zjuwangg commented on a change in pull request #8522: [FLINK-12572][hive]Implement HiveInputFormat to read Hive tables URL: https://github.com/apache/flink/pull/8522#discussion_r290109929
########## File path: flink-connectors/flink-connector-hive/src/main/java/org/apache/flink/batch/connectors/hive/HiveTableInputFormat.java ########## @@ -0,0 +1,275 @@ +/* + * 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.batch.connectors.hive; + +import org.apache.flink.api.common.io.LocatableInputSplitAssigner; +import org.apache.flink.api.common.io.statistics.BaseStatistics; +import org.apache.flink.api.common.typeinfo.TypeInformation; +import org.apache.flink.api.java.hadoop.common.HadoopInputFormatCommonBase; +import org.apache.flink.api.java.hadoop.mapred.wrapper.HadoopDummyReporter; +import org.apache.flink.api.java.typeutils.ResultTypeQueryable; +import org.apache.flink.api.java.typeutils.RowTypeInfo; +import org.apache.flink.core.io.InputSplitAssigner; +import org.apache.flink.table.catalog.hive.util.HiveTableUtil; +import org.apache.flink.types.Row; + +import org.apache.hadoop.conf.Configurable; +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.hive.metastore.api.StorageDescriptor; +import org.apache.hadoop.hive.serde2.Deserializer; +import org.apache.hadoop.hive.serde2.SerDeUtils; +import org.apache.hadoop.hive.serde2.objectinspector.StructField; +import org.apache.hadoop.hive.serde2.objectinspector.StructObjectInspector; +import org.apache.hadoop.io.Writable; +import org.apache.hadoop.mapred.InputFormat; +import org.apache.hadoop.mapred.JobConf; +import org.apache.hadoop.mapred.JobConfigurable; +import org.apache.hadoop.mapred.RecordReader; +import org.apache.hadoop.security.Credentials; +import org.apache.hadoop.security.UserGroupInformation; +import org.apache.hadoop.util.ReflectionUtils; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.io.IOException; +import java.io.ObjectInputStream; +import java.io.ObjectOutputStream; +import java.util.ArrayList; +import java.util.List; +import java.util.Properties; + +import static org.apache.flink.util.Preconditions.checkNotNull; +import static org.apache.hadoop.mapreduce.lib.input.FileInputFormat.INPUT_DIR; + +/** + * The HiveTableInputFormat are inspired by the HCatInputFormat and HadoopInputFormatBase. + * It's used to read from hive partition/non-partition table. + */ +public class HiveTableInputFormat extends HadoopInputFormatCommonBase<Row, HiveTableInputSplit> + implements ResultTypeQueryable { + private static final long serialVersionUID = 6351448428766433164L; + private static Logger logger = LoggerFactory.getLogger(HiveTableInputFormat.class); + + private JobConf jobConf; + + protected transient Writable key; + protected transient Writable value; + + private transient RecordReader<Writable, Writable> recordReader; + protected transient boolean fetched = false; + protected transient boolean hasNext; + + private Boolean isPartitioned; + private RowTypeInfo rowTypeInfo; + + //Necessary info to init deserializer + private String[] partitionColNames; + //For non-partition hive table, partitions only contains one partition which partitionValues is empty. + private List<HiveTablePartition> partitions; + private transient Deserializer deserializer; + //Hive StructField list contain all related info for specific serde. + private transient List<? extends StructField> structFields; + //StructObjectInspector in hive helps us to look into the internal structure of a struct object. + private transient StructObjectInspector structObjectInspector; + private transient InputFormat mapredInputFormat; + private transient HiveTablePartition hiveTablePartition; + + public HiveTableInputFormat( + JobConf jobConf, + Boolean isPartitioned, + String[] partitionColNames, + List<HiveTablePartition> partitions, + RowTypeInfo rowTypeInfo) { + super(jobConf.getCredentials()); + this.rowTypeInfo = checkNotNull(rowTypeInfo, "rowTypeInfo can not be null."); + this.jobConf = new JobConf(jobConf); + this.isPartitioned = checkNotNull(isPartitioned, "isPartitioned can not be null."); Review comment: Yes. ---------------------------------------------------------------- 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: us...@infra.apache.org With regards, Apache Git Services
