Hadoop_21_编写MapReduce程序实现Join功能

Posted 2020-11-20 QueryMarsBo

1.序列化与Writable接口

1.1.hadoop的序列化格式

　　序列化和反序列化就是结构化对象和字节流之间的转换，主要用在内部进程的通讯和持久化存储方面

　　hadoop在节点间的内部通讯使用的是RPC，RPC协议把消息翻译成二进制字节流发送到远程节点，远程节点再通过反序

列化把二进制流转成原始的信息　　

　　hadoop自身的序列化存储格式实现了Writable接口的类,他只实现了前面压缩和快速。但是不容易扩展也不跨语言

　　我们先来看下Writable接口，Writable接口定义了两个方法：

　　1.将数据写入到二进制流中

　　2.从二进制数据流中读取数据

　　

2.reduce端join算法实现

1.需求：

 

 假如数据量巨大，两表的数据是以文件的形式存储在HDFS中，需要用mapreduce程序来实现以下SQL查询运算：

   select  a.id,a.date,b.name,b.category_id,b.price from t_order a join t_product b on a.pid = b.id

2.实现机制：

　　通过将关联的条件pid作为map输出的key，将两表满足join条件的数据并携带数据所来源的文件信息，发往同

一个reducetask，在reduce中进行数据的串联

3.代码实现：

package cn.bigdata.mr.rjoin;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.Writable;

public class InfoBean implements Writable {

    private int order_id;
    private String dateString;
    private String p_id;
    private int amount;
    private String pname;
    private int category_id;
    private float price;

    // flag=0表示这个对象是封装订单表记录
    // flag=1表示这个对象是封装产品信息记录
    private String flag;

    public InfoBean() {
    }

    public void set(int order_id, String dateString, String p_id, int amount, String pname, int category_id, float price, String flag) {
        this.order_id = order_id;
        this.dateString = dateString;
        this.p_id = p_id;
        this.amount = amount;
        this.pname = pname;
        this.category_id = category_id;
        this.price = price;
        this.flag = flag;
    }

    public int getOrder_id() {
        return order_id;
    }

    public void setOrder_id(int order_id) {
        this.order_id = order_id;
    }

    public String getDateString() {
        return dateString;
    }

    public void setDateString(String dateString) {
        this.dateString = dateString;
    }

    public String getP_id() {
        return p_id;
    }

    public void setP_id(String p_id) {
        this.p_id = p_id;
    }

    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 int getCategory_id() {
        return category_id;
    }

    public void setCategory_id(int category_id) {
        this.category_id = category_id;
    }

    public float getPrice() {
        return price;
    }

    public void setPrice(float price) {
        this.price = price;
    }

    public String getFlag() {
        return flag;
    }

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

    /**
     * private int order_id; private String dateString; private int p_id;
     * private int amount; private String pname; private int category_id;
     * private float price;
     */
    @Override
    public void write(DataOutput out) throws IOException {
        out.writeInt(order_id);
        out.writeUTF(dateString);
        out.writeUTF(p_id);
        out.writeInt(amount);
        out.writeUTF(pname);
        out.writeInt(category_id);
        out.writeFloat(price);
        out.writeUTF(flag);
    }

    @Override
    public void readFields(DataInput in) throws IOException {
        this.order_id = in.readInt();
        this.dateString = in.readUTF();
        this.p_id = in.readUTF();
        this.amount = in.readInt();
        this.pname = in.readUTF();
        this.category_id = in.readInt();
        this.price = in.readFloat();
        this.flag = in.readUTF();

    }

    @Override
    public String toString() {
        return "order_id=" + order_id + ", dateString=" + dateString + ", p_id=" + p_id + ", amount=" + amount + ", pname=" + pname + ", category_id=" + category_id + ", price=" + price ;
    }
}

package cn.bigdata.mr.rjoin;
import java.io.IOException;
import java.util.ArrayList;
import org.apache.commons.beanutils.BeanUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

