if (src->sha1_valid && dst->sha1_valid &&
!memcmp(src->sha1, dst->sha1, 20))
return 1;
- if (diff_populate_filespec(src) || diff_populate_filespec(dst))
- /* this is an error but will be caught downstream */
+ if (diff_populate_filespec(src, 1) || diff_populate_filespec(dst, 1))
+ return 0;
+ if (src->size != dst->size)
+ return 0;
+ if (diff_populate_filespec(src, 0) || diff_populate_filespec(dst, 0))
return 0;
if (src->size == dst->size &&
!memcmp(src->data, dst->data, src->size))
* dst, and then some edit has been applied to dst.
*
* Compare them and return how similar they are, representing
- * the score as an integer between 0 and 10000, except
- * where they match exactly it is considered better than anything
- * else.
+ * the score as an integer between 0 and MAX_SCORE.
+ *
+ * When there is an exact match, it is considered a better
+ * match than anything else; the destination does not even
+ * call into this function in that case.
*/
void *delta;
- unsigned long delta_size, base_size;
+ unsigned long delta_size, base_size, src_copied, literal_added;
+ unsigned long delta_limit;
int score;
/* We deal only with regular files. Symlink renames are handled
/* We would not consider edits that change the file size so
* drastically. delta_size must be smaller than
* (MAX_SCORE-minimum_score)/MAX_SCORE * min(src->size, dst->size).
+ *
* Note that base_size == 0 case is handled here already
* and the final score computation below would not have a
* divide-by-zero issue.
if (base_size * (MAX_SCORE-minimum_score) < delta_size * MAX_SCORE)
return 0;
+ if (diff_populate_filespec(src, 0) || diff_populate_filespec(dst, 0))
+ return 0; /* error but caught downstream */
+
+ delta_limit = base_size * (MAX_SCORE-minimum_score) / MAX_SCORE;
delta = diff_delta(src->data, src->size,
dst->data, dst->size,
- &delta_size);
+ &delta_size, delta_limit);
+ if (!delta)
+ /* If delta_limit is exceeded, we have too much differences */
+ return 0;
/* A delta that has a lot of literal additions would have
* big delta_size no matter what else it does.
return 0;
/* Estimate the edit size by interpreting delta. */
- delta_size = count_delta(delta, delta_size);
- free(delta);
- if (delta_size == UINT_MAX)
+ if (count_delta(delta, delta_size, &src_copied, &literal_added)) {
+ free(delta);
return 0;
+ }
+ free(delta);
+
+ /* Extent of damage */
+ if (src->size + literal_added < src_copied)
+ delta_size = 0;
+ else
+ delta_size = (src->size - src_copied) + literal_added;
/*
* Now we will give some score to it. 100% edit gets 0 points
fill_filespec(two, dst->sha1, dst->mode);
dp = diff_queue(renq, one, two);
- dp->score = score ? : 1; /* make sure it is at least 1 */
+ dp->score = score;
dp->source_stays = rename_src[src_index].src_stays;
rename_dst[dst_index].pair = dp;
}
return b->score - a->score;
}
-int diff_scoreopt_parse(const char *opt)
-{
- int diglen, num, scale, i;
- if (opt[0] != '-' || (opt[1] != 'M' && opt[1] != 'C'))
- return -1; /* that is not a -M nor -C option */
- diglen = strspn(opt+2, "0123456789");
- if (diglen == 0 || strlen(opt+2) != diglen)
- return 0; /* use default */
- sscanf(opt+2, "%d", &num);
- for (i = 0, scale = 1; i < diglen; i++)
- scale *= 10;
-
- /* user says num divided by scale and we say internally that
- * is MAX_SCORE * num / scale.
- */
- return MAX_SCORE * num / scale;
-}
-
void diffcore_rename(int detect_rename, int minimum_score)
{
struct diff_queue_struct *q = &diff_queued_diff;
int num_create, num_src, dst_cnt;
if (!minimum_score)
- minimum_score = DEFAULT_MINIMUM_SCORE;
+ minimum_score = DEFAULT_RENAME_SCORE;
renq.queue = NULL;
renq.nr = renq.alloc = 0;
continue; /* unmerged */
else
locate_rename_dst(p->two, 1);
- else if (!DIFF_FILE_VALID(p->two))
- register_rename_src(p->one, 0);
+ else if (!DIFF_FILE_VALID(p->two)) {
+ /* If the source is a broken "delete", and
+ * they did not really want to get broken,
+ * that means the source actually stays.
+ */
+ int stays = (p->broken_pair && !p->score);
+ register_rename_src(p->one, stays);
+ }
else if (detect_rename == DIFF_DETECT_COPY)
register_rename_src(p->one, 1);
}
outq.nr = outq.alloc = 0;
for (i = 0; i < q->nr; i++) {
struct diff_filepair *p = q->queue[i];
- struct diff_rename_dst *dst = locate_rename_dst(p->two, 0);
struct diff_filepair *pair_to_free = NULL;
- if (dst) {
- /* creation */
- if (dst->pair) {
- /* renq has rename/copy to produce
- * this file already, so we do not
- * emit the creation record in the
- * output.
- */
+ if (!DIFF_FILE_VALID(p->one) && DIFF_FILE_VALID(p->two)) {
+ /*
+ * Creation
+ *
+ * We would output this create record if it has
+ * not been turned into a rename/copy already.
+ */
+ struct diff_rename_dst *dst =
+ locate_rename_dst(p->two, 0);
+ if (dst && dst->pair) {
diff_q(&outq, dst->pair);
pair_to_free = p;
}
else
- /* no matching rename/copy source, so record
- * this as a creation.
+ /* no matching rename/copy source, so
+ * record this as a creation.
*/
diff_q(&outq, p);
}
+ else if (DIFF_FILE_VALID(p->one) && !DIFF_FILE_VALID(p->two)) {
+ /*
+ * Deletion
+ *
+ * We would output this delete record if:
+ *
+ * (1) this is a broken delete and the counterpart
+ * broken create remains in the output; or
+ * (2) this is not a broken delete, and renq does
+ * not have a rename/copy to move p->one->path
+ * out.
+ *
+ * Otherwise, the counterpart broken create
+ * has been turned into a rename-edit; or
+ * delete did not have a matching create to
+ * begin with.
+ */
+ if (DIFF_PAIR_BROKEN(p)) {
+ /* broken delete */
+ struct diff_rename_dst *dst =
+ locate_rename_dst(p->one, 0);
+ if (dst && dst->pair)
+ /* counterpart is now rename/copy */
+ pair_to_free = p;
+ }
+ else {
+ for (j = 0; j < renq.nr; j++)
+ if (!strcmp(renq.queue[j]->one->path,
+ p->one->path))
+ break;
+ if (j < renq.nr)
+ /* this path remains */
+ pair_to_free = p;
+ }
+
+ if (pair_to_free)
+ ;
+ else
+ diff_q(&outq, p);
+ }
else if (!diff_unmodified_pair(p))
/* all the usual ones need to be kept */
diff_q(&outq, p);