MapReduce编程之Partitioner

Partitioner决定MapTask输出的数据交由哪个ReduceTask处

理默认实现：分发的key的hash值对ReduceTask个数取模

案例实现

/**
 * 
 * MapReduce编程之Partitioner
 *          Partitioner决定MapTask输出的数据交由哪个ReduceTask处理
 *          默认实现：分发的key的hash值对ReduceTask个数取模
 *
 * 数据：cat partitioner
 *        xiaomi 200
 *        huawei 100
 *        iphone8 50
 *        xiaomi 200
 *        huawei 100
 *        iphone8 50
 *        xiaomi 200
 *        huawei 100
 *        iphone8 50
 *        xiaomi 200
 *        huawei 100
 *        iphone8 50
 *        nokia 20
 */

public class PartitionerApp {

    /**
     * Map:读取输入的文件
     */
    public static class MyMapper extends Mapper{
        LongWritable one = new LongWritable(1);

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            //接收到的每一行数据
            String line = value.toString();

            //按照指定分隔符进行拆分
            String[] words = line.split(" ");

            //通过上下文把map的处理结果输出
            context.write(new Text(words[0]),new LongWritable(Long.parseLong(words[1])));
        }
    }
    /**
     * Reduce: 归并操作
     */
    public static class MyReducer extends Reducer{
        @Override
        protected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException {

            long sum = 0;
            for (LongWritable value:values) {
                //求key出现的次数总和
                sum += value.get();
            }

            //最终统计结果的输出
            context.write(key,new LongWritable(sum));
        }
    }

    public static class MyPartitioner extends Partitioner {
        public int getPartition(Text key, LongWritable value, int numPartitions) {
            if (key.toString().equals("xiaomi")){
                return 0;
            }

            if (key.toString().equals("huawei")){
                return 1;
            }

            if (key.toString().equals("iphone7")){
                return 2;
            }
            return 3;
        }
    }

    /**
     * 定义Driver：封装了MapReduce作业的所有信息
     * @param args
     */
    public static void main(String[] args) throws Exception {

        //创建Configuration
        Configuration configuration = new Configuration();

        //准备清理已存在的输出目录
        Path outputPath = new Path(args[1]);
        FileSystem fileSystem = FileSystem.get(configuration);
        if (fileSystem.exists(outputPath)){
            fileSystem.delete(outputPath,true);
            System.out.println("output file exists, but is has deleted");
        }

        //创建Job
        Job job = Job.getInstance(configuration, "wordcount");

        //设置job的处理类
        job.setJarByClass(PartitionerApp.class);

        //设置作业处理的输入路径
        FileInputFormat.setInputPaths(job,new Path(args[0]));

        //设置map相关参数
        job.setMapperClass(MyMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);

        //设置reduce相关参数
        job.setReducerClass(MyReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);

        //通过job设置combiner处理类，其实逻辑上和我们的reduce一模一样
//        job.setCombinerClass(WordCountApp.MyReducer.class);

        //设置job的partitioner
        job.setPartitionerClass(MyPartitioner.class);
        //设置4个reduce，每个分区一个
        job.setNumReduceTasks(4);

        //设置作业处理的输出路径
        FileOutputFormat.setOutputPath(job,new Path(args[1]));

        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }

}