Merge branch 'js/apply-partial-clone-filters-recursively'

"git clone --filter=... --recurse-submodules" only makes the
top-level a partial clone, while submodules are fully cloned.  This
behaviour is changed to pass the same filter down to the submodules.

* js/apply-partial-clone-filters-recursively:
  clone, submodule: pass partial clone filters to submodules

Documentation/config/clone.txt

@@ -6,3 +6,8 @@ clone.defaultRemoteName::
 clone.rejectShallow::
 	Reject to clone a repository if it is a shallow one, can be overridden by
 	passing option `--reject-shallow` in command line. See linkgit:git-clone[1]
+
+clone.filterSubmodules::
+	If a partial clone filter is provided (see `--filter` in
+	linkgit:git-rev-list[1]) and `--recurse-submodules` is used, also apply
+	the filter to submodules.

Documentation/git-clone.txt

@@ -16,7 +16,7 @@ SYNOPSIS
 	  [--depth <depth>] [--[no-]single-branch] [--no-tags]
 	  [--recurse-submodules[=<pathspec>]] [--[no-]shallow-submodules]
 	  [--[no-]remote-submodules] [--jobs <n>] [--sparse] [--[no-]reject-shallow]
-	  [--filter=<filter>] [--] <repository>
+	  [--filter=<filter> [--also-filter-submodules]] [--] <repository>
 	  [<directory>]
 
 DESCRIPTION
@@ -182,6 +182,11 @@ objects from the source repository into a pack in the cloned repository.
 	at least `<size>`. For more details on filter specifications, see
 	the `--filter` option in linkgit:git-rev-list[1].
 
+--also-filter-submodules::
+	Also apply the partial clone filter to any submodules in the repository.
+	Requires `--filter` and `--recurse-submodules`. This can be turned on by
+	default by setting the `clone.filterSubmodules` config option.
+
 --mirror::
 	Set up a mirror of the source repository.  This implies `--bare`.
 	Compared to `--bare`, `--mirror` not only maps local branches of the

Documentation/git-submodule.txt

@@ -133,7 +133,7 @@ If you really want to remove a submodule from the repository and commit
 that use linkgit:git-rm[1] instead. See linkgit:gitsubmodules[7] for removal
 options.
 
-update [--init] [--remote] [-N|--no-fetch] [--[no-]recommend-shallow] [-f|--force] [--checkout|--rebase|--merge] [--reference <repository>] [--depth <depth>] [--recursive] [--jobs <n>] [--[no-]single-branch] [--] [<path>...]::
+update [--init] [--remote] [-N|--no-fetch] [--[no-]recommend-shallow] [-f|--force] [--checkout|--rebase|--merge] [--reference <repository>] [--depth <depth>] [--recursive] [--jobs <n>] [--[no-]single-branch] [--filter <filter spec>] [--] [<path>...]::
 +
 --
 Update the registered submodules to match what the superproject
@@ -177,6 +177,10 @@ submodule with the `--init` option.
 
 If `--recursive` is specified, this command will recurse into the
 registered submodules, and update any nested submodules within.
+
+If `--filter <filter spec>` is specified, the given partial clone filter will be
+applied to the submodule. See linkgit:git-rev-list[1] for details on filter
+specifications.
 --
 set-branch (-b|--branch) <branch> [--] <path>::
 set-branch (-d|--default) [--] <path>::

builtin/clone.c

@@ -72,6 +72,8 @@ static int option_dissociate;
 static int max_jobs = -1;
 static struct string_list option_recurse_submodules = STRING_LIST_INIT_NODUP;
 static struct list_objects_filter_options filter_options;
+static int option_filter_submodules = -1;    /* unspecified */
+static int config_filter_submodules = -1;    /* unspecified */
 static struct string_list server_options = STRING_LIST_INIT_NODUP;
 static int option_remote_submodules;
 
