master..7534f3c · text

git.iko.soy/text

28 files changed+234−540

unifiedsplit

.gitignore−1 .hgtags−2 Data/Text.hs+15−43 Data/Text/Array.hs+4−5 Data/Text/Encoding.hs+18−7 Data/Text/Encoding/Error.hs+1−3 Data/Text/Internal/Builder.hs+2−17 Data/Text/Internal/Builder/Functions.hs+1−2 Data/Text/Internal/Builder/Int/Digits.hs+1−1 Data/Text/Internal/Fusion.hs+17−27 Data/Text/Internal/Fusion/CaseMapping.hs+112−286 Data/Text/Internal/Fusion/Common.hs+5−5 Data/Text/Internal/Read.hs+3−3 Data/Text/Lazy.hs+8−34 Data/Text/Lazy/Builder.hs+1−1 Data/Text/Lazy/Builder/Int.hs+4−4 Data/Text/Lazy/Encoding.hs+16−6 Data/Text/Lazy/Read.hs+2−4 Data/Text/Read.hs+1−1 benchmarks/haskell/Benchmarks.hs+1−1 benchmarks/haskell/Benchmarks/Pure.hs−7 benchmarks/haskell/Benchmarks/ReadNumbers.hs+5−2 benchmarks/haskell/Benchmarks/Stream.hs+5−16 benchmarks/text-benchmarks.cabal+3−13 changelog.md+1−28 tests/literal-rule-test.sh+1−1 tests/text-tests.cabal+1−1 text.cabal+6−19

.gitignore−1

@@ -1,3 +1,2 @@

11dist

22cabal-dev

3−cabal.sandbox.config

.hgtags−2

@@ -62,5 +62,3 @@ f8a60279237c1c28e094868740d9188dd94fcc9e 1.2.0.0

626278227a84740b70dcd4cf7a65f3bcf603d87e48e2 1.2.1.1

636340f268e6735749ef36f487e1d928eaa957bb431d 1.2.1.2

6464631fd055e27fa10983e17e9ad36d1b285b85c661 1.2.1.3

65−8221a68ed5ec37028357df9c6c25f52320e54ad9 1.2.2.0

66−ce1c5ac65eb9f5580114b4e380092b05a485e95d 1.2.2.1

Data/Text.hs+15−43

@@ -215,13 +215,10 @@ import qualified Data.Text.Array as A

215215import qualified Data.List as L

216216import Data.Binary (Binary(get, put))

217217import Data.Monoid (Monoid(..))

218−#if MIN_VERSION_base(4,9,0)

219−import Data.Semigroup (Semigroup(..))

220−#endif

221218import Data.String (IsString(..))

222219import qualified Data.Text.Internal.Fusion as S

223220import qualified Data.Text.Internal.Fusion.Common as S

224−import Data.Text.Encoding (decodeUtf8', encodeUtf8)

221+import Data.Text.Encoding (decodeUtf8, encodeUtf8)

225222import Data.Text.Internal.Fusion (stream, reverseStream, unstream)

226223import Data.Text.Internal.Private (span_)

227224import Data.Text.Internal (Text(..), empty, firstf, mul, safe, text)

@@ -238,13 +235,10 @@ import Data.ByteString (ByteString)

238235import qualified Data.Text.Lazy as L

239236import Data.Int (Int64)

240237#endif

241−import GHC.Base (eqInt, neInt, gtInt, geInt, ltInt, leInt)

242238#if __GLASGOW_HASKELL__ >= 708

243239import qualified GHC.Exts as Exts

244240#endif

245−#if MIN_VERSION_base(4,7,0)

246241import Text.Printf (PrintfArg, formatArg, formatString)

247−#endif

248242

249243-- $strict

250244--

@@ -333,21 +327,9 @@ instance Ord Text where

333327instance Read Text where

334328 readsPrec p str = [(pack x,y) | (x,y) <- readsPrec p str]

335329

336−#if MIN_VERSION_base(4,9,0)

337−-- Semigroup orphan instances for older GHCs are provided by

338−-- 'semigroups` package

339−

340−instance Semigroup Text where

341− (<>) = append

342−#endif

343−

344330instance Monoid Text where

345331 mempty = empty

346−#if MIN_VERSION_base(4,9,0)

347− mappend = (<>) -- future-proof definition

348−#else

349332 mappend = append

350−#endif

351333 mconcat = concat

352334

353335instance IsString Text where

@@ -366,11 +348,7 @@ instance NFData Text where rnf !_ = ()

366348

367349instance Binary Text where

368350 put t = put (encodeUtf8 t)

369− get = do

370− bs <- get

371− case decodeUtf8' bs of

372− P.Left exn -> P.fail (P.show exn)

373− P.Right a -> P.return a

351+ get = P.fmap decodeUtf8 get

374352

375353-- | This instance preserves data abstraction at the cost of inefficiency.

376354-- We omit reflection services for the sake of data abstraction.

@@ -395,11 +373,8 @@ instance Data Text where

395373 _ -> P.error "gunfold"

396374 dataTypeOf _ = textDataType

397375

398−#if MIN_VERSION_base(4,7,0)

399−-- | Only defined for @base-4.7.0.0@ and later

400376instance PrintfArg Text where

401377 formatArg txt = formatString $ unpack txt

402−#endif

403378

404379packConstr :: Constr

405380packConstr = mkConstr textDataType "pack" [] Prefix

@@ -486,8 +461,8 @@ head t = S.head (stream t)

486461uncons :: Text -> Maybe (Char, Text)

487462uncons t@(Text arr off len)

488463 | len <= 0 = Nothing

489− | otherwise = Just $ let !(Iter c d) = iter t 0

490− in (c, text arr (off+d) (len-d))

464+ | otherwise = Just (c, text arr (off+d) (len-d))

465+ where Iter c d = iter t 0

491466{-# INLINE [1] uncons #-}

492467

493468-- | Lifted from Control.Arrow and specialized.

@@ -572,9 +547,7 @@ isSingleton = S.isSingleton . stream

572547-- Subject to fusion.

573548length :: Text -> Int

574549length t = S.length (stream t)

575−{-# INLINE [0] length #-}

576−-- length needs to be phased after the compareN/length rules otherwise

577−-- it may inline before the rules have an opportunity to fire.

550+{-# INLINE length #-}

578551

579552-- | /O(n)/ Compare the count of characters in a 'Text' to a number.

580553-- Subject to fusion.

@@ -593,32 +566,32 @@ compareLength t n = S.compareLengthI (stream t) n

593566

594567{-# RULES

595568"TEXT ==N/length -> compareLength/==EQ" [~1] forall t n.

596− eqInt (length t) n = compareLength t n == EQ

569+ (==) (length t) n = compareLength t n == EQ

597570 #-}

598571

599572{-# RULES

600573"TEXT /=N/length -> compareLength//=EQ" [~1] forall t n.

601− neInt (length t) n = compareLength t n /= EQ

574+ (/=) (length t) n = compareLength t n /= EQ

602575 #-}

603576

604577{-# RULES

605578"TEXT <N/length -> compareLength/==LT" [~1] forall t n.

606− ltInt (length t) n = compareLength t n == LT

579+ (<) (length t) n = compareLength t n == LT

607580 #-}

608581

609582{-# RULES

610583"TEXT <=N/length -> compareLength//=GT" [~1] forall t n.

611− leInt (length t) n = compareLength t n /= GT

584+ (<=) (length t) n = compareLength t n /= GT

612585 #-}

613586

614587{-# RULES

615588"TEXT >N/length -> compareLength/==GT" [~1] forall t n.

616− gtInt (length t) n = compareLength t n == GT

589+ (>) (length t) n = compareLength t n == GT

617590 #-}

618591

619592{-# RULES

620593"TEXT >=N/length -> compareLength//=LT" [~1] forall t n.

621− geInt (length t) n = compareLength t n /= LT

594+ (>=) (length t) n = compareLength t n /= LT

622595 #-}

623596

624597-- -----------------------------------------------------------------------------

@@ -915,13 +888,13 @@ concatMap f = concat . foldr ((:) . f) []

915888{-# INLINE concatMap #-}

916889

917890-- | /O(n)/ 'any' @p@ @t@ determines whether any character in the

918−-- 'Text' @t@ satisfies the predicate @p@. Subject to fusion.

891+-- 'Text' @t@ satisifes the predicate @p@. Subject to fusion.

919892any :: (Char -> Bool) -> Text -> Bool

920893any p t = S.any p (stream t)

921894{-# INLINE any #-}

922895

923896-- | /O(n)/ 'all' @p@ @t@ determines whether all characters in the

924−-- 'Text' @t@ satisfy the predicate @p@. Subject to fusion.

897+-- 'Text' @t@ satisify the predicate @p@. Subject to fusion.

