packages feed

text-icu 0.6.3.5 → 0.6.3.6

raw patch · 14 files changed

+134/−87 lines, 14 filesdep +HUnitdep +QuickCheckdep +arraydep ~basedep ~text

Dependencies added: HUnit, QuickCheck, array, deepseq, directory, ghc-prim, random, test-framework, test-framework-hunit, test-framework-quickcheck2, text-icu

Dependency ranges changed: base, text

Files

Data/Text/ICU.hs view
@@ -58,6 +58,7 @@     -- $collate     , Collator     , collator+    , collatorWith     , collate     , collateIter     , sortKey@@ -133,10 +134,10 @@ --   third word in the document). -- -- The 'Breaker' type was designed to support these kinds of--- tasks. +-- tasks. -- -- For the impure boundary analysis API (which is richer, but less--- easy to use than the pure API), see the 'Data.Text.ICU.Break'+-- easy to use than the pure API), see the "Data.Text.ICU.Break" -- module.  The impure API supports some uses that may be less -- efficient via the pure API, including: --@@ -150,7 +151,7 @@ -- $collate -- -- For the impure collation API (which is richer, but less easy to--- use than the pure API), see the 'Data.Text.ICU.Collate'+-- use than the pure API), see the "Data.Text.ICU.Collate" -- module.  -- $group
Data/Text/ICU/Collate.hsc view
@@ -30,6 +30,7 @@     , getAttribute     , setAttribute     , sortKey+    , clone     , freeze     ) where @@ -289,11 +290,17 @@ -- Subsequent changes to the 'MCollator' will not affect the state of -- the returned 'Collator'. freeze :: MCollator -> IO Collator-freeze c = do+freeze = fmap C . clone++-- | Make a copy of a mutable 'MCollator'.+-- Subsequent changes to the input 'MCollator' will not affect the state of+-- the returned 'MCollator'.+clone :: MCollator -> IO MCollator+clone c = do   p <- withCollator c $ \cptr ->     with (#const U_COL_SAFECLONE_BUFFERSIZE)       (handleError . ucol_safeClone cptr nullPtr)-  C `fmap` wrap p+  wrap p  foreign import ccall unsafe "hs_text_icu.h __hs_ucol_open" ucol_open     :: CString -> Ptr UErrorCode -> IO (Ptr UCollator)
Data/Text/ICU/Collate/Pure.hs view
@@ -13,7 +13,7 @@ -- libraries. -- -- For the impure collation API (which is richer, but less easy to--- use), see the 'Data.Text.ICU.CollateO' module.+-- use), see the "Data.Text.ICU.Collate" module.  module Data.Text.ICU.Collate.Pure     (@@ -21,12 +21,14 @@     -- $api       Collator     , collator+    , collatorWith     , collate     , collateIter     , sortKey     , uca     ) where +import Control.Monad (forM_) import Data.ByteString (ByteString) import Data.Text (Text) import Data.Text.ICU.Collate.Internal (Collator(..))@@ -36,13 +38,20 @@  -- $api ---                         + -- | Create an immutable 'Collator' for comparing strings. -- -- If 'Root' is passed as the locale, UCA collation rules will be -- used. collator :: LocaleName -> Collator collator loc = unsafePerformIO $ C `fmap` IO.open loc++-- | Create an immutable 'Collator' with the given 'Attribute's.+collatorWith :: LocaleName -> [IO.Attribute] -> Collator+collatorWith loc atts = unsafePerformIO $ do+  mc <- IO.open loc+  forM_ atts $ IO.setAttribute mc+  return (C mc)  -- | Compare two strings. collate :: Collator -> Text -> Text -> Ordering
Data/Text/ICU/Convert.hs view
@@ -120,7 +120,7 @@   unsafePerformIO . unsafeUseAsCStringLen bs $ \(sptr, slen) ->     withConverter cnv $ \cptr -> do       let capacity = slen * 2-      allocaArray capacity $ \tptr -> +      allocaArray capacity $ \tptr ->         fromPtr tptr =<< (fmap fromIntegral . handleError $                           ucnv_toUChars cptr tptr (fromIntegral capacity) sptr                                         (fromIntegral slen))
Data/Text/ICU/Error/Internal.hsc view
