merge-recursive: add computation of collisions due to dir rename & merging

directory renaming and merging can cause one or more files to be moved to
where an existing file is, or to cause several files to all be moved to
the same (otherwise vacant) location.  Add checking and reporting for such
cases, falling back to no-directory-rename handling for such paths.

Reviewed-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 143 insertions, 3 deletions

diff --git a/merge-recursive.c b/merge-recursive.c
index a67bb58da7..50eb6c70dd 100644
--- a/merge-recursive.c
+++ b/merge-recursive.c
@@ -87,6 +87,29 @@ static void dir_rename_entry_init(struct dir_rename_entry *entry,
 	string_list_init(&entry->possible_new_dirs, 0);
 }
 
+static struct collision_entry *collision_find_entry(struct hashmap *hashmap,
+						    char *target_file)
+{
+	struct collision_entry key;
+
+	hashmap_entry_init(&key, strhash(target_file));
+	key.target_file = target_file;
+	return hashmap_get(hashmap, &key, NULL);
+}
+
+static int collision_cmp(void *unused_cmp_data,
+			 const struct collision_entry *e1,
+			 const struct collision_entry *e2,
+			 const void *unused_keydata)
+{
+	return strcmp(e1->target_file, e2->target_file);
+}
+
+static void collision_init(struct hashmap *map)
+{
+	hashmap_init(map, (hashmap_cmp_fn) collision_cmp, NULL, 0);
+}
+
 static void flush_output(struct merge_options *o)
 {
 	if (o->buffer_output < 2 && o->obuf.len) {
@@ -1404,6 +1427,31 @@ static int tree_has_path(struct tree *tree, const char *path)
 			       &hashy, &mode_o);
 }
 
+/*
+ * Return a new string that replaces the beginning portion (which matches
+ * entry->dir), with entry->new_dir.  In perl-speak:
+ *   new_path_name = (old_path =~ s/entry->dir/entry->new_dir/);
+ * NOTE:
+ *   Caller must ensure that old_path starts with entry->dir + '/'.
+ */
+static char *apply_dir_rename(struct dir_rename_entry *entry,
+			      const char *old_path)
+{
+	struct strbuf new_path = STRBUF_INIT;
+	int oldlen, newlen;
+
+	if (entry->non_unique_new_dir)
+		return NULL;
+
+	oldlen = strlen(entry->dir);
+	newlen = entry->new_dir.len + (strlen(old_path) - oldlen) + 1;
+	strbuf_grow(&new_path, newlen);
+	strbuf_addbuf(&new_path, &entry->new_dir);
+	strbuf_addstr(&new_path, &old_path[oldlen]);
+
+	return strbuf_detach(&new_path, NULL);
+}
+
 static void get_renamed_dir_portion(const char *old_path, const char *new_path,
 				    char **old_dir, char **new_dir)
 {
@@ -1673,6 +1721,84 @@ static struct hashmap *get_directory_renames(struct diff_queue_struct *pairs,
 	return dir_renames;
 }
 
