[PATCH 24/30] merge-recursive: Add computation of collisions due to dir rename & merging

From

Elijah Newren <newren@gmail.com>

Date

Nov 10, 2017, 19:05 UTC

Message-ID

<20171110190550.27059-25-newren@gmail.com>

In-Reply-To

<20171110190550.27059-1-newren@gmail.com>

Signed-off-by: Elijah Newren <newren@gmail.com>
---
 merge-recursive.c | 118 +++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 116 insertions(+), 2 deletions(-)

diff --git a/merge-recursive.c b/merge-recursive.c
index 1858686c35..251c4cc7fa 100644
--- a/merge-recursive.c
+++ b/merge-recursive.c
@@ -1408,6 +1408,30 @@ 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/);
+ */
+static char *apply_dir_rename(struct dir_rename_entry *entry,
+			       const char *old_path) {
+	char *new_path;
+	int oldlen, newlen;
+
+	if (entry->non_unique_new_dir)
+		return NULL;
+
+	oldlen = strlen(entry->dir);
+	assert(strncmp(entry->dir, old_path, oldlen) == 0 &&
+	       old_path[oldlen] == '/');
+	newlen = strlen(entry->new_dir) + (strlen(old_path) - oldlen) + 1;
+	new_path = malloc(newlen);
+	strcpy(new_path, entry->new_dir);
+	strcpy(&new_path[strlen(new_path)], &old_path[oldlen]);
+
+	return new_path;
+}
+
 static void get_renamed_dir_portion(const char *old_path, const char *new_path,
 				    char **old_dir, char **new_dir) {
 	*old_dir = NULL;
@@ -1625,6 +1649,82 @@ 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.
@@ -1634,6 +1734,7 @@ 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,
@@ -1641,8 +1742,12 @@ 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) {
@@ -1672,6 +1777,13 @@ 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;
 }
 
@@ -1962,9 +2074,11 @@ static struct rename_info *handle_renames(struct merge_options *o,
 					 dir_re_head, head,
 					 dir_re_merge, merge);
 
-	rei->head_renames  = get_renames(o, head_pairs, head,
+	rei->head_renames  = get_renames(o, head_pairs,
+					 dir_re_merge, head,
 					 common, head, merge, entries);
-	rei->merge_renames = get_renames(o, merge_pairs, merge,
+	rei->merge_renames = get_renames(o, merge_pairs,
+					 dir_re_head, merge,
 					 common, head, merge, entries);
 	*clean = process_renames(o, rei->head_renames, rei->merge_renames);
 

-- 
2.15.0.5.g9567be9905