submodule: fixup nested submodules after moving the submodule

connect_work_tree_and_git_dir is used to connect a submodule worktree with
its git directory and vice versa after events that require a reconnection
such as moving around the working tree. As submodules can have nested
submodules themselves, we'd also want to fix the nested submodules when
asked to. Add an option to recurse into the nested submodules and connect
them as well.

As submodules are identified by their name (which determines their git
directory in relation to their superproject's git directory) internally
and by their path in the working tree of the superproject, we need to
make sure that the mapping of name <-> path is kept intact. We can do
that in the git-mv command by writing out the gitmodules file first
and then forcing a reload of the submodule config machinery.

Signed-off-by: Stefan Beller <[email protected]>
Reviewed-by: Jonathan Tan <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: stefanbeller

builtin/mv.c

@@ -275,10 +275,12 @@ int cmd_mv(int argc, const char **argv, const char *prefix)
 			die_errno(_("renaming '%s' failed"), src);
 		}
 		if (submodule_gitfile[i]) {
-			if (submodule_gitfile[i] != SUBMODULE_WITH_GITDIR)
-				connect_work_tree_and_git_dir(dst, submodule_gitfile[i]);
 			if (!update_path_in_gitmodules(src, dst))
 				gitmodules_modified = 1;
+			if (submodule_gitfile[i] != SUBMODULE_WITH_GITDIR)
+				connect_work_tree_and_git_dir(dst,
+							      submodule_gitfile[i],
+							      1);
 		}
 
 		if (mode == WORKING_DIRECTORY)

builtin/submodule--helper.c

@@ -1260,8 +1260,7 @@ static int module_clone(int argc, const char **argv, const char *prefix)
 		strbuf_reset(&sb);
 	}
 
-	/* Connect module worktree and git dir */
-	connect_work_tree_and_git_dir(path, sm_gitdir);
+	connect_work_tree_and_git_dir(path, sm_gitdir, 0);
 
 	p = git_pathdup_submodule(path, "config");
 	if (!p)

dir.c

@@ -19,6 +19,7 @@
 #include "varint.h"
 #include "ewah/ewok.h"
 #include "fsmonitor.h"
+#include "submodule-config.h"
 
 /*
  * Tells read_directory_recursive how a file or directory should be treated.
@@ -2988,8 +2989,57 @@ 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_)
+static void connect_wt_gitdir_in_nested(const char *sub_worktree,
+					const char *sub_gitdir)
+{
+	int i;
+	struct repository subrepo;
+	struct strbuf sub_wt = STRBUF_INIT;
+	struct strbuf sub_gd = STRBUF_INIT;
+
+	const struct submodule *sub;
+
+	/* If the submodule has no working tree, we can ignore it. */
+	if (repo_init(&subrepo, sub_gitdir, sub_worktree))
+		return;
+
+	if (repo_read_index(&subrepo) < 0)
+		die("index file corrupt in repo %s", subrepo.gitdir);
+
+	for (i = 0; i < subrepo.index->cache_nr; i++) {
+		const struct cache_entry *ce = subrepo.index->cache[i];
+
+		if (!S_ISGITLINK(ce->ce_mode))
+			continue;
+
+		while (i + 1 < subrepo.index->cache_nr &&
+		       !strcmp(ce->name, subrepo.index->cache[i + 1]->name))
+			/*
+			 * Skip entries with the same name in different stages
+			 * to make sure an entry is returned only once.
+			 */
+			i++;
+
+		sub = submodule_from_path(&subrepo, &null_oid, ce->name);
+		if (!sub || !is_submodule_active(&subrepo, ce->name))
+			/* .gitmodules broken or inactive sub */
+			continue;
+
+		strbuf_reset(&sub_wt);
+		strbuf_reset(&sub_gd);
+		strbuf_addf(&sub_wt, "%s/%s", sub_worktree, sub->path);
+		strbuf_addf(&sub_gd, "%s/modules/%s", sub_gitdir, sub->name);
+
+		connect_work_tree_and_git_dir(sub_wt.buf, sub_gd.buf, 1);
+	}
+	strbuf_release(&sub_wt);
+	strbuf_release(&sub_gd);
+	repo_clear(&subrepo);
+}
+
+void connect_work_tree_and_git_dir(const char *work_tree_,
+				   const char *git_dir_,
+				   int recurse_into_nested)
 {
 	struct strbuf gitfile_sb = STRBUF_INIT;
 	struct strbuf cfg_sb = STRBUF_INIT;
@@ -3019,6 +3069,10 @@ void connect_work_tree_and_git_dir(const char *work_tree_, const char *git_dir_)
 	strbuf_release(&gitfile_sb);
 	strbuf_release(&cfg_sb);
 	strbuf_release(&rel_path);
+
+	if (recurse_into_nested)
+		connect_wt_gitdir_in_nested(work_tree, git_dir);
+
 	free(work_tree);
 	free(git_dir);
 }
@@ -3032,5 +3086,5 @@ void relocate_gitdir(const char *path, const char *old_git_dir, const char *new_
 		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);
+	connect_work_tree_and_git_dir(path, new_git_dir, 0);
 }

