com.bigdog.hadoop.mapreduce.combine.WordCountCombineApp.java Source code

Introduction

Here is the source code for com.bigdog.hadoop.mapreduce.combine.WordCountCombineApp.java

Source

/*
 * To change this license header, choose License Headers in Project Properties.
 * To change this template file, choose Tools | Templates
 * and open the template in the editor.
 */

package com.bigdog.hadoop.mapreduce.combine;

import com.bigdog.hadoop.Constants;
import java.net.URI;
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.output.FileOutputFormat;

/**
 *
 * @author jw362j
 */
public class WordCountCombineApp {
    static final String INPUT_PATH = Constants.input;
    static final String OUT_PATH = Constants.output;

    static {
        Configuration.addDefaultResource("hdfs-site.xml");
        Configuration.addDefaultResource("core-site.xml");
        Configuration.addDefaultResource("mapred-site.xml");
    }

    public void combine() throws Exception {
        Configuration conf = new Configuration();
        final FileSystem fileSystem = FileSystem.get(new URI(INPUT_PATH), conf);
        final Path outPath = new Path(OUT_PATH);
        if (fileSystem.exists(outPath)) {
            fileSystem.delete(outPath, true);
        }

        final Job job = new Job(conf, WordCountCombineApp.class.getSimpleName());
        //1.1??
        FileInputFormat.setInputPaths(job, INPUT_PATH);
        //????
        //job.setInputFormatClass(TextInputFormat.class);

        //1.2 map
        job.setMapperClass(MyMapper.class);
        //map<k,v><k3,v3><k2,v2>??
        //job.setMapOutputKeyClass(Text.class);
        //job.setMapOutputValueClass(LongWritable.class);

        //1.3 
        //job.setPartitionerClass(HashPartitioner.class);
        //reduce?
        //job.setNumReduceTasks(1);

        //1.4 TODO ??

        //1.5 
        job.setCombinerClass(MyCombiner.class);

        //2.2 reduce
        job.setReducerClass(MyReducer.class);
        //reduce
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);

        //2.3 
        FileOutputFormat.setOutputPath(job, outPath);
        //?
        //job.setOutputFormatClass(TextOutputFormat.class);

        //job??JobTracker?
        job.waitForCompletion(true);
    }

    /**
    * KEYIN   ?k1      ???
    * VALUEIN   ?v1      
    * KEYOUT   ?k2      ??
    * VALUEOUT   ?v2      ??1
    */
    static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable> {
        protected void map(LongWritable k1, Text v1, Context context)
                throws java.io.IOException, InterruptedException {
            final String[] splited = v1.toString().split(" ");
            for (String word : splited) {
                context.write(new Text(word), new LongWritable(1));
                System.out.println("Mapper<" + word + "," + 1 + ">");
            }
        };
    }

    /**
     * KEYIN   ?k2      ??
     * VALUEIN   ?v2      ??
     * KEYOUT   ?k3      ????
     * VALUEOUT   ?v3      ????
     *
     */
    static class MyReducer extends Reducer<Text, LongWritable, Text, LongWritable> {
        protected void reduce(Text k2, java.lang.Iterable<LongWritable> v2s, Context ctx)
                throws java.io.IOException, InterruptedException {
            //redcuek2
            System.out.println("MyReducer<" + k2.toString() + ",...>");
            long times = 0L;
            for (LongWritable count : v2s) {
                times += count.get();
                //k2,v2?
                System.out.println("MyReducer<" + k2.toString() + "," + count.get() + ">");
            }
            ctx.write(k2, new LongWritable(times));
        };
    }

    static class MyCombiner extends Reducer<Text, LongWritable, Text, LongWritable> {
        protected void reduce(Text k2, java.lang.Iterable<LongWritable> v2s, Context ctx)
                throws java.io.IOException, InterruptedException {
            //redcuek2
            System.out.println("Combiner<" + k2.toString() + ",...>");
            long times = 0L;
            for (LongWritable count : v2s) {
                times += count.get();
                //k2,v2?
                System.out.println("Combiner<" + k2.toString() + "," + count.get() + ">");
            }

            ctx.write(k2, new LongWritable(times));
            //k2,v2?
            System.out.println("Combiner<" + k2.toString() + "," + times + ">");
        };
    }

}