add: warn when adding an embedded repository

It's an easy mistake to add a repository inside another
repository, like:

  git clone $url
  git add .

The resulting entry is a gitlink, but there's no matching
.gitmodules entry. Trying to use "submodule init" (or clone
with --recursive) doesn't do anything useful. Prior to
v2.13, such an entry caused git-submodule to barf entirely.
In v2.13, the entry is considered "inactive" and quietly
ignored. Either way, no clone of your repository can do
anything useful with the gitlink without the user manually
adding the submodule config.

In most cases, the user probably meant to either add a real
submodule, or they forgot to put the embedded repository in
their .gitignore file.

Let's issue a warning when we see this case. There are a few
things to note:

  - the warning will go in the git-add porcelain; anybody
    wanting to do low-level manipulation of the index is
    welcome to create whatever funny states they want.

  - we detect the case by looking for a newly added gitlink;
    updates via "git add submodule" are perfectly reasonable,
    and this avoids us having to investigate .gitmodules
    entirely

  - there's a command-line option to suppress the warning.
    This is needed for git-submodule itself (which adds the
    entry before adding any submodule config), but also
    provides a mechanism for other scripts doing
    submodule-like things.

We could make this a hard error instead of a warning.
However, we do add lots of sub-repos in our test suite. It's
not _wrong_ to do so. It just creates a state where users
may be surprised. Pointing them in the right direction with
a gentle hint is probably the best option.

There is a config knob that can disable the (long) hint. But
I intentionally omitted a config knob to disable the warning
entirely. Whether the warning is sensible or not is
generally about context, not about the user's preferences.
If there's a tool or workflow that adds gitlinks without
matching .gitmodules, it should probably be taught about the
new command-line option, rather than blanket-disabling the
warning.

Signed-off-by: Jeff King <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Documentation/config.txt

@@ -348,6 +348,9 @@ advice.*::
 	rmHints::
 		In case of failure in the output of linkgit:git-rm[1],
 		show directions on how to proceed from the current state.
+	addEmbeddedRepo::
+		Advice on what to do when you've accidentally added one
+		git repo inside of another.
 --
 
 core.fileMode::

Documentation/git-add.txt

@@ -165,6 +165,13 @@ for "git add --no-all <pathspec>...", i.e. ignored removed files.
 	be ignored, no matter if they are already present in the work
 	tree or not.
 
+--no-warn-embedded-repo::
+	By default, `git add` will warn when adding an embedded
+	repository to the index without using `git submodule add` to
+	create an entry in `.gitmodules`. This option will suppress the
+	warning (e.g., if you are manually performing operations on
+	submodules).
+
 --chmod=(+|-)x::
 	Override the executable bit of the added files.  The executable
 	bit is only changed in the index, the files on disk are left

advice.c

@@ -15,6 +15,7 @@ int advice_detached_head = 1;
 int advice_set_upstream_failure = 1;
 int advice_object_name_warning = 1;
 int advice_rm_hints = 1;
+int advice_add_embedded_repo = 1;
 
 static struct {
 	const char *name;
@@ -35,6 +36,7 @@ static struct {
 	{ "setupstreamfailure", &advice_set_upstream_failure },
 	{ "objectnamewarning", &advice_object_name_warning },
 	{ "rmhints", &advice_rm_hints },
+	{ "addembeddedrepo", &advice_add_embedded_repo },
 
 	/* make this an alias for backward compatibility */
 	{ "pushnonfastforward", &advice_push_update_rejected }

advice.h

@@ -18,6 +18,7 @@ extern int advice_detached_head;
 extern int advice_set_upstream_failure;
 extern int advice_object_name_warning;
 extern int advice_rm_hints;
+extern int advice_add_embedded_repo;
 
 int git_default_advice_config(const char *var, const char *value);
 __attribute__((format (printf, 1, 2)))

builtin/add.c

@@ -249,6 +249,7 @@ N_("The following paths are ignored by one of your .gitignore files:\n");
 
 static int verbose, show_only, ignored_too, refresh_only;
 static int ignore_add_errors, intent_to_add, ignore_missing;
+static int warn_on_embedded_repo = 1;
 
 #define ADDREMOVE_DEFAULT 1
 static int addremove = ADDREMOVE_DEFAULT;
@@ -282,6 +283,8 @@ static struct option builtin_add_options[] = {
 	OPT_BOOL( 0 , "ignore-errors", &ignore_add_errors, N_("just skip files which cannot be added because of errors")),
 	OPT_BOOL( 0 , "ignore-missing", &ignore_missing, N_("check if - even missing - files are ignored in dry run")),
 	OPT_STRING( 0 , "chmod", &chmod_arg, N_("(+/-)x"), N_("override the executable bit of the listed files")),
+	OPT_HIDDEN_BOOL(0, "warn-embedded-repo", &warn_on_embedded_repo,
+			N_("warn when adding an embedded repository")),
 	OPT_END(),
 };
 
