Merge branch 'en/rename-directory-detection'

Rename detection logic in "diff" family that is used in "merge" has
learned to guess when all of x/a, x/b and x/c have moved to z/a,
z/b and z/c, it is likely that x/d added in the meantime would also
want to move to z/d by taking the hint that the entire directory
'x' moved to 'z'.  A bug causing dirty files involved in a rename
to be overwritten during merge has also been fixed as part of this
work.

* en/rename-directory-detection: (29 commits)
  merge-recursive: ensure we write updates for directory-renamed file
  merge-recursive: avoid spurious rename/rename conflict from dir renames
  directory rename detection: new testcases showcasing a pair of bugs
  merge-recursive: fix remaining directory rename + dirty overwrite cases
  merge-recursive: fix overwriting dirty files involved in renames
  merge-recursive: avoid clobbering untracked files with directory renames
  merge-recursive: apply necessary modifications for directory renames
  merge-recursive: when comparing files, don't include trees
  merge-recursive: check for file level conflicts then get new name
  merge-recursive: add computation of collisions due to dir rename & merging
  merge-recursive: check for directory level conflicts
  merge-recursive: add get_directory_renames()
  merge-recursive: make a helper function for cleanup for handle_renames
  merge-recursive: split out code for determining diff_filepairs
  merge-recursive: make !o->detect_rename codepath more obvious
  merge-recursive: fix leaks of allocated renames and diff_filepairs
  merge-recursive: introduce new functions to handle rename logic
  merge-recursive: move the get_renames() function
  directory rename detection: tests for handling overwriting dirty files
  directory rename detection: tests for handling overwriting untracked files
  ...

9 files changed, 5197 insertions, 115 deletions

diff --git a/merge-recursive.c b/merge-recursive.c
index 869092f7b9..55d1e779a0 100644
--- a/merge-recursive.c
+++ b/merge-recursive.c
@@ -49,6 +49,67 @@ 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 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) {
@@ -119,6 +180,7 @@ static int oid_eq(const struct object_id *a, const struct object_id *b)
 
 enum rename_type {
 	RENAME_NORMAL = 0,
+	RENAME_DIR,
 	RENAME_DELETE,
 	RENAME_ONE_FILE_TO_ONE,
 	RENAME_ONE_FILE_TO_TWO,
@@ -275,32 +337,37 @@ static void init_tree_desc_from_tree(struct tree_desc *desc, struct tree *tree)
 	init_tree_desc(desc, tree->buffer, tree->size);
 }
 
-static int git_merge_trees(int index_only,
+static int git_merge_trees(struct merge_options *o,
 			   struct tree *common,
 			   struct tree *head,
 			   struct tree *merge)
 {
 	int rc;
 	struct tree_desc t[3];
-	struct unpack_trees_options opts;
 
-	memset(&opts, 0, sizeof(opts));
-	if (index_only)
-		opts.index_only = 1;
+	memset(&o->unpack_opts, 0, sizeof(o->unpack_opts));
+	if (o->call_depth)
+		o->unpack_opts.index_only = 1;
 	else
-		opts.update = 1;
-	opts.merge = 1;
-	opts.head_idx = 2;
-	opts.fn = threeway_merge;
-	opts.src_index = &the_index;
-	opts.dst_index = &the_index;
-	setup_unpack_trees_porcelain(&opts, "merge");
+		o->unpack_opts.update = 1;
+	o->unpack_opts.merge = 1;
+	o->unpack_opts.head_idx = 2;
+	o->unpack_opts.fn = threeway_merge;
+	o->unpack_opts.src_index = &the_index;
+	o->unpack_opts.dst_index = &the_index;
+	setup_unpack_trees_porcelain(&o->unpack_opts, "merge");
 
 	init_tree_desc_from_tree(t+0, common);
 	init_tree_desc_from_tree(t+1, head);
 	init_tree_desc_from_tree(t+2, merge);
 
