com.ema.hadoop.wordcount.WordCount.java Source code

Introduction

Here is the source code for com.ema.hadoop.wordcount.WordCount.java

Source

package com.ema.hadoop.wordcount;

/*
 * 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.
 */

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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

/**
 *
 * @author sharispe
 */
public class WordCount {

    public static void main(String[] args) throws Exception {

        if (args.length != 2) {
            System.err.println("Usage: WordCount <input path> <output path>");
            System.exit(-1);
        }

        Job job = Job.getInstance();
        job.setJarByClass(WordCount.class);
        job.setJobName("Word count job");

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

        job.setMapperClass(WCMapper.class);
        job.setReducerClass(WCReducer.class);

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

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