diffcore-break: similarity estimator fix.

This is a companion patch to the previous fix to diffcore-rename.
The merging-back process should use a logic similar to what is used
there.

Signed-off-by: Junio C Hamano <junkio@cox.net>

diff --git a/diffcore-break.c b/diffcore-break.c
index 0fc2b86..71ad58a 100644 (file)
--- a/diffcore-break.c
+++ b/diffcore-break.c
@@ -45,8 +45,8 @@ static int should_break(struct diff_filespec *src,
         * 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, src_copied, literal_added,
+               src_removed;
 
        *merge_score_p = 0; /* assume no deletion --- "do not break"
                             * is the default.
@@ -72,33 +72,40 @@ static int should_break(struct diff_filespec *src,
                                   &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 = src_removed * MAX_SCORE / src->size;
+
        /* 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 / base_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)

diff --git a/diffcore.h b/diffcore.h
index dba4f17..d31b3b4 100644 (file)
--- a/diffcore.h
+++ b/diffcore.h
@@ -17,8 +17,8 @@
  */
 #define MAX_SCORE 60000.0
 #define DEFAULT_RENAME_SCORE 30000 /* rename/copy similarity minimum (50%) */
-#define DEFAULT_BREAK_SCORE  30000 /* minimum for break to happen (50%)*/
-#define DEFAULT_MERGE_SCORE  48000 /* maximum for break-merge to happen (80%)*/
+#define DEFAULT_BREAK_SCORE  30000 /* minimum for break to happen (50%) */
+#define DEFAULT_MERGE_SCORE  36000 /* maximum for break-merge to happen 60%) */
 
 #define MINIMUM_BREAK_SIZE     400 /* do not break a file smaller than this */