{-# LINE 1 "templates/wrappers.hs" #-} -- ----------------------------------------------------------------------------- -- Alex wrapper code. -- -- This code is in the PUBLIC DOMAIN; you may copy it freely and use -- it for any purpose whatsoever. import Data.Word (Word8) import Data.Char (ord) import qualified Data.Bits -- | Encode a Haskell String to a list of Word8 values, in UTF8 format. utf8Encode :: Char -> [Word8] utf8Encode = uncurry (:) . utf8Encode' utf8Encode' :: Char -> (Word8, [Word8]) utf8Encode' c = case go (ord c) of (x, xs) -> (fromIntegral x, map fromIntegral xs) where go oc | oc <= 0x7f = ( oc , [ ]) | oc <= 0x7ff = ( 0xc0 + (oc `Data.Bits.shiftR` 6) , [0x80 + oc Data.Bits..&. 0x3f ]) | oc <= 0xffff = ( 0xe0 + (oc `Data.Bits.shiftR` 12) , [0x80 + ((oc `Data.Bits.shiftR` 6) Data.Bits..&. 0x3f) , 0x80 + oc Data.Bits..&. 0x3f ]) | otherwise = ( 0xf0 + (oc `Data.Bits.shiftR` 18) , [0x80 + ((oc `Data.Bits.shiftR` 12) Data.Bits..&. 0x3f) , 0x80 + ((oc `Data.Bits.shiftR` 6) Data.Bits..&. 0x3f) , 0x80 + oc Data.Bits..&. 0x3f ]) type Byte = Word8 -- ----------------------------------------------------------------------------- -- The input type -- ----------------------------------------------------------------------------- -- Token positions -- `Posn' records the location of a token in the input text. It has three -- fields: the address (number of chacaters preceding the token), line number -- and column of a token within the file. `start_pos' gives the position of the -- start of the file and `eof_pos' a standard encoding for the end of file. -- `move_pos' calculates the new position after traversing a given character, -- assuming the usual eight character tab stops. -- ----------------------------------------------------------------------------- -- Monad (default and with ByteString input) -- ----------------------------------------------------------------------------- -- Basic wrapper type AlexInput = (Char,[Byte],String) alexInputPrevChar :: AlexInput -> Char alexInputPrevChar (c,_,_) = c -- alexScanTokens :: String -> [token] alexScanTokens str = go ('\n',[],str) where go inp__@(_,_bs,s) = case alexScan inp__ 0 of AlexEOF -> [] AlexError _ -> error "lexical error" AlexSkip inp__' _ln -> go inp__' AlexToken inp__' len act -> act (take len s) : go inp__' alexGetByte :: AlexInput -> Maybe (Byte,AlexInput) alexGetByte (c,(b:bs),s) = Just (b,(c,bs,s)) alexGetByte (_,[],[]) = Nothing alexGetByte (_,[],(c:s)) = case utf8Encode' c of (b, bs) -> Just (b, (c, bs, s)) -- ----------------------------------------------------------------------------- -- Basic wrapper, ByteString version -- ----------------------------------------------------------------------------- -- Posn wrapper -- Adds text positions to the basic model. -- ----------------------------------------------------------------------------- -- Posn wrapper, ByteString version -- ----------------------------------------------------------------------------- -- GScan wrapper -- For compatibility with previous versions of Alex, and because we can.