925898all :: (Char -> Bool) -> Text -> Bool

926899all p t = S.all p (stream t)

927900{-# INLINE all #-}

@@ -1191,9 +1164,8 @@ dropWhile p t@(Text arr off len) = loop 0 0

11911164 #-}

11921165

11931166-- | /O(n)/ 'dropWhileEnd' @p@ @t@ returns the prefix remaining after

1194−-- dropping characters that satisfy the predicate @p@ from the end of

1167+-- dropping characters that fail the predicate @p@ from the end of

11951168-- @t@. Subject to fusion.

1196−--

11971169-- Examples:

11981170--

11991171-- > dropWhileEnd (=='.') "foo..." == "foo"

@@ -1213,7 +1185,7 @@ dropWhileEnd p t@(Text arr off len) = loop (len-1) len

12131185 #-}

12141186

12151187-- | /O(n)/ 'dropAround' @p@ @t@ returns the substring remaining after

1216−-- dropping characters that satisfy the predicate @p@ from both the

1188+-- dropping characters that fail the predicate @p@ from both the

12171189-- beginning and end of @t@. Subject to fusion.

12181190dropAround :: (Char -> Bool) -> Text -> Text

12191191dropAround p = dropWhile p . dropWhileEnd p

Data/Text/Array.hs+4−5

@@ -20,7 +20,7 @@

2020-- > import qualified Data.Text.Array as A

2121--

2222-- The names in this module resemble those in the 'Data.Array' family

23−-- of modules, but are shorter due to the assumption of qualified

23+-- of modules, but are shorter due to the assumption of qualifid

2424-- naming.

2525module Data.Text.Array

2626 (

@@ -74,7 +74,7 @@ import Foreign.C.Types (CInt, CSize)

7474#endif

7575import GHC.Base (ByteArray#, MutableByteArray#, Int(..),

7676 indexWord16Array#, newByteArray#,

77− unsafeFreezeByteArray#, writeWord16Array#)

77+ unsafeCoerce#, writeWord16Array#)

7878import GHC.ST (ST(..), runST)

7979import GHC.Word (Word16(..))

8080import Prelude hiding (length, read)

@@ -130,9 +130,8 @@ array_size_error = error "Data.Text.Array.new: size overflow"

130130

131131-- | Freeze a mutable array. Do not mutate the 'MArray' afterwards!

132132unsafeFreeze :: MArray s -> ST s Array

133−unsafeFreeze MArray{..} = ST $ \s1# ->

134− case unsafeFreezeByteArray# maBA s1# of

135− (# s2#, ba# #) -> (# s2#, Array ba#

133+unsafeFreeze MArray{..} = ST $ \s# ->

134+ (# s#, Array (unsafeCoerce# maBA)

136135#if defined(ASSERTS)

137136 maLen

138137#endif

Data/Text/Encoding.hs+18−7

@@ -55,9 +55,13 @@ module Data.Text.Encoding

5555 , encodeUtf32LE

5656 , encodeUtf32BE

5757

58+#if MIN_VERSION_bytestring(0,10,4)

5859 -- * Encoding Text using ByteString Builders

60+ -- | /Note/ that these functions are only available if built against

61+ -- @bytestring >= 0.10.4.0@.

5962 , encodeUtf8Builder

6063 , encodeUtf8BuilderEscaped

64+#endif

6165 ) where

6266

6367#if __GLASGOW_HASKELL__ >= 702

@@ -66,15 +70,24 @@ import Control.Monad.ST.Unsafe (unsafeIOToST, unsafeSTToIO)

6670import Control.Monad.ST (unsafeIOToST, unsafeSTToIO)

6771#endif

6872

73+#if MIN_VERSION_bytestring(0,10,4)

74+import Data.Bits ((.&.))

75+import Data.Text.Internal.Unsafe.Char (ord)

76+import qualified Data.ByteString.Builder as B

77+import qualified Data.ByteString.Builder.Internal as B hiding (empty, append)

78+import qualified Data.ByteString.Builder.Prim as BP

79+import qualified Data.ByteString.Builder.Prim.Internal as BP

80+import qualified Data.Text.Internal.Encoding.Utf16 as U16

81+#endif

82+

6983import Control.Exception (evaluate, try)

7084import Control.Monad.ST (runST)

71−import Data.Bits ((.&.))

7285import Data.ByteString as B

7386import Data.ByteString.Internal as B hiding (c2w)

7487import Data.Text.Encoding.Error (OnDecodeError, UnicodeException, strictDecode)

7588import Data.Text.Internal (Text(..), safe, text)

7689import Data.Text.Internal.Private (runText)

77−import Data.Text.Internal.Unsafe.Char (ord, unsafeWrite)

90+import Data.Text.Internal.Unsafe.Char (unsafeWrite)

7891import Data.Text.Internal.Unsafe.Shift (shiftR)

7992import Data.Text.Show ()

8093import Data.Text.Unsafe (unsafeDupablePerformIO)

@@ -85,13 +98,8 @@ import Foreign.Marshal.Utils (with)

8598import Foreign.Ptr (Ptr, minusPtr, nullPtr, plusPtr)

8699import Foreign.Storable (Storable, peek, poke)

87100import GHC.Base (ByteArray#, MutableByteArray#)

88−import qualified Data.ByteString.Builder as B

89−import qualified Data.ByteString.Builder.Internal as B hiding (empty, append)

90−import qualified Data.ByteString.Builder.Prim as BP

91−import qualified Data.ByteString.Builder.Prim.Internal as BP

92101import qualified Data.Text.Array as A

93102import qualified Data.Text.Internal.Encoding.Fusion as E

94−import qualified Data.Text.Internal.Encoding.Utf16 as U16

95103import qualified Data.Text.Internal.Fusion as F

96104

97105#include "text_cbits.h"

@@ -307,6 +315,8 @@ decodeUtf8' :: ByteString -> Either UnicodeException Text

307315decodeUtf8' = unsafeDupablePerformIO . try . evaluate . decodeUtf8With strictDecode

308316{-# INLINE decodeUtf8' #-}

309317

318+#if MIN_VERSION_bytestring(0,10,4)

319+

310320-- | Encode text to a ByteString 'B.Builder' using UTF-8 encoding.

311321encodeUtf8Builder :: Text -> B.Builder

312322encodeUtf8Builder = encodeUtf8BuilderEscaped (BP.liftFixedToBounded BP.word8)

@@ -367,6 +377,7 @@ encodeUtf8BuilderEscaped be =

367377 outerLoop i (B.BufferRange op ope)

368378 where

369379 poke8 j v = poke (op `plusPtr` j) (fromIntegral v :: Word8)

380+#endif

370381

371382-- | Encode text using UTF-8 encoding.

372383encodeUtf8 :: Text -> ByteString

Data/Text/Encoding/Error.hs+1−3

@@ -1,7 +1,5 @@

11{-# LANGUAGE CPP, DeriveDataTypeable #-}

2−#if __GLASGOW_HASKELL__ >= 704

3−{-# LANGUAGE Safe #-}

4−#elif __GLASGOW_HASKELL__ >= 702

2+#if __GLASGOW_HASKELL__ >= 702

53{-# LANGUAGE Trustworthy #-}

64#endif

75-- |

Data/Text/Internal/Builder.hs+2−17

@@ -6,7 +6,7 @@

66-- Module : Data.Text.Internal.Builder

9−-- License : BSD-style (see LICENSE)

9+-- License : BSD3-style (see LICENSE)

1010--

1111-- Maintainer : Johan Tibell <johan.tibell@gmail.com>

1212-- Stability : experimental

@@ -59,9 +59,6 @@ module Data.Text.Internal.Builder

5959

6060import Control.Monad.ST (ST, runST)

6161import Data.Monoid (Monoid(..))

62−#if MIN_VERSION_base(4,9,0)

63−import Data.Semigroup (Semigroup(..))

64−#endif

6562import Data.Text.Internal (Text(..))

6663import Data.Text.Internal.Lazy (smallChunkSize)

6764import Data.Text.Unsafe (inlineInterleaveST)

@@ -92,22 +89,12 @@ newtype Builder = Builder {

9289 -> ST s [S.Text]

9390 }

9491

95−#if MIN_VERSION_base(4,9,0)

96−instance Semigroup Builder where

97− (<>) = append

98− {-# INLINE (<>) #-}

99−#endif

100−

10192instance Monoid Builder where

10293 mempty = empty

10394 {-# INLINE mempty #-}

104−#if MIN_VERSION_base(4,9,0)

105− mappend = (<>) -- future-proof definition

106−#else

10795 mappend = append

108−#endif

10996 {-# INLINE mappend #-}

110− mconcat = foldr mappend Data.Monoid.mempty

97+ mconcat = foldr mappend mempty

11198 {-# INLINE mconcat #-}

11299

113100instance String.IsString Builder where

@@ -242,8 +229,6 @@ flush = Builder $ \ k buf@(Buffer p o u l) ->

242229 !t = Text arr o u

243230 ts <- inlineInterleaveST (k b)

244231 return $! t : ts

245−{-# INLINE [1] flush #-}

246−-- defer inlining so that flush/flush rule may fire.

