templates4/re.scala
author Christian Urban <urbanc@in.tum.de>
Wed, 28 Nov 2018 17:13:40 +0000
changeset 219 44161f2c3226
child 220 3020f8c76baa
permissions -rw-r--r--
updated

// Part 1 about Regular Expression Matching
//==========================================


abstract class Rexp
case object ZERO extends Rexp
case object ONE extends Rexp
case class CHAR(c: Char) extends Rexp
case class ALT(r1: Rexp, r2: Rexp) extends Rexp   // alternative 
case class SEQ(r1: Rexp, r2: Rexp) extends Rexp   // sequence
case class STAR(r: Rexp) extends Rexp             // star


// some convenience for typing in regular expressions

import scala.language.implicitConversions    
import scala.language.reflectiveCalls 

def charlist2rexp(s: List[Char]): Rexp = s match {
  case Nil => ONE
  case c::Nil => CHAR(c)
  case c::s => SEQ(CHAR(c), charlist2rexp(s))
}
implicit def string2rexp(s: String): Rexp = charlist2rexp(s.toList)

implicit def RexpOps (r: Rexp) = new {
  def | (s: Rexp) = ALT(r, s)
  def % = STAR(r)
  def ~ (s: Rexp) = SEQ(r, s)
}

implicit def stringOps (s: String) = new {
  def | (r: Rexp) = ALT(s, r)
  def | (r: String) = ALT(s, r)
  def % = STAR(s)
  def ~ (r: Rexp) = SEQ(s, r)
  def ~ (r: String) = SEQ(s, r)
}

// (1) Complete the function nullable according to
// the definition given in the coursework; this 
// function checks whether a regular expression
// can match the empty string and Returns a boolean
// accordingly.

//def nullable (r: Rexp) : Boolean = ...


// (2) Complete the function der according to
// the definition given in the coursework; this
// function calculates the derivative of a 
// regular expression w.r.t. a character.

//def der (c: Char, r: Rexp) : Rexp = ...


// (3) Complete the simp function according to
// the specification given in the coursework; this
// function simplifies a regular expression from
// the inside out, like you would simplify arithmetic 
// expressions; however it does not simplify inside 
// STAR-regular expressions.

//def simp(r: Rexp) : Rexp = ... 


// (4) Complete the two functions below; the first 
// calculates the derivative w.r.t. a string; the second
// is the regular expression matcher taking a regular
// expression and a string and checks whether the
// string matches the regular expression

//def ders (s: List[Char], r: Rexp) : Rexp = ... 

//def matcher(r: Rexp, s: String): Boolean = ...


// (5) Complete the size function for regular
// expressions according to the specification 
// given in the coursework.

//def size(r: Rexp): Int = ...


// some testing data

/*
matcher(("a" ~ "b") ~ "c", "abc")  // => true
matcher(("a" ~ "b") ~ "c", "ab")   // => false

// the supposedly 'evil' regular expression (a*)* b
val EVIL = SEQ(STAR(STAR(CHAR('a'))), CHAR('b'))

matcher(EVIL, "a" * 1000 ++ "b")   // => true
matcher(EVIL, "a" * 1000)          // => false

// size without simplifications
size(der('a', der('a', EVIL)))             // => 28
size(der('a', der('a', der('a', EVIL))))   // => 58

// size with simplification
size(simp(der('a', der('a', EVIL))))           // => 8
size(simp(der('a', der('a', der('a', EVIL))))) // => 8

// Java needs around 30 seconds for matching 28 a's with EVIL. 
//
// Lets see how long it really takes to match strings with 
// 0.5 Million a's...it should be in the range of some
// seconds.

def time_needed[T](i: Int, code: => T) = {
  val start = System.nanoTime()
  for (j <- 1 to i) code
  val end = System.nanoTime()
  (end - start)/(i * 1.0e9)
}

for (i <- 0 to 5000000 by 500000) {
  println(i + " " + "%.5f".format(time_needed(2, matcher(EVIL, "a" * i))))
}

*/