[PATCH v8 00/29] Add directory rename detection to git

@@ -439,4 +439,147 @@ test_expect_failure '1f-check: Split a directory into two other directories' '
 #   in section 2, plus testcases 3a and 4a.
 ###########################################################################
 
+
+###########################################################################
+# SECTION 2: Split into multiple directories, with equal number of paths
+#
+# Explore the splitting-a-directory rules a bit; what happens in the
+# edge cases?
+#
+# Note that there is a closely related case of a directory not being
+# split on either side of history, but being renamed differently on
+# each side.  See testcase 8e for that.
+###########################################################################
+
+# Testcase 2a, Directory split into two on one side, with equal numbers of paths
+#   Commit O: z/{b,c}
+#   Commit A: y/b, w/c
+#   Commit B: z/{b,c,d}
+#   Expected: y/b, w/c, z/d, with warning about z/ -> (y/ vs. w/) conflict
+test_expect_success '2a-setup: Directory split into two on one side, with equal numbers of paths' '
+	test_create_repo 2a &&
+	(
+		cd 2a &&
+
+		mkdir z &&
+		echo b >z/b &&
+		echo c >z/c &&
+		git add z &&
+		test_tick &&
+		git commit -m "O" &&
+
+		git branch O &&
+		git branch A &&
+		git branch B &&
+
+		git checkout A &&
+		mkdir y &&
+		mkdir w &&
+		git mv z/b y/ &&
+		git mv z/c w/ &&
+		test_tick &&
+		git commit -m "A" &&
+
+		git checkout B &&
+		echo d >z/d &&
+		git add z/d &&
+		test_tick &&
+		git commit -m "B"
+	)
+'
+
+test_expect_failure '2a-check: Directory split into two on one side, with equal numbers of paths' '
+	(
+		cd 2a &&
+
+		git checkout A^0 &&
+
+		test_must_fail git merge -s recursive B^0 >out &&
+		test_i18ngrep "CONFLICT.*directory rename split" out &&
+
+		git ls-files -s >out &&
+		test_line_count = 3 out &&
+		git ls-files -u >out &&
+		test_line_count = 0 out &&
+		git ls-files -o >out &&
+		test_line_count = 1 out &&
+
+		git rev-parse >actual \
+			:0:y/b :0:w/c :0:z/d &&
+		git rev-parse >expect \
+			 O:z/b  O:z/c  B:z/d &&
+		test_cmp expect actual
+	)
+'
+
+# Testcase 2b, Directory split into two on one side, with equal numbers of paths
+#   Commit O: z/{b,c}
+#   Commit A: y/b, w/c
+#   Commit B: z/{b,c}, x/d
+#   Expected: y/b, w/c, x/d; No warning about z/ -> (y/ vs. w/) conflict
+test_expect_success '2b-setup: Directory split into two on one side, with equal numbers of paths' '
+	test_create_repo 2b &&
+	(
+		cd 2b &&
+
+		mkdir z &&
+		echo b >z/b &&
+		echo c >z/c &&
+		git add z &&
+		test_tick &&
+		git commit -m "O" &&
+
+		git branch O &&
+		git branch A &&
+		git branch B &&
+
+		git checkout A &&
+		mkdir y &&
+		mkdir w &&
+		git mv z/b y/ &&
+		git mv z/c w/ &&
+		test_tick &&
+		git commit -m "A" &&
+
+		git checkout B &&
+		mkdir x &&
+		echo d >x/d &&
+		git add x/d &&
+		test_tick &&
+		git commit -m "B"
+	)
+'
+
+test_expect_success '2b-check: Directory split into two on one side, with equal numbers of paths' '
+	(
+		cd 2b &&
+
+		git checkout A^0 &&
+
+		git merge -s recursive B^0 >out &&
+
+		git ls-files -s >out &&
+		test_line_count = 3 out &&
+		git ls-files -u >out &&
+		test_line_count = 0 out &&
+		git ls-files -o >out &&
+		test_line_count = 1 out &&
+
+		git rev-parse >actual \
+			:0:y/b :0:w/c :0:x/d &&
+		git rev-parse >expect \
+			 O:z/b  O:z/c  B:x/d &&
+		test_cmp expect actual &&
+		test_i18ngrep ! "CONFLICT.*directory rename split" out
+	)
+'
+
+###########################################################################
+# Rules suggested by section 2:
+#
+#   None; the rule was already covered in section 1.  These testcases are
+#   here just to make sure the conflict resolution and necessary warning
+#   messages are handled correctly.
+###########################################################################
+
 test_done

@@ -1667,6 +1667,12 @@ struct rename_info {
 	struct string_list *merge_renames;
 };
 
+static void initial_cleanup_rename(struct diff_queue_struct *pairs)
+{
+	free(pairs->queue);
+	free(pairs);
+}
+
 static int handle_renames(struct merge_options *o,
 			  struct tree *common,
 			  struct tree *head,