@@ -151,6 +153,8 @@ static struct option builtin_clone_options[] = {
 	OPT_SET_INT('6', "ipv6", &family, N_("use IPv6 addresses only"),
 			TRANSPORT_FAMILY_IPV6),
 	OPT_PARSE_LIST_OBJECTS_FILTER(&filter_options),
+	OPT_BOOL(0, "also-filter-submodules", &option_filter_submodules,
+		    N_("apply partial clone filters to submodules")),
 	OPT_BOOL(0, "remote-submodules", &option_remote_submodules,
 		    N_("any cloned submodules will use their remote-tracking branch")),
 	OPT_BOOL(0, "sparse", &option_sparse_checkout,
@@ -651,7 +655,7 @@ static int git_sparse_checkout_init(const char *repo)
 	return result;
 }
 
-static int checkout(int submodule_progress)
+static int checkout(int submodule_progress, int filter_submodules)
 {
 	struct object_id oid;
 	char *head;
@@ -730,6 +734,10 @@ static int checkout(int submodule_progress)
 			strvec_push(&args, "--no-fetch");
 		}
 
+		if (filter_submodules && filter_options.choice)
+			strvec_pushf(&args, "--filter=%s",
+				     expand_list_objects_filter_spec(&filter_options));
+
 		if (option_single_branch >= 0)
 			strvec_push(&args, option_single_branch ?
 					       "--single-branch" :
@@ -750,6 +758,8 @@ static int git_clone_config(const char *k, const char *v, void *cb)
 	}
 	if (!strcmp(k, "clone.rejectshallow"))
 		config_reject_shallow = git_config_bool(k, v);
+	if (!strcmp(k, "clone.filtersubmodules"))
+		config_filter_submodules = git_config_bool(k, v);
 
 	return git_default_config(k, v, cb);
 }
@@ -872,6 +882,7 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 	struct remote *remote;
 	int err = 0, complete_refs_before_fetch = 1;
 	int submodule_progress;
+	int filter_submodules = 0;
 
 	struct transport_ls_refs_options transport_ls_refs_options =
 		TRANSPORT_LS_REFS_OPTIONS_INIT;
@@ -1067,6 +1078,27 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 	if (option_reject_shallow != -1)
 		reject_shallow = option_reject_shallow;
 
+	/*
+	 * If option_filter_submodules is specified from CLI option,
+	 * ignore config_filter_submodules from git_clone_config.
+	 */
+	if (config_filter_submodules != -1)
+		filter_submodules = config_filter_submodules;
+	if (option_filter_submodules != -1)
+		filter_submodules = option_filter_submodules;
+
+	/*
+	 * Exit if the user seems to be doing something silly with submodule
+	 * filter flags (but not with filter configs, as those should be
+	 * set-and-forget).
+	 */
+	if (option_filter_submodules > 0 && !filter_options.choice)
+		die(_("the option '%s' requires '%s'"),
+		    "--also-filter-submodules", "--filter");
+	if (option_filter_submodules > 0 && !option_recurse_submodules.nr)
+		die(_("the option '%s' requires '%s'"),
+		    "--also-filter-submodules", "--recurse-submodules");
+
 	/*
 	 * apply the remote name provided by --origin only after this second
 	 * call to git_config, to ensure it overrides all config-based values.
@@ -1300,7 +1332,7 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 	}
 
 	junk_mode = JUNK_LEAVE_REPO;
-	err = checkout(submodule_progress);
+	err = checkout(submodule_progress, filter_submodules);
 
 	free(remote_name);
 	strbuf_release(&reflog_msg);

builtin/submodule--helper.c

@@ -21,6 +21,7 @@
 #include "object-store.h"
 #include "advice.h"
 #include "branch.h"
+#include "list-objects-filter-options.h"
 
