packed-backend: check whether the "packed-refs" is sorted

We will always try to sort the "packed-refs" increasingly by comparing
the refname. So, we should add checks to verify whether the "packed-refs"
is sorted.

It may seem that we could add a new "struct strbuf refname" into the
"struct fsck_packed_ref_entry" and during the parsing process, we could
store the refname into the entry and then we could compare later.
However, this is not a good design due to the following reasons:

1. Because we need to store the state across the whole checking
   lifetime, we would consume a lot of memory if there are many entries
   in the "packed-refs" file.
2. The most important is that we cannot reuse the existing compare
   functions which cause repetition.

So, instead of storing the "struct strbuf", let's use the existing
structure "struct snaphost_record". And thus we could use the existing
function "cmp_packed_ref_records".

However, this function need an extra parameter for "struct snaphost".
Extract the common part into a new function "cmp_packed_ref_records" to
reuse this function to compare.

Then, create a new function "packed_fsck_ref_sorted" to use the new fsck
message "packedRefUnsorted(ERROR)" to report to the user.

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

@@ -190,6 +190,9 @@
 `packedRefMissingHeader`::
 	(INFO) The "packed-refs" file does not contain the header.
 
+`packedRefUnsorted`::
+	(ERROR) The "packed-refs" file is not sorted.
+
 `refMissingNewline`::
 	(INFO) A loose ref that does not end with newline(LF). As
 	valid implementations of Git never created such a loose ref

fsck.h

@@ -56,6 +56,7 @@ enum fsck_msg_type {
 	FUNC(MISSING_TYPE_ENTRY, ERROR) \
 	FUNC(MULTIPLE_AUTHORS, ERROR) \
 	FUNC(PACKED_REF_ENTRY_NOT_TERMINATED, ERROR) \
+	FUNC(PACKED_REF_UNSORTED, ERROR) \
 	FUNC(TREE_NOT_SORTED, ERROR) \
 	FUNC(UNKNOWN_TYPE, ERROR) \
 	FUNC(ZERO_PADDED_DATE, ERROR) \

refs/packed-backend.c

@@ -301,14 +301,8 @@ struct snapshot_record {
 	size_t len;
 };
 
-static int cmp_packed_ref_records(const void *v1, const void *v2,
-				  void *cb_data)
+static int cmp_packed_refname(const char *r1, const char *r2)
 {
-	const struct snapshot *snapshot = cb_data;
-	const struct snapshot_record *e1 = v1, *e2 = v2;
-	const char *r1 = e1->start + snapshot_hexsz(snapshot) + 1;
-	const char *r2 = e2->start + snapshot_hexsz(snapshot) + 1;
-
 	while (1) {
 		if (*r1 == '\n')
 			return *r2 == '\n' ? 0 : -1;
@@ -323,6 +317,17 @@ static int cmp_packed_ref_records(const void *v1, const void *v2,
 	}
 }
 
+static int cmp_packed_ref_records(const void *v1, const void *v2,
+				  void *cb_data)
+{
+	const struct snapshot *snapshot = cb_data;
+	const struct snapshot_record *e1 = v1, *e2 = v2;
+	const char *r1 = e1->start + snapshot_hexsz(snapshot) + 1;
+	const char *r2 = e2->start + snapshot_hexsz(snapshot) + 1;
+
+	return cmp_packed_refname(r1, r2);
+}
+
 /*
  * Compare a snapshot record at `rec` to the specified NUL-terminated
  * refname.
@@ -1776,13 +1781,17 @@ struct fsck_packed_ref_entry {
 	int has_peeled;
 	struct object_id oid;
 	struct object_id peeled;
+
+	struct snapshot_record record;
 };
 
-static struct fsck_packed_ref_entry *create_fsck_packed_ref_entry(int line_number)
+static struct fsck_packed_ref_entry *create_fsck_packed_ref_entry(int line_number,
+								  const char *start)
 {
 	struct fsck_packed_ref_entry *entry = xcalloc(1, sizeof(*entry));
 	entry->line_number = line_number;
 	entry->has_peeled = 0;
+	entry->record.start = start;
 	return entry;
 }
 
@@ -1981,6 +1990,50 @@ static int packed_fsck_ref_oid(struct fsck_options *o, struct ref_store *ref_sto
 	return ret;
 }
 
