Scribd
Upload
9 views2 pages

Wrordcount

The document contains a Java implementation of a Hadoop MapReduce program for word count. It includes a Mapper class (WCMapper) that splits input text into words and emits each word with a count of one, and a Reducer class (WCReducer) that sums the counts for each word. The WCDriver class configures and runs the MapReduce job, taking input and output paths as arguments.

Uploaded by

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

Wrordcount

The document contains a Java implementation of a Hadoop MapReduce program for word count. It includes a Mapper class (WCMapper) that splits input text into words and emits each word with a count of one, and a Reducer class (WCReducer) that sums the counts for each word. The WCDriver class configures and runs the MapReduce job, taking input and output paths as arguments.

Uploaded by

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

import java.io.

IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reporter;

public class WCMapper extends MapReduceBase implements Mapper<LongWritable,


Text, Text, IntWritable> {

// Map function
public void map(LongWritable key, Text value, OutputCollector<Text,
IntWritable> output, Reporter rep) throws IOException
{

String line = value.toString();

// Splitting the line on spaces


for (String word : line.split(" "))
{
if (word.length() > 0)
{
output.collect(new Text(word), new IntWritable(1));
}
}
}
}

import java.io.IOException;
import java.util.Iterator;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;

public class WCReducer extends MapReduceBase implements Reducer<Text,


IntWritable, Text, IntWritable> {

// Reduce function
public void reduce(Text key, Iterator<IntWritable> value,
OutputCollector<Text, IntWritable> output,
Reporter rep) throws IOException
{

int count = 0;

// Counting the frequency of each words


while (value.hasNext())
{
IntWritable i = value.next();
count += i.get();
}

output.collect(key, new IntWritable(count));


}
}

// Importing libraries
import java.io.IOException;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class WCDriver extends Configured implements Tool {

public int run(String args[]) throws IOException


{
if (args.length < 2)
{
System.out.println("Please give valid inputs");
return -1;
}

JobConf conf = new JobConf(WCDriver.class);


FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
conf.setMapperClass(WCMapper.class);
conf.setReducerClass(WCReducer.class);
conf.setMapOutputKeyClass(Text.class);
conf.setMapOutputValueClass(IntWritable.class);
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);
JobClient.runJob(conf);
return 0;
}

// Main Method
public static void main(String args[]) throws Exception
{
int exitCode = ToolRunner.run(new WCDriver(), args);
System.out.println(exitCode);
}
}

You might also like