@@ -1697,16 +1703,13 @@ static int handle_renames(struct merge_options *o,
 	 * data structures are still needed and referenced in
 	 * process_entry().  But there are a few things we can free now.
 	 */
-
-	free(head_pairs->queue);
-	free(head_pairs);
-	free(merge_pairs->queue);
-	free(merge_pairs);
+	initial_cleanup_rename(head_pairs);
+	initial_cleanup_rename(merge_pairs);
 
 	return clean;
 }
 
-static void cleanup_rename(struct string_list *rename)
+static void final_cleanup_rename(struct string_list *rename)
 {
 	const struct rename *re;
 	int i;

@@ -1722,10 +1725,10 @@ static void cleanup_rename(struct string_list *rename)
 	free(rename);
 }
 
-static void cleanup_renames(struct rename_info *re_info)
+static void final_cleanup_renames(struct rename_info *re_info)
 {
-	cleanup_rename(re_info->head_renames);
-	cleanup_rename(re_info->merge_renames);
+	final_cleanup_rename(re_info->head_renames);
+	final_cleanup_rename(re_info->merge_renames);
 }
 
 static struct object_id *stage_oid(const struct object_id *oid, unsigned mode)

@@ -2128,7 +2131,7 @@ int merge_trees(struct merge_options *o,
 		}
 
 cleanup:
-		cleanup_renames(&re_info);
+		final_cleanup_renames(&re_info);
 
 		string_list_clear(entries, 1);
 		free(entries);

@@ -1323,11 +1323,22 @@ static int handle_file(struct merge_options *o,
 
 	add = filespec_from_entry(&other, dst_entry, stage ^ 1);
 	if (add) {
+		int ren_src_was_dirty = was_dirty(o, rename->path);
 		char *add_name = unique_path(o, rename->path, other_branch);
 		if (update_file(o, 0, &add->oid, add->mode, add_name))
 			return -1;
 
-		remove_file(o, 0, rename->path, 0);
+		if (ren_src_was_dirty) {
+			output(o, 1, _("Refusing to lose dirty file at %s"),
+			       rename->path);
+		}
+		/*
+		 * Because the double negatives somehow keep confusing me...
+		 *    1) update_wd iff !ren_src_was_dirty.
+		 *    2) no_wd iff !update_wd
+		 *    3) so, no_wd == !!ren_src_was_dirty == ren_src_was_dirty
+		 */
+		remove_file(o, 0, rename->path, ren_src_was_dirty);
 		dst_name = unique_path(o, rename->path, cur_branch);
 	} else {
 		if (dir_in_way(rename->path, !o->call_depth, 0)) {

@@ -1465,7 +1476,10 @@ static int conflict_rename_rename_2to1(struct merge_options *o,
 		char *new_path2 = unique_path(o, path, ci->branch2);
 		output(o, 1, _("Renaming %s to %s and %s to %s instead"),
 		       a->path, new_path1, b->path, new_path2);
-		if (would_lose_untracked(path))
+		if (was_dirty(o, path))
+			output(o, 1, _("Refusing to lose dirty file at %s"),
+			       path);
+		else if (would_lose_untracked(path))
 			/*
 			 * Only way we get here is if both renames were from
 			 * a directory rename AND user had an untracked file

@@ -2074,6 +2088,7 @@ static void apply_directory_rename_modifications(struct merge_options *o,
 {
 	struct string_list_item *item;
 	int stage = (tree == a_tree ? 2 : 3);
+	int update_wd;
 
 	/*
 	 * In all cases where we can do directory rename detection,

@@ -2084,7 +2099,11 @@ static void apply_directory_rename_modifications(struct merge_options *o,
 	 * saying the file would have been overwritten), but it might
 	 * be dirty, though.
 	 */
-	remove_file(o, 1, pair->two->path, 0 /* no_wd */);
+	update_wd = !was_dirty(o, pair->two->path);
+	if (!update_wd)
+		output(o, 1, _("Refusing to lose dirty file at %s"),
+		       pair->two->path);
+	remove_file(o, 1, pair->two->path, !update_wd);
 
 	/* Find or create a new re->dst_entry */
 	item = string_list_lookup(entries, new_path);

@@ -3370,7 +3370,7 @@ test_expect_success '11b-setup: Avoid losing dirty file involved in directory re
 	)
 '
 
-test_expect_failure '11b-check: Avoid losing dirty file involved in directory rename' '
+test_expect_success '11b-check: Avoid losing dirty file involved in directory rename' '
 	(
 		cd 11b &&
 

@@ -3512,7 +3512,7 @@ test_expect_success '11d-setup: Avoid losing not-uptodate with rename + D/F conf
 	)
 '
 
-test_expect_failure '11d-check: Avoid losing not-uptodate with rename + D/F conflict' '
+test_expect_success '11d-check: Avoid losing not-uptodate with rename + D/F conflict' '
 	(
 		cd 11d &&
 

@@ -3591,7 +3591,7 @@ test_expect_success '11e-setup: Avoid deleting not-uptodate with dir rename/rena
 	)
 '
 