 #define OPT_QUIET (1 << 0)
 #define OPT_CACHED (1 << 1)
@@ -1631,6 +1632,7 @@ struct module_clone_data {
 	const char *name;
 	const char *url;
 	const char *depth;
+	struct list_objects_filter_options *filter_options;
 	struct string_list reference;
 	unsigned int quiet: 1;
 	unsigned int progress: 1;
@@ -1797,6 +1799,10 @@ static int clone_submodule(struct module_clone_data *clone_data)
 			strvec_push(&cp.args, "--dissociate");
 		if (sm_gitdir && *sm_gitdir)
 			strvec_pushl(&cp.args, "--separate-git-dir", sm_gitdir, NULL);
+		if (clone_data->filter_options && clone_data->filter_options->choice)
+			strvec_pushf(&cp.args, "--filter=%s",
+				     expand_list_objects_filter_spec(
+					     clone_data->filter_options));
 		if (clone_data->single_branch >= 0)
 			strvec_push(&cp.args, clone_data->single_branch ?
 				    "--single-branch" :
@@ -1853,6 +1859,7 @@ static int module_clone(int argc, const char **argv, const char *prefix)
 {
 	int dissociate = 0, quiet = 0, progress = 0, require_init = 0;
 	struct module_clone_data clone_data = MODULE_CLONE_DATA_INIT;
+	struct list_objects_filter_options filter_options;
 
 	struct option module_clone_options[] = {
 		OPT_STRING(0, "prefix", &clone_data.prefix,
@@ -1882,17 +1889,19 @@ static int module_clone(int argc, const char **argv, const char *prefix)
 			   N_("disallow cloning into non-empty directory")),
 		OPT_BOOL(0, "single-branch", &clone_data.single_branch,
 			 N_("clone only one branch, HEAD or --branch")),
+		OPT_PARSE_LIST_OBJECTS_FILTER(&filter_options),
 		OPT_END()
 	};
 
 	const char *const git_submodule_helper_usage[] = {
 		N_("git submodule--helper clone [--prefix=<path>] [--quiet] "
 		   "[--reference <repository>] [--name <name>] [--depth <depth>] "
-		   "[--single-branch] "
+		   "[--single-branch] [--filter <filter-spec>]"
 		   "--url <url> --path <path>"),
 		NULL
 	};
 
+	memset(&filter_options, 0, sizeof(filter_options));
 	argc = parse_options(argc, argv, prefix, module_clone_options,
 			     git_submodule_helper_usage, 0);
 
@@ -1900,12 +1909,14 @@ static int module_clone(int argc, const char **argv, const char *prefix)
 	clone_data.quiet = !!quiet;
 	clone_data.progress = !!progress;
 	clone_data.require_init = !!require_init;
+	clone_data.filter_options = &filter_options;
 
 	if (argc || !clone_data.url || !clone_data.path || !*(clone_data.path))
 		usage_with_options(git_submodule_helper_usage,
 				   module_clone_options);
 
 	clone_submodule(&clone_data);
+	list_objects_filter_release(&filter_options);
 	return 0;
 }
 
@@ -1995,6 +2006,7 @@ struct submodule_update_clone {
 	const char *recursive_prefix;
 	const char *prefix;
 	int single_branch;
+	struct list_objects_filter_options *filter_options;
 
 	/* to be consumed by git-submodule.sh */
 	struct update_clone_data *update_clone;
@@ -2155,6 +2167,9 @@ static int prepare_to_clone_next_submodule(const struct cache_entry *ce,
 		strvec_pushl(&child->args, "--prefix", suc->prefix, NULL);
 	if (suc->recommend_shallow && sub->recommend_shallow == 1)
 		strvec_push(&child->args, "--depth=1");
+	if (suc->filter_options && suc->filter_options->choice)
+		strvec_pushf(&child->args, "--filter=%s",
+			     expand_list_objects_filter_spec(suc->filter_options));
 	if (suc->require_init)
 		strvec_push(&child->args, "--require-init");
 	strvec_pushl(&child->args, "--path", sub->path, NULL);
@@ -2499,6 +2514,8 @@ static int update_clone(int argc, const char **argv, const char *prefix)
 	const char *update = NULL;
 	struct pathspec pathspec;
 	struct submodule_update_clone suc = SUBMODULE_UPDATE_CLONE_INIT;
+	struct list_objects_filter_options filter_options;
+	int ret;
 
 	struct option module_update_clone_options[] = {
 		OPT_STRING(0, "prefix", &prefix,
@@ -2529,6 +2546,7 @@ static int update_clone(int argc, const char **argv, const char *prefix)
 			   N_("disallow cloning into non-empty directory")),
 		OPT_BOOL(0, "single-branch", &suc.single_branch,
 			 N_("clone only one branch, HEAD or --branch")),
+		OPT_PARSE_LIST_OBJECTS_FILTER(&filter_options),
 		OPT_END()
 	};
 
