ref: add symref content check for files backend

We have already introduced the checks for regular refs. There is no need
to check the consistency of the target which the symref points to.
Instead, we just need to check the content of the symref itself.

A regular file is accepted as a textual symref if it begins with
"ref:", followed by zero or more whitespaces, followed by the full
refname, followed only by whitespace characters. We always write
a single SP after "ref:" and a single LF after the refname, but
third-party reimplementations of Git may have taken advantage of the
looser syntax. Put it more specific, we accept the following contents
of the symref:

1. "ref: refs/heads/master   "
2. "ref: refs/heads/master   \n  \n"
3. "ref: refs/heads/master\n\n"

Thus, we could reuse "refMissingNewline" and "trailingRefContent"
FSCK_INFOs to do the same retroactive tightening as we introduce for
regular references.

But we do not allow any other trailing garbage. The followings are bad
symref contents which will be reported as fsck error by "git-fsck(1)".

1. "ref: refs/heads/master garbage\n"
2. "ref: refs/heads/master \n\n\n garbage  "

And we introduce a new "badReferentName(ERROR)" fsck message to report
above errors to the user.

In order to check the content of the symref, create a function
"files_fsck_symref_target". It will first check whether the "referent"
is under the "refs/" directory, if not, we will report "escapeReferent"
fsck error message to notify the user this situation.

Then, we will first check whether the symref content misses the newline
by peeking the last byte of the "referent" to see whether it is '\n'.

And we will remember the untrimmed length of the "referent" and call
"strbuf_rtrim()" on "referent". Then, we will call "check_refname_format"
to check whether the trimmed referent format is valid. If not, we will
report to the user that the symref points to referent which has invalid
format. If it is valid, we will compare the untrimmed length and trimmed
length, if they are not the same, we need to warn the user there is some
trailing garbage in the symref content.

At last, we need to check whether the referent is a directory. We cannot
distinguish whether a given reference like "refs/heads/a" is a file or a
directory by using "check_refname_format". We have already checked bad
file type when iterating the "refs/" directory but we ignore the
directory. Thus, we need to explicitly add check here.

Mentored-by: Patrick Steinhardt <[email protected]>
Mentored-by: Karthik Nayak <[email protected]>
Signed-off-by: shejialuo <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: shejialuo

Documentation/fsck-msgids.txt

@@ -28,6 +28,12 @@
 `badRefName`::
 	(ERROR) A ref has an invalid format.
 
+`badReferentFiletype`::
+	(ERROR) The referent of a symref has a bad file type.
+
+`badReferentName`::
+	(ERROR) The referent name of a symref is invalid.
+
 `badTagName`::
 	(INFO) A tag has an invalid format.
 
@@ -49,6 +55,9 @@
 `emptyName`::
 	(WARN) A path contains an empty name.
 
+`escapeReferent`::
+	(ERROR) The referent of a symref is outside the "ref" directory.
+
 `extraHeaderEntry`::
 	(IGNORE) Extra headers found after `tagger`.
 

fsck.h

@@ -34,11 +34,14 @@ enum fsck_msg_type {
 	FUNC(BAD_REF_CONTENT, ERROR) \
 	FUNC(BAD_REF_FILETYPE, ERROR) \
 	FUNC(BAD_REF_NAME, ERROR) \
+	FUNC(BAD_REFERENT_FILETYPE, ERROR) \
+	FUNC(BAD_REFERENT_NAME, ERROR) \
 	FUNC(BAD_TIMEZONE, ERROR) \
 	FUNC(BAD_TREE, ERROR) \
 	FUNC(BAD_TREE_SHA1, ERROR) \
 	FUNC(BAD_TYPE, ERROR) \
 	FUNC(DUPLICATE_ENTRIES, ERROR) \
+	FUNC(ESCAPE_REFERENT, ERROR) \
 	FUNC(MISSING_AUTHOR, ERROR) \
 	FUNC(MISSING_COMMITTER, ERROR) \
 	FUNC(MISSING_EMAIL, ERROR) \

refs/files-backend.c

@@ -3434,11 +3434,80 @@ typedef int (*files_fsck_refs_fn)(struct ref_store *ref_store,
 				  const char *refs_check_dir,
 				  struct dir_iterator *iter);
 