-test_expect_failure '11e-check: Avoid deleting not-uptodate with dir rename/rename(1to2)/add' '
+test_expect_success '11e-check: Avoid deleting not-uptodate with dir rename/rename(1to2)/add' '
 	(
 		cd 11e &&
 

@@ -3667,7 +3667,7 @@ test_expect_success '11f-setup: Avoid deleting not-uptodate with dir rename/rena
 	)
 '
 
-test_expect_failure '11f-check: Avoid deleting not-uptodate with dir rename/rename(2to1)' '
+test_expect_success '11f-check: Avoid deleting not-uptodate with dir rename/rename(2to1)' '
 	(
 		cd 11f &&
 

@@ -1394,6 +1394,15 @@ static struct diff_queue_struct *get_diffpairs(struct merge_options *o,
 	return ret;
 }
 
+static int tree_has_path(struct tree *tree, const char *path)
+{
+	unsigned char hashy[GIT_MAX_RAWSZ];
+	unsigned int mode_o;
+
+	return !get_tree_entry(tree->object.oid.hash, path,
+			       hashy, &mode_o);
+}
+
 static void get_renamed_dir_portion(const char *old_path, const char *new_path,
 				    char **old_dir, char **new_dir)
 {

@@ -1449,6 +1458,112 @@ static void get_renamed_dir_portion(const char *old_path, const char *new_path,
 	}
 }
 
+static void remove_hashmap_entries(struct hashmap *dir_renames,
+				   struct string_list *items_to_remove)
+{
+	int i;
+	struct dir_rename_entry *entry;
+
+	for (i = 0; i < items_to_remove->nr; i++) {
+		entry = items_to_remove->items[i].util;
+		hashmap_remove(dir_renames, entry, NULL);
+	}
+	string_list_clear(items_to_remove, 0);
+}
+
+/*
+ * There are a couple things we want to do at the directory level:
+ *   1. Check for both sides renaming to the same thing, in order to avoid
+ *      implicit renaming of files that should be left in place.  (See
+ *      testcase 6b in t6043 for details.)
+ *   2. Prune directory renames if there are still files left in the
+ *      the original directory.  These represent a partial directory rename,
+ *      i.e. a rename where only some of the files within the directory
+ *      were renamed elsewhere.  (Technically, this could be done earlier
+ *      in get_directory_renames(), except that would prevent us from
+ *      doing the previous check and thus failing testcase 6b.)
+ *   3. Check for rename/rename(1to2) conflicts (at the directory level).
+ *      In the future, we could potentially record this info as well and
+ *      omit reporting rename/rename(1to2) conflicts for each path within
+ *      the affected directories, thus cleaning up the merge output.
+ *   NOTE: We do NOT check for rename/rename(2to1) conflicts at the
+ *         directory level, because merging directories is fine.  If it
+ *         causes conflicts for files within those merged directories, then
+ *         that should be detected at the individual path level.
+ */
+static void handle_directory_level_conflicts(struct merge_options *o,
+					     struct hashmap *dir_re_head,
+					     struct tree *head,
+					     struct hashmap *dir_re_merge,
+					     struct tree *merge)
+{
+	struct hashmap_iter iter;
+	struct dir_rename_entry *head_ent;
+	struct dir_rename_entry *merge_ent;
+
+	struct string_list remove_from_head = STRING_LIST_INIT_NODUP;
+	struct string_list remove_from_merge = STRING_LIST_INIT_NODUP;
+
+	hashmap_iter_init(dir_re_head, &iter);
+	while ((head_ent = hashmap_iter_next(&iter))) {
+		merge_ent = dir_rename_find_entry(dir_re_merge, head_ent->dir);
+		if (merge_ent &&
+		    !head_ent->non_unique_new_dir &&
+		    !merge_ent->non_unique_new_dir &&
+		    !strbuf_cmp(&head_ent->new_dir, &merge_ent->new_dir)) {
+			/* 1. Renamed identically; remove it from both sides */
+			string_list_append(&remove_from_head,
+					   head_ent->dir)->util = head_ent;
+			strbuf_release(&head_ent->new_dir);
+			string_list_append(&remove_from_merge,
+					   merge_ent->dir)->util = merge_ent;
+			strbuf_release(&merge_ent->new_dir);
+		} else if (tree_has_path(head, head_ent->dir)) {
+			/* 2. This wasn't a directory rename after all */
+			string_list_append(&remove_from_head,
+					   head_ent->dir)->util = head_ent;
+			strbuf_release(&head_ent->new_dir);
+		}
+	}
+
+	remove_hashmap_entries(dir_re_head, &remove_from_head);
+	remove_hashmap_entries(dir_re_merge, &remove_from_merge);
+
+	hashmap_iter_init(dir_re_merge, &iter);
+	while ((merge_ent = hashmap_iter_next(&iter))) {
+		head_ent = dir_rename_find_entry(dir_re_head, merge_ent->dir);
+		if (tree_has_path(merge, merge_ent->dir)) {
+			/* 2. This wasn't a directory rename after all */
+			string_list_append(&remove_from_merge,
+					   merge_ent->dir)->util = merge_ent;
+		} else if (head_ent &&
+			   !head_ent->non_unique_new_dir &&
+			   !merge_ent->non_unique_new_dir) {
+			/* 3. rename/rename(1to2) */
+			/*
+			 * We can assume it's not rename/rename(1to1) because
+			 * that was case (1), already checked above.  So we
+			 * know that head_ent->new_dir and merge_ent->new_dir
+			 * are different strings.
+			 */
+			output(o, 1, _("CONFLICT (rename/rename): "
+				       "Rename directory %s->%s in %s. "
+				       "Rename directory %s->%s in %s"),
+			       head_ent->dir, head_ent->new_dir.buf, o->branch1,
+			       head_ent->dir, merge_ent->new_dir.buf, o->branch2);
+			string_list_append(&remove_from_head,
+					   head_ent->dir)->util = head_ent;
+			strbuf_release(&head_ent->new_dir);
+			string_list_append(&remove_from_merge,
+					   merge_ent->dir)->util = merge_ent;
+			strbuf_release(&merge_ent->new_dir);
+		}
+	}
+
+	remove_hashmap_entries(dir_re_head, &remove_from_head);
+	remove_hashmap_entries(dir_re_merge, &remove_from_merge);
+}
+
 static struct hashmap *get_directory_renames(struct diff_queue_struct *pairs,
 					     struct tree *tree)
 {

