com.marklogic.contentpump.CompressedDelimitedJSONInputFormat Maven / Gradle / Ivy
/*
* Copyright (c) 2019 MarkLogic Corporation
*
* 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.marklogic.contentpump;
import java.io.IOException;
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 com.marklogic.mapreduce.CompressionCodec;
import com.marklogic.mapreduce.DocumentURIWithSourceInfo;
/**
* InputFormat for compressed delimited json.
* @author mattsun
*
*/
public class CompressedDelimitedJSONInputFormat extends
FileAndDirectoryInputFormat {
@Override
public RecordReader createRecordReader(InputSplit split,
TaskAttemptContext context) throws IOException,
InterruptedException {
String codec = context.getConfiguration().get(
ConfigConstants.CONF_INPUT_COMPRESSION_CODEC,
CompressionCodec.ZIP.toString());
if (codec.equalsIgnoreCase(CompressionCodec.ZIP.toString())) {
return new ZipDelimitedJSONReader();
} else if (codec.equalsIgnoreCase(CompressionCodec.GZIP.toString())) {
return new GzipDelimitedJSONReader();
} else {
throw new UnsupportedOperationException("Unsupported codec: "
+ codec);
}
}
@Override
protected boolean isSplitable(JobContext context, Path filename) {
return false;
}
}