Instead of using map, it uses mapPartitions. It is better than csv-parsing-ex2.scala

csv-parsing-ex3scala

//CSV parsing program using opencsv library
//spark-shell --packages net.sf.opencsv:opencsv:2.3
//Or
//Add this to sbt: libraryDependencies += "net.sf.opencsv" % "opencsv" % "2.3"  

import au.com.bytecode.opencsv.CSVParser
var linesRdd = sc.textFile("/data/spark/temps.csv");
def parseCSV(itr:Iterator[String]):Iterator[Array[String]] = {
    val parser = new CSVParser(',')
    for(line <- itr)
        yield parser.parseLine(line)
}
//Check with simple example
val x = parseCSV(Array("1,2,3","a,b,c").iterator)
linesRdd.mapPartitions(parseCSV)