@@ -1910,6 +2025,10 @@ static int handle_renames(struct merge_options *o,
 	dir_re_head = get_directory_renames(head_pairs, head);
 	dir_re_merge = get_directory_renames(merge_pairs, merge);
 
+	handle_directory_level_conflicts(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,

@@ -49,6 +49,44 @@ static unsigned int path_hash(const char *path)
 	return ignore_case ? strihash(path) : strhash(path);
 }
 
+static struct dir_rename_entry *dir_rename_find_entry(struct hashmap *hashmap,
+						      char *dir)
+{
+	struct dir_rename_entry key;
+
+	if (dir == NULL)
+		return NULL;
+	hashmap_entry_init(&key, strhash(dir));
+	key.dir = dir;
+	return hashmap_get(hashmap, &key, NULL);
+}
+
+static int dir_rename_cmp(const void *unused_cmp_data,
+			  const void *entry,
+			  const void *entry_or_key,
+			  const void *unused_keydata)
+{
+	const struct dir_rename_entry *e1 = entry;
+	const struct dir_rename_entry *e2 = entry_or_key;
+
+	return strcmp(e1->dir, e2->dir);
+}
+
+static void dir_rename_init(struct hashmap *map)
+{
+	hashmap_init(map, dir_rename_cmp, NULL, 0);
+}
+
+static void dir_rename_entry_init(struct dir_rename_entry *entry,
+				  char *directory)
+{
+	hashmap_entry_init(entry, strhash(directory));
+	entry->dir = directory;
+	entry->non_unique_new_dir = 0;
+	strbuf_init(&entry->new_dir, 0);
+	string_list_init(&entry->possible_new_dirs, 0);
+}
+
 static void flush_output(struct merge_options *o)
 {
 	if (o->buffer_output < 2 && o->obuf.len) {

@@ -1356,6 +1394,169 @@ static struct diff_queue_struct *get_diffpairs(struct merge_options *o,
 	return ret;
 }
 
