{-# OPTIONS -#include "WCsubst.h" #-}
-----------------------------------------------------------------------------
-- |
--- Module : GHC.Unicde
+-- Module : GHC.Unicode
-- Copyright : (c) The University of Glasgow, 2003
-- License : see libraries/base/LICENSE
--
--
-----------------------------------------------------------------------------
+-- #hide
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
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
isLatin1 :: Char -> Bool
isLatin1 c = c <= '\xff'
-isAsciiUpper, isAsciiLower :: Char -> Bool
+-- | Selects ASCII lower-case letters,
+-- i.e. characters satisfying both 'isAscii' and 'isLower'.
+isAsciiLower :: Char -> Bool
isAsciiLower c = c >= 'a' && c <= 'z'
+
+-- | Selects ASCII upper-case letters,
+-- i.e. characters satisfying both 'isAscii' and 'isUpper'.
+isAsciiUpper :: Char -> Bool
isAsciiUpper c = c >= 'A' && c <= 'Z'
-- | Selects control characters, which are the non-printing characters of
c == '\xa0' ||
iswspace (fromIntegral (ord c)) /= 0
--- | Selects alphabetic Unicode characters (letters) that are not lower-case.
--- (In Unicode terms, this includes letters in upper and title cases,
--- as well as modifier letters and other letters.)
+-- | Selects upper-case or title-case alphabetic Unicode characters (letters).
+-- Title case is used by a small number of letter ligatures like the
+-- single-character form of /Lj/.
isUpper :: Char -> Bool
-- | Selects lower-case alphabetic Unicode characters (letters).
isLower :: Char -> Bool
--- | Selects alphabetic Unicode characters (letters).
+-- | 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.isLetter'.
isAlpha :: Char -> Bool
-- | Selects alphabetic or numeric digit Unicode characters.
isHexDigit c = isDigit c || c >= 'A' && c <= 'F' ||
c >= 'a' && c <= 'f'
--- | Convert a letter to the corresponding upper-case letter, leaving any
--- other character unchanged. Any Unicode letter which has an upper-case
--- equivalent is transformed.
+-- | Convert a letter to the corresponding upper-case letter, if any.
+-- Any other character is returned unchanged.
toUpper :: Char -> Char
--- | Convert a letter to the corresponding lower-case letter, leaving any
--- other character unchanged. Any Unicode letter which has a lower-case
--- equivalent is transformed.
+-- | Convert a letter to the corresponding lower-case letter, if any.
+-- Any other character is returned unchanged.
toLower :: Char -> Char
--- | Convert a letter to the corresponding title-case letter, leaving any
--- other character unchanged. Any Unicode letter which has a lower-case
--- equivalent is transformed.
+-- | Convert a letter to the corresponding title-case or upper-case
+-- letter, if any. (Title case differs from upper case only for a small
+-- number of ligature letters.)
+-- Any other character is returned unchanged.
toTitle :: Char -> Char
-- -----------------------------------------------------------------------------
-- Regardless of the O/S and Library, use the functions contained in WCsubst.c
-type WInt = HTYPE_WINT_T
type CInt = HTYPE_INT
isAlpha c = iswalpha (fromIntegral (ord c)) /= 0
towtitle :: CInt -> CInt
foreign import ccall unsafe "u_gencat"
- wgencat :: CInt -> Int
+ wgencat :: CInt -> CInt
-- -----------------------------------------------------------------------------
-- No libunicode, so fall back to the ASCII-only implementation (never used, indeed)