Merge branch 'sb/submodule-embed-gitdir'

A new submodule helper "git submodule embedgitdirs" to make it
easier to move embedded .git/ directory for submodules in a
superproject to .git/modules/ (and point the latter with the former
that is turned into a "gitdir:" file) has been added.

* sb/submodule-embed-gitdir:
  worktree: initialize return value for submodule_uses_worktrees
  submodule: add absorb-git-dir function
  move connect_work_tree_and_git_dir to dir.h
  worktree: check if a submodule uses worktrees
  test-lib-functions.sh: teach test_commit -C <dir>
  submodule helper: support super prefix
  submodule: use absolute path for computing relative path connecting

Documentation/git-submodule.txt

@@ -22,6 +22,7 @@ SYNOPSIS
 	      [commit] [--] [<path>...]
 'git submodule' [--quiet] foreach [--recursive] <command>
 'git submodule' [--quiet] sync [--recursive] [--] [<path>...]
+'git submodule' [--quiet] absorbgitdirs [--] [<path>...]
 
 
 DESCRIPTION
@@ -245,6 +246,20 @@ sync::
 If `--recursive` is specified, this command will recurse into the
 registered submodules, and sync any nested submodules within.
 
+absorbgitdirs::
+	If a git directory of a submodule is inside the submodule,
+	move the git directory of the submodule into its superprojects
+	`$GIT_DIR/modules` path and then connect the git directory and
+	its working directory by setting the `core.worktree` and adding
+	a .git file pointing to the git directory embedded in the
+	superprojects git directory.
++
+A repository that was cloned independently and later added as a submodule or
+old setups have the submodules git directory inside the submodule instead of
+embedded into the superprojects git directory.
++
+This command is recursive by default.
+
 OPTIONS
 -------
 -q::

builtin/submodule--helper.c

@@ -1091,21 +1091,62 @@ static int resolve_remote_submodule_branch(int argc, const char **argv,
 	return 0;
 }
 
+static int absorb_git_dirs(int argc, const char **argv, const char *prefix)
+{
+	int i;
+	struct pathspec pathspec;
+	struct module_list list = MODULE_LIST_INIT;
+	unsigned flags = ABSORB_GITDIR_RECURSE_SUBMODULES;
+
+	struct option embed_gitdir_options[] = {
+		OPT_STRING(0, "prefix", &prefix,
+			   N_("path"),
+			   N_("path into the working tree")),
+		OPT_BIT(0, "--recursive", &flags, N_("recurse into submodules"),
+			ABSORB_GITDIR_RECURSE_SUBMODULES),
+		OPT_END()
+	};
+
+	const char *const git_submodule_helper_usage[] = {
+		N_("git submodule--helper embed-git-dir [<path>...]"),
+		NULL
+	};
+
+	argc = parse_options(argc, argv, prefix, embed_gitdir_options,
+			     git_submodule_helper_usage, 0);
+
+	gitmodules_config();
+	git_config(submodule_config, NULL);
+
+	if (module_list_compute(argc, argv, prefix, &pathspec, &list) < 0)
+		return 1;
+
+	for (i = 0; i < list.nr; i++)
+		absorb_git_dir_into_superproject(prefix,
+				list.entries[i]->name, flags);
+
+	return 0;
+}
+
+#define SUPPORT_SUPER_PREFIX (1<<0)
+
 struct cmd_struct {
 	const char *cmd;
 	int (*fn)(int, const char **, const char *);
+	unsigned option;
 };
 
 static struct cmd_struct commands[] = {
-	{"list", module_list},
-	{"name", module_name},
-	{"clone", module_clone},
-	{"update-clone", update_clone},
-	{"relative-path", resolve_relative_path},
-	{"resolve-relative-url", resolve_relative_url},
-	{"resolve-relative-url-test", resolve_relative_url_test},
-	{"init", module_init},
-	{"remote-branch", resolve_remote_submodule_branch}
+	{"list", module_list, 0},
+	{"name", module_name, 0},
+	{"clone", module_clone, 0},
+	{"update-clone", update_clone, 0},
+	{"relative-path", resolve_relative_path, 0},
+	{"resolve-relative-url", resolve_relative_url, 0},
+	{"resolve-relative-url-test", resolve_relative_url_test, 0},
+	{"init", module_init, 0},
+	{"remote-branch", resolve_remote_submodule_branch, 0},
+	{"absorb-git-dirs", absorb_git_dirs, SUPPORT_SUPER_PREFIX},
 };
 
 int cmd_submodule__helper(int argc, const char **argv, const char *prefix)
@@ -1115,9 +1156,15 @@ int cmd_submodule__helper(int argc, const char **argv, const char *prefix)
 		die(_("submodule--helper subcommand must be "
 		      "called with a subcommand"));
 