+static void get_renamed_dir_portion(const char *old_path, const char *new_path,
+				    char **old_dir, char **new_dir)
+{
+	char *end_of_old, *end_of_new;
+	int old_len, new_len;
+
+	*old_dir = NULL;
+	*new_dir = NULL;
+
+	/*
+	 * For
+	 *    "a/b/c/d/e/foo.c" -> "a/b/some/thing/else/e/foo.c"
+	 * the "e/foo.c" part is the same, we just want to know that
+	 *    "a/b/c/d" was renamed to "a/b/some/thing/else"
+	 * so, for this example, this function returns "a/b/c/d" in
+	 * *old_dir and "a/b/some/thing/else" in *new_dir.
+	 *
+	 * Also, if the basename of the file changed, we don't care.  We
+	 * want to know which portion of the directory, if any, changed.
+	 */
+	end_of_old = strrchr(old_path, '/');
+	end_of_new = strrchr(new_path, '/');
+
+	if (end_of_old == NULL || end_of_new == NULL)
+		return;
+	while (*--end_of_new == *--end_of_old &&
+	       end_of_old != old_path &&
+	       end_of_new != new_path)
+		; /* Do nothing; all in the while loop */
+	/*
+	 * We've found the first non-matching character in the directory
+	 * paths.  That means the current directory we were comparing
+	 * represents the rename.  Move end_of_old and end_of_new back
+	 * to the full directory name.
+	 */
+	if (*end_of_old == '/')
+		end_of_old++;
+	if (*end_of_old != '/')
+		end_of_new++;
+	end_of_old = strchr(end_of_old, '/');
+	end_of_new = strchr(end_of_new, '/');
+
+	/*
+	 * It may have been the case that old_path and new_path were the same
+	 * directory all along.  Don't claim a rename if they're the same.
+	 */
+	old_len = end_of_old - old_path;
+	new_len = end_of_new - new_path;
+
+	if (old_len != new_len || strncmp(old_path, new_path, old_len)) {
+		*old_dir = xstrndup(old_path, old_len);
+		*new_dir = xstrndup(new_path, new_len);
+	}
+}
+
+static struct hashmap *get_directory_renames(struct diff_queue_struct *pairs,
+					     struct tree *tree)
+{
+	struct hashmap *dir_renames;
+	struct hashmap_iter iter;
+	struct dir_rename_entry *entry;
+	int i;
+
+	/*
+	 * Typically, we think of a directory rename as all files from a
+	 * certain directory being moved to a target directory.  However,
+	 * what if someone first moved two files from the original
+	 * directory in one commit, and then renamed the directory
+	 * somewhere else in a later commit?  At merge time, we just know
+	 * that files from the original directory went to two different
+	 * places, and that the bulk of them ended up in the same place.
+	 * We want each directory rename to represent where the bulk of the
+	 * files from that directory end up; this function exists to find
+	 * where the bulk of the files went.
+	 *
+	 * The first loop below simply iterates through the list of file
+	 * renames, finding out how often each directory rename pair
+	 * possibility occurs.
+	 */
+	dir_renames = xmalloc(sizeof(struct hashmap));
+	dir_rename_init(dir_renames);
+	for (i = 0; i < pairs->nr; ++i) {
+		struct string_list_item *item;
+		int *count;
+		struct diff_filepair *pair = pairs->queue[i];
+		char *old_dir, *new_dir;
+
+		/* File not part of directory rename if it wasn't renamed */
+		if (pair->status != 'R')
+			continue;
+
+		get_renamed_dir_portion(pair->one->path, pair->two->path,
+					&old_dir,        &new_dir);
+		if (!old_dir)
+			/* Directory didn't change at all; ignore this one. */
+			continue;
+
+		entry = dir_rename_find_entry(dir_renames, old_dir);
+		if (!entry) {
+			entry = xmalloc(sizeof(struct dir_rename_entry));
+			dir_rename_entry_init(entry, old_dir);
+			hashmap_put(dir_renames, entry);
+		} else {
+			free(old_dir);
+		}
+		item = string_list_lookup(&entry->possible_new_dirs, new_dir);
+		if (!item) {
+			item = string_list_insert(&entry->possible_new_dirs,
+						  new_dir);
+			item->util = xcalloc(1, sizeof(int));
+		} else {
+			free(new_dir);
+		}
+		count = item->util;
+		*count += 1;
+	}
+
+	/*
+	 * For each directory with files moved out of it, we find out which
+	 * target directory received the most files so we can declare it to
+	 * be the "winning" target location for the directory rename.  This
+	 * winner gets recorded in new_dir.  If there is no winner
+	 * (multiple target directories received the same number of files),
+	 * we set non_unique_new_dir.  Once we've determined the winner (or
+	 * that there is no winner), we no longer need possible_new_dirs.
+	 */
+	hashmap_iter_init(dir_renames, &iter);
+	while ((entry = hashmap_iter_next(&iter))) {
+		int max = 0;
+		int bad_max = 0;
+		char *best = NULL;
+
+		for (i = 0; i < entry->possible_new_dirs.nr; i++) {
+			int *count = entry->possible_new_dirs.items[i].util;
+
+			if (*count == max)
+				bad_max = max;
+			else if (*count > max) {
+				max = *count;
+				best = entry->possible_new_dirs.items[i].string;
+			}
+		}
+		if (bad_max == max)
+			entry->non_unique_new_dir = 1;
+		else {
+			assert(entry->new_dir.len == 0);
+			strbuf_addstr(&entry->new_dir, best);
+		}
+		/*
+		 * The relevant directory sub-portion of the original full
+		 * filepaths were xstrndup'ed before inserting into
+		 * possible_new_dirs, and instead of manually iterating the
+		 * list and free'ing each, just lie and tell
+		 * possible_new_dirs that it did the strdup'ing so that it
+		 * will free them for us.
+		 */
+		entry->possible_new_dirs.strdup_strings = 1;
+		string_list_clear(&entry->possible_new_dirs, 1);
+	}
+
+	return dir_renames;
+}
+
 /*
  * Get information of all renames which occurred in 'pairs', making use of
  * any implicit directory renames inferred from the other side of history.

