Spark_自定义分区器

自定义分区器：

1. 继承Partitioner
2. 重写方法

  val sparkConf: SparkConf = new SparkConf().setMaster("local[*]").setAppName("spark")
    val sc = new SparkContext(sparkConf)
    val rdd: RDD[(String, String)] = sc.makeRDD(List(
      ("nba", "a"),
      ("cba", "aa"),
      ("nba", "aaa"),
      ("wba", "aaaa")
    ),2)
    val resultRDD: RDD[(String, String)] = rdd.partitionBy(new MyPartitioner)
    resultRDD.saveAsTextFile("output")
  }
  class MyPartitioner extends Partitioner{
    override def numPartitions: Int = 3

    override def getPartition(key: Any): Int = {
       key match {
         case "nba" => 0
         case "cba" => 1
         case _ => 2
       }
    }