dir.h

@@ -359,7 +359,17 @@ 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);
+
+/*
+ * Connect a worktree to a git directory by creating (or overwriting) a
+ * '.git' file containing the location of the git directory. In the git
+ * directory set the core.worktree setting to indicate where the worktree is.
+ * When `recurse_into_nested` is set, recurse into any nested submodules,
+ * connecting them as well.
+ */
+extern void connect_work_tree_and_git_dir(const char *work_tree,
+					  const char *git_dir,
+					  int recurse_into_nested);
 extern void relocate_gitdir(const char *path,
 			    const char *old_git_dir,
 			    const char *new_git_dir);

repository.c

@@ -135,9 +135,9 @@ static int read_and_verify_repository_format(struct repository_format *format,
  * Initialize 'repo' based on the provided 'gitdir'.
  * Return 0 upon success and a non-zero value upon failure.
  */
-static int repo_init(struct repository *repo,
-		     const char *gitdir,
-		     const char *worktree)
+int repo_init(struct repository *repo,
+	      const char *gitdir,
+	      const char *worktree)
 {
 	struct repository_format format;
 	memset(repo, 0, sizeof(*repo));

repository.h

@@ -97,6 +97,9 @@ extern void repo_set_gitdir(struct repository *repo,
 extern void repo_set_worktree(struct repository *repo, const char *path);
 extern void repo_set_hash_algo(struct repository *repo, int algo);
 extern void initialize_the_repository(void);
+extern int repo_init(struct repository *r,
+		     const char *gitdir,
+		     const char *worktree);
 extern int repo_submodule_init(struct repository *submodule,
 			       struct repository *superproject,
 			       const char *path);

submodule.c

@@ -1625,7 +1625,7 @@ int submodule_move_head(const char *path,
 		} else {
 			char *gitdir = xstrfmt("%s/modules/%s",
 				    get_git_common_dir(), sub->name);
-			connect_work_tree_and_git_dir(path, gitdir);
+			connect_work_tree_and_git_dir(path, gitdir, 0);
 			free(gitdir);
 
 			/* make sure the index is clean as well */
@@ -1635,7 +1635,7 @@ int submodule_move_head(const char *path,
 		if (old && (flags & SUBMODULE_MOVE_HEAD_FORCE)) {
 			char *gitdir = xstrfmt("%s/modules/%s",
 				    get_git_common_dir(), sub->name);
-			connect_work_tree_and_git_dir(path, gitdir);
+			connect_work_tree_and_git_dir(path, gitdir, 1);
 			free(gitdir);
 		}
 	}
@@ -1948,7 +1948,7 @@ void absorb_git_dir_into_superproject(const char *prefix,
 		if (!sub)
 			die(_("could not lookup name for submodule '%s'"), path);
 		connect_work_tree_and_git_dir(path,
-			git_path("modules/%s", sub->name));
+			git_path("modules/%s", sub->name), 0);
 	} else {
 		/* Is it already absorbed into the superprojects git dir? */
 		char *real_sub_git_dir = real_pathdup(sub_git_dir, 1);

t/t7001-mv.sh

@@ -491,7 +491,7 @@ test_expect_success 'moving a submodule in nested directories' '
 	test_cmp expect actual
 '
 
-test_expect_failure 'moving nested submodules' '
+test_expect_success 'moving nested submodules' '
 	git commit -am "cleanup commit" &&
 	mkdir sub_nested_nested &&
 	(cd sub_nested_nested &&