WordCountDriver.java

package sdz.hadoop.wordcount;

import java.io.IOException;
import java.util.Iterator;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;

import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;

import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
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;
import org.apache.hadoop.mapreduce.Reducer;

import java.util.StringTokenizer;
import org.apache.hadoop.util.GenericOptionsParser;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class WordCountDriver extends Configured implements Tool {
    public int run(String[] args) throws Exception {
        if (args.length != 2) {
            System.out.println("Usage: [input] [output]");
            System.exit(-1);
        }

        Job job = Job.getInstance(getConf());
        job.setJobName("wordcount");

        job.setJarByClass(WordCountDriver.class);
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

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

        Path inputFilePath = new Path(args[0]);
        Path outputFilePath = new Path(args[1]);

        FileInputFormat.setInputDirRecursive(job, true);

        FileInputFormat.addInputPath(job, inputFilePath);
        FileOutputFormat.setOutputPath(job, outputFilePath);

        FileSystem fs = FileSystem.newInstance(getConf());

        if (fs.exists(outputFilePath)) {
            fs.delete(outputFilePath, true);
        }

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

    public static void main(String[] args) throws Exception {
        WordCountDriver wordcountDriver = new WordCountDriver();
        int res = ToolRunner.run(wordcountDriver, args);
        System.exit(res);
    }

}