cache_ref_iterator_begin(): make function smarter

Change `cache_ref_iterator_begin()` to take two new arguments:

* `prefix` -- to iterate only over references with the specified
  prefix.

* `prime_dir` -- to "prime" (i.e., pre-load) the cache before starting
  the iteration.

The new functionality makes it possible for
`files_ref_iterator_begin()` to be made more ignorant of the internals
of `ref_cache`, and `find_containing_dir()` and `prime_ref_dir()` to
be made private.

Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 56 insertions, 53 deletions

diff --git a/refs/files-backend.c b/refs/files-backend.c
index 7ae7c6a..8c36086 100644
--- a/refs/files-backend.c
+++ b/refs/files-backend.c
@@ -1082,7 +1082,6 @@ static struct ref_iterator *files_ref_iterator_begin(
 		const char *prefix, unsigned int flags)
 {
 	struct files_ref_store *refs;
-	struct ref_dir *loose_dir, *packed_dir;
 	struct ref_iterator *loose_iter, *packed_iter;
 	struct files_ref_iterator *iter;
 	struct ref_iterator *ref_iterator;
@@ -1106,41 +1105,24 @@ static struct ref_iterator *files_ref_iterator_begin(
 	 * condition if loose refs are migrated to the packed-refs
 	 * file by a simultaneous process, but our in-memory view is
 	 * from before the migration. We ensure this as follows:
-	 * First, we call prime_ref_dir(), which pre-reads the loose
-	 * references for the subtree into the cache. (If they've
-	 * already been read, that's OK; we only need to guarantee
-	 * that they're read before the packed refs, not *how much*
-	 * before.) After that, we call get_packed_ref_cache(), which
-	 * internally checks whether the packed-ref cache is up to
-	 * date with what is on disk, and re-reads it if not.
+	 * First, we call start the loose refs iteration with its
+	 * `prime_ref` argument set to true. This causes the loose
+	 * references in the subtree to be pre-read into the cache.
+	 * (If they've already been read, that's OK; we only need to
+	 * guarantee that they're read before the packed refs, not
+	 * *how much* before.) After that, we call
+	 * get_packed_ref_cache(), which internally checks whether the
+	 * packed-ref cache is up to date with what is on disk, and
+	 * re-reads it if not.
 	 */
 
-	loose_dir = get_loose_ref_dir(refs);
-
-	if (prefix && *prefix)
-		loose_dir = find_containing_dir(loose_dir, prefix, 0);
-
-	if (loose_dir) {
-		prime_ref_dir(loose_dir);
-		loose_iter = cache_ref_iterator_begin(loose_dir);
-	} else {
-		/* There's nothing to iterate over. */
-		loose_iter = empty_ref_iterator_begin();
-	}
+	loose_iter = cache_ref_iterator_begin(get_loose_ref_cache(refs),
+					      prefix, 1);
 
 	iter->packed_ref_cache = get_packed_ref_cache(refs);
 	acquire_packed_ref_cache(iter->packed_ref_cache);
-	packed_dir = get_packed_ref_dir(iter->packed_ref_cache);
-
-	if (prefix && *prefix)
-		packed_dir = find_containing_dir(packed_dir, prefix, 0);
-
-	if (packed_dir) {
-		packed_iter = cache_ref_iterator_begin(packed_dir);
-	} else {
-		/* There's nothing to iterate over. */
-		packed_iter = empty_ref_iterator_begin();
-	}
+	packed_iter = cache_ref_iterator_begin(iter->packed_ref_cache->cache,
+					       prefix, 0);
 
 	iter->iter0 = overlay_ref_iterator_begin(loose_iter, packed_iter);
 	iter->flags = flags;
diff --git a/refs/ref-cache.c b/refs/ref-cache.c
index 38d4c31..b3a3035 100644
--- a/refs/ref-cache.c
+++ b/refs/ref-cache.c
@@ -177,8 +177,17 @@ static struct ref_dir *search_for_subdir(struct ref_dir *dir,
 	return get_ref_dir(entry);
 }
 
