Learn Scalding with Alice

scalding_alice.scala

/**
Get the last line of text in Alice in Wonderland that contains each of the top 20 frequent words in the book 
NOT ACTUALLY TESTED, just logically combined. See fork source for original version that is mulch ore likely to work.
*/
import scala.io.Source
val alice = Source.fromURL("http://www.gutenberg.org/files/11/11.txt").getLines.zipWithIndex.toList
val aliceWords = TypedPipe.from(alice).flatMap { case (text, _) => text.split("\\s+").toList }
val wordCount = aliceWords.map { word => (word, 1L) }.group.sum
val top20 = wordCount.groupAll.sortBy { case (word, count) => -count }.take(20).values 
val lastLine = alicePipe.flatMap { case (text, line) => text.split("\\s+").toList.map { word => (word, line) }}.group.max
lastLine.map { case (word, lastLine) => (lastLine, word) }.group.join(alicePipe.swap.group).dump