Spark中自定义排序

项目创建参考：http://blog.csdn.net/tototuzuoquan/article/details/74571374

package cn.toto.spark

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

/**
  * Created by toto on 2017/7/8.
  */
object OrderContext {

  implicit val girlOrdering = new Ordering[Girl] {
    override def compare(x: Girl, y: Girl): Int = {
      if(x.faceValue > y.faceValue) 1
      else if(x.faceValue == y.faceValue) {
        if(x.age > y.age) -1 else 1
      } else -1
    }
  }
}

//sort => 规则 先按faceValue，比较年龄
//name,faceValue,age
object CustomSort {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("CustomSort").setMaster("local[2]")
    val sc = new SparkContext(conf)
    val rdd1 = sc.parallelize(List(("yangliying",90,28,1),("gaoyuanyuan",90,27,2),("liutao",95,22,3),("yangzi",97,22,4)))
    //import OrderContext._
    val rdd2: RDD[(String, Int, Int, Int)] = rdd1.sortBy(x => Girl(x._2, x._3), false)
    println(rdd2.collect().toBuffer)
    sc.stop()
  }
}

/**
  * 第一种方式
  * @param faceValue
  * @param age
  */
case class Girl(val faceValue: Int, val age: Int) extends Ordered[Girl] with Serializable {
  override def compare(that: Girl): Int = {
    if(this.faceValue == that.faceValue) {
      that.age - this.age
    } else {
      this.faceValue - that.faceValue
    }
  }
}

/**
  * 第二种，通过隐式转换完成排序
  */
//case class Girl(falceValue:Int,age:Int) extends Serializable

运行结果是：