247232

248233------------------------------------------------------------------------

249234

Data/Text/Internal/Builder/Functions.hs+1−2

@@ -23,8 +23,7 @@ module Data.Text.Internal.Builder.Functions

2323

2424import Data.Monoid (mappend)

2525import Data.Text.Lazy.Builder (Builder)

26−import GHC.Base (chr#,ord#,(+#),Int(I#),Char(C#))

27−import Prelude ()

26+import GHC.Base

2827

2928-- | Unsafe conversion for decimal digits.

3029{-# INLINE i2d #-}

Data/Text/Internal/Builder/Int/Digits.hs+1−1

@@ -2,7 +2,7 @@

33-- Module: Data.Text.Internal.Builder.Int.Digits

5−-- License: BSD-style

5+-- License: BSD3

66-- Maintainer: Bryan O'Sullivan <bos@serpentine.com>

77-- Stability: experimental

88-- Portability: portable

Data/Text/Internal/Fusion.hs+17−27

@@ -98,35 +98,25 @@ reverseStream (Text arr off len) = Stream next (off+len-1) (betweenSize (len `sh

9898-- | /O(n)/ Convert a 'Stream Char' into a 'Text'.

9999unstream :: Stream Char -> Text

100100unstream (Stream next0 s0 len) = runText $ \done -> do

101− -- Before encoding each char we perform a buffer realloc check assuming

102− -- worst case encoding size of two 16-bit units for the char. Just add an

103− -- extra space to the buffer so that we do not end up reallocating even when

104− -- all the chars are encoded as single unit.

105− let mlen = upperBound 4 len + 1

101+ let mlen = upperBound 4 len

106102 arr0 <- A.new mlen

107− let outer !arr !maxi = encode

103+ let outer arr top = loop

108104 where

109− -- keep the common case loop as small as possible

110− encode !si !di =

111− case next0 si of

112− Done -> done arr di

113− Skip si' -> encode si' di

114− Yield c si'

115− -- simply check for the worst case

116− | maxi < di + 1 -> realloc si di

117− | otherwise -> do

118− n <- unsafeWrite arr di c

119− encode si' (di + n)

120−

121− -- keep uncommon case separate from the common case code

122− {-# NOINLINE realloc #-}

123− realloc !si !di = do

124− let newlen = (maxi + 1) * 2

125− arr' <- A.new newlen

126− A.copyM arr' 0 arr 0 di

127− outer arr' (newlen - 1) si di

128−

129− outer arr0 (mlen - 1) s0 0

105+ loop !s !i =

106+ case next0 s of

107+ Done -> done arr i

108+ Skip s' -> loop s' i

109+ Yield x s'

110+ | j >= top -> {-# SCC "unstream/resize" #-} do

111+ let top' = (top + 1) `shiftL` 1

112+ arr' <- A.new top'

113+ A.copyM arr' 0 arr 0 top

114+ outer arr' top' s i

115+ | otherwise -> do d <- unsafeWrite arr i x

116+ loop s' (i+d)

117+ where j | ord x < 0x10000 = i

118+ | otherwise = i + 1

119+ outer arr0 mlen s0 0

130120{-# INLINE [0] unstream #-}

131121{-# RULES "STREAM stream/unstream fusion" forall s. stream (unstream s) = s #-}

132122

Data/Text/Internal/Fusion/CaseMapping.hs+112−286

@@ -1,10 +1,10 @@

11{-# LANGUAGE Rank2Types #-}

22-- AUTOMATICALLY GENERATED - DO NOT EDIT

33-- Generated by scripts/CaseMapping.hs

4−-- CaseFolding-8.0.0.txt

5−-- Date: 2015-01-13, 18:16:36 GMT [MD]

6−-- SpecialCasing-8.0.0.txt

7−-- Date: 2014-12-16, 23:08:04 GMT [MD]

4+-- CaseFolding-7.0.0.txt

5+-- Date: 2014-04-09, 20:00:56 GMT [MD]

6+-- SpecialCasing-7.0.0.txt

7+-- Date: 2014-03-18, 07:18:02 GMT [MD]

99module Data.Text.Internal.Fusion.CaseMapping where

1010import Data.Char

@@ -337,6 +337,8 @@ foldMapping '\x017f' s = Yield '\x0073' (CC s '\x0000' '\x0000')

337337foldMapping '\x01f0' s = Yield '\x006a' (CC s '\x030c' '\x0000')

338338-- COMBINING GREEK YPOGEGRAMMENI

339339foldMapping '\x0345' s = Yield '\x03b9' (CC s '\x0000' '\x0000')

340+-- GREEK CAPITAL LETTER YOT

341+foldMapping '\x037f' s = Yield '\x03f3' (CC s '\x0000' '\x0000')

340342-- GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS

341343foldMapping '\x0390' s = Yield '\x03b9' (CC s '\x0308' '\x0301')

342344-- GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS

@@ -357,20 +359,20 @@ foldMapping '\x03f0' s = Yield '\x03ba' (CC s '\x0000' '\x0000')

357359foldMapping '\x03f1' s = Yield '\x03c1' (CC s '\x0000' '\x0000')

358360-- GREEK LUNATE EPSILON SYMBOL

359361foldMapping '\x03f5' s = Yield '\x03b5' (CC s '\x0000' '\x0000')

362+-- CYRILLIC CAPITAL LETTER EN WITH LEFT HOOK

363+foldMapping '\x0528' s = Yield '\x0529' (CC s '\x0000' '\x0000')

364+-- CYRILLIC CAPITAL LETTER DZZHE

365+foldMapping '\x052a' s = Yield '\x052b' (CC s '\x0000' '\x0000')

366+-- CYRILLIC CAPITAL LETTER DCHE

367+foldMapping '\x052c' s = Yield '\x052d' (CC s '\x0000' '\x0000')

368+-- CYRILLIC CAPITAL LETTER EL WITH DESCENDER

369+foldMapping '\x052e' s = Yield '\x052f' (CC s '\x0000' '\x0000')

360370-- ARMENIAN SMALL LIGATURE ECH YIWN

361371foldMapping '\x0587' s = Yield '\x0565' (CC s '\x0582' '\x0000')

362−-- CHEROKEE SMALL LETTER YE

363−foldMapping '\x13f8' s = Yield '\x13f0' (CC s '\x0000' '\x0000')

364−-- CHEROKEE SMALL LETTER YI

365−foldMapping '\x13f9' s = Yield '\x13f1' (CC s '\x0000' '\x0000')

366−-- CHEROKEE SMALL LETTER YO

367−foldMapping '\x13fa' s = Yield '\x13f2' (CC s '\x0000' '\x0000')

368−-- CHEROKEE SMALL LETTER YU

369−foldMapping '\x13fb' s = Yield '\x13f3' (CC s '\x0000' '\x0000')

370−-- CHEROKEE SMALL LETTER YV

371−foldMapping '\x13fc' s = Yield '\x13f4' (CC s '\x0000' '\x0000')

372−-- CHEROKEE SMALL LETTER MV

373−foldMapping '\x13fd' s = Yield '\x13f5' (CC s '\x0000' '\x0000')

372+-- GEORGIAN CAPITAL LETTER YN

373+foldMapping '\x10c7' s = Yield '\x2d27' (CC s '\x0000' '\x0000')

374+-- GEORGIAN CAPITAL LETTER AEN

375+foldMapping '\x10cd' s = Yield '\x2d2d' (CC s '\x0000' '\x0000')

374376-- LATIN SMALL LETTER H WITH LINE BELOW

375377foldMapping '\x1e96' s = Yield '\x0068' (CC s '\x0331' '\x0000')

376378-- LATIN SMALL LETTER T WITH DIAERESIS

@@ -545,174 +547,36 @@ foldMapping '\x1ff6' s = Yield '\x03c9' (CC s '\x0342' '\x0000')

545547foldMapping '\x1ff7' s = Yield '\x03c9' (CC s '\x0342' '\x03b9')

546548-- GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI

547549foldMapping '\x1ffc' s = Yield '\x03c9' (CC s '\x03b9' '\x0000')

548−-- LATIN CAPITAL LETTER J WITH CROSSED-TAIL

549−foldMapping '\xa7b2' s = Yield '\x029d' (CC s '\x0000' '\x0000')

550−-- LATIN CAPITAL LETTER CHI

551−foldMapping '\xa7b3' s = Yield '\xab53' (CC s '\x0000' '\x0000')

