Hadoop学习之路(6)MapReduce自定义分区实现

MapReduce自带的分区器是HashPartitioner

原理：先对map输出的key求hash值，再模上reduce task个数，根据结果，决定此输出kv对，被匹配的reduce任务取走。



自定义分分区需要继承Partitioner，复写getpariton()方法

自定义分区类：



注意：map的输出是<K,V>键值对

其中int partitionIndex = dict.get(text.toString())，partitionIndex是获取K的值

附：被计算的的文本

Dear Dear Bear Bear River Car Dear Dear  Bear Rive
Dear Dear Bear Bear River Car Dear Dear  Bear Rive

需要在main函数中设置，指定自定义分区类



自定义分区类：

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Partitioner;
import java.util.HashMap;
public class CustomPartitioner extends Partitioner<Text, IntWritable> {
    public static HashMap<String, Integer> dict = new HashMap<String, Integer>();
    //Text代表着map阶段输出的key,IntWritable代表着输出的值
    static{
        dict.put("Dear", 0);
        dict.put("Bear", 1);
        dict.put("River", 2);
        dict.put("Car", 3);
    }
    public int getPartition(Text text, IntWritable intWritable, int i) {
        //
        int partitionIndex = dict.get(text.toString());
        return partitionIndex;
    }
}

注意：map的输出结果是键值对<K,V>,int partitionIndex = dict.get(text.toString());中的partitionIndex是map输出键值对中的键的值，也就是K的值。

Maper类：

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class WordCountMap extends Mapper<LongWritable, Text, Text, IntWritable> {
    public void map(LongWritable key, Text value, Context context)
            throws IOException, InterruptedException {
        String[] words = value.toString().split("\t");
        for (String word : words) {
            // 每个单词出现１次，作为中间结果输出
            context.write(new Text(word), new IntWritable(1));
        }
    }
}

Reducer类：

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
public class WordCountMap extends Mapper<LongWritable, Text, Text, IntWritable> {
    public void map(LongWritable key, Text value, Context context)
            throws IOException, InterruptedException {
        String[] words = value.toString().split("\t");
        for (String word : words) {
            // 每个单词出现１次，作为中间结果输出
            context.write(new Text(word), new IntWritable(1));
        }
    }
}

main函数：

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;
public class WordCountMain {
    public static void main(String[] args) throws IOException,
            ClassNotFoundException, InterruptedException {
        if (args.length != 2 || args == null) {
            System.out.println("please input Path!");
            System.exit(0);
        }
        Configuration configuration = new Configuration();
        configuration.set("mapreduce.job.jar","/home/bruce/project/kkbhdp01/target/com.kaikeba.hadoop-1.0-SNAPSHOT.jar");
        Job job = Job.getInstance(configuration, WordCountMain.class.getSimpleName());
        // 打jar包
        job.setJarByClass(WordCountMain.class);
        // 通过job设置输入/输出格式
        //job.setInputFormatClass(TextInputFormat.class);
        //job.setOutputFormatClass(TextOutputFormat.class);
        // 设置输入/输出路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        // 设置处理Map/Reduce阶段的类
        job.setMapperClass(WordCountMap.class);
        //map combine
        //job.setCombinerClass(WordCountReduce.class);
        job.setReducerClass(WordCountReduce.class);
        //如果map、reduce的输出的kv对类型一致，直接设置reduce的输出的kv对就行；如果不一样，需要分别设置map, reduce的输出的kv类型
        //job.setMapOutputKeyClass(.class)
        // 设置最终输出key/value的类型m
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        job.setPartitionerClass(CustomPartitioner.class);
        job.setNumReduceTasks(4);
        // 提交作业
        job.waitForCompletion(true);

    }
}

main函数参数设置：