diff --git a/Data/Text/ICU/Convert.hs b/Data/Text/ICU/Convert.hs new file mode 100644 --- /dev/null +++ b/Data/Text/ICU/Convert.hs @@ -0,0 +1,236 @@ +{-# LANGUAGE CPP, ForeignFunctionInterface #-} +-- | +-- Module : Data.Text.ICU.Convert +-- Copyright : (c) Bryan O'Sullivan 2009 +-- +-- License : BSD-style +-- Maintainer : bos@serpentine.com +-- Stability : experimental +-- Portability : GHC +-- +-- Character set conversion functions for Unicode, implemented as +-- bindings to the International Components for Unicode (ICU) +-- libraries. + +module Data.Text.ICU.Convert + ( + -- * Character set conversion + Converter + -- ** Basic functions + , open + , fromUnicode + , toUnicode + -- ** Converter metadata + , getName + , usesFallback + , isAmbiguous + -- * Functions for controlling global behavior + , getDefaultName + , setDefaultName + -- * Miscellaneous functions + , compareNames + , aliases + -- * Metadata + , converterNames + , standardNames + ) where + +import Data.ByteString.Internal (ByteString, createAndTrim) +import Data.ByteString.Unsafe (unsafeUseAsCStringLen) +import Data.Int (Int32) +import Data.Text (Text) +import Data.Text.Foreign (fromPtr, lengthWord16, useAsPtr) +import Data.Text.ICU.Convert.Internal +import Data.Text.ICU.Error.Internal (UErrorCode, handleError) +import Data.Word (Word16) +import Foreign.C.String (CString, peekCString, withCString) +import Foreign.C.Types (CInt) +import Foreign.ForeignPtr (newForeignPtr) +import Foreign.Marshal.Array (allocaArray) +import Foreign.Ptr (FunPtr, Ptr, castPtr, nullPtr) +import System.IO.Unsafe (unsafePerformIO) +import Data.Text.ICU.Internal (UBool, UChar, asBool, asOrdering) + +-- | Do a fuzzy compare of two converter/alias names. The comparison +-- is case-insensitive, ignores leading zeroes if they are not +-- followed by further digits, and ignores all but letters and digits. +-- Thus the strings @\"UTF-8\"@, @\"utf_8\"@, @\"u*T\@f08\"@ and +-- @\"Utf 8\"@ are exactly equivalent. See section 1.4, Charset Alias +-- Matching in Unicode Technical Standard #22 at +-- +compareNames :: String -> String -> Ordering +compareNames a b = + unsafePerformIO . withCString a $ \aptr -> + fmap asOrdering . withCString b $ ucnv_compareNames aptr + +-- | Create a 'Converter' with the name of a coded character set +-- specified as a string. The actual name will be resolved with the +-- alias file using a case-insensitive string comparison that ignores +-- leading zeroes and all non-alphanumeric characters. E.g., the +-- names @\"UTF8\"@, @\"utf-8\"@, @\"u*T\@f08\"@ and @\"Utf 8\"@ are +-- all equivalent (see also 'compareNames'). If an empty string is +-- passed for the converter name, it will create one with the +-- 'getDefaultName' return value. +-- +-- A converter name may contain options like a locale specification to +-- control the specific behavior of the newly instantiated converter. +-- The meaning of the options depends on the particular converter. If +-- an option is not defined for or recognized by a given converter, +-- then it is ignored. +-- +-- Options are appended to the converter name string, with a comma +-- between the name and the first option and also between adjacent +-- options. +-- +-- If the alias is ambiguous, then the preferred converter is used. +-- +-- The conversion behavior and names can vary between platforms. ICU +-- may convert some characters differently from other +-- platforms. Details on this topic are in the ICU User's Guide at +-- . Aliases +-- starting with a @\"cp\"@ prefix have no specific meaning other than +-- its an alias starting with the letters @\"cp\"@. Please do not +-- associate any meaning to these aliases. +open :: String -- ^ Name of the converter to use. + -> Maybe Bool -- ^ Whether to use fallback mappings + -- (see 'usesFallback' for details). + -> IO Converter +open name mf = do + c <- fmap Converter . newForeignPtr ucnv_close =<< named (handleError . ucnv_open) + case mf of + Just f -> withConverter c $ \p -> ucnv_setFallback p . fromIntegral . fromEnum $ f + _ -> return () + return c + where named act + | null name = act nullPtr + | otherwise = withCString name act + +-- | Convert the Unicode string into a codepage string using the given +-- converter. +fromUnicode :: Converter -> Text -> ByteString +fromUnicode cnv t = + unsafePerformIO . useAsPtr t $ \tptr tlen -> + withConverter cnv $ \cptr -> do + let capacity = fromIntegral . max_bytes_for_string cptr . fromIntegral $ + lengthWord16 t + createAndTrim (fromIntegral capacity) $ \sptr -> + fmap fromIntegral . handleError $ + ucnv_fromUChars cptr (castPtr sptr) capacity tptr (fromIntegral tlen) + +-- | Convert the codepage string into a Unicode string using the given +-- converter. +toUnicode :: Converter -> ByteString -> Text +toUnicode cnv bs = + unsafePerformIO . unsafeUseAsCStringLen bs $ \(sptr, slen) -> + withConverter cnv $ \cptr -> do + let capacity = slen * 2 + allocaArray capacity $ \tptr -> + fromPtr tptr =<< (fmap fromIntegral . handleError $ + ucnv_toUChars cptr tptr (fromIntegral capacity) sptr + (fromIntegral slen)) + +-- | Determines whether the converter uses fallback mappings or not. +-- This flag has restrictions. Regardless of this flag, the converter +-- will always use fallbacks from Unicode Private Use code points, as +-- well as reverse fallbacks (to Unicode). For details see \".ucm +-- File Format\" in the Conversion Data chapter of the ICU User Guide: +-- +usesFallback :: Converter -> Bool +usesFallback cnv = unsafePerformIO $ + asBool `fmap` withConverter cnv ucnv_usesFallback + +-- | Returns the current default converter name. If you want to 'open' +-- a default converter, you do not need to use this function. It is +-- faster to pass the empty string to 'open' the default converter. +getDefaultName :: IO String +getDefaultName = peekCString =<< ucnv_getDefaultName + +-- | Indicates whether the converter contains ambiguous mappings of +-- the same character or not. +isAmbiguous :: Converter -> Bool +isAmbiguous cnv = asBool . unsafePerformIO $ withConverter cnv ucnv_isAmbiguous + +-- | Sets the current default converter name. If this function needs +-- to be called, it should be called during application +-- initialization. Most of the time, the results from 'getDefaultName' +-- or 'open' with an empty string argument is sufficient for your +-- application. +-- +-- /Note/: this function is not thread safe. /Do not/ call this +-- function when /any/ ICU function is being used from more than one +-- thread! +setDefaultName :: String -> IO () +setDefaultName s = withCString s $ ucnv_setDefaultName + +-- | A list of the canonical names of all available converters. +converterNames :: [String] +{-# NOINLINE converterNames #-} +converterNames = unsafePerformIO $ + mapM ((peekCString =<<) . ucnv_getAvailableName) [0..ucnv_countAvailable-1] + +-- | The list of supported standard names. +standardNames :: [String] +{-# NOINLINE standardNames #-} +standardNames = filter (not . null) . unsafePerformIO $ + mapM ((peekCString =<<) . handleError . ucnv_getStandard) [0..ucnv_countStandards-1] + +-- | Return the aliases for a given converter or alias name. +aliases :: String -> [String] +aliases name = unsafePerformIO . withCString name $ \ptr -> do + count <- handleError $ ucnv_countAliases ptr + if count == 0 + then return [] + else mapM ((peekCString =<<) . handleError . ucnv_getAlias ptr) [0..count-1] + +foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_open" ucnv_open + :: CString -> Ptr UErrorCode -> IO (Ptr UConverter) + +foreign import ccall unsafe "hs_text_icu.h &__hs_ucnv_close" ucnv_close + :: FunPtr (Ptr UConverter -> IO ()) + +foreign import ccall unsafe "__get_max_bytes_for_string" max_bytes_for_string + :: Ptr UConverter -> CInt -> CInt + +foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_toUChars" ucnv_toUChars + :: Ptr UConverter -> Ptr UChar -> Int32 -> CString -> Int32 + -> Ptr UErrorCode -> IO Int32 + +foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_fromUChars" ucnv_fromUChars + :: Ptr UConverter -> CString -> Int32 -> Ptr UChar -> Int32 + -> Ptr UErrorCode -> IO Int32 + +foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_compareNames" ucnv_compareNames + :: CString -> CString -> IO CInt + +foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_getDefaultName" ucnv_getDefaultName + :: IO CString + +foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_setDefaultName" ucnv_setDefaultName + :: CString -> IO () + +foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_countAvailable" ucnv_countAvailable + :: Int32 + +foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_getAvailableName" ucnv_getAvailableName + :: Int32 -> IO CString + +foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_countAliases" ucnv_countAliases + :: CString -> Ptr UErrorCode -> IO Word16 + +foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_getAlias" ucnv_getAlias + :: CString -> Word16 -> Ptr UErrorCode -> IO CString + +foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_countStandards" ucnv_countStandards + :: Word16 + +foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_getStandard" ucnv_getStandard + :: Word16 -> Ptr UErrorCode -> IO CString + +foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_usesFallback" ucnv_usesFallback + :: Ptr UConverter -> IO UBool + +foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_setFallback" ucnv_setFallback + :: Ptr UConverter -> UBool -> IO () + +foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_isAmbiguous" ucnv_isAmbiguous + :: Ptr UConverter -> IO UBool diff --git a/Data/Text/ICU/Convert/Internal.hs b/Data/Text/ICU/Convert/Internal.hs new file mode 100644 --- /dev/null +++ b/Data/Text/ICU/Convert/Internal.hs @@ -0,0 +1,50 @@ +{-# LANGUAGE DeriveDataTypeable, EmptyDataDecls, ForeignFunctionInterface #-} +-- | +-- Module : Data.Text.ICU.Convert.Internal +-- Copyright : (c) Bryan O'Sullivan 2009 +-- +-- License : BSD-style +-- Maintainer : bos@serpentine.com +-- Stability : experimental +-- Portability : GHC +-- +-- Low-level character set types and functions. + +module Data.Text.ICU.Convert.Internal + ( + Converter(..) + , UConverter + , getName + , withConverter + ) where + +import Data.Text.ICU.Error.Internal (UErrorCode, handleError) +import Data.Typeable (Typeable) +import Foreign.C.String (CString, peekCString) +import Foreign.ForeignPtr (ForeignPtr, withForeignPtr) +import Foreign.Ptr (Ptr) +import System.IO.Unsafe (unsafePerformIO) + +data UConverter + +-- | Character set converter type. /Note/: this structure is not +-- thread safe. It is /not/ safe to use value of this type +-- simultaneously from multiple threads. +data Converter = Converter {-# UNPACK #-} !(ForeignPtr UConverter) + deriving (Eq, Typeable) + +instance Show Converter where + show c = "Converter " ++ show (getName c) + +withConverter :: Converter -> (Ptr UConverter -> IO a) -> IO a +{-# INLINE withConverter #-} +withConverter (Converter cnv) action = withForeignPtr cnv action + +-- | Gets the internal, canonical name of the converter. +getName :: Converter -> String +getName cnv = unsafePerformIO . + withConverter cnv $ \ptr -> + peekCString =<< handleError (ucnv_getName ptr) + +foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_getName" ucnv_getName + :: Ptr UConverter -> Ptr UErrorCode -> IO CString diff --git a/Data/Text/ICU/Converter.hs b/Data/Text/ICU/Converter.hs deleted file mode 100644 --- a/Data/Text/ICU/Converter.hs +++ /dev/null @@ -1,235 +0,0 @@ -{-# LANGUAGE CPP, ForeignFunctionInterface #-} --- | --- Module : Data.Text.ICU.Converter --- Copyright : (c) Bryan O'Sullivan 2009 --- --- License : BSD-style --- Maintainer : bos@serpentine.com --- Stability : experimental --- Portability : GHC --- --- Character set conversion functions for Unicode, implemented as --- bindings to the International Components for Unicode (ICU) --- libraries. - -module Data.Text.ICU.Converter - ( - -- * Character set conversion - Converter - -- ** Basic functions - , open - , fromUnicode - , toUnicode - -- ** Converter metadata - , getName - , usesFallback - , setFallback - , isAmbiguous - -- * Functions for controlling global behavior - , getDefaultName - , setDefaultName - -- * Miscellaneous functions - , compareNames - , aliases - -- * Metadata - , converterNames - , standardNames - ) where - -import Data.ByteString.Internal (ByteString, createAndTrim) -import Data.ByteString.Unsafe (unsafeUseAsCStringLen) -import Data.Int (Int32) -import Data.Text (Text) -import Data.Text.Foreign (fromPtr, lengthWord16, useAsPtr) -import Data.Text.ICU.Converter.Internal -import Data.Text.ICU.Error.Internal (UErrorCode, handleError) -import Data.Word (Word16) -import Foreign.C.String (CString, peekCString, withCString) -import Foreign.C.Types (CInt) -import Foreign.ForeignPtr (newForeignPtr) -import Foreign.Marshal.Array (allocaArray) -import Foreign.Ptr (FunPtr, Ptr, castPtr, nullPtr) -import System.IO.Unsafe (unsafePerformIO) -import Data.Text.ICU.Internal (UBool, UChar, asBool, asOrdering) - --- | Do a fuzzy compare of two converter/alias names. The comparison --- is case-insensitive, ignores leading zeroes if they are not --- followed by further digits, and ignores all but letters and digits. --- Thus the strings @\"UTF-8\"@, @\"utf_8\"@, @\"u*T\@f08\"@ and --- @\"Utf 8\"@ are exactly equivalent. See section 1.4, Charset Alias --- Matching in Unicode Technical Standard #22 at --- -compareNames :: String -> String -> Ordering -compareNames a b = - unsafePerformIO . withCString a $ \aptr -> - fmap asOrdering . withCString b $ ucnv_compareNames aptr - --- | Create a 'Converter' with the name of a coded character set --- specified as a string. The actual name will be resolved with the --- alias file using a case-insensitive string comparison that ignores --- leading zeroes and all non-alphanumeric characters. E.g., the --- names @\"UTF8\"@, @\"utf-8\"@, @\"u*T\@f08\"@ and @\"Utf 8\"@ are --- all equivalent (see also 'compareNames'). If an empty string is --- passed for the converter name, it will create one with the --- 'getDefaultName' return value. --- --- A converter name may contain options like a locale specification to --- control the specific behavior of the newly instantiated converter. --- The meaning of the options depends on the particular converter. If --- an option is not defined for or recognized by a given converter, --- then it is ignored. --- --- Options are appended to the converter name string, with a comma --- between the name and the first option and also between adjacent --- options. --- --- If the alias is ambiguous, then the preferred converter is used. --- --- The conversion behavior and names can vary between platforms. ICU --- may convert some characters differently from other --- platforms. Details on this topic are in the ICU User's Guide at --- . Aliases --- starting with a @\"cp\"@ prefix have no specific meaning other than --- its an alias starting with the letters @\"cp\"@. Please do not --- associate any meaning to these aliases. -open :: String -> IO Converter -open name = - fmap Converter . newForeignPtr ucnv_close =<< named (handleError . ucnv_open) - where named act - | null name = act nullPtr - | otherwise = withCString name act - --- | Convert the Unicode string into a codepage string using the given --- converter. -fromUnicode :: Converter -> Text -> IO ByteString -fromUnicode cnv t = - useAsPtr t $ \tptr tlen -> - withConverter cnv $ \cptr -> do - let capacity = fromIntegral . max_bytes_for_string cptr . fromIntegral $ - lengthWord16 t - createAndTrim (fromIntegral capacity) $ \sptr -> - fmap fromIntegral . handleError $ - ucnv_fromUChars cptr (castPtr sptr) capacity tptr (fromIntegral tlen) - --- | Convert the codepage string into a Unicode string using the given --- converter. -toUnicode :: Converter -> ByteString -> IO Text -toUnicode cnv bs = - unsafeUseAsCStringLen bs $ \(sptr, slen) -> - withConverter cnv $ \cptr -> do - let capacity = slen * 2 - allocaArray capacity $ \tptr -> - fromPtr tptr =<< (fmap fromIntegral . handleError $ - ucnv_toUChars cptr tptr (fromIntegral capacity) sptr - (fromIntegral slen)) - --- | Determines whether the converter uses fallback mappings or not. --- This flag has restrictions; see 'setFallback'. -usesFallback :: Converter -> IO Bool -usesFallback cnv = asBool `fmap` withConverter cnv ucnv_usesFallback - --- | Sets the converter to use fallback mappings or not. Regardless --- of this flag, the converter will always use fallbacks from Unicode --- Private Use code points, as well as reverse fallbacks (to Unicode). --- For details see \".ucm File Format\" in the Conversion Data chapter --- of the ICU User Guide: --- -setFallback :: Converter -> Bool -> IO () -setFallback cnv flag = - withConverter cnv $ \p -> (ucnv_setFallback p (fromIntegral (fromEnum flag))) - --- | Returns the current default converter name. If you want to 'open' --- a default converter, you do not need to use this function. It is --- faster to pass the empty string to 'open' the default converter. -getDefaultName :: IO String -getDefaultName = peekCString =<< ucnv_getDefaultName - --- | Indicates whether the converter contains ambiguous mappings of --- the same character or not. -isAmbiguous :: Converter -> Bool -isAmbiguous cnv = asBool . unsafePerformIO $ withConverter cnv ucnv_isAmbiguous - --- | Sets the current default converter name. If this function needs --- to be called, it should be called during application --- initialization. Most of the time, the results from 'getDefaultName' --- or 'open' with an empty string argument is sufficient for your --- application. --- --- /Note/: this function is not thread safe. /Do not/ call this --- function when /any/ ICU function is being used from more than one --- thread! -setDefaultName :: String -> IO () -setDefaultName s = withCString s $ ucnv_setDefaultName - --- | A list of the canonical names of all available converters. -converterNames :: [String] -{-# NOINLINE converterNames #-} -converterNames = unsafePerformIO $ - mapM ((peekCString =<<) . ucnv_getAvailableName) [0..ucnv_countAvailable-1] - --- | The list of supported standard names. -standardNames :: [String] -{-# NOINLINE standardNames #-} -standardNames = filter (not . null) . unsafePerformIO $ - mapM ((peekCString =<<) . handleError . ucnv_getStandard) [0..ucnv_countStandards-1] - --- | Return the aliases for a given converter or alias name. -aliases :: String -> [String] -aliases name = unsafePerformIO . withCString name $ \ptr -> do - count <- ucnv_countAliases ptr - if count == 0 - then return [] - else mapM ((peekCString =<<) . handleError . ucnv_getAlias ptr) [0..count-1] - -foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_open" ucnv_open - :: CString -> Ptr UErrorCode -> IO (Ptr UConverter) - -foreign import ccall unsafe "hs_text_icu.h &__hs_ucnv_close" ucnv_close - :: FunPtr (Ptr UConverter -> IO ()) - -foreign import ccall unsafe "__get_max_bytes_for_string" max_bytes_for_string - :: Ptr UConverter -> CInt -> CInt - -foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_toUChars" ucnv_toUChars - :: Ptr UConverter -> Ptr UChar -> Int32 -> CString -> Int32 - -> Ptr UErrorCode -> IO Int32 - -foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_fromUChars" ucnv_fromUChars - :: Ptr UConverter -> CString -> Int32 -> Ptr UChar -> Int32 - -> Ptr UErrorCode -> IO Int32 - -foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_compareNames" ucnv_compareNames - :: CString -> CString -> IO CInt - -foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_getDefaultName" ucnv_getDefaultName - :: IO CString - -foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_setDefaultName" ucnv_setDefaultName - :: CString -> IO () - -foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_countAvailable" ucnv_countAvailable - :: Int32 - -foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_getAvailableName" ucnv_getAvailableName - :: Int32 -> IO CString - -foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_countAliases" ucnv_countAliases - :: CString -> IO Word16 - -foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_getAlias" ucnv_getAlias - :: CString -> Word16 -> Ptr UErrorCode -> IO CString - -foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_countStandards" ucnv_countStandards - :: Word16 - -foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_getStandard" ucnv_getStandard - :: Word16 -> Ptr UErrorCode -> IO CString - -foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_usesFallback" ucnv_usesFallback - :: Ptr UConverter -> IO UBool - -foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_setFallback" ucnv_setFallback - :: Ptr UConverter -> UBool -> IO () - -foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_isAmbiguous" ucnv_isAmbiguous - :: Ptr UConverter -> IO UBool diff --git a/Data/Text/ICU/Converter/Internal.hs b/Data/Text/ICU/Converter/Internal.hs deleted file mode 100644 --- a/Data/Text/ICU/Converter/Internal.hs +++ /dev/null @@ -1,50 +0,0 @@ -{-# LANGUAGE DeriveDataTypeable, EmptyDataDecls, ForeignFunctionInterface #-} --- | --- Module : Data.Text.ICU.Converter.Internal --- Copyright : (c) Bryan O'Sullivan 2009 --- --- License : BSD-style --- Maintainer : bos@serpentine.com --- Stability : experimental --- Portability : GHC --- --- Low-level character set types and functions. - -module Data.Text.ICU.Converter.Internal - ( - Converter(..) - , UConverter - , getName - , withConverter - ) where - -import Data.Text.ICU.Error.Internal (UErrorCode, handleError) -import Data.Typeable (Typeable) -import Foreign.C.String (CString, peekCString) -import Foreign.ForeignPtr (ForeignPtr, withForeignPtr) -import Foreign.Ptr (Ptr) -import System.IO.Unsafe (unsafePerformIO) - -data UConverter - --- | Character set converter type. /Note/: this structure is not --- thread safe. It is /not/ safe to use value of this type --- simultaneously from multiple threads. -data Converter = Converter {-# UNPACK #-} !(ForeignPtr UConverter) - deriving (Eq, Typeable) - -instance Show Converter where - show c = "Converter " ++ show (getName c) - -withConverter :: Converter -> (Ptr UConverter -> IO a) -> IO a -{-# INLINE withConverter #-} -withConverter (Converter cnv) action = withForeignPtr cnv action - --- | Gets the internal, canonical name of the converter. -getName :: Converter -> String -getName cnv = unsafePerformIO . - withConverter cnv $ \ptr -> - peekCString =<< handleError (ucnv_getName ptr) - -foreign import ccall unsafe "hs_text_icu.h __hs_ucnv_getName" ucnv_getName - :: Ptr UConverter -> Ptr UErrorCode -> IO CString diff --git a/Data/Text/ICU/Error/Internal.hs b/Data/Text/ICU/Error/Internal.hs --- a/Data/Text/ICU/Error/Internal.hs +++ b/Data/Text/ICU/Error/Internal.hs @@ -15,13 +15,13 @@ , withError ) where -import Control.Exception -import Foreign.Ptr -import Foreign.Marshal.Alloc +import Control.Exception (Exception, throw) +import Foreign.Ptr (Ptr) +import Foreign.Marshal.Alloc (alloca) import Data.Typeable (Typeable) import Foreign.C.String (CString, peekCString) import Foreign.C.Types (CInt) -import Foreign.Storable +import Foreign.Storable (peek, poke) import System.IO.Unsafe (unsafePerformIO) type UErrorCode = CInt diff --git a/Data/Text/ICU/Normalize.hsc b/Data/Text/ICU/Normalize.hsc new file mode 100644 --- /dev/null +++ b/Data/Text/ICU/Normalize.hsc @@ -0,0 +1,308 @@ +{-# LANGUAGE CPP, DeriveDataTypeable, ForeignFunctionInterface, + GeneralizedNewtypeDeriving #-} +-- | +-- Module : Data.Text.ICU.Normalize +-- Copyright : (c) Bryan O'Sullivan 2009 +-- +-- License : BSD-style +-- Maintainer : bos@serpentine.com +-- Stability : experimental +-- Portability : GHC +-- +-- Character set normalization functions for Unicode, implemented as +-- bindings to the International Components for Unicode (ICU) +-- libraries. + +module