ngramown.Ngramown.java Source code

Introduction

Here is the source code for ngramown.Ngramown.java

Source

/*
 * 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.
 */
package ngramown;

import java.io.IOException;
import java.util.Scanner;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

public class Ngramown {

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

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

        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {

            /*int gramSize = 0;
            System.out.println("Enter gram size:");
            Scanner in = new Scanner(System.in);
            gramSize = in.nextInt();*/
            int gramSize = 2;

            StringTokenizer itr = new StringTokenizer(value.toString());
            int i;
            while (itr.hasMoreTokens()) {
                String ourword = itr.nextToken();
                int length = ourword.length();
                for (i = 0; i <= (length - gramSize); i++) {
                    String ourword1 = ourword.substring(i, i + (gramSize));
                    word.set(ourword1);
                    context.write(word, one);
                }
            }
        }
    }

    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();
        Path inputPath = new Path(args[0]);
        Path outputPath = new Path(args[1]);
        Job job = Job.getInstance(conf, "ngram");
        job.setJarByClass(Ngramown.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        FileInputFormat.addInputPath(job, inputPath);
        FileOutputFormat.setOutputPath(job, outputPath);
        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}