massdosage commented on a change in pull request #933: URL: https://github.com/apache/incubator-iceberg/pull/933#discussion_r414474126
########## File path: mr/src/main/java/org/apache/iceberg/mr/mapred/IcebergInputFormat.java ########## @@ -0,0 +1,259 @@ +/* + * 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.iceberg.mr.mapred; + +import java.io.DataInput; +import java.io.DataOutput; +import java.io.IOException; +import java.net.URI; +import java.net.URISyntaxException; +import java.util.Iterator; +import java.util.List; +import java.util.stream.Collectors; +import java.util.stream.StreamSupport; +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.io.CombineHiveInputFormat; +import org.apache.hadoop.mapred.FileSplit; +import org.apache.hadoop.mapred.InputFormat; +import org.apache.hadoop.mapred.InputSplit; +import org.apache.hadoop.mapred.JobConf; +import org.apache.hadoop.mapred.RecordReader; +import org.apache.hadoop.mapred.Reporter; +import org.apache.iceberg.CombinedScanTask; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.FileScanTask; +import org.apache.iceberg.Schema; +import org.apache.iceberg.Table; +import org.apache.iceberg.data.Record; +import org.apache.iceberg.hadoop.HadoopInputFile; +import org.apache.iceberg.hadoop.HadoopTables; +import org.apache.iceberg.io.CloseableIterable; +import org.apache.iceberg.io.InputFile; +import org.apache.iceberg.mr.SerializationUtil; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +/** + * CombineHiveInputFormat.AvoidSplitCombination is implemented to correctly delegate InputSplit + * creation to this class. See: https://stackoverflow.com/questions/29133275/ + * custom-inputformat-getsplits-never-called-in-hive + */ +public class IcebergInputFormat<T> implements InputFormat<Void, T>, CombineHiveInputFormat.AvoidSplitCombination { Review comment: OK, I'm a bit confused now. Do we want to keep this here, move it to `iceberg-hive` or create a new subproject? Bear in mind that there will be other classes like the Hive SerDe, StorageHandler etc. built around this in future. We were intending to put all that in `iceberg-hive` but if you'd prefer to have some other subproject that contains them all that's fine too. ---------------------------------------------------------------- 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 --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org
