refs: add GIT_REF_URI to specify reference backend and directory

Git allows setting a different object directory via
'GIT_OBJECT_DIRECTORY', but provides no equivalent for references.
This asymmetry makes it difficult to test different reference backends
or use alternative reference storage locations without modifying the
repository structure.

Add a new environment variable 'GIT_REF_URI' that specifies both the
reference backend and directory path using a URI format:

    <ref_backend>://<URI-for-resource>

When set, this variable is used to obtain the main reference store for
all Git commands. The variable is checked in `get_main_ref_store()`
when lazily assigning `repo->refs_private`. We cannot initialize this
earlier in `repo_set_gitdir()` because the repository's hash algorithm
isn't known at that point, and the reftable backend requires this
information during initialization.

When used with worktrees, the specified directory is treated as the
reference directory for all worktree operations.

Add a new test file 't1423-ref-backend.sh' to test this environment
variable.

Helped-by: Jean-Noël Avila <jn.avila@free.fr>
Signed-off-by: Karthik Nayak <karthik.188@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Documentation/git.adoc

@@ -584,6 +584,14 @@ double-quotes and respecting backslash escapes. E.g., the value
 	repositories will be set to this value. The default is "files".
 	See `--ref-format` in linkgit:git-init[1].
 
+`GIT_REF_URI`::
+    Specify which reference backend to be used along with its URI. Reference
+    backends like the files, reftable backend use the $GIT_DIR as their URI.
++
+Expects the format `<ref_backend>://<URI-for-resource>`, where the
+_<ref_backend>_ specifies the reference backend and the _<URI-for-resource>_
+specifies the URI used by the backend.
+
 Git Commits
 ~~~~~~~~~~~
 `GIT_AUTHOR_NAME`::

environment.h

@@ -42,6 +42,7 @@
 #define GIT_OPTIONAL_LOCKS_ENVIRONMENT "GIT_OPTIONAL_LOCKS"
 #define GIT_TEXT_DOMAIN_DIR_ENVIRONMENT "GIT_TEXTDOMAINDIR"
 #define GIT_ATTR_SOURCE_ENVIRONMENT "GIT_ATTR_SOURCE"
+#define GIT_REF_URI_ENVIRONMENT "GIT_REF_URI"
 
 /*
  * Environment variable used to propagate the --no-advice global option to the

refs.c

@@ -2186,15 +2186,70 @@ static struct ref_store *get_ref_store_for_dir(struct repository *r,
 	return maybe_debug_wrap_ref_store(dir, ref_store);
 }
 
+static struct ref_store *get_ref_store_from_uri(struct repository *repo,
+						const char *uri)
+{
+	struct string_list ref_backend_info = STRING_LIST_INIT_DUP;
+	enum ref_storage_format format;
+	struct ref_store *store = NULL;
+	char *format_string;
+	char *dir;
+
+	if (!uri) {
+		error(_("reference backend uri is not provided"));
+		goto cleanup;
+	}
+
+	if (string_list_split(&ref_backend_info, uri, ":", 2) != 2) {
+		error(_("invalid reference backend uri format '%s'"), uri);
+		goto cleanup;
+	}
+
+	format_string = ref_backend_info.items[0].string;
+	if (!starts_with(ref_backend_info.items[1].string, "//")) {
+		error(_("invalid reference backend uri format '%s'"), uri);
+		goto cleanup;
+	}
+	dir = ref_backend_info.items[1].string + 2;
+
+	if (!dir[0]) {
+		error(_("invalid path in uri '%s'"), uri);
+		goto cleanup;
+	}
+
+	format = ref_storage_format_by_name(format_string);
+	if (format == REF_STORAGE_FORMAT_UNKNOWN) {
+		error(_("unknown reference backend '%s'"), format_string);
+		goto cleanup;
+	}
+
+	store = get_ref_store_for_dir(repo, dir, format);
+
+cleanup:
+	string_list_clear(&ref_backend_info, 0);
+	return store;
+}
+
 struct ref_store *get_main_ref_store(struct repository *r)
 {
+	char *ref_uri;
+
 	if (r->refs_private)
 		return r->refs_private;
 
 	if (!r->gitdir)
 		BUG("attempting to get main_ref_store outside of repository");
 
