Reproduces go-to Word Count example

WordCount.scala

import gallia._

// ===========================================================================
object WordCount { // see http://spark.apache.org/examples.html and https://hadoop.apache.org/docs/current/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html

  def main(args: Array[String]): Unit = {

    // INPUT: "Hello World Bye World\nHello Hadoop Goodbye Hadoop"

    // ---------------------------------------------------------------------------
    println("word count:")
    "/tmp/sentences.list"
      .stream(_.lines) // also see https://github.com/galliaproject/gallia-core/blob/init/README.md#spark-rdds
        .split(_line ~> 'word).by(" ")
        .flattenBy('word)
        .generate(_count).from('word).using(_ => 1)        
        .sum(_count).by('word)        
      .printJsonl()      
      /*
        OUTPUT:
          {"word":"Hello","_count":2}
          {"word":"World","_count":2}
          {"word":"Bye","_count":1}
          {"word":"Hadoop","_count":2}
          {"word":"Goodbye","_count":1}
      */

    // ---------------------------------------------------------------------------
    println("\ncount word length:") // because why not
    "/tmp/sentences.list"
      .stream(_.lines) // also see https://github.com/galliaproject/gallia-core/blob/init/README.md#spark-rdds
        .split(_line ~> 'word).by(" ")
        .flattenBy('word)
        .generate('word_length).from(_.string('word)).using(_.size)        
        .count('word ~> _count).by('word_length)
      .printJsonl()
      /*
       OUTPUT: 
          {"word_length":5,"_count":4}
          {"word_length":3,"_count":1}
          {"word_length":6,"_count":2}
          {"word_length":7,"_count":1} 
      */
  }
}

// ===========================================================================