import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import java.io.IOException;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.*;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.io.*;
public class WordCount
{
public static void main(String []args) throws Exception
{
if(args.length!=2)
{
System.err.println("Invalid command");
System.exit(0);
}
Configuration conf = new Configuration();
Job job = new Job(conf, "WordCount");
job.setJarByClass(WordCount.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.setMapperClass(WordMapper.class);
job.setReducerClass(WordReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.waitForCompletion(true);
}
class WordMapper extends Mapper<LongWritable, Text, Text, IntWritable>
{
public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException
{
String line = value.toString();
String[] word = line.split(" ");
for(String i : word)
{
if(i.length()>0)
{
context.write(new Text(i), new IntWritable(1));
}
}
}
}
class WordReducer extends Reducer<Text, IntWritable, Text, IntWritable>
{
public void reduce(Text key, Iterable<IntWritable> value, Context context) throws IOException, InterruptedException
{
int count =0;
for(IntWritable i: value)
{
count = count+ i.get();
}
context.write(key, new IntWritable(count));
}
}
}