Merge branch 'pc/submodule-helper-foreach'

The bulk of "git submodule foreach" has been rewritten in C.

* pc/submodule-helper-foreach:
  submodule: port submodule subcommand 'foreach' from shell to C
  submodule foreach: document variable '$displaypath'
  submodule foreach: document '$sm_path' instead of '$path'
  submodule foreach: correct '$path' in nested submodules from a subdirectory

4 files changed, 190 insertions, 47 deletions

diff --git a/Documentation/git-submodule.txt b/Documentation/git-submodule.txt
index ef9d9d28a9..ba3c4df550 100644
--- a/Documentation/git-submodule.txt
+++ b/Documentation/git-submodule.txt
@@ -183,12 +183,17 @@ information too.
 
 foreach [--recursive] <command>::
 	Evaluates an arbitrary shell command in each checked out submodule.
-	The command has access to the variables $name, $path, $sha1 and
-	$toplevel:
+	The command has access to the variables $name, $sm_path, $displaypath,
+	$sha1 and $toplevel:
 	$name is the name of the relevant submodule section in `.gitmodules`,
-	$path is the name of the submodule directory relative to the
-	superproject, $sha1 is the commit as recorded in the superproject,
-	and $toplevel is the absolute path to the top-level of the superproject.
+	$sm_path is the path of the submodule as recorded in the immediate
+	superproject, $displaypath contains the relative path from the
+	current working directory to the submodules root directory,
+	$sha1 is the commit as recorded in the immediate
+	superproject, and $toplevel is the absolute path to the top-level
+	of the immediate superproject.
+	Note that to avoid conflicts with '$PATH' on Windows, the '$path'
+	variable is now a deprecated synonym of '$sm_path' variable.
 	Any submodules defined in the superproject but not checked out are
 	ignored by this command. Unless given `--quiet`, foreach prints the name
 	of each submodule before evaluating the command.
diff --git a/builtin/submodule--helper.c b/builtin/submodule--helper.c
index bd250ca216..c9c2f0e102 100644
--- a/builtin/submodule--helper.c
+++ b/builtin/submodule--helper.c
@@ -440,6 +440,149 @@ static void for_each_listed_submodule(const struct module_list *list,
 		fn(list->entries[i], cb_data);
 }
 
