* 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;
- int to_break = 0;
+ unsigned long delta_size, base_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))
- return 0; /* leave symlink rename alone */
+ 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 &&
- !memcmp(src->sha1, dst->sha1, 20))
+ !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)
+ 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->data, src->size,
- dst->data, dst->size,
+ 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.
*/
- 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;
- }
-
+ *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.
*/
- 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)
+ 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 (break_score * base_size < delta_size * MAX_SCORE)
- to_break = 1;
+ if ((src->size * break_score < src_removed * MAX_SCORE) &&
+ (literal_added * 20 < src_removed) &&
+ (literal_added * 20 < src_copied))
+ return 0;
- return to_break;
+ return 1;
}
void diffcore_break(int break_score)
struct diff_filepair *p = q->queue[i];
int score;
- /* We deal only with in-place edit of non directory.
+ /*
+ * 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) &&
- !S_ISDIR(p->one->mode) && !S_ISDIR(p->two->mode) &&
+ 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)) {