lex.icl

   1 implementation module lex
   2
   3 import Control.Monad
   4 import Data.Either, Data.Maybe, Data.Map, Data.Func
   5 import StdString
   6 import StdTuple
   7 import StdBool
   8 import StdList
   9 import StdChar
  10
  11 SingleCharTokens :: Map Char Token
  12 SingleCharTokens = fromList [
  13         ('(', BraceOpenToken), (')', BraceCloseToken), ('{', CBraceOpenToken),
  14         ('}', CBraceCloseToken), ('[', SquareOpenToken), (']', SquareCloseToken),
  15         (',', CommaToken), (':', ColonToken), (';', SColonToken),
  16         ('.', DotToken), ('+', PlusToken), ('*', StarToken), ('/', SlashToken),
  17         ('%', PercentToken), ('=', AssignmentToken), ('<', LesserToken),
  18         ('>', BiggerToken), ('!', ExclamationToken)]
  19
  20 EscapeMap :: Map Char Char
  21 EscapeMap = fromList [('a', toChar 7), ('b', '\b'), ('f', '\f'), ('n', '\n'),
  22         ('r', '\r'), ('t', '\t'), ('v', '\v')]
  23
  24 lexer :: [Char] -> LexerOutput
  25 lexer [] = Right []
  26 lexer x = case lex x of
  27         (Right t, rest) = lexer rest >>= \ts.Right [t:ts]
  28         (Left e, _) = Left e
  29
  30 lex :: [Char] -> (Either String Token, [Char])
  31 lex [] = (Right EndOfFileToken, [])
  32 lex ['/':'/':xs] = lex $ dropWhile ((<>) '\n') xs
  33 lex ['/':'*':xs] =
  34         lex $ tl $ map snd $ dropWhile ((<>) ('*', '/')) $ zip2 [zero:xs] xs
  35 lex ['v':'a':'r':xs] = (Right VarToken, xs)
  36 lex ['V':'o':'i':'d':xs] = (Right VoidToken, xs)
  37 lex ['r':'e':'t':'u':'r':'n':xs] = (Right ReturnToken, xs)
  38 lex ['i':'f':xs] = (Right IfToken, xs)
  39 lex ['e':'l':'s':'e':xs] = (Right ElseToken, xs)
  40 lex ['w':'h':'i':'l':'e':xs] = (Right WhileToken, xs)
  41 lex ['T':'r':'u':'e':xs] = (Right TrueToken, xs)
  42 lex ['F':'a':'l':'s':'e':xs] = (Right FalseToken, xs)
  43 lex ['I':'n':'t':xs] = (Right IntTypeToken, xs)
  44 lex ['C':'h':'a':'r':xs] = (Right CharTypeToken, xs)
  45 lex ['B':'o':'o':'l':xs] = (Right BoolTypeToken, xs)
  46 lex [':':':':xs] = (Right DoubleColonToken, xs)
  47 lex ['!':'=':xs] = (Right NotEqualToken, xs)
  48 lex ['<':'=':xs] = (Right LesserEqToken, xs)
  49 lex ['>':'=':xs] = (Right GreaterEqToken, xs)
  50 lex ['=':'=':xs] = (Right EqualsToken, xs)
  51 lex ['&':'&':xs] = (Right AmpersandsToken, xs)
  52 lex ['|':'|':xs] = (Right PipesToken, xs)
  53 lex ['-':'>':xs] = (Right ArrowToken, xs)
  54 lex ['\'':x:'\'':xs] = (Right (CharToken x), xs)
  55 lex ['\'':'\\':x:'\'':xs] = case get x EscapeMap of
  56         Just t = (Right (CharToken t), xs)
  57         _ = (Left ("Unknown escape: \\" +++ toString x), [])
  58 lex ['-':t=:[x:xs]]
  59 | isDigit x = let (i, r) = span isDigit t in (Right (NumberToken ['-':i]), r)
  60 | otherwise = (Right DashToken, xs)
  61 lex t=:[x:xs] = case get x SingleCharTokens of
  62         (Just tok) = (Right tok, xs)
  63         Nothing
  64         | isSpace x = lex xs
  65         | isDigit x = let (i, r) = span isDigit t in (Right (NumberToken i), r)
  66         | isAlpha x = let (i, r) = span isIdent t in (Right (IdentToken i), r)
  67                 with isIdent c = isAlphanum c || c == '_'
  68         | otherwise = (Left ("Unexpected character: " +++ toString x), [])