+/*
+ * Check the symref "referent" and "referent_path". For textual symref,
+ * "referent" would be the content after "refs:".
+ */
+static int files_fsck_symref_target(struct fsck_options *o,
+				    struct fsck_ref_report *report,
+				    struct strbuf *referent,
+				    struct strbuf *referent_path)
+{
+	size_t len = referent->len - 1;
+	struct stat st;
+	int ret = 0;
+
+	if (!starts_with(referent->buf, "refs/")) {
+		ret = fsck_report_ref(o, report,
+				      FSCK_MSG_ESCAPE_REFERENT,
+				      "points to ref outside the refs directory");
+		goto out;
+	}
+
+	if (referent->buf[referent->len - 1] != '\n') {
+		ret = fsck_report_ref(o, report,
+				      FSCK_MSG_REF_MISSING_NEWLINE,
+				      "missing newline");
+		len++;
+	}
+
+	strbuf_rtrim(referent);
+	if (check_refname_format(referent->buf, 0)) {
+		ret = fsck_report_ref(o, report,
+				      FSCK_MSG_BAD_REFERENT_NAME,
+				      "points to refname with invalid format");
+		goto out;
+	}
+
+	if (len != referent->len) {
+		ret = fsck_report_ref(o, report,
+				      FSCK_MSG_TRAILING_REF_CONTENT,
+				      "trailing garbage in ref");
+	}
+
+	/*
+	 * Dangling symrefs are common and so we don't report them.
+	 */
+	if (lstat(referent_path->buf, &st)) {
+		if (errno != ENOENT) {
+			ret = error_errno(_("unable to stat '%s'"),
+					  referent_path->buf);
+		}
+		goto out;
+	}
+
+	/*
+	 * We cannot distinguish whether "refs/heads/a" is a directory or not by
+	 * using "check_refname_format(referent->buf, 0)". Instead, we need to
+	 * check the file type of the target.
+	 */
+	if (S_ISDIR(st.st_mode)) {
+		ret = fsck_report_ref(o, report,
+				      FSCK_MSG_BAD_REFERENT_FILETYPE,
+				      "points to the directory");
+		goto out;
+	}
+
+out:
+	return ret;
+}
+
 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 referent_path = STRBUF_INIT;
 	struct strbuf ref_content = STRBUF_INIT;
 	struct strbuf referent = STRBUF_INIT;
 	struct strbuf refname = STRBUF_INIT;
@@ -3484,12 +3553,24 @@ static int files_fsck_refs_content(struct ref_store *ref_store,
 					      "trailing garbage in ref");
 			goto cleanup;
 		}
+	} else {
+		strbuf_addf(&referent_path, "%s/%s",
+			    ref_store->gitdir, referent.buf);
+		/*
+		 * the referent may contain the spaces and the newline, need to
+		 * trim for path.
+		 */
+		strbuf_rtrim(&referent_path);
+		ret = files_fsck_symref_target(o, &report,
+					       &referent,
+					       &referent_path);
 	}
 
 cleanup:
 	strbuf_release(&refname);
 	strbuf_release(&ref_content);
 	strbuf_release(&referent);
+	strbuf_release(&referent_path);
 	return ret;
 }
 

t/t0602-reffiles-fsck.sh

@@ -209,4 +209,121 @@ test_expect_success 'regular ref content should be checked (aggregate)' '
 	test_cmp expect sorted_err
 '
 