@@ -1667,8 +1868,21 @@ struct rename_info {
 	struct string_list *merge_renames;
 };
 
-static void initial_cleanup_rename(struct diff_queue_struct *pairs)
+static void initial_cleanup_rename(struct diff_queue_struct *pairs,
+				   struct hashmap *dir_renames)
 {
+	struct hashmap_iter iter;
+	struct dir_rename_entry *e;
+
+	hashmap_iter_init(dir_renames, &iter);
+	while ((e = hashmap_iter_next(&iter))) {
+		free(e->dir);
+		strbuf_release(&e->new_dir);
+		/* possible_new_dirs already cleared in get_directory_renames */
+	}
+	hashmap_free(dir_renames, 1);
+	free(dir_renames);
+
 	free(pairs->queue);
 	free(pairs);
 }

@@ -1681,6 +1895,7 @@ static int handle_renames(struct merge_options *o,
 			  struct rename_info *ri)
 {
 	struct diff_queue_struct *head_pairs, *merge_pairs;
+	struct hashmap *dir_re_head, *dir_re_merge;
 	int clean;
 
 	ri->head_renames = NULL;

@@ -1692,6 +1907,9 @@ static int handle_renames(struct merge_options *o,
 	head_pairs = get_diffpairs(o, common, head);
 	merge_pairs = get_diffpairs(o, common, merge);
 
+	dir_re_head = get_directory_renames(head_pairs, head);
+	dir_re_merge = get_directory_renames(merge_pairs, merge);
+
 	ri->head_renames  = get_renames(o, head_pairs, head,
 					 common, head, merge, entries);
 	ri->merge_renames = get_renames(o, merge_pairs, merge,

@@ -1703,8 +1921,8 @@ static int handle_renames(struct merge_options *o,
 	 * data structures are still needed and referenced in
 	 * process_entry().  But there are a few things we can free now.
 	 */
-	initial_cleanup_rename(head_pairs);
-	initial_cleanup_rename(merge_pairs);
+	initial_cleanup_rename(head_pairs, dir_re_head);
+	initial_cleanup_rename(merge_pairs, dir_re_merge);
 
 	return clean;
 }

@@ -29,6 +29,24 @@ struct merge_options {
 	struct string_list df_conflict_file_set;
 };
 
+/*
+ * For dir_rename_entry, directory names are stored as a full path from the
+ * toplevel of the repository and do not include a trailing '/'.  Also:
+ *
+ *   dir:                original name of directory being renamed
+ *   non_unique_new_dir: if true, could not determine new_dir
+ *   new_dir:            final name of directory being renamed
+ *   possible_new_dirs:  temporary used to help determine new_dir; see comments
+ *                       in get_directory_renames() for details
+ */
+struct dir_rename_entry {
+	struct hashmap_entry ent; /* must be the first member! */
+	char *dir;
+	unsigned non_unique_new_dir:1;
+	struct strbuf new_dir;
+	struct string_list possible_new_dirs;
+};
+
 /* merge_trees() but with recursive ancestor consolidation */
 int merge_recursive(struct merge_options *o,
 		    struct commit *h1,

@@ -850,4 +850,334 @@ test_expect_success '4a-check: Directory split, with original directory still pr
 #   detection.)  But, sadly, see testcase 8b.
 ###########################################################################
 
