HYTcrab commented on code in PR #3916: URL: https://github.com/apache/flink-cdc/pull/3916#discussion_r2098359060
########## flink-cdc-connect/flink-cdc-pipeline-connectors/flink-cdc-pipeline-connector-jdbc-parent/flink-cdc-pipeline-connector-jdbc-core/src/main/java/org/apache/flink/cdc/connectors/jdbc/sink/v2/JdbcWriter.java: ########## @@ -0,0 +1,239 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.flink.cdc.connectors.jdbc.sink.v2; + +import org.apache.flink.api.connector.sink2.Sink; +import org.apache.flink.api.connector.sink2.StatefulSink; +import org.apache.flink.cdc.common.event.TableId; +import org.apache.flink.cdc.common.schema.Schema; +import org.apache.flink.cdc.connectors.jdbc.config.JdbcSinkConfig; +import org.apache.flink.cdc.connectors.jdbc.dialect.JdbcSinkDialect; +import org.apache.flink.cdc.connectors.jdbc.sink.utils.JsonWrapper; +import org.apache.flink.connector.jdbc.JdbcExecutionOptions; +import org.apache.flink.connector.jdbc.JdbcStatementBuilder; +import org.apache.flink.connector.jdbc.datasource.connections.JdbcConnectionProvider; +import org.apache.flink.connector.jdbc.internal.JdbcOutputFormat; +import org.apache.flink.connector.jdbc.internal.JdbcOutputSerializer; +import org.apache.flink.connector.jdbc.internal.executor.JdbcBatchStatementExecutor; +import org.apache.flink.connector.jdbc.sink.writer.JdbcWriterState; + +import org.apache.flink.shaded.jackson2.com.fasterxml.jackson.core.JsonProcessingException; +import org.apache.flink.shaded.jackson2.com.fasterxml.jackson.core.type.TypeReference; + +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.io.IOException; +import java.util.Collections; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import java.util.Optional; +import java.util.concurrent.ConcurrentHashMap; +import java.util.function.Function; +import java.util.stream.Collectors; + +import static org.apache.flink.cdc.connectors.jdbc.sink.v2.RowKind.PK_ROW; +import static org.apache.flink.util.Preconditions.checkNotNull; + +/** Implementation class of the {@link StatefulSink.StatefulSinkWriter} interface. */ +public class JdbcWriter<IN> implements StatefulSink.StatefulSinkWriter<IN, JdbcWriterState> { + private static final Logger LOG = LoggerFactory.getLogger(JdbcWriter.class); + + private final JdbcExecutionOptions executionOptions; + private final JdbcConnectionProvider connectionProvider; + private final JdbcOutputSerializer<Object> outputSerializer; + private final RecordSerializationSchema<IN> serializationSchema; + private final JsonWrapper jsonWrapper; + + private final JdbcSinkDialect dialect; + private final Map<TableId, RichJdbcOutputFormat> outputHandlers; + + public JdbcWriter( + Sink.InitContext initContext, + JdbcExecutionOptions executionOptions, + JdbcConnectionProvider connectionProvider, + JdbcOutputSerializer<Object> outputSerializer, + RecordSerializationSchema<IN> serializationSchema, + JdbcSinkDialect dialect, + JdbcSinkConfig sinkConfig) { + + checkNotNull(initContext, "initContext must be defined"); + checkNotNull(executionOptions, "executionOptions must be defined"); + checkNotNull(connectionProvider, "connectionProvider must be defined"); + checkNotNull(outputSerializer, "outputSerializer must be defined"); + checkNotNull(serializationSchema, "serializationSchema must be defined"); + checkNotNull(sinkConfig, "sinkConfig must be defined"); + + this.jsonWrapper = new JsonWrapper(); + this.executionOptions = executionOptions; + this.connectionProvider = connectionProvider; + this.outputSerializer = outputSerializer; + this.serializationSchema = serializationSchema; + this.dialect = dialect; + this.outputHandlers = new ConcurrentHashMap<>(); + } + + @Override + public List<JdbcWriterState> snapshotState(long checkpointId) { + // Jdbc sink supports at-least-once semantic only. No state snapshotting & restoring + // required. + return Collections.emptyList(); + } + + @Override + public void write(IN event, Context context) throws IOException { + JdbcRowData[] rowDataElements = serializationSchema.serialize(event); + for (JdbcRowData rowData : rowDataElements) { + TableId tableId = rowData.getTableId(); + if (RowKind.SCHEMA_CHANGE.is(rowData.getRowKind())) { + // All previous outputHandlers would expire after schema changes. + flush(false); + Optional.ofNullable(outputHandlers.remove(tableId)) + .ifPresent(JdbcOutputFormat::close); Review Comment: The `close` method of `JdbcOutputFormat` closes the underlying JDBC connection. If multiple `outputHandler` share the same connection, closing and removing the `outputHandler` for a single table will also invalidate the others. As a result, the remaining outputHandlers will fail to write subsequent DataChangeEvents correctly. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: issues-unsubscr...@flink.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
