[project @ 2005-03-14 18:02:48 by ross]

[ghc-base.git] / GHC / Unicode.hs

diff --git a/GHC/Unicode.hs b/GHC/Unicode.hs
index 6a4732b..da74685 100644 (file)
--- a/GHC/Unicode.hs
+++ b/GHC/Unicode.hs
@@ -2,7 +2,7 @@
 {-# OPTIONS -#include "WCsubst.h" #-}
 -----------------------------------------------------------------------------
 -- |
--- Module      :  GHC.Unicde
+-- Module      :  GHC.Unicode
 -- Copyright   :  (c) The University of Glasgow, 2003
 -- License     :  see libraries/base/LICENSE
 -- 
@@ -17,20 +17,13 @@
 -----------------------------------------------------------------------------
 
 module GHC.Unicode (
-    GeneralCategory (..),
-    generalCategory,
     isAscii, isLatin1, isControl,
     isAsciiUpper, isAsciiLower,
     isPrint, isSpace,  isUpper,
     isLower, isAlpha,  isDigit,
     isOctDigit, isHexDigit, isAlphaNum,
     toUpper, toLower, toTitle,
-    isLetter,               -- :: Char -> Bool
-    isMark,                 -- :: Char -> Bool
-    isNumber,               -- :: Char -> Bool
-    isPunctuation,          -- :: Char -> Bool
-    isSymbol,               -- :: Char -> Bool
-    isSeparator,            -- :: Char -> Bool
+    wgencat,
   ) where
 
 import GHC.Base
@@ -38,106 +31,9 @@ import GHC.Real  (fromIntegral)
 import GHC.Int
 import GHC.Word
 import GHC.Num  (fromInteger)
-import GHC.Read
-import GHC.Show
-import GHC.Enum
 
 #include "HsBaseConfig.h"
 
--- | 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)
-
--- | Retrieves the general Unicode category of the character.
-generalCategory :: Char -> GeneralCategory
-generalCategory c = toEnum (wgencat (fromIntegral (ord c)))
-
--- ------------------------------------------------------------------------
--- These are copied from Hugs Unicode.hs
-
--- derived character classifiers
-
-isLetter :: Char -> Bool
-isLetter c = case generalCategory c of
-        UppercaseLetter         -> True
-        LowercaseLetter         -> True
-        TitlecaseLetter         -> True
-        ModifierLetter          -> True
-        OtherLetter             -> True
-        _                       -> False
-
-isMark :: Char -> Bool
-isMark c = case generalCategory c of
-        NonSpacingMark          -> True
-        SpacingCombiningMark    -> True
-        EnclosingMark           -> True
-        _                       -> False
-
-isNumber :: Char -> Bool
-isNumber c = case generalCategory c of
-        DecimalNumber           -> True
-        LetterNumber            -> True
-        OtherNumber             -> True
-        _                       -> False
-
-isPunctuation :: Char -> Bool
-isPunctuation c = case generalCategory c of
-        ConnectorPunctuation    -> True
-        DashPunctuation         -> True
-        OpenPunctuation         -> True
-        ClosePunctuation        -> True
-        InitialQuote            -> True
-        FinalQuote              -> True
-        OtherPunctuation        -> True
-        _                       -> False
-
-isSymbol :: Char -> Bool
-isSymbol c = case generalCategory c of
-        MathSymbol              -> True
-        CurrencySymbol          -> True
-        ModifierSymbol          -> True
-        OtherSymbol             -> True
-        _                       -> False
-
-isSeparator :: Char -> Bool
-isSeparator c = case generalCategory c of
-        Space                   -> True
-        LineSeparator           -> True
-        ParagraphSeparator      -> True
-        _                       -> False
-
 -- | Selects the first 128 characters of the Unicode character set,
 -- corresponding to the ASCII character set.
 isAscii                 :: Char -> Bool