diff mbox series

[GSoC,v14,11/11] fsck: add ref name check for files backend

Message ID ZqumjDzfeaLZQgr5@ArchLinux (mailing list archive)
State Superseded
Headers show
Series ref consistency check infra setup | expand

Commit Message

shejialuo Aug. 1, 2024, 3:15 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 "@".

However, a file ending with ".lock" should not be marked as having a bad
ref name. It is expected that concurrent writers may have such lock files.
We currently ignore this situation. But for bare ".lock" file, we will
report it as error.

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 <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          | 32 ++++++++++++
 t/t0602-reffiles-fsck.sh      | 94 +++++++++++++++++++++++++++++++++++
 4 files changed, 130 insertions(+)
 create mode 100755 t/t0602-reffiles-fsck.sh

Comments

Patrick Steinhardt Aug. 5, 2024, 12:58 p.m. UTC | #1
On Thu, Aug 01, 2024 at 11:15:24PM +0800, shejialuo wrote:
> diff --git a/refs/files-backend.c b/refs/files-backend.c
> index 5574e78656..1186b6cbb1 100644
> --- a/refs/files-backend.c
> +++ b/refs/files-backend.c
> @@ -3419,6 +3419,37 @@ 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;
> +	size_t len = 0;
> +	int ret = 0;
> +
> +	/*
> +	 * Ignore the files ending with ".lock" as they may be lock files
> +	 * However, do not allow bare ".lock" files.
> +	 */
> +	if (strip_suffix(iter->basename, ".lock", &len) && (len != 0))
> +		goto clean;

Better:

    if (ends_with(iter->basename, ".lock))
            goto cleanup;

Patrick
diff mbox series

Patch

diff --git a/Documentation/fsck-msgids.txt b/Documentation/fsck-msgids.txt
index 7c809fddf1..68a2801f15 100644
--- a/Documentation/fsck-msgids.txt
+++ b/Documentation/fsck-msgids.txt
@@ -22,6 +22,9 @@ 
 `badRefFiletype`::
 	(ERROR) A ref has a bad file type.
 
+`badRefName`::
+	(ERROR) A ref has an invalid format.
+
 `badTagName`::
 	(INFO) A tag has an invalid format.
 
diff --git a/fsck.h b/fsck.h
index af02174973..500b4c04d2 100644
--- a/fsck.h
+++ b/fsck.h
@@ -32,6 +32,7 @@  enum fsck_msg_type {
 	FUNC(BAD_OBJECT_SHA1, ERROR) \
 	FUNC(BAD_PARENT_SHA1, ERROR) \
 	FUNC(BAD_REF_FILETYPE, 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 5574e78656..1186b6cbb1 100644
--- a/refs/files-backend.c
+++ b/refs/files-backend.c
@@ -3419,6 +3419,37 @@  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;
+	size_t len = 0;
+	int ret = 0;
+
+	/*
+	 * Ignore the files ending with ".lock" as they may be lock files
+	 * However, do not allow bare ".lock" files.
+	 */
+	if (strip_suffix(iter->basename, ".lock", &len) && (len != 0))
+		goto clean;
+
+	if (check_refname_format(iter->basename, REFNAME_ALLOW_ONELEVEL)) {
+		struct fsck_ref_report report = { .path = NULL };
+
+		strbuf_addf(&sb, "%s/%s", refs_check_dir, iter->relative_path);
+		report.path = sb.buf;
+		ret = fsck_report_ref(o, &report,
+				      FSCK_MSG_BAD_REF_NAME,
+				      "invalid refname format");
+	}
+
+clean:
+	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,
@@ -3471,6 +3502,7 @@  static int files_fsck_refs(struct ref_store *ref_store,
 			   struct fsck_options *o)
 {
 	files_fsck_refs_fn fsck_refs_fn[]= {
+		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..2be28427ab
--- /dev/null
+++ b/t/t0602-reffiles-fsck.sh
@@ -0,0 +1,94 @@ 
+#!/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_PASSES_SANITIZE_LEAK=true
+
+. ./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 &&
+
+	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 &&
+
+	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 &&
+
+	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 &&
+
+	cp $tag_dir_prefix/tag-1 $tag_dir_prefix/tag-1.lock &&
+	git fsck 2>err &&
+	rm $tag_dir_prefix/tag-1.lock &&
+	test_must_be_empty err &&
+
+	cp $tag_dir_prefix/tag-1 $tag_dir_prefix/.lock &&
+	test_must_fail git fsck 2>err &&
+	cat >expect <<-EOF &&
+	error: refs/tags/.lock: badRefName: invalid refname format
+	EOF
+	rm $tag_dir_prefix/.lock &&
+	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 &&
+
+
+	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 &&
+
+
+	cp $branch_dir_prefix/branch-1 $branch_dir_prefix/@ &&
+	git -c fsck.badRefName=ignore fsck 2>err &&
+	test_must_be_empty err
+'
+
+test_done