@@ -295,6 +298,45 @@ static int add_config(const char *var, const char *value, void *cb)
 	return git_default_config(var, value, cb);
 }
 
+static const char embedded_advice[] = N_(
+"You've added another git repository inside your current repository.\n"
+"Clones of the outer repository will not contain the contents of\n"
+"the embedded repository and will not know how to obtain it.\n"
+"If you meant to add a submodule, use:\n"
+"\n"
+"	git submodule add <url> %s\n"
+"\n"
+"If you added this path by mistake, you can remove it from the\n"
+"index with:\n"
+"\n"
+"	git rm --cached %s\n"
+"\n"
+"See \"git help submodule\" for more information."
+);
+
+static void check_embedded_repo(const char *path)
+{
+	struct strbuf name = STRBUF_INIT;
+
+	if (!warn_on_embedded_repo)
+		return;
+	if (!ends_with(path, "/"))
+		return;
+
+	/* Drop trailing slash for aesthetics */
+	strbuf_addstr(&name, path);
+	strbuf_strip_suffix(&name, "/");
+
+	warning(_("adding embedded git repository: %s"), name.buf);
+	if (advice_add_embedded_repo) {
+		advise(embedded_advice, name.buf, name.buf);
+		/* there may be multiple entries; advise only once */
+		advice_add_embedded_repo = 0;
+	}
+
+	strbuf_release(&name);
+}
+
 static int add_files(struct dir_struct *dir, int flags)
 {
 	int i, exit_status = 0;
@@ -307,12 +349,14 @@ static int add_files(struct dir_struct *dir, int flags)
 		exit_status = 1;
 	}
 
-	for (i = 0; i < dir->nr; i++)
+	for (i = 0; i < dir->nr; i++) {
+		check_embedded_repo(dir->entries[i]->name);
 		if (add_file_to_index(&the_index, dir->entries[i]->name, flags)) {
 			if (!ignore_add_errors)
 				die(_("adding files failed"));
 			exit_status = 1;
 		}
+	}
 	return exit_status;
 }
 

git-submodule.sh

@@ -213,7 +213,8 @@ cmd_add()
 		die "$(eval_gettext "'\$sm_path' already exists in the index and is not a submodule")"
 	fi
 
-	if test -z "$force" && ! git add --dry-run --ignore-missing "$sm_path" > /dev/null 2>&1
+	if test -z "$force" &&
+		! git add --dry-run --ignore-missing --no-warn-embedded-repo "$sm_path" > /dev/null 2>&1
 	then
 		eval_gettextln "The following path is ignored by one of your .gitignore files:
 \$sm_path
@@ -267,7 +268,7 @@ or you are unsure what this means choose another name with the '--name' option."
 	fi
 	git config submodule."$sm_name".url "$realrepo"
 
-	git add $force "$sm_path" ||
+	git add --no-warn-embedded-repo $force "$sm_path" ||
 	die "$(eval_gettext "Failed to add submodule '\$sm_path'")"
 
 	git config -f .gitmodules submodule."$sm_name".path "$sm_path" &&

t/t7414-submodule-mistakes.sh

@@ -0,0 +1,37 @@
+#!/bin/sh
+
+test_description='handling of common mistakes people may make with submodules'
+. ./test-lib.sh
+
+test_expect_success 'create embedded repository' '
+	git init embed &&
+	test_commit -C embed one
+'
+
+test_expect_success 'git-add on embedded repository warns' '
+	test_when_finished "git rm --cached -f embed" &&
+	git add embed 2>stderr &&
+	test_i18ngrep warning stderr
+'
+
+test_expect_success '--no-warn-embedded-repo suppresses warning' '
+	test_when_finished "git rm --cached -f embed" &&
+	git add --no-warn-embedded-repo embed 2>stderr &&
+	test_i18ngrep ! warning stderr
+'
+
+test_expect_success 'no warning when updating entry' '
+	test_when_finished "git rm --cached -f embed" &&
+	git add embed &&
+	git -C embed commit --allow-empty -m two &&
+	git add embed 2>stderr &&
+	test_i18ngrep ! warning stderr
+'
+
+test_expect_success 'submodule add does not warn' '
+	test_when_finished "git rm -rf submodule .gitmodules" &&
+	git submodule add ./embed submodule 2>stderr &&
+	test_i18ngrep ! warning stderr
+'
+
+test_done