MapJoin多表联合

需求：将商品数据和订单数据关联起来

有如下两组数据：

01 小米
02 华为
03 格力
04 8848
05 Dell
......

-----------------------------

201901 01 1
201902 02 2
201903 03 3
201904 01 4
201905 02 5
201906 03 6
201906 04 9
201904 05 4
201905 05 5
201906 03 6
201906 04 9
......

现在需要使用MapJoin将两组数据关联起来，类似SQL的多表关联查询：

1：创建DistributedCacheMapper类

package MapJoin;
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;
import java.io.*;
import java.util.HashMap;
import java.util.Map;

/**
 * 1.两个表join
 * 2.小表加缓存
 * 3.setup方法的使用
 */

public class DistributedCacheMapper extends Mapper {
    Map pdMap = new HashMap<>();
    Text k = new Text();

    /**
     *
     * 初始化方法
     * 把pd.txt加载进来
     * @param context
     * @throws IOException
     * @throws InterruptedException
     */
    @Override
    protected void setup(Context context) throws IOException, InterruptedException {
        //将pd.txt文件加载进来
        BufferedReader reader = new BufferedReader(new InputStreamReader(
                new FileInputStream(new File("E:\\bigdata_code\\pd.txt")), "UTF-8"));

        String line;
        //导包注意：org.apache.commons.lang.StringUtils，是commons包，不是hadoop包
        while (StringUtils.isNotEmpty(line = reader.readLine())) {
            String[] fields = line.split(" ");
            //产品id，产品名字
            String pid = fields[0];
            String pname = fields[1];
            pdMap.put(pid,pname);
        }
        reader.close();
    }

    /**
     * order.txt的处理
     *
     * @param key
     * @param value
     * @param context
     * @throws IOException
     * @throws InterruptedException
     */
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //转类型
        String line = value.toString();
        //切分
        String[] fields = line.split(" ");
        //订单id、产品id、产品数量
        String orderId = fields[0];
        String pid = fields[1];
        String amount = fields[2];
        //通过pid(key)，拿到pname(value)
        String pname = pdMap.get(pid);

        //数据字段拼接
        k.set(orderId + "\t" + pname + "\t" + amount );

        context.write(k,NullWritable.get());
    }
}

2：创建DistributedCacheDriver类

package MapJoin;
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;
import java.io.IOException;
import java.net.URI;
import java.net.URISyntaxException;

public class DistributedCacheDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException, URISyntaxException {
        args = new String[]{"E:\\bigdata_code\\order.txt","E:\\bigdata_code\\our1"};

        //1:获取job信息
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        //2:设置加载包路径
        job.setJarByClass(DistributedCacheDriver.class);
        //3:关联map，设置输出数据类型
        job.setMapperClass(DistributedCacheMapper.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);
        //4:设置输入输出路径
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));

        job.addCacheFile(new URI("file:///e:/bigdata_code/pd.txt"));
        job.setNumReduceTasks(0);
        //5:提交
        job.waitForCompletion(true);
    }
}
运行后输出结果如下：

201901    小米    1
201902    华为    2
201903    格力    3
201904    小米    4
201905    华为    5
201906    格力    6
201906    8848    9
201904    戴尔    4
201905    戴尔    5
201906    格力    6
201906    8848    9