SourabhBadhya commented on code in PR #5251: URL: https://github.com/apache/hive/pull/5251#discussion_r1644025199
########## iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/IcebergMergeTaskProperties.java: ########## @@ -42,14 +45,23 @@ public Path getTmpLocation() { return new Path(location + "/data/"); } - public StorageFormatDescriptor getStorageFormatDescriptor() throws IOException { - FileFormat fileFormat = FileFormat.fromString(properties.getProperty(TableProperties.DEFAULT_FILE_FORMAT, - TableProperties.DEFAULT_FILE_FORMAT_DEFAULT)); - StorageFormatDescriptor descriptor = storageFormatFactory.get(fileFormat.name()); - if (descriptor == null) { - throw new IOException("Unsupported storage format descriptor"); + @Override + public Map<Path, Object> getSplitProperties() throws IOException { Review Comment: Well the idea is that this can include anything which is related to the split itself. Hence I have generically added it as a split property. ########## iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/mapreduce/IcebergMergeSplit.java: ########## @@ -0,0 +1,79 @@ +/* + * 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.mapreduce; + +import java.io.DataInput; +import java.io.DataOutput; +import java.io.IOException; +import java.util.Map; +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.iceberg.ContentFile; +import org.apache.iceberg.util.SerializationUtil; + +public class IcebergMergeSplit extends FileSplit implements org.apache.hadoop.mapred.InputSplit { + private transient Configuration conf; + private ContentFile contentFile; + + // public no-argument constructor for deserialization + public IcebergMergeSplit() { + } + + public IcebergMergeSplit(Configuration conf, + CombineHiveInputFormat.CombineHiveInputSplit split, + Integer partition, Map<Path, Object> properties) throws IOException { Review Comment: Well the idea is that this can include anything which is related to the split itself. Hence I have generically added it as a split property. ########## ql/src/java/org/apache/hadoop/hive/ql/io/CombineHiveRecordReader.java: ########## @@ -88,14 +90,26 @@ public CombineHiveRecordReader(InputSplit split, Configuration conf, } } + FileSplit inputSplit; // create a split for the given partition - FileSplit fsplit = new FileSplit(hsplit.getPaths()[partition], hsplit - .getStartOffsets()[partition], hsplit.getLengths()[partition], hsplit - .getLocations()); + if (inputFormat instanceof CombineHiveInputFormat.MergeSplit) { + if (mrwork == null) { Review Comment: Done. -- 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: gitbox-unsubscr...@hive.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org