@@ -173,6 +173,20 @@
`nullSha1`::
(WARN) Tree contains entries pointing to a null sha1.
+`refMissingNewline`::
+ (INFO) A loose ref that does not end with newline(LF). As
+ valid implementations of Git never created such a loose ref
+ file, it may become an error in the future. Report to the
+ git@vger.kernel.org mailing list if you see this error, as
+ we need to know what tools created such a file.
+
+`trailingRefContent`::
+ (INFO) A loose ref has trailing content. As valid implementations
+ of Git never created such a loose ref file, it may become an
+ error in the future. Report to the git@vger.kernel.org mailing
+ list if you see this error, as we need to know what tools
+ created such a file.
+
`treeNotSorted`::
(ERROR) A tree is not properly sorted.
@@ -85,6 +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)
@@ -1789,7 +1789,7 @@ 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);
@@ -569,7 +569,7 @@ 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)
@@ -606,7 +606,7 @@ 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)) {
@@ -628,6 +628,10 @@ int parse_loose_ref_contents(const struct git_hash_algo *algop,
*failure_errno = EINVAL;
return -1;
}
+
+ if (trailing)
+ *trailing = p;
+
return 0;
}
@@ -3513,6 +3517,7 @@ static int files_fsck_refs_content(struct ref_store *ref_store,
struct strbuf ref_content = STRBUF_INIT;
struct strbuf referent = STRBUF_INIT;
struct fsck_ref_report report = { 0 };
+ const char *trailing = NULL;
unsigned int type = 0;
int failure_errno = 0;
struct object_id oid;
@@ -3533,7 +3538,7 @@ static int files_fsck_refs_content(struct ref_store *ref_store,
if (parse_loose_ref_contents(ref_store->repo->hash_algo,
ref_content.buf, &oid, &referent,
- &type, &failure_errno)) {
+ &type, &trailing, &failure_errno)) {
strbuf_rtrim(&ref_content);
ret = fsck_report_ref(o, &report,
FSCK_MSG_BAD_REF_CONTENT,
@@ -3541,6 +3546,21 @@ static int files_fsck_refs_content(struct ref_store *ref_store,
goto cleanup;
}
+ if (!(type & REF_ISSYMREF)) {
+ if (!*trailing) {
+ ret = fsck_report_ref(o, &report,
+ FSCK_MSG_REF_MISSING_NEWLINE,
+ "misses LF at the end");
+ goto cleanup;
+ }
+ if (*trailing != '\n' || *(trailing + 1)) {
+ ret = fsck_report_ref(o, &report,
+ FSCK_MSG_TRAILING_REF_CONTENT,
+ "has trailing garbage: '%s'", trailing);
+ goto cleanup;
+ }
+ }
+
cleanup:
strbuf_release(&ref_content);
strbuf_release(&referent);
@@ -716,7 +716,7 @@ 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
@@ -201,6 +201,61 @@ test_expect_success 'regular ref content should be checked (individual)' '
error: refs/heads/a/b/branch-bad: badRefContent: $bad_content
EOF
rm $branch_dir_prefix/a/b/branch-bad &&
+ test_cmp expect err &&
+
+ printf "%s" "$(git rev-parse main)" >$branch_dir_prefix/branch-no-newline &&
+ git refs verify 2>err &&
+ cat >expect <<-EOF &&
+ warning: refs/heads/branch-no-newline: refMissingNewline: misses LF at the end
+ EOF
+ rm $branch_dir_prefix/branch-no-newline &&
+ test_cmp expect err &&
+
+ printf "%s garbage" "$(git rev-parse main)" >$branch_dir_prefix/branch-garbage &&
+ git refs verify 2>err &&
+ cat >expect <<-EOF &&
+ warning: refs/heads/branch-garbage: trailingRefContent: has trailing garbage: '\'' garbage'\''
+ EOF
+ rm $branch_dir_prefix/branch-garbage &&
+ test_cmp expect err &&
+
+ printf "%s\n\n\n" "$(git rev-parse main)" >$tag_dir_prefix/tag-garbage-1 &&
+ git refs verify 2>err &&
+ cat >expect <<-EOF &&
+ warning: refs/tags/tag-garbage-1: trailingRefContent: has trailing garbage: '\''
+
+
+ '\''
+ EOF
+ rm $tag_dir_prefix/tag-garbage-1 &&
+ test_cmp expect err &&
+
+ printf "%s\n\n\n garbage" "$(git rev-parse main)" >$tag_dir_prefix/tag-garbage-2 &&
+ git refs verify 2>err &&
+ cat >expect <<-EOF &&