-	rc = unpack_trees(3, t, &opts);
+	rc = unpack_trees(3, t, &o->unpack_opts);
+	/*
+	 * unpack_trees NULLifies src_index, but it's used in verify_uptodate,
+	 * so set to the new index which will usually have modification
+	 * timestamp info copied over.
+	 */
+	o->unpack_opts.src_index = &the_index;
 	cache_tree_free(&active_cache_tree);
 	return rc;
 }
@@ -360,6 +427,21 @@ static void get_files_dirs(struct merge_options *o, struct tree *tree)
 	read_tree_recursive(tree, "", 0, 0, &match_all, save_files_dirs, o);
 }
 
+static int get_tree_entry_if_blob(const unsigned char *tree,
+				  const char *path,
+				  unsigned char *hashy,
+				  unsigned int *mode_o)
+{
+	int ret;
+
+	ret = get_tree_entry(tree, path, hashy, mode_o);
+	if (S_ISDIR(*mode_o)) {
+		hashcpy(hashy, null_sha1);
+		*mode_o = 0;
+	}
+	return ret;
+}
+
 /*
  * Returns an index_entry instance which doesn't have to correspond to
  * a real cache entry in Git's index.
@@ -370,12 +452,12 @@ static struct stage_data *insert_stage_data(const char *path,
 {
 	struct string_list_item *item;
 	struct stage_data *e = xcalloc(1, sizeof(struct stage_data));
-	get_tree_entry(o->object.oid.hash, path,
-			e->stages[1].oid.hash, &e->stages[1].mode);
-	get_tree_entry(a->object.oid.hash, path,
-			e->stages[2].oid.hash, &e->stages[2].mode);
-	get_tree_entry(b->object.oid.hash, path,
-			e->stages[3].oid.hash, &e->stages[3].mode);
+	get_tree_entry_if_blob(o->object.oid.hash, path,
+			       e->stages[1].oid.hash, &e->stages[1].mode);
+	get_tree_entry_if_blob(a->object.oid.hash, path,
+			       e->stages[2].oid.hash, &e->stages[2].mode);
+	get_tree_entry_if_blob(b->object.oid.hash, path,
+			       e->stages[3].oid.hash, &e->stages[3].mode);
 	item = string_list_insert(entries, path);
 	item->util = e;
 	return e;
@@ -534,78 +616,10 @@ struct rename {
 	 */
 	struct stage_data *src_entry;
 	struct stage_data *dst_entry;
+	unsigned add_turned_into_rename:1;
 	unsigned processed:1;
 };
 
-/*
- * Get information of all renames which occurred between 'o_tree' and
- * 'tree'. We need the three trees in the merge ('o_tree', 'a_tree' and
- * 'b_tree') to be able to associate the correct cache entries with
- * the rename information. 'tree' is always equal to either a_tree or b_tree.
- */
-static struct string_list *get_renames(struct merge_options *o,
-				       struct tree *tree,
-				       struct tree *o_tree,
-				       struct tree *a_tree,
-				       struct tree *b_tree,
-				       struct string_list *entries)
-{
-	int i;
-	struct string_list *renames;
-	struct diff_options opts;
-
-	renames = xcalloc(1, sizeof(struct string_list));
-	if (!o->detect_rename)
-		return renames;
-
-	diff_setup(&opts);
-	opts.flags.recursive = 1;
-	opts.flags.rename_empty = 0;
-	opts.detect_rename = DIFF_DETECT_RENAME;
-	opts.rename_limit = o->merge_rename_limit >= 0 ? o->merge_rename_limit :
-			    o->diff_rename_limit >= 0 ? o->diff_rename_limit :
-			    1000;
-	opts.rename_score = o->rename_score;
-	opts.show_rename_progress = o->show_rename_progress;
-	opts.output_format = DIFF_FORMAT_NO_OUTPUT;
-	diff_setup_done(&opts);
-	diff_tree_oid(&o_tree->object.oid, &tree->object.oid, "", &opts);
-	diffcore_std(&opts);
-	if (opts.needed_rename_limit > o->needed_rename_limit)
-		o->needed_rename_limit = opts.needed_rename_limit;
-	for (i = 0; i < diff_queued_diff.nr; ++i) {
-		struct string_list_item *item;
-		struct rename *re;
-		struct diff_filepair *pair = diff_queued_diff.queue[i];
-		if (pair->status != 'R') {
-			diff_free_filepair(pair);
-			continue;
-		}
-		re = xmalloc(sizeof(*re));
-		re->processed = 0;
-		re->pair = pair;
-		item = string_list_lookup(entries, re->pair->one->path);
-		if (!item)
-			re->src_entry = insert_stage_data(re->pair->one->path,
-					o_tree, a_tree, b_tree, entries);
-		else
-			re->src_entry = item->util;
-
-		item = string_list_lookup(entries, re->pair->two->path);
-		if (!item)
-			re->dst_entry = insert_stage_data(re->pair->two->path,
-					o_tree, a_tree, b_tree, entries);
-		else
-			re->dst_entry = item->util;
-		item = string_list_insert(renames, pair->one->path);
-		item->util = re;
-	}
-	opts.output_format = DIFF_FORMAT_NO_OUTPUT;
-	diff_queued_diff.nr = 0;
-	diff_flush(&opts);
-	return renames;
-}
-
 static int update_stages(struct merge_options *opt, const char *path,
 			 const struct diff_filespec *o,
 			 const struct diff_filespec *a,
@@ -637,6 +651,27 @@ static int update_stages(struct merge_options *opt, const char *path,
 	return 0;
 }
 
