Untitled

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.output.FileOutputFormat;
 
public class WCDriver {
 
public static void main(String[] args) throws Exception {
Job job = new Job();
job.setJarByClass(WCDriver.class);
job.setJobName("Word Count");
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.setMapperClass(WCMapper.class);
job.setReducerClass(WCReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
boolean success = job.waitForCompletion(true);
System.exit(success ? 0 : 1);
}
}
 
 
 
 
WCMapper.java
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.mapreduce.Mapper;
 
public class WCMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
 
@Override
 
public void map(LongWritable key, Text value, Context context) throws IOException,
InterruptedException{
 
String line = value.toString();
for(String word: line.split("\\W+")) {
if(word.length() > 0) {
context.write(new Text(word), new IntWritable(1));
}
}
}
}
 
 
 
 
 
WCReducer.java
import java.io.IOException;
 
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
 
public class WCReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
 
@Override
public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException,
InterruptedException{
 
int wordCount = 0;
for(IntWritable value :values){
wordCount += value.get();
}
context.write(key, new IntWritable(wordCount));
}
}