Consistent message encoding while reusing log from an existing commit.

diff --git a/diffcore-break.c b/diffcore-break.c
index 0fc2b860bef30ee5a37b90df835e66f0dc74ab70..acb18db1db27dc29fdb76bd519174aa56f56121d 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.
@@ -56,7 +56,7 @@ static int should_break(struct diff_filespec *src,
                return 0; /* leave symlink rename alone */
 
        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))
@@ -68,37 +68,45 @@ static int should_break(struct diff_filespec *src,
 
        if (diffcore_count_changes(src->data, src->size,
                                   dst->data, dst->size,
+                                  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 = 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)