diff -r 53f08d873e09 -r 7af2eea19646 solutions/cw4/lexer.sc --- a/solutions/cw4/lexer.sc Sun Sep 17 19:12:57 2023 +0100 +++ b/solutions/cw4/lexer.sc Tue Sep 19 09:54:41 2023 +0100 @@ -1,5 +1,5 @@ -import scala.language.implicitConversions -import scala.language.reflectiveCalls +// Lexer from CW2 with additions to the rules +//============================================ // Rexp abstract class Rexp @@ -27,7 +27,7 @@ case class Rec(x: String, v: Val) extends Val -// Convenience typing +// Convenience for typing def charlist2rexp(s : List[Char]): Rexp = s match { case Nil => ONE case c::Nil => CHAR(c) @@ -37,13 +37,13 @@ implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList) -implicit def RexpOps(r: Rexp) = new { +extension (r: Rexp) { def | (s: Rexp) = ALT(r, s) def % = STAR(r) def ~ (s: Rexp) = SEQ(r, s) } -implicit def stringOps(s: String) = new { +extension (s: String) { def | (r: Rexp) = ALT(s, r) def | (r: String) = ALT(s, r) def % = STAR(s) @@ -82,7 +82,7 @@ case RECD(_, r1) => der(c, r1) case RANGE(s) => if (s.contains(c)) ONE else ZERO case PLUS(r1) => SEQ(der(c, r1), STAR(r1)) - case OPTIONAL(r1) => ALT(der(c, r1), ZERO) + case OPTIONAL(r1) => der(c, r1) case NTIMES(r, i) => if (i == 0) ZERO else SEQ(der(c, r), NTIMES(r, i - 1)) } @@ -119,7 +119,7 @@ case RECD(x, r) => Rec(x, mkeps(r)) case PLUS(r) => Stars(List(mkeps(r))) // the first copy must match the empty string - case OPTIONAL(r) => Right(Empty) + case OPTIONAL(r) => if (nullable(r)) Stars(List(mkeps(r))) else Stars(Nil) case NTIMES(r, i) => Stars(List.fill(i)(mkeps(r))) } @@ -136,7 +136,7 @@ case (RANGE(_), Empty) => Chr(c) case (PLUS(r), Sequ(v1, Stars(vs))) => Stars(inj(r, c, v1)::vs) - case (OPTIONAL(r), Left(v1)) => Left(inj(r, c, v1)) + case (OPTIONAL(r), v1) => Stars(List(inj(r, c, v1))) case (NTIMES(r, n), Sequ(v1, Stars(vs))) => Stars(inj(r, c, v1)::vs) } @@ -199,20 +199,21 @@ def lexing_simp(r: Rexp, s: String) = env(lex_simp(r, s.toList)) // Language specific code -val KEYWORD : Rexp = "while" | "if" | "then" | "else" | "do" | "for" | "to" | "true" | "false" | "read" | "write" | "skip" +// Language specific code +val KEYWORD : Rexp = "while" | "if" | "then" | "else" | "do" | "for" | "upto" | "true" | "false" | "read" | "write" | "skip" | "break" val OP : Rexp = "+" | "-" | "*" | "%" | "/" | "==" | "!=" | ">" | "<" | ">=" | "<=" | ":=" | "&&" | "||" -val LET: Rexp = RANGE(('A' to 'Z').toSet ++ ('a' to 'z')) -val SYM : Rexp = LET | RANGE(Set('.', '_', '>', '<', '=', ';', ',', ':')) +val LET: Rexp = RANGE(('A' to 'Z').toSet ++ ('a' to 'z').toSet) +val SYM : Rexp = RANGE(Set('.', '_', '>', '<', '=', ';', ',', ':', ')', '(')) val PARENS : Rexp = "(" | "{" | ")" | "}" val SEMI : Rexp = ";" val WHITESPACE : Rexp = PLUS(" ") | "\n" | "\t" | "\r" val DIGIT : Rexp = RANGE(('0' to '9').toSet) val DIGIT1 : Rexp = RANGE(('1' to '9').toSet) -val STRING : Rexp = "\"" ~ (SYM | " " | "\\n" | DIGIT).% ~ "\"" +val STRING : Rexp = "\"" ~ (LET | SYM | DIGIT | " " | "\\n").% ~ "\"" val ID : Rexp = LET ~ (LET | "_" | DIGIT).% val NUM : Rexp = "0" | (DIGIT1 ~ DIGIT.%) val EOL : Rexp = "\n" | "\r\n" -val COMMENT : Rexp = "//" ~ (SYM | PARENS | " " | DIGIT).% ~ EOL +val COMMENT : Rexp = "//" ~ (LET | SYM | PARENS | " " | DIGIT).% ~ EOL val WHILE_REGS = (("k" $ KEYWORD) | ("o" $ OP) | @@ -224,6 +225,8 @@ ("n" $ NUM) | ("c" $ COMMENT)).% + + // Token abstract class Token extends Serializable case class T_KEYWORD(s: String) extends Token