+static struct dir_rename_entry *check_dir_renamed(const char *path,
+						  struct hashmap *dir_renames)
+{
+	char temp[PATH_MAX];
+	char *end;
+	struct dir_rename_entry *entry;
+
+	strcpy(temp, path);
+	while ((end = strrchr(temp, '/'))) {
+		*end = '\0';
+		entry = dir_rename_find_entry(dir_renames, temp);
+		if (entry)
+			return entry;
+	}
+	return NULL;
+}
+
+static void compute_collisions(struct hashmap *collisions,
+			       struct hashmap *dir_renames,
+			       struct diff_queue_struct *pairs)
+{
+	int i;
+
+	/*
+	 * Multiple files can be mapped to the same path due to directory
+	 * renames done by the other side of history.  Since that other
+	 * side of history could have merged multiple directories into one,
+	 * if our side of history added the same file basename to each of
+	 * those directories, then all N of them would get implicitly
+	 * renamed by the directory rename detection into the same path,
+	 * and we'd get an add/add/.../add conflict, and all those adds
+	 * from *this* side of history.  This is not representable in the
+	 * index, and users aren't going to easily be able to make sense of
+	 * it.  So we need to provide a good warning about what's
+	 * happening, and fall back to no-directory-rename detection
+	 * behavior for those paths.
+	 *
+	 * See testcases 9e and all of section 5 from t6043 for examples.
+	 */
+	collision_init(collisions);
+
+	for (i = 0; i < pairs->nr; ++i) {
+		struct dir_rename_entry *dir_rename_ent;
+		struct collision_entry *collision_ent;
+		char *new_path;
+		struct diff_filepair *pair = pairs->queue[i];
+
+		if (pair->status == 'D')
+			continue;
+		dir_rename_ent = check_dir_renamed(pair->two->path,
+						   dir_renames);
+		if (!dir_rename_ent)
+			continue;
+
+		new_path = apply_dir_rename(dir_rename_ent, pair->two->path);
+		if (!new_path)
+			/*
+			 * dir_rename_ent->non_unique_new_path is true, which
+			 * means there is no directory rename for us to use,
+			 * which means it won't cause us any additional
+			 * collisions.
+			 */
+			continue;
+		collision_ent = collision_find_entry(collisions, new_path);
+		if (!collision_ent) {
+			collision_ent = xcalloc(1,
+						sizeof(struct collision_entry));
+			hashmap_entry_init(collision_ent, strhash(new_path));
+			hashmap_put(collisions, collision_ent);
+			collision_ent->target_file = new_path;
+		} else {
+			free(new_path);
+		}
+		string_list_insert(&collision_ent->source_files,
+				   pair->two->path);
+	}
+}
+
 /*
  * Get information of all renames which occurred in 'pairs', making use of
  * any implicit directory renames inferred from the other side of history.
@@ -1682,6 +1808,7 @@ static struct hashmap *get_directory_renames(struct diff_queue_struct *pairs,
  */
 static struct string_list *get_renames(struct merge_options *o,
 				       struct diff_queue_struct *pairs,
+				       struct hashmap *dir_renames,
 				       struct tree *tree,
 				       struct tree *o_tree,
 				       struct tree *a_tree,
@@ -1689,8 +1816,12 @@ static struct string_list *get_renames(struct merge_options *o,
 				       struct string_list *entries)
 {
 	int i;
+	struct hashmap collisions;
+	struct hashmap_iter iter;
+	struct collision_entry *e;
 	struct string_list *renames;
 
+	compute_collisions(&collisions, dir_renames, pairs);
 	renames = xcalloc(1, sizeof(struct string_list));
 
 	for (i = 0; i < pairs->nr; ++i) {
@@ -1721,6 +1852,13 @@ static struct string_list *get_renames(struct merge_options *o,
 		item = string_list_insert(renames, pair->one->path);
 		item->util = re;
 	}
+
+	hashmap_iter_init(&collisions, &iter);
+	while ((e = hashmap_iter_next(&iter))) {
+		free(e->target_file);
+		string_list_clear(&e->source_files, 0);
+	}
+	hashmap_free(&collisions, 1);
 	return renames;
 }
 
@@ -2030,9 +2168,11 @@ static int handle_renames(struct merge_options *o,
 					 dir_re_head, head,
 					 dir_re_merge, merge);
 
-	ri->head_renames  = get_renames(o, head_pairs, head,
-					 common, head, merge, entries);
-	ri->merge_renames = get_renames(o, merge_pairs, merge,
+	ri->head_renames  = get_renames(o, head_pairs,
+					dir_re_merge, head,
+					common, head, merge, entries);
+	ri->merge_renames = get_renames(o, merge_pairs,
+					dir_re_head, merge,
 					 common, head, merge, entries);
 	clean = process_renames(o, ri->head_renames, ri->merge_renames);