spark重写排序规则（二）

1.样例类实现自定义排序，需要实现ordered特质,不需要实现serializable，不需要new对象（本文样例类）
2.普通类实现自定义排序，需要实现ordered特质,实现serializable

姓名name 年龄age 颜值fv
文本为(Array(“mimi1 22 85”, “mimi2 22 86”, “mimi3 23 86”))
按照颜值降序、年龄降序排列

import org.apache.spark.rdd.RDD
import org.apache.spark.{
    
    SparkConf, SparkContext}

object CustomSort_2 {
    
    
  def main(args: Array[String]): Unit = {
    
    
    val conf = new SparkConf()
    conf.setAppName(this.getClass.getName).setMaster("local[2]")
   val sc = new SparkContext(conf)
    val userInfo: RDD[String]
         = sc.parallelize(Array("mimi1 22 85", "mimi2 22 86", "mimi3 23 86"))
       //对文本进行拆分，并返回一个元组
    val personRDD: RDD[(String, Int, Int)] = userInfo.map(x => {
    
    
      val arr = x.split(" ")
      val name = arr(0)
      val age = arr(1).toInt
      val fv = arr(2).toInt
      (name, age, fv)
    })
    //指定排序规则，把元组的字段传入person2中，按照person2的compare方法进行排序
    val sorted: RDD[(String, Int, Int)] = personRDD.sortBy(x => person2(x._1, x._2, x._3))
    println(sorted.collect.toBuffer)
  }
}
case class person2(val name:String,val age:Int, val fv:Int) extends Ordered[person2]{
    
    
  override def compare(that: person2): Int = {
    
    
    if(this.fv!=that.fv)
      that.fv- this.fv
    else that.age - this.age
  }

  override def toString: String = s"$name,$age,$fv"
}

运行结果

ArrayBuffer((mimi3,23,86), (mimi2,22,86), (mimi1,22,85))