word count in hadoop: ol' school map reduce in plain java and mpreduce core libraries, in 59 lines of java

wc.mapreduce.java

package com.natalinobusa;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
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 java.io.IOException;

class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    public void map(LongWritable key, Text value, org.apache.hadoop.mapreduce.Mapper.Context context)
            throws IOException, InterruptedException {
        String line = value.toString().toLowerCase();
        for (String word : line.split("\\W+")) {
            if (word.length() > 0) {
                context.write(new Text(word), new IntWritable(1));
            }
        }
    }
}

class SumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    public void reduce(Text key, Iterable<IntWritable> values, Context context)
            throws IOException, InterruptedException {
        int wordCount = 0;
        for (IntWritable value : values) {
            wordCount += value.get();
        }
        context.write(key, new IntWritable(wordCount));
    }
}

public class WordCount {
    public static void main(String[] args) throws Exception {
        if (args.length != 2) {
            System.out.printf("Usage: WordCount <input dir> <output dir>%n");
            System.exit(-1);
        }

        Job job = new Job();
        job.setJarByClass(WordCount.class);
        job.setJobName("Word Count");
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(SumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        boolean success = job.waitForCompletion(true);
        System.exit(success ? 0 : 1);
    }
}