hadoop-17 Join的多种应用

Posted by 蓝染君

On 2023年 9月 26日

已关闭评论

Reduce Join

Map端的主要工作，为来自不同表或文件的key/value对，打标签以区别不同来源的记录，然后用连接字段为key，其余部分和新加的标志作为value，最后进行输出。
Reduce端的主要工作，在Reduce端以连接字段作为key的分组已经完成，我们只需要在每一个分组当中将那些来源不同文件的记录（在Map阶段已经打标志）分开，最后进行合并就ok了

TableBean.java

import org.apache.hadoop.io.Writable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

public class TableBean implements Writable {
    private String id;  // 订单id
    private String pid;  // 商品id
    private int amount;  // 商品数量
    private String pname;  // 商品名称
    private String flag;  // 标记是哪张表 order pd

    // 空参构造
    public TableBean() {
    }

    public String getId() {
        return id;
    }

    public void setId(String id) {
        this.id = id;
    }

    public String getPid() {
        return pid;
    }

    public void setPid(String pid) {
        this.pid = pid;
    }

    public int getAmount() {
        return amount;
    }

    public void setAmount(int amount) {
        this.amount = amount;
    }

    public String getPname() {
        return pname;
    }

    public void setPname(String pname) {
        this.pname = pname;
    }

    public String getFlag() {
        return flag;
    }

    public void setFlag(String flag) {
        this.flag = flag;
    }

    // 序列化
    @Override
    public void write(DataOutput out) throws IOException {
        out.writeUTF(id);
        out.writeUTF(pid);
        out.writeInt(amount);
        out.writeUTF(pname);
        out.writeUTF(flag);
    }

    // 反序列化
    @Override
    public void readFields(DataInput in) throws IOException {
        this.id = in.readUTF();
        this.pid = in.readUTF();
        this.amount = in.readInt();
        this.pname = in.readUTF();
        this.flag = in.readUTF();
    }

    @Override
    public String toString() {
        return  id + "\t" + pname + "\t" + amount;
    }
}

TableMapper.java

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
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 Text outK = new Text();
    private TableBean outV = new TableBean();
    private String fileName;

    @Override
    protected void setup(Context context) throws IOException, InterruptedException {
        // 初始化 order pd
        FileSplit split = (FileSplit) context.getInputSplit();
        fileName = split.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
        String[] split = line.split("\t");
        if (fileName.contains("order")) {
            // 封装kv
            outK.set(split[1]);
            outV.setId(split[0]);
            outV.setPid(split[1]);
            outV.setAmount(Integer.parseInt(split[2]));
            outV.setPname("");
            outV.setFlag("order");
        } else {
            // 封装kv
            outK.set(split[0]);
            outV.setPid(split[0]);
            outV.setPname(split[1]);
            outV.setId("");
            outV.setAmount(0);
            outV.setFlag("pd");
        }
        context.write(outK, outV);
    }
}

TableReducer.java

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 {
        // 创建集合
        ArrayList<TableBean> orderBeans = new ArrayList<>();
        TableBean pdBean = new TableBean();
        for (TableBean value : values) {
            if ("order".equals(value.getFlag())) {  // 订单表
                // hadoop底层改动了 Iterable values 列表添加 只添加内存地址，并且会覆盖
                // 需要使用中间变量 传递对象过去
                TableBean tmpTableBean = new TableBean();
                try {
                    // 复制value属性值
                    BeanUtils.copyProperties(tmpTableBean, value);
                } catch (IllegalAccessException | InvocationTargetException e) {
                    e.printStackTrace();
                }
                orderBeans.add(tmpTableBean);
            } else {  // 商品表
                try {
                    BeanUtils.copyProperties(pdBean, value);
                } catch (IllegalAccessException | InvocationTargetException e) {
                    e.printStackTrace();
                }
            }
        }
        for (TableBean orderBean : orderBeans) {
            orderBean.setPname(pdBean.getPname());
            context.write(orderBean, NullWritable.get());
        }
    }
}

TableDriver.java

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;

public class TableDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        // 1.获取job
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        // 2.设置jar
        job.setJarByClass(TableDriver.class);
        // 3.关联mapper 和 reducer
        job.setMapperClass(TableMapper.class);
        job.setReducerClass(TableReducer.class);
        // 4.设置mapper输出kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(TableBean.class);
        // 5.设置最终输出kv类型
        job.setOutputKeyClass(TableBean.class);
        job.setOutputValueClass(NullWritable.class);

        // 6.设置输入输出路径
        FileInputFormat.setInputPaths(job, new Path("E:\\hadoop\\tableinput"));
        FileOutputFormat.setOutputPath(job, new Path("E:\\hadoop\\tableoutput"));
        // 7.提交job
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }
}

ReduceJoin是在Reduce阶段完成，Reduce端的处理压力太大，Map阶段的运算负载则很低，资源利用率不高，而且在Reduce阶段极易产生数据倾斜

Map Join

适用于一张很小的小表join一张大表

采用DistrubutedCache

在Mapper的setup阶段，将文件读取到缓存集合中
在Driver驱动类中，加载缓存

//缓存普通文件到Task运行节点
job.addCacheFile(new URI("fille:///e:/cache/pd.txt"));
// 如果是集群运行，需要设置HDFS路径
job.addCacheFile(new URI("hdfs://hadoop102:8020/cache/pd.txt"));

MapJoinMapper.java

import org.apache.commons.lang3.StringUtils;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
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.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.URI;
import java.nio.charset.StandardCharsets;
import java.util.HashMap;

public class MapJoinMapper extends Mapper<LongWritable, Text, Text, NullWritable> {
    private HashMap<String, String> pdMap = new HashMap<>();
    private Text outK = new Text();

    @Override
    protected void setup(Context context) throws IOException, InterruptedException {
        // 获取缓存文件，并把文件内容封装到集合
        URI[] cacheFiles = context.getCacheFiles();
        FileSystem fs = FileSystem.get(context.getConfiguration());
        FSDataInputStream fis = fs.open(new Path(cacheFiles[0]));
        // 从流中读取数据
        BufferedReader reader = new BufferedReader(new InputStreamReader(fis, StandardCharsets.UTF_8));
        String line;
        while (!StringUtils.isEmpty(line = reader.readLine())) {
            // 切割
            String[] fields = line.split("\t");
            // 赋值
            pdMap.put(fields[0], fields[1]);
        }
        // 关流
        IOUtils.closeStream(reader);
    }

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        // 处理order.txt
        String line = value.toString();
        String[] split = line.split("\t");
        // 获取pid
        String pname = pdMap.get(split[1]);
        outK.set(split[0] + "\t" + pname + "\t" + split[2]);
        context.write(outK, NullWritable.get());
    }
}

MapJoinDriver.java

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 MapJoinDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException, URISyntaxException {
        // 1.获取job
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        // 2.设置jar
        job.setJarByClass(MapJoinDriver.class);
        // 3.关联mapper 和 reducer
        job.setMapperClass(MapJoinMapper.class);
        // 4.设置mapper输出kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);
        // 5.设置最终输出kv类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        //取消reduce阶段
        job.setNumReduceTasks(0);
        // 加载缓存数据
        job.addCacheFile(new URI("file:///E:/hadoop/tableinput/pd.txt"));

        // 6.设置输入输出路径
        FileInputFormat.setInputPaths(job, new Path("E:\\hadoop\\tableinput2"));
        FileOutputFormat.setOutputPath(job, new Path("E:\\hadoop\\tableoutput2"));

        // 7.提交job
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }
}

Blog

About 蓝染君