写一个统计单词的mapreduce程序

好的，以下是一个简单的MapReduce程序，用于统计输入文件中各个单词出现的次数：

Mapper 函数：

public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    
    private Text word = new Text();
    private final static IntWritable ONE = new IntWritable(1);
    
    public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        StringTokenizer tokenizer = new StringTokenizer(line);
        while (tokenizer.hasMoreTokens()) {
            word.set(tokenizer.nextToken());
            context.write(word, ONE);
        }
    }
}

Reducer 函数：

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);
    }
}

MapReduce 驱动程序：

public class WordCount {

    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(WordCountMapper.class);
        job.setCombinerClass(WordCountReducer.class);
        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);
    }
}

以上程序的作用是：读取输入文件，将每一行拆分为单词，然后输出每个单词以及它们出现的次数。其中，Mapper 函数读取每个单词，然后以 (单词,1) 的形式输出；Reducer 函数接收 Mapper 输出的键值对，对每个键进行求和，并输出最终结果；MapReduce 驱动程序则配置 Mapper、Reducer 函数和输入输出路径，启动 MapReduce 作业。