Spark TopN操作

package com.spark.core

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

//orderid,userid,money,productid
object TopN {

  System.setProperty("hadoop.home.dir","D:\\soft\\hadoop\\hadoop-2.7.3")

  def main(args: Array[String]): Unit = {

    val conf = new SparkConf().setMaster("local[*]").setAppName("topn")
    val sc = new SparkContext(conf)

    var idx = 0
    val six = sc.textFile(args(0))
    //方式一
    //    six.filter(x => (x.trim().length>0) && (x.split(",").length==4))
    //      .map(line => line.split(",")(2))
    //      .map(x => (x.toInt,""))
    //      .sortByKey(false)
    //      .map(x=>x._1)
    //      .take(5)
    //      .foreach(x => {
    //        idx = idx+1
    //        println(idx +"\t"+x)})

    //方式二
//        six.filter(x => (x.trim().length>0) && (x.split(",").length==4))
//          .map(line => line.split(",")(2))
//          .sortBy(line => line.toInt, false)
//          .take(5)
//          .foreach(x => {
//            idx = idx+1
//            println(idx +"\t"+x)})

    //方式三
    six.filter(x => (x.trim().length > 0) && (x.split(",").length == 4))
      .map(line => line.split(",")(2).toInt)
      .top(5)
      .foreach(x => {
        idx = idx + 1
        println(idx + "\t" + x)
      })
  }

}