-struct ref_dir *find_containing_dir(struct ref_dir *dir,
-				    const char *refname, int mkdir)
+/*
+ * If refname is a reference name, find the ref_dir within the dir
+ * tree that should hold refname. If refname is a directory name
+ * (i.e., it ends in '/'), then return that ref_dir itself. dir must
+ * represent the top-level directory and must already be complete.
+ * Sort ref_dirs and recurse into subdirectories as necessary. If
+ * mkdir is set, then create any missing directories; otherwise,
+ * return NULL if the desired directory cannot be found.
+ */
+static struct ref_dir *find_containing_dir(struct ref_dir *dir,
+					   const char *refname, int mkdir)
 {
 	const char *slash;
 	for (slash = strchr(refname, '/'); slash; slash = strchr(slash + 1, '/')) {
@@ -328,7 +337,11 @@ int do_for_each_entry_in_dir(struct ref_dir *dir,
 	return 0;
 }
 
-void prime_ref_dir(struct ref_dir *dir)
+/*
+ * Load all of the refs from `dir` (recursively) into our in-memory
+ * cache.
+ */
+static void prime_ref_dir(struct ref_dir *dir)
 {
 	/*
 	 * The hard work of loading loose refs is done by get_ref_dir(), so we
@@ -494,12 +507,25 @@ static struct ref_iterator_vtable cache_ref_iterator_vtable = {
 	cache_ref_iterator_abort
 };
 
-struct ref_iterator *cache_ref_iterator_begin(struct ref_dir *dir)
+struct ref_iterator *cache_ref_iterator_begin(struct ref_cache *cache,
+					      const char *prefix,
+					      int prime_dir)
 {
+	struct ref_dir *dir;
 	struct cache_ref_iterator *iter;
 	struct ref_iterator *ref_iterator;
 	struct cache_ref_iterator_level *level;
 
+	dir = get_ref_dir(cache->root);
+	if (prefix && *prefix)
+		dir = find_containing_dir(dir, prefix, 0);
+	if (!dir)
+		/* There's nothing to iterate over. */
+		return  empty_ref_iterator_begin();
+
+	if (prime_dir)
+		prime_ref_dir(dir);
+
 	iter = xcalloc(1, sizeof(*iter));
 	ref_iterator = &iter->base;
 	base_ref_iterator_init(ref_iterator, &cache_ref_iterator_vtable);
@@ -510,5 +536,9 @@ struct ref_iterator *cache_ref_iterator_begin(struct ref_dir *dir)
 	level->index = -1;
 	level->dir = dir;
 
+	if (prefix && *prefix)
+		ref_iterator = prefix_ref_iterator_begin(ref_iterator,
+							 prefix, 0);
+
 	return ref_iterator;
 }
diff --git a/refs/ref-cache.h b/refs/ref-cache.h
index 6eecdf4..5e7a918 100644
--- a/refs/ref-cache.h
+++ b/refs/ref-cache.h
@@ -235,25 +235,21 @@ int remove_entry_from_dir(struct ref_dir *dir, const char *refname);
 int add_ref_entry(struct ref_dir *dir, struct ref_entry *ref);
 
 /*
- * If refname is a reference name, find the ref_dir within the dir
- * tree that should hold refname. If refname is a directory name
- * (i.e., it ends in '/'), then return that ref_dir itself. dir must
- * represent the top-level directory and must already be complete.
- * Sort ref_dirs and recurse into subdirectories as necessary. If
- * mkdir is set, then create any missing directories; otherwise,
- * return NULL if the desired directory cannot be found.
- */
-struct ref_dir *find_containing_dir(struct ref_dir *dir,
-				    const char *refname, int mkdir);
-
-/*
  * Find the value entry with the given name in dir, sorting ref_dirs
  * and recursing into subdirectories as necessary.  If the name is not
  * found or it corresponds to a directory entry, return NULL.
  */
 struct ref_entry *find_ref_entry(struct ref_dir *dir, const char *refname);
 
-struct ref_iterator *cache_ref_iterator_begin(struct ref_dir *dir);
+/*
+ * Start iterating over references in `cache`. If `prefix` is
+ * specified, only include references whose names start with that
+ * prefix. If `prime_dir` is true, then fill any incomplete
+ * directories before beginning the iteration.
+ */
+struct ref_iterator *cache_ref_iterator_begin(struct ref_cache *cache,
+					      const char *prefix,
+					      int prime_dir);
 
 typedef int each_ref_entry_fn(struct ref_entry *entry, void *cb_data);
 
@@ -279,9 +275,4 @@ int do_for_each_entry_in_dir(struct ref_dir *dir,
  */
 enum peel_status peel_entry(struct ref_entry *entry, int repeel);
 
-/*
- * Load all of the refs from `dir` into our in-memory cache.
- */
-void prime_ref_dir(struct ref_dir *dir);
-
 #endif /* REFS_REF_CACHE_H */