import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;

public class WordCount {

  public static void main(String[] args) {
    JobClient client = new JobClient();
    JobConf conf = new JobConf(WordCount.class);

    // specify output types
    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(IntWritable.class);

    // specify input and output dirs
    String outputname = "output";
    conf.setInputPath(new Path("input"));
    conf.setOutputPath(new Path(outputname));

    // specify a mapper
    conf.setMapperClass(WordCountMapper.class);

    // specify a reducer
    conf.setReducerClass(WordCountReducer.class);
    conf.setCombinerClass(WordCountReducer.class);

    client.setConf(conf);
    
    // Before running the job, delete the output files
    HadoopFS hdfs_rmr = new HadoopFS("-rmr "+outputname);
    hdfs_rmr.callCommand();
    
    try {
      JobClient.runJob(conf);
    } catch (Exception e) {
      e.printStackTrace();
    }
    
    HadoopFS hdfs_cat = new HadoopFS("-cat "+outputname+"/*");
    hdfs_cat.callCommand();
    for (String line : hdfs_cat.stdout) {
    	System.out.println(line);
    }
  }
}