promisor-remote: teach lazy-fetch in any repo

This is one step towards supporting partial clone submodules.

Even after this patch, we will still lack partial clone submodules
support, primarily because a lot of Git code that accesses submodule
objects does so by adding their object stores as alternates, meaning
that any lazy fetches that would occur in the submodule would be done
based on the config of the superproject, not of the submodule. This also
prevents testing of the functionality in this patch by user-facing
commands. So for now, test this mechanism using a test helper.

Besides that, there is some code that uses the wrapper functions
like has_promisor_remote(). Those will need to be checked to see if they
could support the non-wrapper functions instead (and thus support any
repository, not just the_repository).

Signed-off-by: Jonathan Tan <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>
Reviewed-by: Elijah Newren <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: jonathantanmy

Makefile

@@ -725,6 +725,7 @@ TEST_BUILTINS_OBJS += test-oidmap.o
 TEST_BUILTINS_OBJS += test-online-cpus.o
 TEST_BUILTINS_OBJS += test-parse-options.o
 TEST_BUILTINS_OBJS += test-parse-pathspec-file.o
+TEST_BUILTINS_OBJS += test-partial-clone.o
 TEST_BUILTINS_OBJS += test-path-utils.o
 TEST_BUILTINS_OBJS += test-pcre2-config.o
 TEST_BUILTINS_OBJS += test-pkt-line.o

object-file.c

@@ -1570,15 +1570,12 @@ static int do_oid_object_info_extended(struct repository *r,
 		}
 
 		/* Check if it is a missing object */
-		if (fetch_if_missing && has_promisor_remote() &&
-		    !already_retried && r == the_repository &&
+		if (fetch_if_missing && repo_has_promisor_remote(r) &&
+		    !already_retried &&
 		    !(flags & OBJECT_INFO_SKIP_FETCH_OBJECT)) {
 			/*
 			 * TODO Investigate checking promisor_remote_get_direct()
 			 * TODO return value and stopping on error here.
-			 * TODO Pass a repository struct through
-			 * promisor_remote_get_direct(), such that arbitrary
-			 * repositories work.
 			 */
 			promisor_remote_get_direct(r, real, 1);
 			already_retried = 1;

promisor-remote.c

@@ -10,7 +10,8 @@ struct promisor_remote_config {
 	struct promisor_remote **promisors_tail;
 };
 
-static int fetch_objects(const char *remote_name,
+static int fetch_objects(struct repository *repo,
+			 const char *remote_name,
 			 const struct object_id *oids,
 			 int oid_nr)
 {
@@ -20,6 +21,8 @@ static int fetch_objects(const char *remote_name,
 
 	child.git_cmd = 1;
 	child.in = -1;
+	if (repo != the_repository)
+		prepare_other_repo_env(&child.env_array, repo->gitdir);
 	strvec_pushl(&child.args, "-c", "fetch.negotiationAlgorithm=noop",
 		     "fetch", remote_name, "--no-tags",
 		     "--no-write-fetch-head", "--recurse-submodules=no",
@@ -240,10 +243,8 @@ int promisor_remote_get_direct(struct repository *repo,
 
 	promisor_remote_init(repo);
 
-	if (repo != the_repository)
-		BUG("only the_repository is supported for now");
 	for (r = repo->promisor_remote_config->promisors; r; r = r->next) {
-		if (fetch_objects(r->name, remaining_oids, remaining_nr) < 0) {
+		if (fetch_objects(repo, r->name, remaining_oids, remaining_nr) < 0) {
 			if (remaining_nr == 1)
 				continue;
 			remaining_nr = remove_fetched_oids(repo, &remaining_oids,

t/helper/test-partial-clone.c

@@ -0,0 +1,43 @@
+#include "cache.h"
+#include "test-tool.h"
+#include "repository.h"
+#include "object-store.h"
+
+/*
+ * Prints the size of the object corresponding to the given hash in a specific
+ * gitdir. This is similar to "git -C gitdir cat-file -s", except that this
+ * exercises the code that accesses the object of an arbitrary repository that
+ * is not the_repository. ("git -C gitdir" makes it so that the_repository is
+ * the one in gitdir.)
+ */
+static void object_info(const char *gitdir, const char *oid_hex)
+{
+	struct repository r;
+	struct object_id oid;
+	unsigned long size;
+	struct object_info oi = {.sizep = &size};
+	const char *p;
+
+	if (repo_init(&r, gitdir, NULL))
+		die("could not init repo");
+	if (parse_oid_hex(oid_hex, &oid, &p))
+		die("could not parse oid");
+	if (oid_object_info_extended(&r, &oid, &oi, 0))
+		die("could not obtain object info");
+	printf("%d\n", (int) size);
+}
+
+int cmd__partial_clone(int argc, const char **argv)
+{
+	setup_git_directory();
+
+	if (argc < 4)
+		die("too few arguments");
+
+	if (!strcmp(argv[1], "object-info"))
+		object_info(argv[2], argv[3]);
+	else
+		die("invalid argument '%s'", argv[1]);
+
+	return 0;
+}

t/helper/test-tool.c

@@ -46,6 +46,7 @@ static struct test_cmd cmds[] = {
 	{ "online-cpus", cmd__online_cpus },
 	{ "parse-options", cmd__parse_options },
 	{ "parse-pathspec-file", cmd__parse_pathspec_file },
+	{ "partial-clone", cmd__partial_clone },
 	{ "path-utils", cmd__path_utils },
 	{ "pcre2-config", cmd__pcre2_config },
 	{ "pkt-line", cmd__pkt_line },

t/helper/test-tool.h

@@ -35,6 +35,7 @@ int cmd__oidmap(int argc, const char **argv);
 int cmd__online_cpus(int argc, const char **argv);
 int cmd__parse_options(int argc, const char **argv);
 int cmd__parse_pathspec_file(int argc, const char** argv);
+int cmd__partial_clone(int argc, const char **argv);
 int cmd__path_utils(int argc, const char **argv);
 int cmd__pcre2_config(int argc, const char **argv);
 int cmd__pkt_line(int argc, const char **argv);

t/t0410-partial-clone.sh

@@ -604,6 +604,29 @@ test_expect_success 'do not fetch when checking existence of tree we construct o
 	git -C repo cherry-pick side1
 '
 
+test_expect_success 'lazy-fetch when accessing object not in the_repository' '
+	rm -rf full partial.git &&
+	test_create_repo full &&
+	test_commit -C full create-a-file file.txt &&
+
+	test_config -C full uploadpack.allowfilter 1 &&
+	test_config -C full uploadpack.allowanysha1inwant 1 &&
+	git clone --filter=blob:none --bare "file://$(pwd)/full" partial.git &&
+	FILE_HASH=$(git -C full rev-parse HEAD:file.txt) &&
+
+	# Sanity check that the file is missing
+	git -C partial.git rev-list --objects --missing=print HEAD >out &&
+	grep "[?]$FILE_HASH" out &&
+
+	git -C full cat-file -s "$FILE_HASH" >expect &&
+	test-tool partial-clone object-info partial.git "$FILE_HASH" >actual &&
+	test_cmp expect actual &&
+
+	# Sanity check that the file is now present
+	git -C partial.git rev-list --objects --missing=print HEAD >out &&
+	! grep "[?]$FILE_HASH" out
+'
+
 . "$TEST_DIRECTORY"/lib-httpd.sh
 start_httpd