@@ -2541,20 +2559,26 @@ static int update_clone(int argc, const char **argv, const char *prefix)
 	update_clone_config_from_gitmodules(&suc.max_jobs);
 	git_config(git_update_clone_config, &suc.max_jobs);
 
+	memset(&filter_options, 0, sizeof(filter_options));
 	argc = parse_options(argc, argv, prefix, module_update_clone_options,
 			     git_submodule_helper_usage, 0);
+	suc.filter_options = &filter_options;
 
 	if (update)
 		if (parse_submodule_update_strategy(update, &suc.update) < 0)
 			die(_("bad value for update parameter"));
 
-	if (module_list_compute(argc, argv, prefix, &pathspec, &suc.list) < 0)
+	if (module_list_compute(argc, argv, prefix, &pathspec, &suc.list) < 0) {
+		list_objects_filter_release(&filter_options);
 		return 1;
+	}
 
 	if (pathspec.nr)
 		suc.warn_if_uninitialized = 1;
 
-	return update_submodules(&suc);
+	ret = update_submodules(&suc);
+	list_objects_filter_release(&filter_options);
+	return ret;
 }
 
 static int run_update_procedure(int argc, const char **argv, const char *prefix)

git-submodule.sh

@@ -10,7 +10,7 @@ USAGE="[--quiet] [--cached]
    or: $dashless [--quiet] status [--cached] [--recursive] [--] [<path>...]
    or: $dashless [--quiet] init [--] [<path>...]
    or: $dashless [--quiet] deinit [-f|--force] (--all| [--] <path>...)
-   or: $dashless [--quiet] update [--init] [--remote] [-N|--no-fetch] [-f|--force] [--checkout|--merge|--rebase] [--[no-]recommend-shallow] [--reference <repository>] [--recursive] [--[no-]single-branch] [--] [<path>...]
+   or: $dashless [--quiet] update [--init [--filter=<filter-spec>]] [--remote] [-N|--no-fetch] [-f|--force] [--checkout|--merge|--rebase] [--[no-]recommend-shallow] [--reference <repository>] [--recursive] [--[no-]single-branch] [--] [<path>...]
    or: $dashless [--quiet] set-branch (--default|--branch <branch>) [--] <path>
    or: $dashless [--quiet] set-url [--] <path> <newurl>
    or: $dashless [--quiet] summary [--cached|--files] [--summary-limit <n>] [commit] [--] [<path>...]
@@ -49,6 +49,7 @@ dissociate=
 single_branch=
 jobs=
 recommend_shallow=
+filter=
 
 die_if_unmatched ()
 {
@@ -347,6 +348,14 @@ cmd_update()
 		--no-single-branch)
 			single_branch="--no-single-branch"
 			;;
+		--filter)
+			case "$2" in '') usage ;; esac
+			filter="--filter=$2"
+			shift
+			;;
+		--filter=*)
+			filter="$1"
+			;;
 		--)
 			shift
 			break
@@ -361,6 +370,11 @@ cmd_update()
 		shift
 	done
 
+	if test -n "$filter" && test "$init" != "1"
+	then
+		usage
+	fi
+
 	if test -n "$init"
 	then
 		cmd_init "--" "$@" || return
@@ -379,6 +393,7 @@ cmd_update()
 		$single_branch \
 		$recommend_shallow \
 		$jobs \
+		$filter \
 		-- \
 		"$@" || echo "#unmatched" $?
 	} | {

t/t5617-clone-submodules-remote.sh

@@ -28,6 +28,13 @@ test_expect_success 'setup' '
 	)
 '
 
+# bare clone giving "srv.bare" for use as our server.
+test_expect_success 'setup bare clone for server' '
+	git clone --bare "file://$(pwd)/." srv.bare &&
+	git -C srv.bare config --local uploadpack.allowfilter 1 &&
+	git -C srv.bare config --local uploadpack.allowanysha1inwant 1
+'
+
 test_expect_success 'clone with --no-remote-submodules' '
 	test_when_finished "rm -rf super_clone" &&
 	git clone --recurse-submodules --no-remote-submodules "file://$pwd/." super_clone &&
@@ -65,4 +72,38 @@ test_expect_success 'clone with --single-branch' '
 	)
 '
 
