[GSoC,v8,8/9] fsck: add ref name check for files backend

Commit Message

shejialuo July 8, 2024, 1:36 p.m. UTC

The git-fsck(1) only implicitly checks the reference, it does not fully
check refs with bad format name such as standalone "@" and name ending
with ".lock".

In order to provide such checks, add a new fsck message id "badRefName"
with default ERROR type. Use existing "check_refname_format" to explicit
check the ref name. And add a new unit test to verify the functionality.

Mentored-by: Patrick Steinhardt <[e-mail]>
Mentored-by: Karthik Nayak <[e-mail]>
Signed-off-by: shejialuo <[e-mail]>
---
 Documentation/fsck-msgids.txt |   3 +
 fsck.h                        |   1 +
 refs/files-backend.c          |  20 +++++++
 t/t0602-reffiles-fsck.sh      | 101 ++++++++++++++++++++++++++++++++++
 4 files changed, 125 insertions(+)
 create mode 100755 t/t0602-reffiles-fsck.sh

Patch

diff --git a/Documentation/fsck-msgids.txt b/Documentation/fsck-msgids.txt
index f643585a34..dab4012246 100644
--- a/Documentation/fsck-msgids.txt
+++ b/Documentation/fsck-msgids.txt
@@ -19,6 +19,9 @@ 
 `badParentSha1`::
 	(ERROR) A commit object has a bad parent sha1.
 
+`badRefName`::
+	(ERROR) A ref has a bad name.
+
 `badTagName`::
 	(INFO) A tag has an invalid format.
 
diff --git a/fsck.h b/fsck.h
index 246055c0f9..90457d1a1f 100644
--- a/fsck.h
+++ b/fsck.h
@@ -31,6 +31,7 @@  enum fsck_msg_type {
 	FUNC(BAD_NAME, ERROR) \
 	FUNC(BAD_OBJECT_SHA1, ERROR) \
 	FUNC(BAD_PARENT_SHA1, ERROR) \
+	FUNC(BAD_REF_NAME, ERROR) \
 	FUNC(BAD_TIMEZONE, ERROR) \
 	FUNC(BAD_TREE, ERROR) \
 	FUNC(BAD_TREE_SHA1, ERROR) \
diff --git a/refs/files-backend.c b/refs/files-backend.c
index 84acb58782..69a76048d3 100644
--- a/refs/files-backend.c
+++ b/refs/files-backend.c
@@ -3419,6 +3419,25 @@  typedef int (*files_fsck_refs_fn)(struct fsck_options *o,
 				  const char *refs_check_dir,
 				  struct dir_iterator *iter);
 
+static int files_fsck_refs_name(struct fsck_options *o,
+				const char *gitdir UNUSED,
+				const char *refs_check_dir,
+				struct dir_iterator *iter)
+{
+	struct strbuf sb = STRBUF_INIT;
+	int ret = 0;
+
+	if (check_refname_format(iter->basename, REFNAME_ALLOW_ONELEVEL)) {
+		strbuf_addf(&sb, "%s/%s", refs_check_dir, iter->relative_path);
+		ret = fsck_refs_report(o, NULL, sb.buf,
+				       FSCK_MSG_BAD_REF_NAME,
+				       "invalid refname format");
+	}
+
+	strbuf_release(&sb);
+	return ret;
+}
+
 static int files_fsck_refs_dir(struct ref_store *ref_store,
 			       struct fsck_options *o,
 			       const char *refs_check_dir,
@@ -3470,6 +3489,7 @@  static int files_fsck_refs(struct ref_store *ref_store,
 {
 	int ret;
 	files_fsck_refs_fn fsck_refs_fns[]= {
+		files_fsck_refs_name,
 		NULL
 	};
 
