package demos;

import java.io.IOException;
import java.util.HashSet;
import java.util.Iterator;
import java.util.StringTokenizer;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.FileSplit;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;

public class LineIndexer{ 

	public static class LineIndexMapper extends MapReduceBase implements Mapper<LongWritable, Text, Text, Text> {
		private final static Text word = new Text();
		private final static Text location = new Text();

		public void map(LongWritable key, Text val, OutputCollector<Text, Text> output, Reporter reporter)
						throws IOException {
			// get the filename where this line came from
			FileSplit fileSplit = (FileSplit)reporter.getInputSplit();
			String fileName = fileSplit.getPath().getName();
			location.set(fileName);

			String line = val.toString();
			StringTokenizer itr = new StringTokenizer(line.toLowerCase());
			
			while (itr.hasMoreTokens()) {
				word.set(itr.nextToken());
				output.collect(word, location);
			}
		}
	}

	public static class LineIndexReducer extends MapReduceBase implements Reducer<Text, Text, Text, Text> {
		private final static HashSet<String> files = new HashSet<String>();
		
		public void reduce(Text key, Iterator<Text> values,
				OutputCollector<Text, Text> output, Reporter reporter)
						throws IOException {
			files.clear();
			
			boolean first = true;
			StringBuilder toReturn = new StringBuilder();
			
			while (values.hasNext()){
				String filename = values.next().toString();
				
				if( !files.contains(filename) ){	
					files.add(filename);
					
					if (!first) {
						toReturn.append(", ");
					}
					
					first = false;
					toReturn.append(filename);
				}
			}

			output.collect(key, new Text(toReturn.toString()));
		}
	}

	public static void run(String input, String output){
		JobClient client = new JobClient();
		JobConf conf = new JobConf(LineIndexer.class);

		conf.setJobName("LineIndexer");

		conf.setOutputKeyClass(Text.class);
		conf.setOutputValueClass(Text.class);

		FileInputFormat.addInputPath(conf, new Path(input));
		FileOutputFormat.setOutputPath(conf, new Path(output));

		conf.setMapperClass(LineIndexMapper.class);
		conf.setReducerClass(LineIndexReducer.class);

		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("LineIndexer <input_dir> <output_dir>");
		}else{
			run(args[0], args[1]);
		}
	}
}