-	for (i = 0; i < ARRAY_SIZE(commands); i++)
-		if (!strcmp(argv[1], commands[i].cmd))
+	for (i = 0; i < ARRAY_SIZE(commands); i++) {
+		if (!strcmp(argv[1], commands[i].cmd)) {
+			if (get_super_prefix() &&
+			    !(commands[i].option & SUPPORT_SUPER_PREFIX))
+				die(_("%s doesn't support --super-prefix"),
+				    commands[i].cmd);
 			return commands[i].fn(argc - 1, argv + 1, prefix);
+		}
+	}
 
 	die(_("'%s' is not a valid submodule--helper "
 	      "subcommand"), argv[1]);

dir.c

@@ -2748,3 +2748,40 @@ void untracked_cache_add_to_index(struct index_state *istate,
 {
 	untracked_cache_invalidate_path(istate, path);
 }
+
+/* Update gitfile and core.worktree setting to connect work tree and git dir */
+void connect_work_tree_and_git_dir(const char *work_tree_, const char *git_dir_)
+{
+	struct strbuf file_name = STRBUF_INIT;
+	struct strbuf rel_path = STRBUF_INIT;
+	char *git_dir = xstrdup(real_path(git_dir_));
+	char *work_tree = xstrdup(real_path(work_tree_));
+
+	/* Update gitfile */
+	strbuf_addf(&file_name, "%s/.git", work_tree);
+	write_file(file_name.buf, "gitdir: %s",
+		   relative_path(git_dir, work_tree, &rel_path));
+
+	/* Update core.worktree setting */
+	strbuf_reset(&file_name);
+	strbuf_addf(&file_name, "%s/config", git_dir);
+	git_config_set_in_file(file_name.buf, "core.worktree",
+			       relative_path(work_tree, git_dir, &rel_path));
+
+	strbuf_release(&file_name);
+	strbuf_release(&rel_path);
+	free(work_tree);
+	free(git_dir);
+}
+
+/*
+ * Migrate the git directory of the given path from old_git_dir to new_git_dir.
+ */
+void relocate_gitdir(const char *path, const char *old_git_dir, const char *new_git_dir)
+{
+	if (rename(old_git_dir, new_git_dir) < 0)
+		die_errno(_("could not migrate git directory from '%s' to '%s'"),
+			old_git_dir, new_git_dir);
+
+	connect_work_tree_and_git_dir(path, new_git_dir);
+}

dir.h

@@ -335,4 +335,8 @@ struct untracked_cache *read_untracked_extension(const void *data, unsigned long
 void write_untracked_extension(struct strbuf *out, struct untracked_cache *untracked);
 void add_untracked_cache(struct index_state *istate);
 void remove_untracked_cache(struct index_state *istate);
+extern void connect_work_tree_and_git_dir(const char *work_tree, const char *git_dir);
+extern void relocate_gitdir(const char *path,
+			    const char *old_git_dir,
+			    const char *new_git_dir);
 #endif

git-submodule.sh

@@ -1127,6 +1127,11 @@ cmd_sync()
 	done
 }
 
+cmd_absorbgitdirs()
+{
+	git submodule--helper absorb-git-dirs --prefix "$wt_prefix" "$@"
+}
+
 # This loop parses the command line arguments to find the
 # subcommand name to dispatch.  Parsing of the subcommand specific
 # options are primarily done by the subcommand implementations.
@@ -1136,7 +1141,7 @@ cmd_sync()
 while test $# != 0 && test -z "$command"
 do
 	case "$1" in
-	add | foreach | init | deinit | update | status | summary | sync)
+	add | foreach | init | deinit | update | status | summary | sync | absorbgitdirs)
 		command=$1
 		;;
 	-q|--quiet)

git.c

@@ -493,7 +493,7 @@ static struct cmd_struct commands[] = {
 	{ "stage", cmd_add, RUN_SETUP | NEED_WORK_TREE },
 	{ "status", cmd_status, RUN_SETUP | NEED_WORK_TREE },
 	{ "stripspace", cmd_stripspace },
-	{ "submodule--helper", cmd_submodule__helper, RUN_SETUP },
+	{ "submodule--helper", cmd_submodule__helper, RUN_SETUP | SUPPORT_SUPER_PREFIX},
 	{ "symbolic-ref", cmd_symbolic_ref, RUN_SETUP },
 	{ "tag", cmd_tag, RUN_SETUP },
 	{ "unpack-file", cmd_unpack_file, RUN_SETUP },

submodule.c

@@ -14,6 +14,7 @@
 #include "blob.h"
 #include "thread-utils.h"
 #include "quote.h"
+#include "worktree.h"
 
 static int config_fetch_recurse_submodules = RECURSE_SUBMODULES_ON_DEMAND;
 static int parallel_jobs = 1;
@@ -1296,30 +1297,6 @@ int merge_submodule(unsigned char result[20], const char *path,
 	return 0;
 }
 
