-lexer _ = Left "Not Implemented"
-
-Start :: *World -> *World
-Start w
-# (args, w) = getCommandLine w // We lezen nu nog standaard van stdin
-# (out, w) = stdio w
-# (toparse, out) = readEntireFile out
-# out = out <<< toString (lexer toparse)
-# (b, w) = fclose out w
-| not b = setReturnCode 1 w
-= w
+lexer r = case runParser (lexProgram 1 1) r of
+ (Right p, _) = Right p
+ (Left e, _) = Left e
+
+lexProgram :: Int Int -> Parser Char [Token]
+lexProgram line column = lexToken >>= \t->case t of
+ LexEOF = pure []
+ (LexItemError e) = fail <?>
+ PositionalError line column ("LexerError: " +++ e)
+ (LexToken c t) = lexProgram line (column+c)
+ >>= \rest->pure [{line=line, column=column, token=t}:rest]
+ LexNL = lexProgram (line+1) 1
+ (LexSpace l c) = lexProgram (line+l) (column+c)
+
+:: LexItem
+ = LexToken Int TokenValue
+ | LexSpace Int Int
+ | LexNL
+ | LexEOF
+ | LexItemError String
+
+lexToken :: Parser Char LexItem
+lexToken =
+ //Comments
+ lexBlockComment <|> lexComment <|>
+ //Keyword tokens
+ lexKw "var" VarToken <|> lexKw "Void" VoidToken <|>
+ lexKw "return" ReturnToken <|> lexKw "if" IfToken <|>
+ lexKw "else" ElseToken <|> lexKw "while" WhileToken <|>
+ lexKw "True" TrueToken <|> lexKw "False" FalseToken <|>
+ lexKw "Int" IntTypeToken <|> lexKw "Bool" BoolTypeToken <|>
+ lexKw "Char" CharTypeToken <|>
+ //Character tokens
+ lexEscape <|> lexCharacter <|>
+ //Two char ops tokens
+ lexWord "::" DoubleColonToken <|> lexWord "!=" NotEqualToken <|>
+ lexWord "<=" LesserEqToken <|> lexWord ">=" GreaterEqToken <|>
+ lexWord "==" EqualsToken <|> lexWord "&&" AmpersandsToken <|>
+ lexWord "||" PipesToken <|> lexWord "[]" EmptyListToken <|>
+ lexWord "->" ArrowToken <|>
+ //One char ops tokens
+ lexWord "(" BraceOpenToken <|>
+ lexWord ")" BraceCloseToken <|> lexWord "{" CBraceOpenToken <|>
+ lexWord "}" CBraceCloseToken <|> lexWord "[" SquareOpenToken <|>
+ lexWord "]" SquareCloseToken <|> lexWord "," CommaToken <|>
+ lexWord ":" ColonToken <|> lexWord ";" SColonToken <|>
+ lexWord "." DotToken <|> lexWord "+" PlusToken <|>
+ lexWord "*" StarToken <|> lexWord "/" SlashToken <|>
+ lexWord "%" PercentToken <|> lexWord "=" AssignmentToken <|>
+ lexWord "<" LesserToken <|> lexWord ">" BiggerToken <|>
+ lexWord "!" ExclamationToken <|> lexWord "-" DashToken <|>
+ //Number and identifier tokens
+ lexNumber <|> lexIdentifier <|>
+ (item '\n' >>| pure LexNL) <|>
+ (satisfy isSpace >>| (pure $ LexSpace 0 1)) <|>
+ (eof >>| pure LexEOF)