WORD COUNT

单词计数是最简单也是最能体现MapReduce思想的程序之一，可以称为MapReduce版"Hello World"，该程序的完整代码可以在Hadoop安装包的"src/examples"目录下找到。单词计数主要完成功能是：统计一系列文本文件中每个单词出现的次数

程序的功能：假设现在有n个文本，WordCount程序就是利用MR计算模型来统计这n个文本中每个单词出现的总次数。

程序的源代码

import java.io.IOException;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class WordCount extends Configured implements Tool {

    public static class MapClass 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 itr = new StringTokenizer(line);
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                output.collect(word, one);
            }
        }
    }

    /**
     * A reducer class that just emits the sum of the input values.
     */
    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));
        }
    }

    static int printUsage() {
        System.out.println("wordcount [-m <maps>] [-r <reduces>] <input> <output>");
        ToolRunner.printGenericCommandUsage(System.out);
        return -1;
    }

    /**
     * The main driver for word count map/reduce program. Invoke this method to
     * submit the map/reduce job.
     *
     * @throws IOException
     *             When there is communication problems with the job tracker.
     */
    public int run(String[] args) throws Exception {
        JobConf conf = new JobConf(getConf(), WordCount.class);
        conf.setJobName("wordcount");

        // the keys are words (strings)
        conf.setOutputKeyClass(Text.class);
        // the values are counts (ints)
        conf.setOutputValueClass(IntWritable.class);

        conf.setMapperClass(MapClass.class);
        conf.setCombinerClass(Reduce.class);
        conf.setReducerClass(Reduce.class);

        List<String> other_args = new ArrayList<String>();
        for (int i = 0; i < args.length; ++i) {
            try {
                if ("-m".equals(args[i])) {
                    conf.setNumMapTasks(Integer.parseInt(args[++i]));
                } else if ("-r".equals(args[i])) {
                    conf.setNumReduceTasks(Integer.parseInt(args[++i]));
                } else {
                    other_args.add(args[i]);
                }
            } catch (NumberFormatException except) {
                System.out.println("ERROR: Integer expected instead of "
                        + args[i]);
                return printUsage();
            } catch (ArrayIndexOutOfBoundsException except) {
                System.out.println("ERROR: Required parameter missing from "
                        + args[i - 1]);
                return printUsage();
            }
        }

        // Make sure there are exactly 2 parameters left.
        if (other_args.size() != 2) {
            System.out.println("ERROR: Wrong number of parameters: "
                    + other_args.size() + " instead of 2.");
            return printUsage();
        }
        FileInputFormat.setInputPaths(conf, other_args.get(0));
        FileOutputFormat.setOutputPath(conf, new Path(other_args.get(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);
    }

}

摘自http://samwalt.iteye.com/blog/1026170