552−-- LATIN CAPITAL LETTER BETA

553−foldMapping '\xa7b4' s = Yield '\xa7b5' (CC s '\x0000' '\x0000')

554−-- LATIN CAPITAL LETTER OMEGA

555−foldMapping '\xa7b6' s = Yield '\xa7b7' (CC s '\x0000' '\x0000')

556−-- CHEROKEE SMALL LETTER A

557−foldMapping '\xab70' s = Yield '\x13a0' (CC s '\x0000' '\x0000')

558−-- CHEROKEE SMALL LETTER E

559−foldMapping '\xab71' s = Yield '\x13a1' (CC s '\x0000' '\x0000')

560−-- CHEROKEE SMALL LETTER I

561−foldMapping '\xab72' s = Yield '\x13a2' (CC s '\x0000' '\x0000')

562−-- CHEROKEE SMALL LETTER O

563−foldMapping '\xab73' s = Yield '\x13a3' (CC s '\x0000' '\x0000')

564−-- CHEROKEE SMALL LETTER U

565−foldMapping '\xab74' s = Yield '\x13a4' (CC s '\x0000' '\x0000')

566−-- CHEROKEE SMALL LETTER V

567−foldMapping '\xab75' s = Yield '\x13a5' (CC s '\x0000' '\x0000')

568−-- CHEROKEE SMALL LETTER GA

569−foldMapping '\xab76' s = Yield '\x13a6' (CC s '\x0000' '\x0000')

570−-- CHEROKEE SMALL LETTER KA

571−foldMapping '\xab77' s = Yield '\x13a7' (CC s '\x0000' '\x0000')

572−-- CHEROKEE SMALL LETTER GE

573−foldMapping '\xab78' s = Yield '\x13a8' (CC s '\x0000' '\x0000')

574−-- CHEROKEE SMALL LETTER GI

575−foldMapping '\xab79' s = Yield '\x13a9' (CC s '\x0000' '\x0000')

576−-- CHEROKEE SMALL LETTER GO

577−foldMapping '\xab7a' s = Yield '\x13aa' (CC s '\x0000' '\x0000')

578−-- CHEROKEE SMALL LETTER GU

579−foldMapping '\xab7b' s = Yield '\x13ab' (CC s '\x0000' '\x0000')

580−-- CHEROKEE SMALL LETTER GV

581−foldMapping '\xab7c' s = Yield '\x13ac' (CC s '\x0000' '\x0000')

582−-- CHEROKEE SMALL LETTER HA

583−foldMapping '\xab7d' s = Yield '\x13ad' (CC s '\x0000' '\x0000')

584−-- CHEROKEE SMALL LETTER HE

585−foldMapping '\xab7e' s = Yield '\x13ae' (CC s '\x0000' '\x0000')

586−-- CHEROKEE SMALL LETTER HI

587−foldMapping '\xab7f' s = Yield '\x13af' (CC s '\x0000' '\x0000')

588−-- CHEROKEE SMALL LETTER HO

589−foldMapping '\xab80' s = Yield '\x13b0' (CC s '\x0000' '\x0000')

590−-- CHEROKEE SMALL LETTER HU

591−foldMapping '\xab81' s = Yield '\x13b1' (CC s '\x0000' '\x0000')

592−-- CHEROKEE SMALL LETTER HV

593−foldMapping '\xab82' s = Yield '\x13b2' (CC s '\x0000' '\x0000')

594−-- CHEROKEE SMALL LETTER LA

595−foldMapping '\xab83' s = Yield '\x13b3' (CC s '\x0000' '\x0000')

596−-- CHEROKEE SMALL LETTER LE

597−foldMapping '\xab84' s = Yield '\x13b4' (CC s '\x0000' '\x0000')

598−-- CHEROKEE SMALL LETTER LI

599−foldMapping '\xab85' s = Yield '\x13b5' (CC s '\x0000' '\x0000')

600−-- CHEROKEE SMALL LETTER LO

601−foldMapping '\xab86' s = Yield '\x13b6' (CC s '\x0000' '\x0000')

602−-- CHEROKEE SMALL LETTER LU

603−foldMapping '\xab87' s = Yield '\x13b7' (CC s '\x0000' '\x0000')

604−-- CHEROKEE SMALL LETTER LV

605−foldMapping '\xab88' s = Yield '\x13b8' (CC s '\x0000' '\x0000')

606−-- CHEROKEE SMALL LETTER MA

607−foldMapping '\xab89' s = Yield '\x13b9' (CC s '\x0000' '\x0000')

608−-- CHEROKEE SMALL LETTER ME

609−foldMapping '\xab8a' s = Yield '\x13ba' (CC s '\x0000' '\x0000')

610−-- CHEROKEE SMALL LETTER MI

611−foldMapping '\xab8b' s = Yield '\x13bb' (CC s '\x0000' '\x0000')

612−-- CHEROKEE SMALL LETTER MO

613−foldMapping '\xab8c' s = Yield '\x13bc' (CC s '\x0000' '\x0000')

614−-- CHEROKEE SMALL LETTER MU

615−foldMapping '\xab8d' s = Yield '\x13bd' (CC s '\x0000' '\x0000')

616−-- CHEROKEE SMALL LETTER NA

617−foldMapping '\xab8e' s = Yield '\x13be' (CC s '\x0000' '\x0000')

618−-- CHEROKEE SMALL LETTER HNA

619−foldMapping '\xab8f' s = Yield '\x13bf' (CC s '\x0000' '\x0000')

620−-- CHEROKEE SMALL LETTER NAH

621−foldMapping '\xab90' s = Yield '\x13c0' (CC s '\x0000' '\x0000')

622−-- CHEROKEE SMALL LETTER NE

623−foldMapping '\xab91' s = Yield '\x13c1' (CC s '\x0000' '\x0000')

624−-- CHEROKEE SMALL LETTER NI

625−foldMapping '\xab92' s = Yield '\x13c2' (CC s '\x0000' '\x0000')

626−-- CHEROKEE SMALL LETTER NO

627−foldMapping '\xab93' s = Yield '\x13c3' (CC s '\x0000' '\x0000')

628−-- CHEROKEE SMALL LETTER NU

629−foldMapping '\xab94' s = Yield '\x13c4' (CC s '\x0000' '\x0000')

630−-- CHEROKEE SMALL LETTER NV

631−foldMapping '\xab95' s = Yield '\x13c5' (CC s '\x0000' '\x0000')

632−-- CHEROKEE SMALL LETTER QUA

633−foldMapping '\xab96' s = Yield '\x13c6' (CC s '\x0000' '\x0000')

634−-- CHEROKEE SMALL LETTER QUE

635−foldMapping '\xab97' s = Yield '\x13c7' (CC s '\x0000' '\x0000')

636−-- CHEROKEE SMALL LETTER QUI

637−foldMapping '\xab98' s = Yield '\x13c8' (CC s '\x0000' '\x0000')

638−-- CHEROKEE SMALL LETTER QUO

639−foldMapping '\xab99' s = Yield '\x13c9' (CC s '\x0000' '\x0000')

640−-- CHEROKEE SMALL LETTER QUU

641−foldMapping '\xab9a' s = Yield '\x13ca' (CC s '\x0000' '\x0000')

642−-- CHEROKEE SMALL LETTER QUV

643−foldMapping '\xab9b' s = Yield '\x13cb' (CC s '\x0000' '\x0000')

644−-- CHEROKEE SMALL LETTER SA

645−foldMapping '\xab9c' s = Yield '\x13cc' (CC s '\x0000' '\x0000')

646−-- CHEROKEE SMALL LETTER S

647−foldMapping '\xab9d' s = Yield '\x13cd' (CC s '\x0000' '\x0000')

648−-- CHEROKEE SMALL LETTER SE

649−foldMapping '\xab9e' s = Yield '\x13ce' (CC s '\x0000' '\x0000')

650−-- CHEROKEE SMALL LETTER SI

651−foldMapping '\xab9f' s = Yield '\x13cf' (CC s '\x0000' '\x0000')

652−-- CHEROKEE SMALL LETTER SO

653−foldMapping '\xaba0' s = Yield '\x13d0' (CC s '\x0000' '\x0000')

654−-- CHEROKEE SMALL LETTER SU

655−foldMapping '\xaba1' s = Yield '\x13d1' (CC s '\x0000' '\x0000')

656−-- CHEROKEE SMALL LETTER SV

657−foldMapping '\xaba2' s = Yield '\x13d2' (CC s '\x0000' '\x0000')

658−-- CHEROKEE SMALL LETTER DA

659−foldMapping '\xaba3' s = Yield '\x13d3' (CC s '\x0000' '\x0000')

660−-- CHEROKEE SMALL LETTER TA

661−foldMapping '\xaba4' s = Yield '\x13d4' (CC s '\x0000' '\x0000')