Data.Text.ICU.Normalize + ( + -- * Unicode normalization API + -- $api + NormalizationMode(..) + -- * Normalization functions + , normalize + -- * Normalization checks + , NormalizationCheckResult(..) + , quickCheck + , isNormalized + -- * Normalization-sensitive comparison + , CompareOption(..) + , compare + ) where + +#ifdef mingw32_HOST_OS +#define U_HAVE_INTTYPES_H 1 +#endif + +#include +#include + +import Control.Exception (throw) +import Control.Monad (when) +import Data.Text (Text) +import Data.Text.Foreign (fromPtr, useAsPtr) +import Data.Text.ICU.Error (u_BUFFER_OVERFLOW_ERROR) +import Data.Text.ICU.Error.Internal (UErrorCode, isFailure, handleError, withError) +import Data.Text.ICU.Internal (UBool, UChar, asBool, asOrdering) +import Data.Typeable (Typeable) +import Data.Int (Int32) +import Data.Word (Word32) +import Foreign.C.Types (CInt) +import Foreign.Marshal.Array (allocaArray) +import Foreign.Ptr (Ptr) +import System.IO.Unsafe (unsafePerformIO) +import Prelude hiding (compare) +import Data.List (foldl') +import Data.Bits ((.|.)) + +-- $api +-- +-- 'normalize' transforms Unicode text into an equivalent composed or +-- decomposed form, allowing for easier sorting and searching of text. +-- 'normalize' supports the standard normalization forms described in +-- , +-- Unicode Standard Annex #15: Unicode Normalization Forms. +-- +-- Characters with accents or other adornments can be encoded in +-- several different ways in Unicode. For example, take the character A-acute. +-- In Unicode, this can be encoded as a single character (the +-- \"composed\" form): +-- +-- @ +-- 00C1 LATIN CAPITAL LETTER A WITH ACUTE +-- @ +-- +-- or as two separate characters (the \"decomposed\" form): +-- +-- @ +-- 0041 LATIN CAPITAL LETTER A +-- 0301 COMBINING ACUTE ACCENT +-- @ +-- +-- To a user of your program, however, both of these sequences should +-- be treated as the same \"user-level\" character \"A with acute +-- accent\". When you are searching or comparing text, you must +-- ensure that these two sequences are treated equivalently. In +-- addition, you must handle characters with more than one accent. +-- Sometimes the order of a character's combining accents is +-- significant, while in other cases accent sequences in different +-- orders are really equivalent. +-- +-- Similarly, the string \"ffi\" can be encoded as three separate letters: +-- +-- @ +-- 0066 LATIN SMALL LETTER F +-- 0066 LATIN SMALL LETTER F +-- 0069 LATIN SMALL LETTER I +-- @ +-- +-- or as the single character +-- +-- @ +-- FB03 LATIN SMALL LIGATURE FFI +-- @ +-- +-- The \"ffi\" ligature is not a distinct semantic character, and +-- strictly speaking it shouldn't be in Unicode at all, but it was +-- included for compatibility with existing character sets that +-- already provided it. The Unicode standard identifies such +-- characters by giving them \"compatibility\" decompositions into the +-- corresponding semantic characters. When sorting and searching, you +-- will often want to use these mappings. +-- +-- 'normalize' helps solve these problems by transforming text into +-- the canonical composed and decomposed forms as shown in the first +-- example above. In addition, you can have it perform compatibility +-- decompositions so that you can treat compatibility characters the +-- same as their equivalents. Finally, 'normalize' rearranges accents +-- into the proper canonical order, so that you do not have to worry +-- about accent rearrangement on your own. +-- +-- Form 'FCD', \"Fast C or D\", is also designed for collation. It +-- allows to work on strings that are not necessarily normalized with +-- an algorithm (like in collation) that works under \"canonical +-- closure\", i.e., it treats precomposed characters and their +-- decomposed equivalents the same. +-- +-- It is not a normalization form because it does not provide for +-- uniqueness of representation. Multiple strings may be canonically +-- equivalent (their NFDs are identical) and may all conform to 'FCD' +-- without being identical themselves. +-- +-- The form is defined such that the \"raw decomposition\", the +-- recursive canonical decomposition of each character, results in a +-- string that is canonically ordered. This means that precomposed +-- characters are allowed for as long as their decompositions do not +-- need canonical reordering. +-- +-- Its advantage for a process like collation is that all 'NFD' and +-- most 'NFC' texts - and many unnormalized texts - already conform to +-- 'FCD' and do not need to be normalized ('NFD') for such a +-- process. The 'FCD' 'quickCheck' will return 'Yes' for most strings +-- in practice. +-- +-- @'normalize' 'FCD'@ may be implemented with 'NFD'. +-- +-- For more details on 'FCD' see the collation design document: +-- +-- +-- ICU collation performs either 'NFD' or 'FCD' normalization +-- automatically if normalization is turned on for the collator +-- object. Beyond collation and string search, normalized strings may +-- be useful for string equivalence comparisons, +-- transliteration/transcription, unique representations, etc. +-- +-- The W3C generally recommends to exchange texts in 'NFC'. Note also +-- that most legacy character encodings use only precomposed forms and +-- often do not encode any combining marks by themselves. For +-- conversion to such character encodings the Unicode text needs to be +-- normalized to 'NFC'. For more usage examples, see the Unicode +-- Standard Annex. + +type UCompareOption = Word32 + +-- | Options to 'compare'. +data CompareOption = InputIsFCD + -- ^ The caller knows that both strings fulfill the + -- 'FCD' conditions. If not set, 'compare' will + -- 'quickCheck' for 'FCD' and normalize if + -- necessary. + | CompareCodePointOrder + -- ^ Choose code point order instead of code unit + -- order. + | CompareIgnoreCase + -- ^ Compare strings case-insensitively using case + -- folding, instead of case-sensitively. If set, + -- then the following case folding options are + -- used. + | FoldCaseExcludeSpecialI + -- ^ When case folding, exclude the special I + -- character. For use with Turkic + -- (Turkish/Azerbaijani) text data. + deriving (Eq, Show, Enum, Typeable) + +fromCompareOption :: CompareOption -> UCompareOption +fromCompareOption InputIsFCD = #const UNORM_INPUT_IS_FCD +fromCompareOption CompareCodePointOrder = #const U_COMPARE_CODE_POINT_ORDER +fromCompareOption CompareIgnoreCase = #const U_COMPARE_IGNORE_CASE +fromCompareOption FoldCaseExcludeSpecialI = #const U_FOLD_CASE_EXCLUDE_SPECIAL_I + +reduceCompareOptions :: [CompareOption] -> UCompareOption +reduceCompareOptions = foldl' orO (#const U_FOLD_CASE_DEFAULT) + where a `orO` b = a .