[PATCH v2 2/4] ref: add regular ref content check for files backend

[shejialuo <shejialuo@gmail.com>]

We implicitly rely on "git-fsck(1)" to check the consistency of regular
refs. However, when parsing the regular refs for files backend by using
"files-backend.c::parse_loose_ref_contents", we allow the ref content to
be end with no newline or contain some garbages.

It may seem that we should report an error or warn fsck message to the
user about above situations. However, there may be some third-party
tools customizing the content of refs. We should not report an error
fsck message.

And we cannot either report a warn fsck message to the user. This is
because if the caller set the "strict" field in "fsck_options" to
to upgrade the fsck warnings to errors.

We should not allow the user to upgrade the fsck warnings to errors. It
might cause compatibility issue which will break the legacy repository.
So we add the following two fsck infos to represent the situation where
the ref content ends without newline or has garbages:

1. "refMissingNewline(INFO)": A valid ref does not end with newline.
2. "trailingRefContent(INFO)": A ref has trailing contents.

In "fsck.c::fsck_vreport", we will convert "FSCK_INFO" to "FSCK_WARN",
and we can still warn the user about these situations when using
"git-refs verify" without introducing compatibility issue.

In current "git-fsck(1)", it will report an error when the ref content
is bad, so we should following this to report an error to the user when
"parse_loose_ref_contents" fails. And we add a new fsck error message
called "badRefContent(ERROR)" to represent that a ref has a bad content.

In order to tell whether the ref has trailing content, add a new
parameter "trailing" to "parse_loose_ref_contents". Then introduce a new
function "files_fsck_refs_content" to check the regular refs to enhance
the "git-refs verify".

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 |  9 ++++
 fsck.h                        |  3 ++
 refs.c                        |  2 +-
 refs/files-backend.c          | 68 ++++++++++++++++++++++++++-
 refs/refs-internal.h          |  2 +-
 t/t0602-reffiles-fsck.sh      | 87 +++++++++++++++++++++++++++++++++++
 6 files changed, 167 insertions(+), 4 deletions(-)

diff --git a/Documentation/fsck-msgids.txt b/Documentation/fsck-msgids.txt
index 68a2801f15..fc074fc571 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 a bad content.
+
 `badRefFiletype`::
 	(ERROR) A ref has a bad file type.
 
@@ -170,6 +173,12 @@
 `nullSha1`::
 	(WARN) Tree contains entries pointing to a null sha1.
 
+`refMissingNewline`::
+	(INFO) A valid ref does not end with newline.
+
+`trailingRefContent`::
+	(INFO) A ref has trailing contents.
+
 `treeNotSorted`::
 	(ERROR) A tree is not properly sorted.
 
diff --git a/fsck.h b/fsck.h
index 500b4c04d2..b85072df57 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) \
@@ -84,6 +85,8 @@ enum fsck_msg_type {
 	FUNC(MAILMAP_SYMLINK, INFO) \
 	FUNC(BAD_TAG_NAME, INFO) \
 	FUNC(MISSING_TAGGER_ENTRY, INFO) \
+	FUNC(REF_MISSING_NEWLINE, INFO) \
+	FUNC(TRAILING_REF_CONTENT, INFO) \
 	/* ignored (elevated when requested) */ \
 	FUNC(EXTRA_HEADER_ENTRY, IGNORE)
 
diff --git a/refs.c b/refs.c
index 74de3d3009..5e74881945 100644
--- a/refs.c
+++ b/refs.c
@@ -1758,7 +1758,7 @@ static int refs_read_special_head(struct ref_store *ref_store,
 	}
 
 	result = parse_loose_ref_contents(ref_store->repo->hash_algo, content.buf,
-					  oid, referent, type, failure_errno);
+					  oid, referent, type, NULL, failure_errno);
 
 done:
 	strbuf_release(&full_path);
diff --git a/refs/files-backend.c b/refs/files-backend.c
index d6fc3bd67c..69c00073eb 100644
--- a/refs/files-backend.c
+++ b/refs/files-backend.c
@@ -560,7 +560,7 @@ static int read_ref_internal(struct ref_store *ref_store, const char *refname,
 	buf = sb_contents.buf;
 
 	ret = parse_loose_ref_contents(ref_store->repo->hash_algo, buf,
-				       oid, referent, type, &myerr);
+				       oid, referent, type, NULL, &myerr);
 
 out:
 	if (ret && !myerr)
@@ -597,7 +597,7 @@ static int files_read_symbolic_ref(struct ref_store *ref_store, const char *refn
 int parse_loose_ref_contents(const struct git_hash_algo *algop,
 			     const char *buf, struct object_id *oid,
 			     struct strbuf *referent, unsigned int *type,
-			     int *failure_errno)
+			     const char **trailing, int *failure_errno)
 {
 	const char *p;
 	if (skip_prefix(buf, "ref:", &buf)) {
@@ -619,6 +619,10 @@ int parse_loose_ref_contents(const struct git_hash_algo *algop,
 		*failure_errno = EINVAL;
 		return -1;
 	}
+
+	if (trailing)
+		*trailing = p;
+
 	return 0;
 }
 