diff --git a/t/t0602-reffiles-fsck.sh b/t/t0602-reffiles-fsck.sh
new file mode 100755
index 0000000000..b2db58d2c6
--- /dev/null
+++ b/t/t0602-reffiles-fsck.sh
@@ -0,0 +1,101 @@ 
+#!/bin/sh
+
+test_description='Test reffiles backend consistency check'
+
+GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=main
+export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME
+GIT_TEST_DEFAULT_REF_FORMAT=files
+export GIT_TEST_DEFAULT_REF_FORMAT
+
+. ./test-lib.sh
+
+test_expect_success 'ref name should be checked' '
+	test_when_finished "rm -rf repo" &&
+	git init repo &&
+	branch_dir_prefix=.git/refs/heads &&
+	tag_dir_prefix=.git/refs/tags &&
+	(
+		cd repo &&
+		git commit --allow-empty -m initial &&
+		git checkout -b branch-1 &&
+		git tag tag-1 &&
+		git commit --allow-empty -m second &&
+		git checkout -b branch-2 &&
+		git tag tag-2 &&
+		git tag multi_hierarchy/tag-2
+	) &&
+	(
+		cd repo &&
+		cp $branch_dir_prefix/branch-1 $branch_dir_prefix/.branch-1 &&
+		test_must_fail git fsck 2>err &&
+		cat >expect <<-EOF &&
+		error: refs/heads/.branch-1: badRefName: invalid refname format
+		EOF
+		rm $branch_dir_prefix/.branch-1 &&
+		test_cmp expect err
+	) &&
+	(
+		cd repo &&
+		cp $tag_dir_prefix/tag-1 $tag_dir_prefix/tag-1.lock &&
+		test_must_fail git fsck 2>err &&
+		cat >expect <<-EOF &&
+		error: refs/tags/tag-1.lock: badRefName: invalid refname format
+		EOF
+		rm $tag_dir_prefix/tag-1.lock &&
+		test_cmp expect err
+	) &&
+	(
+		cd repo &&
+		cp $branch_dir_prefix/branch-1 $branch_dir_prefix/@ &&
+		test_must_fail git fsck 2>err &&
+		cat >expect <<-EOF &&
+		error: refs/heads/@: badRefName: invalid refname format
+		EOF
+		rm $branch_dir_prefix/@ &&
+		test_cmp expect err
+	) &&
+	(
+		cd repo &&
+		cp $tag_dir_prefix/multi_hierarchy/tag-2 $tag_dir_prefix/multi_hierarchy/@ &&
+		test_must_fail git fsck 2>err &&
+		cat >expect <<-EOF &&
+		error: refs/tags/multi_hierarchy/@: badRefName: invalid refname format
+		EOF
+		rm $tag_dir_prefix/multi_hierarchy/@ &&
+		test_cmp expect err
+	)
+'
+
+test_expect_success 'ref name check should be adapted into fsck messages' '
+	test_when_finished "rm -rf repo" &&
+	git init repo &&
+	branch_dir_prefix=.git/refs/heads &&
+	tag_dir_prefix=.git/refs/tags &&
+	(
+		cd repo &&
+		git commit --allow-empty -m initial &&
+		git checkout -b branch-1 &&
+		git tag tag-1 &&
+		git commit --allow-empty -m second &&
+		git checkout -b branch-2 &&
+		git tag tag-2
+	) &&
+	(
+		cd repo &&
+		cp $branch_dir_prefix/branch-1 $branch_dir_prefix/.branch-1 &&
+		git -c fsck.badRefName=warn fsck 2>err &&
+		cat >expect <<-EOF &&
+		warning: refs/heads/.branch-1: badRefName: invalid refname format
+		EOF
+		rm $branch_dir_prefix/.branch-1 &&
+		test_cmp expect err
+	) &&
+	(
+		cd repo &&
+		cp $branch_dir_prefix/branch-1 $branch_dir_prefix/@ &&
+		git -c fsck.badRefName=ignore fsck 2>err &&
+		test_must_be_empty err
+	)
+'
+
+test_done