* match than anything else; the destination does not even
* call into this function in that case.
*/
- unsigned long delta_size, base_size, src_copied, literal_added;
+ unsigned long max_size, delta_size, base_size, src_copied, literal_added;
unsigned long delta_limit;
int score;
if (!S_ISREG(src->mode) || !S_ISREG(dst->mode))
return 0;
- delta_size = ((src->size < dst->size) ?
- (dst->size - src->size) : (src->size - dst->size));
+ max_size = ((src->size > dst->size) ? src->size : dst->size);
base_size = ((src->size < dst->size) ? src->size : dst->size);
+ delta_size = max_size - base_size;
/* We would not consider edits that change the file size so
* drastically. delta_size must be smaller than
delta_limit = base_size * (MAX_SCORE-minimum_score) / MAX_SCORE;
if (diffcore_count_changes(src->data, src->size,
dst->data, dst->size,
+ &src->cnt_data, &dst->cnt_data,
delta_limit,
&src_copied, &literal_added))
return 0;
- /* 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
- * and 0% edit gets MAX_SCORE points.
+ /* How similar are they?
+ * what percentage of material in dst are from source?
*/
- score = MAX_SCORE - (MAX_SCORE * delta_size / base_size);
- if (score < 0) return 0;
- if (MAX_SCORE < score) return MAX_SCORE;
+ if (!dst->size)
+ score = 0; /* should not happen */
+ else
+ score = src_copied * MAX_SCORE / max_size;
return score;
}
m->score = estimate_similarity(one, two,
minimum_score);
}
+ /* We do not need the text anymore */
+ diff_free_filespec_data(two);
dst_cnt++;
}
/* cost matrix sorted by most to least similar pair */