#include "cache.h"
#include "diff.h"
#include "diffcore.h"
-#include "delta.h"
-#include "count-delta.h"
-static int very_different(struct diff_filespec *src,
- struct diff_filespec *dst,
- int min_score)
+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? min_score is the minimum amount of
- * new material that must exist in the dst and not in src for
- * the pair to be considered a complete rewrite, and recommended
- * to be set to a very high value, 99% or so.
+ * of delete and create?
*
- * The value we return represents the amount of new material
- * that is in dst and not in src. We return 0 when we do not
- * want to get the filepair broken.
+ * 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;
+ 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 (diff_populate_filespec(src, 1) || diff_populate_filespec(dst, 1))
- return 0; /* error but caught downstream */
-
- delta_size = ((src->size < dst->size) ?
- (dst->size - src->size) : (src->size - dst->size));
-
- /* Notice that we use max of src and dst as the base size,
- * unlike rename similarity detection. This is so that we do
- * not mistake a large addition as a complete rewrite.
- */
- base_size = ((src->size < dst->size) ? dst->size : src->size);
-
- /*
- * If file size difference is too big compared to the
- * base_size, we declare this a complete rewrite.
- */
- if (base_size * min_score < delta_size * MAX_SCORE)
- return MAX_SCORE;
+ if (src->sha1_valid && dst->sha1_valid &&
+ !memcmp(src->sha1, dst->sha1, 20))
+ return 0; /* they are the same */
if (diff_populate_filespec(src, 0) || diff_populate_filespec(dst, 0))
return 0; /* error but caught downstream */
- delta = diff_delta(src->data, src->size,
- dst->data, dst->size,
- &delta_size);
-
- /* A delta that has a lot of literal additions would have
- * big delta_size no matter what else it does.
- */
- if (base_size * min_score < delta_size * MAX_SCORE)
- return MAX_SCORE;
+ 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 */
- /* Estimate the edit size by interpreting delta. */
- if (count_delta(delta, delta_size, &src_copied, &literal_added)) {
- free(delta);
+ if (diffcore_count_changes(src->data, src->size,
+ dst->data, dst->size,
+ 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;
}
- free(delta);
+ src_removed = src->size - src_copied;
- /* Extent of damage */
- if (src->size + literal_added < src_copied)
- delta_size = 0;
- else
- delta_size = (src->size - src_copied) + literal_added;
+ /* 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 = src_removed * MAX_SCORE / src->size;
- if (base_size < delta_size)
- return MAX_SCORE;
+ /* 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 delta_size * MAX_SCORE / base_size;
+ return 1;
}
-void diffcore_break(int min_score)
+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;
- if (!min_score)
- min_score = DEFAULT_BREAK_SCORE;
+ /* 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;
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)) {
- score = very_different(p->one, p->two, min_score);
- if (min_score <= score) {
+ 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);
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;
+}