forks.scala

//command line args:
val buckets = 5
val myBucket = 1//method 2 only

//helper functions
case class TableWithHash(tableName: String, hash: Int)
def hashTable(string: tableName): TableWithHash = {
  TableWithHash(tableName, (tableName.hashCode % buckets).toInt)
}

//filler functions:
def getAllTables(): Seq[String] = {
  Seq("foo", "bar", "baz")
}
def printCount(tableName: String): Unit = {
  println("-1") 
}
def countInBackground(tables: Seq[TableWithHash]): Unit = {
  import sys.process._
  "spark-submit . . . Somehow.Count tables".!!
}

//method 1:
{
  val allTables = getAllTables()
  val tables = allTables.map(hashTable)
  val groupedTables = tables.groupBy(_.hash)
  
  groupedTables.foreach(group => {
    countInBackground(group._2)
  })
}

//method 2:
{
  val allTables = getAllTables()
  val tables = allTables.map(hashTable)
  tables.foreach(table => {
    if(table.hash == myBucket)
      printCount(table.tableName)
  })
}