+struct cb_foreach {
+	int argc;
+	const char **argv;
+	const char *prefix;
+	int quiet;
+	int recursive;
+};
+#define CB_FOREACH_INIT { 0 }
+
+static void runcommand_in_submodule_cb(const struct cache_entry *list_item,
+				       void *cb_data)
+{
+	struct cb_foreach *info = cb_data;
+	const char *path = list_item->name;
+	const struct object_id *ce_oid = &list_item->oid;
+
+	const struct submodule *sub;
+	struct child_process cp = CHILD_PROCESS_INIT;
+	char *displaypath;
+
+	displaypath = get_submodule_displaypath(path, info->prefix);
+
+	sub = submodule_from_path(the_repository, &null_oid, path);
+
+	if (!sub)
+		die(_("No url found for submodule path '%s' in .gitmodules"),
+			displaypath);
+
+	if (!is_submodule_populated_gently(path, NULL))
+		goto cleanup;
+
+	prepare_submodule_repo_env(&cp.env_array);
+
+	/*
+	 * For the purpose of executing <command> in the submodule,
+	 * separate shell is used for the purpose of running the
+	 * child process.
+	 */
+	cp.use_shell = 1;
+	cp.dir = path;
+
+	/*
+	 * NEEDSWORK: the command currently has access to the variables $name,
+	 * $sm_path, $displaypath, $sha1 and $toplevel only when the command
+	 * contains a single argument. This is done for maintaining a faithful
+	 * translation from shell script.
+	 */
+	if (info->argc == 1) {
+		char *toplevel = xgetcwd();
+		struct strbuf sb = STRBUF_INIT;
+
+		argv_array_pushf(&cp.env_array, "name=%s", sub->name);
+		argv_array_pushf(&cp.env_array, "sm_path=%s", path);
+		argv_array_pushf(&cp.env_array, "displaypath=%s", displaypath);
+		argv_array_pushf(&cp.env_array, "sha1=%s",
+				oid_to_hex(ce_oid));
+		argv_array_pushf(&cp.env_array, "toplevel=%s", toplevel);
+
+		/*
+		 * Since the path variable was accessible from the script
+		 * before porting, it is also made available after porting.
+		 * The environment variable "PATH" has a very special purpose
+		 * on windows. And since environment variables are
+		 * case-insensitive in windows, it interferes with the
+		 * existing PATH variable. Hence, to avoid that, we expose
+		 * path via the args argv_array and not via env_array.
+		 */
+		sq_quote_buf(&sb, path);
+		argv_array_pushf(&cp.args, "path=%s; %s",
+				 sb.buf, info->argv[0]);
+		strbuf_release(&sb);
+		free(toplevel);
+	} else {
+		argv_array_pushv(&cp.args, info->argv);
+	}
+
+	if (!info->quiet)
+		printf(_("Entering '%s'\n"), displaypath);
+
+	if (info->argv[0] && run_command(&cp))
+		die(_("run_command returned non-zero status for %s\n."),
+			displaypath);
+
+	if (info->recursive) {
+		struct child_process cpr = CHILD_PROCESS_INIT;
+
+		cpr.git_cmd = 1;
+		cpr.dir = path;
+		prepare_submodule_repo_env(&cpr.env_array);
+
+		argv_array_pushl(&cpr.args, "--super-prefix", NULL);
+		argv_array_pushf(&cpr.args, "%s/", displaypath);
+		argv_array_pushl(&cpr.args, "submodule--helper", "foreach", "--recursive",
+				NULL);
+
+		if (info->quiet)
+			argv_array_push(&cpr.args, "--quiet");
+
+		argv_array_pushv(&cpr.args, info->argv);
+
+		if (run_command(&cpr))
+			die(_("run_command returned non-zero status while"
+				"recursing in the nested submodules of %s\n."),
+				displaypath);
+	}
+
+cleanup:
+	free(displaypath);
+}
+
+static int module_foreach(int argc, const char **argv, const char *prefix)
+{
+	struct cb_foreach info = CB_FOREACH_INIT;
+	struct pathspec pathspec;
+	struct module_list list = MODULE_LIST_INIT;
+
+	struct option module_foreach_options[] = {
+		OPT__QUIET(&info.quiet, N_("Suppress output of entering each submodule command")),
+		OPT_BOOL(0, "recursive", &info.recursive,
+			 N_("Recurse into nested submodules")),
+		OPT_END()
+	};
+
+	const char *const git_submodule_helper_usage[] = {
+		N_("git submodule--helper foreach [--quiet] [--recursive] <command>"),
+		NULL
+	};
+
+	argc = parse_options(argc, argv, prefix, module_foreach_options,
+			     git_submodule_helper_usage, PARSE_OPT_KEEP_UNKNOWN);
+
+	if (module_list_compute(0, NULL, prefix, &pathspec, &list) < 0)
+		return 1;
+
+	info.argc = argc;
+	info.argv = argv;
+	info.prefix = prefix;
+
+	for_each_listed_submodule(&list, runcommand_in_submodule_cb, &info);
+
+	return 0;
+}
+
 struct init_cb {
 	const char *prefix;
 	unsigned int flags;
@@ -1876,6 +2019,7 @@ static struct cmd_struct commands[] = {
 	{"relative-path", resolve_relative_path, 0},
 	{"resolve-relative-url", resolve_relative_url, 0},
 	{"resolve-relative-url-test", resolve_relative_url_test, 0},
+	{"foreach", module_foreach, SUPPORT_SUPER_PREFIX},
 	{"init", module_init, SUPPORT_SUPER_PREFIX},
 	{"status", module_status, SUPPORT_SUPER_PREFIX},
 	{"print-default-remote", print_default_remote, 0},
diff --git a/git-submodule.sh b/git-submodule.sh
index 78073cd87d..5f9d9f6ea3 100755
--- a/git-submodule.sh
+++ b/git-submodule.sh
@@ -335,45 +335,7 @@ cmd_foreach()
 		shift
 	done
 