+
+###########################################################################
+# SECTION 5: Files/directories in the way of subset of to-be-renamed paths
+#
+# Implicitly renaming files due to a detected directory rename could run
+# into problems if there are files or directories in the way of the paths
+# we want to rename.  Explore such cases in this section.
+###########################################################################
+
+# Testcase 5a, Merge directories, other side adds files to original and target
+#   Commit O: z/{b,c},       y/d
+#   Commit A: z/{b,c,e_1,f}, y/{d,e_2}
+#   Commit B: y/{b,c,d}
+#   Expected: z/e_1, y/{b,c,d,e_2,f} + CONFLICT warning
+#   NOTE: While directory rename detection is active here causing z/f to
+#         become y/f, we did not apply this for z/e_1 because that would
+#         give us an add/add conflict for y/e_1 vs y/e_2.  This problem with
+#         this add/add, is that both versions of y/e are from the same side
+#         of history, giving us no way to represent this conflict in the
+#         index.
+
+test_expect_success '5a-setup: Merge directories, other side adds files to original and target' '
+	test_create_repo 5a &&
+	(
+		cd 5a &&
+
+		mkdir z &&
+		echo b >z/b &&
+		echo c >z/c &&
+		mkdir y &&
+		echo d >y/d &&
+		git add z y &&
+		test_tick &&
+		git commit -m "O" &&
+
+		git branch O &&
+		git branch A &&
+		git branch B &&
+
+		git checkout A &&
+		echo e1 >z/e &&
+		echo f >z/f &&
+		echo e2 >y/e &&
+		git add z/e z/f y/e &&
+		test_tick &&
+		git commit -m "A" &&
+
+		git checkout B &&
+		git mv z/b y/ &&
+		git mv z/c y/ &&
+		rmdir z &&
+		test_tick &&
+		git commit -m "B"
+	)
+'
+
+test_expect_failure '5a-check: Merge directories, other side adds files to original and target' '
+	(
+		cd 5a &&
+
+		git checkout A^0 &&
+
+		test_must_fail git merge -s recursive B^0 >out &&
+		test_i18ngrep "CONFLICT.*implicit dir rename" out &&
+
+		git ls-files -s >out &&
+		test_line_count = 6 out &&
+		git ls-files -u >out &&
+		test_line_count = 0 out &&
+		git ls-files -o >out &&
+		test_line_count = 1 out &&
+
+		git rev-parse >actual \
+			:0:y/b :0:y/c :0:y/d :0:y/e :0:z/e :0:y/f &&
+		git rev-parse >expect \
+			 O:z/b  O:z/c  O:y/d  A:y/e  A:z/e  A:z/f &&
+		test_cmp expect actual
+	)
+'
+
+# Testcase 5b, Rename/delete in order to get add/add/add conflict
+#   (Related to testcase 8d; these may appear slightly inconsistent to users;
+#    Also related to testcases 7d and 7e)
+#   Commit O: z/{b,c,d_1}
+#   Commit A: y/{b,c,d_2}
+#   Commit B: z/{b,c,d_1,e}, y/d_3
+#   Expected: y/{b,c,e}, CONFLICT(add/add: y/d_2 vs. y/d_3)
+#   NOTE: If z/d_1 in commit B were to be involved in dir rename detection, as
+#         we normaly would since z/ is being renamed to y/, then this would be
+#         a rename/delete (z/d_1 -> y/d_1 vs. deleted) AND an add/add/add
+#         conflict of y/d_1 vs. y/d_2 vs. y/d_3.  Add/add/add is not
+#         representable in the index, so the existence of y/d_3 needs to
+#         cause us to bail on directory rename detection for that path, falling
+#         back to git behavior without the directory rename detection.
+
+test_expect_success '5b-setup: Rename/delete in order to get add/add/add conflict' '
+	test_create_repo 5b &&
+	(
+		cd 5b &&
+
+		mkdir z &&
+		echo b >z/b &&
+		echo c >z/c &&
+		echo d1 >z/d &&
+		git add z &&
+		test_tick &&
+		git commit -m "O" &&
+
+		git branch O &&
+		git branch A &&
+		git branch B &&
+
+		git checkout A &&
+		git rm z/d &&
+		git mv z y &&
+		echo d2 >y/d &&
+		git add y/d &&
+		test_tick &&
+		git commit -m "A" &&
+
+		git checkout B &&
+		mkdir y &&
+		echo d3 >y/d &&
+		echo e >z/e &&
+		git add y/d z/e &&
+		test_tick &&
+		git commit -m "B"
+	)
+'
+
+test_expect_failure '5b-check: Rename/delete in order to get add/add/add conflict' '
+	(
+		cd 5b &&
+
+		git checkout A^0 &&
+
+		test_must_fail git merge -s recursive B^0 >out &&
+		test_i18ngrep "CONFLICT (add/add).* y/d" out &&
+
+		git ls-files -s >out &&
+		test_line_count = 5 out &&
+		git ls-files -u >out &&
+		test_line_count = 2 out &&
+		git ls-files -o >out &&
+		test_line_count = 1 out &&
+
+		git rev-parse >actual \
+			:0:y/b :0:y/c :0:y/e :2:y/d :3:y/d &&
+		git rev-parse >expect \
+			 O:z/b  O:z/c  B:z/e  A:y/d  B:y/d &&
+		test_cmp expect actual &&
+
+		test_must_fail git rev-parse :1:y/d &&
+		test_path_is_file y/d
+	)
+'
+
+# Testcase 5c, Transitive rename would cause rename/rename/rename/add/add/add
+#   (Directory rename detection would result in transitive rename vs.
