lirui-apache commented on a change in pull request #9864: [FLINK-14254][table] Introduce FileSystemOutputFormat for batch URL: https://github.com/apache/flink/pull/9864#discussion_r344031968
########## File path: flink-connectors/flink-connector-hive/src/main/java/org/apache/flink/connectors/hive/HiveOutputFormatFactory.java ########## @@ -0,0 +1,220 @@ +/* + * 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.connectors.hive; + +import org.apache.flink.configuration.Configuration; +import org.apache.flink.core.fs.Path; +import org.apache.flink.table.api.TableSchema; +import org.apache.flink.table.catalog.hive.client.HiveShim; +import org.apache.flink.table.catalog.hive.client.HiveShimLoader; +import org.apache.flink.table.filesystem.OutputFormatFactory; +import org.apache.flink.table.functions.hive.conversion.HiveInspectors; +import org.apache.flink.table.functions.hive.conversion.HiveObjectConversion; +import org.apache.flink.table.types.DataType; +import org.apache.flink.types.Row; +import org.apache.flink.util.Preconditions; +import org.apache.flink.util.StringUtils; + +import org.apache.hadoop.hive.conf.HiveConf; +import org.apache.hadoop.hive.metastore.api.SerDeInfo; +import org.apache.hadoop.hive.ql.exec.FileSinkOperator.RecordWriter; +import org.apache.hadoop.hive.serde2.Deserializer; +import org.apache.hadoop.hive.serde2.SerDeException; +import org.apache.hadoop.hive.serde2.SerDeUtils; +import org.apache.hadoop.hive.serde2.Serializer; +import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector; +import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorFactory; +import org.apache.hadoop.hive.serde2.objectinspector.StructObjectInspector; +import org.apache.hadoop.io.SequenceFile; +import org.apache.hadoop.io.compress.CompressionCodec; +import org.apache.hadoop.mapred.FileOutputFormat; +import org.apache.hadoop.mapred.JobConf; +import org.apache.hadoop.mapred.SequenceFileOutputFormat; +import org.apache.hadoop.util.ReflectionUtils; + +import java.io.IOException; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.List; +import java.util.Properties; + +/** + * Hive {@link OutputFormatFactory}, use {@link RecordWriter} to write record. + */ +public class HiveOutputFormatFactory implements OutputFormatFactory<Row> { + + private static final long serialVersionUID = 1L; + + private final String outputFormat; + + private final SerDeInfo serDeInfo; + + private final String[] allColumns; + + private final DataType[] allTypes; + + private final String[] partitionColumns; + + private final Properties tableProperties; + + private final String hiveVersion; + + private final JobConfWrapper confWrapper; + + // number of non-partitioning columns + private transient int numNonPartitionColumns; + + // SerDe in Hive-1.2.1 and Hive-2.3.4 can be of different classes, make sure to use a common base class + private transient Serializer recordSerDe; + + // to convert Flink object to Hive object + private transient HiveObjectConversion[] hiveConversions; + + //StructObjectInspector represents the hive row structure. + private transient StructObjectInspector rowObjectInspector; + + private transient boolean inited; + + private transient HiveShim hiveShim; Review comment: I understand this is just refactoring code. But HiveShim is now a Serializable. So actually we can simply hold a HiveShim instance and don't need the `hiveVersion` field. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
