package org.myorg;

import java.io.IOException;
import java.util.*;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred.*;
import org.apache.hadoop.util.*;

public class FilterData {

	public static class Map extends MapReduceBase implements Mapper<LongWritable, Text, Text, Text> {
		private Text ipadr = new Text();
		private Text monthFile = new Text();

		public void map(LongWritable key, Text value, OutputCollector<Text, Text> output, Reporter reporter) throws IOException {
			String line = value.toString();
			String[] temp = line.split("\"", 0);
			if (temp.length == 3){
				String[] temp2 = temp[1].split(" ", 0);
				String[] temp3 = temp[0].split(" ", 0);
				String[] temp4 = temp3[3].split("/", 0);
				monthFile.set(temp4[1] + temp2[1]);
				ipadr.set(temp3[0]);
				output.collect(monthFile, ipadr);
			}
		}
	}

	public static class Reduce extends MapReduceBase implements Reducer<Text, Text, Text, Text> {
		Text result = new Text();

		public void reduce(Text key, Iterator<Text> values, OutputCollector<Text, Text> output, Reporter reporter) throws IOException {
			String temp = "[";
			TreeSet <String> ts = new TreeSet<String>();
			while (values.hasNext()) {
				s.add(values.next().toString());
				if (temp.equals("["))
					temp = temp + values.next().toString();
				else
					temp = temp + " " + values.next().toString();
			}
			for (String s : ts){
				if (temp.equals("["))
					temp = temp + s;
				else
					temp = temp + " " + s;
			}
			temp = temp + "]";
			result.set(temp);
			output.collect(key, result);
		}
	}

	public static void main(String[] args) throws Exception {
		JobConf conf = new JobConf(FilterData.class);
		conf.setJobName("filterdata");

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

		conf.setMapperClass(Map.class);
		conf.setCombinerClass(Reduce.class);
		conf.setReducerClass(Reduce.class);

		conf.setInputFormat(TextInputFormat.class);
		conf.setOutputFormat(TextOutputFormat.class);

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

		JobClient.runJob(conf);
	}
}