package demos;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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 SimpleWordFreqHistogram {
	public static void run(String input, String output){
		JobConf conf = new JobConf(SimpleWordFreqHistogram.class);
		conf.setJobName("simple word freq histogram");
		
		conf.setOutputKeyClass(IntWritable.class);
		conf.setOutputValueClass(IntWritable.class);

		conf.setMapperClass(WordFreqMapper.class);
		conf.setCombinerClass(SumReducer.class);
		conf.setReducerClass(SumReducer.class);
		
		// specify input and output dirs
	    FileInputFormat.addInputPath(conf, new Path(input));
	    FileOutputFormat.setOutputPath(conf, new Path(output));
		
	    JobClient client = new JobClient();
	    
	    client.setConf(conf);
	    try {
	      JobClient.runJob(conf);
	    } catch (Exception e) {
	      e.printStackTrace();
	    }
	}
	
	public static void main(String[] args) {
		if( args.length != 2 ){
			System.err.println("SimpleWordFreqHistogram <input_dir> <output_dir>");
		}else{
			run(args[0], args[1]);
		}
	}
}