+#    rename/rename(1to2) and turn it into a rename/rename(1to3).  Further,
+#    rename paths conflict with separate adds on the other side)
+#   (Related to testcases 3b and 7c)
+#   Commit O: z/{b,c}, x/d_1
+#   Commit A: y/{b,c,d_2}, w/d_1
+#   Commit B: z/{b,c,d_1,e}, w/d_3, y/d_4
+#   Expected: A mess, but only a rename/rename(1to2)/add/add mess.  Use the
+#             presence of y/d_4 in B to avoid doing transitive rename of
+#             x/d_1 -> z/d_1 -> y/d_1, so that the only paths we have at
+#             y/d are y/d_2 and y/d_4.  We still do the move from z/e to y/e,
+#             though, because it doesn't have anything in the way.
+
+test_expect_success '5c-setup: Transitive rename would cause rename/rename/rename/add/add/add' '
+	test_create_repo 5c &&
+	(
+		cd 5c &&
+
+		mkdir z &&
+		echo b >z/b &&
+		echo c >z/c &&
+		mkdir x &&
+		echo d1 >x/d &&
+		git add z x &&
+		test_tick &&
+		git commit -m "O" &&
+
+		git branch O &&
+		git branch A &&
+		git branch B &&
+
+		git checkout A &&
+		git mv z y &&
+		echo d2 >y/d &&
+		git add y/d &&
+		git mv x w &&
+		test_tick &&
+		git commit -m "A" &&
+
+		git checkout B &&
+		git mv x/d z/ &&
+		mkdir w &&
+		mkdir y &&
+		echo d3 >w/d &&
+		echo d4 >y/d &&
+		echo e >z/e &&
+		git add w/ y/ z/e &&
+		test_tick &&
+		git commit -m "B"
+	)
+'
+
+test_expect_failure '5c-check: Transitive rename would cause rename/rename/rename/add/add/add' '
+	(
+		cd 5c &&
+
+		git checkout A^0 &&
+
+		test_must_fail git merge -s recursive B^0 >out &&
+		test_i18ngrep "CONFLICT (rename/rename).*x/d.*w/d.*z/d" out &&
+		test_i18ngrep "CONFLICT (add/add).* y/d" out &&
+
+		git ls-files -s >out &&
+		test_line_count = 9 out &&
+		git ls-files -u >out &&
+		test_line_count = 6 out &&
+		git ls-files -o >out &&
+		test_line_count = 3 out &&
+
+		git rev-parse >actual \
+			:0:y/b :0:y/c :0:y/e &&
+		git rev-parse >expect \
+			 O:z/b  O:z/c  B:z/e &&
+		test_cmp expect actual &&
+
+		test_must_fail git rev-parse :1:y/d &&
+		git rev-parse >actual \
+			:2:w/d :3:w/d :1:x/d :2:y/d :3:y/d :3:z/d &&
+		git rev-parse >expect \
+			 O:x/d  B:w/d  O:x/d  A:y/d  B:y/d  O:x/d &&
+		test_cmp expect actual &&
+
+		git hash-object >actual \
+			w/d~HEAD w/d~B^0 z/d &&
+		git rev-parse >expect \
+			O:x/d    B:w/d   O:x/d &&
+		test_cmp expect actual &&
+		test_path_is_missing x/d &&
+		test_path_is_file y/d &&
+		grep -q "<<<<" y/d  # conflict markers should be present
+	)
+'
+
+# Testcase 5d, Directory/file/file conflict due to directory rename
+#   Commit O: z/{b,c}
+#   Commit A: y/{b,c,d_1}
+#   Commit B: z/{b,c,d_2,f}, y/d/e
+#   Expected: y/{b,c,d/e,f}, z/d_2, CONFLICT(file/directory), y/d_1~HEAD
+#   Note: The fact that y/d/ exists in B makes us bail on directory rename
+#         detection for z/d_2, but that doesn't prevent us from applying the
+#         directory rename detection for z/f -> y/f.
+
+test_expect_success '5d-setup: Directory/file/file conflict due to directory rename' '
+	test_create_repo 5d &&
+	(
+		cd 5d &&
+
+		mkdir z &&
+		echo b >z/b &&
+		echo c >z/c &&
+		git add z &&
+		test_tick &&
+		git commit -m "O" &&
+
+		git branch O &&
+		git branch A &&
+		git branch B &&
+
+		git checkout A &&
+		git mv z y &&
+		echo d1 >y/d &&
+		git add y/d &&
+		test_tick &&
+		git commit -m "A" &&
+
+		git checkout B &&
+		mkdir -p y/d &&
+		echo e >y/d/e &&
+		echo d2 >z/d &&
+		echo f >z/f &&
+		git add y/d/e z/d z/f &&
+		test_tick &&
+		git commit -m "B"
+	)
+'
+
+test_expect_failure '5d-check: Directory/file/file conflict due to directory rename' '
+	(
+		cd 5d &&
+
+		git checkout A^0 &&
+
+		test_must_fail git merge -s recursive B^0 >out &&
+		test_i18ngrep "CONFLICT (file/directory).*y/d" out &&
+
+		git ls-files -s >out &&
+		test_line_count = 6 out &&
+		git ls-files -u >out &&
+		test_line_count = 1 out &&
+		git ls-files -o >out &&
+		test_line_count = 2 out &&
+
+		git rev-parse >actual \
+			:0:y/b :0:y/c :0:z/d :0:y/f :2:y/d :0:y/d/e &&
+		git rev-parse >expect \
+			 O:z/b  O:z/c  B:z/d  B:z/f  A:y/d  B:y/d/e &&
+		test_cmp expect actual &&
+
+		git hash-object y/d~HEAD >actual &&
+		git rev-parse A:y/d >expect &&
+		test_cmp expect actual
+	)
+'
+
+###########################################################################
+# Rules suggested by section 5:
+#
+#   If a subset of to-be-renamed files have a file or directory in the way,
+#   "turn off" the directory rename for those specific sub-paths, falling
+#   back to old handling.  But, sadly, see testcases 8a and 8b.
+###########################################################################
+
 test_done