2022-03-08

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


public class WCMapper extends Mapper<LongWritable,Text,Text,LongWritable>{
    final LongWritable one = new LongWritable(1);
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        String[] words = line.split("\t");
        for (String w:words) {
            context.write(new Text(w),one);
        }   
    }
}

public class WCReducer extends Reducer<Text,LongWritable,Text,LongWritable>{
    @Override
    protected void reduce(Text key, Iterable<LongWritable> values,Context context) throws IOException, InterruptedException {
        int valueout = 0;
        for(LongWritable value:values) {
            valueout += value.get();
        }
        context.write(key, new LongWritable(valueout));
    }
}

public class Driver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        job.setJarByClass(Driver.class);
        job.setMapperClass(WCMapper.class);
        job.setReducerClass(WCReducer.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));
        job.waitForCompletion(true);
    }