scala_split_code

import scala.collection.mutable.ArrayBuffer
import scala.annotation.tailrec
import scala.collection.mutable.ListBuffer
//import org.apache.commons.lang3.StringUtils


object Test
{
  def split(s: String, c: Char, i: Int = 0): List[String] = if (i < 0) Nil else {
    val p = s indexOf (c, i)
    if (p < 0) s.substring(i) :: Nil else s.substring(i, p) :: split(s, c, p + 1)
  }

  def split2(s: String, c: Char): Seq[String] = {
    val buffer = ListBuffer.empty[String]
    @tailrec def recurse(i: Int): Seq[String] =  {
      val p = s indexOf (c, i)
      if (p < 0) {
        buffer += s.substring(i)
        buffer.toList
      } else {
        buffer += s.substring(i, p)
        recurse(p + 1)
      }
    }
    recurse(0)
  }

  def main(args: Array[String])
  {
    var len = 0
    val t1 = System.currentTimeMillis()
    io.Source.fromFile(args(0)).getLines.foreach { line =>
      val s_line = line.split('\t')
      len += line.length
    }
    val t2 = System.currentTimeMillis()
    val s1 = (t2-t1)/1000.0

    var mb_s = (len/(1024.0*1024.0))/s1
    println(mb_s + " MB/s - Scala split('\\t')")

    len = 0
    val t3 = System.currentTimeMillis()
    io.Source.fromFile(args(0)).getLines.foreach { line =>
      val s_line = line.split("\t")
      len += line.length
    }
    val t4 = System.currentTimeMillis()
    val s2 = (t4-t3)/1000.0

    mb_s = (len/(1024.0*1024.0))/s2
    println(mb_s + " MB/s - Scala split(\"\\t\")")

    len = 0
    val t5 = System.currentTimeMillis()
    io.Source.fromFile(args(0)).getLines.foreach { line =>
      val s_line = split(line, '\t')
      len += line.length
    }
    val t6 = System.currentTimeMillis()
    val s3 = (t6-t5)/1000.0

    mb_s = (len/(1024.0*1024.0))/s3
    println(mb_s + " MB/s - dcsobralWork-1")

    len = -1
    val t7 = System.currentTimeMillis()
    io.Source.fromFile(args(0)).getLines.foreach { line =>
      val s_line = split2(line, '\t')
      len += line.length
    }
    val t8 = System.currentTimeMillis()
    val s4 = (t8-t7)/1000.0

    mb_s = (len/(1024.0*1024.0))/s4
    println(mb_s + " MB/s - dcsobralWork-2")

  }
}