clone: teach --recurse-submodules to optionally take a pathspec

Teach clone --recurse-submodules to optionally take a pathspec argument
which describes which submodules should be recursively initialized and
cloned.  If no pathspec is provided, --recurse-submodules will
recursively initialize and clone all submodules by using a default
pathspec of ".".  In order to construct more complex pathspecs,
--recurse-submodules can be given multiple times.

This also configures the 'submodule.active' configuration option to be
the given pathspec, such that any future invocation of `git submodule
update` will keep up with the pathspec.

Additionally the switch '--recurse' is removed from the Documentation as
well as marked hidden in the options array, to streamline the options
for submodules.  A simple '--recurse' doesn't convey what is being
recursed, e.g. it could mean directories or trees (c.f. ls-tree) In a
lot of other commands we already have '--recurse-submodules' to mean
recursing into submodules, so advertise this spelling here as the
genuine option.

Signed-off-by: Brandon Williams <bmwill@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

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

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),
 			   sha1_to_hex(sha1), "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 "

t/t7400-submodule-basic.sh

@@ -1188,4 +1188,72 @@ test_expect_success 'submodule update and setting submodule.<name>.active' '
 	test_cmp expect actual
 '
 
+test_expect_success 'clone --recurse-submodules with a pathspec works' '
+	test_when_finished "rm -rf multisuper_clone" &&
+	cat >expected <<-\EOF &&
+	 sub0 (test2)
+	-sub1
+	-sub2
+	-sub3
+	EOF
+
+	git clone --recurse-submodules="sub0" multisuper multisuper_clone &&
+	git -C multisuper_clone submodule status |cut -c1,43- >actual &&
+	test_cmp actual expected
+'
+
+test_expect_success 'clone with multiple --recurse-submodules options' '
+	test_when_finished "rm -rf multisuper_clone" &&
+	cat >expect <<-\EOF &&
+	-sub0
+	 sub1 (test2)
+	-sub2
+	 sub3 (test2)
+	EOF
+
+	git clone --recurse-submodules="." \
+		  --recurse-submodules=":(exclude)sub0" \
+		  --recurse-submodules=":(exclude)sub2" \
+		  multisuper multisuper_clone &&
+	git -C multisuper_clone submodule status |cut -c1,43- >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'clone and subsequent updates correctly auto-initialize submodules' '
+	test_when_finished "rm -rf multisuper_clone" &&
+	cat <<-\EOF >expect &&
+	-sub0
+	 sub1 (test2)
+	-sub2
+	 sub3 (test2)
+	EOF
+
+	cat <<-\EOF >expect2 &&
+	-sub0
+	 sub1 (test2)
+	-sub2
+	 sub3 (test2)
+	-sub4
+	 sub5 (test2)
+	EOF
+
+	git clone --recurse-submodules="." \
+		  --recurse-submodules=":(exclude)sub0" \
+		  --recurse-submodules=":(exclude)sub2" \
+		  --recurse-submodules=":(exclude)sub4" \
+		  multisuper multisuper_clone &&
+
+	git -C multisuper_clone submodule status |cut -c1,43- >actual &&
+	test_cmp expect actual &&
+
+	git -C multisuper submodule add ../sub1 sub4 &&
+	git -C multisuper submodule add ../sub1 sub5 &&
+	git -C multisuper commit -m "add more submodules" &&
+	# obtain the new superproject
+	git -C multisuper_clone pull &&
+	git -C multisuper_clone submodule update --init &&
+	git -C multisuper_clone submodule status |cut -c1,43- >actual &&
+	test_cmp expect2 actual
+'
+
 test_done