+-- | Unicode General Categories (column 2 of the UnicodeData table)
+-- in the order they are listed in the Unicode standard.
+
+data GeneralCategory
+ = UppercaseLetter -- ^ Lu: Letter, Uppercase
+ | LowercaseLetter -- ^ Ll: Letter, Lowercase
+ | TitlecaseLetter -- ^ Lt: Letter, Titlecase
+ | ModifierLetter -- ^ Lm: Letter, Modifier
+ | OtherLetter -- ^ Lo: Letter, Other
+ | NonSpacingMark -- ^ Mn: Mark, Non-Spacing
+ | SpacingCombiningMark -- ^ Mc: Mark, Spacing Combining
+ | EnclosingMark -- ^ Me: Mark, Enclosing
+ | DecimalNumber -- ^ Nd: Number, Decimal
+ | LetterNumber -- ^ Nl: Number, Letter
+ | OtherNumber -- ^ No: Number, Other
+ | ConnectorPunctuation -- ^ Pc: Punctuation, Connector
+ | DashPunctuation -- ^ Pd: Punctuation, Dash
+ | OpenPunctuation -- ^ Ps: Punctuation, Open
+ | ClosePunctuation -- ^ Pe: Punctuation, Close
+ | InitialQuote -- ^ Pi: Punctuation, Initial quote
+ | FinalQuote -- ^ Pf: Punctuation, Final quote
+ | OtherPunctuation -- ^ Po: Punctuation, Other
+ | MathSymbol -- ^ Sm: Symbol, Math
+ | CurrencySymbol -- ^ Sc: Symbol, Currency
+ | ModifierSymbol -- ^ Sk: Symbol, Modifier
+ | OtherSymbol -- ^ So: Symbol, Other
+ | Space -- ^ Zs: Separator, Space
+ | LineSeparator -- ^ Zl: Separator, Line
+ | ParagraphSeparator -- ^ Zp: Separator, Paragraph
+ | Control -- ^ Cc: Other, Control
+ | Format -- ^ Cf: Other, Format
+ | Surrogate -- ^ Cs: Other, Surrogate
+ | PrivateUse -- ^ Co: Other, Private Use
+ | NotAssigned -- ^ Cn: Other, Not Assigned
+ deriving (Eq, Ord, Enum, Read, Show, Bounded, Ix)
+
+-- | The Unicode general category of the character.
+generalCategory :: Char -> GeneralCategory
+#if defined(__GLASGOW_HASKELL__) || defined(__NHC__)
+generalCategory c = toEnum $ fromIntegral $ wgencat $ fromIntegral $ ord c
+#endif
+#ifdef __HUGS__
+generalCategory c = toEnum (primUniGenCat c)
+#endif
+
+-- derived character classifiers
+
+-- | Selects alphabetic Unicode characters (lower-case, upper-case and
+-- title-case letters, plus letters of caseless scripts and modifiers letters).
+-- This function is equivalent to 'Data.Char.isAlpha'.
+isLetter :: Char -> Bool
+isLetter c = case generalCategory c of
+ UppercaseLetter -> True
+ LowercaseLetter -> True
+ TitlecaseLetter -> True
+ ModifierLetter -> True
+ OtherLetter -> True
+ _ -> False
+
+-- | Selects Unicode mark characters, e.g. accents and the like, which
+-- combine with preceding letters.
+isMark :: Char -> Bool
+isMark c = case generalCategory c of
+ NonSpacingMark -> True
+ SpacingCombiningMark -> True
+ EnclosingMark -> True
+ _ -> False
+
+-- | Selects Unicode numeric characters, including digits from various
+-- scripts, Roman numerals, etc.
+isNumber :: Char -> Bool
+isNumber c = case generalCategory c of
+ DecimalNumber -> True
+ LetterNumber -> True
+ OtherNumber -> True
+ _ -> False
+
+-- | Selects Unicode punctuation characters, including various kinds
+-- of connectors, brackets and quotes.
+isPunctuation :: Char -> Bool
+isPunctuation c = case generalCategory c of
+ ConnectorPunctuation -> True
+ DashPunctuation -> True
+ OpenPunctuation -> True
+ ClosePunctuation -> True
+ InitialQuote -> True
+ FinalQuote -> True
+ OtherPunctuation -> True
+ _ -> False
+
+-- | Selects Unicode symbol characters, including mathematical and
+-- currency symbols.
+isSymbol :: Char -> Bool
+isSymbol c = case generalCategory c of
+ MathSymbol -> True
+ CurrencySymbol -> True
+ ModifierSymbol -> True
+ OtherSymbol -> True
+ _ -> False
+
+-- | Selects Unicode space and separator characters.
+isSeparator :: Char -> Bool
+isSeparator c = case generalCategory c of
+ Space -> True
+ LineSeparator -> True
+ ParagraphSeparator -> True
+ _ -> False
+
+#ifdef __NHC__
+-- dummy implementation
+toTitle :: Char -> Char
+toTitle = toUpper
+#endif