module Text.Highlighting.Kate.Syntax.Haskell ( highlight, parseExpression, syntaxName, syntaxExtensions ) where
import Text.Highlighting.Kate.Definitions
import Text.Highlighting.Kate.Common
import Text.ParserCombinators.Parsec
import Control.Monad (when)
import Data.Map (fromList)
import Data.Maybe (fromMaybe, maybeToList)
import qualified Data.Set as Set
syntaxName :: String
syntaxName = "Haskell"
syntaxExtensions :: String
syntaxExtensions = "*.hs"
highlight :: String -> Either String [SourceLine]
highlight input =
case runParser parseSource startingState "source" input of
Left err -> Left $ show err
Right result -> Right result
parseExpression :: GenParser Char SyntaxState LabeledSource
parseExpression = do
st <- getState
let oldLang = synStLanguage st
setState $ st { synStLanguage = "Haskell" }
context <- currentContext <|> (pushContext "code" >> currentContext)
result <- parseRules context
updateState $ \st -> st { synStLanguage = oldLang }
return result
parseSource = do
lineContents <- lookAhead wholeLine
updateState $ \st -> st { synStCurrentLine = lineContents }
result <- manyTill parseSourceLine eof
return $ map normalizeHighlighting result
startingState = SyntaxState {synStContexts = fromList [("Haskell",["code"])], synStLanguage = "Haskell", synStCurrentLine = "", synStCharsParsedInLine = 0, synStPrevChar = '\n', synStCaseSensitive = True, synStKeywordCaseSensitive = True, synStCaptures = []}
parseSourceLine = manyTill parseExpressionInternal pEndLine
pEndLine = do
lookAhead $ newline <|> (eof >> return '\n')
context <- currentContext
case context of
"code" -> return () >> pHandleEndLine
"comment" -> (popContext) >> pEndLine
"comments" -> return () >> pHandleEndLine
"char" -> (popContext) >> pEndLine
"string" -> return () >> pHandleEndLine
"infix" -> return () >> pHandleEndLine
_ -> pHandleEndLine
withAttribute attr txt = do
when (null txt) $ fail "Parser matched no text"
let labs = attr : maybeToList (lookup attr styles)
st <- getState
let oldCharsParsed = synStCharsParsedInLine st
let prevchar = if null txt then '\n' else last txt
updateState $ \st -> st { synStCharsParsedInLine = oldCharsParsed + length txt, synStPrevChar = prevchar }
return (labs, txt)
styles = [("Comment","co"),("Pragma","ot"),("Keyword","kw"),("Type Prelude","dt"),("Function Prelude","fu"),("Data Prelude","kw"),("Class Prelude","kw"),("Signature","ot"),("Operator","fu"),("Type","dt"),("Special","ot"),("Decimal","dv"),("Float","fl"),("Char","ch"),("String","st"),("Function Infix","ot"),("EnumFromTo","ot")]
parseExpressionInternal = do
context <- currentContext
parseRules context <|> (pDefault >>= withAttribute (fromMaybe "" $ lookup context defaultAttributes))
list_keywords = Set.fromList $ words $ "as case class data deriving do else hiding if import in infixl infixr instance let module newtype of primitive qualified then type where"
list_prelude_function = Set.fromList $ words $ "FilePath IOError abs acos acosh all and any appendFile approxRational asTypeOf asin asinh atan atan2 atanh basicIORun break catch ceiling chr compare concat concatMap const cos cosh curry cycle decodeFloat denominator digitToInt div divMod drop dropWhile either elem encodeFloat enumFrom enumFromThen enumFromThenTo enumFromTo error even exp exponent fail filter flip floatDigits floatRadix floatRange floor fmap foldl foldl1 foldr foldr1 fromDouble fromEnum fromInt fromInteger fromIntegral fromRational fst gcd getChar getContents getLine group head id inRange index init intToDigit interact ioError isAlpha isAlphaNum isAscii isControl isDenormalized isDigit isHexDigit isIEEE isInfinite isLower isNaN isNegativeZero isOctDigit isPrint isSpace isUpper iterate last lcm length lex lexDigits lexLitChar lines log logBase lookup map mapM mapM_ max maxBound maximum maybe min minBound minimum mod negate not notElem null numerator odd or ord otherwise pack pi pred primExitWith print product properFraction putChar putStr putStrLn quot quotRem range rangeSize read readDec readFile readFloat readHex readIO readInt readList readLitChar readLn readOct readParen readSigned reads readsPrec realToFrac recip rem repeat replicate return reverse round scaleFloat scanl scanl1 scanr scanr1 seq sequence sequence_ show showChar showInt showList showLitChar showParen showSigned showString shows showsPrec significand signum sin sinh snd sort span splitAt sqrt subtract succ sum tail take takeWhile tan tanh threadToIOResult toEnum toInt toInteger toLower toRational toUpper truncate uncurry undefined unlines until unwords unzip unzip3 userError words writeFile zip zip3 zipWith zipWith3"
list_prelude_class = Set.fromList $ words $ "Bounded Enum Eq Floating Fractional Functor Integral Ix Monad Num Ord Read Real RealFloat RealFrac Show"
list_prelude_type = Set.fromList $ words $ "Bool Char Double Either FilePath Float Int Integer IO IOError Maybe Ordering Ratio Rational ReadS ShowS String ByteString"
list_prelude_data = Set.fromList $ words $ "False True Left Right Just Nothing EQ LT GT"
regex_'5c'7b'2d'23'2e'2a'23'2d'5c'7d = compileRegex "\\{-#.*#-\\}"
regex_'5c'7b'2d'5b'5e'23'5d'3f = compileRegex "\\{-[^#]?"
