diffcore-rename: similarity estimator fix.

diff --git a/diffcore-rename.c b/diffcore-rename.c
index e17dd90058443ea75321f8c48818bd0094bd76a3..625b589fb728e5ae94b3b13d419b43c30347508d 100644 (file)
--- a/diffcore-rename.c
+++ b/diffcore-rename.c
@@ -4,8 +4,6 @@
 #include "cache.h"
 #include "diff.h"
 #include "diffcore.h"
-#include "delta.h"
-#include "count-delta.h"
 
 /* Table of rename/copy destinations */
 
@@ -135,7 +133,6 @@ static int estimate_similarity(struct diff_filespec *src,
         * match than anything else; the destination does not even
         * call into this function in that case.
         */
-       void *delta;
        unsigned long delta_size, base_size, src_copied, literal_added;
        unsigned long delta_limit;
        int score;
@@ -165,40 +162,23 @@ static int estimate_similarity(struct diff_filespec *src,
        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_limit);
-       if (!delta)
-               /* If delta_limit is exceeded, we have too much differences */
+       if (diffcore_count_changes(src->data, src->size,
+                                  dst->data, dst->size,
+                                  delta_limit,
+                                  &src_copied, &literal_added))
                return 0;
 
-       /* A delta that has a lot of literal additions would have
-        * big delta_size no matter what else it does.
+       /* How similar are they?
+        * what percentage of material in dst are from source?
         */
-       if (base_size * (MAX_SCORE-minimum_score) < delta_size * MAX_SCORE)
-               return 0;
-
-       /* Estimate the edit size by interpreting delta. */
-       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;
+       if (dst->size < src_copied)
+               score = MAX_SCORE;
+       else if (!dst->size)
+               score = 0; /* should not happen */
        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.
-        */
-       score = MAX_SCORE - (MAX_SCORE * delta_size / base_size); 
-       if (score < 0) return 0;
-       if (MAX_SCORE < score) return MAX_SCORE;
+               score = src_copied * MAX_SCORE / dst->size;
        return score;
 }
 
@@ -282,8 +262,8 @@ void diffcore_rename(struct diff_options *options)
                else if (detect_rename == DIFF_DETECT_COPY)
                        register_rename_src(p->one, 1);
        }
-       if (rename_dst_nr == 0 ||
-           (0 <= rename_limit && rename_limit < rename_dst_nr))
+       if (rename_dst_nr == 0 || rename_src_nr == 0 ||
+           (0 < rename_limit && rename_limit < rename_dst_nr))
                goto cleanup; /* nothing to do */
 
        /* We really want to cull the candidates list early
@@ -307,6 +287,9 @@ void diffcore_rename(struct diff_options *options)
        if (rename_count == rename_dst_nr)
                goto cleanup;
 
+       if (minimum_score == MAX_SCORE)
+               goto cleanup;
+
        num_create = (rename_dst_nr - rename_count);
        num_src = rename_src_nr;
        mx = xmalloc(sizeof(*mx) * num_create * num_src);