Orphaned Web Pages Finder using Hadoop

OrphanPages.java

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.NullWritable;
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.Tool;
import org.apache.hadoop.util.ToolRunner;

import java.io.IOException;
import java.util.StringTokenizer;
import java.util.Set;
import java.util.TreeSet;

public class OrphanPages extends Configured implements Tool {

    public static void main(String[] args) throws Exception {
        int res = ToolRunner.run(new Configuration(), new OrphanPages(), args);
        System.exit(res);
    }
// <<< Don't Change

    @Override
    public int run(String[] args) throws Exception {
        Configuration conf = getConf();
        Job job = Job.getInstance(conf, "orphanedpages");

        job.setOutputKeyClass(IntWritable.class);
        job.setOutputValueClass(NullWritable.class);

        job.setMapOutputKeyClass(IntWritable.class);
        job.setMapOutputValueClass(IntWritable.class);

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

        job.setMapperClass(LinkCountMap.class);
        job.setReducerClass(OrphanPageReduce.class);

        job.setJarByClass(OrphanPages.class);
        return job.waitForCompletion(true) ? 0 : 1;
    }

    public static class LinkCountMap extends Mapper<Object, Text, IntWritable, IntWritable> {
        @Override
        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            String line = value.toString();
            StringTokenizer tokenizer = new StringTokenizer(line, " :");
            IntWritable page = new IntWritable(Integer.parseInt(tokenizer.nextToken().trim()));
            context.write(page, new IntWritable(0));
            
            while (tokenizer.hasMoreTokens()) {
                String linkedPage = tokenizer.nextToken().trim();
                context.write(new IntWritable(Integer.parseInt(linkedPage)), new IntWritable(1));
            }
        }
    }

    public static class OrphanPageReduce extends Reducer<IntWritable, IntWritable, IntWritable, NullWritable> {
        Set<Integer> linkToCount = new TreeSet<Integer>();

        @Override
        public void reduce(IntWritable key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int count = 0;
            for (IntWritable value : values) {
                count += value.get();
            }

            if (count == 0) {
                context.write(key, NullWritable.get());
            }
        }
    }
}