Merge branch 'ps/clone-into-reftable-repository'

"git clone" has been prepared to allow cloning a repository with
non-default hash function into a repository that uses the reftable
backend.

* ps/clone-into-reftable-repository:
  builtin/clone: create the refdb with the correct object format
  builtin/clone: skip reading HEAD when retrieving remote
  builtin/clone: set up sparse checkout later
  builtin/clone: fix bundle URIs with mismatching object formats
  remote-curl: rediscover repository when fetching refs
  setup: allow skipping creation of the refdb
  setup: extract function to create the refdb

8 files changed, 150 insertions, 91 deletions

diff --git a/builtin/clone.c b/builtin/clone.c
index d1801bbe1a..343f536cf8 100644
--- a/builtin/clone.c
+++ b/builtin/clone.c
@@ -1101,8 +1101,14 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 		}
 	}
 
+	/*
+	 * Initialize the repository, but skip initializing the reference
+	 * database. We do not yet know about the object format of the
+	 * repository, and reference backends may persist that information into
+	 * their on-disk data structures.
+	 */
 	init_db(git_dir, real_git_dir, option_template, GIT_HASH_UNKNOWN, NULL,
-		do_not_override_repo_unix_permissions, INIT_DB_QUIET);
+		do_not_override_repo_unix_permissions, INIT_DB_QUIET | INIT_DB_SKIP_REFDB);
 
 	if (real_git_dir) {
 		free((char *)git_dir);
@@ -1189,10 +1195,7 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 	if (option_required_reference.nr || option_optional_reference.nr)
 		setup_reference();
 
-	if (option_sparse_checkout && git_sparse_checkout_init(dir))
-		return 1;
-
-	remote = remote_get(remote_name);
+	remote = remote_get_early(remote_name);
 
 	refspec_appendf(&remote->fetch, "+%s*:%s*", src_ref_prefix,
 			branch_top.buf);
@@ -1270,6 +1273,27 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 	if (transport->smart_options && !deepen && !filter_options.choice)
 		transport->smart_options->check_self_contained_and_connected = 1;
 
+	strvec_push(&transport_ls_refs_options.ref_prefixes, "HEAD");
+	refspec_ref_prefixes(&remote->fetch,
+			     &transport_ls_refs_options.ref_prefixes);
+	if (option_branch)
+		expand_ref_prefix(&transport_ls_refs_options.ref_prefixes,
+				  option_branch);
+	if (!option_no_tags)
+		strvec_push(&transport_ls_refs_options.ref_prefixes,
+			    "refs/tags/");
+
+	refs = transport_get_remote_refs(transport, &transport_ls_refs_options);
+
+	/*
+	 * Now that we know what algorithm the remote side is using, let's set
+	 * ours to the same thing.
+	 */
+	hash_algo = hash_algo_by_ptr(transport_get_hash_algo(transport));
+	initialize_repository_version(hash_algo, 1);
+	repo_set_hash_algo(the_repository, hash_algo);
+	create_reference_database(NULL, 1);
+
 	/*
 	 * Before fetching from the remote, download and install bundle
 	 * data from the --bundle-uri option.
@@ -1285,24 +1309,7 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 				bundle_uri);
 		else if (has_heuristic)
 			git_config_set_gently("fetch.bundleuri", bundle_uri);
-	}
-
-	strvec_push(&transport_ls_refs_options.ref_prefixes, "HEAD");
-	refspec_ref_prefixes(&remote->fetch,
-			     &transport_ls_refs_options.ref_prefixes);
-	if (option_branch)
-		expand_ref_prefix(&transport_ls_refs_options.ref_prefixes,
-				  option_branch);
-	if (!option_no_tags)
-		strvec_push(&transport_ls_refs_options.ref_prefixes,
-			    "refs/tags/");
-
-	refs = transport_get_remote_refs(transport, &transport_ls_refs_options);
-
-	if (refs)
-		mapped_refs = wanted_peer_refs(refs, &remote->fetch);
-
-	if (!bundle_uri) {
+	} else {
 		/*
 		* Populate transport->got_remote_bundle_uri and
 		* transport->bundle_uri. We might get nothing.
@@ -1323,13 +1330,8 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 		}
 	}
 