+static int update_stages_for_stage_data(struct merge_options *opt,
+					const char *path,
+					const struct stage_data *stage_data)
+{
+	struct diff_filespec o, a, b;
+
+	o.mode = stage_data->stages[1].mode;
+	oidcpy(&o.oid, &stage_data->stages[1].oid);
+
+	a.mode = stage_data->stages[2].mode;
+	oidcpy(&a.oid, &stage_data->stages[2].oid);
+
+	b.mode = stage_data->stages[3].mode;
+	oidcpy(&b.oid, &stage_data->stages[3].oid);
+
+	return update_stages(opt, path,
+			     is_null_oid(&o.oid) ? NULL : &o,
+			     is_null_oid(&a.oid) ? NULL : &a,
+			     is_null_oid(&b.oid) ? NULL : &b);
+}
+
 static void update_entry(struct stage_data *entry,
 			 struct diff_filespec *o,
 			 struct diff_filespec *a,
@@ -765,6 +800,20 @@ static int would_lose_untracked(const char *path)
 	return !was_tracked(path) && file_exists(path);
 }
 
+static int was_dirty(struct merge_options *o, const char *path)
+{
+	struct cache_entry *ce;
+	int dirty = 1;
+
+	if (o->call_depth || !was_tracked(path))
+		return !dirty;
+
+	ce = cache_file_exists(path, strlen(path), ignore_case);
+	dirty = (ce->ce_stat_data.sd_mtime.sec > 0 &&
+		 verify_uptodate(ce, &o->unpack_opts) != 0);
+	return dirty;
+}
+
 static int make_room_for_path(struct merge_options *o, const char *path)
 {
 	int status, i;
@@ -1114,6 +1163,38 @@ static int merge_file_one(struct merge_options *o,
 	return merge_file_1(o, &one, &a, &b, branch1, branch2, mfi);
 }
 
+static int conflict_rename_dir(struct merge_options *o,
+			       struct diff_filepair *pair,
+			       const char *rename_branch,
+			       const char *other_branch)
+{
+	const struct diff_filespec *dest = pair->two;
+
+	if (!o->call_depth && would_lose_untracked(dest->path)) {
+		char *alt_path = unique_path(o, dest->path, rename_branch);
+
+		output(o, 1, _("Error: Refusing to lose untracked file at %s; "
+			       "writing to %s instead."),
+		       dest->path, alt_path);
+		/*
+		 * Write the file in worktree at alt_path, but not in the
+		 * index.  Instead, write to dest->path for the index but
+		 * only at the higher appropriate stage.
+		 */
+		if (update_file(o, 0, &dest->oid, dest->mode, alt_path))
+			return -1;
+		free(alt_path);
+		return update_stages(o, dest->path, NULL,
+				     rename_branch == o->branch1 ? dest : NULL,
+				     rename_branch == o->branch1 ? NULL : dest);
+	}
+
+	/* Update dest->path both in index and in worktree */
+	if (update_file(o, 1, &dest->oid, dest->mode, dest->path))
+		return -1;
+	return 0;
+}
+
 static int handle_change_delete(struct merge_options *o,
 				 const char *path, const char *old_path,
 				 const struct object_id *o_oid, int o_mode,
@@ -1127,7 +1208,8 @@ static int handle_change_delete(struct merge_options *o,
 	const char *update_path = path;
 	int ret = 0;
 
