关于join

1.ReduceJoin

思路: map负责数据整合,reduce负责进行join
缺点: 数据倾斜,Reduce处理太多而Map处理的太少. 这样Reduce的负载太大了.

• map

package com.atguigu.mapreduce.reducejoin;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;

import java.io.IOException;

public class TableMapper extends Mapper<LongWritable,Text,Text,TableBean> {

    private String filename;
    private Text outK = new Text();
    private TableBean outV = new TableBean();

    @Override
    protected void setup(Context context) throws IOException, InterruptedException {
        //获取对应文件名称
        InputSplit split = context.getInputSplit();
        FileSplit fileSplit = (FileSplit) split;
        filename = fileSplit.getPath().getName();
    }

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        //获取一行
        String line = value.toString();

        //判断是哪个文件,然后针对文件进行不同的操作
        if(filename.contains("order")){  //订单表的处理
            String[] split = line.split("\t");
            //封装outK
            outK.set(split[1]);
            //封装outV
            outV.setId(split[0]);
            outV.setPid(split[1]);
            outV.setAmount(Integer.parseInt(split[2]));
            outV.setPname("");
            outV.setFlag("order");
        }else {                             //商品表的处理
            String[] split = line.split("\t");
            //封装outK
            outK.set(split[0]);
            //封装outV
            outV.setId("");
            outV.setPid(split[0]);
            outV.setAmount(0);
            outV.setPname(split[1]);
            outV.setFlag("pd");
        }

        //写出KV
        context.write(outK,outV);
    }
}

• reduce

package com.atguigu.mapreduce.reducejoin;

import org.apache.commons.beanutils.BeanUtils;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;
import java.lang.reflect.InvocationTargetException;
import java.util.ArrayList;

public class TableReducer extends Reducer<Text,TableBean,TableBean, NullWritable> {

    @Override
    protected void reduce(Text key, Iterable<TableBean> values, Context context) throws IOException, InterruptedException {

        ArrayList<TableBean> orderBeans = new ArrayList<>();
        TableBean pdBean = new TableBean();

        for (TableBean value : values) {

            //判断数据来自哪个表
            if("order".equals(value.getFlag())){   //订单表

			  //创建一个临时TableBean对象接收value
                TableBean tmpOrderBean = new TableBean();

                try {
                    BeanUtils.copyProperties(tmpOrderBean,value);
                } catch (IllegalAccessException e) {
                    e.printStackTrace();
                } catch (InvocationTargetException e) {
                    e.printStackTrace();
                }

			  //将临时TableBean对象添加到集合orderBeans
                orderBeans.add(tmpOrderBean);
            }else {                                    //商品表
                try {
                    BeanUtils.copyProperties(pdBean,value);
                } catch (IllegalAccessException e) {
                    e.printStackTrace();
                } catch (InvocationTargetException e) {
                    e.printStackTrace();
                }
            }
        }

        //遍历集合orderBeans,替换掉每个orderBean的pid为pname,然后写出
        for (TableBean orderBean : orderBeans) {

            orderBean.setPname(pdBean.getPname());

		   //写出修改后的orderBean对象
            context.write(orderBean,NullWritable.get());
        }
    }
}

2.mapJoin

优点:

• 1. 在map端将数据进行处理,实现数据合并
     配置: 设置分布式缓存 将小文件加载到每个mapTask运行的机器上
     代码:
     1.Driver

job.addCacheFile(new URI("file:///D:/input/tablecache/pd.txt"));
// Map端Join的逻辑不需要Reduce阶段，设置reduceTask数量为0
job.setNumReduceTasks(0);   

2.在MapJoinMapper类中的setup方法中读取缓存文件

 private Map<String, String> pdMap = new HashMap<>();
    private Text text = new Text();

    //任务开始前将pd数据缓存进pdMap
    @Override
    protected void setup(Context context) throws IOException, InterruptedException {


        //通过缓存文件得到小表数据pd.txt
        URI[] cacheFiles = context.getCacheFiles();
        Path path = new Path(cacheFiles[0]);

        //获取文件系统对象,并开流
        FileSystem fs = FileSystem.get(context.getConfiguration());
        FSDataInputStream fis = fs.open(path);

        //通过包装流转换为reader,方便按行读取
        BufferedReader reader = new BufferedReader(new InputStreamReader(fis, "UTF-8"));

        //逐行读取，按行处理
        String line;
        while (StringUtils.isNotEmpty(line = reader.readLine())) {
            //切割一行    
//01	小米
            String[] split = line.split("\t");
            pdMap.put(split[0], split[1]);
        }

        //关流
        IOUtils.closeStream(reader);
IOUtils.closeStream(fis);
    }