packfile: introduce function to load and add packfiles

We have a recurring pattern where we essentially perform an upsert of a
packfile in case it isn't yet known by the packfile store. The logic to
do so is non-trivial as we have to reconstruct the packfile's key, check
the map of packfiles, then create the new packfile and finally add it to
the store.

Introduce a new function that does this dance for us. Refactor callsites
to use it.

Signed-off-by: Patrick Steinhardt <ps@pks.im>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

builtin/fast-import.c

@@ -897,11 +897,11 @@ static void end_packfile(void)
 		idx_name = keep_pack(create_index());
 
 		/* Register the packfile with core git's machinery. */
-		new_p = add_packed_git(pack_data->repo, idx_name, strlen(idx_name), 1);
+		new_p = packfile_store_load_pack(pack_data->repo->objects->packfiles,
+						 idx_name, 1);
 		if (!new_p)
 			die("core git rejected index %s", idx_name);
 		all_packs[pack_id] = new_p;
-		packfile_store_add_pack(the_repository->objects->packfiles, new_p);
 		free(idx_name);
 
 		/* Print the boundary */

builtin/index-pack.c

@@ -1640,13 +1640,9 @@ static void final(const char *final_pack_name, const char *curr_pack_name,
 	rename_tmp_packfile(&final_index_name, curr_index_name, &index_name,
 			    hash, "idx", 1);
 
-	if (do_fsck_object) {
+	if (do_fsck_object)
-		struct packed_git *p;
+		packfile_store_load_pack(the_repository->objects->packfiles,
-		p = add_packed_git(the_repository, final_index_name,
+					 final_index_name, 0);
-				   strlen(final_index_name), 0);
-		if (p)
-			packfile_store_add_pack(the_repository->objects->packfiles, p);
-	}
 
 	if (!from_stdin) {
 		printf("%s\n", hash_to_hex(hash));

midx.c

@@ -443,7 +443,6 @@ int prepare_midx_pack(struct multi_pack_index *m,
 {
 	struct repository *r = m->source->odb->repo;
 	struct strbuf pack_name = STRBUF_INIT;
-	struct strbuf key = STRBUF_INIT;
 	struct packed_git *p;
 
 	pack_int_id = midx_for_pack(&m, pack_int_id);
@@ -455,25 +454,11 @@ int prepare_midx_pack(struct multi_pack_index *m,
 
 	strbuf_addf(&pack_name, "%s/pack/%s", m->source->path,
 		    m->pack_names[pack_int_id]);
-
+	p = packfile_store_load_pack(r->objects->packfiles,
-	/* pack_map holds the ".pack" name, but we have the .idx */
+				     pack_name.buf, m->source->local);
-	strbuf_addbuf(&key, &pack_name);
+	if (p)
-	strbuf_strip_suffix(&key, ".idx");
-	strbuf_addstr(&key, ".pack");
-	p = hashmap_get_entry_from_hash(&r->objects->packfiles->map,
-					strhash(key.buf), key.buf,
-					struct packed_git, packmap_ent);
-	if (!p) {
-		p = add_packed_git(r, pack_name.buf, pack_name.len,
-				   m->source->local);
-		if (p) {
-			packfile_store_add_pack(r->objects->packfiles, p);
 		list_add_tail(&p->mru, &r->objects->packfiles->mru);
-		}
-	}
-
 	strbuf_release(&pack_name);
-	strbuf_release(&key);
 
 	if (!p) {
 		m->packs[pack_int_id] = MIDX_PACK_ERROR;

packfile.c

@@ -792,6 +792,33 @@ void packfile_store_add_pack(struct packfile_store *store,
 	hashmap_add(&store->map, &pack->packmap_ent);
 }
 
+struct packed_git *packfile_store_load_pack(struct packfile_store *store,
+					    const char *idx_path, int local)
+{
+	struct strbuf key = STRBUF_INIT;
+	struct packed_git *p;
+
+	/*
+	 * We're being called with the path to the index file, but `pack_map`
+	 * holds the path to the packfile itself.
+	 */
+	strbuf_addstr(&key, idx_path);
+	strbuf_strip_suffix(&key, ".idx");
+	strbuf_addstr(&key, ".pack");
+
+	p = hashmap_get_entry_from_hash(&store->map, strhash(key.buf), key.buf,
+					struct packed_git, packmap_ent);
+	if (!p) {
+		p = add_packed_git(store->odb->repo, idx_path,
+				   strlen(idx_path), local);
+		if (p)
+			packfile_store_add_pack(store, p);
+	}
+
+	strbuf_release(&key);
+	return p;
+}
+
 void (*report_garbage)(unsigned seen_bits, const char *path);
 
 static void report_helper(const struct string_list *list,
@@ -891,23 +918,14 @@ static void prepare_pack(const char *full_name, size_t full_name_len,
 			 const char *file_name, void *_data)
 {
 	struct prepare_pack_data *data = (struct prepare_pack_data *)_data;
-	struct packed_git *p;
 	size_t base_len = full_name_len;
 
 	if (strip_suffix_mem(full_name, &base_len, ".idx") &&
 	    !(data->m && midx_contains_pack(data->m, file_name))) {
-		struct hashmap_entry hent;
+		char *trimmed_path = xstrndup(full_name, full_name_len);
-		char *pack_name = xstrfmt("%.*s.pack", (int)base_len, full_name);
+		packfile_store_load_pack(data->r->objects->packfiles,
-		unsigned int hash = strhash(pack_name);
+					 trimmed_path, data->local);
-		hashmap_entry_init(&hent, hash);
+		free(trimmed_path);
-
-		/* Don't reopen a pack we already have. */
-		if (!hashmap_get(&data->r->objects->packfiles->map, &hent, pack_name)) {
-			p = add_packed_git(data->r, full_name, full_name_len, data->local);
-			if (p)
-				packfile_store_add_pack(data->r->objects->packfiles, p);
-		}
-		free(pack_name);
 	}
 
 	if (!report_garbage)

packfile.h

@@ -127,6 +127,14 @@ void packfile_store_reprepare(struct packfile_store *store);
 void packfile_store_add_pack(struct packfile_store *store,
 			     struct packed_git *pack);
 
+/*
+ * Open the packfile and add it to the store if it isn't yet known. Returns
+ * either the newly opened packfile or the preexisting packfile. Returns a
+ * `NULL` pointer in case the packfile could not be opened.
+ */
+struct packed_git *packfile_store_load_pack(struct packfile_store *store,
+					    const char *idx_path, int local);
+
 struct pack_window {
 	struct pack_window *next;
 	unsigned char *base;