+ warning: refs/tags/tag-garbage-2: trailingRefContent: has trailing garbage: '\''
+
+
+ garbage'\''
+ EOF
+ rm $tag_dir_prefix/tag-garbage-2 &&
+ test_cmp expect err &&
+
+ printf "%s garbage\na" "$(git rev-parse main)" >$tag_dir_prefix/tag-garbage-3 &&
+ git refs verify 2>err &&
+ cat >expect <<-EOF &&
+ warning: refs/tags/tag-garbage-3: trailingRefContent: has trailing garbage: '\'' garbage
+ a'\''
+ EOF
+ rm $tag_dir_prefix/tag-garbage-3 &&
+ test_cmp expect err &&
+
+ printf "%s garbage" "$(git rev-parse main)" >$tag_dir_prefix/tag-garbage-4 &&
+ test_must_fail git -c fsck.trailingRefContent=error refs verify 2>err &&
+ cat >expect <<-EOF &&
+ error: refs/tags/tag-garbage-4: trailingRefContent: has trailing garbage: '\'' garbage'\''
+ EOF
+ rm $tag_dir_prefix/tag-garbage-4 &&
test_cmp expect err
'
@@ -219,12 +274,16 @@ test_expect_success 'regular ref content should be checked (aggregate)' '
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 &&
+ printf "%s" "$(git rev-parse main)" >$branch_dir_prefix/branch-no-newline &&
+ printf "%s garbage" "$(git rev-parse main)" >$branch_dir_prefix/branch-garbage &&
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
+ warning: refs/heads/branch-garbage: trailingRefContent: has trailing garbage: '\'' garbage'\''
+ warning: refs/heads/branch-no-newline: refMissingNewline: misses LF at the end
EOF
sort err >sorted_err &&
test_cmp expect sorted_err
@@ -278,6 +337,14 @@ test_expect_success 'ref content checks should work with worktrees' '
error: worktrees/worktree-1/refs/worktree/bad-branch-3: badRefContent: $bad_content_3
EOF
rm $worktree1_refdir_prefix/bad-branch-3 &&
+ test_cmp expect err &&
+
+ printf "%s" "$(git rev-parse HEAD)" >$worktree1_refdir_prefix/branch-no-newline &&
+ git refs verify 2>err &&
+ cat >expect <<-EOF &&
+ warning: worktrees/worktree-1/refs/worktree/branch-no-newline: refMissingNewline: misses LF at the end
+ EOF
+ rm $worktree1_refdir_prefix/branch-no-newline &&
test_cmp expect err
'
We have already used "parse_loose_ref_contents" function to check whether the ref content is valid in files backend. However, by using "parse_loose_ref_contents", we allow the ref's content to end with garbage or without a newline. Even though we never create such loose refs ourselves, we have accepted such loose refs. So, it is entirely possible that some third-party tools may rely on such loose refs being valid. We should not report an error fsck message at current. We should notify the users about such "curiously formatted" loose refs so that adequate care is taken before we decide to tighten the rules in the future. And it's not suitable either to report a warn fsck message to the user. We don't yet want the "--strict" flag that controls this bit to end up generating errors for such weirdly-formatted reference contents, as we first want to assess whether this retroactive tightening will cause issues for any tools out there. It may cause compatibility issues which may break the repository. So, we add the following two fsck infos to represent the situation where the ref content ends without newline or has trailing garbages: 1. refMissingNewline(INFO): A loose ref that does not end with newline(LF). 2. trailingRefContent(INFO): A loose ref has trailing content. It might appear that we can't provide the user with any warnings by using FSCK_INFO. However, 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 issues. 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 | 14 ++++++++ fsck.h | 2 ++ refs.c | 2 +- refs/files-backend.c | 26 ++++++++++++-- refs/refs-internal.h | 2 +- t/t0602-reffiles-fsck.sh | 67 +++++++++++++++++++++++++++++++++++ 6 files changed, 108 insertions(+), 5 deletions(-)