662−-- CHEROKEE SMALL LETTER DE

663−foldMapping '\xaba5' s = Yield '\x13d5' (CC s '\x0000' '\x0000')

664−-- CHEROKEE SMALL LETTER TE

665−foldMapping '\xaba6' s = Yield '\x13d6' (CC s '\x0000' '\x0000')

666−-- CHEROKEE SMALL LETTER DI

667−foldMapping '\xaba7' s = Yield '\x13d7' (CC s '\x0000' '\x0000')

668−-- CHEROKEE SMALL LETTER TI

669−foldMapping '\xaba8' s = Yield '\x13d8' (CC s '\x0000' '\x0000')

670−-- CHEROKEE SMALL LETTER DO

671−foldMapping '\xaba9' s = Yield '\x13d9' (CC s '\x0000' '\x0000')

672−-- CHEROKEE SMALL LETTER DU

673−foldMapping '\xabaa' s = Yield '\x13da' (CC s '\x0000' '\x0000')

674−-- CHEROKEE SMALL LETTER DV

675−foldMapping '\xabab' s = Yield '\x13db' (CC s '\x0000' '\x0000')

676−-- CHEROKEE SMALL LETTER DLA

677−foldMapping '\xabac' s = Yield '\x13dc' (CC s '\x0000' '\x0000')

678−-- CHEROKEE SMALL LETTER TLA

679−foldMapping '\xabad' s = Yield '\x13dd' (CC s '\x0000' '\x0000')

680−-- CHEROKEE SMALL LETTER TLE

681−foldMapping '\xabae' s = Yield '\x13de' (CC s '\x0000' '\x0000')

682−-- CHEROKEE SMALL LETTER TLI

683−foldMapping '\xabaf' s = Yield '\x13df' (CC s '\x0000' '\x0000')

684−-- CHEROKEE SMALL LETTER TLO

685−foldMapping '\xabb0' s = Yield '\x13e0' (CC s '\x0000' '\x0000')

686−-- CHEROKEE SMALL LETTER TLU

687−foldMapping '\xabb1' s = Yield '\x13e1' (CC s '\x0000' '\x0000')

688−-- CHEROKEE SMALL LETTER TLV

689−foldMapping '\xabb2' s = Yield '\x13e2' (CC s '\x0000' '\x0000')

690−-- CHEROKEE SMALL LETTER TSA

691−foldMapping '\xabb3' s = Yield '\x13e3' (CC s '\x0000' '\x0000')

692−-- CHEROKEE SMALL LETTER TSE

693−foldMapping '\xabb4' s = Yield '\x13e4' (CC s '\x0000' '\x0000')

694−-- CHEROKEE SMALL LETTER TSI

695−foldMapping '\xabb5' s = Yield '\x13e5' (CC s '\x0000' '\x0000')

696−-- CHEROKEE SMALL LETTER TSO

697−foldMapping '\xabb6' s = Yield '\x13e6' (CC s '\x0000' '\x0000')

698−-- CHEROKEE SMALL LETTER TSU

699−foldMapping '\xabb7' s = Yield '\x13e7' (CC s '\x0000' '\x0000')

700−-- CHEROKEE SMALL LETTER TSV

701−foldMapping '\xabb8' s = Yield '\x13e8' (CC s '\x0000' '\x0000')

702−-- CHEROKEE SMALL LETTER WA

703−foldMapping '\xabb9' s = Yield '\x13e9' (CC s '\x0000' '\x0000')

704−-- CHEROKEE SMALL LETTER WE

705−foldMapping '\xabba' s = Yield '\x13ea' (CC s '\x0000' '\x0000')

706−-- CHEROKEE SMALL LETTER WI

707−foldMapping '\xabbb' s = Yield '\x13eb' (CC s '\x0000' '\x0000')

708−-- CHEROKEE SMALL LETTER WO

709−foldMapping '\xabbc' s = Yield '\x13ec' (CC s '\x0000' '\x0000')

710−-- CHEROKEE SMALL LETTER WU

711−foldMapping '\xabbd' s = Yield '\x13ed' (CC s '\x0000' '\x0000')

712−-- CHEROKEE SMALL LETTER WV

713−foldMapping '\xabbe' s = Yield '\x13ee' (CC s '\x0000' '\x0000')

714−-- CHEROKEE SMALL LETTER YA

715−foldMapping '\xabbf' s = Yield '\x13ef' (CC s '\x0000' '\x0000')

550+-- COPTIC CAPITAL LETTER BOHAIRIC KHEI

551+foldMapping '\x2cf2' s = Yield '\x2cf3' (CC s '\x0000' '\x0000')

552+-- CYRILLIC CAPITAL LETTER DOUBLE O

553+foldMapping '\xa698' s = Yield '\xa699' (CC s '\x0000' '\x0000')

554+-- CYRILLIC CAPITAL LETTER CROSSED O

555+foldMapping '\xa69a' s = Yield '\xa69b' (CC s '\x0000' '\x0000')

556+-- LATIN CAPITAL LETTER C WITH BAR

557+foldMapping '\xa792' s = Yield '\xa793' (CC s '\x0000' '\x0000')

558+-- LATIN CAPITAL LETTER B WITH FLOURISH

559+foldMapping '\xa796' s = Yield '\xa797' (CC s '\x0000' '\x0000')

560+-- LATIN CAPITAL LETTER F WITH STROKE

561+foldMapping '\xa798' s = Yield '\xa799' (CC s '\x0000' '\x0000')

562+-- LATIN CAPITAL LETTER VOLAPUK AE

563+foldMapping '\xa79a' s = Yield '\xa79b' (CC s '\x0000' '\x0000')

564+-- LATIN CAPITAL LETTER VOLAPUK OE

565+foldMapping '\xa79c' s = Yield '\xa79d' (CC s '\x0000' '\x0000')

566+-- LATIN CAPITAL LETTER VOLAPUK UE

567+foldMapping '\xa79e' s = Yield '\xa79f' (CC s '\x0000' '\x0000')

568+-- LATIN CAPITAL LETTER H WITH HOOK

569+foldMapping '\xa7aa' s = Yield '\x0266' (CC s '\x0000' '\x0000')

570+-- LATIN CAPITAL LETTER REVERSED OPEN E

571+foldMapping '\xa7ab' s = Yield '\x025c' (CC s '\x0000' '\x0000')

572+-- LATIN CAPITAL LETTER SCRIPT G

573+foldMapping '\xa7ac' s = Yield '\x0261' (CC s '\x0000' '\x0000')

574+-- LATIN CAPITAL LETTER L WITH BELT

575+foldMapping '\xa7ad' s = Yield '\x026c' (CC s '\x0000' '\x0000')

576+-- LATIN CAPITAL LETTER TURNED K

577+foldMapping '\xa7b0' s = Yield '\x029e' (CC s '\x0000' '\x0000')

578+-- LATIN CAPITAL LETTER TURNED T

579+foldMapping '\xa7b1' s = Yield '\x0287' (CC s '\x0000' '\x0000')

716580-- LATIN SMALL LIGATURE FF

717581foldMapping '\xfb00' s = Yield '\x0066' (CC s '\x0066' '\x0000')

718582-- LATIN SMALL LIGATURE FI

@@ -737,106 +601,68 @@ foldMapping '\xfb15' s = Yield '\x0574' (CC s '\x056b' '\x0000')

737601foldMapping '\xfb16' s = Yield '\x057e' (CC s '\x0576' '\x0000')

738602-- ARMENIAN SMALL LIGATURE MEN XEH

739603foldMapping '\xfb17' s = Yield '\x0574' (CC s '\x056d' '\x0000')

740−-- OLD HUNGARIAN CAPITAL LETTER A

741−foldMapping '\x10c80' s = Yield '\x10cc0' (CC s '\x0000' '\x0000')

742−-- OLD HUNGARIAN CAPITAL LETTER AA

743−foldMapping '\x10c81' s = Yield '\x10cc1' (CC s '\x0000' '\x0000')

744−-- OLD HUNGARIAN CAPITAL LETTER EB

745−foldMapping '\x10c82' s = Yield '\x10cc2' (CC s '\x0000' '\x0000')

746−-- OLD HUNGARIAN CAPITAL LETTER AMB

747−foldMapping '\x10c83' s = Yield '\x10cc3' (CC s '\x0000' '\x0000')

748−-- OLD HUNGARIAN CAPITAL LETTER EC

749−foldMapping '\x10c84' s = Yield '\x10cc4' (CC s '\x0000' '\x0000')

750−-- OLD HUNGARIAN CAPITAL LETTER ENC

751−foldMapping '\x10c85' s = Yield '\x10cc5' (CC s '\x0000' '\x0000')

