com.marklogic.contentpump.StreamingDocumentInputFormat 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.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.JobContext;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import com.marklogic.mapreduce.DocumentURIWithSourceInfo;
import com.marklogic.mapreduce.StreamLocator;
/**
* FileInputFormat for unbuffered streaming documents. Used when streaming
* option is set to true.
*
* @author jchen
*/
public class StreamingDocumentInputFormat extends
CombineDocumentInputFormat {
protected boolean isSplitable(JobContext context, StreamLocator filename) {
return false;
}
@Override
public RecordReader createRecordReader(
InputSplit split, TaskAttemptContext context)
throws IOException, InterruptedException {
return new StreamingDocumentReader();
}
}