-		/*
-		 * Now that we know what algorithm the remote side is using,
-		 * let's set ours to the same thing.
-		 */
-	hash_algo = hash_algo_by_ptr(transport_get_hash_algo(transport));
-	initialize_repository_version(hash_algo, 1);
-	repo_set_hash_algo(the_repository, hash_algo);
+	if (refs)
+		mapped_refs = wanted_peer_refs(refs, &remote->fetch);
 
 	if (mapped_refs) {
 		/*
@@ -1432,6 +1434,9 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 		dissociate_from_references();
 	}
 
+	if (option_sparse_checkout && git_sparse_checkout_init(dir))
+		return 1;
+
 	junk_mode = JUNK_LEAVE_REPO;
 	err = checkout(submodule_progress, filter_submodules);
 
diff --git a/remote-curl.c b/remote-curl.c
index ef05752ca5..fc29757b65 100644
--- a/remote-curl.c
+++ b/remote-curl.c
@@ -1564,8 +1564,11 @@ int cmd_main(int argc, const char **argv)
 		if (buf.len == 0)
 			break;
 		if (starts_with(buf.buf, "fetch ")) {
-			if (nongit)
-				die(_("remote-curl: fetch attempted without a local repo"));
+			if (nongit) {
+				setup_git_directory_gently(&nongit);
+				if (nongit)
+					die(_("remote-curl: fetch attempted without a local repo"));
+			}
 			parse_fetch(&buf);
 
 		} else if (!strcmp(buf.buf, "list") || starts_with(buf.buf, "list ")) {
diff --git a/remote.c b/remote.c
index abb24822be..051d0a64a0 100644
--- a/remote.c
+++ b/remote.c
@@ -509,7 +509,7 @@ static void alias_all_urls(struct remote_state *remote_state)
 	}
 }
 
-static void read_config(struct repository *repo)
+static void read_config(struct repository *repo, int early)
 {
 	int flag;
 
@@ -518,7 +518,7 @@ static void read_config(struct repository *repo)
 	repo->remote_state->initialized = 1;
 
 	repo->remote_state->current_branch = NULL;
-	if (startup_info->have_repository) {
+	if (startup_info->have_repository && !early) {
 		const char *head_ref = refs_resolve_ref_unsafe(
 			get_main_ref_store(repo), "HEAD", 0, NULL, &flag);
 		if (head_ref && (flag & REF_ISSYMREF) &&
@@ -561,7 +561,7 @@ static const char *remotes_remote_for_branch(struct remote_state *remote_state,
 
 const char *remote_for_branch(struct branch *branch, int *explicit)
 {
-	read_config(the_repository);
+	read_config(the_repository, 0);
 	die_on_missing_branch(the_repository, branch);
 
 	return remotes_remote_for_branch(the_repository->remote_state, branch,
@@ -587,7 +587,7 @@ remotes_pushremote_for_branch(struct remote_state *remote_state,
 
 const char *pushremote_for_branch(struct branch *branch, int *explicit)
 {
-	read_config(the_repository);
+	read_config(the_repository, 0);
 	die_on_missing_branch(the_repository, branch);
 
 	return remotes_pushremote_for_branch(the_repository->remote_state,
@@ -599,7 +599,7 @@ static struct remote *remotes_remote_get(struct remote_state *remote_state,
 
 const char *remote_ref_for_branch(struct branch *branch, int for_push)
 {
-	read_config(the_repository);
+	read_config(the_repository, 0);
 	die_on_missing_branch(the_repository, branch);
 
 	if (branch) {
@@ -709,7 +709,13 @@ remotes_remote_get(struct remote_state *remote_state, const char *name)
 
 struct remote *remote_get(const char *name)
 {
-	read_config(the_repository);
+	read_config(the_repository, 0);
+	return remotes_remote_get(the_repository->remote_state, name);
+}
+
+struct remote *remote_get_early(const char *name)
+{
+	read_config(the_repository, 1);
 	return remotes_remote_get(the_repository->remote_state, name);
 }
 