/**
 * 订单表和商品表合到一起
    order.txt(订单id, 日期, 商品编号, 数量)
        1001    20150710    P0001    2
        1002    20150710    P0001    3
        1002    20150710    P0002    3
        1003    20150710    P0003    3
    product.txt(商品编号, 商品名字, 价格, 数量)
        P0001    小米5    1001    2
        P0002    锤子T1    1000    3
        P0003    锤子    1002    4
 */
public class RJoin {

    static class RJoinMapper extends Mapper<LongWritable, Text, Text, InfoBean> {
        InfoBean bean = new InfoBean();
        Text k = new Text();

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String line = value.toString();

            FileSplit inputSplit = (FileSplit) context.getInputSplit();
            String name = inputSplit.getPath().getName();
            System.out.println("kkkkkkkkkkkkkkkkkkkkkk"+name);
            // 通过文件名判断是哪种数据
            String pid = "";
            if (name.startsWith("order")) {
                String[] fields = line.split(",");
                // id date pid amount
                pid = fields[2];
                bean.set(Integer.parseInt(fields[0]), fields[1], pid, Integer.parseInt(fields[3]), "", 0, 0, "0");

            } else {
                String[] fields = line.split(",");
                // id pname category_id price
                pid = fields[0];
                bean.set(0, "", pid, 0, fields[1], Integer.parseInt(fields[2]), Float.parseFloat(fields[3]), "1");

            }
            k.set(pid);
            context.write(k, bean);
        }
    }

    static class RJoinReducer extends Reducer<Text, InfoBean, InfoBean, NullWritable> {

        @Override
        protected void reduce(Text pid, Iterable<InfoBean> beans, Context context) throws IOException, InterruptedException {
            InfoBean pdBean = new InfoBean();
            ArrayList<InfoBean> orderBeans = new ArrayList<InfoBean>();

            for (InfoBean bean : beans) {
                if ("1".equals(bean.getFlag())) {    //产品的
                    try {
                        BeanUtils.copyProperties(pdBean, bean);
                    } catch (Exception e) {
                        e.printStackTrace();
                    }
                } else {
                    InfoBean odbean = new InfoBean();
                    try {
                        BeanUtils.copyProperties(odbean, bean);
                        orderBeans.add(odbean);
                    } catch (Exception e) {
                        e.printStackTrace();
                    }
                }
            }

            // 拼接两类数据形成最终结果
            for (InfoBean bean : orderBeans) {

                bean.setPname(pdBean.getPname());
                bean.setCategory_id(pdBean.getCategory_id());
                bean.setPrice(pdBean.getPrice());

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

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        
        conf.set("mapred.textoutputformat.separator", ",");
        
        Job job = Job.getInstance(conf);

        // 指定本程序的jar包所在的本地路径
        // job.setJarByClass(RJoin.class);
//        job.setJar("c:/join.jar");

        job.setJarByClass(RJoin.class);
        // 指定本业务job要使用的mapper/Reducer业务类
        job.setMapperClass(RJoinMapper.class);
        job.setReducerClass(RJoinReducer.class);

        // 指定mapper输出数据的kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(InfoBean.class);

        // 指定最终输出的数据的kv类型
        job.setOutputKeyClass(InfoBean.class);
        job.setOutputValueClass(NullWritable.class);

        // 指定job的输入原始文件所在目录
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        // 指定job的输出结果所在目录
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        // 将job中配置的相关参数，以及job所用的java类所在的jar包，提交给yarn去运行
        /* job.submit(); */
        boolean res = job.waitForCompletion(true);
        System.exit(res ? 0 : 1);
    }
}

运行结果：

order_id=1002, dateString=20150710, p_id=P0001, amount=3, pname=sss, category_id=1001, price=2.0
order_id=1001, dateString=20150710, p_id=P0001, amount=2, pname=sss, category_id=1001, price=2.0
order_id=1002, dateString=20150710, p_id=P0002, amount=3, pname=111, category_id=1000, price=3.0
order_id=1003, dateString=20150710, p_id=P0003, amount=3, pname=www, category_id=1002, price=4.0