sink(ticdc): fix incorrect sanitize (#12044)

close #11727
pingcap · Feb 5, 2025 · e150d73 · e150d73
1 parent 77be86e
commit e150d73
Show file tree

Hide file tree

Showing 3 changed files with 4 additions and 9 deletions.
diff --git a/pkg/sink/codec/avro/avro_test.go b/pkg/sink/codec/avro/avro_test.go
@@ -912,7 +912,7 @@ func TestSanitizeName(t *testing.T) {
 		common.SanitizeName("1ColumnNameStartWithNumber"),
 	)
 	require.Equal(t, "A_B", common.SanitizeName("A.B"))
-	require.Equal(t, "columnNameWith______", common.SanitizeName("columnNameWith中文"))
+	require.Equal(t, "columnNameWith__", common.SanitizeName("columnNameWith中文"))
 }
 
 func TestGetAvroNamespace(t *testing.T) {

diff --git a/pkg/sink/codec/common/helper.go b/pkg/sink/codec/common/helper.go
@@ -224,10 +224,7 @@ func SanitizeName(name string) string {
 			}
 			changed = true
 		} else if !isValidNonFirstCharacter(c) {
-			b := []byte(string(c))
-			for k := 0; k < len(b); k++ {
-				sb.WriteString(replacementChar)
-			}
+			sb.WriteString(replacementChar)
 			changed = true
 		} else {
 			sb.WriteRune(c)
@@ -252,10 +249,7 @@ func SanitizeTopicName(name string) string {
 	var sb strings.Builder
 	for _, c := range name {
 		if !isValidNonFirstCharacterForTopicName(c) {
-			b := []byte(string(c))
-			for k := 0; k < len(b); k++ {
-				sb.WriteString(replacementChar)
-			}
+			sb.WriteString(replacementChar)
 			changed = true
 		} else {
 			sb.WriteRune(c)

diff --git a/tests/integration_tests/debezium/docker-compose.yml b/tests/integration_tests/debezium/docker-compose.yml
@@ -45,6 +45,7 @@ services:
       - CONFIG_STORAGE_TOPIC=my_connect_configs
       - OFFSET_STORAGE_TOPIC=my_connect_offsets
       - STATUS_STORAGE_TOPIC=my_connect_statuses
+      - LANG=C.UTF-8
   # watcher_dbz: # For Debug Purpose
   #   restart: always
   #   image: quay.io/debezium/kafka:2.4