[PATCH v5 3/9] ref: port git-fsck(1) regular refs check for files backend

[shejialuo <shejialuo@gmail.com>]

"git-fsck(1)" has some consistency checks for regular refs. As we want
to align the checks "git refs verify" performs with them (and eventually
call the unified code that checks refs from both), port the logic
"git-fsck" has to "git refs verify".

"git-fsck(1)" will report an error when the ref content is invalid.
Following this, add a similar check to "git refs verify". Then add a new
fsck error message "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          | 45 ++++++++++++++++++++++++
 t/t0602-reffiles-fsck.sh      | 66 +++++++++++++++++++++++++++++++++++
 4 files changed, 115 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 57318b4c4e..35b3fa983e 100644
--- a/refs/files-backend.c
+++ b/refs/files-backend.c
@@ -3504,6 +3504,50 @@ 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 = fsck_report_ref(o, &report,
+				      FSCK_MSG_BAD_REF_CONTENT,
+				      "cannot read ref file");
+		goto cleanup;
+	}
+
+	if (parse_loose_ref_contents(ref_store->repo->hash_algo,
+				     ref_content.buf, &oid, &referent,
+				     &type, &failure_errno)) {
+		strbuf_rtrim(&ref_content);
+		ret = fsck_report_ref(o, &report,
+				      FSCK_MSG_BAD_REF_CONTENT,
+				      "%s", ref_content.buf);
+		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,
@@ -3586,6 +3630,7 @@ 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 4c6cd6f7d0..628f9bcc46 100755
--- a/t/t0602-reffiles-fsck.sh
+++ b/t/t0602-reffiles-fsck.sh
@@ -148,4 +148,70 @@ test_expect_success 'ref name check should work for multiple worktrees' '
 	)
 '
 
+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 "$branch_dir_prefix/a/b" &&
+
+	git refs verify 2>err &&
+	test_must_be_empty err &&
+
+	bad_content=$(git rev-parse main)x &&
+	printf "%s" $bad_content >$tag_dir_prefix/tag-bad-1 &&
+	test_must_fail git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	error: refs/tags/tag-bad-1: badRefContent: $bad_content
+	EOF
+	rm $tag_dir_prefix/tag-bad-1 &&
+	test_cmp expect err &&
+
+	bad_content=xfsazqfxcadas &&
+	printf "%s" $bad_content >$tag_dir_prefix/tag-bad-2 &&
+	test_must_fail git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	error: refs/tags/tag-bad-2: badRefContent: $bad_content
+	EOF
+	rm $tag_dir_prefix/tag-bad-2 &&
+	test_cmp expect err &&
+
+	bad_content=Xfsazqfxcadas &&
+	printf "%s" $bad_content >$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: $bad_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" &&
+
+	bad_content_1=$(git rev-parse main)x &&
+	bad_content_2=xfsazqfxcadas &&
+	bad_content_3=Xfsazqfxcadas &&
+	printf "%s" $bad_content_1 >$tag_dir_prefix/tag-bad-1 &&
+	printf "%s" $bad_content_2 >$tag_dir_prefix/tag-bad-2 &&
+	printf "%s" $bad_content_3 >$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: $bad_content_3
+	error: refs/tags/tag-bad-1: badRefContent: $bad_content_1
+	error: refs/tags/tag-bad-2: badRefContent: $bad_content_2
+	EOF
+	sort err >sorted_err &&
+	test_cmp expect sorted_err
+'
+
 test_done
-- 
2.46.2