source: branches/2.2/plugins/LocalFilesEditor/codemirror/mode/haskell/haskell.js @ 10310

CodeMirror.defineMode("haskell", function(cmCfg, modeCfg) {

  function switchState(source, setState, f) {
    setState(f);
    return f(source, setState);
  }
  
  // These should all be Unicode extended, as per the Haskell 2010 report
  var smallRE = /[a-z_]/;
  var largeRE = /[A-Z]/;
  var digitRE = /[0-9]/;
  var hexitRE = /[0-9A-Fa-f]/;
  var octitRE = /[0-7]/;
  var idRE = /[a-z_A-Z0-9']/;
  var symbolRE = /[-!#$%&*+.\/<=>?@\\^|~:]/;
  var specialRE = /[(),;[\]`{}]/;
  var whiteCharRE = /[ \t\v\f]/; // newlines are handled in tokenizer
    
  function normal(source, setState) {
    if (source.eatWhile(whiteCharRE)) {
      return null;
    }
      
    var ch = source.next();
    if (specialRE.test(ch)) {
      if (ch == '{' && source.eat('-')) {
        var t = "hs-comment";
        if (source.eat('#')) {
          t = "hs-pragma";
        }
        return switchState(source, setState, ncomment(t, 1));
      }
      return "hs-special";
    }
    
    if (ch == '\'') {
      if (source.eat('\\')) {
        source.next();  // should handle other escapes here
      }
      else {
        source.next();
      }
      if (source.eat('\'')) {
        return "hs-char";
      }
      return "hs-error";
    }
    
    if (ch == '"') {
      return switchState(source, setState, stringLiteral);
    }
      
    if (largeRE.test(ch)) {
      source.eatWhile(idRE);
      if (source.eat('.')) {
        return "hs-qualifier";
      }
      return "hs-conid";
    }
      
    if (smallRE.test(ch)) {
      source.eatWhile(idRE);
      return "hs-varid";
    }
      
    if (digitRE.test(ch)) {
      if (ch == '0') {
        if (source.eat(/[xX]/)) {
          source.eatWhile(hexitRE); // should require at least 1
          return "hs-integer";
        }
        if (source.eat(/[oO]/)) {
          source.eatWhile(octitRE); // should require at least 1
          return "hs-integer";
        }
      }
      source.eatWhile(digitRE);
      var t = "hs-integer";
      if (source.eat('.')) {
        t = "hs-float";
        source.eatWhile(digitRE); // should require at least 1
      }
      if (source.eat(/[eE]/)) {
        t = "hs-float";
        source.eat(/[-+]/);
        source.eatWhile(digitRE); // should require at least 1
      }
      return t;
    }
      
    if (symbolRE.test(ch)) {
      if (ch == '-' && source.eat(/-/)) {
        source.eatWhile(/-/);
        if (!source.eat(symbolRE)) {
          source.skipToEnd();
          return "hs-comment";
        }
      }
      var t = "hs-varsym";
      if (ch == ':') {
        t = "hs-consym";
      }
      source.eatWhile(symbolRE);
      return t;    
    }
      
    return "hs-error";
  }
    
  function ncomment(type, nest) {
    if (nest == 0) {
      return normal;
    }
    return function(source, setState) {
      var currNest = nest;
      while (!source.eol()) {
        ch = source.next();
        if (ch == '{' && source.eat('-')) {
          ++currNest;
        }
        else if (ch == '-' && source.eat('}')) {
          --currNest;
          if (currNest == 0) {
            setState(normal);
            return type;
          }
        }
      }
      setState(ncomment(type, currNest));
      return type;
    }
  }
    
  function stringLiteral(source, setState) {
    while (!source.eol()) {
      var ch = source.next();
      if (ch == '"') {
        setState(normal);
        return "hs-string";
      }
      if (ch == '\\') {
        if (source.eol() || source.eat(whiteCharRE)) {
          setState(stringGap);
          return "hs-string";
        }
        if (source.eat('&')) {
        }
        else {
          source.next(); // should handle other escapes here
        }
      }
    }
    setState(normal);
    return "hs-error";
  }
  
