黑猴子的家：MapReduce Map端表合并（Distributedcache）案例二

1、分析

适用于关联表中有小表的情形；
可以将小表分发到所有的map节点，这样，map节点就可以在本地对自己所读到的大表数据进行合并并输出最终结果，可以大大提高合并操作的并发度，加快处理速度。

2、先在驱动模块中添加缓存文件

import java.net.URI;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
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;

public class DistributedCacheDriver {

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

        // 1 获取job信息
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

        // 2 设置加载jar包路径
        job.setJarByClass(DistributedCacheDriver.class);

        // 3 关联map
        job.setMapperClass(DistributedCacheMapper.class);
        
        // 4 设置最终输出数据类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        // 5 设置输入输出路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        // 6 加载缓存数据
        job.addCacheFile(new URI("file:///e:/inputcache/pd.txt"));
        
        // 7 map端join的逻辑不需要reduce阶段，设置reducetask数量为0
        job.setNumReduceTasks(0);

        // 8 提交
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }
}

3、读取缓存的文件数据

import java.io.BufferedReader;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.HashMap;
import java.util.Map;
import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class DistributedCacheMapper extends Mapper<LongWritable, Text, Text, NullWritable>{

    Map<String, String> pdMap = new HashMap<>();
    
    @Override
    protected void setup(Mapper<LongWritable, Text, Text, NullWritable>.Context context)
            throws IOException, InterruptedException {
        // 1 获取缓存的文件
        BufferedReader reader = new BufferedReader(new InputStreamReader(new FileInputStream("pd.txt"),"UTF-8"));
        
        String line;
        while(StringUtils.isNotEmpty(line = reader.readLine())){
            // 2 切割
            String[] fields = line.split("\t");
            
            // 3 缓存数据到集合
            pdMap.put(fields[0], fields[1]);
        }
        
        // 4 关流
        reader.close();
    }
    
    Text k = new Text();
    
    @Override
    protected void map(LongWritable key, Text value, Context context)
            throws IOException, InterruptedException {
        // 1 获取一行
        String line = value.toString();
        
        // 2 截取
        String[] fields = line.split("\t");
        
        // 3 获取产品id
        String pId = fields[1];
        
        // 4 获取商品名称
        String pdName = pdMap.get(pId);
        
        // 5 拼接
        k.set(line + "\t"+ pdName);
        
        // 6 写出
        context.write(k, NullWritable.get());
    }
}

4、Code -> GitHub

https://github.com/liufengji/hadoop_mapreduce.git