+test_expect_success 'textual symref 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 "$branch_dir_prefix/a/b" &&
+
+	printf "ref: refs/heads/branch\n" >$branch_dir_prefix/branch-good &&
+	git refs verify 2>err &&
+	rm $branch_dir_prefix/branch-good &&
+	test_must_be_empty err &&
+
+	printf "ref: refs/heads/branch" >$branch_dir_prefix/branch-no-newline-1 &&
+	git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	warning: refs/heads/branch-no-newline-1: refMissingNewline: missing newline
+	EOF
+	rm $branch_dir_prefix/branch-no-newline-1 &&
+	test_cmp expect err &&
+
+	printf "ref: refs/heads/branch     " >$branch_dir_prefix/a/b/branch-trailing-1 &&
+	git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	warning: refs/heads/a/b/branch-trailing-1: refMissingNewline: missing newline
+	warning: refs/heads/a/b/branch-trailing-1: trailingRefContent: trailing garbage in ref
+	EOF
+	rm $branch_dir_prefix/a/b/branch-trailing-1 &&
+	test_cmp expect err &&
+
+	printf "ref: refs/heads/branch\n\n" >$branch_dir_prefix/a/b/branch-trailing-2 &&
+	git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	warning: refs/heads/a/b/branch-trailing-2: trailingRefContent: trailing garbage in ref
+	EOF
+	rm $branch_dir_prefix/a/b/branch-trailing-2 &&
+	test_cmp expect err &&
+
+	printf "ref: refs/heads/branch \n" >$branch_dir_prefix/a/b/branch-trailing-3 &&
+	git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	warning: refs/heads/a/b/branch-trailing-3: trailingRefContent: trailing garbage in ref
+	EOF
+	rm $branch_dir_prefix/a/b/branch-trailing-3 &&
+	test_cmp expect err &&
+
+	printf "ref: refs/heads/branch \n  " >$branch_dir_prefix/a/b/branch-complicated &&
+	git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	warning: refs/heads/a/b/branch-complicated: refMissingNewline: missing newline
+	warning: refs/heads/a/b/branch-complicated: trailingRefContent: trailing garbage in ref
+	EOF
+	rm $branch_dir_prefix/a/b/branch-complicated &&
+	test_cmp expect err &&
+
+	printf "ref: refs/heads/.branch\n" >$branch_dir_prefix/branch-bad-1 &&
+	test_must_fail git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	error: refs/heads/branch-bad-1: badReferentName: points to refname with invalid format
+	EOF
+	rm $branch_dir_prefix/branch-bad-1 &&
+	test_cmp expect err &&
+
+	printf "ref: reflogs/heads/main\n" >$branch_dir_prefix/branch-bad-2 &&
+	test_must_fail git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	error: refs/heads/branch-bad-2: escapeReferent: points to ref outside the refs directory
+	EOF
+	rm $branch_dir_prefix/branch-bad-2 &&
+	test_cmp expect err &&
+
+	printf "ref: refs/heads/a\n" >$branch_dir_prefix/branch-bad-3 &&
+	test_must_fail git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	error: refs/heads/branch-bad-3: badReferentFiletype: points to the directory
+	EOF
+	rm $branch_dir_prefix/branch-bad-3 &&
+	test_cmp expect err
+'
+
+test_expect_success 'textual symref content should be checked (aggregate)' '
+	test_when_finished "rm -rf repo" &&
+	git init repo &&
+	branch_dir_prefix=.git/refs/heads &&
+	tag_dir_prefix=.git/refs/tags &&
+	cd repo &&
+	test_commit default &&
+	mkdir -p "$branch_dir_prefix/a/b" &&
+
+	printf "ref: refs/heads/branch\n" >$branch_dir_prefix/branch-good &&
+	printf "ref: refs/heads/branch" >$branch_dir_prefix/branch-no-newline-1 &&
+	printf "ref: refs/heads/branch     " >$branch_dir_prefix/a/b/branch-trailing-1 &&
+	printf "ref: refs/heads/branch\n\n" >$branch_dir_prefix/a/b/branch-trailing-2 &&
+	printf "ref: refs/heads/branch \n" >$branch_dir_prefix/a/b/branch-trailing-3 &&
+	printf "ref: refs/heads/branch \n  " >$branch_dir_prefix/a/b/branch-complicated &&
+	printf "ref: refs/heads/.branch\n" >$branch_dir_prefix/branch-bad-1 &&
+	printf "ref: reflogs/heads/main\n" >$branch_dir_prefix/branch-bad-2 &&
+	printf "ref: refs/heads/a\n" >$branch_dir_prefix/branch-bad-3 &&
+
+	test_must_fail git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	error: refs/heads/branch-bad-1: badReferentName: points to refname with invalid format
+	error: refs/heads/branch-bad-2: escapeReferent: points to ref outside the refs directory
+	error: refs/heads/branch-bad-3: badReferentFiletype: points to the directory
+	warning: refs/heads/a/b/branch-complicated: refMissingNewline: missing newline
+	warning: refs/heads/a/b/branch-complicated: trailingRefContent: trailing garbage in ref
+	warning: refs/heads/a/b/branch-trailing-1: refMissingNewline: missing newline
+	warning: refs/heads/a/b/branch-trailing-1: trailingRefContent: trailing garbage in ref
+	warning: refs/heads/a/b/branch-trailing-2: trailingRefContent: trailing garbage in ref
+	warning: refs/heads/a/b/branch-trailing-3: trailingRefContent: trailing garbage in ref
+	warning: refs/heads/branch-no-newline-1: refMissingNewline: missing newline
+	EOF
+	sort err >sorted_err &&
+	test_cmp expect sorted_err
+'
+
 test_done