org.apache.hadoop.examples.AggregateWordCount 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.hadoop.examples;
import java.io.IOException;
import java.util.ArrayList;
import java.util.StringTokenizer;
import java.util.Map.Entry;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorBaseDescriptor;
import org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorJob;
/**
* This is an example Aggregated Hadoop Map/Reduce application. It reads the
* text input files, breaks each line into words and counts them. The output is
* a locally sorted list of words and the count of how often they occurred.
*
* To run: bin/hadoop jar hadoop-*-examples.jar aggregatewordcount
* in-dir out-dir numOfReducers textinputformat
*
*/
public class AggregateWordCount {
public static class WordCountPlugInClass extends
ValueAggregatorBaseDescriptor {
@Override
public ArrayList> generateKeyValPairs(Object key,
Object val) {
String countType = LONG_VALUE_SUM;
ArrayList> retv = new ArrayList>();
String line = val.toString();
StringTokenizer itr = new StringTokenizer(line);
while (itr.hasMoreTokens()) {
Entry e = generateEntry(countType, itr.nextToken(), ONE);
if (e != null) {
retv.add(e);
}
}
return retv;
}
}
/**
* The main driver for word count map/reduce program. Invoke this method to
* submit the map/reduce job.
*
* @throws IOException
* When there is communication problems with the job tracker.
*/
@SuppressWarnings("unchecked")
public static void main(String[] args)
throws IOException, InterruptedException, ClassNotFoundException {
Job job = ValueAggregatorJob.createValueAggregatorJob(args
, new Class[] {WordCountPlugInClass.class});
job.setJarByClass(AggregateWordCount.class);
int ret = job.waitForCompletion(true) ? 0 : 1;
System.exit(ret);
}
}