stub voor parsen gemaakt

[cc1516.git] / lex.icl

diff --git a/lex.icl b/lex.icl
index 0b6272c..e2d679a 100644 (file)
--- a/lex.icl
+++ b/lex.icl
@@ -1,30 +1,25 @@
 implementation module lex
 
 import Control.Monad
-import Data.Either
-import Data.Maybe
-import Data.Map
+import Data.Either, Data.Maybe, Data.Map, Data.Func
 import StdString
+import StdTuple
 import StdBool
 import StdList
 import StdChar
-import StdFile
-import System.CommandLine
-import qualified Text
 
 SingleCharTokens :: Map Char Token
 SingleCharTokens = fromList [
        ('(', BraceOpenToken), (')', BraceCloseToken), ('{', CBraceOpenToken),
        ('}', CBraceCloseToken), ('[', SquareOpenToken), (']', SquareCloseToken),
        (',', CommaToken), (':', ColonToken), (';', SColonToken),
-       ('.', DotToken), ('+', PlusToken), ('-', DashToken), ('*', StarToken),
-       ('/', SlashToken), ('%', PercentToken), ('=', AssignmentToken),
-       ('<', LesserToken), ('>', BiggerToken), ('!', ExclamationToken)]
+       ('.', DotToken), ('+', PlusToken), ('*', StarToken), ('/', SlashToken),
+       ('%', PercentToken), ('=', AssignmentToken), ('<', LesserToken),
+       ('>', BiggerToken), ('!', ExclamationToken)]
 
 EscapeMap :: Map Char Char
-EscapeMap = fromList [
-       ('a', toChar 7), ('b', '\b'), ('f', '\f'), ('n', '\n'), ('r', '\r'),
-       ('t', '\t'), ('v', '\v')]
+EscapeMap = fromList [('a', toChar 7), ('b', '\b'), ('f', '\f'), ('n', '\n'),
+       ('r', '\r'), ('t', '\t'), ('v', '\v')]
 
 lexer :: [Char] -> LexerOutput
 lexer [] = Right []
@@ -34,43 +29,40 @@ lexer x = case lex x of
 
 lex :: [Char] -> (Either String Token, [Char])
 lex [] = (Right EndOfFileToken, [])
-//Comments
-lex ['/':'/':x:rest] = if (x == '\n') (lex rest) (lex ['/':'/':rest])
-lex ['/':'*':x1:x2:rest] = if (x1 == '*' && x2 == '/') 
-       (lex rest) (lex ['/':'*':rest])
-//Keyword tokens
-lex ['v':'a':'r':rest] = (Right VarToken, rest)
-lex ['V':'o':'i':'d':rest] = (Right VoidToken, rest)
-lex ['r':'e':'t':'u':'r':'n':rest] = (Right ReturnToken, rest)
-lex ['i':'f':rest] = (Right IfToken, rest)
-lex ['e':'l':'s':'e':rest] = (Right ElseToken, rest)
-lex ['w':'h':'i':'l':'e':rest] = (Right WhileToken, rest)
-lex ['T':'r':'u':'e':rest] = (Right TrueToken, rest)
-lex ['F':'a':'l':'s':'e':rest] = (Right FalseToken, rest)
-lex ['I':'n':'t':rest] = (Right IntTypeToken, rest)
-lex ['C':'h':'a':'r':rest] = (Right CharTypeToken, rest)
-lex ['B':'o':'o':'l':rest] = (Right BoolTypeToken, rest)
-//Two character tokens
-lex [':':':':rest] = (Right DoubleColonToken, rest)
-lex ['!':'=':rest] = (Right NotEqualToken, rest)
-lex ['<':'=':rest] = (Right LesserEqToken, rest)
-lex ['>':'=':rest] = (Right GreaterEqToken, rest)
-lex ['=':'=':rest] = (Right EqualsToken, rest)
-lex ['&':'&':rest] = (Right AmpersandsToken, rest)
-lex ['|':'|':rest] = (Right PipesToken, rest)
-lex ['-':'>':rest] = (Right ArrowToken, rest)
-//One character tokens
-//Value tokens
-lex ['\'':x:'\'':rest] = (Right (CharToken x), rest)
-lex ['\'':'\\':x:'\'':rest] = case get x EscapeMap of
-       Just t = (Right (CharToken t), rest)
+lex ['/':'/':xs] = lex $ dropWhile ((<>) '\n') xs
+lex ['/':'*':xs] =
+       lex $ tl $ map snd $ dropWhile ((<>) ('*', '/')) $ zip2 [zero:xs] xs
+lex ['v':'a':'r':xs] = (Right VarToken, xs)
+lex ['V':'o':'i':'d':xs] = (Right VoidToken, xs)
+lex ['r':'e':'t':'u':'r':'n':xs] = (Right ReturnToken, xs)
+lex ['i':'f':xs] = (Right IfToken, xs)
+lex ['e':'l':'s':'e':xs] = (Right ElseToken, xs)
+lex ['w':'h':'i':'l':'e':xs] = (Right WhileToken, xs)
+lex ['T':'r':'u':'e':xs] = (Right TrueToken, xs)
+lex ['F':'a':'l':'s':'e':xs] = (Right FalseToken, xs)
+lex ['I':'n':'t':xs] = (Right IntTypeToken, xs)
+lex ['C':'h':'a':'r':xs] = (Right CharTypeToken, xs)
+lex ['B':'o':'o':'l':xs] = (Right BoolTypeToken, xs)
+lex [':':':':xs] = (Right DoubleColonToken, xs)
+lex ['!':'=':xs] = (Right NotEqualToken, xs)
+lex ['<':'=':xs] = (Right LesserEqToken, xs)
+lex ['>':'=':xs] = (Right GreaterEqToken, xs)
+lex ['=':'=':xs] = (Right EqualsToken, xs)
+lex ['&':'&':xs] = (Right AmpersandsToken, xs)
+lex ['|':'|':xs] = (Right PipesToken, xs)
+lex ['-':'>':xs] = (Right ArrowToken, xs)
+lex ['\'':x:'\'':xs] = (Right (CharToken x), xs)
+lex ['\'':'\\':x:'\'':xs] = case get x EscapeMap of
+       Just t = (Right (CharToken t), xs)
        _ = (Left ("Unknown escape: \\" +++ toString x), [])
-lex [x:rest]
-# t = get x SingleCharTokens
-| isJust t = (Right (fromJust t), rest)
-| isSpace x = lex rest
-| isDigit x = let (is, rest`) = span isDigit rest in
-       (Right (NumberToken [x:is]), rest`)
-| isAlpha x = let (is, rest`) = span (\c.isAlphanum c || c == '_') rest in
-       (Right (IdentToken [x:is]), rest`)
-| otherwise = (Left ("Unexpected character: " +++ toString x), [])
+lex ['-':t=:[x:xs]]
+| isDigit x = let (i, r) = span isDigit t in (Right (NumberToken ['-':i]), r)
+| otherwise = (Right DashToken, xs)
+lex t=:[x:xs] = case get x SingleCharTokens of
+       (Just tok) = (Right tok, xs)
+       Nothing
+       | isSpace x = lex xs
+       | isDigit x = let (i, r) = span isDigit t in (Right (NumberToken i), r)
+       | isAlpha x = let (i, r) = span isIdent t in (Right (IdentToken i), r)
+               with isIdent c = isAlphanum c || c == '_'
+       | otherwise = (Left ("Unexpected character: " +++ toString x), [])