org.apache.hudi.hadoop.HoodieHFileInputFormat Maven / Gradle / Ivy
/*
* 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;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.ArrayWritable;
import org.apache.hadoop.io.NullWritable;
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.hadoop.utils.HoodieInputFormatUtils;
import java.io.IOException;
/**
* HoodieInputFormat for HUDI datasets which store data in HFile base file format.
*/
@UseFileSplitsFromInputFormat
public class HoodieHFileInputFormat extends HoodieCopyOnWriteTableInputFormat {
protected HoodieDefaultTimeline filterInstantsTimeline(HoodieDefaultTimeline timeline) {
return HoodieInputFormatUtils.filterInstantsTimeline(timeline);
}
@Override
public RecordReader getRecordReader(final InputSplit split, final JobConf job,
final Reporter reporter) throws IOException {
return new HoodieHFileRecordReader(conf, split, job);
}
@Override
protected boolean isSplitable(FileSystem fs, Path filename) {
// This file isn't splittable.
return false;
}
}