TestMR.java : basic map reduce program that takes input path as an argument

amazon-emr-testMR.java

/**
 * http://sujee.net/tech/articles/amazon-emr-beyond-basics/
 * takes one argument for input path
 */
public class TestMR extends Configured implements Tool
{

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

    @Override
    public int run(String[] args) throws Exception
    {
        if (args.length < 1)
        {
            System.err.printf("Usage: %s [generic options] <input_paths>\n", getClass().getSimpleName());
            ToolRunner.printGenericCommandUsage(System.err);
            return -1;
        }

        Configuration conf = getConf();

        Job job = new Job(conf, "TestMR");
        job.setJarByClass(TestMR.class);
        job.setMapperClass(TestMapper.class);
        job.setReducerClass(TestReducer.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
        job.setOutputFormatClass(Text.class);

        FileInputFormat.addInputPath(job, args[0]);
        FileInputFormat.addOutputPath(job, args[1]);

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

}