-/* Update gitfile and core.worktree setting to connect work tree and git dir */
-void connect_work_tree_and_git_dir(const char *work_tree, const char *git_dir)
-{
-	struct strbuf file_name = STRBUF_INIT;
-	struct strbuf rel_path = STRBUF_INIT;
-	const char *real_work_tree = xstrdup(real_path(work_tree));
-
-	/* Update gitfile */
-	strbuf_addf(&file_name, "%s/.git", work_tree);
-	write_file(file_name.buf, "gitdir: %s",
-		   relative_path(git_dir, real_work_tree, &rel_path));
-
-	/* Update core.worktree setting */
-	strbuf_reset(&file_name);
-	strbuf_addf(&file_name, "%s/config", git_dir);
-	git_config_set_in_file(file_name.buf, "core.worktree",
-			       relative_path(real_work_tree, git_dir,
-					     &rel_path));
-
-	strbuf_release(&file_name);
-	strbuf_release(&rel_path);
-	free((void *)real_work_tree);
-}
-
 int parallel_submodules(void)
 {
 	return parallel_jobs;
@@ -1335,3 +1312,105 @@ void prepare_submodule_repo_env(struct argv_array *out)
 	}
 	argv_array_push(out, "GIT_DIR=.git");
 }
+
+/*
+ * Embeds a single submodules git directory into the superprojects git dir,
+ * non recursively.
+ */
+static void relocate_single_git_dir_into_superproject(const char *prefix,
+						      const char *path)
+{
+	char *old_git_dir = NULL, *real_old_git_dir = NULL, *real_new_git_dir = NULL;
+	const char *new_git_dir;
+	const struct submodule *sub;
+
+	if (submodule_uses_worktrees(path))
+		die(_("relocate_gitdir for submodule '%s' with "
+		      "more than one worktree not supported"), path);
+
+	old_git_dir = xstrfmt("%s/.git", path);
+	if (read_gitfile(old_git_dir))
+		/* If it is an actual gitfile, it doesn't need migration. */
+		return;
+
+	real_old_git_dir = xstrdup(real_path(old_git_dir));
+
+	sub = submodule_from_path(null_sha1, path);
+	if (!sub)
+		die(_("could not lookup name for submodule '%s'"), path);
+
+	new_git_dir = git_path("modules/%s", sub->name);
+	if (safe_create_leading_directories_const(new_git_dir) < 0)
+		die(_("could not create directory '%s'"), new_git_dir);
+	real_new_git_dir = xstrdup(real_path(new_git_dir));
+
+	if (!prefix)
+		prefix = get_super_prefix();
+
+	fprintf(stderr, _("Migrating git directory of '%s%s' from\n'%s' to\n'%s'\n"),
+		prefix ? prefix : "", path,
+		real_old_git_dir, real_new_git_dir);
+
+	relocate_gitdir(path, real_old_git_dir, real_new_git_dir);
+
+	free(old_git_dir);
+	free(real_old_git_dir);
+	free(real_new_git_dir);
+}
+
+/*
+ * Migrate the git directory of the submodule given by path from
+ * having its git directory within the working tree to the git dir nested
+ * in its superprojects git dir under modules/.
+ */
+void absorb_git_dir_into_superproject(const char *prefix,
+				      const char *path,
+				      unsigned flags)
+{
+	const char *sub_git_dir, *v;
+	char *real_sub_git_dir = NULL, *real_common_git_dir = NULL;
+	struct strbuf gitdir = STRBUF_INIT;
+
+	strbuf_addf(&gitdir, "%s/.git", path);
+	sub_git_dir = resolve_gitdir(gitdir.buf);
+
+	/* Not populated? */
+	if (!sub_git_dir)
+		goto out;
+
+	/* Is it already absorbed into the superprojects git dir? */
+	real_sub_git_dir = xstrdup(real_path(sub_git_dir));
+	real_common_git_dir = xstrdup(real_path(get_git_common_dir()));
+	if (!skip_prefix(real_sub_git_dir, real_common_git_dir, &v))
+		relocate_single_git_dir_into_superproject(prefix, path);
+
+	if (flags & ABSORB_GITDIR_RECURSE_SUBMODULES) {
+		struct child_process cp = CHILD_PROCESS_INIT;
+		struct strbuf sb = STRBUF_INIT;
+
+		if (flags & ~ABSORB_GITDIR_RECURSE_SUBMODULES)
+			die("BUG: we don't know how to pass the flags down?");
+
+		if (get_super_prefix())
+			strbuf_addstr(&sb, get_super_prefix());
+		strbuf_addstr(&sb, path);
+		strbuf_addch(&sb, '/');
+
+		cp.dir = path;
+		cp.git_cmd = 1;
+		cp.no_stdin = 1;
+		argv_array_pushl(&cp.args, "--super-prefix", sb.buf,
+					   "submodule--helper",
+					   "absorb-git-dirs", NULL);
+		prepare_submodule_repo_env(&cp.env_array);
+		if (run_command(&cp))
+			die(_("could not recurse into submodule '%s'"), path);
+
+		strbuf_release(&sb);
+	}
+
+out:
+	strbuf_release(&gitdir);
+	free(real_sub_git_dir);
+	free(real_common_git_dir);
+}