|. fromCompareOption b + +type UNormalizationMode = CInt + +-- | Normalization modes. +data NormalizationMode + = None -- ^ No decomposition/composition. + | NFD -- ^ Canonical decomposition. + | NFKD -- ^ Compatibility decomposition. + | NFC -- ^ Canonical decomposition followed by canonical composition. + | NFKC -- ^ Compatibility decomposition followed by canonical composition. + | FCD -- ^ \"Fast C or D\" form. + deriving (Eq, Show, Enum, Typeable) + +toNM :: NormalizationMode -> UNormalizationMode +toNM None = #const UNORM_NONE +toNM NFD = #const UNORM_NFD +toNM NFKD = #const UNORM_NFKD +toNM NFC = #const UNORM_NFC +toNM NFKC = #const UNORM_NFKC +toNM FCD = #const UNORM_FCD + +type UNormalizationCheckResult = CInt + +-- | Result of a fast normalization check using 'quickCheck'. +data NormalizationCheckResult + = No -- ^ Text is not normalized. + | Perhaps -- ^ It cannot be determined whether text is in normalized + -- form without further thorough checks. + | Yes -- ^ Text is in normalized form. + deriving (Eq, Show, Enum, Typeable) + +toNCR :: UNormalizationCheckResult -> NormalizationCheckResult +toNCR (#const UNORM_NO) = No +toNCR (#const UNORM_MAYBE) = Perhaps +toNCR (#const UNORM_YES) = Yes +toNCR _ = error "toNormalizationCheckResult" + +-- | Normalize a string according the specified normalization mode. +normalize :: NormalizationMode -> Text -> Text +normalize mode t = unsafePerformIO . useAsPtr t $ \sptr slen -> + let slen' = fromIntegral slen + mode' = toNM mode + loop dlen = + (either loop return =<<) . + allocaArray dlen $ \dptr -> do + (err, newLen) <- withError $ + unorm_normalize sptr slen' mode' 0 dptr (fromIntegral dlen) + when (isFailure err && err /= u_BUFFER_OVERFLOW_ERROR) $ + throw err + let newLen' = fromIntegral newLen + if newLen' > dlen + then return (Left newLen') + else Right `fmap` fromPtr dptr newLen' + in loop slen + + +-- | Perform an efficient check on a string, to quickly determine if +-- the string is in a particular normalization format. +-- +-- A 'Perhaps' result indicates that a more thorough check is +-- required, e.g. with 'isNormalized'. The user may have to put the +-- string in its normalized form and compare the results. +quickCheck :: NormalizationMode -> Text -> NormalizationCheckResult +quickCheck mode t = + unsafePerformIO . useAsPtr t $ \ptr len -> + fmap toNCR . handleError $ unorm_quickCheck ptr (fromIntegral len) + (toNM mode) + +-- | Indicate whether a string is in a given normalization form. +-- +-- Unlike 'quickCheck', this function returns a definitive result. +-- For 'NFD', 'NFKD', and 'FCD' normalization forms, both functions +-- work in exactly the same ways. For 'NFC' and 'NFKC' forms, where +-- 'quickCheck' may return 'Perhaps', this function will perform +-- further tests to arrive at a definitive result. +isNormalized :: NormalizationMode -> Text -> Bool +isNormalized mode t = + unsafePerformIO . useAsPtr t $ \ptr len -> + fmap asBool . handleError $ unorm_isNormalized ptr (fromIntegral len) + (toNM mode) + +-- | Compare two strings for canonical equivalence. Further options +-- include case-insensitive comparison and code point order (as +-- opposed to code unit order). +-- +-- Canonical equivalence between two strings is defined as their +-- normalized forms ('NFD' or 'NFC') being identical. This function +-- compares strings incrementally instead of normalizing (and +-- optionally case-folding) both strings entirely, improving +-- performance significantly. +-- +-- Bulk normalization is only necessary if the strings do not fulfill +-- the FCD conditions. Only in this case, and only if the strings are +-- relatively long, is memory allocated temporarily. For FCD strings +-- and short non-FCD strings there is no memory allocation. +compare :: [CompareOption] -> Text -> Text -> Ordering +compare opts a b = unsafePerformIO . + useAsPtr a $ \aptr alen -> + useAsPtr b $ \bptr blen -> + fmap asOrdering . handleError $ + unorm_compare aptr (fromIntegral alen) bptr (fromIntegral blen) + (reduceCompareOptions opts) + +foreign import ccall unsafe "hs_text_icu.h __hs_unorm_compare" unorm_compare + :: Ptr UChar -> Int32 -> Ptr UChar -> Int32 -> Word32 + -> Ptr UErrorCode -> IO Int32 + +foreign import ccall unsafe "hs_text_icu.h __hs_unorm_quickCheck" unorm_quickCheck + :: Ptr UChar -> Int32 -> UNormalizationMode -> Ptr UErrorCode + -> IO UNormalizationCheckResult + +foreign import ccall unsafe "hs_text_icu.h __hs_unorm_isNormalized" unorm_isNormalized + :: Ptr UChar -> Int32 -> UNormalizationMode -> Ptr UErrorCode -> IO UBool + +foreign import ccall unsafe "hs_text_icu.h __hs_unorm_normalize" unorm_normalize + :: Ptr UChar -> Int32 -> UNormalizationMode -> Int32 + -> Ptr UChar -> Int32 -> Ptr UErrorCode -> IO Int32 diff --git a/Data/Text/ICU/Normalizer.hsc b/Data/Text/ICU/Normalizer.hsc deleted file mode 100644 --- a/Data/Text/ICU/Normalizer.hsc +++ /dev/null @@ -1,303 +0,0 @@ -{-# LANGUAGE CPP, DeriveDataTypeable, ForeignFunctionInterface, - GeneralizedNewtypeDeriving #-} --- | --- Module : Data.Text.ICU.Normalizer --- Copyright : (c) Bryan O'Sullivan 2009 --- --- License : BSD-style --- Maintainer : bos@serpentine.com --- Stability : experimental --- Portability : GHC --- --- Character set