diff -r a80f0cf17f91 -r 5988e44ea048 matcher.scala
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/matcher.scala	Wed Nov 14 08:45:30 2012 +0000
@@ -0,0 +1,100 @@
+
+// regular expressions including NOT
+abstract class Rexp
+
+case object NULL extends Rexp
+case object EMPTY 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
+case class NOT(r: Rexp) extends Rexp
+
+
+// some convenience for typing in regular expressions
+def charlist2rexp(s : List[Char]) : Rexp = s match {
+  case Nil => EMPTY
+  case c::Nil => CHAR(c)
+  case c::s => SEQ(CHAR(c), charlist2rexp(s))
+}
+implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
+
+
+// nullable function: tests whether the regular 
+// expression can recognise the empty string
+def nullable (r: Rexp) : Boolean = r match {
+  case NULL => false
+  case EMPTY => true
+  case CHAR(_) => false
+  case ALT(r1, r2) => nullable(r1) || nullable(r2)
+  case SEQ(r1, r2) => nullable(r1) && nullable(r2)
+  case STAR(_) => true
+  case NOT(r) => !(nullable(r))
+}
+
+// tests whether a regular expression 
+// cannot recognise more
+def no_more (r: Rexp) : Boolean = r match {
+  case NULL => true
+  case EMPTY => false
+  case CHAR(_) => false
+  case ALT(r1, r2) => no_more(r1) && no_more(r2)
+  case SEQ(r1, r2) => if (nullable(r1)) (no_more(r1) && no_more(r2)) else no_more(r1)
+  case STAR(_) => false
+  case NOT(r) => !(no_more(r))
+}
+
+
+// derivative of a regular expression w.r.t. a character
+def der (c: Char, r: Rexp) : Rexp = r match {
+  case NULL => NULL
+  case EMPTY => NULL  case CHAR(d) => if (c == d) EMPTY else NULL
+  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(r) => SEQ(der(c, r), STAR(r))
+  case NOT(r) => NOT(der (c, r))
+}
+
+// regular expression for specifying 
+// ranges of characters
+def RANGE(s : List[Char]) : Rexp = s match {
+  case Nil => NULL
+  case c::Nil => CHAR(c)
+  case c::s => ALT(CHAR(c), RANGE(s))
+}
+
+// one or more
+def PLUS(r: Rexp) = SEQ(r, STAR(r))
+
+
+type Rule[T] = (Rexp, List[Char] => T)
+
+def error (s: String) = throw new IllegalArgumentException ("Cannot tokenize: " + s)
+
+def munch[T](r: Rexp, action: List[Char] => T, s: List[Char], t: List[Char]) : Option[(List[Char], T)] = 
+  s match {
+    case Nil if (nullable(r)) => Some(Nil, action(t))
+    case Nil => None
+    case c::s if (no_more(der (c, r)) && nullable(r)) => Some(c::s, action(t))
+    case c::s if (no_more(der (c, r))) => None
+    case c::s => munch(der (c, r), action, s, t ::: List(c))
+  }
+
+def one_token[T](rs: List[Rule[T]], s: List[Char]) : (List[Char], T) = {
+ val somes = rs.map { (r) => munch(r._1, r._2, s, Nil) } .flatten
+ if (somes == Nil) error(s.mkString) else (somes sortBy (_._1.length) head)
+}
+
+def tokenize[T](rs: List[Rule[T]], s: List[Char]) : List[T] = s match {
+  case Nil => Nil
+  case _ => one_token(rs, s) match {
+    case (rest, token) => token :: tokenize(rs, rest) 
+  }
+}
+
+
+
+
+