Java tutorial
/* * To change this license header, choose License Headers in Project Properties. * To change this template file, choose Tools | Templates * and open the template in the editor. */ package edu.ncku.ikdd; import java.io.IOException; import java.util.Iterator; import java.util.StringTokenizer; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.*; import org.apache.hadoop.mapred.*; /** * * @author ril */ public class WordCount { public static class Map extends MapReduceBase implements Mapper<LongWritable, Text, Text, IntWritable> { private Text word = new Text(); private static final IntWritable one = new IntWritable(1); 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); } } } 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 static void main(String[] argv) throws Exception { 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(argv[0])); FileOutputFormat.setOutputPath(conf, new Path(argv[1])); JobClient.runJob(conf); } }