+static int packed_fsck_ref_sorted(struct fsck_options *o,
+				  struct ref_store *ref_store,
+				  struct fsck_packed_ref_entry **entries,
+				  int nr)
+{
+	size_t hexsz = ref_store->repo->hash_algo->hexsz;
+	struct strbuf packed_entry = STRBUF_INIT;
+	struct fsck_ref_report report = { 0 };
+	struct strbuf refname1 = STRBUF_INIT;
+	struct strbuf refname2 = STRBUF_INIT;
+	int ret = 0;
+
+	for (int i = 1; i < nr; i++) {
+		const char *r1 = entries[i - 1]->record.start + hexsz + 1;
+		const char *r2 = entries[i]->record.start + hexsz + 1;
+
+		if (cmp_packed_refname(r1, r2) >= 0) {
+			const char *err_fmt =
+				"refname '%s' is not less than next refname '%s'";
+			const char *eol;
+			eol = memchr(entries[i - 1]->record.start, '\n',
+				     entries[i - 1]->record.len);
+			strbuf_add(&refname1, r1, eol - r1);
+			eol = memchr(entries[i]->record.start, '\n',
+				     entries[i]->record.len);
+			strbuf_add(&refname2, r2, eol - r2);
+
+			strbuf_addf(&packed_entry, "packed-refs line %d",
+				    entries[i - 1]->line_number);
+			report.path = packed_entry.buf;
+			ret = fsck_report_ref(o, &report,
+					      FSCK_MSG_PACKED_REF_UNSORTED,
+					      err_fmt, refname1.buf, refname2.buf);
+			goto cleanup;
+		}
+	}
+
+cleanup:
+	strbuf_release(&packed_entry);
+	strbuf_release(&refname1);
+	strbuf_release(&refname2);
+	return ret;
+}
+
 static int packed_fsck_ref_content(struct fsck_options *o,
 				   struct ref_store *ref_store,
 				   const char *start, const char *eof)
@@ -2010,7 +2063,7 @@ static int packed_fsck_ref_content(struct fsck_options *o,
 	ALLOC_ARRAY(entries, entry_alloc);
 	while (start < eof) {
 		struct fsck_packed_ref_entry *entry
-			= create_fsck_packed_ref_entry(line_number);
+			= create_fsck_packed_ref_entry(line_number, start);
 		ALLOC_GROW(entries, entry_nr + 1, entry_alloc);
 		entries[entry_nr++] = entry;
 
@@ -2026,16 +2079,19 @@ static int packed_fsck_ref_content(struct fsck_options *o,
 			start = eol + 1;
 			line_number++;
 		}
+		entry->record.len = start - entry->record.start;
 	}
 
 	/*
 	 * If there is anything wrong during the parsing of the "packed-refs"
 	 * file, we should not check the object of the refs.
 	 */
-	if (ret)
+	if (ret) {
 		o->safe_object_check = 0;
-	else
+	} else {
 		ret |= packed_fsck_ref_oid(o, ref_store, entries, entry_nr);
+		ret |= packed_fsck_ref_sorted(o, ref_store, entries, entry_nr);
+	}
 
 	free_fsck_packed_ref_entries(entries, entry_nr);
 	return ret;

t/t0602-reffiles-fsck.sh

@@ -765,4 +765,44 @@ test_expect_success 'packed-refs objects should be checked' '
 	done
 '
 
+test_expect_success 'packed-ref sorted should be checked' '
+	test_when_finished "rm -rf repo" &&
+	git init repo &&
+	cd repo &&
+	test_commit default &&
+	git branch branch-1 &&
+	git branch branch-2 &&
+	git tag -a annotated-tag-1 -m tag-1 &&
+
+	branch_1_oid=$(git rev-parse branch-1) &&
+	branch_2_oid=$(git rev-parse branch-2) &&
+	tag_1_oid=$(git rev-parse annotated-tag-1) &&
+	tag_1_peeled_oid=$(git rev-parse annotated-tag-1^{}) &&
+
+	refname1="refs/heads/main" &&
+	refname2="refs/heads/foo" &&
+	refname3="refs/tags/foo" &&
+
+	printf "# pack-refs with: peeled fully-peeled sorted \n"  >.git/packed-refs &&
+	printf "%s %s\n" "$branch_2_oid" "$refname1" >>.git/packed-refs &&
+	printf "%s %s\n" "$branch_1_oid" "$refname2" >>.git/packed-refs &&
+	test_must_fail git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	error: packed-refs line 2: packedRefUnsorted: refname '\''$refname1'\'' is not less than next refname '\''$refname2'\''
+	EOF
+	rm .git/packed-refs &&
+	test_cmp expect err &&
+
+	printf "# pack-refs with: peeled fully-peeled sorted \n"  >.git/packed-refs &&
+	printf "%s %s\n" "$tag_1_oid" "$refname3" >>.git/packed-refs &&
+	printf "^%s\n" "$tag_1_peeled_oid" >>.git/packed-refs &&
+	printf "%s %s\n" "$branch_2_oid" "$refname2" >>.git/packed-refs &&
+	test_must_fail git refs verify 2>err &&
+	cat >expect <<-EOF &&
+	error: packed-refs line 2: packedRefUnsorted: refname '\''$refname3'\'' is not less than next refname '\''$refname2'\''
+	EOF
+	rm .git/packed-refs &&
+	test_cmp expect err
+'
+
 test_done