@@ -3430,6 +3434,65 @@ 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};
+	const char *trailing = NULL;
+	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_ISREG(iter->st.st_mode)) {
+		if (strbuf_read_file(&ref_content, iter->path.buf, 0) < 0) {
+			ret = error_errno(_("%s/%s: unable to read the ref"),
+					  refs_check_dir, iter->relative_path);
+			goto cleanup;
+		}
+
+		if (parse_loose_ref_contents(ref_store->repo->hash_algo,
+					     ref_content.buf, &oid, &referent,
+					     &type, &trailing, &failure_errno)) {
+			ret = fsck_report_ref(o, &report,
+					      FSCK_MSG_BAD_REF_CONTENT,
+					      "invalid ref content");
+			goto cleanup;
+		}
+
+		if (!(type & REF_ISSYMREF)) {
+			if (*trailing == '\0') {
+				ret = fsck_report_ref(o, &report,
+						      FSCK_MSG_REF_MISSING_NEWLINE,
+						      "missing newline");
+				goto cleanup;
+			}
+
+			if (*trailing != '\n' || (*(trailing + 1) != '\0')) {
+				ret = fsck_report_ref(o, &report,
+						      FSCK_MSG_TRAILING_REF_CONTENT,
+						      "trailing garbage in ref");
+				goto cleanup;
+			}
+		}
+		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 +3575,7 @@ 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/refs/refs-internal.h b/refs/refs-internal.h
index 2313c830d8..73b05f971b 100644
--- a/refs/refs-internal.h
+++ b/refs/refs-internal.h
@@ -715,7 +715,7 @@ struct ref_store {
 int parse_loose_ref_contents(const struct git_hash_algo *algop,
 			     const char *buf, struct object_id *oid,
 			     struct strbuf *referent, unsigned int *type,
-			     int *failure_errno);
+			     const char **trailing, int *failure_errno);
 
 /*
  * Fill in the generic part of refs and add it to our collection of
diff --git a/t/t0602-reffiles-fsck.sh b/t/t0602-reffiles-fsck.sh
index 71a4d1a5ae..7c1910d784 100755
--- a/t/t0602-reffiles-fsck.sh
+++ b/t/t0602-reffiles-fsck.sh
@@ -89,4 +89,91 @@ 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' '
+	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 checkout -b a/b/tag-2 &&
+
+	printf "%s" "$(git rev-parse branch-1)" > $branch_dir_prefix/branch-1-no-newline &&
+	git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	warning: refs/heads/branch-1-no-newline: refMissingNewline: missing newline
+	EOF
+	rm $branch_dir_prefix/branch-1-no-newline &&
+	test_cmp expect err &&
+
+	printf "%s garbage" "$(git rev-parse branch-1)" > $branch_dir_prefix/branch-1-garbage &&
+	git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	warning: refs/heads/branch-1-garbage: trailingRefContent: trailing garbage in ref
+	EOF
+	rm $branch_dir_prefix/branch-1-garbage &&
+	test_cmp expect err &&
+
+	printf "%s\n\n\n" "$(git rev-parse tag-1)" > $tag_dir_prefix/tag-1-garbage &&
+	git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	warning: refs/tags/tag-1-garbage: trailingRefContent: trailing garbage in ref
+	EOF
+	rm $tag_dir_prefix/tag-1-garbage &&
+	test_cmp expect err &&
+
+	printf "%s\n\n\n  garbage" "$(git rev-parse tag-1)" > $tag_dir_prefix/tag-1-garbage &&
+	git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	warning: refs/tags/tag-1-garbage: trailingRefContent: trailing garbage in ref
+	EOF
+	rm $tag_dir_prefix/tag-1-garbage &&
+	test_cmp expect err &&
+
+	printf "%s    garbage\n\na" "$(git rev-parse tag-2)" > $tag_dir_prefix/tag-2-garbage &&
+	git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	warning: refs/tags/tag-2-garbage: trailingRefContent: trailing garbage in ref
+	EOF
+	rm $tag_dir_prefix/tag-2-garbage &&
+	test_cmp expect err &&
+
+	printf "%s garbage" "$(git rev-parse tag-1)" > $tag_dir_prefix/tag-1-garbage &&
+	test_must_fail git -c fsck.trailingRefContent=error refs verify 2>err &&
+	cat >expect <<-EOF &&
+	error: refs/tags/tag-1-garbage: trailingRefContent: trailing garbage in ref
+	EOF
+	rm $tag_dir_prefix/tag-1-garbage &&
+	test_cmp expect err &&
+
+	printf "%sx" "$(git rev-parse tag-1)" > $tag_dir_prefix/tag-1-bad &&
+	test_must_fail git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	error: refs/tags/tag-1-bad: badRefContent: invalid ref content
+	EOF
+	rm $tag_dir_prefix/tag-1-bad &&
+	test_cmp expect err &&
+
+	printf "xfsazqfxcadas" > $tag_dir_prefix/tag-2-bad &&
+	test_must_fail git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	error: refs/tags/tag-2-bad: badRefContent: invalid ref content
+	EOF
+	rm $tag_dir_prefix/tag-2-bad &&
+	test_cmp expect err &&
+
+	printf "xfsazqfxcadas" > $branch_dir_prefix/a/b/branch-2-bad &&
+	test_must_fail git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	error: refs/heads/a/b/branch-2-bad: badRefContent: invalid ref content
+	EOF
+	rm $branch_dir_prefix/a/b/branch-2-bad &&
+	test_cmp expect err
+'
+
 test_done
-- 
2.46.0