mapReduceBasics.WordCount.java Source code

Introduction

Here is the source code for mapReduceBasics.WordCount.java

Source

package mapReduceBasics;

/*
 * To change this license header, choose License Headers in Project Properties.
 * To change this template file, choose Tools | Templates
 * and open the template in the editor.
 */

/**
 *
 * @author hduser
 */
import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class WordCount {

    public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {

        private final static IntWritable constantOne = new IntWritable(1);
        private Text inputWord = new Text();

        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            StringTokenizer inputRecord = new StringTokenizer(value.toString());
            System.err.println("New Line # " + value.toString());
            while (inputRecord.hasMoreTokens()) {
                inputWord.set(inputRecord.nextToken());
                System.err.println("New Word # " + inputWord);
                context.write(inputWord, constantOne);
            }
        }
    }

    public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();

        public void reduce(Text key, Iterable<IntWritable> values, Context context)
                throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            result.set(sum);
            context.write(key, result);
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        GenericOptionsParser GOP = new GenericOptionsParser(conf, args);
        Configuration newConf = GOP.getConfiguration();
        String[] otherArgs = GOP.getRemainingArgs();
        System.err.println("Best of Luck");
        Job job = new Job(newConf, "word count");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        Path inputPath = new Path(otherArgs[0]);
        Path outputPath = new Path(otherArgs[1]);

        FileInputFormat.addInputPath(job, inputPath);
        FileOutputFormat.setOutputPath(job, outputPath);

        FileSystem fs = FileSystem.get(conf);
        fs.delete(outputPath, true);

        //    job.setNumReduceTasks(3);
        System.err.println("Input Format - " + job.getInputFormatClass());
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}