An example of broadcast variables in spark using scala.

broadcast-example.scala

var commonWords = Array("a", "an", "the", "of", "at", "is", "am","are","this","that","at", "in", "or", "and", "or", "not", "be", "for", "to", "it")
val commonWordsMap = collection.mutable.Map[String, Int]()
for(word <- commonWords){
    commonWordsMap(word) = 1
}
var commonWordsBC = sc.broadcast(commonWordsMap)

var file = sc.textFile("/data/mr/wordcount/input/big.txt")
def toWords(line:String):Array[String] = {  
    var words = line.split(" ")
    var output = Array[String]();
    for(word <- words){
        if(! (commonWordsBC.value contains word.toLowerCase.trim.replaceAll("[^a-z]",""))) output = output :+ word;
    }
    return output;
}
var uncommonWords = file.flatMap(toWords)
uncommonWords.take(100)