Merge branch 'es/name-hash-no-trailing-slash-in-dirs'

Clean up the internal of the name-hash mechanism used to work
around case insensitivity on some filesystems to cleanly fix a
long-standing API glitch where the caller of cache_name_exists()
that ask about a directory with a counted string was required to
have '/' at one location past the end of the string.

* es/name-hash-no-trailing-slash-in-dirs:
  dir: revert work-around for retired dangerous behavior
  name-hash: stop storing trailing '/' on paths in index_state.dir_hash
  employ new explicit "exists in index?" API
  name-hash: refactor polymorphic index_name_exists()

5 files changed, 50 insertions, 51 deletions

diff --git a/cache.h b/cache.h
index 51d6602cd9..2d86b695a9 100644
--- a/cache.h
+++ b/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 */
diff --git a/dir.c b/dir.c
index b439ff0e63..23b6de4703 100644
--- a/dir.c
+++ b/dir.c
@@ -860,7 +860,7 @@ static struct dir_entry *dir_entry_new(const char *pathname, int len)
 
 static struct dir_entry *dir_add_name(struct dir_struct *dir, const char *pathname, int len)
 {
-	if (cache_name_exists(pathname, len, ignore_case))
+	if (cache_file_exists(pathname, len, ignore_case))
 		return NULL;
 
 	ALLOC_GROW(dir->entries, dir->nr+1, dir->alloc);
@@ -885,11 +885,11 @@ enum exist_status {
 /*
  * Do not use the alphabetically sorted index to look up
  * the directory name; instead, use the case insensitive
- * name hash.
+ * directory hash.
  */
 static enum exist_status directory_exists_in_index_icase(const char *dirname, int len)
 {
-	const struct cache_entry *ce = cache_name_exists(dirname, len + 1, ignore_case);
+	const struct cache_entry *ce = cache_dir_exists(dirname, len);
 	unsigned char endchar;
 
 	if (!ce)
@@ -1071,7 +1071,7 @@ static int get_index_dtype(const char *path, int len)
 	int pos;
 	const struct cache_entry *ce;
 
-	ce = cache_name_exists(path, len, 0);
+	ce = cache_file_exists(path, len, 0);
 	if (ce) {
 		if (!ce_uptodate(ce))
 			return DT_UNKNOWN;
@@ -1131,7 +1131,7 @@ static enum path_treatment treat_one_path(struct dir_struct *dir,
 					  int dtype, struct dirent *de)
 {
 	int exclude;
-	int has_path_in_index = !!cache_name_exists(path->buf, path->len, ignore_case);
+	int has_path_in_index = !!cache_file_exists(path->buf, path->len, ignore_case);
 
 	if (dtype == DT_UNKNOWN)
 		dtype = get_dtype(de, path->buf, path->len);
@@ -1160,21 +1160,9 @@ static enum path_treatment treat_one_path(struct dir_struct *dir,
 	 */
 	if ((dir->flags & DIR_COLLECT_KILLED_ONLY) &&
 	    (dtype == DT_DIR) &&
-	    !has_path_in_index) {
-		/*
-		 * NEEDSWORK: directory_exists_in_index_icase()
-		 * assumes that one byte past the given path is
-		 * readable and has '/', which needs to be fixed, but
-		 * until then, work it around in the caller.
-		 */
-		strbuf_addch(path, '/');
-		if (directory_exists_in_index(path->buf, path->len - 1) ==
-		    index_nonexistent) {
-			strbuf_setlen(path, path->len - 1);
-			return path_none;
-		}
-		strbuf_setlen(path, path->len - 1);
-	}
+	    !has_path_in_index &&
+	    (directory_exists_in_index(path->buf, path->len) == index_nonexistent))
+		return path_none;
 
 	exclude = is_excluded(dir, path->buf, &dtype);
 
diff --git a/name-hash.c b/name-hash.c
index 617c86c537..e5b6e1ad23 100644
--- a/name-hash.c
+++ b/name-hash.c
@@ -58,9 +58,9 @@ static struct dir_entry *hash_dir_entry(struct index_state *istate,
 {
 	/*
 	 * Throw each directory component in the hash for quick lookup
-	 * during a git status. Directory components are stored with their
+	 * during a git status. Directory components are stored without their
 	 * closing slash.  Despite submodules being a directory, they never
-	 * reach this point, because they are stored without a closing slash
+	 * reach this point, because they are stored
 	 * in index_state.name_hash (as ordinary cache_entries).
 	 *
 	 * Note that the cache_entry stored with the dir_entry merely
@@ -78,6 +78,7 @@ static struct dir_entry *hash_dir_entry(struct index_state *istate,
 		namelen--;
 	if (namelen <= 0)
 		return NULL;
+	namelen--;
 
 	/* lookup existing entry for that directory */
 	dir = find_dir_entry(istate, ce->name, namelen);
@@ -97,7 +98,7 @@ static struct dir_entry *hash_dir_entry(struct index_state *istate,
 		}
 
 		/* recursively add missing parent directories */
-		dir->parent = hash_dir_entry(istate, ce, namelen - 1);
+		dir->parent = hash_dir_entry(istate, ce, namelen);
 	}
 	return dir;
 }
@@ -222,7 +223,29 @@ 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);
+	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 +260,16 @@ 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 - 1);
+	return index_file_exists(istate, name, namelen, icase);
+}
+
 static int free_dir_entry(void *entry, void *unused)
 {
 	struct dir_entry *dir = entry;
diff --git a/read-cache.c b/read-cache.c
index 6bbe1b1fb3..33dd676ccb 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -643,7 +643,7 @@ int add_to_index(struct index_state *istate, const char *path, struct stat *st,
 			if (*ptr == '/') {
 				struct cache_entry *foundce;
 				++ptr;
-				foundce = index_name_exists(istate, ce->name, ptr - ce->name, ignore_case);
+				foundce = index_dir_exists(istate, ce->name, ptr - ce->name - 1);
 				if (foundce) {
 					memcpy((void *)startPtr, foundce->name + (startPtr - ce->name), ptr - startPtr);
 					startPtr = ptr;
@@ -652,7 +652,7 @@ int add_to_index(struct index_state *istate, const char *path, struct stat *st,
 		}
 	}
 
-	alias = index_name_exists(istate, ce->name, ce_namelen(ce), ignore_case);
+	alias = index_file_exists(istate, ce->name, ce_namelen(ce), ignore_case);
 	if (alias && !ce_stage(alias) && !ie_match_stat(istate, alias, st, ce_option)) {
 		/* Nothing changed, really */
 		free(ce);
diff --git a/unpack-trees.c b/unpack-trees.c
index 1a61e6f363..35cb05e92b 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -1357,7 +1357,7 @@ static int icase_exists(struct unpack_trees_options *o, const char *name, int le
 {
 	const struct cache_entry *src;
 
-	src = index_name_exists(o->src_index, name, len, 1);
+	src = index_file_exists(o->src_index, name, len, 1);
 	return src && !ie_match_stat(o->src_index, src, st, CE_MATCH_IGNORE_VALID|CE_MATCH_IGNORE_SKIP_WORKTREE);
 }
 
@@ -1403,7 +1403,7 @@ static int check_ok_to_remove(const char *name, int len, int dtype,
 	 * delete this path, which is in a subdirectory that
 	 * is being replaced with a blob.
 	 */
-	result = index_name_exists(&o->result, name, len, 0);
+	result = index_file_exists(&o->result, name, len, 0);
 	if (result) {
 		if (result->ce_flags & CE_REMOVE)
 			return 0;