mapreduce combiner的应用

1. combiner是MR程序中Mapper和Reducer之外的一种组件
2. combiner组件的父类就是Reducer
3. combiner和reducer的区别在于运行的位置：

     Combiner是在每一个maptask所在的节点运行

     Reducer是接收全局所有Mapper的输出结果；

   4 combiner的意义就是对每一个maptask的输出进行局部汇总，以减小网络传输量

   具体实现步骤：

1. 自定义一个combiner继承Reducer，重写reduce方法
2. 在job中设置：  job.setCombinerClass(CustomCombiner.class)

  5 combiner能够应用的前提是不能影响最终的业务逻辑

  而且，combiner的输出kv应该跟reducer的输入kv类型要对应起来

 

import java.io.IOException;
import java.net.URI;
import java.net.URISyntaxException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

public class WordCount {

    public static void main(String[] args) throws Exception {

        if (args.length < 2) {
            System.err.println("Uage:<in> <out>");
            System.exit(2);
        }

        String inputPath = args[0];
        Path outputPath = new Path(args[1]);

        //1.configuration
        Configuration conf = new Configuration();
        URI uri = new URI("hdfs://192.168.0.200:9000");
        FileSystem fileSystem = FileSystem.get(uri, conf);

        if (fileSystem.exists(outputPath)) {
            boolean b = fileSystem.delete(outputPath, true);
            System.out.println("已存在目录删除："+b);
        }

        //2.建立job
        Job job = Job.getInstance(conf, WordCount.class.getName());
        job.setJarByClass(WordCount.class);

        //3.输入文件
        FileInputFormat.setInputPaths(job, new Path(inputPath));

        //4.格式化输入文件
        job.setInputFormatClass(TextInputFormat.class);

        //5.map
        job.setMapperClass(MapWordCountTask.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);

        //6.reduce
        job.setReducerClass(ReduceWordCountTask.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);

        /**指定本job使用combiner组件，组件所用的类为ReduceWordCountTask**/
        job.setCombinerClass(ReduceWordCountTask.class);

        //7.输出文件
        FileOutputFormat.setOutputPath(job, outputPath);

        //8.输出文件格式化
        job.setOutputFormatClass(TextOutputFormat.class);

        //9.提交给集群执行
        job.waitForCompletion(true);

    }

    public static class MapWordCountTask extends Mapper<LongWritable, Text, Text, LongWritable> {

        private Text k2 = new Text();
        private LongWritable v2 = new LongWritable();

        @Override
        protected void map(LongWritable key, Text value, Context context) throws Exception {
            String content = value.toString();
            StringTokenizer st = new StringTokenizer(content);
            while (st.hasMoreElements()) {
                k2.set(st.nextToken());
                v2.set(1L);
                context.write(k2, v2);
            }
        }
    }

    public static class ReduceWordCountTask extends Reducer<Text, LongWritable, Text, LongWritable> {

        private LongWritable v3 = new LongWritable();

        @Override
        protected void reduce(Text k2, Iterable<LongWritable> v2s,Context context) throws Exception {
            long sum = 0;
            for (LongWritable longWritable : v2s) {
                sum += longWritable.get();
                v3.set(sum);
            }
            context.write(k2, v3);
        }
    }
}