submodule.h

@@ -68,7 +68,6 @@ int find_unpushed_submodules(struct sha1_array *commits, const char *remotes_nam
 extern int push_unpushed_submodules(struct sha1_array *commits,
 				    const char *remotes_name,
 				    int dry_run);
-void connect_work_tree_and_git_dir(const char *work_tree, const char *git_dir);
 int parallel_submodules(void);
 
 /*
@@ -78,4 +77,8 @@ int parallel_submodules(void);
  */
 void prepare_submodule_repo_env(struct argv_array *out);
 
+#define ABSORB_GITDIR_RECURSE_SUBMODULES (1<<0)
+extern void absorb_git_dir_into_superproject(const char *prefix,
+					     const char *path,
+					     unsigned flags);
 #endif

t/t7412-submodule-absorbgitdirs.sh

@@ -0,0 +1,101 @@
+#!/bin/sh
+
+test_description='Test submodule absorbgitdirs
+
+This test verifies that `git submodue absorbgitdirs` moves a submodules git
+directory into the superproject.
+'
+
+. ./test-lib.sh
+
+test_expect_success 'setup a real submodule' '
+	git init sub1 &&
+	test_commit -C sub1 first &&
+	git submodule add ./sub1 &&
+	test_tick &&
+	git commit -m superproject
+'
+
+test_expect_success 'absorb the git dir' '
+	>expect.1 &&
+	>expect.2 &&
+	>actual.1 &&
+	>actual.2 &&
+	git status >expect.1 &&
+	git -C sub1 rev-parse HEAD >expect.2 &&
+	git submodule absorbgitdirs &&
+	git fsck &&
+	test -f sub1/.git &&
+	test -d .git/modules/sub1 &&
+	git status >actual.1 &&
+	git -C sub1 rev-parse HEAD >actual.2 &&
+	test_cmp expect.1 actual.1 &&
+	test_cmp expect.2 actual.2
+'
+
+test_expect_success 'absorbing does not fail for deinitalized submodules' '
+	test_when_finished "git submodule update --init" &&
+	git submodule deinit --all &&
+	git submodule absorbgitdirs &&
+	test -d .git/modules/sub1 &&
+	test -d sub1 &&
+	! test -e sub1/.git
+'
+
+test_expect_success 'setup nested submodule' '
+	git init sub1/nested &&
+	test_commit -C sub1/nested first_nested &&
+	git -C sub1 submodule add ./nested &&
+	test_tick &&
+	git -C sub1 commit -m "add nested" &&
+	git add sub1 &&
+	git commit -m "sub1 to include nested submodule"
+'
+
+test_expect_success 'absorb the git dir in a nested submodule' '
+	git status >expect.1 &&
+	git -C sub1/nested rev-parse HEAD >expect.2 &&
+	git submodule absorbgitdirs &&
+	test -f sub1/nested/.git &&
+	test -d .git/modules/sub1/modules/nested &&
+	git status >actual.1 &&
+	git -C sub1/nested rev-parse HEAD >actual.2 &&
+	test_cmp expect.1 actual.1 &&
+	test_cmp expect.2 actual.2
+'
+
+test_expect_success 'setup a gitlink with missing .gitmodules entry' '
+	git init sub2 &&
+	test_commit -C sub2 first &&
+	git add sub2 &&
+	git commit -m superproject
+'
+
+test_expect_success 'absorbing the git dir fails for incomplete submodules' '
+	git status >expect.1 &&
+	git -C sub2 rev-parse HEAD >expect.2 &&
+	test_must_fail git submodule absorbgitdirs &&
+	git -C sub2 fsck &&
+	test -d sub2/.git &&
+	git status >actual &&
+	git -C sub2 rev-parse HEAD >actual.2 &&
+	test_cmp expect.1 actual.1 &&
+	test_cmp expect.2 actual.2
+'
+
+test_expect_success 'setup a submodule with multiple worktrees' '
+	# first create another unembedded git dir in a new submodule
+	git init sub3 &&
+	test_commit -C sub3 first &&
+	git submodule add ./sub3 &&
+	test_tick &&
+	git commit -m "add another submodule" &&
+	git -C sub3 worktree add ../sub3_second_work_tree
+'
+
+test_expect_success 'absorbing fails for a submodule with multiple worktrees' '
+	test_must_fail git submodule absorbgitdirs sub3 2>error &&
+	test_i18ngrep "not supported" error
+'
+
+test_done