-	if (dir_in_way(path, !o->call_depth, 0)) {
+	if (dir_in_way(path, !o->call_depth, 0) ||
+	    (!o->call_depth && would_lose_untracked(path))) {
 		update_path = alt_path = unique_path(o, path, change_branch);
 	}
 
@@ -1242,17 +1324,34 @@ 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)) {
 			dst_name = unique_path(o, rename->path, cur_branch);
 			output(o, 1, _("%s is a directory in %s adding as %s instead"),
 			       rename->path, other_branch, dst_name);
+		} else if (!o->call_depth &&
+			   would_lose_untracked(rename->path)) {
+			dst_name = unique_path(o, rename->path, cur_branch);
+			output(o, 1, _("Refusing to lose untracked file at %s; "
+				       "adding as %s instead"),
+			       rename->path, dst_name);
 		}
 	}
 	if ((ret = update_file(o, 0, &rename->oid, rename->mode, dst_name)))
@@ -1378,11 +1477,43 @@ 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);
-		remove_file(o, 0, path, 0);
+		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
+			 * at the location where both files end up after the
+			 * two directory renames.  See testcase 10d of t6043.
+			 */
+			output(o, 1, _("Refusing to lose untracked file at "
+				       "%s, even though it's in the way."),
+			       path);
+		else
+			remove_file(o, 0, path, 0);
 		ret = update_file(o, 0, &mfi_c1.oid, mfi_c1.mode, new_path1);
 		if (!ret)
 			ret = update_file(o, 0, &mfi_c2.oid, mfi_c2.mode,
 					  new_path2);
+		/*
+		 * unpack_trees() actually populates the index for us for
+		 * "normal" rename/rename(2to1) situtations so that the
+		 * correct entries are at the higher stages, which would
+		 * make the call below to update_stages_for_stage_data
+		 * unnecessary.  However, if either of the renames came
+		 * from a directory rename, then unpack_trees() will not
+		 * have gotten the right data loaded into the index, so we
+		 * need to do so now.  (While it'd be tempting to move this
+		 * call to update_stages_for_stage_data() to
+		 * apply_directory_rename_modifications(), that would break
+		 * our intermediate calls to would_lose_untracked() since
+		 * those rely on the current in-memory index.  See also the
+		 * big "NOTE" in update_stages()).
+		 */
+		if (update_stages_for_stage_data(o, path, ci->dst_entry1))
+			ret = -1;
+
 		free(new_path2);
 		free(new_path1);
 	}
@@ -1390,6 +1521,754 @@ static int conflict_rename_rename_2to1(struct merge_options *o,
 	return ret;
 }
 