752−-- OLD HUNGARIAN CAPITAL LETTER ECS

753−foldMapping '\x10c86' s = Yield '\x10cc6' (CC s '\x0000' '\x0000')

754−-- OLD HUNGARIAN CAPITAL LETTER ED

755−foldMapping '\x10c87' s = Yield '\x10cc7' (CC s '\x0000' '\x0000')

756−-- OLD HUNGARIAN CAPITAL LETTER AND

757−foldMapping '\x10c88' s = Yield '\x10cc8' (CC s '\x0000' '\x0000')

758−-- OLD HUNGARIAN CAPITAL LETTER E

759−foldMapping '\x10c89' s = Yield '\x10cc9' (CC s '\x0000' '\x0000')

760−-- OLD HUNGARIAN CAPITAL LETTER CLOSE E

761−foldMapping '\x10c8a' s = Yield '\x10cca' (CC s '\x0000' '\x0000')

762−-- OLD HUNGARIAN CAPITAL LETTER EE

763−foldMapping '\x10c8b' s = Yield '\x10ccb' (CC s '\x0000' '\x0000')

764−-- OLD HUNGARIAN CAPITAL LETTER EF

765−foldMapping '\x10c8c' s = Yield '\x10ccc' (CC s '\x0000' '\x0000')

766−-- OLD HUNGARIAN CAPITAL LETTER EG

767−foldMapping '\x10c8d' s = Yield '\x10ccd' (CC s '\x0000' '\x0000')

768−-- OLD HUNGARIAN CAPITAL LETTER EGY

769−foldMapping '\x10c8e' s = Yield '\x10cce' (CC s '\x0000' '\x0000')

770−-- OLD HUNGARIAN CAPITAL LETTER EH

771−foldMapping '\x10c8f' s = Yield '\x10ccf' (CC s '\x0000' '\x0000')

772−-- OLD HUNGARIAN CAPITAL LETTER I

773−foldMapping '\x10c90' s = Yield '\x10cd0' (CC s '\x0000' '\x0000')

774−-- OLD HUNGARIAN CAPITAL LETTER II

775−foldMapping '\x10c91' s = Yield '\x10cd1' (CC s '\x0000' '\x0000')

776−-- OLD HUNGARIAN CAPITAL LETTER EJ

777−foldMapping '\x10c92' s = Yield '\x10cd2' (CC s '\x0000' '\x0000')

778−-- OLD HUNGARIAN CAPITAL LETTER EK

779−foldMapping '\x10c93' s = Yield '\x10cd3' (CC s '\x0000' '\x0000')

780−-- OLD HUNGARIAN CAPITAL LETTER AK

781−foldMapping '\x10c94' s = Yield '\x10cd4' (CC s '\x0000' '\x0000')

782−-- OLD HUNGARIAN CAPITAL LETTER UNK

783−foldMapping '\x10c95' s = Yield '\x10cd5' (CC s '\x0000' '\x0000')

784−-- OLD HUNGARIAN CAPITAL LETTER EL

785−foldMapping '\x10c96' s = Yield '\x10cd6' (CC s '\x0000' '\x0000')

786−-- OLD HUNGARIAN CAPITAL LETTER ELY

787−foldMapping '\x10c97' s = Yield '\x10cd7' (CC s '\x0000' '\x0000')

788−-- OLD HUNGARIAN CAPITAL LETTER EM

789−foldMapping '\x10c98' s = Yield '\x10cd8' (CC s '\x0000' '\x0000')

790−-- OLD HUNGARIAN CAPITAL LETTER EN

791−foldMapping '\x10c99' s = Yield '\x10cd9' (CC s '\x0000' '\x0000')

792−-- OLD HUNGARIAN CAPITAL LETTER ENY

793−foldMapping '\x10c9a' s = Yield '\x10cda' (CC s '\x0000' '\x0000')

794−-- OLD HUNGARIAN CAPITAL LETTER O

795−foldMapping '\x10c9b' s = Yield '\x10cdb' (CC s '\x0000' '\x0000')

796−-- OLD HUNGARIAN CAPITAL LETTER OO

797−foldMapping '\x10c9c' s = Yield '\x10cdc' (CC s '\x0000' '\x0000')

798−-- OLD HUNGARIAN CAPITAL LETTER NIKOLSBURG OE

799−foldMapping '\x10c9d' s = Yield '\x10cdd' (CC s '\x0000' '\x0000')

800−-- OLD HUNGARIAN CAPITAL LETTER RUDIMENTA OE

801−foldMapping '\x10c9e' s = Yield '\x10cde' (CC s '\x0000' '\x0000')

802−-- OLD HUNGARIAN CAPITAL LETTER OEE

803−foldMapping '\x10c9f' s = Yield '\x10cdf' (CC s '\x0000' '\x0000')

804−-- OLD HUNGARIAN CAPITAL LETTER EP

805−foldMapping '\x10ca0' s = Yield '\x10ce0' (CC s '\x0000' '\x0000')

806−-- OLD HUNGARIAN CAPITAL LETTER EMP

807−foldMapping '\x10ca1' s = Yield '\x10ce1' (CC s '\x0000' '\x0000')

808−-- OLD HUNGARIAN CAPITAL LETTER ER

809−foldMapping '\x10ca2' s = Yield '\x10ce2' (CC s '\x0000' '\x0000')

810−-- OLD HUNGARIAN CAPITAL LETTER SHORT ER

811−foldMapping '\x10ca3' s = Yield '\x10ce3' (CC s '\x0000' '\x0000')

812−-- OLD HUNGARIAN CAPITAL LETTER ES

813−foldMapping '\x10ca4' s = Yield '\x10ce4' (CC s '\x0000' '\x0000')

814−-- OLD HUNGARIAN CAPITAL LETTER ESZ

815−foldMapping '\x10ca5' s = Yield '\x10ce5' (CC s '\x0000' '\x0000')

816−-- OLD HUNGARIAN CAPITAL LETTER ET

817−foldMapping '\x10ca6' s = Yield '\x10ce6' (CC s '\x0000' '\x0000')

818−-- OLD HUNGARIAN CAPITAL LETTER ENT

819−foldMapping '\x10ca7' s = Yield '\x10ce7' (CC s '\x0000' '\x0000')

820−-- OLD HUNGARIAN CAPITAL LETTER ETY

821−foldMapping '\x10ca8' s = Yield '\x10ce8' (CC s '\x0000' '\x0000')

822−-- OLD HUNGARIAN CAPITAL LETTER ECH

823−foldMapping '\x10ca9' s = Yield '\x10ce9' (CC s '\x0000' '\x0000')

824−-- OLD HUNGARIAN CAPITAL LETTER U

825−foldMapping '\x10caa' s = Yield '\x10cea' (CC s '\x0000' '\x0000')

826−-- OLD HUNGARIAN CAPITAL LETTER UU

827−foldMapping '\x10cab' s = Yield '\x10ceb' (CC s '\x0000' '\x0000')

828−-- OLD HUNGARIAN CAPITAL LETTER NIKOLSBURG UE

829−foldMapping '\x10cac' s = Yield '\x10cec' (CC s '\x0000' '\x0000')

830−-- OLD HUNGARIAN CAPITAL LETTER RUDIMENTA UE

831−foldMapping '\x10cad' s = Yield '\x10ced' (CC s '\x0000' '\x0000')

832−-- OLD HUNGARIAN CAPITAL LETTER EV

833−foldMapping '\x10cae' s = Yield '\x10cee' (CC s '\x0000' '\x0000')

834−-- OLD HUNGARIAN CAPITAL LETTER EZ

835−foldMapping '\x10caf' s = Yield '\x10cef' (CC s '\x0000' '\x0000')

836−-- OLD HUNGARIAN CAPITAL LETTER EZS

837−foldMapping '\x10cb0' s = Yield '\x10cf0' (CC s '\x0000' '\x0000')

838−-- OLD HUNGARIAN CAPITAL LETTER ENT-SHAPED SIGN

839−foldMapping '\x10cb1' s = Yield '\x10cf1' (CC s '\x0000' '\x0000')

840−-- OLD HUNGARIAN CAPITAL LETTER US

841−foldMapping '\x10cb2' s = Yield '\x10cf2' (CC s '\x0000' '\x0000')

604+-- WARANG CITI CAPITAL LETTER NGAA

605+foldMapping '\x118a0' s = Yield '\x118c0' (CC s '\x0000' '\x0000')

606+-- WARANG CITI CAPITAL LETTER A

607+foldMapping '\x118a1' s = Yield '\x118c1' (CC s '\x0000' '\x0000')

608+-- WARANG CITI CAPITAL LETTER WI

609+foldMapping '\x118a2' s = Yield '\x118c2' (CC s '\x0000' '\x0000')