normalization functions for Unicode, implemented as --- bindings to the International Components for Unicode (ICU) --- libraries. - -module Data.Text.ICU.Normalizer - ( - -- * Unicode normalization API - -- $api - NormalizationMode(..) - -- * Normalization functions - , normalize - -- * Normalization checks - , NormalizationCheckResult(..) - , quickCheck - , isNormalized - -- * Normalization-sensitive comparison - , CompareOption - , u_INPUT_IS_FCD - , u_COMPARE_CODE_POINT_ORDER - , u_COMPARE_IGNORE_CASE - , compare - ) where - -#ifdef mingw32_HOST_OS -#define U_HAVE_INTTYPES_H 1 -#endif - -#include - -import Control.Exception (throw) -import Control.Monad (when) -import Data.Text (Text) -import Data.Text.Foreign (fromPtr, useAsPtr) -import Data.Text.ICU.Error (u_BUFFER_OVERFLOW_ERROR) -import Data.Text.ICU.Error.Internal (UErrorCode, isFailure, handleError, withError) -import Data.Text.ICU.Internal (UBool, UChar, asBool, asOrdering) -import Data.Typeable (Typeable) -import Data.Int (Int32) -import Data.Word (Word32) -import Foreign.C.Types (CInt) -import Foreign.Marshal.Array (allocaArray) -import Foreign.Ptr (Ptr) -import System.IO.Unsafe (unsafePerformIO) -import Prelude hiding (compare) -import Data.List (foldl') -import Data.Bits ((.|.)) - --- $api --- --- 'normalize' transforms Unicode text into an equivalent composed or --- decomposed form, allowing for easier sorting and searching of text. --- 'normalize' supports the standard normalization forms described in --- , --- Unicode Standard Annex #15: Unicode Normalization Forms. --- --- Characters with accents or other adornments can be encoded in --- several different ways in Unicode. For example, take the character A-acute. --- In Unicode, this can be encoded as a single character (the --- \"composed\" form): --- --- @ --- 00C1 LATIN CAPITAL LETTER A WITH ACUTE --- @ --- --- or as two separate characters (the \"decomposed\" form): --- --- @ --- 0041 LATIN CAPITAL LETTER A --- 0301 COMBINING ACUTE ACCENT --- @ --- --- To a user of your program, however, both of these sequences should --- be treated as the same \"user-level\" character \"A with acute --- accent\". When you are searching or comparing text, you must --- ensure that these two sequences are treated equivalently. In --- addition, you must handle characters with more than one accent. --- Sometimes the order of a character's combining accents is --- significant, while in other cases accent sequences in different --- orders are really equivalent. --- --- Similarly, the string \"ffi\" can be encoded as three separate letters: --- --- @ --- 0066 LATIN SMALL LETTER F --- 0066 LATIN SMALL LETTER F --- 0069 LATIN SMALL LETTER I --- @ --- --- or as the single character --- --- @ --- FB03 LATIN SMALL LIGATURE FFI --- @ --- --- The \"ffi\" ligature is not a distinct semantic character, and --- strictly speaking it shouldn't be in Unicode at all, but it was --- included for compatibility with existing character sets that --- already provided it. The Unicode standard identifies such --- characters by giving them \"compatibility\" decompositions into the --- corresponding semantic characters. When sorting and searching, you --- will often want to use these mappings. --- --- 'normalize' helps solve these problems by transforming text into --- the canonical composed and decomposed forms as shown in the first --- example above. In addition, you can have it perform compatibility --- decompositions so that you can treat compatibility characters the --- same as their equivalents. Finally, 'normalize' rearranges accents --- into the proper canonical order, so that you do not have to worry --- about accent rearrangement on your own. --- --- Form 'FCD', \"Fast C or D\", is also designed for collation. It --- allows to work on strings that are not necessarily normalized with --- an algorithm (like in collation) that works under \"canonical --- closure\", i.e., it treats precomposed characters and their --- decomposed equivalents the same. --- --- It is not a normalization form because it does not provide for --- uniqueness of representation. Multiple strings may be canonically --- equivalent (their NFDs are identical) and may all conform to 'FCD' --- without being identical themselves. --- --- The form is defined such that the \"raw decomposition\", the --- recursive canonical decomposition of each character, results in a --- string that is canonically ordered. This means that precomposed --- characters are allowed for as long as their decompositions do not --- need canonical reordering. --- --- Its advantage for a process like collation is that all 'NFD' and --- most 'NFC' texts - and many unnormalized texts - already conform to --- 'FCD' and do not need to be normalized ('NFD') for such a --- process. The 'FCD' 'quickCheck' will return 'Yes' for most strings --- in practice. --- --- @'normalize' 'FCD'@ may be implemented with 'NFD'. --- --- For more details on 'FCD' see the collation design document: --- --- --- ICU collation performs either 'NFD' or 'FCD' normalization --- automatically if normalization is turned on for the collator --- object. Beyond collation and string search, normalized strings may --- be useful for string equivalence comparisons, --- transliteration/transcription, unique representations, etc. --- --- The W3C generally recommends to exchange texts in 'NFC'. Note also --- that most legacy character encodings use only precomposed forms and --- often do not encode any combining marks by themselves. For --- conversion to such character encodings the Unicode text needs to be --- normalized to 'NFC'. For more usage examples, see the Unicode --- Standard Annex. - -newtype CompareOption = CompareOption { - fromCompareOption :: Word32 - } deriving (Eq, Typeable) - -foldCompareOptions :: [CompareOption] -> Word32 -foldCompareOptions = foldl' orO 0 - where a `orO` b = a .