@@ -722,7 +728,7 @@ remotes_pushremote_get(struct remote_state *remote_state, const char *name)
 
 struct remote *pushremote_get(const char *name)
 {
-	read_config(the_repository);
+	read_config(the_repository, 0);
 	return remotes_pushremote_get(the_repository->remote_state, name);
 }
 
@@ -738,7 +744,7 @@ int remote_is_configured(struct remote *remote, int in_repo)
 int for_each_remote(each_remote_fn fn, void *priv)
 {
 	int i, result = 0;
-	read_config(the_repository);
+	read_config(the_repository, 0);
 	for (i = 0; i < the_repository->remote_state->remotes_nr && !result;
 	     i++) {
 		struct remote *remote =
@@ -1831,7 +1837,7 @@ struct branch *branch_get(const char *name)
 {
 	struct branch *ret;
 
-	read_config(the_repository);
+	read_config(the_repository, 0);
 	if (!name || !*name || !strcmp(name, "HEAD"))
 		ret = the_repository->remote_state->current_branch;
 	else
@@ -1973,7 +1979,7 @@ static const char *branch_get_push_1(struct remote_state *remote_state,
 
 const char *branch_get_push(struct branch *branch, struct strbuf *err)
 {
-	read_config(the_repository);
+	read_config(the_repository, 0);
 	die_on_missing_branch(the_repository, branch);
 
 	if (!branch)
diff --git a/remote.h b/remote.h
index cdc8b1db42..79353ba226 100644
--- a/remote.h
+++ b/remote.h
@@ -118,6 +118,7 @@ struct remote {
  * and configuration.
  */
 struct remote *remote_get(const char *name);
+struct remote *remote_get_early(const char *name);
 
 struct remote *pushremote_get(const char *name);
 int remote_is_configured(struct remote *remote, int in_repo);
diff --git a/setup.c b/setup.c
index 50131be7cc..bc90bbd033 100644
--- a/setup.c
+++ b/setup.c
@@ -1887,21 +1887,79 @@ void initialize_repository_version(int hash_algo, int reinit)
 		git_config_set_gently("extensions.objectformat", NULL);
 }
 