+/*
+ * Get the diff_filepairs changed between o_tree and tree.
+ */
+static struct diff_queue_struct *get_diffpairs(struct merge_options *o,
+					       struct tree *o_tree,
+					       struct tree *tree)
+{
+	struct diff_queue_struct *ret;
+	struct diff_options opts;
+
+	diff_setup(&opts);
+	opts.flags.recursive = 1;
+	opts.flags.rename_empty = 0;
+	opts.detect_rename = DIFF_DETECT_RENAME;
+	opts.rename_limit = o->merge_rename_limit >= 0 ? o->merge_rename_limit :
+			    o->diff_rename_limit >= 0 ? o->diff_rename_limit :
+			    1000;
+	opts.rename_score = o->rename_score;
+	opts.show_rename_progress = o->show_rename_progress;
+	opts.output_format = DIFF_FORMAT_NO_OUTPUT;
+	diff_setup_done(&opts);
+	diff_tree_oid(&o_tree->object.oid, &tree->object.oid, "", &opts);
+	diffcore_std(&opts);
+	if (opts.needed_rename_limit > o->needed_rename_limit)
+		o->needed_rename_limit = opts.needed_rename_limit;
+
+	ret = xmalloc(sizeof(*ret));
+	*ret = diff_queued_diff;
+
+	opts.output_format = DIFF_FORMAT_NO_OUTPUT;
+	diff_queued_diff.nr = 0;
+	diff_queued_diff.queue = NULL;
+	diff_flush(&opts);
+	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);
+}
+
+/*
+ * 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)
+{
+	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 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);
+}
+
+/*
+ * See if there is a directory rename for path, and if there are any file
+ * level conflicts for the renamed location.  If there is a rename and
+ * there are no conflicts, return the new name.  Otherwise, return NULL.
+ */
+static char *handle_path_level_conflicts(struct merge_options *o,
+					 const char *path,
+					 struct dir_rename_entry *entry,
+					 struct hashmap *collisions,
+					 struct tree *tree)
+{
+	char *new_path = NULL;
+	struct collision_entry *collision_ent;
+	int clean = 1;
+	struct strbuf collision_paths = STRBUF_INIT;
+
+	/*
+	 * entry has the mapping of old directory name to new directory name
+	 * that we want to apply to path.
+	 */
+	new_path = apply_dir_rename(entry, path);
+
+	if (!new_path) {
+		/* This should only happen when entry->non_unique_new_dir set */
+		if (!entry->non_unique_new_dir)
+			BUG("entry->non_unqiue_dir not set and !new_path");
+		output(o, 1, _("CONFLICT (directory rename split): "
+			       "Unclear where to place %s because directory "
+			       "%s was renamed to multiple other directories, "
+			       "with no destination getting a majority of the "
+			       "files."),
+		       path, entry->dir);
+		clean = 0;
+		return NULL;
+	}
+
+	/*
+	 * The caller needs to have ensured that it has pre-populated
+	 * collisions with all paths that map to new_path.  Do a quick check
+	 * to ensure that's the case.
+	 */
+	collision_ent = collision_find_entry(collisions, new_path);
+	if (collision_ent == NULL)
+		BUG("collision_ent is NULL");
+
+	/*
+	 * Check for one-sided add/add/.../add conflicts, i.e.
+	 * where implicit renames from the other side doing
+	 * directory rename(s) can affect this side of history
+	 * to put multiple paths into the same location.  Warn
+	 * and bail on directory renames for such paths.
+	 */
+	if (collision_ent->reported_already) {
+		clean = 0;
+	} else if (tree_has_path(tree, new_path)) {
+		collision_ent->reported_already = 1;
+		strbuf_add_separated_string_list(&collision_paths, ", ",
+						 &collision_ent->source_files);
+		output(o, 1, _("CONFLICT (implicit dir rename): Existing "
+			       "file/dir at %s in the way of implicit "
+			       "directory rename(s) putting the following "
+			       "path(s) there: %s."),
+		       new_path, collision_paths.buf);
+		clean = 0;
+	} else if (collision_ent->source_files.nr > 1) {
+		collision_ent->reported_already = 1;
+		strbuf_add_separated_string_list(&collision_paths, ", ",
+						 &collision_ent->source_files);
+		output(o, 1, _("CONFLICT (implicit dir rename): Cannot map "
+			       "more than one path to %s; implicit directory "
+			       "renames tried to put these paths there: %s"),
+		       new_path, collision_paths.buf);
+		clean = 0;
+	}
+
+	/* Free memory we no longer need */
+	strbuf_release(&collision_paths);
+	if (!clean && new_path) {
+		free(new_path);
+		return NULL;
+	}
+
+	return new_path;
+}
+
+/*
+ * 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)
+{
+	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;
+}
+
+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 != 'A' && pair->status != 'R')
+			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);
+	}
+}
+
+static char *check_for_directory_rename(struct merge_options *o,
+					const char *path,
+					struct tree *tree,
+					struct hashmap *dir_renames,