repository: drop initialize_the_repository()

Now that we have dropped `the_index`, `initialize_the_repository()`
doesn't really do a lot anymore except for setting up the pointer for
`the_repository` and then calling `initialize_repository()`. The former
can be replaced by statically initializing the pointer though, which
basically makes this function moot.

Convert callers to instead call `initialize_repository(the_repository)`
and drop `initialize_thee_repository()`.

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

common-main.c

@@ -48,7 +48,7 @@ int main(int argc, const char **argv)
 	setlocale(LC_CTYPE, "");
 	git_setup_gettext();
 
-	initialize_the_repository();
+	initialize_repository(the_repository);
 
 	attr_start();
 

oss-fuzz/fuzz-commit-graph.c

@@ -11,7 +11,8 @@ int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size)
 {
 	struct commit_graph *g;
 
-	initialize_the_repository();
+	initialize_repository(the_repository);
+
 	/*
 	 * Initialize the_repository with commit-graph settings that would
 	 * normally be read from the repository's gitdir. We want to avoid

repository.c

@@ -17,22 +17,35 @@
 
 /* The main repository */
 static struct repository the_repo;
-struct repository *the_repository;
+struct repository *the_repository = &the_repo;
 
-static void initialize_repository(struct repository *repo)
+void initialize_repository(struct repository *repo)
 {
 	repo->objects = raw_object_store_new();
 	repo->remote_state = remote_state_new();
 	repo->parsed_objects = parsed_object_pool_new();
 	ALLOC_ARRAY(repo->index, 1);
 	index_state_init(repo->index, repo);
-}
 
-void initialize_the_repository(void)
-{
-	the_repository = &the_repo;
-	initialize_repository(the_repository);
-	repo_set_hash_algo(&the_repo, GIT_HASH_SHA1);
+	/*
+	 * Unfortunately, we need to keep this hack around for the time being:
+	 *
+	 *   - Not setting up the hash algorithm for `the_repository` leads to
+	 *     crashes because `the_hash_algo` is a macro that expands to
+	 *     `the_repository->hash_algo`. So if Git commands try to access
+	 *     `the_hash_algo` without a Git directory we crash.
+	 *
+	 *   - Setting up the hash algorithm to be SHA1 by default breaks other
+	 *     commands when running with SHA256.
+	 *
+	 * This is another point in case why having global state is a bad idea.
+	 * Eventually, we should remove this hack and stop setting the hash
+	 * algorithm in this function altogether. Instead, it should only ever
+	 * be set via our repository setup procedures. But that requires more
+	 * work.
+	 */
+	if (repo == the_repository)
+		repo_set_hash_algo(repo, GIT_HASH_SHA1);
 }
 
 static void expand_base_dir(char **out, const char *in,

repository.h

@@ -207,7 +207,7 @@ void repo_set_worktree(struct repository *repo, const char *path);
 void repo_set_hash_algo(struct repository *repo, int algo);
 void repo_set_compat_hash_algo(struct repository *repo, int compat_algo);
 void repo_set_ref_storage_format(struct repository *repo, unsigned int format);
-void initialize_the_repository(void);
+void initialize_repository(struct repository *repo);
 RESULT_MUST_BE_USED
 int repo_init(struct repository *r, const char *gitdir, const char *worktree);
 

t/helper/test-read-cache.c

@@ -9,7 +9,7 @@ int cmd__read_cache(int argc, const char **argv)
 	int i, cnt = 1;
 	const char *name = NULL;
 
-	initialize_the_repository();
+	initialize_repository(the_repository);
 
 	if (argc > 1 && skip_prefix(argv[1], "--print-and-refresh=", &name)) {
 		argc--;