name-hash: refactor polymorphic index_name_exists()

Depending upon the absence or presence of a trailing '/' on the incoming
pathname, index_name_exists() checks either if a file is present in the
index or if a directory is represented within the index. Each caller
explicitly chooses the mode of operation by adding or removing a
trailing '/' before invoking index_name_exists().

Since these two modes of operations are disjoint and have no code in
common (one searches index_state.name_hash; the other dir_hash), they
can be represented more naturally as distinct functions: one to search
for a file, and one for a directory.

Splitting index searching into two functions relieves callers of the
artificial burden of having to add or remove a slash to select the mode
of operation; instead they just call the desired function. A subsequent
patch will take advantage of this benefit in order to eliminate the
requirement that the incoming pathname for a directory search must have
a trailing slash.

(In order to avoid disturbing in-flight topics, index_name_exists() is
retained as a thin wrapper dispatching either to index_dir_exists() or
index_file_exists().)

Signed-off-by: Eric Sunshine <sunshine@sunshineco.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Author: sunshineco

cache.h

@@ -314,6 +314,8 @@ extern void free_name_hash(struct index_state *istate);
 #define refresh_cache(flags) refresh_index(&the_index, (flags), NULL, NULL, NULL)
 #define ce_match_stat(ce, st, options) ie_match_stat(&the_index, (ce), (st), (options))
 #define ce_modified(ce, st, options) ie_modified(&the_index, (ce), (st), (options))
+#define cache_dir_exists(name, namelen) index_dir_exists(&the_index, (name), (namelen))
+#define cache_file_exists(name, namelen, igncase) index_file_exists(&the_index, (name), (namelen), (igncase))
 #define cache_name_exists(name, namelen, igncase) index_name_exists(&the_index, (name), (namelen), (igncase))
 #define cache_name_is_other(name, namelen) index_name_is_other(&the_index, (name), (namelen))
 #define resolve_undo_clear() resolve_undo_clear_index(&the_index)
@@ -463,6 +465,8 @@ extern int write_index(struct index_state *, int newfd);
 extern int discard_index(struct index_state *);
 extern int unmerged_index(const struct index_state *);
 extern int verify_path(const char *path);
+extern struct cache_entry *index_dir_exists(struct index_state *istate, const char *name, int namelen);
+extern struct cache_entry *index_file_exists(struct index_state *istate, const char *name, int namelen, int igncase);
 extern struct cache_entry *index_name_exists(struct index_state *istate, const char *name, int namelen, int igncase);
 extern int index_name_pos(const struct index_state *, const char *name, int namelen);
 #define ADD_CACHE_OK_TO_ADD 1		/* Ok to add */

name-hash.c

@@ -222,7 +222,29 @@ static int same_name(const struct cache_entry *ce, const char *name, int namelen
 	return slow_same_name(name, namelen, ce->name, len);
 }
 
-struct cache_entry *index_name_exists(struct index_state *istate, const char *name, int namelen, int icase)
+struct cache_entry *index_dir_exists(struct index_state *istate, const char *name, int namelen)
+{
+	struct cache_entry *ce;
+	struct dir_entry *dir;
+
+	lazy_init_name_hash(istate);
+	dir = find_dir_entry(istate, name, namelen);
+	if (dir && dir->nr)
+		return dir->ce;
+
+	/*
+	 * It might be a submodule. Unlike plain directories, which are stored
+	 * in the dir-hash, submodules are stored in the name-hash, so check
+	 * there, as well.
+	 */
+	ce = index_file_exists(istate, name, namelen - 1, 1);
+	if (ce && S_ISGITLINK(ce->ce_mode))
+		return ce;
+
+	return NULL;
+}
+
+struct cache_entry *index_file_exists(struct index_state *istate, const char *name, int namelen, int icase)
 {
 	unsigned int hash = hash_name(name, namelen);
 	struct cache_entry *ce;
@@ -237,32 +259,16 @@ struct cache_entry *index_name_exists(struct index_state *istate, const char *na
 		}
 		ce = ce->next;
 	}
-
-	/*
-	 * When looking for a directory (trailing '/'), it might be a
-	 * submodule or a directory. Despite submodules being directories,
-	 * they are stored in the name hash without a closing slash.
-	 * When ignore_case is 1, directories are stored in a separate hash
-	 * table *with* their closing slash.
-	 *
-	 * The side effect of this storage technique is we have need to
-	 * lookup the directory in a separate hash table, and if not found
-	 * remove the slash from name and perform the lookup again without
-	 * the slash.  If a match is made, S_ISGITLINK(ce->mode) will be
-	 * true.
-	 */
-	if (icase && name[namelen - 1] == '/') {
-		struct dir_entry *dir = find_dir_entry(istate, name, namelen);
-		if (dir && dir->nr)
-			return dir->ce;
-
-		ce = index_name_exists(istate, name, namelen - 1, icase);
-		if (ce && S_ISGITLINK(ce->ce_mode))
-			return ce;
-	}
 	return NULL;
 }
 
+struct cache_entry *index_name_exists(struct index_state *istate, const char *name, int namelen, int icase)
+{
+	if (namelen > 0 && name[namelen - 1] == '/')
+		return index_dir_exists(istate, name, namelen);
+	return index_file_exists(istate, name, namelen, icase);
+}
+
 static int free_dir_entry(void *entry, void *unused)
 {
 	struct dir_entry *dir = entry;