+# do basic partial clone from "srv.bare"
+# confirm partial clone was registered in the local config for super and sub.
+test_expect_success 'clone with --filter' '
+	git clone --recurse-submodules \
+		--filter blob:none --also-filter-submodules \
+		"file://$pwd/srv.bare" super_clone &&
+	test_cmp_config -C super_clone true remote.origin.promisor &&
+	test_cmp_config -C super_clone blob:none remote.origin.partialclonefilter &&
+	test_cmp_config -C super_clone/sub true remote.origin.promisor &&
+	test_cmp_config -C super_clone/sub blob:none remote.origin.partialclonefilter
+'
+
+# check that clone.filterSubmodules works (--also-filter-submodules can be
+# omitted)
+test_expect_success 'filters applied with clone.filterSubmodules' '
+	test_config_global clone.filterSubmodules true &&
+	git clone --recurse-submodules --filter blob:none \
+		"file://$pwd/srv.bare" super_clone2 &&
+	test_cmp_config -C super_clone2 true remote.origin.promisor &&
+	test_cmp_config -C super_clone2 blob:none remote.origin.partialclonefilter &&
+	test_cmp_config -C super_clone2/sub true remote.origin.promisor &&
+	test_cmp_config -C super_clone2/sub blob:none remote.origin.partialclonefilter
+'
+
+test_expect_success '--no-also-filter-submodules overrides clone.filterSubmodules=true' '
+	test_config_global clone.filterSubmodules true &&
+	git clone --recurse-submodules --filter blob:none \
+		--no-also-filter-submodules \
+		"file://$pwd/srv.bare" super_clone3 &&
+	test_cmp_config -C super_clone3 true remote.origin.promisor &&
+	test_cmp_config -C super_clone3 blob:none remote.origin.partialclonefilter &&
+	test_cmp_config -C super_clone3/sub false --default false remote.origin.promisor
+'
+
 test_done

t/t7814-grep-recurse-submodules.sh

@@ -544,4 +544,45 @@ test_expect_failure 'grep saves textconv cache in the appropriate repository' '
 	test_path_is_file "$sub_textconv_cache"
 '
 
+test_expect_success 'grep partially-cloned submodule' '
+	# Set up clean superproject and submodule for partial cloning.
+	git init super &&
+	git init super/sub &&
+	(
+		cd super &&
+		test_commit --no-tag "Add file in superproject" \
+			super-file "Some content for super-file" &&
+		test_commit -C sub --no-tag "Add file in submodule" \
+			sub-file "Some content for sub-file" &&
+		git submodule add ./sub &&
+		git commit -m "Add other as submodule sub" &&
+		test_tick &&
+		test_commit -C sub --no-tag --append "Update file in submodule" \
+			sub-file "Some more content for sub-file" &&
+		git add sub &&
+		git commit -m "Update submodule" &&
+		test_tick &&
+		git config --local uploadpack.allowfilter 1 &&
+		git config --local uploadpack.allowanysha1inwant 1 &&
+		git -C sub config --local uploadpack.allowfilter 1 &&
+		git -C sub config --local uploadpack.allowanysha1inwant 1
+	) &&
+	# Clone the superproject & submodule, then make sure we can lazy-fetch submodule objects.
+	git clone --filter=blob:none --also-filter-submodules \
+		--recurse-submodules "file://$(pwd)/super" partial &&
+	(
+		cd partial &&
+		cat >expect <<-\EOF &&
+		HEAD^:sub/sub-file:Some content for sub-file
+		HEAD^:super-file:Some content for super-file
+		EOF
+
+		GIT_TRACE2_EVENT="$(pwd)/trace2.log" git grep -e content \
+			--recurse-submodules HEAD^ >actual &&
+		test_cmp expect actual &&
+		# Verify that we actually fetched data from the promisor remote:
+		grep \"category\":\"promisor\",\"key\":\"fetch_count\",\"value\":\"1\" trace2.log
+	)
+'
+
 test_done