|. fromCompareOption b - -#{enum CompareOption, CompareOption, - u_INPUT_IS_FCD = UNORM_INPUT_IS_FCD, - u_COMPARE_CODE_POINT_ORDER = U_COMPARE_CODE_POINT_ORDER, - u_COMPARE_IGNORE_CASE = U_COMPARE_IGNORE_CASE - } - -type UNormalizationMode = CInt - -data NormalizationMode - = None -- ^ No decomposition/composition. - | NFD -- ^ Canonical decomposition. - | NFKD -- ^ Compatibility decomposition. - | NFC -- ^ Canonical decomposition followed by canonical composition. - | NFKC -- ^ Compatibility decomposition followed by canonical composition. - | FCD -- ^ \"Fast C or D\" form. - deriving (Eq, Show, Enum, Typeable) - -toNM :: NormalizationMode -> UNormalizationMode -toNM None = #const UNORM_NONE -toNM NFD = #const UNORM_NFD -toNM NFKD = #const UNORM_NFKD -toNM NFC = #const UNORM_NFC -toNM NFKC = #const UNORM_NFKC -toNM FCD = #const UNORM_FCD - -type UNormalizationCheckResult = CInt - --- | Result of a fast normalization check using 'quickCheck'. -data NormalizationCheckResult - = No -- ^ Text is not normalized. - | Perhaps -- ^ It cannot be determined whether text is in normalized - -- form without further thorough checks. - | Yes -- ^ Text is in normalized form. - deriving (Eq, Show, Enum, Typeable) - -toNCR :: UNormalizationCheckResult -> NormalizationCheckResult -toNCR (#const UNORM_NO) = No -toNCR (#const UNORM_MAYBE) = Perhaps -toNCR (#const UNORM_YES) = Yes -toNCR _ = error "toNormalizationCheckResult" - --- | Normalize a string according the specified normalization mode. -normalize :: NormalizationMode -> Text -> Text -normalize mode t = unsafePerformIO . useAsPtr t $ \sptr slen -> - let slen' = fromIntegral slen - mode' = toNM mode - loop dlen = - (either loop return =<<) . - allocaArray dlen $ \dptr -> do - (err, newLen) <- withError $ - unorm_normalize sptr slen' mode' 0 dptr (fromIntegral dlen) - when (isFailure err && err /= u_BUFFER_OVERFLOW_ERROR) $ - throw err - let newLen' = fromIntegral newLen - if newLen' > dlen - then return (Left newLen') - else Right `fmap` fromPtr dptr newLen' - in loop slen - - --- | Perform an efficient check on a string, to quickly determine if --- the string is in a particular normalization format. --- --- A 'Perhaps' result indicates that a more thorough check is --- required, e.g. with 'isNormalized'. The user may have to put the --- string in its normalized form and compare the results. -quickCheck :: NormalizationMode -> Text -> NormalizationCheckResult -quickCheck mode t = - unsafePerformIO . useAsPtr t $ \ptr len -> - fmap toNCR . handleError $ unorm_quickCheck ptr (fromIntegral len) - (toNM mode) - --- | Indicate whether a string is in a given normalization form. --- --- Unlike 'quickCheck', this function returns a definitive result. --- For 'NFD', 'NFKD', and 'FCD' normalization forms, both functions --- work in exactly the same ways. For 'NFC' and 'NFKC' forms, where --- 'quickCheck' may return 'Perhaps', this function will perform --- further tests to arrive at a definitive result. -isNormalized :: NormalizationMode -> Text -> Bool -isNormalized mode t = - unsafePerformIO . useAsPtr t $ \ptr len -> - fmap asBool . handleError $ unorm_isNormalized ptr (fromIntegral len) - (toNM mode) - --- | Compare two strings for canonical equivalence. --- Further options include case-insensitive comparison and --- code point order (as opposed to code unit order). --- --- Canonical equivalence between two strings is defined as their normalized --- forms (NFD or NFC) being identical. --- This function compares strings incrementally instead of normalizing --- (and optionally case-folding) both strings entirely, --- improving performance significantly. --- --- Bulk normalization is only necessary if the strings do not fulfill the FCD --- conditions. Only in this case, and only if the strings are relatively long, --- is memory allocated temporarily. --- For FCD strings and short non-FCD strings there is no memory allocation. --- --- Options: --- --- ['u_INPUT_IS_FCD'] Set if the caller knows that both strings fulfill the FCD conditions. --- If not set, the function will 'quickCheck' for FCD --- and normalize if necessary. --- --- ['u_COMPARE_CODE_POINT_ORDER'] Set to choose code point order instead of code unit order. --- --- ['u_COMPARE_IGNORE_CASE'] Set to compare strings case-insensitively using case folding, --- instead of case-sensitively. --- If set, then the following case folding options are used. -compare :: [CompareOption] -> Text -> Text -> Ordering -compare opts a b = unsafePerformIO . - useAsPtr a $ \aptr alen -> - useAsPtr b $ \bptr blen -> - fmap asOrdering . handleError $ - unorm_compare aptr (fromIntegral alen) bptr (fromIntegral blen) - (foldCompareOptions opts) - -foreign import ccall unsafe "hs_text_icu.h __hs_unorm_compare" unorm_compare - :: Ptr UChar -> Int32 -> Ptr UChar -> Int32 -> Word32 - -> Ptr UErrorCode -> IO Int32 - -foreign import ccall unsafe "hs_text_icu.h __hs_unorm_quickCheck" unorm_quickCheck - :: Ptr UChar -> Int32 -> UNormalizationMode -> Ptr UErrorCode - -> IO UNormalizationCheckResult - -foreign import ccall unsafe "hs_text_icu.h __hs_unorm_isNormalized" unorm_isNormalized - :: Ptr UChar -> Int32 -> UNormalizationMode -> Ptr UErrorCode -> IO UBool - -foreign import ccall unsafe "hs_text_icu.h __hs_unorm_normalize" unorm_normalize - :: Ptr UChar -> Int32 -> UNormalizationMode -> Int32 - -> Ptr UChar -> Int32 -> Ptr UErrorCode -> IO Int32 diff --git a/text-icu.cabal b/text-icu.cabal --- a/text-icu.cabal +++ b/text-icu.cabal @@ -1,5 +1,5 @@ name: text-icu -version: 0.2.0.0 +version: 0.3.0.0 synopsis: Bindings to the ICU library description: Haskell bindings to the International Components for Unicode (ICU) libraries. These libraries provide @@ -21,11 +21,11 @@ build-depends: base >= 4 exposed-modules: - Data.Text.ICU.Converter + Data.Text.ICU.Convert Data.Text.ICU.Error - Data.Text.ICU.Normalizer + Data.Text.ICU.Normalize other-modules: - Data.Text.ICU.Converter.Internal + Data.Text.ICU.Convert.Internal Data.Text.ICU.Error.Internal Data.Text.ICU.Internal c-sources: cbits/text_icu.c