regex_'2d'2d'5b'5e'5c'2d'21'23'5c'24'25'26'5c'2a'5c'2b'2f'3c'3d'3e'5c'3f'5c'40'5c'5e'5c'7c'7e'5c'2e'3a'5d'2e'2a'24 = compileRegex "--[^\\-!#\\$%&\\*\\+/<=>\\?\\@\\^\\|~\\.:].*$"
regex_'28'3a'3a'7c'3d'3e'7c'5c'2d'3e'7c'3c'5c'2d'29 = compileRegex "(::|=>|\\->|<\\-)"
regex_'5cs'2a'5ba'2dz'5d'5ba'2dzA'2dZ0'2d9'5f'27'5d'2a'5cs'2a'28'3f'3d'3a'3a'5b'5e'5c'2d'21'23'5c'24'25'26'5c'2a'5c'2b'2f'3c'3d'3e'5c'3f'5c'40'5c'5e'5c'7c'7e'5c'2e'3a'5d'29 = compileRegex "\\s*[a-z][a-zA-Z0-9_']*\\s*(?=::[^\\-!#\\$%&\\*\\+/<=>\\?\\@\\^\\|~\\.:])"
regex_'5cs'2a'28'5c'28'5b'5c'2d'21'23'5c'24'25'26'5c'2a'5c'2b'2f'3c'3d'3e'5c'3f'5c'40'5c'5e'5c'7c'7e'5c'2e'3a'5d'2a'5c'29'29'2a'5cs'2a'28'3f'3d'3a'3a'5b'5e'5c'2d'21'23'5c'24'25'26'5c'2a'5c'2b'2f'3c'3d'3e'5c'3f'5c'40'5c'5e'5c'7c'7e'5c'2e'3a'5d'29 = compileRegex "\\s*(\\([\\-!#\\$%&\\*\\+/<=>\\?\\@\\^\\|~\\.:]*\\))*\\s*(?=::[^\\-!#\\$%&\\*\\+/<=>\\?\\@\\^\\|~\\.:])"
regex_'28'5bA'2dZ'5d'5ba'2dzA'2dZ0'2d9'5f'27'5d'2a'5c'2e'29'2a'5ba'2dz'5d'5ba'2dzA'2dZ0'2d9'5f'27'5d'2a = compileRegex "([A-Z][a-zA-Z0-9_']*\\.)*[a-z][a-zA-Z0-9_']*"
regex_'28'5bA'2dZ'5d'5ba'2dzA'2dZ0'2d0'5f'27'5d'2a'5c'2e'29'2a'5b'5c'2d'21'23'5c'24'25'26'5c'2a'5c'2b'2f'3c'3d'3e'5c'3f'5c'40'5c'5e'5c'7c'7e'5c'2e'3a'5d'2b = compileRegex "([A-Z][a-zA-Z0-0_']*\\.)*[\\-!#\\$%&\\*\\+/<=>\\?\\@\\^\\|~\\.:]+"
regex_'28'5bA'2dZ'5d'5ba'2dzA'2dZ0'2d9'5f'27'5d'2a'5c'2e'29'2a'5bA'2dZ'5d'5ba'2dzA'2dZ0'2d9'5f'27'5d'2a = compileRegex "([A-Z][a-zA-Z0-9_']*\\.)*[A-Z][a-zA-Z0-9_']*"
regex_'5cd'2b'5c'2e'5cd'2b = compileRegex "\\d+\\.\\d+"
regex_'5c'5c'2e = compileRegex "\\\\."
