Here we have 3 classes one for Mapper, one for Reducer and one main class for word count.
Map.Java
package Hadoop.Practice;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.io.*;
public class Map extends Mapper<LongWritable, Text, Text, IntWritable>
{
@Override
public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException
{
IntWritable one = new IntWritable(1);
Text word = new Text();
String line = value.toString();
StringTokenizer tokens = new StringTokenizer(line);
while(tokens.hasMoreTokens())
{
word.set(tokens.nextToken());
context.write(word, one);
}
}
}
Reduce.Java
package Hadoop.Practice;
import java.io.IOException;
import java.util.Iterator;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class Reduce extends Reducer<Text, IntWritable, Text, IntWritable>
{
@Override
public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException
{
int sum = 0;
Iterator<IntWritable> itr = values.iterator();
while(itr.hasNext())
{
sum += itr.next().get();
}
context.write(key, new IntWritable(sum));
}
}
WordCount.java
package Hadoop.Practice;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
public class WordCount
{
public static void main(String args[])
{
try
{
Job job = Job.getInstance();
job.setJobName("Word Count Job");
job.setJarByClass(WordCount.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.waitForCompletion(true);
}
catch(Exception e)
{
e.printStackTrace();
}
}
}