WordCount.java

package example1.mr;

import org.apache.hadoop.conf.Configuration;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.map.TokenCounterMapper;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.mapreduce.lib.reduce.IntSumReducer;

public class WordCount {

	public static void main(String[] args) throws Exception {
		Configuration conf = new Configuration();
		Job job = new Job(conf, "wordcount-java");
		job.setJarByClass(WordCount.class);

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

		job.setMapperClass(TokenCounterMapper.class);
		job.setCombinerClass(IntSumReducer.class);
		job.setReducerClass(IntSumReducer.class);

		job.setInputFormatClass(TextInputFormat.class);
		job.setOutputFormatClass(TextOutputFormat.class);

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

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