+static int is_reinit(void)
+{
+	struct strbuf buf = STRBUF_INIT;
+	char junk[2];
+	int ret;
+
+	git_path_buf(&buf, "HEAD");
+	ret = !access(buf.buf, R_OK) || readlink(buf.buf, junk, sizeof(junk) - 1) != -1;
+	strbuf_release(&buf);
+	return ret;
+}
+
+void create_reference_database(const char *initial_branch, int quiet)
+{
+	struct strbuf err = STRBUF_INIT;
+	int reinit = is_reinit();
+
+	/*
+	 * We need to create a "refs" dir in any case so that older versions of
+	 * Git can tell that this is a repository. This serves two main purposes:
+	 *
+	 * - Clients will know to stop walking the parent-directory chain when
+	 *   detecting the Git repository. Otherwise they may end up detecting
+	 *   a Git repository in a parent directory instead.
+	 *
+	 * - Instead of failing to detect a repository with unknown reference
+	 *   format altogether, old clients will print an error saying that
+	 *   they do not understand the reference format extension.
+	 */
+	safe_create_dir(git_path("refs"), 1);
+	adjust_shared_perm(git_path("refs"));
+
+	if (refs_init_db(&err))
+		die("failed to set up refs db: %s", err.buf);
+
+	/*
+	 * Point the HEAD symref to the initial branch with if HEAD does
+	 * not yet exist.
+	 */
+	if (!reinit) {
+		char *ref;
+
+		if (!initial_branch)
+			initial_branch = git_default_branch_name(quiet);
+
+		ref = xstrfmt("refs/heads/%s", initial_branch);
+		if (check_refname_format(ref, 0) < 0)
+			die(_("invalid initial branch name: '%s'"),
+			    initial_branch);
+
+		if (create_symref("HEAD", ref, NULL) < 0)
+			exit(1);
+		free(ref);
+	}
+
+	if (reinit && initial_branch)
+		warning(_("re-init: ignored --initial-branch=%s"),
+			initial_branch);
+
+	strbuf_release(&err);
+}
+
 static int create_default_files(const char *template_path,
 				const char *original_git_dir,
-				const char *initial_branch,
 				const struct repository_format *fmt,
 				int prev_bare_repository,
-				int init_shared_repository,
-				int quiet)
+				int init_shared_repository)
 {
 	struct stat st1;
 	struct strbuf buf = STRBUF_INIT;
 	char *path;
-	char junk[2];
 	int reinit;
 	int filemode;
-	struct strbuf err = STRBUF_INIT;
 	const char *init_template_dir = NULL;
 	const char *work_tree = get_git_work_tree();
 
@@ -1921,6 +1979,8 @@ static int create_default_files(const char *template_path,
 	reset_shared_repository();
 	git_config(git_default_config, NULL);
 
+	reinit = is_reinit();
+
 	/*
 	 * We must make sure command-line options continue to override any
 	 * values we might have just re-read from the config.
@@ -1964,39 +2024,6 @@ static int create_default_files(const char *template_path,
 		adjust_shared_perm(get_git_dir());
 	}
 
-	/*
-	 * We need to create a "refs" dir in any case so that older
-	 * versions of git can tell that this is a repository.
-	 */
-	safe_create_dir(git_path("refs"), 1);
-	adjust_shared_perm(git_path("refs"));
-
-	if (refs_init_db(&err))
-		die("failed to set up refs db: %s", err.buf);
-
-	/*
-	 * Point the HEAD symref to the initial branch with if HEAD does
-	 * not yet exist.
-	 */
-	path = git_path_buf(&buf, "HEAD");
-	reinit = (!access(path, R_OK)
-		  || readlink(path, junk, sizeof(junk)-1) != -1);
-	if (!reinit) {
-		char *ref;
-
-		if (!initial_branch)
-			initial_branch = git_default_branch_name(quiet);
-
-		ref = xstrfmt("refs/heads/%s", initial_branch);
-		if (check_refname_format(ref, 0) < 0)
-			die(_("invalid initial branch name: '%s'"),
-			    initial_branch);
-
-		if (create_symref("HEAD", ref, NULL) < 0)
-			exit(1);
-		free(ref);
-	}
-
 	initialize_repository_version(fmt->hash_algo, 0);
 
 	/* Check filemode trustability */
@@ -2156,14 +2183,11 @@ int init_db(const char *git_dir, const char *real_git_dir,
 	validate_hash_algorithm(&repo_fmt, hash);
 
 	reinit = create_default_files(template_dir, original_git_dir,
-				      initial_branch, &repo_fmt,
-				      prev_bare_repository,
-				      init_shared_repository,
-				      flags & INIT_DB_QUIET);
-	if (reinit && initial_branch)
-		warning(_("re-init: ignored --initial-branch=%s"),
-			initial_branch);
+				      &repo_fmt, prev_bare_repository,
+				      init_shared_repository);
 
