def scalding()

in src/main/scala/com/spotify/bdrc/pipeline/WordCount.scala [28:36]


  def scalding(input: TypedPipe[String]): TypedPipe[(String, Long)] = {
    input
      .flatMap(_.split("[^a-zA-Z']+").filter(_.nonEmpty))
      // `groupBy` is lazy
      .groupBy(identity)
      // Operations like `size` after `groupBy` can be lifted into the map phase
      .size
      .toTypedPipe
  }