610+-- WARANG CITI CAPITAL LETTER YU

611+foldMapping '\x118a3' s = Yield '\x118c3' (CC s '\x0000' '\x0000')

612+-- WARANG CITI CAPITAL LETTER YA

613+foldMapping '\x118a4' s = Yield '\x118c4' (CC s '\x0000' '\x0000')

614+-- WARANG CITI CAPITAL LETTER YO

615+foldMapping '\x118a5' s = Yield '\x118c5' (CC s '\x0000' '\x0000')

616+-- WARANG CITI CAPITAL LETTER II

617+foldMapping '\x118a6' s = Yield '\x118c6' (CC s '\x0000' '\x0000')

618+-- WARANG CITI CAPITAL LETTER UU

619+foldMapping '\x118a7' s = Yield '\x118c7' (CC s '\x0000' '\x0000')

620+-- WARANG CITI CAPITAL LETTER E

621+foldMapping '\x118a8' s = Yield '\x118c8' (CC s '\x0000' '\x0000')

622+-- WARANG CITI CAPITAL LETTER O

623+foldMapping '\x118a9' s = Yield '\x118c9' (CC s '\x0000' '\x0000')

624+-- WARANG CITI CAPITAL LETTER ANG

625+foldMapping '\x118aa' s = Yield '\x118ca' (CC s '\x0000' '\x0000')

626+-- WARANG CITI CAPITAL LETTER GA

627+foldMapping '\x118ab' s = Yield '\x118cb' (CC s '\x0000' '\x0000')

628+-- WARANG CITI CAPITAL LETTER KO

629+foldMapping '\x118ac' s = Yield '\x118cc' (CC s '\x0000' '\x0000')

630+-- WARANG CITI CAPITAL LETTER ENY

631+foldMapping '\x118ad' s = Yield '\x118cd' (CC s '\x0000' '\x0000')

632+-- WARANG CITI CAPITAL LETTER YUJ

633+foldMapping '\x118ae' s = Yield '\x118ce' (CC s '\x0000' '\x0000')

634+-- WARANG CITI CAPITAL LETTER UC

635+foldMapping '\x118af' s = Yield '\x118cf' (CC s '\x0000' '\x0000')

636+-- WARANG CITI CAPITAL LETTER ENN

637+foldMapping '\x118b0' s = Yield '\x118d0' (CC s '\x0000' '\x0000')

638+-- WARANG CITI CAPITAL LETTER ODD

639+foldMapping '\x118b1' s = Yield '\x118d1' (CC s '\x0000' '\x0000')

640+-- WARANG CITI CAPITAL LETTER TTE

641+foldMapping '\x118b2' s = Yield '\x118d2' (CC s '\x0000' '\x0000')

642+-- WARANG CITI CAPITAL LETTER NUNG

643+foldMapping '\x118b3' s = Yield '\x118d3' (CC s '\x0000' '\x0000')

644+-- WARANG CITI CAPITAL LETTER DA

645+foldMapping '\x118b4' s = Yield '\x118d4' (CC s '\x0000' '\x0000')

646+-- WARANG CITI CAPITAL LETTER AT

647+foldMapping '\x118b5' s = Yield '\x118d5' (CC s '\x0000' '\x0000')

648+-- WARANG CITI CAPITAL LETTER AM

649+foldMapping '\x118b6' s = Yield '\x118d6' (CC s '\x0000' '\x0000')

650+-- WARANG CITI CAPITAL LETTER BU

651+foldMapping '\x118b7' s = Yield '\x118d7' (CC s '\x0000' '\x0000')

652+-- WARANG CITI CAPITAL LETTER PU

653+foldMapping '\x118b8' s = Yield '\x118d8' (CC s '\x0000' '\x0000')

654+-- WARANG CITI CAPITAL LETTER HIYO

655+foldMapping '\x118b9' s = Yield '\x118d9' (CC s '\x0000' '\x0000')

656+-- WARANG CITI CAPITAL LETTER HOLO

657+foldMapping '\x118ba' s = Yield '\x118da' (CC s '\x0000' '\x0000')

658+-- WARANG CITI CAPITAL LETTER HORR

659+foldMapping '\x118bb' s = Yield '\x118db' (CC s '\x0000' '\x0000')

660+-- WARANG CITI CAPITAL LETTER HAR

661+foldMapping '\x118bc' s = Yield '\x118dc' (CC s '\x0000' '\x0000')

662+-- WARANG CITI CAPITAL LETTER SSUU

663+foldMapping '\x118bd' s = Yield '\x118dd' (CC s '\x0000' '\x0000')

664+-- WARANG CITI CAPITAL LETTER SII

665+foldMapping '\x118be' s = Yield '\x118de' (CC s '\x0000' '\x0000')

666+-- WARANG CITI CAPITAL LETTER VIYO

667+foldMapping '\x118bf' s = Yield '\x118df' (CC s '\x0000' '\x0000')

842668foldMapping c s = Yield (toLower c) (CC s '\0' '\0')

Data/Text/Internal/Fusion/Common.hs+5−5

@@ -593,7 +593,7 @@ concatMap f = foldr (append . f) empty

593593{-# INLINE [0] concatMap #-}

594594

595595-- | /O(n)/ any @p @xs determines if any character in the stream

596−-- @xs@ satisfies the predicate @p@.

596+-- @xs@ satisifes the predicate @p@.

597597any :: (Char -> Bool) -> Stream Char -> Bool

598598any p (Stream next0 s0 _len) = loop_any s0

599599 where

@@ -605,7 +605,7 @@ any p (Stream next0 s0 _len) = loop_any s0

605605{-# INLINE [0] any #-}

606606

607607-- | /O(n)/ all @p @xs determines if all characters in the 'Text'

608−-- @xs@ satisfy the predicate @p@.

608+-- @xs@ satisify the predicate @p@.

609609all :: (Char -> Bool) -> Stream Char -> Bool

610610all p (Stream next0 s0 _len) = loop_all s0

611611 where

@@ -669,12 +669,12 @@ scanl f z0 (Stream next0 s0 len) = Stream next (Scan1 z0 s0) (len+1) -- HINT may

669669-- ** Generating and unfolding streams

670670

671671replicateCharI :: Integral a => a -> Char -> Stream Char

672−replicateCharI !n !c

672+replicateCharI n c

673673 | n < 0 = empty

674674 | otherwise = Stream next 0 (fromIntegral n) -- HINT maybe too low

675675 where

676− next !i | i >= n = Done

677− | otherwise = Yield c (i + 1)

676+ next i | i >= n = Done

677+ | otherwise = Yield c (i + 1)

678678{-# INLINE [0] replicateCharI #-}

679679

680680data RI s = RI !s {-# UNPACK #-} !Int64

Data/Text/Internal/Read.hs+3−3

@@ -7,7 +7,7 @@

77-- Stability : experimental

88-- Portability : GHC

99--

10−-- Common internal functions for reading textual data.

10+-- Common internal functiopns for reading textual data.

1111module Data.Text.Internal.Read

1212 (

1313 IReader

@@ -18,7 +18,7 @@ module Data.Text.Internal.Read

1818 , perhaps

1919 ) where

2020

21−import Control.Applicative as App (Applicative(..))

21+import Control.Applicative (Applicative(..))

2222import Control.Arrow (first)

2323import Control.Monad (ap)

2424import Data.Char (ord)

@@ -38,7 +38,7 @@ instance Applicative (IParser t) where

3838 (<*>) = ap

3939

4040instance Monad (IParser t) where

41− return = App.pure

41+ return = pure

4242 m >>= k = P $ \t -> case runP m t of

4343 Left err -> Left err

4444 Right (a,t') -> runP (k a) t'

Data/Text/Lazy.hs+8−34

@@ -215,9 +215,6 @@ import Data.Data (Data(gfoldl, toConstr, gunfold, dataTypeOf), constrIndex,

215215 Constr, mkConstr, DataType, mkDataType, Fixity(Prefix))

216216import Data.Binary (Binary(get, put))

217217import Data.Monoid (Monoid(..))

218−#if MIN_VERSION_base(4,9,0)

219−import Data.Semigroup (Semigroup(..))

220−#endif

221218import Data.String (IsString(..))