+	if (!(flags & INIT_DB_SKIP_REFDB))
+		create_reference_database(initial_branch, flags & INIT_DB_QUIET);
 	create_object_directory();
 
 	if (get_shared_repository()) {
diff --git a/setup.h b/setup.h
index b48cf1c43b..3f0f17c351 100644
--- a/setup.h
+++ b/setup.h
@@ -169,14 +169,16 @@ int verify_repository_format(const struct repository_format *format,
  */
 void check_repository_format(struct repository_format *fmt);
 
-#define INIT_DB_QUIET 0x0001
-#define INIT_DB_EXIST_OK 0x0002
+#define INIT_DB_QUIET      (1 << 0)
+#define INIT_DB_EXIST_OK   (1 << 1)
+#define INIT_DB_SKIP_REFDB (1 << 2)
 
 int init_db(const char *git_dir, const char *real_git_dir,
 	    const char *template_dir, int hash_algo,
 	    const char *initial_branch, int init_shared_repository,
 	    unsigned int flags);
 void initialize_repository_version(int hash_algo, int reinit);
+void create_reference_database(const char *initial_branch, int quiet);
 
 /*
  * NOTE NOTE NOTE!!
diff --git a/t/t5550-http-fetch-dumb.sh b/t/t5550-http-fetch-dumb.sh
index e444b30bf6..4c3b32785d 100755
--- a/t/t5550-http-fetch-dumb.sh
+++ b/t/t5550-http-fetch-dumb.sh
@@ -66,11 +66,11 @@ test_expect_success 'create empty remote repository' '
 	setup_post_update_server_info_hook "$HTTPD_DOCUMENT_ROOT_PATH/empty.git"
 '
 
-test_expect_success 'empty dumb HTTP repository has default hash algorithm' '
+test_expect_success 'empty dumb HTTP repository falls back to SHA1' '
 	test_when_finished "rm -fr clone-empty" &&
 	git clone $HTTPD_URL/dumb/empty.git clone-empty &&
 	git -C clone-empty rev-parse --show-object-format >empty-format &&
-	test "$(cat empty-format)" = "$(test_oid algo)"
+	test "$(cat empty-format)" = sha1
 '
 
 setup_askpass_helper
diff --git a/t/t5558-clone-bundle-uri.sh b/t/t5558-clone-bundle-uri.sh
index 996a08e90c..1ca5f745e7 100755
--- a/t/t5558-clone-bundle-uri.sh
+++ b/t/t5558-clone-bundle-uri.sh
@@ -33,6 +33,15 @@ test_expect_success 'clone with path bundle' '
 	test_cmp expect actual
 '
 
+test_expect_success 'clone with path bundle and non-default hash' '
+	test_when_finished "rm -rf clone-path-non-default-hash" &&
+	GIT_DEFAULT_HASH=sha256 git clone --bundle-uri="clone-from/B.bundle" \
+		clone-from clone-path-non-default-hash &&
+	git -C clone-path-non-default-hash rev-parse refs/bundles/topic >actual &&
+	git -C clone-from rev-parse topic >expect &&
+	test_cmp expect actual
+'
+
 test_expect_success 'clone with file:// bundle' '
 	git clone --bundle-uri="file://$(pwd)/clone-from/B.bundle" \
 		clone-from clone-file &&
@@ -284,6 +293,15 @@ test_expect_success 'clone HTTP bundle' '
 	test_config -C clone-http log.excludedecoration refs/bundle/
 '
 
+test_expect_success 'clone HTTP bundle with non-default hash' '
+	test_when_finished "rm -rf clone-http-non-default-hash" &&
+	GIT_DEFAULT_HASH=sha256 git clone --bundle-uri="$HTTPD_URL/B.bundle" \
+		"$HTTPD_URL/smart/fetch.git" clone-http-non-default-hash &&
+	git -C clone-http-non-default-hash rev-parse refs/bundles/topic >actual &&
+	git -C clone-from rev-parse topic >expect &&
+	test_cmp expect actual
+'
+
 test_expect_success 'clone bundle list (HTTP, no heuristic)' '
 	test_when_finished rm -f trace*.txt &&