t/test-lib-functions.sh

@@ -157,16 +157,21 @@ debug () {
 	 GIT_TEST_GDB=1 "$@"
 }
 
-# Call test_commit with the arguments "<message> [<file> [<contents> [<tag>]]]"
+# Call test_commit with the arguments
+# [-C <directory>] <message> [<file> [<contents> [<tag>]]]"
 #
 # This will commit a file with the given contents and the given commit
 # message, and tag the resulting commit with the given tag name.
 #
 # <file>, <contents>, and <tag> all default to <message>.
+#
+# If the first argument is "-C", the second argument is used as a path for
+# the git invocations.
 
 test_commit () {
 	notick= &&
 	signoff= &&
+	indir= &&
 	while test $# != 0
 	do
 		case "$1" in
@@ -176,21 +181,26 @@ test_commit () {
 		--signoff)
 			signoff="$1"
 			;;
+		-C)
+			indir="$2"
+			shift
+			;;
 		*)
 			break
 			;;
 		esac
 		shift
 	done &&
+	indir=${indir:+"$indir"/} &&
 	file=${2:-"$1.t"} &&
-	echo "${3-$1}" > "$file" &&
-	git add "$file" &&
+	echo "${3-$1}" > "$indir$file" &&
+	git ${indir:+ -C "$indir"} add "$file" &&
 	if test -z "$notick"
 	then
 		test_tick
 	fi &&
-	git commit $signoff -m "$1" &&
-	git tag "${4:-$1}"
+	git ${indir:+ -C "$indir"} commit $signoff -m "$1" &&
+	git ${indir:+ -C "$indir"} tag "${4:-$1}"
 }
 
 # Call test_merge with the arguments "<message> <commit>", where <commit>

worktree.c

@@ -380,3 +380,53 @@ const struct worktree *find_shared_symref(const char *symref,
 
 	return existing;
 }
+
+int submodule_uses_worktrees(const char *path)
+{
+	char *submodule_gitdir;
+	struct strbuf sb = STRBUF_INIT;
+	DIR *dir;
+	struct dirent *d;
+	int ret = 0;
+	struct repository_format format;
+
+	submodule_gitdir = git_pathdup_submodule(path, "%s", "");
+	if (!submodule_gitdir)
+		return 0;
+
+	/* The env would be set for the superproject. */
+	get_common_dir_noenv(&sb, submodule_gitdir);
+
+	/*
+	 * The check below is only known to be good for repository format
+	 * version 0 at the time of writing this code.
+	 */
+	strbuf_addstr(&sb, "/config");
+	read_repository_format(&format, sb.buf);
+	if (format.version != 0) {
+		strbuf_release(&sb);
+		return 1;
+	}
+
+	/* Replace config by worktrees. */
+	strbuf_setlen(&sb, sb.len - strlen("config"));
+	strbuf_addstr(&sb, "worktrees");
+
+	/* See if there is any file inside the worktrees directory. */
+	dir = opendir(sb.buf);
+	strbuf_release(&sb);
+	free(submodule_gitdir);
+
+	if (!dir)
+		return 0;
+
+	while ((d = readdir(dir)) != NULL) {
+		if (is_dot_or_dotdot(d->d_name))
+			continue;
+
+		ret = 1;
+		break;
+	}
+	closedir(dir);
+	return ret;
+}

worktree.h

@@ -27,6 +27,11 @@ struct worktree {
  */
 extern struct worktree **get_worktrees(unsigned flags);
 
+/*
+ * Returns 1 if linked worktrees exist, 0 otherwise.
+ */
+extern int submodule_uses_worktrees(const char *path);
+
 /*
  * Return git dir of the worktree. Note that the path may be relative.
  * If wt is NULL, git dir of current worktree is returned.