diffcore-rename: favour identical basenames

When there are several candidates for a rename source, and one of them
has an identical basename to the rename target, take that one.

Noticed by Govind Salinas, posted by Shawn O. Pearce, partial patch
by Linus Torvalds.

Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/diffcore-rename.c b/diffcore-rename.c
index 93c40d9e04f35897b1ac2ad578db0c0972aacbc1..79c984c9cf5489d22f359b7a2ad3464ffc271c35 100644 (file)
--- a/diffcore-rename.c
+++ b/diffcore-rename.c
@@ -119,6 +119,21 @@ static int is_exact_match(struct diff_filespec *src,
        return 0;
 }
 
+static int basename_same(struct diff_filespec *src, struct diff_filespec *dst)
+{
+       int src_len = strlen(src->path), dst_len = strlen(dst->path);
+       while (src_len && dst_len) {
+               char c1 = src->path[--src_len];
+               char c2 = dst->path[--dst_len];
+               if (c1 != c2)
+                       return 0;
+               if (c1 == '/')
+                       return 1;
+       }
+       return (!src_len || src->path[src_len - 1] == '/') &&
+               (!dst_len || dst->path[dst_len - 1] == '/');
+}
+
 struct diff_score {
        int src; /* index in rename_src */
        int dst; /* index in rename_dst */
@@ -186,8 +201,11 @@ 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;
 }
 
@@ -295,9 +313,22 @@ void diffcore_rename(struct diff_options *options)
                        if (rename_dst[i].pair)
                                continue; /* dealt with an earlier round */
                        for (j = 0; j < rename_src_nr; j++) {
+                               int k;
                                struct diff_filespec *one = rename_src[j].one;
                                if (!is_exact_match(one, two, contents_too))
                                        continue;
+
+                               /* see if there is a basename match, too */
+                               for (k = j; k < rename_src_nr; k++) {
+                                       one = rename_src[k].one;
+                                       if (basename_same(one, two) &&
+                                               is_exact_match(one, two,
+                                                       contents_too)) {
+                                               j = k;
+                                               break;
+                                       }
+                               }
+
                                record_rename_pair(i, j, (int)MAX_SCORE);
                                rename_count++;
                                break; /* we are done with this entry */

diff --git a/t/t4001-diff-rename.sh b/t/t4001-diff-rename.sh
index 2e3c20d6b9468bf413e97d422e7dbe13ac4238cd..90c085f82814fc973ec7f0732b419cd631e9dc43 100755 (executable)
--- a/t/t4001-diff-rename.sh
+++ b/t/t4001-diff-rename.sh
@@ -64,4 +64,17 @@ test_expect_success \
     'validate the output.' \
     'compare_diff_patch current expected'
 
+test_expect_success 'favour same basenames over different ones' '
+       cp path1 another-path &&
+       git add another-path &&
+       git commit -m 1 &&
+       git rm path1 &&
+       mkdir subdir &&
+       git mv another-path subdir/path1 &&
+       git runstatus | grep "renamed: .*path1 -> subdir/path1"'
+
+test_expect_success  'favour same basenames even with minor differences' '
+       git show HEAD:path1 | sed "s/15/16/" > subdir/path1 &&
+       git runstatus | grep "renamed: .*path1 -> subdir/path1"'
+
 test_done