MyJobCount.java

package stubs;

import java.io.IOException;

import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
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.KeyValueTextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class MyJobCount extends Configured implements Tool {

	public static class MapClass extends Mapper<Text, Text, Text, Text> {
		@Override
		public void map(Text key, Text value, Context context)
				throws IOException, InterruptedException {
			context.write(value, key);
		}
	}

	public static class Reduce extends Reducer<Text, Text, Text, IntWritable> {

		@Override
		public void reduce(Text key, Iterable<Text> values, Context context)
				throws IOException, InterruptedException {
			int count = 0;
			for (Text value : values) {
				count++;
			}
			context.write(key, new IntWritable(count));
		}
	}

	public int run(String[] args) throws Exception {
		Configuration conf = new Configuration();
		conf.set("key.value.separator.in.input.line", ",");

		Job job = new Job(conf);
		job.setJarByClass(MyJobCount.class);

		Path in = new Path(args[0]);
		Path out = new Path(args[1]);

		FileInputFormat.setInputPaths(job, in);
		FileOutputFormat.setOutputPath(job, out);

		job.setJobName("MyCountJob");
		job.setMapperClass(MapClass.class);
		job.setReducerClass(Reduce.class);

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

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

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