maprecuce系列（4）——reduce端join算法实现

一、需求

1、如下订单表：id、date、pid、amount

1001,20160710,P0001,21002,20160710,P0001,31002,20170710,P0002,31001,20160710,P0001,21002,20140710,P0003,31003,20150710,P0002,3

2、如下商品信息表：id,panme,category_id,price

P0001,xiaomi5,1000,2P0002,chuiziT1,1000,3P0003,meizu,1001,3

其中订单表中的pid对应商品列表中的id。
如果进行聊表查询所有的详细信息，想想，如果是在sql中就非常简单了：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
3、思路：
如果利用mapreduce进行处理，其实我们可以想象，
在maptask后，同样的key被归为一组，传递给reduceTask来进行处理的，这时我如果把两个表以同一个key来map，所以最后在，reduce的时候合并起来就肯定是订单和商品的详细信息了。

二、代码实现

1、首先定义个bean包含所有的订单信息和商品信息，当同时得有一个flag来区分这个bean到底是订单，还是商品：
InfoBean1.java

package join;import org.apache.hadoop.io.Writable;import java.io.DataInput;import java.io.DataOutput;import java.io.IOException;/** * * Created by tianjun on 2017/3/17. */public class InfoBean1  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表示封装的是订单表记录    //flag=1表示封装的是产品信息记录    private String 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;    }    public InfoBean1() {    }    public InfoBean1(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 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;    }    @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 {        order_id = in.readInt();        dateString= in.readUTF();        p_id = in.readUTF();        amount = in.readInt();        pname = in.readUTF();        category_id = in.readInt();        price = in.readFloat();        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;    }}

2、join功能的实现：
Rjoin.java

package join;import org.apache.commons.beanutils.BeanUtils;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.FileSystem;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;import java.io.IOException;import java.net.URI;import java.net.URISyntaxException;import java.util.ArrayList;/** * Created by tianjun on 2017/3/17. */public class Rjoin {    static class RjoinMapper extends Mapper<LongWritable, Text, Text, InfoBean1> {        InfoBean1 infoBean = new InfoBean1();        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();            //通过文件名判断是那种数据            String pid = "";            if (name.startsWith("order")) {                String[] fields = line.split(",");                pid = fields[2];                infoBean.set(Integer.parseInt(fields[0]), fields[1], pid, Integer.parseInt(fields[3]), "", 0, 0, "0");            } else {                String[] fields = line.split(",");                pid = fields[0];                infoBean.set(0, "", pid, 0, fields[1], Integer.parseInt(fields[2]), Float.parseFloat(fields[3]), "1");            }            k.set(pid);            context.write(k, infoBean);        }    }    static class RjoinReducer extends Reducer<Text, InfoBean1, InfoBean1, NullWritable> {        @Override        protected void reduce(Text key, Iterable<InfoBean1> values, Context context) throws IOException, InterruptedException {            InfoBean1 pdBean = new InfoBean1();            ArrayList<InfoBean1> orderBeans = new ArrayList<>();            for (InfoBean1 bean : values) {                if ("1".equals(bean.getFlag())) {                    try {                        BeanUtils.copyProperties(pdBean, bean);                    } catch (Exception e) {                        e.printStackTrace();                    }                } else {                    InfoBean1 odBean = new InfoBean1();                    try {                        BeanUtils.copyProperties(odBean, bean);                        orderBeans.add(odBean);                    } catch (Exception e) {                        e.printStackTrace();                    }                }            }            for (InfoBean1 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 IOException, ClassNotFoundException, InterruptedException, URISyntaxException {        String os = System.getProperty("os.name").toLowerCase();        if (os.contains("windows")) {            System.setProperty("HADOOP_USER_NAME", "root");        }        Configuration conf = new Configuration();        conf.set("mapreduce.framework.name","yarn");        conf.set("yarn.resourcemanager.hostname","mini01");        conf.set("fs.defaultFS","hdfs://mini01:9000/");//            默认就是local模式//        conf.set("mapreduce.framework.name","local");//        conf.set("mapreduce.jobtracker.address","local");//        conf.set("fs.defaultFS","file:///");        Job wcjob = Job.getInstance(conf);        wcjob.setJar("F:/myWorkPlace/java/dubbo/demo/dubbo-demo/mr-demo1/target/mr.demo-1.0-SNAPSHOT.jar");        //如果从本地拷贝，是不行的，这时需要使用setJar//        wcjob.setJarByClass(Rjoin.class);        wcjob.setMapperClass(RjoinMapper.class);        wcjob.setReducerClass(RjoinReducer.class);        //设置我们的业务逻辑Mapper类的输出key和value的数据类型        wcjob.setMapOutputKeyClass(Text.class);        wcjob.setMapOutputValueClass(InfoBean1.class);        //设置我们的业务逻辑Reducer类的输出key和value的数据类型        wcjob.setOutputKeyClass(InfoBean1.class);        wcjob.setOutputValueClass(NullWritable.class);        //如果不设置InputFormat，默认就是使用TextInputFormat.class//        wcjob.setInputFormatClass(CombineFileInputFormat.class);//        CombineFileInputFormat.setMaxInputSplitSize(wcjob,4194304);//        CombineFileInputFormat.setMinInputSplitSize(wcjob,2097152);        FileSystem fs = FileSystem.get(new URI("hdfs://mini01:9000"), new Configuration(), "root");        Path path = new Path("hdfs://mini01:9000/wc/rjoin");        if (fs.exists(path)) {            fs.delete(path, true);        }        //指定要处理的数据所在的位置        FileInputFormat.setInputPaths(wcjob, new Path("hdfs://mini01:9000/input/rjoin"));        //指定处理完成之后的结果所保存的位置        FileOutputFormat.setOutputPath(wcjob, new Path("hdfs://mini01:9000/wc/rjoin"));        boolean res = wcjob.waitForCompletion(true);        System.exit(res ? 0 : 1);    }}

三、结果

处理结果如下：

order_id=1001, dateString='20150710', p_id='P0001', amount=2, pname='xiaomi5', category_id=1000, price=2.0order_id=1002, dateString='20150710', p_id='P0001', amount=3, pname='xiaomi5', category_id=1000, price=2.0order_id=1001, dateString='20150710', p_id='P0001', amount=2, pname='xiaomi5', category_id=1000, price=2.0order_id=1003, dateString='20150710', p_id='P0002', amount=3, pname='chuiziT1', category_id=1000, price=3.0order_id=1002, dateString='20150710', p_id='P0002', amount=3, pname='chuiziT1', category_id=1000, price=3.0order_id=1002, dateString='20150710', p_id='P0003', amount=3, pname='meizu', category_id=1001, price=3.0