-	r->refs_private = get_ref_store_for_dir(r, r->gitdir, r->ref_storage_format);
+	ref_uri = getenv(GIT_REF_URI_ENVIRONMENT);
+	if (ref_uri) {
+		r->refs_private = get_ref_store_from_uri(r, ref_uri);
+		if (!r->refs_private)
+			die("failed to initialize ref store from URI: %s", ref_uri);
+
+	} else {
+		r->refs_private = get_ref_store_for_dir(r, r->gitdir,
+							r->ref_storage_format);
+	}
 	return r->refs_private;
 }
 

t/meson.build

@@ -208,6 +208,7 @@ integration_tests = [
   't1420-lost-found.sh',
   't1421-reflog-write.sh',
   't1422-show-ref-exists.sh',
+  't1423-ref-backend.sh',
   't1430-bad-ref-name.sh',
   't1450-fsck.sh',
   't1451-fsck-buffer.sh',

t/t1423-ref-backend.sh

@@ -0,0 +1,121 @@
+#!/bin/sh
+
+test_description='Test different reference backend URIs'
+
+. ./test-lib.sh
+
+test_expect_success 'empty uri provided' '
+	test_when_finished "rm -rf repo" &&
+	git init --ref-format=files repo &&
+	(
+		cd repo &&
+		GIT_REF_URI="" &&
+		export GIT_REF_URI &&
+		test_must_fail git refs list 2>err &&
+		test_grep "invalid reference backend uri format" err
+	)
+'
+
+test_expect_success 'invalid uri provided' '
+	test_when_finished "rm -rf repo" &&
+	git init --ref-format=files repo &&
+	(
+		cd repo &&
+		GIT_REF_URI="reftable@/home/reftable" &&
+		export GIT_REF_URI &&
+		test_must_fail git refs list 2>err &&
+		test_grep "invalid reference backend uri format" err
+	)
+'
+
+test_expect_success 'empty path in uri' '
+	test_when_finished "rm -rf repo" &&
+	git init --ref-format=files repo &&
+	(
+		cd repo &&
+		GIT_REF_URI="reftable://" &&
+		export GIT_REF_URI &&
+		test_must_fail git refs list 2>err &&
+		test_grep "invalid path in uri" err
+	)
+'
+
+test_expect_success 'uri ends at colon' '
+	test_when_finished "rm -rf repo" &&
+	git init --ref-format=files repo &&
+	(
+		cd repo &&
+		GIT_REF_URI="reftable:" &&
+		export GIT_REF_URI &&
+		test_must_fail git refs list 2>err &&
+		test_grep "invalid reference backend uri format" err
+	)
+'
+
+test_expect_success 'unknown reference backend' '
+	test_when_finished "rm -rf repo" &&
+	git init --ref-format=files repo &&
+	(
+		cd repo &&
+		GIT_REF_URI="db://.git" &&
+		export GIT_REF_URI &&
+		test_must_fail git refs list 2>err &&
+		test_grep "unknown reference backend" err
+	)
+'
+
+ref_formats="files reftable"
+for from_format in $ref_formats
+do
+	for to_format in $ref_formats
+	do
+		if test "$from_format" = "$to_format"
+		then
+			continue
+		fi
+
+		test_expect_success "read from $to_format backend" '
+			test_when_finished "rm -rf repo" &&
+			git init --ref-format=$from_format repo &&
+			(
+				cd repo &&
+				test_commit 1 &&
+				test_commit 2 &&
+				test_commit 3 &&
+
+				git refs migrate --dry-run --ref-format=$to_format >out &&
+				BACKEND_PATH=$(cat out | sed "s/.* ${SQ}\(.*\)${SQ}/\1/") &&
+				git refs list >expect &&
+				GIT_REF_URI="$to_format://$BACKEND_PATH" git refs list >actual &&
+				test_cmp expect actual
+			)
+		'
+
+		test_expect_success "write to $to_format backend" '
+			test_when_finished "rm -rf repo" &&
+			git init --ref-format=$from_format repo &&
+			(
+				cd repo &&
+				test_commit 1 &&
+				test_commit 2 &&
+				test_commit 3 &&
+
+				git refs migrate --dry-run --ref-format=$to_format >out &&
+				git refs list >expect &&
+
+				BACKEND_PATH=$(cat out | sed "s/.* ${SQ}\(.*\)${SQ}/\1/") &&
+				GIT_REF_URI="$to_format://$BACKEND_PATH" git tag -d 1 &&
+
+				git refs list >actual &&
+				test_cmp expect actual &&
+
+				GIT_REF_URI="$to_format://$BACKEND_PATH" git refs list >expect &&
+				git refs list >out &&
+				cat out | grep -v "refs/tags/1" >actual &&
+				test_cmp expect actual
+			)
+		'
+	done
+done
+
+test_done