X-Git-Url: http://git.megacz.com/?a=blobdiff_plain;f=Data%2FChar.hs;h=48de79862d709e2d636bcec03b0defd738fac484;hb=202065fe56bd604d26d1924cbc9c0959266ca7ea;hp=c8c630e922435f8307487d1c42ed300e74ecd13c;hpb=aaedec91d25e9240edda260e6a0aaf9f76844864;p=ghc-base.git

diff --git a/Data/Char.hs b/Data/Char.hs
index c8c630e..48de798 100644
--- a/Data/Char.hs
+++ b/Data/Char.hs
@@ -1,4 +1,4 @@
-{-# OPTIONS -fno-implicit-prelude #-}
+{-# OPTIONS_GHC -fno-implicit-prelude #-}
 -----------------------------------------------------------------------------
 -- |
 -- Module      :  Data.Char
@@ -6,7 +6,7 @@
 -- License     :  BSD-style (see the file libraries/base/LICENSE)
 -- 
 -- Maintainer  :  libraries@haskell.org
--- Stability   :  provisional
+-- Stability   :  stable
 -- Portability :  portable
 --
 -- The Char type and associated operations.
@@ -23,14 +23,20 @@ module Data.Char
     -- | Unicode characters are divided into letters, numbers, marks,
     -- punctuation, symbols, separators (including spaces) and others
     -- (including control characters).
-    -- The full set of Unicode character attributes is not accessible
-    -- in this library.
-    , isAscii, isLatin1, isControl, isSpace
-    , isLower, isUpper,  isAlpha,   isAlphaNum, isPrint
-    , isDigit, isOctDigit, isHexDigit  -- :: Char -> Bool
+    , isControl, isSpace
+    , isLower, isUpper, isAlpha, isAlphaNum, isPrint
+    , isDigit, isOctDigit, isHexDigit
+    , isLetter, isMark, isNumber, isPunctuation, isSymbol, isSeparator
+
+    -- ** Subranges
+    , isAscii, isLatin1
+    , isAsciiUpper, isAsciiLower
+
+    -- ** Unicode general categories
+    , GeneralCategory(..), generalCategory
 
     -- * Case conversion
-    , toUpper, toLower  -- :: Char -> Char
+    , toUpper, toLower, toTitle  -- :: Char -> Char
 
     -- * Single digit characters
     , digitToInt        -- :: Char -> Int
@@ -50,10 +56,12 @@ module Data.Char
 
 #ifdef __GLASGOW_HASKELL__
 import GHC.Base
+import GHC.Real (fromIntegral)
 import GHC.Show
-import GHC.Read (readLitChar, lexLitChar)
+import GHC.Read (Read, readLitChar, lexLitChar)
 import GHC.Unicode
 import GHC.Num
+import GHC.Enum
 #endif
 
 #ifdef __HUGS__
@@ -64,6 +72,8 @@ import Hugs.Char
 import Prelude
 import Prelude(Char,String)
 import Char
+import NHC.FFI (CInt)
+foreign import ccall unsafe "WCsubst.h u_gencat" wgencat :: CInt -> Int
 #endif
 
 -- | Convert a single digit 'Char' to the corresponding 'Int'.  
@@ -76,3 +86,123 @@ digitToInt c
  | c >= 'a' && c <= 'f' =  ord c - ord 'a' + 10
  | c >= 'A' && c <= 'F' =  ord c - ord 'A' + 10
  | otherwise	        =  error ("Char.digitToInt: not a digit " ++ show c) -- sigh
+
+#ifndef __GLASGOW_HASKELL__
+isAsciiUpper, isAsciiLower :: Char -> Bool
+isAsciiLower c          =  c >= 'a' && c <= 'z'
+isAsciiUpper c          =  c >= 'A' && c <= 'Z'
+#endif
+
+-- | 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)
+
+-- | The Unicode general category of the character.
+generalCategory :: Char -> GeneralCategory
+#if defined(__GLASGOW_HASKELL__) || defined(__NHC__)
+generalCategory c = toEnum (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