MapReduce 自定义计数器

MapReduce 允许用户编写程序来定义计数器，计数器的值可在 mapper 或 reduce 中增加，计数器由一个 Java 枚举（enum）类型来定义，以便对有关的计数器分组，一个作业可以定义的枚举类型数量不像，各个枚举类型所包含的字段也不限。枚举类型的名称即为组的名称，枚举类型的字段是计数器的名称。

计数器是全局的，换言之，MapReduce 框架将跨所有 map 和 reduce 聚集这些计数器，并在作业结束时产生一个最终结果。

示例：

在 wordcount 添加计数器来记录所有 长度小于5(SHORT_WORD)和长度大于10 (LONG_WORD)的单词

public class wordcount extends Configured implements Tool {
    
    enum MyCounter {
        LONG_WORD,  // 长度小于5
        SHORT_WORD  // 长度大于10
    }

    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());

                if (word.getLength() < 5) {
                    context.getCounter(MyCounter.SHORT_WORD).increment(1);
                } else if (word.getLength() > 10){
                    context.getCounter(MyCounter.LONG_WORD).increment(1);
                }

                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);
        }
    }

    @Override
    public int run(String[] args) throws Exception {
        if (args.length < 2) {
            System.err.println("Usage: wordcount <in> [<in>...] <out>");
            System.exit(2);
        }
        Job job = Job.getInstance(this.getConf(), "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);
        for (int i = 0; i < args.length - 1; ++i) {
            FileInputFormat.addInputPath(job, new Path(args[i]));
        }
        FileOutputFormat.setOutputPath(job,
                new Path(args[args.length - 1]));
        return job.waitForCompletion(true) ? 0 : 1;
    }
    
    public static void main(String[] args) throws Exception {
        int code = ToolRunner.run(new wordcount(), args);
        System.exit(code);
    }
}

当程序执行完后，会输出自定义的 计数器值