编写并运行MapReduce程序WordCount

WordCount是MapReduce中最基本的程序之一，它用于计算文本中每个单词的出现次数。下面是WordCount的Java代码：

import java.io.IOException;
import java.util.StringTokenizer;
 
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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
 
public class WordCount {
 
    public static class TokenizerMapper 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 itr = new StringTokenizer(value.toString());
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                context.write(word, one);
            }
        }
    }
 
    public static class IntSumReducer 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);
        }
    }
 
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.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);
    }
}

这个程序的输入是一个文本文件，输出是每个单词出现的次数。在运行之前，你需要安装Hadoop并将输入文件放入HDFS。运行MapReduce程序的命令如下：

hadoop jar WordCount.jar WordCount /input /output

其中，WordCount.jar是你打包好的Java程序，input是输入文件的路径，output是输出目录的路径。执行这个命令后，MapReduce作业就会在Hadoop集群上运行。