Merge branch 'bw/submodule-is-active'

"what URL do we want to update this submodule?" and "are we
interested in this submodule?" are split into two distinct
concepts, and then the way used to express the latter got extended,
paving a way to make it easier to manage a project with many
submodules and make it possible to later extend use of multiple
worktrees for a project with submodules.

* bw/submodule-is-active:
  submodule add: respect submodule.active and submodule.<name>.active
  submodule--helper init: set submodule.<name>.active
  clone: teach --recurse-submodules to optionally take a pathspec
  submodule init: initialize active submodules
  submodule: decouple url and submodule interest
  submodule--helper clone: check for configured submodules using helper
  submodule sync: use submodule--helper is-active
  submodule sync: skip work for inactive submodules
  submodule status: use submodule--helper is-active
  submodule--helper: add is-active subcommand

Documentation/config.txt

@@ -3013,8 +3013,9 @@ submodule.<name>.url::
 	The URL for a submodule. This variable is copied from the .gitmodules
 	file to the git config via 'git submodule init'. The user can change
 	the configured URL before obtaining the submodule via 'git submodule
-	update'. After obtaining the submodule, the presence of this variable
-	is used as a sign whether the submodule is of interest to git commands.
+	update'. If neither submodule.<name>.active or submodule.active are
+	set, the presence of this variable is used as a fallback to indicate
+	whether the submodule is of interest to git commands.
 	See linkgit:git-submodule[1] and linkgit:gitmodules[5] for details.
 
 submodule.<name>.update::
@@ -3052,6 +3053,16 @@ submodule.<name>.ignore::
 	"--ignore-submodules" option. The 'git submodule' commands are not
 	affected by this setting.
 
+submodule.<name>.active::
+	Boolean value indicating if the submodule is of interest to git
+	commands.  This config option takes precedence over the
+	submodule.active config option.
+
+submodule.active::
+	A repeated field which contains a pathspec used to match against a
+	submodule's path to determine if the submodule is of interest to git
+	commands.
+
 submodule.fetchJobs::
 	Specifies how many submodules are fetched/cloned at the same time.
 	A positive integer allows up to that number of submodules fetched

Documentation/git-clone.txt

@@ -14,7 +14,7 @@ SYNOPSIS
 	  [-o <name>] [-b <name>] [-u <upload-pack>] [--reference <repository>]
 	  [--dissociate] [--separate-git-dir <git dir>]
 	  [--depth <depth>] [--[no-]single-branch]
-	  [--recursive | --recurse-submodules] [--[no-]shallow-submodules]
+	  [--recurse-submodules] [--[no-]shallow-submodules]
 	  [--jobs <n>] [--] <repository> [<directory>]
 
 DESCRIPTION
@@ -215,10 +215,14 @@ objects from the source repository into a pack in the cloned repository.
 	branch when `--single-branch` clone was made, no remote-tracking
 	branch is created.
 
---recursive::
---recurse-submodules::
-	After the clone is created, initialize all submodules within,
-	using their default settings. This is equivalent to running
+--recurse-submodules[=<pathspec]::
+	After the clone is created, initialize and clone submodules
+	within based on the provided pathspec.  If no pathspec is
+	provided, all submodules are initialized and cloned.
+	Submodules are initialized and cloned using their default
+	settings.  The resulting clone has `submodule.active` set to
+	the provided pathspec, or "." (meaning all submodules) if no
+	pathspec is provided.  This is equivalent to running
 	`git submodule update --init --recursive` immediately after
 	the clone is finished. This option is ignored if the cloned
 	repository does not have a worktree/checkout (i.e. if any of

Documentation/git-submodule.txt

@@ -129,7 +129,9 @@ init [--] [<path>...]::
 	repository will be assumed to be upstream.
 +
 Optional <path> arguments limit which submodules will be initialized.
-If no path is specified, all submodules are initialized.
+If no path is specified and submodule.active has been configured, submodules
+configured to be active will be initialized, otherwise all submodules are
+initialized.
 +
 When present, it will also copy the value of `submodule.$name.update`.
 This command does not alter existing information in .git/config.

