diff -r bc131735c940 -r 438459a8e48b testing4/re.scala --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/testing4/re.scala Thu Nov 22 17:35:30 2018 +0000 @@ -0,0 +1,159 @@ +// Part 1 about Regular Expression Matching +//========================================== + +object CW8a { + +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 +case class SEQ(r1: Rexp, r2: Rexp) extends Rexp +case class STAR(r: Rexp) extends Rexp + +// 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) +} + +// (1a) Complete the function nullable according to +// the definition given in the coursework; this +// function checks whether a regular expression +// can match the empty string + +def nullable (r: Rexp) : Boolean = r match { + case ZERO => false + case ONE => true + case CHAR(_) => false + case ALT(r1, r2) => nullable(r1) || nullable(r2) + case SEQ(r1, r2) => nullable(r1) && nullable(r2) + case STAR(_) => true +} + +// (1b) 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 = r match { + case ZERO => ZERO + case ONE => ZERO + case CHAR(d) => if (c == d) ONE else ZERO + case ALT(r1, r2) => ALT(der(c, r1), der(c, r2)) + case SEQ(r1, r2) => + if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2)) + else SEQ(der(c, r1), r2) + case STAR(r1) => SEQ(der(c, r1), STAR(r1)) +} + +// (1c) Complete the function der according to +// the specification given in the coursework; this +// function simplifies a regular expression; +// however it does not simplify inside STAR-regular +// expressions + +def simp(r: Rexp) : Rexp = r match { + case ALT(r1, r2) => (simp(r1), simp(r2)) match { + case (ZERO, r2s) => r2s + case (r1s, ZERO) => r1s + case (r1s, r2s) => if (r1s == r2s) r1s else ALT (r1s, r2s) + } + case SEQ(r1, r2) => (simp(r1), simp(r2)) match { + case (ZERO, _) => ZERO + case (_, ZERO) => ZERO + case (ONE, r2s) => r2s + case (r1s, ONE) => r1s + case (r1s, r2s) => SEQ(r1s, r2s) + } + case r => r +} + +// (1d) 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 = s match { + case Nil => r + case c::s => ders(s, simp(der(c, r))) +} + +// main matcher function +def matcher(r: Rexp, s: String): Boolean = nullable(ders(s.toList, r)) + +// (1e) Complete the size function for regular +// expressions according to the specification +// given in the coursework. + +def size(r: Rexp): Int = r match { + case ZERO => 1 + case ONE => 1 + case CHAR(_) => 1 + case ALT(r1, r2) => 1 + size(r1) + size (r2) + case SEQ(r1, r2) => 1 + size(r1) + size (r2) + case STAR(r1) => 1 + size(r1) +} + + + +// 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 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)))) +} +*/ + +}