  function stringGap(source, setState) {
    if (source.eat('\\')) {
      return switchState(source, setState, stringLiteral);
    }
    source.next();
    setState(normal);
    return "hs-error";
  }
  
  
  var wellKnownWords = (function() {
    var wkw = {};
    function setType(t) {
      return function () {
        for (var i = 0; i < arguments.length; i++)
          wkw[arguments[i]] = t;
      }
    }
    
    setType("hs-reservedid")(
      "case", "class", "data", "default", "deriving", "do", "else", "foreign",
      "if", "import", "in", "infix", "infixl", "infixr", "instance", "let",
      "module", "newtype", "of", "then", "type", "where", "_");
      
    setType("hs-reservedop")(
      "\.\.", ":", "::", "=", "\\", "\"", "<-", "->", "@", "~", "=>");
      
    setType("hs-prelude-varsym")(
      "!!", "$!", "$", "&&", "+", "++", "-", ".", "/", "/=", "<", "<=", "=<<",
      "==", ">", ">=", ">>", ">>=", "^", "^^", "||", "*", "**");
      
    setType("hs-prelude-conid")(
      "Bool", "Bounded", "Char", "Double", "EQ", "Either", "Enum", "Eq",
      "False", "FilePath", "Float", "Floating", "Fractional", "Functor", "GT",
      "IO", "IOError", "Int", "Integer", "Integral", "Just", "LT", "Left",
      "Maybe", "Monad", "Nothing", "Num", "Ord", "Ordering", "Rational", "Read",
      "ReadS", "Real", "RealFloat", "RealFrac", "Right", "Show", "ShowS",
      "String", "True");
      
    setType("hs-prelude-varid")(
      "abs", "acos", "acosh", "all", "and", "any", "appendFile", "asTypeOf",
      "asin", "asinh", "atan", "atan2", "atanh", "break", "catch", "ceiling",
      "compare", "concat", "concatMap", "const", "cos", "cosh", "curry",
      "cycle", "decodeFloat", "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", "fromEnum", "fromInteger",
      "fromIntegral", "fromRational", "fst", "gcd", "getChar", "getContents",
      "getLine", "head", "id", "init", "interact", "ioError", "isDenormalized",
      "isIEEE", "isInfinite", "isNaN", "isNegativeZero", "iterate", "last",
      "lcm", "length", "lex", "lines", "log", "logBase", "lookup", "map",
      "mapM", "mapM_", "max", "maxBound", "maximum", "maybe", "min", "minBound",
      "minimum", "mod", "negate", "not", "notElem", "null", "odd", "or",
      "otherwise", "pi", "pred", "print", "product", "properFraction",
      "putChar", "putStr", "putStrLn", "quot", "quotRem", "read", "readFile",
      "readIO", "readList", "readLn", "readParen", "reads", "readsPrec",
      "realToFrac", "recip", "rem", "repeat", "replicate", "return", "reverse",
      "round", "scaleFloat", "scanl", "scanl1", "scanr", "scanr1", "seq",
      "sequence", "sequence_", "show", "showChar", "showList", "showParen",
      "showString", "shows", "showsPrec", "significand", "signum", "sin",
      "sinh", "snd", "span", "splitAt", "sqrt", "subtract", "succ", "sum",
      "tail", "take", "takeWhile", "tan", "tanh", "toEnum", "toInteger",
      "toRational", "truncate", "uncurry", "undefined", "unlines", "until",
      "unwords", "unzip", "unzip3", "userError", "words", "writeFile", "zip",
      "zip3", "zipWith", "zipWith3");
      
    return wkw;
  })();
    
  
  
  return {
    startState: function ()  { return { f: normal }; },
    copyState:  function (s) { return { f: s.f }; },
    
    token: function(stream, state) {
      var t = state.f(stream, function(s) { state.f = s; });
      var w = stream.current();
      return (w in wellKnownWords) ? wellKnownWords[w] : t;
    }
  };

});

CodeMirror.defineMIME("text/x-haskell", "haskell");