cp_a.CP_A.java Source code

Introduction

Here is the source code for cp_a.CP_A.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 cp_a;

/**
 *
 * @author rajor
 */
import java.io.IOException;
import java.util.HashMap;
import java.util.StringTokenizer;
import java.util.regex.Pattern;

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.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class CP_A {

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

        private final static IntWritable one = new IntWritable(1);
        private static final Pattern UNDESIRABLES = Pattern.compile("[(){},.;!+\"?<>%]");
        public String[] keywords = { "education", "economy", "sports", "government" };
        HashMap<String, Integer> hashmap = new HashMap<String, Integer>();

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

            StringTokenizer itr = new StringTokenizer(
                    UNDESIRABLES.matcher(value.toString()).replaceAll(" ").trim());

            for (String keyword : keywords) {
                hashmap.put(keyword, 0);
            }
            String fileName = ((FileSplit) context.getInputSplit()).getPath().getName();
            while (itr.hasMoreTokens()) {

                //remove unwanted characters 
                //to count words that end or start with special character
                String word = UNDESIRABLES.matcher(itr.nextToken().toString()).replaceAll("");
                word = word.toLowerCase();
                if (hashmap.containsKey(word)) {
                    context.write(new Text(fileName + "-" + word), new IntWritable(1));
                }

            }
        }
    }

    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);
            System.out.println(key + ":" + sum);
            context.write(key, result);
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(CP_A.class);

        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);

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

        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}