Map Reduce Java Codes

PHOTO EMBED

Wed Jul 02 2025 06:13:01 GMT+0000 (Coordinated Universal Time)

Saved by @signup #java

//WordCountMapper.java
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class WordCountMapper 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 tokenizer = new StringTokenizer(value.toString());
            while (tokenizer.hasMoreTokens()) {
            String cleanWord = tokenizer.nextToken().toLowerCase().replaceAll("[^a-zA-Z0-9]", "");
            word.set(cleanWord);
            context.write(word, one);
        }
    }
}


//WordCountReducer.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 WordCountReducer 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);
    }
}


//WordCountDriver.java
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class WordCountDriver {
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
 	Job job = Job.getInstance(conf, "Word Count");

        job.setJarByClass(WordCountDriver.class);

        job.setMapperClass(WordCountMapper.class);
        job.setCombinerClass(WordCountReducer.class); // optional
        job.setReducerClass(WordCountReducer.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);
      }
}



Steps:
mkdir wordcount_classes
mkdir sample

cp WordCountMapper.java sample/
cp WordCountReducer.java sample/
cp WordCountDriver.java sample/


cd sample

javac -classpath $(hadoop classpath) -d ../wordcount_classes *.java

cd ..

jar -cvf wordcount.jar -C wordcount_classes/ .

echo "Hadoop is a framework for distributed Processing" > input.txt

hdfs dfs -mkdir /wordcountinput

hdfs dfs -put input.txt /wordcountinput

hadoop jar wordcount.jar WordCountDriver /wordcountinput/input.txt /wordcountoutput

hdfs dfs -ls /wordcountoutput

hdfs dfs -cat /wordcountoutput/p*
content_copyCOPY