Spark编程--案例：二次排序

优先根据第一列值排序，如果第一列值相等，根据第二列值排序

 

package com.zwq

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

object SecondarySortApp extends  App {
  val conf = new SparkConf().setMaster("local").setAppName("SecondarySortApp")
  val sc = new SparkContext(conf)
  val array = Array("8 3", "5 6", "5 3", "4 9", "4 7", "3 2", "1 6")
  val rdd = sc.parallelize(array)
  rdd.map(_.split(" "))
    .map(item => (item(0).toInt, item(1).toInt))
    .map(item => (new SecondarySortKey(item._1, item._2), s"${item._1} ${item._2}"))
    .sortByKey(false)
    .foreach(x => println(x._2))
}


class SecondarySortKey(val first:Int, val second: Int) extends Ordered[SecondarySortKey] with Serializable{
  override def compare(that: SecondarySortKey): Int = {
    if (this.first - that.first != 0){
      this.first - that.first
    }else {
      this.second - that.second
    }
  }
}