))
	228	die("internal error in merge #2");
	229	if (DIFF_FILE_VALID(c->one))
	230	die("internal error in merge #3");
	231	if (!DIFF_FILE_VALID(c->two))
	232	die("internal error in merge #4");
	233
366175ef JH	234	dp = diff_queue(outq, d->one, c->two);
366175ef JH	235	dp->score = p->score;
19397b45 JH	236	diff_free_filespec_data(d->two);
19397b45 JH	237	diff_free_filespec_data(c->one);
eeaa4603 JH	238	free(d);
	239	free(c);
	240	}
	241
	242	void diffcore_merge_broken(void)
	243	{
	244	struct diff_queue_struct *q = &diff_queued_diff;
	245	struct diff_queue_struct outq;
	246	int i, j;
	247
	248	outq.nr = outq.alloc = 0;
	249	outq.queue = NULL;
	250
	251	for (i = 0; i < q->nr; i++) {
	252	struct diff_filepair *p = q->queue[i];
	253	if (!p)
	254	/* we already merged this with its peer */
	255	continue;
	256	else if (p->broken_pair &&
eeaa4603 JH	257	!strcmp(p->one->path, p->two->path)) {
	258	/* If the peer also survived rename/copy, then
	259	* we merge them back together.
	260	*/
	261	for (j = i + 1; j < q->nr; j++) {
	262	struct diff_filepair *pp = q->queue[j];
	263	if (pp->broken_pair &&
eeaa4603 JH	264	!strcmp(pp->one->path, pp->two->path) &&
	265	!strcmp(p->one->path, pp->two->path)) {
	266	/* Peer survived. Merge them */
	267	merge_broken(p, pp, &outq);
	268	q->queue[j] = NULL;
	269	break;
	270	}
	271	}
	272	if (q->nr <= j)
	273	/* The peer did not survive, so we keep
	274	* it in the output.
	275	*/
	276	diff_q(&outq, p);
	277	}
	278	else
	279	diff_q(&outq, p);
	280	}
	281	free(q->queue);
	282	*q = outq;
	283
	284	return;
	285	}