@@ -37,7 +37,7 @@ #include <unicode/utypes.h>  type UErrorCode = CInt-    + -- | ICU error type.  This is an instance of the 'Exception' type -- class.  A value of this type may be thrown as an exception by most -- ICU functions.
Data/Text/ICU/Internal.hsc view
@@ -87,7 +87,7 @@                 -- and the root resource, see                 -- <http://userguide.icu-project.org/locale/resources>.                 | Locale String -- ^ A specific locale.-                | Current       -- ^ The program's current locale. +                | Current       -- ^ The program's current locale.                   deriving (Eq, Ord, Read, Show)  instance IsString LocaleName where
Data/Text/ICU/Iterator.hs view
@@ -61,7 +61,8 @@ {-# INLINE fromText #-}  -- | Construct a 'CharIterator' from a Unicode string encoded as a--- UTF-8 'ByteString'.+-- UTF-8 'ByteString'. The validity of the encoded string is *not*+-- checked. fromUtf8 :: ByteString -> CharIterator fromUtf8 = CIUTF8 {-# INLINE fromUtf8 #-}
Data/Text/ICU/Normalize.hsc view
@@ -192,7 +192,7 @@     | 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@@ -209,8 +209,8 @@   in handleOverflowError (fromIntegral slen)      (\dptr dlen -> unorm_normalize sptr slen' mode' 0 dptr (fromIntegral dlen))      (\dptr dlen -> fromPtr (castPtr dptr) (fromIntegral dlen))-    -      ++ -- | Perform an efficient check on a string, to quickly determine if -- the string is in a particular normalization form. --
Data/Text/ICU/Regex.hs view
@@ -63,7 +63,7 @@ import Foreign.Marshal.Alloc (alloca) import Foreign.Storable (peek) import System.IO.Unsafe (unsafePerformIO)-                   + instance Show Regex where     show re = "Regex " ++ show (pattern re)
Data/Text/ICU/Text.hs view
@@ -22,11 +22,10 @@ import Data.Int (Int32) import Data.Text (Text) import Data.Text.Foreign (fromPtr, useAsPtr)-import Data.Text.ICU.Error.Internal (UErrorCode, handleError, handleOverflowError)+import Data.Text.ICU.Error.Internal (UErrorCode, handleOverflowError) import Data.Text.ICU.Internal (LocaleName, UChar, withLocaleName) import Data.Word (Word32) import Foreign.C.String (CString)-import Foreign.Marshal.Array (allocaArray) import Foreign.Ptr (Ptr, castPtr) import System.IO.Unsafe (unsafePerformIO) @@ -48,14 +47,9 @@ toCaseFold excludeI s = unsafePerformIO .   useAsPtr s $ \sptr slen -> do     let opts = fromIntegral . fromEnum $ excludeI-        go len = allocaArray len $ \dptr -> do-          n <- fmap fromIntegral . handleError $-               u_strFoldCase dptr (fromIntegral len) sptr-                                  (fromIntegral slen) opts-          if n > len-            then go n-            else fromPtr dptr (fromIntegral n)-    go (fromIntegral slen)+    handleOverflowError (fromIntegral slen)+        (\dptr dlen -> u_strFoldCase dptr dlen sptr (fromIntegral slen) opts)+        (\dptr dlen -> fromPtr (castPtr dptr) (fromIntegral dlen))  type CaseMapper = Ptr UChar -> Int32 -> Ptr UChar -> Int32 -> CString                 -> Ptr UErrorCode -> IO Int32
+ benchmarks/Breaker.hs view
@@ -0,0 +1,50 @@+-- Estimate the time difference between creating a breaker.++{-# LANGUAGE OverloadedStrings #-}++import Control.Monad+import qualified Data.Text as T+import Data.Text.IO as T+import Data.Text.ICU.Break as IO+import Data.Text.ICU as ICU+import System.Environment++consume b = go+  where+    go = do+      m <- next b+      case m of+        Nothing -> return ()+        Just _ -> go++manyBreakers (t:ts) = do+  b <- IO.breakWord "en" t+  consume b+  manyBreakers ts+manyBreakers _ = return ()++oneBreaker ts = do+  b <- IO.breakWord "en" ""+  forM_ ts $ \t -> do+    setText b t+    consume b++cloneBreakers ts = do+  b <- IO.breakWord "en" ""+  forM_ ts $ \t -> do+    b' <- clone b+    setText b' t+    consume b'++pureBreaker ts = do+  let b = ICU.breakWord "en"+  forM_ ts $ \t -> length (breaks b t) `seq` return ()++main = do+  (kind:files) <- getArgs+  let act = case kind of+              "one" -> oneBreaker+              "many" -> manyBreakers+              "clone" -> cloneBreakers+              "pure" -> pureBreaker+  forM_ files $ \f -> T.readFile f >>= act . T.lines
