MR--WordCount的MapReduce程序注释

程序基于Hadoop2.7.4开发, 可运行

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();
        @Override
        protected void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            //使用StringTokenizer而不使用split()方法是为了提升效率
            StringTokenizer itr = new StringTokenizer(value.toString());
            while (itr.hasMoreTokens()){
                //set text to contain a content of string
                word.set(itr.nextToken());
                //generate a output pair
                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 {
            //计次
            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);
    }
}