Hadoop之mapreduce数据排序案例（详细代码）

mapreduce排序案例

1、需求

查看员工的薪资，按部门、薪资升序排序。

2、分析

如果key属于某个自定义类，且期望key按某种力式进行排序，此时这个自定类就要实现Java中的Comparble接口；另外，这个自定义类还需要实现Hadoop的Writable 序列化接口(更简单点，直接实现WritableComparable接口即可)。
可以把员工的属性封装为Employee类，并实现WriableComparable接口，按部门，薪资实现排序。这次不需要使用 Reduer 程序主方法需要用 job. etSortComparatorClass()指定比较器所在的类。

3、代码实现

EmployeeSortMapper.class

package mr;

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.IOException;

public class EmployeeSortMapper extends Mapper<LongWritable,Text,Employee, NullWritable> {
    @Override
    protected void map(LongWritable key1, Text value1, Context context) throws IOException, InterruptedException {
        //数据：7654，MARTIN	，SALESMAN，7698，1981/9/28，1250，1400，30
        String data = value1.toString();
        //分词
        String[] words = data.split(",");
        //创建员工对象
        Employee e = new Employee();
        //设置员工的属性
        // 员工号
        e.setEmpno(Integer.parseInt(words[0]));
        //姓名
        e.setEname(words[1]);
        //职位
        e.setJob(words[2]);
        //老板号（注意：可能没有老板号）
        try{
            e.setMgr(Integer.parseInt(words[3]));
        }catch (Exception ex){
            //没有老板号
            e.setMgr(-1);
        }
        //入职日期
        e.setHiredate(words[4]);
        //月薪
        e.setSal(Integer.parseInt(words[5]));
        //奖金（注意：奖金也有可能没有）
        try{
            e.setComm(Integer.parseInt(words[6]));
        }catch (Exception ex){
            //没有奖金
            e.setComm(0);
        }
        //部门号
        e.setDeptno(Integer.parseInt(words[7]));
        //输出
        context.write(e,NullWritable.get());
    }
}

Employee.class

package mr;

import org.apache.hadoop.io.WritableComparable;

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

//1.若要把Employee作为key2，则需要实现序列化
//2.员工对象为Employee类，可被排序
//数据：7654，MARTIN	，SALESMAN，7698，1981/9/28，1250，1400，30
public class Employee implements WritableComparable<Employee> {
    private int empno;
    private String ename;
    private String job;
    private int mgr;
    private String hiredate;
    private int sal;
    private int comm;
    private int deptno;
    
    @Override
    public String toString(){
        return "Employee[empno="+empno+",ename="+ename+",sal="+sal+",deptno="+deptno+"]";
    }
    @Override
    public int compareTo(Employee o) {
        //多个列的排序：select * from emp order by deptno,sal;
        //首先按照deptno排序
        if(this.deptno >o.getDeptno()){
            return 1;
        }else if(this.deptno < o.getDeptno()){
            return -1;
        }
        //如果deptno相等，按照sal排序
        if(this.sal >= o.getSal()){
            return 1;
        }else{
            return -1;
        }

    }

    @Override
    public void write(DataOutput output) throws IOException {
        //序列化
        output.writeInt(this.empno);
        output.writeUTF(this.ename);
        output.writeUTF(this.job);
        output.writeInt(this.mgr);
        output.writeUTF(this.hiredate);
        output.writeInt(this.sal);
        output.writeInt(this.comm);
        output.writeInt(this.deptno);
    }

    @Override
    public void readFields(DataInput input) throws IOException {
        //反序列化
        this.empno = input.readInt();
        this.ename = input.readUTF();
        this.job = input.readUTF();
        this.mgr = input.readInt();
        this.hiredate = input.readUTF();
        this.sal = input.readInt();
        this.comm = input.readInt();
        this.deptno = input.readInt();
    }

    public int getEmpno() {
        return empno;
    }

    public void setEmpno(int empno) {
        this.empno = empno;
    }

    public String getEname() {
        return ename;
    }

    public void setEname(String ename) {
        this.ename = ename;
    }

    public String getJob() {
        return job;
    }

    public void setJob(String job) {
        this.job = job;
    }

    public int getMgr() {
        return mgr;
    }

    public void setMgr(int mgr) {
        this.mgr = mgr;
    }

    public String getHiredate() {
        return hiredate;
    }

    public void setHiredate(String hiredate) {
        this.hiredate = hiredate;
    }

    public int getSal() {
        return sal;
    }

    public void setSal(int sal) {
        this.sal = sal;
    }

    public int getComm() {
        return comm;
    }

    public void setComm(int comm) {
        this.comm = comm;
    }

    public int getDeptno() {
        return deptno;
    }

    public void setDeptno(int deptno) {
        this.deptno = deptno;
    }
}

EmployeeSortMain.class

package mr;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class EmployeeSortMain {
    public static void main(String[] args) throws Exception{
        //创建一个job
        Job job = Job.getInstance(new Configuration());
        job.setJarByClass(EmployeeSortMain.class);
        //指定job的mapper和输出的类型 k2  v2
        job.setMapperClass(EmployeeSortMapper.class);
        job.setOutputKeyClass(Employee.class);
        job.setMapOutputValueClass(NullWritable.class);
        //指定job的输入和输出的路径
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));
        //提交程序，并且监控打印程序执行的结果
        boolean b = job.waitForCompletion(true);
        System.exit(b?0:1);
    }
}

4、提交作业到集群运行

上传刚刚生成的jar包（我重新命名为emp）和emp.csv文件到 root。
emp.csv内容如下：

7369,SMITH,CLERK,7902,1980/12/17,800,,20
7499,ALLEN,SALESMAN,7698,1981/2/20,1600,300,30
7521,WARD,SALESMAN,7698,1981/2/22,1250,500,30
7566,JONES,MANAGER,7839,1981/4/2,2975,,20
7654,MARTIN,SALESMAN,7698,1981/9/28,1250,1400,30
7698,BLAKE,MANAGER,7839,1981/5/1,2850,,30
7782,CLARK,MANAGER,7839,1981/6/9,2450,,10
7788,SCOTT,ANALYST,7566,1987/4/19,3000,,20
7839,KING,PRESIDENT,,1981/11/17,5000,,10
7844,TURNER,SALESMAN,7698,1981/9/8,1500,0,30
7876,ADAMS,CLERK,7788,1987/5/23,1100,,20
7900,JAMES,CLERK,7698,1981/12/3,950,,30
7902,FORD,ANALYST,7566,1981/12/3,3000,,20
7934,MILLER,CLERK,7782,1982/1/23,1300,,10

先把emp.csv上传到HDFS的input目录上

hadoop fs -put emp.csv /input

执行jar包

hadoop jar emp.jar /input/emp.csv /output/sort

看到这个就是成功啦

查看结果：

hadoop fs -cat /output/sort/part-r-00000

更详细的操作可以参照另一篇博客：Hadoop 之Mapreduce wordcount词频统计案例（详解）