+ tests/Tests.hs view
@@ -0,0 +1,8 @@+module Main (main) where++import Test.Framework (defaultMain)++import qualified Properties++main :: IO ()+main = defaultMain [Properties.tests]
− tests/benchmarks/Breaker.hs 
@@ -1,50 +0,0 @@--- Estimate the time difference between creating a breaker.--{-# LANGUAGE OverloadedStrings #-}--import Control.Monad-import qualified Data.Text as T-import Data.Text.IO as T-import Data.Text.ICU.Break as IO-import Data.Text.ICU as ICU-import System.Environment--consume b = go-  where-    go = do-      m <- next b-      case m of-        Nothing -> return ()-        Just _ -> go--manyBreakers (t:ts) = do-  b <- IO.breakWord "en" t-  consume b-  manyBreakers ts-manyBreakers _ = return ()--oneBreaker ts = do-  b <- IO.breakWord "en" ""-  forM_ ts $ \t -> do-    setText b t-    consume b--cloneBreakers ts = do-  b <- IO.breakWord "en" ""-  forM_ ts $ \t -> do-    b' <- clone b-    setText b' t-    consume b'--pureBreaker ts = do-  let b = ICU.breakWord "en"-  forM_ ts $ \t -> length (breaks b t) `seq` return ()--main = do-  (kind:files) <- getArgs-  let act = case kind of-              "one" -> oneBreaker-              "many" -> manyBreakers-              "clone" -> cloneBreakers-              "pure" -> pureBreaker-  forM_ files $ \f -> T.readFile f >>= act . T.lines
text-icu.cabal view
@@ -1,8 +1,8 @@ name:           text-icu-version:        0.6.3.5+version:        0.6.3.6 synopsis:       Bindings to the ICU library-homepage:       https://bitbucket.org/bos/text-icu-bug-reports:    https://bitbucket.org/bos/text-icu/issues+homepage:       https://github.com/bos/text-icu+bug-reports:    https://github.com/bos/text-icu/issues description:   Haskell bindings to the International Components for Unicode (ICU)   libraries.  These libraries provide robust and full-featured Unicode@@ -30,19 +30,21 @@   .   * Regular expression search and replace. maintainer:     Bryan O'Sullivan <bos@serpentine.com>-copyright:      2009, 2010 Bryan O'Sullivan+copyright:      2009-2013 Bryan O'Sullivan category:       Data, Text license:        BSD3 license-file:   LICENSE build-type:     Simple-cabal-version:  >= 1.6+cabal-version:  >= 1.10 extra-source-files:-  README.markdown include/hs_text_icu.h tests/benchmarks/Breaker.hs+  README.markdown include/hs_text_icu.h benchmarks/Breaker.hs  library-  build-depends:     base < 5, bytestring, text >= 0.9.1.0 && <= 0.12.0.0-  if impl(ghc >= 6.10)-    build-depends:   base >= 4+  default-language:  Haskell98+  build-depends:+    base >= 4 && < 5,+    bytestring,+    text >= 0.9.1.0    exposed-modules:       Data.Text.ICU@@ -79,10 +81,35 @@   if impl(ghc >= 6.8)     ghc-options: -fwarn-tabs -source-repository head-  type:     mercurial-  location: https://bitbucket.org/bos/text-icu+test-suite tests+  default-language: Haskell98+  type:             exitcode-stdio-1.0+  hs-source-dirs:   tests+  main-is:          Tests.hs +  ghc-options:+    -Wall -threaded -O0 -rtsopts++  build-depends:+    HUnit >= 1.2,+    QuickCheck >= 2.4,+    array,+    base >= 4 && < 5,+    bytestring,+    deepseq,+    directory,+    ghc-prim,+    random,+    test-framework >= 0.4,+    test-framework-hunit >= 0.2,+    test-framework-quickcheck2 >= 0.2,+    text,+    text-icu+ source-repository head   type:     git   location: https://github.com/bos/text-icu++source-repository head+  type:     mercurial+  location: https://bitbucket.org/bos/text-icu