builtin/clone.c

@@ -39,7 +39,7 @@ static const char * const builtin_clone_usage[] = {
 };
 
 static int option_no_checkout, option_bare, option_mirror, option_single_branch = -1;
-static int option_local = -1, option_no_hardlinks, option_shared, option_recursive;
+static int option_local = -1, option_no_hardlinks, option_shared;
 static int option_shallow_submodules;
 static int deepen;
 static char *option_template, *option_depth, *option_since;
@@ -56,6 +56,21 @@ static struct string_list option_required_reference = STRING_LIST_INIT_NODUP;
 static struct string_list option_optional_reference = STRING_LIST_INIT_NODUP;
 static int option_dissociate;
 static int max_jobs = -1;
+static struct string_list option_recurse_submodules = STRING_LIST_INIT_NODUP;
+
+static int recurse_submodules_cb(const struct option *opt,
+				 const char *arg, int unset)
+{
+	if (unset)
+		string_list_clear((struct string_list *)opt->value, 0);
+	else if (arg)
+		string_list_append((struct string_list *)opt->value, arg);
+	else
+		string_list_append((struct string_list *)opt->value,
+				   (const char *)opt->defval);
+
+	return 0;
+}
 
 static struct option builtin_clone_options[] = {
 	OPT__VERBOSITY(&option_verbosity),
@@ -74,10 +89,13 @@ static struct option builtin_clone_options[] = {
 		    N_("don't use local hardlinks, always copy")),
 	OPT_BOOL('s', "shared", &option_shared,
 		    N_("setup as shared repository")),
-	OPT_BOOL(0, "recursive", &option_recursive,
-		    N_("initialize submodules in the clone")),
-	OPT_BOOL(0, "recurse-submodules", &option_recursive,
-		    N_("initialize submodules in the clone")),
+	{ OPTION_CALLBACK, 0, "recursive", &option_recurse_submodules,
+	  N_("pathspec"), N_("initialize submodules in the clone"),
+	  PARSE_OPT_OPTARG | PARSE_OPT_HIDDEN, recurse_submodules_cb,
+	  (intptr_t)"." },
+	{ OPTION_CALLBACK, 0, "recurse-submodules", &option_recurse_submodules,
+	  N_("pathspec"), N_("initialize submodules in the clone"),
+	  PARSE_OPT_OPTARG, recurse_submodules_cb, (intptr_t)"." },
 	OPT_INTEGER('j', "jobs", &max_jobs,
 		    N_("number of submodules cloned in parallel")),
 	OPT_STRING(0, "template", &option_template, N_("template-directory"),
@@ -733,7 +751,7 @@ static int checkout(int submodule_progress)
 	err |= run_hook_le(NULL, "post-checkout", sha1_to_hex(null_sha1),
 			   oid_to_hex(&oid), "1", NULL);
 
-	if (!err && option_recursive) {
+	if (!err && (option_recurse_submodules.nr > 0)) {
 		struct argv_array args = ARGV_ARRAY_INIT;
 		argv_array_pushl(&args, "submodule", "update", "--init", "--recursive", NULL);
 
@@ -957,7 +975,25 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 			fprintf(stderr, _("Cloning into '%s'...\n"), dir);
 	}
 
-	if (option_recursive) {
+	if (option_recurse_submodules.nr > 0) {
+		struct string_list_item *item;
+		struct strbuf sb = STRBUF_INIT;
+
+		/* remove duplicates */
+		string_list_sort(&option_recurse_submodules);
+		string_list_remove_duplicates(&option_recurse_submodules, 0);
+
+		/*
+		 * NEEDSWORK: In a multi-working-tree world, this needs to be
+		 * set in the per-worktree config.
+		 */
+		for_each_string_list_item(item, &option_recurse_submodules) {
+			strbuf_addf(&sb, "submodule.active=%s",
+				    item->string);
+			string_list_append(&option_config,
+					   strbuf_detach(&sb, NULL));
+		}
+
 		if (option_required_reference.nr &&
 		    option_optional_reference.nr)
 			die(_("clone --recursive is not compatible with "

builtin/submodule--helper.c

@@ -270,6 +270,29 @@ static int module_list_compute(int argc, const char **argv,
 	return result;
 }
 