-	toplevel=$(pwd)
-
-	# dup stdin so that it can be restored when running the external
-	# command in the subshell (and a recursive call to this function)
-	exec 3<&0
-
-	{
-		git submodule--helper list --prefix "$wt_prefix" ||
-		echo "#unmatched" $?
-	} |
-	while read -r mode sha1 stage sm_path
-	do
-		die_if_unmatched "$mode" "$sha1"
-		if test -e "$sm_path"/.git
-		then
-			displaypath=$(git submodule--helper relative-path "$prefix$sm_path" "$wt_prefix")
-			say "$(eval_gettext "Entering '\$displaypath'")"
-			name=$(git submodule--helper name "$sm_path")
-			(
-				prefix="$prefix$sm_path/"
-				sanitize_submodule_env
-				cd "$sm_path" &&
-				sm_path=$(git submodule--helper relative-path "$sm_path" "$wt_prefix") &&
-				# we make $path available to scripts ...
-				path=$sm_path &&
-				if test $# -eq 1
-				then
-					eval "$1"
-				else
-					"$@"
-				fi &&
-				if test -n "$recursive"
-				then
-					cmd_foreach "--recursive" "$@"
-				fi
-			) <&3 3<&- ||
-			die "$(eval_gettext "Stopping at '\$displaypath'; script returned non-zero status.")"
-		fi
-	done
+	git ${wt_prefix:+-C "$wt_prefix"} ${prefix:+--super-prefix "$prefix"} submodule--helper foreach ${GIT_QUIET:+--quiet} ${recursive:+--recursive} "$@"
 }
 
 #
diff --git a/t/t7407-submodule-foreach.sh b/t/t7407-submodule-foreach.sh
index 6ba5daf42e..77729ac4aa 100755
--- a/t/t7407-submodule-foreach.sh
+++ b/t/t7407-submodule-foreach.sh
@@ -82,16 +82,16 @@ test_expect_success 'test basic "submodule foreach" usage' '
 
 cat >expect <<EOF
 Entering '../sub1'
-$pwd/clone-foo1-../sub1-$sub1sha1
+$pwd/clone-foo1-sub1-../sub1-$sub1sha1
 Entering '../sub3'
-$pwd/clone-foo3-../sub3-$sub3sha1
+$pwd/clone-foo3-sub3-../sub3-$sub3sha1
 EOF
 
 test_expect_success 'test "submodule foreach" from subdirectory' '
 	mkdir clone/sub &&
 	(
 		cd clone/sub &&
-		git submodule foreach "echo \$toplevel-\$name-\$sm_path-\$sha1" >../../actual
+		git submodule foreach "echo \$toplevel-\$name-\$sm_path-\$displaypath-\$sha1" >../../actual
 	) &&
 	test_i18ncmp expect actual
 '
@@ -196,6 +196,38 @@ test_expect_success 'test messages from "foreach --recursive" from subdirectory'
 	) &&
 	test_i18ncmp expect actual
 '
+sub1sha1=$(cd clone2/sub1 && git rev-parse HEAD)
+sub2sha1=$(cd clone2/sub2 && git rev-parse HEAD)
+sub3sha1=$(cd clone2/sub3 && git rev-parse HEAD)
+nested1sha1=$(cd clone2/nested1 && git rev-parse HEAD)
+nested2sha1=$(cd clone2/nested1/nested2 && git rev-parse HEAD)
+nested3sha1=$(cd clone2/nested1/nested2/nested3 && git rev-parse HEAD)
+submodulesha1=$(cd clone2/nested1/nested2/nested3/submodule && git rev-parse HEAD)
+
+cat >expect <<EOF
+Entering '../nested1'
+toplevel: $pwd/clone2 name: nested1 path: nested1 displaypath: ../nested1 hash: $nested1sha1
+Entering '../nested1/nested2'
+toplevel: $pwd/clone2/nested1 name: nested2 path: nested2 displaypath: ../nested1/nested2 hash: $nested2sha1
+Entering '../nested1/nested2/nested3'
+toplevel: $pwd/clone2/nested1/nested2 name: nested3 path: nested3 displaypath: ../nested1/nested2/nested3 hash: $nested3sha1
+Entering '../nested1/nested2/nested3/submodule'
+toplevel: $pwd/clone2/nested1/nested2/nested3 name: submodule path: submodule displaypath: ../nested1/nested2/nested3/submodule hash: $submodulesha1
+Entering '../sub1'
+toplevel: $pwd/clone2 name: foo1 path: sub1 displaypath: ../sub1 hash: $sub1sha1
+Entering '../sub2'
+toplevel: $pwd/clone2 name: foo2 path: sub2 displaypath: ../sub2 hash: $sub2sha1
+Entering '../sub3'
+toplevel: $pwd/clone2 name: foo3 path: sub3 displaypath: ../sub3 hash: $sub3sha1
+EOF
+
+test_expect_success 'test "submodule foreach --recursive" from subdirectory' '
+	(
+		cd clone2/untracked &&
+		git submodule foreach --recursive "echo toplevel: \$toplevel name: \$name path: \$sm_path displaypath: \$displaypath hash: \$sha1" >../../actual
+	) &&
+	test_i18ncmp expect actual
+'
 
 cat > expect <<EOF
 nested1-nested1