scrunch.scala

object WordCount extends PipelineApp {

  def ScrunchWordCount(file: String) = {
    read(from.textFile(file))
      .flatMap(_.split("\\W+")
      .filter(!_.isEmpty()))
      .count
  }

  val counts = join(countWords(args(0)), countWords(args(1)))
  write(counts, to.textFile(args(2)))
}


object ScoobiWordCount {
  def main(allArgs: Array[String]) = withHadoopArgs(allArgs) { args =>
    val lines: DList[String] = fromTextFile(args(0))
 
    val counts: DList[(String, Int)] = lines.flatMap(_.split(" "))
                                            .map(word => (word, 1))
                                            .groupByKey
                                            .combine(_+_)
 
    persist(toTextFile(counts, args(1)))
  }
}