fast-import.c: fix regression due to strbuf conversion

diff --git a/diffcore-rename.c b/diffcore-rename.c
index 93c40d9e04f35897b1ac2ad578db0c0972aacbc1..142e5376dd741377c311075816f139a0949ee82f 100644 (file)
--- a/diffcore-rename.c
+++ b/diffcore-rename.c
@@ -119,10 +119,26 @@ 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 */
        int score;
+       int name_score;
 };
 
 static int estimate_similarity(struct diff_filespec *src,
@@ -168,14 +184,14 @@ static int estimate_similarity(struct diff_filespec *src,
        if (base_size * (MAX_SCORE-minimum_score) < delta_size * MAX_SCORE)
                return 0;
 
-       if (diff_populate_filespec(src, 0) || diff_populate_filespec(dst, 0))
+       if ((!src->cnt_data && diff_populate_filespec(src, 0))
+               || (!dst->cnt_data && diff_populate_filespec(dst, 0)))
                return 0; /* error but caught downstream */
 
 
        delta_limit = (unsigned long)
                (base_size * (MAX_SCORE-minimum_score) / MAX_SCORE);
-       if (diffcore_count_changes(src->data, src->size,
-                                  dst->data, dst->size,
+       if (diffcore_count_changes(src, dst,
                                   &src->cnt_data, &dst->cnt_data,
                                   delta_limit,
                                   &src_copied, &literal_added))
@@ -224,6 +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;
 }
 
@@ -279,10 +299,25 @@ void diffcore_rename(struct diff_options *options)
                else if (detect_rename == DIFF_DETECT_COPY)
                        register_rename_src(p->one, 1, p->score);
        }
-       if (rename_dst_nr == 0 || rename_src_nr == 0 ||
-           (0 < rename_limit && rename_limit < rename_dst_nr))
+       if (rename_dst_nr == 0 || rename_src_nr == 0)
                goto cleanup; /* nothing to do */
 
+       /*
+        * This basically does a test for the rename matrix not
+        * growing larger than a "rename_limit" square matrix, ie:
+        *
+        *    rename_dst_nr * rename_src_nr > rename_limit * rename_limit
+        *
+        * but handles the potential overflow case specially (and we
+        * assume at least 32-bit integers)
+        */
+       if (rename_limit <= 0 || rename_limit > 32767)
+               rename_limit = 32767;
+       if (rename_dst_nr > rename_limit && rename_src_nr > rename_limit)
+               goto cleanup;
+       if (rename_dst_nr * rename_src_nr > rename_limit * rename_limit)
+               goto cleanup;
+
        /* We really want to cull the candidates list early
         * with cheap tests in order to avoid doing deltas.
         * The first round matches up the up-to-date entries,
@@ -295,9 +330,22 @@ 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 */
@@ -329,10 +377,11 @@ void diffcore_rename(struct diff_options *options)
                        m->dst = i;
                        m->score = estimate_similarity(one, two,
                                                       minimum_score);
-                       diff_free_filespec_data(one);
+                       m->name_score = basename_same(one, two);
+                       diff_free_filespec_blob(one);
                }
                /* We do not need the text anymore */
-               diff_free_filespec_data(two);
+               diff_free_filespec_blob(two);
                dst_cnt++;
        }
        /* cost matrix sorted by most to least similar pair */