[PATCH v4 2/5] ref: port git-fsck(1) regular refs check for files backend

[shejialuo <shejialuo@gmail.com>]

We implicitly rely on "git-fsck(1)" to check the consistency of regular
refs. However, we have already set up the infrastructure of the ref
consistency checks. We need to port original checks from "git-fsck(1)".
Thus, we could clean the "git-fsck(1)" code by removing these implicit
checks.

The "git-fsck(1)" command reports an error when the ref content is
invalid. Following this, add a similar check to "git refs verify".
Add a new fsck error message called "badRefContent(ERROR)" to represent
that a ref has an invalid content.

Mentored-by: Patrick Steinhardt <ps@pks.im>
Mentored-by: Karthik Nayak <karthik.188@gmail.com>
Signed-off-by: shejialuo <shejialuo@gmail.com>
---
 Documentation/fsck-msgids.txt |  3 ++
 fsck.h                        |  1 +
 refs/files-backend.c          | 43 +++++++++++++++++++++++++
 t/t0602-reffiles-fsck.sh      | 60 +++++++++++++++++++++++++++++++++++
 4 files changed, 107 insertions(+)

diff --git a/Documentation/fsck-msgids.txt b/Documentation/fsck-msgids.txt
index 68a2801f15..22c385ea22 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.
 
+`badRefContent`::
+	(ERROR) A ref has bad content.
+
 `badRefFiletype`::
 	(ERROR) A ref has a bad file type.
 
diff --git a/fsck.h b/fsck.h
index 500b4c04d2..0d99a87911 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_CONTENT, ERROR) \
 	FUNC(BAD_REF_FILETYPE, ERROR) \
 	FUNC(BAD_REF_NAME, ERROR) \
 	FUNC(BAD_TIMEZONE, ERROR) \
diff --git a/refs/files-backend.c b/refs/files-backend.c
index 890d0324e1..b1ed2e5c04 100644
--- a/refs/files-backend.c
+++ b/refs/files-backend.c
@@ -3430,6 +3430,48 @@ typedef int (*files_fsck_refs_fn)(struct ref_store *ref_store,
 				  const char *refs_check_dir,
 				  struct dir_iterator *iter);
 
+static int files_fsck_refs_content(struct ref_store *ref_store,
+				   struct fsck_options *o,
+				   const char *refs_check_dir,
+				   struct dir_iterator *iter)
+{
+	struct strbuf ref_content = STRBUF_INIT;
+	struct strbuf referent = STRBUF_INIT;
+	struct strbuf refname = STRBUF_INIT;
+	struct fsck_ref_report report = {0};
+	unsigned int type = 0;
+	int failure_errno = 0;
+	struct object_id oid;
+	int ret = 0;
+
+	strbuf_addf(&refname, "%s/%s", refs_check_dir, iter->relative_path);
+	report.path = refname.buf;
+
+	if (S_ISLNK(iter->st.st_mode))
+		goto cleanup;
+
+	if (strbuf_read_file(&ref_content, iter->path.buf, 0) < 0) {
+		ret = error_errno(_("unable to read ref '%s/%s'"),
+				  refs_check_dir, iter->relative_path);
+		goto cleanup;
+	}
+
+	if (parse_loose_ref_contents(ref_store->repo->hash_algo,
+				     ref_content.buf, &oid, &referent,
+				     &type, &failure_errno)) {
+		ret = fsck_report_ref(o, &report,
+				      FSCK_MSG_BAD_REF_CONTENT,
+				      "invalid ref content");
+		goto cleanup;
+	}
+
+cleanup:
+	strbuf_release(&refname);
+	strbuf_release(&ref_content);
+	strbuf_release(&referent);
+	return ret;
+}
+
 static int files_fsck_refs_name(struct ref_store *ref_store UNUSED,
 				struct fsck_options *o,
 				const char *refs_check_dir,
@@ -3512,6 +3554,7 @@ static int files_fsck_refs(struct ref_store *ref_store,
 {
 	files_fsck_refs_fn fsck_refs_fn[]= {
 		files_fsck_refs_name,
+		files_fsck_refs_content,
 		NULL,
 	};
 
diff --git a/t/t0602-reffiles-fsck.sh b/t/t0602-reffiles-fsck.sh
index 71a4d1a5ae..a1205b3a3b 100755
--- a/t/t0602-reffiles-fsck.sh
+++ b/t/t0602-reffiles-fsck.sh
@@ -89,4 +89,64 @@ test_expect_success 'ref name check should be adapted into fsck messages' '
 	test_must_be_empty err
 '
 
+test_expect_success 'regular ref content should be checked (individual)' '
+	test_when_finished "rm -rf repo" &&
+	git init repo &&
+	branch_dir_prefix=.git/refs/heads &&
+	tag_dir_prefix=.git/refs/tags &&
+	cd repo &&
+	test_commit default &&
+	mkdir -p "$branch_dir_prefix/a/b" &&
+
+	git refs verify 2>err &&
+	test_must_be_empty err &&
+
+	printf "%sx" "$(git rev-parse main)" >$tag_dir_prefix/tag-bad-1 &&
+	test_must_fail git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	error: refs/tags/tag-bad-1: badRefContent: invalid ref content
+	EOF
+	rm $tag_dir_prefix/tag-bad-1 &&
+	test_cmp expect err &&
+
+	printf "xfsazqfxcadas" >$tag_dir_prefix/tag-bad-2 &&
+	test_must_fail git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	error: refs/tags/tag-bad-2: badRefContent: invalid ref content
+	EOF
+	rm $tag_dir_prefix/tag-bad-2 &&
+	test_cmp expect err &&
+
+	printf "xfsazqfxcadas" >$branch_dir_prefix/a/b/branch-bad &&
+	test_must_fail git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	error: refs/heads/a/b/branch-bad: badRefContent: invalid ref content
+	EOF
+	rm $branch_dir_prefix/a/b/branch-bad &&
+	test_cmp expect err
+'
+
+test_expect_success 'regular ref content should be checked (aggregate)' '
+	test_when_finished "rm -rf repo" &&
+	git init repo &&
+	branch_dir_prefix=.git/refs/heads &&
+	tag_dir_prefix=.git/refs/tags &&
+	cd repo &&
+	test_commit default &&
+	mkdir -p "$branch_dir_prefix/a/b" &&
+
+	printf "%sx" "$(git rev-parse main)" >$tag_dir_prefix/tag-bad-1 &&
+	printf "xfsazqfxcadas" >$tag_dir_prefix/tag-bad-2 &&
+	printf "xfsazqfxcadas" >$branch_dir_prefix/a/b/branch-bad &&
+
+	test_must_fail git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	error: refs/heads/a/b/branch-bad: badRefContent: invalid ref content
+	error: refs/tags/tag-bad-1: badRefContent: invalid ref content
+	error: refs/tags/tag-bad-2: badRefContent: invalid ref content
+	EOF
+	sort err >sorted_err &&
+	test_cmp expect sorted_err
+'
+
 test_done
-- 
2.46.0