refs/reftable: add fsck check for checking the table name

Add glue code in 'refs/reftable-backend.c' which calls the reftable
library to perform the fsck checks. Here we also map the reftable errors
to Git' fsck errors.

Introduce a check to validate table names for a given reftable stack.
Also add 'badReftableTableName' as a corresponding error within Git. The
reftable specification mentions:

  It suggested to use
  ${min_update_index}-${max_update_index}-${random}.ref as a naming
  convention.

So treat non-conformant file names as warnings.

While adding the fsck header to 'refs/reftable-backend.c', modify the
list to maintain lexicographical ordering.

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

Author: KarthikNayak

Documentation/fsck-msgids.adoc

@@ -38,6 +38,9 @@
 `badReferentName`::
 	(ERROR) The referent name of a symref is invalid.
 
+`badReftableTableName`::
+	(WARN) A reftable table has an invalid name.
+
 `badTagName`::
 	(INFO) A tag has an invalid format.
 

fsck.h

@@ -73,6 +73,7 @@ enum fsck_msg_type {
 	FUNC(UNKNOWN_TYPE, ERROR) \
 	FUNC(ZERO_PADDED_DATE, ERROR) \
 	/* warnings */ \
+	FUNC(BAD_REFTABLE_TABLE_NAME, WARN) \
 	FUNC(EMPTY_NAME, WARN) \
 	FUNC(FULL_PATHNAME, WARN) \
 	FUNC(HAS_DOT, WARN) \

refs/reftable-backend.c

@@ -6,6 +6,7 @@
 #include "../config.h"
 #include "../dir.h"
 #include "../environment.h"
+#include "../fsck.h"
 #include "../gettext.h"
 #include "../hash.h"
 #include "../hex.h"
@@ -15,10 +16,11 @@
 #include "../path.h"
 #include "../refs.h"
 #include "../reftable/reftable-basics.h"
-#include "../reftable/reftable-stack.h"
-#include "../reftable/reftable-record.h"
 #include "../reftable/reftable-error.h"
+#include "../reftable/reftable-fsck.h"
 #include "../reftable/reftable-iterator.h"
+#include "../reftable/reftable-record.h"
+#include "../reftable/reftable-stack.h"
 #include "../repo-settings.h"
 #include "../setup.h"
 #include "../strmap.h"
@@ -2674,11 +2676,56 @@ static int reftable_be_reflog_expire(struct ref_store *ref_store,
 	return ret;
 }
 
-static int reftable_be_fsck(struct ref_store *ref_store UNUSED,
-			    struct fsck_options *o UNUSED,
+static void reftable_fsck_verbose_handler(const char *msg, void *cb_data)
+{
+	struct fsck_options *o = cb_data;
+
+	if (o->verbose)
+		fprintf_ln(stderr, "%s", msg);
+}
+
+static const enum fsck_msg_id fsck_msg_id_map[] = {
+	[REFTABLE_FSCK_ERROR_TABLE_NAME] = FSCK_MSG_BAD_REFTABLE_TABLE_NAME,
+};
+
+static int reftable_fsck_error_handler(struct reftable_fsck_info *info,
+				       void *cb_data)
+{
+	struct fsck_ref_report report = { .path = info->path };
+	struct fsck_options *o = cb_data;
+	enum fsck_msg_id msg_id;
+
+	if (info->error < 0 || info->error >= REFTABLE_FSCK_MAX_VALUE)
+		BUG("unknown fsck error: %d", (int)info->error);
+
+	msg_id = fsck_msg_id_map[info->error];
+
+	if (!msg_id)
+		BUG("fsck_msg_id value missing for reftable error: %d", (int)info->error);
+
+	return fsck_report_ref(o, &report, msg_id, "%s", info->msg);
+}
+
+static int reftable_be_fsck(struct ref_store *ref_store, struct fsck_options *o,
 			    struct worktree *wt UNUSED)
 {
-	return 0;
+	struct reftable_ref_store *refs;
+	struct strmap_entry *entry;
+	struct hashmap_iter iter;
+	int ret = 0;
+
+	refs = reftable_be_downcast(ref_store, REF_STORE_READ, "fsck");
+
+	ret |= reftable_fsck_check(refs->main_backend.stack, reftable_fsck_error_handler,
+				   reftable_fsck_verbose_handler, o);
+
+	strmap_for_each_entry(&refs->worktree_backends, &iter, entry) {
+		struct reftable_backend *b = (struct reftable_backend *)entry->value;
+		ret |= reftable_fsck_check(b->stack, reftable_fsck_error_handler,
+					   reftable_fsck_verbose_handler, o);
+	}
+
+	return ret;
 }
 
 struct ref_storage_be refs_be_reftable = {

t/meson.build

@@ -145,6 +145,7 @@ integration_tests = [
   't0611-reftable-httpd.sh',
   't0612-reftable-jgit-compatibility.sh',
   't0613-reftable-write-options.sh',
+  't0614-reftable-fsck.sh',
   't1000-read-tree-m-3way.sh',
   't1001-read-tree-m-2way.sh',
   't1002-read-tree-m-u-2way.sh',

t/t0614-reftable-fsck.sh

@@ -0,0 +1,58 @@
+#!/bin/sh
+
+test_description='Test reftable backend consistency check'
+
+GIT_TEST_DEFAULT_REF_FORMAT=reftable
+export GIT_TEST_DEFAULT_REF_FORMAT
+
+. ./test-lib.sh
+
+test_expect_success "no errors reported on a well formed repository" '
+	test_when_finished "rm -rf repo" &&
+	git init repo &&
+	(
+		cd repo &&
+		git commit --allow-empty -m initial &&
+
+		for i in $(test_seq 20)
+		do
+			git update-ref refs/heads/branch-$i HEAD || return 1
+		done &&
+
+		# The repository should end up with multiple tables.
+		test_line_count ">" 1 .git/reftable/tables.list &&
+
+		git refs verify 2>err &&
+		test_must_be_empty err
+	)
+'
+
+for TABLE_NAME in "foo-bar-e4d12d59.ref" \
+	"0x00000000zzzz-0x00000000zzzz-e4d12d59.ref" \
+	"0x000000000001-0x000000000002-e4d12d59.abc" \
+	"0x000000000001-0x000000000002-e4d12d59.refabc"; do
+	test_expect_success "table name $TABLE_NAME should be checked" '
+		test_when_finished "rm -rf repo" &&
+		git init repo &&
+		(
+			cd repo &&
+			git commit --allow-empty -m initial &&
+
+			git refs verify 2>err &&
+			test_must_be_empty err &&
+
+			EXISTING_TABLE=$(head -n1 .git/reftable/tables.list) &&
+			mv ".git/reftable/$EXISTING_TABLE" ".git/reftable/$TABLE_NAME" &&
+			sed "s/${EXISTING_TABLE}/${TABLE_NAME}/g" .git/reftable/tables.list > tables.list &&
+			mv tables.list .git/reftable/tables.list &&
+
+			git refs verify 2>err &&
+			cat >expect <<-EOF &&
+			warning: ${TABLE_NAME}: badReftableTableName: invalid reftable table name
+			EOF
+			test_cmp expect err
+		)
+	'
+done
+
+test_done