+static void module_list_active(struct module_list *list)
+{
+	int i;
+	struct module_list active_modules = MODULE_LIST_INIT;
+
+	gitmodules_config();
+
+	for (i = 0; i < list->nr; i++) {
+		const struct cache_entry *ce = list->entries[i];
+
+		if (!is_submodule_initialized(ce->name))
+			continue;
+
+		ALLOC_GROW(active_modules.entries,
+			   active_modules.nr + 1,
+			   active_modules.alloc);
+		active_modules.entries[active_modules.nr++] = ce;
+	}
+
+	free(list->entries);
+	*list = active_modules;
+}
+
 static int module_list(int argc, const char **argv, const char *prefix)
 {
 	int i;
@@ -333,6 +356,18 @@ static void init_submodule(const char *path, const char *prefix, int quiet)
 		die(_("No url found for submodule path '%s' in .gitmodules"),
 			displaypath);
 
+	/*
+	 * NEEDSWORK: In a multi-working-tree world, this needs to be
+	 * set in the per-worktree config.
+	 *
+	 * Set active flag for the submodule being initialized
+	 */
+	if (!is_submodule_initialized(path)) {
+		strbuf_reset(&sb);
+		strbuf_addf(&sb, "submodule.%s.active", sub->name);
+		git_config_set_gently(sb.buf, "true");
+	}
+
 	/*
 	 * Copy url setting when it is not set yet.
 	 * To look up the url in .git/config, we must not fall back to
@@ -420,6 +455,13 @@ static int module_init(int argc, const char **argv, const char *prefix)
 	if (module_list_compute(argc, argv, prefix, &pathspec, &list) < 0)
 		return 1;
 
+	/*
+	 * If there are no path args and submodule.active is set then,
+	 * by default, only initialize 'active' modules.
+	 */
+	if (!argc && git_config_get_value_multi("submodule.active"))
+		module_list_active(&list);
+
 	for (i = 0; i < list.nr; i++)
 		init_submodule(list.entries[i]->name, prefix, quiet);
 
@@ -741,7 +783,6 @@ static int prepare_to_clone_next_submodule(const struct cache_entry *ce,
 	struct strbuf displaypath_sb = STRBUF_INIT;
 	struct strbuf sb = STRBUF_INIT;
 	const char *displaypath = NULL;
-	char *url = NULL;
 	int needs_cloning = 0;
 
 	if (ce_stage(ce)) {
@@ -775,15 +816,8 @@ static int prepare_to_clone_next_submodule(const struct cache_entry *ce,
 		goto cleanup;
 	}
 
-	/*
-	 * Looking up the url in .git/config.
-	 * We must not fall back to .gitmodules as we only want
-	 * to process configured submodules.
-	 */
-	strbuf_reset(&sb);
-	strbuf_addf(&sb, "submodule.%s.url", sub->name);
-	git_config_get_string(sb.buf, &url);
-	if (!url) {
+	/* Check if the submodule has been initialized. */
+	if (!is_submodule_initialized(ce->name)) {
 		next_submodule_warn_missing(suc, out, displaypath);
 		goto cleanup;
 	}
@@ -817,7 +851,7 @@ static int prepare_to_clone_next_submodule(const struct cache_entry *ce,
 		argv_array_push(&child->args, "--depth=1");
 	argv_array_pushl(&child->args, "--path", sub->path, NULL);
 	argv_array_pushl(&child->args, "--name", sub->name, NULL);
-	argv_array_pushl(&child->args, "--url", url, NULL);
+	argv_array_pushl(&child->args, "--url", sub->url, NULL);
 	if (suc->references.nr) {
 		struct string_list_item *item;
 		for_each_string_list_item(item, &suc->references)
@@ -827,7 +861,6 @@ static int prepare_to_clone_next_submodule(const struct cache_entry *ce,
 		argv_array_push(&child->args, suc->depth);
 
 cleanup:
-	free(url);
 	strbuf_reset(&displaypath_sb);
 	strbuf_reset(&sb);
 
@@ -1109,6 +1142,16 @@ static int absorb_git_dirs(int argc, const char **argv, const char *prefix)
 	return 0;
 }
 
