// Created as a template for  Advanced Database Systems 2019

import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class SomeMapReduce_wc {
    public static class MyMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    	public static IntWritable one = new IntWritable(1);

        public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String[] result = value.toString().split("\\W+");
            for (String s : result) {
                context.write(new Text(s.toLowerCase()), one);
            }
        }
    }
    public static class MyReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    	public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            context.write(key, new IntWritable(sum));
        }
    }
    public static void main(String[] args) throws Exception {
    	Configuration conf1 = new Configuration();
    	conf1.set("mapreduce.output.textoutputformat.separator",",");  // This ensures that output is comma separated
    	Job job = Job.getInstance(conf1);
    	job.setJarByClass(SomeMapReduce_wc.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        job.setMapperClass(MyMapper.class);
        job.setReducerClass(MyReducer.class);
        job.setCombinerClass(MyReducer.class); // To allow the reducer to be used as a Combiner too
//	job.setNumReduceTasks(8);     // Uncomment this to run the job with more than one Reduce tasks. Depending on the system, this may produce a speedup.
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        boolean status = job.waitForCompletion(true);
        if (status) {
            System.exit(0);
        } else {
            System.exit(1);
        }
    }
}