Scala function takes 2 hours with 2 million values - list

Question

Would be grateful if any ideas to speed it up!
case class Pair(aa:String, bb:String)
case class OutputRow(bb:String, aa:String, bb_2:String, aa_2:String)
def startSearch(
_1_sorted: Array[Pair] ,
_2_hashmap: HashMap[String, String] ) : ArrayBuffer[OutputRow] = {
var outputTableListBuffer = ArrayBuffer[OutputRow]()
var searchComparisionFlag = false
var storeMain = Pair("0","0") //Initialize with Dummy data
var i = 0
def search(xxxx_1: Pair): Unit = {
if (searchComparisionFlag==true) {
var _2_exists = _2_hashmap.exists(_._1 == xxxx_1.aa)
if (_2_exists) {
val _2_xxxx = _2_hashmap(xxxx_1.aa)
outputTableListBuffer.append(OutputRow(storeMain.aa, storeMain.bb,_2_xxxx, xxxx_1.aa))
i = i + 1
if (i % 1000 == 0) println("In recursive search storeMain: ", storeMain)
var storePair = Pair(_2_xxxx,xxxx_1.aa)
search(storePair)
} else {
searchComparisionFlag = false
return
}
} else {
var _2_exists = _2_hashmap.exists(_._1 == xxxx_1.aa)
if (_2_exists) {
val _2_xxxx = _2_hashmap(xxxx_1.aa)
searchComparisionFlag = true
outputTableListBuffer.append(OutputRow(xxxx_1.aa, xxxx_1.bb,_2_xxxx, xxxx_1.aa))
var store = Pair(_2_xxxx,xxxx_1.aa)
search(store)
}
}
}
_1_sorted.foreach{ aa_1 =>
val store = Pair(aa_1.aa, aa_1.bb)
storeMain = store
search(store)
}
outputTableListBuffer
}
The above function takes 2 hours with 1 million values in _1_sorted and with a good 1 Million lookup in the hashmap.
Any ideas to speed this up?
This is a recursive logic function

Answer 1

The biggest problem is this:
_2_hashmap.exists(_._1 == xxxx_1.aa)
This is checking every single element of the hashmap on every call. Instead, use get:
_2_hashmap.get(xxxx_1.aa) match {
Some(_2_xxxx) => // Found
???
None => // Not found
???
}
Other code issues:
Don't use return
Pass flags down through recursive call rather than using global var
Use val wherever possible
Don't start variable names with _