Thanks to visit codestin.com
Credit goes to www.scribd.com

Scribd
Upload
63 views2 pages

Word Count Program

This document contains a Java implementation of a Hadoop MapReduce program for counting words in text files. It includes a Mapper class that tokenizes input text and emits each word with a count of one, and a Reducer class that sums the counts for each word. The main method sets up the job configuration and specifies input and output paths.

Uploaded by

sivamuppalaneni29
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
63 views2 pages

Word Count Program

This document contains a Java implementation of a Hadoop MapReduce program for counting words in text files. It includes a Mapper class that tokenizes input text and emits each word with a count of one, and a Reducer class that sums the counts for each word. The main method sets up the job configuration and specifies input and output paths.

Uploaded by

sivamuppalaneni29
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

import java.io.

IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
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.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 WordCount {

public static class TokenizerMapper


extends Mapper<Object, Text, Text, IntWritable>{

private final static IntWritable one = new IntWritable(1);


private Text word = new Text();

public void map(Object key, Text value, Context context


) throws IOException, InterruptedException {
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(word, one);
}
}
}

public static class IntSumReducer


extends Reducer<Text,IntWritable,Text,IntWritable> {
private IntWritable result = new IntWritable();

public void reduce(Text key, Iterable<IntWritable> values,


Context context
) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
result.set(sum);
context.write(key, result);
}
}

public static void main(String[] args) throws Exception {


Configuration conf = new Configuration();
Job job = Job.getInstance(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}

You might also like