com.expedia.dsp.data.squeeze.impl.text.TextCombineFileInputFormat Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of datasqueeze Show documentation
Show all versions of datasqueeze Show documentation
Hadoop utility to compact small files
/**
* Copyright (C) 2018 Expedia Group
*
* Licensed 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 com.expedia.dsp.data.squeeze.impl.text;
import com.expedia.dsp.data.squeeze.impl.CombineFileWritable;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.JobContext;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.input.CombineFileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.CombineFileRecordReader;
import org.apache.hadoop.mapreduce.lib.input.CombineFileSplit;
import java.io.IOException;
/**
* Text Combine file input format reads multiple files in same mapper.
*
* @author Yashraj R. Sontakke
*/
public class TextCombineFileInputFormat extends CombineFileInputFormat {
public TextCombineFileInputFormat() {
super();
}
@Override
public RecordReader createRecordReader(InputSplit split, TaskAttemptContext context) throws IOException {
return new CombineFileRecordReader((CombineFileSplit) split, context, TextRecordReader.class);
}
@Override
protected boolean isSplitable(JobContext context, Path file) {
return false;
}
}