org.apache.hadoop.examples.AggregateWordHistogram Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of hadoop-mapreduce-examples Show documentation
Apache Hadoop MapReduce Examples
There is a newer version: 3.4.1
Show newest version
/**
 * 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.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. Computes the
 * histogram of the words in the input texts.
 * 
 * To run: bin/hadoop jar hadoop-*-examples.jar aggregatewordhist in-dir
 * out-dir numOfReducers textinputformat
 * 
 */
public class AggregateWordHistogram {

  public static class AggregateWordHistogramPlugin 
    extends ValueAggregatorBaseDescriptor {
    
    /**
     * Parse the given value, generate an aggregation-id/value pair per word.
     * The ID is of type VALUE_HISTOGRAM, with WORD_HISTOGRAM as the real id.
     * The value is WORD\t1.
     *
     * @return a list of the generated pairs.
     */
    @Override
    public ArrayList> generateKeyValPairs(Object key,
                                          Object val) {
      String words[] = val.toString().split(" |\t");
      ArrayList> retv = new ArrayList>();
      for (int i = 0; i < words.length; i++) {
        Text valCount = new Text(words[i] + "\t" + "1");
        Entry en = generateEntry(VALUE_HISTOGRAM, "WORD_HISTOGRAM",
                                 valCount);
        retv.add(en);
      }
      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[] {AggregateWordHistogramPlugin.class});
    job.setJarByClass(AggregateWordCount.class);
    int ret = job.waitForCompletion(true) ? 0 : 1;
    System.exit(ret);
  }
}