hyracks-examples/hadoop-compat-example/hadoopcompathelper/src/main/java/edu/uci/ics/hyracks/examples/wordcount/WordCount.java

/*
 * Copyright 2009-2010 by The Regents of the University of California
 * 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 from
 * 
 *     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 edu.uci.ics.hyracks.examples.wordcount;

import java.io.IOException;
import java.io.Serializable;
import java.util.Iterator;
import java.util.StringTokenizer;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;

public class WordCount implements Serializable {
    public static class Map extends MapReduceBase implements Mapper<LongWritable, Text, Text, IntWritable>,
            Serializable {

        private final static IntWritable ONE = new IntWritable(1);
        private Text word = new Text();

        public void map(LongWritable key, Text value, OutputCollector<Text, IntWritable> output, Reporter reporter)
                throws IOException {
            String line = value.toString();
            StringTokenizer tokenizer = new StringTokenizer(line);
            while (tokenizer.hasMoreTokens()) {
                String token = tokenizer.nextToken();
                word.set(token);
                output.collect(word, ONE);
            }
        }
    }

    public static class Reduce extends MapReduceBase implements Reducer<Text, IntWritable, Text, IntWritable>,
            Serializable {

        public void reduce(Text key, Iterator<IntWritable> values, OutputCollector<Text, IntWritable> output,
                Reporter reporter) throws IOException {
            int sum = 0;
            while (values.hasNext()) {
                sum += values.next().get();
            }
            output.collect(key, new IntWritable(sum));
        }
    }
}