Merge branch 'rs/diff'

* rs/diff:
  diff: round down similarity index
  diffcore-rename: don't change similarity index based on basename equality

3 files changed, 25 insertions, 15 deletions

diff --git a/Documentation/diff-format.txt b/Documentation/diff-format.txt
index 18d49d2c3b..001503205b 100644
--- a/Documentation/diff-format.txt
+++ b/Documentation/diff-format.txt
@@ -126,6 +126,13 @@ the file that rename/copy produces, respectively.
     If there is need for such substitution then the whole
     pathname is put in double quotes.
 
+The similarity index is the percentage of unchanged lines, and
+the dissimilarity index is the percentage of changed lines.  It
+is a rounded down integer, followed by a percent sign.  The
+similarity index value of 100% is thus reserved for two equal
+files, while 100% dissimilarity means that no line from the old
+file made it into the new one.
+
 
 combined diff format
 --------------------
diff --git a/diff.c b/diff.c
index 9938969fa5..e0edb98846 100644
--- a/diff.c
+++ b/diff.c
@@ -1813,6 +1813,11 @@ static void diff_fill_sha1_info(struct diff_filespec *one)
 		hashclr(one->sha1);
 }
 
+static int similarity_index(struct diff_filepair *p)
+{
+	return p->score * 100 / MAX_SCORE;
+}
+
 static void run_diff(struct diff_filepair *p, struct diff_options *o)
 {
 	const char *pgm = external_diff();
@@ -1847,23 +1852,20 @@ static void run_diff(struct diff_filepair *p, struct diff_options *o)
 				"similarity index %d%%\n"
 				"copy from %s\n"
 				"copy to %s\n",
-				(int)(0.5 + p->score * 100.0/MAX_SCORE),
-				name_munged, other_munged);
+				similarity_index(p), name_munged, other_munged);
 		break;
 	case DIFF_STATUS_RENAMED:
 		len += snprintf(msg + len, sizeof(msg) - len,
 				"similarity index %d%%\n"
 				"rename from %s\n"
 				"rename to %s\n",
-				(int)(0.5 + p->score * 100.0/MAX_SCORE),
-				name_munged, other_munged);
+				similarity_index(p), name_munged, other_munged);
 		break;
 	case DIFF_STATUS_MODIFIED:
 		if (p->score) {
 			len += snprintf(msg + len, sizeof(msg) - len,
 					"dissimilarity index %d%%\n",
-					(int)(0.5 + p->score *
-					      100.0/MAX_SCORE));
+					similarity_index(p));
 			complete_rewrite = 1;
 			break;
 		}
@@ -2387,8 +2389,7 @@ static void diff_flush_raw(struct diff_filepair *p,
 	}
 
 	if (p->score)
-		sprintf(status, "%c%03d", p->status,
-			(int)(0.5 + p->score * 100.0/MAX_SCORE));
+		sprintf(status, "%c%03d", p->status, similarity_index(p));
 	else {
 		status[0] = p->status;
 		status[1] = 0;
@@ -2670,8 +2671,7 @@ static void show_rename_copy(const char *renamecopy, struct diff_filepair *p)
 {
 	char *names = pprint_rename(p->one->path, p->two->path);
 
-	printf(" %s %s (%d%%)\n", renamecopy, names,
-	       (int)(0.5 + p->score * 100.0/MAX_SCORE));
+	printf(" %s %s (%d%%)\n", renamecopy, names, similarity_index(p));
 	free(names);
 	show_mode_change(p, 0);
 }
@@ -2695,7 +2695,7 @@ static void diff_summary(struct diff_filepair *p)
 		if (p->score) {
 			char *name = quote_one(p->two->path);
 			printf(" rewrite %s (%d%%)\n", name,
-				(int)(0.5 + p->score * 100.0/MAX_SCORE));
+			       similarity_index(p));
 			free(name);
 			show_mode_change(p, 0);
 		} else	show_mode_change(p, 1);
diff --git a/diffcore-rename.c b/diffcore-rename.c
index 79c984c9cf..e0a89f3796 100644
--- a/diffcore-rename.c
+++ b/diffcore-rename.c
@@ -138,6 +138,7 @@ struct diff_score {
 	int src; /* index in rename_src */
 	int dst; /* index in rename_dst */
 	int score;
+	int name_score;
 };
 
 static int estimate_similarity(struct diff_filespec *src,
@@ -201,11 +202,8 @@ static int estimate_similarity(struct diff_filespec *src,
 	 */
 	if (!dst->size)
 		score = 0; /* should not happen */
-	else {
+	else
 		score = (int)(src_copied * MAX_SCORE / max_size);
-		if (basename_same(src, dst))
-			score++;
-	}
 	return score;
 }
 
@@ -242,6 +240,10 @@ static void record_rename_pair(int dst_index, int src_index, int score)
 static int score_compare(const void *a_, const void *b_)
 {
 	const struct diff_score *a = a_, *b = b_;
+
+	if (a->score == b->score)
+		return b->name_score - a->name_score;
+
 	return b->score - a->score;
 }
 
@@ -360,6 +362,7 @@ void diffcore_rename(struct diff_options *options)
 			m->dst = i;
 			m->score = estimate_similarity(one, two,
 						       minimum_score);
+			m->name_score = basename_same(one, two);
 			diff_free_filespec_data(one);
 		}
 		/* We do not need the text anymore */