Word Count extends Configured - Java Big Data

Java examples for Big Data:Hadoop

  1. HOME
  2. Java
  3. Big Data
  4. Hadoop

Description

Word Count extends Configured

Demo Code

//package org.myorg;
import java.io.IOException;
import java.util.*;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred.*;
import org.apache.hadoop.util.*;

public class WordCount extends Configured implements Tool {

    public static class Map extends MapReduceBase implements
            Mapper<LongWritable, Text, Text, IntWritable> {
        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(LongWritable key, Text value,
                OutputCollector<Text, IntWritable> output, Reporter reporter)
                throws IOException {
            String line = value.toString();
            StringTokenizer tokenizer = new StringTokenizer(line);
            while (tokenizer.hasMoreTokens()) {
                word.set(tokenizer.nextToken());
                output.collect(word, one);
            }/*w  w w  .j a  v a 2 s  .  com*/
        }
    }

    public static class Reduce extends MapReduceBase implements
            Reducer<Text, IntWritable, Text, IntWritable> {
        public void reduce(Text key, Iterator<IntWritable> values,
                OutputCollector<Text, IntWritable> output, Reporter reporter)
                throws IOException {
            int sum = 0;
            while (values.hasNext()) {
                sum += values.next().get();
            }
            output.collect(key, new IntWritable(sum));
        }
    }

    public int run(String[] args) throws Exception {
        JobConf conf = new JobConf(getConf(), WordCount.class);
        conf.setJobName("wordcount");
        conf.setOutputKeyClass(Text.class);
        conf.setOutputValueClass(IntWritable.class);

        conf.setMapperClass(Map.class);
        //conf.setCombinerClass(Reduce.class);
        conf.setReducerClass(Reduce.class);

        conf.setInputFormat(TextInputFormat.class);
        conf.setOutputFormat(TextOutputFormat.class);
        FileInputFormat.setInputPaths(conf, new Path(args[0]));
        FileOutputFormat.setOutputPath(conf, new Path(args[1]));
        JobClient.runJob(conf);
        return 0;
    }

    public static void main(String[] args) throws Exception {
        int res = ToolRunner
                .run(new Configuration(), new WordCount(), args);
        System.exit(res);
        JobConf conf = new JobConf(WordCount.class);
          conf.setJobName("wordcount");

          conf.setOutputKeyClass(Text.class);
          conf.setOutputValueClass(IntWritable.class);

          conf.setMapperClass(Map.class);
          //conf.setCombinerClass(Reduce.class);
          conf.setReducerClass(Reduce.class);

          conf.setInputFormat(TextInputFormat.class);
          conf.setOutputFormat(TextOutputFormat.class);

          FileInputFormat.setInputPaths(conf, new Path(args[0]));
          FileOutputFormat.setOutputPath(conf, new Path(args[1]));

          JobClient.runJob(conf);
    }
}

Related Tutorials