com.jbw.tar.sf.TarDriver.java Source code

Introduction

Here is the source code for com.jbw.tar.sf.TarDriver.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 com.jbw.tar.sf;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

/**
 *
 * @author alvin
 */
public class TarDriver extends Configured implements Tool {

    @Override
    public int run(String[] strings) throws Exception {
        Configuration conf = getConf();
        Path in = new Path(conf.get("input"));
        Path out = new Path(conf.get("output"));

        Job job = Job.getInstance(conf);
        job.setJarByClass(TarDriver.class);
        job.setJobName("test");

        job.setMapperClass(SmallFileMapper.class);

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

        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job, in);

        job.setOutputFormatClass(TarOutputFormat.class);
        TarOutputFormat.setOutputPath(job, out);

        // job.setNumReduceTasks(0);

        /*
            job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TarOutputFormat.class);
        job.setOutputKeyClass(LongWritable.class);
        job.setOutputValueClass(Text.class);
         */
        return job.waitForCompletion(true) ? 0 : 1;
    }

    public static void main(String[] args) throws Exception {
        System.exit(ToolRunner.run(new TarDriver(), args));
    }
}