+static int is_active(int argc, const char **argv, const char *prefix)
+{
+	if (argc != 2)
+		die("submodule--helper is-active takes exactly 1 arguments");
+
+	gitmodules_config();
+
+	return !is_submodule_initialized(argv[1]);
+}
+
 #define SUPPORT_SUPER_PREFIX (1<<0)
 
 struct cmd_struct {
@@ -1128,6 +1171,7 @@ static struct cmd_struct commands[] = {
 	{"init", module_init, SUPPORT_SUPER_PREFIX},
 	{"remote-branch", resolve_remote_submodule_branch, 0},
 	{"absorb-git-dirs", absorb_git_dirs, SUPPORT_SUPER_PREFIX},
+	{"is-active", is_active, 0},
 };
 
 int cmd_submodule__helper(int argc, const char **argv, const char *prefix)

git-submodule.sh

@@ -278,6 +278,20 @@ or you are unsure what this means choose another name with the '--name' option."
 	fi &&
 	git add --force .gitmodules ||
 	die "$(eval_gettext "Failed to register submodule '\$sm_path'")"
+
+	# NEEDSWORK: In a multi-working-tree world, this needs to be
+	# set in the per-worktree config.
+	if git config --get submodule.active >/dev/null
+	then
+		# If the submodule being adding isn't already covered by the
+		# current configured pathspec, set the submodule's active flag
+		if ! git submodule--helper is-active "$sm_path"
+		then
+			git config submodule."$sm_name".active "true"
+		fi
+	else
+		git config submodule."$sm_name".active "true"
+	fi
 }
 
 #
@@ -1010,14 +1024,13 @@ cmd_status()
 	do
 		die_if_unmatched "$mode" "$sha1"
 		name=$(git submodule--helper name "$sm_path") || exit
-		url=$(git config submodule."$name".url)
 		displaypath=$(git submodule--helper relative-path "$prefix$sm_path" "$wt_prefix")
 		if test "$stage" = U
 		then
 			say "U$sha1 $displaypath"
 			continue
 		fi
-		if test -z "$url" ||
+		if ! git submodule--helper is-active "$sm_path" ||
 		{
 			! test -d "$sm_path"/.git &&
 			! test -f "$sm_path"/.git
@@ -1090,6 +1103,13 @@ cmd_sync()
 	while read mode sha1 stage sm_path
 	do
 		die_if_unmatched "$mode" "$sha1"
+
+		# skip inactive submodules
+		if ! git submodule--helper is-active "$sm_path"
+		then
+			continue
+		fi
+
 		name=$(git submodule--helper name "$sm_path")
 		url=$(git config -f .gitmodules --get submodule."$name".url)
 
@@ -1112,27 +1132,24 @@ cmd_sync()
 			;;
 		esac
 
-		if git config "submodule.$name.url" >/dev/null 2>/dev/null
+		displaypath=$(git submodule--helper relative-path "$prefix$sm_path" "$wt_prefix")
+		say "$(eval_gettext "Synchronizing submodule url for '\$displaypath'")"
+		git config submodule."$name".url "$super_config_url"
+
+		if test -e "$sm_path"/.git
 		then
-			displaypath=$(git submodule--helper relative-path "$prefix$sm_path" "$wt_prefix")
-			say "$(eval_gettext "Synchronizing submodule url for '\$displaypath'")"
-			git config submodule."$name".url "$super_config_url"
+		(
+			sanitize_submodule_env
+			cd "$sm_path"
+			remote=$(get_default_remote)
+			git config remote."$remote".url "$sub_origin_url"
 
-			if test -e "$sm_path"/.git
+			if test -n "$recursive"
 			then
-			(
-				sanitize_submodule_env
-				cd "$sm_path"
-				remote=$(get_default_remote)
-				git config remote."$remote".url "$sub_origin_url"
-
-				if test -n "$recursive"
-				then
-					prefix="$prefix$sm_path/"
-					eval cmd_sync
-				fi
-			)
+				prefix="$prefix$sm_path/"
+				eval cmd_sync
 			fi
+		)
 		fi
 	done
 }