vinothchandar commented on a change in pull request #1804: URL: https://github.com/apache/hudi/pull/1804#discussion_r475940809
########## File path: hudi-hadoop-mr/src/main/java/org/apache/hudi/hadoop/realtime/HoodieHFileRealtimeInputFormat.java ########## @@ -0,0 +1,110 @@ +/* + * 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.hudi.hadoop.realtime; + +import java.io.IOException; +import java.util.Arrays; +import java.util.stream.Stream; + +import org.apache.hadoop.fs.FileStatus; +import org.apache.hadoop.hive.serde2.ColumnProjectionUtils; +import org.apache.hadoop.io.ArrayWritable; +import org.apache.hadoop.io.NullWritable; +import org.apache.hadoop.mapred.FileSplit; +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.hudi.common.table.timeline.HoodieDefaultTimeline; +import org.apache.hudi.common.util.ValidationUtils; +import org.apache.hudi.hadoop.HoodieHFileInputFormat; +import org.apache.hudi.hadoop.UseFileSplitsFromInputFormat; +import org.apache.hudi.hadoop.UseRecordReaderFromInputFormat; +import org.apache.hudi.hadoop.utils.HoodieInputFormatUtils; +import org.apache.hudi.hadoop.utils.HoodieRealtimeInputFormatUtils; +import org.apache.log4j.LogManager; +import org.apache.log4j.Logger; + +/** + * HoodieRealtimeInputFormat for HUDI datasets which store data in HFile base file format. + */ +@UseRecordReaderFromInputFormat +@UseFileSplitsFromInputFormat +public class HoodieHFileRealtimeInputFormat extends HoodieHFileInputFormat { + + private static final Logger LOG = LogManager.getLogger(HoodieHFileRealtimeInputFormat.class); + + @Override + public InputSplit[] getSplits(JobConf job, int numSplits) throws IOException { + Stream<FileSplit> fileSplits = Arrays.stream(super.getSplits(job, numSplits)).map(is -> (FileSplit) is); + return HoodieRealtimeInputFormatUtils.getRealtimeSplits(job, fileSplits); + } + + @Override + public FileStatus[] listStatus(JobConf job) throws IOException { + // Call the HoodieInputFormat::listStatus to obtain all latest hfiles, based on commit timeline. + return super.listStatus(job); + } + + @Override + protected HoodieDefaultTimeline filterInstantsTimeline(HoodieDefaultTimeline timeline) { + // no specific filtering for Realtime format + return timeline; + } + + @Override + public RecordReader<NullWritable, ArrayWritable> getRecordReader(final InputSplit split, final JobConf jobConf, + final Reporter reporter) throws IOException { + // Hive on Spark invokes multiple getRecordReaders from different threads in the same spark task (and hence the Review comment: we need to share code somehow. This same large comment need not be in multiple places ---------------------------------------------------------------- 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]
