RDD 辅助功能 implicts

object RDDImplict{
implicit class RDDOps[T](rdd: RDD[T]) {
  def partitionBy(f: T => Boolean): (RDD[T], RDD[T]) = {
    val passes = rdd.filter(f)
    val fails = rdd.filter(e => !f(e)) // Spark doesn't have filterNot
    (passes, fails)
  }
}}
import RDDImplict._
val (matches, matchesNot) = sc.parallelize(1 to 100).cache().partitionBy(_ % 2 == 0)



object BadImplicit {

  implicit class DataFrameTransforms(df: DataFrame) {
    def withGreeting(): DataFrame = {
      df.withColumn("greeting", lit("hello world"))
    }
    def withFarewell(): DataFrame = {
      df.withColumn("farewell", lit("goodbye"))
    }
  }
}


import BadImplicit._
val df = Seq(
  "funny",
  "person"
).toDF("something")
val hiDf = df.withGreeting().withFarewell()