defaultAttributes = [("code","Normal"),("comment","Comment"),("comments","Comment"),("char","Char"),("string","String"),("infix","Function Infix")]
parseRules "code" =
do (attr, result) <- (((pRegExpr regex_'5c'7b'2d'23'2e'2a'23'2d'5c'7d >>= withAttribute "Pragma"))
<|>
((pRegExpr regex_'5c'7b'2d'5b'5e'23'5d'3f >>= withAttribute "Comment") >>~ pushContext "comments")
<|>
((pRegExpr regex_'2d'2d'5b'5e'5c'2d'21'23'5c'24'25'26'5c'2a'5c'2b'2f'3c'3d'3e'5c'3f'5c'40'5c'5e'5c'7c'7e'5c'2e'3a'5d'2e'2a'24 >>= withAttribute "Comment") >>~ pushContext "comment")
<|>
((pKeyword " \n\t.():!+,-<=>%&*/;?[]^{|}~\\" list_keywords >>= withAttribute "Keyword"))
<|>
((pKeyword " \n\t.():!+,-<=>%&*/;?[]^{|}~\\" list_prelude_function >>= withAttribute "Function Prelude"))
<|>
((pKeyword " \n\t.():!+,-<=>%&*/;?[]^{|}~\\" list_prelude_type >>= withAttribute "Type Prelude"))
<|>
((pKeyword " \n\t.():!+,-<=>%&*/;?[]^{|}~\\" list_prelude_data >>= withAttribute "Data Prelude"))
<|>
((pKeyword " \n\t.():!+,-<=>%&*/;?[]^{|}~\\" list_prelude_class >>= withAttribute "Class Prelude"))
<|>
((pRegExpr regex_'28'3a'3a'7c'3d'3e'7c'5c'2d'3e'7c'3c'5c'2d'29 >>= withAttribute "Special"))
<|>
((pAnyChar "\8759\8658\8594\8592\8704\8707" >>= withAttribute "Special"))
<|>
((pRegExpr regex_'5cs'2a'5ba'2dz'5d'5ba'2dzA'2dZ0'2d9'5f'27'5d'2a'5cs'2a'28'3f'3d'3a'3a'5b'5e'5c'2d'21'23'5c'24'25'26'5c'2a'5c'2b'2f'3c'3d'3e'5c'3f'5c'40'5c'5e'5c'7c'7e'5c'2e'3a'5d'29 >>= withAttribute "Signature"))
<|>
((pRegExpr regex_'5cs'2a'28'5c'28'5b'5c'2d'21'23'5c'24'25'26'5c'2a'5c'2b'2f'3c'3d'3e'5c'3f'5c'40'5c'5e'5c'7c'7e'5c'2e'3a'5d'2a'5c'29'29'2a'5cs'2a'28'3f'3d'3a'3a'5b'5e'5c'2d'21'23'5c'24'25'26'5c'2a'5c'2b'2f'3c'3d'3e'5c'3f'5c'40'5c'5e'5c'7c'7e'5c'2e'3a'5d'29 >>= withAttribute "Signature"))
<|>
((pRegExpr regex_'28'5bA'2dZ'5d'5ba'2dzA'2dZ0'2d9'5f'27'5d'2a'5c'2e'29'2a'5ba'2dz'5d'5ba'2dzA'2dZ0'2d9'5f'27'5d'2a >>= withAttribute "Function"))
<|>
((pRegExpr regex_'28'5bA'2dZ'5d'5ba'2dzA'2dZ0'2d0'5f'27'5d'2a'5c'2e'29'2a'5b'5c'2d'21'23'5c'24'25'26'5c'2a'5c'2b'2f'3c'3d'3e'5c'3f'5c'40'5c'5e'5c'7c'7e'5c'2e'3a'5d'2b >>= withAttribute "Operator"))
<|>
((pRegExpr regex_'28'5bA'2dZ'5d'5ba'2dzA'2dZ0'2d9'5f'27'5d'2a'5c'2e'29'2a'5bA'2dZ'5d'5ba'2dzA'2dZ0'2d9'5f'27'5d'2a >>= withAttribute "Type"))
<|>
((pInt >>= withAttribute "Decimal"))
<|>
((pRegExpr regex_'5cd'2b'5c'2e'5cd'2b >>= withAttribute "Float"))
<|>
((pDetectChar False '\'' >>= withAttribute "Char") >>~ pushContext "char")
<|>
((pDetectChar False '"' >>= withAttribute "String") >>~ pushContext "string")
<|>
((pDetectChar False '`' >>= withAttribute "Function Infix") >>~ pushContext "infix")
<|>
((pDetect2Chars False '.' '.' >>= withAttribute "EnumFromTo"))
<|>
((pAnyChar "\8229" >>= withAttribute "EnumFromTo")))
return (attr, result)
parseRules "comment" =
pzero
parseRules "comments" =
do (attr, result) <- ((pDetect2Chars False '-' '}' >>= withAttribute "Comment") >>~ (popContext))
return (attr, result)
parseRules "char" =
do (attr, result) <- (((pRegExpr regex_'5c'5c'2e >>= withAttribute "Char"))
<|>
((pDetectChar False '\'' >>= withAttribute "Char") >>~ (popContext)))
return (attr, result)
parseRules "string" =
do (attr, result) <- (((pRegExpr regex_'5c'5c'2e >>= withAttribute "String"))
<|>
((pDetectChar False '"' >>= withAttribute "String") >>~ (popContext)))
return (attr, result)
parseRules "infix" =
do (attr, result) <- ((pDetectChar False '`' >>= withAttribute "Function Infix") >>~ (popContext))
return (attr, result)
parseRules x = fail $ "Unknown context" ++ x