222219import qualified Data.Text as T

223220import qualified Data.Text.Internal as T

@@ -229,7 +226,7 @@ import Data.Text.Internal.Lazy.Fusion (stream, unstream)

229226import Data.Text.Internal.Lazy (Text(..), chunk, empty, foldlChunks,

230227 foldrChunks, smallChunkSize)

231228import Data.Text.Internal (firstf, safe, text)

232−import Data.Text.Lazy.Encoding (decodeUtf8', encodeUtf8)

229+import Data.Text.Lazy.Encoding (decodeUtf8, encodeUtf8)

233230import qualified Data.Text.Internal.Functions as F

234231import Data.Text.Internal.Lazy.Search (indices)

235232#if __GLASGOW_HASKELL__ >= 702

@@ -241,9 +238,7 @@ import qualified GHC.Base as GHC

241238import qualified GHC.Exts as Exts

242239#endif

243240import GHC.Prim (Addr#)

244−#if MIN_VERSION_base(4,7,0)

245241import Text.Printf (PrintfArg, formatArg, formatString)

246−#endif

247242

248243-- $fusion

249244--

@@ -341,21 +336,9 @@ instance Show Text where

341336instance Read Text where

342337 readsPrec p str = [(pack x,y) | (x,y) <- readsPrec p str]

343338

344−#if MIN_VERSION_base(4,9,0)

345−-- Semigroup orphan instances for older GHCs are provided by

346−-- 'semigroups` package

347−

348−instance Semigroup Text where

349− (<>) = append

350−#endif

351−

352339instance Monoid Text where

353340 mempty = empty

354−#if MIN_VERSION_base(4,9,0)

355− mappend = (<>) -- future-proof definition

356−#else

357341 mappend = append

358−#endif

359342 mconcat = concat

360343

361344instance IsString Text where

@@ -376,11 +359,7 @@ instance NFData Text where

376359

377360instance Binary Text where

378361 put t = put (encodeUtf8 t)

379− get = do

380− bs <- get

381− case decodeUtf8' bs of

382− P.Left exn -> P.fail (P.show exn)

383− P.Right a -> P.return a

362+ get = P.fmap decodeUtf8 get

384363

385364-- | This instance preserves data abstraction at the cost of inefficiency.

386365-- We omit reflection services for the sake of data abstraction.

@@ -395,11 +374,8 @@ instance Data Text where

395374 _ -> error "Data.Text.Lazy.Text.gunfold"

396375 dataTypeOf _ = textDataType

397376

398−#if MIN_VERSION_base(4,7,0)

399−-- | Only defined for @base-4.7.0.0@ and later

400377instance PrintfArg Text where

401378 formatArg txt = formatString $ unpack txt

402−#endif

403379

404380packConstr :: Constr

405381packConstr = mkConstr textDataType "pack" [] Prefix

@@ -545,7 +521,7 @@ tail Empty = emptyError "tail"

545521 unstream (S.tail (stream t)) = tail t

546522 #-}

547523

548−-- | /O(n\/c)/ Returns all but the last character of a 'Text', which must

524+-- | /O(1)/ Returns all but the last character of a 'Text', which must

549525-- be non-empty. Subject to fusion.

550526init :: Text -> Text

551527init (Chunk t0 ts0) = go t0 ts0

@@ -581,7 +557,7 @@ isSingleton :: Text -> Bool

581557isSingleton = S.isSingleton . stream

582558{-# INLINE isSingleton #-}

583559

584−-- | /O(n\/c)/ Returns the last character of a 'Text', which must be

560+-- | /O(1)/ Returns the last character of a 'Text', which must be

585561-- non-empty. Subject to fusion.

586562last :: Text -> Char

587563last Empty = emptyError "last"

@@ -881,13 +857,13 @@ concatMap f = concat . foldr ((:) . f) []

881857{-# INLINE concatMap #-}

882858

883859-- | /O(n)/ 'any' @p@ @t@ determines whether any character in the

884−-- 'Text' @t@ satisfies the predicate @p@. Subject to fusion.

860+-- 'Text' @t@ satisifes the predicate @p@. Subject to fusion.

885861any :: (Char -> Bool) -> Text -> Bool

886862any p t = S.any p (stream t)

887863{-# INLINE any #-}

888864

889865-- | /O(n)/ 'all' @p@ @t@ determines whether all characters in the

890−-- 'Text' @t@ satisfy the predicate @p@. Subject to fusion.

866+-- 'Text' @t@ satisify the predicate @p@. Subject to fusion.

891867all :: (Char -> Bool) -> Text -> Bool

892868all p t = S.all p (stream t)

893869{-# INLINE all #-}

@@ -1176,11 +1152,9 @@ dropWhile p t0 = dropWhile' t0

11761152"LAZY TEXT dropWhile -> unfused" [1] forall p t.

11771153 unstream (S.dropWhile p (stream t)) = dropWhile p t

11781154 #-}

1179−

11801155-- | /O(n)/ 'dropWhileEnd' @p@ @t@ returns the prefix remaining after

1181−-- dropping characters that satisfy the predicate @p@ from the end of

1156+-- dropping characters that fail the predicate @p@ from the end of

11821157-- @t@.

1183−--

11841158-- Examples:

11851159--

11861160-- > dropWhileEnd (=='.') "foo..." == "foo"

@@ -1197,7 +1171,7 @@ dropWhileEnd p = go

11971171{-# INLINE dropWhileEnd #-}

11981172

11991173-- | /O(n)/ 'dropAround' @p@ @t@ returns the substring remaining after

1200−-- dropping characters that satisfy the predicate @p@ from both the

1174+-- dropping characters that fail the predicate @p@ from both the

12011175-- beginning and end of @t@. Subject to fusion.

12021176dropAround :: (Char -> Bool) -> Text -> Text

12031177dropAround p = dropWhile p . dropWhileEnd p

Data/Text/Lazy/Builder.hs+1−1

@@ -8,7 +8,7 @@

88-- Module : Data.Text.Lazy.Builder

11−-- License : BSD-style (see LICENSE)

11+-- License : BSD3-style (see LICENSE)

1212--

1313-- Maintainer : Johan Tibell <johan.tibell@gmail.com>

1414-- Stability : experimental

Data/Text/Lazy/Builder/Int.hs+4−4

@@ -7,7 +7,7 @@

77-- Module: Data.Text.Lazy.Builder.Int

10−-- License: BSD-style

10+-- License: BSD3

1111-- Maintainer: Bryan O'Sullivan <bos@serpentine.com>

1212-- Stability: experimental

1313-- Portability: portable

@@ -35,7 +35,7 @@ import Control.Monad.ST

3535

3636#ifdef __GLASGOW_HASKELL__

3737# if defined(INTEGER_GMP)

38−import GHC.Integer.GMP.Internals (Integer(S#))

38+import GHC.Integer.GMP.Internals

3939# elif defined(INTEGER_SIMPLE)

4040import GHC.Integer

4141# else

@@ -55,7 +55,7 @@ decimal :: Integral a => a -> Builder

5555{-# RULES "decimal/Int16" decimal = boundedDecimal :: Int16 -> Builder #-}

5656{-# RULES "decimal/Int32" decimal = boundedDecimal :: Int32 -> Builder #-}

5757{-# RULES "decimal/Int64" decimal = boundedDecimal :: Int64 -> Builder #-}

58−{-# RULES "decimal/Word" decimal = positive :: Data.Word.Word -> Builder #-}

58+{-# RULES "decimal/Word" decimal = positive :: Word -> Builder #-}

5959{-# RULES "decimal/Word8" decimal = positive :: Word8 -> Builder #-}

6060{-# RULES "decimal/Word16" decimal = positive :: Word16 -> Builder #-}

6161{-# RULES "decimal/Word32" decimal = positive :: Word32 -> Builder #-}

@@ -247,7 +247,7 @@ integer base i

247247 PAIR(x,y) -> pblock q <> pblock r <> putB ns

248248 where q = fromInteger x

249249 r = fromInteger y

250− putB _ = Data.Monoid.mempty

250+ putB _ = mempty

251251

252252 int :: Int -> Builder

253253 int x | base == 10 = decimal x

Data/Text/Lazy/Encoding.hs+16−6

@@ -46,23 +46,27 @@ module Data.Text.Lazy.Encoding

4646 , encodeUtf32LE

4747 , encodeUtf32BE

4848

49+#if MIN_VERSION_bytestring(0,10,4)

4950 -- * Encoding Text using ByteString Builders

5051 , encodeUtf8Builder

5152 , encodeUtf8BuilderEscaped

53+#endif

5254 ) where

5355

5456import Control.Exception (evaluate, try)

55−import Data.Monoid (Monoid(..))

5657import Data.Text.Encoding.Error (OnDecodeError, UnicodeException, strictDecode)

5758import Data.Text.Internal.Lazy (Text(..), chunk, empty, foldrChunks)

58−import Data.Word (Word8)

5959import qualified Data.ByteString as S

60−import qualified Data.ByteString.Builder as B

61−import qualified Data.ByteString.Builder.Extra as B (safeStrategy, toLazyByteStringWith)

62−import qualified Data.ByteString.Builder.Prim as BP

6360import qualified Data.ByteString.Lazy as B

6461import qualified Data.ByteString.Lazy.Internal as B

6562import qualified Data.ByteString.Unsafe as B

63+#if MIN_VERSION_bytestring(0,10,4)

64+import Data.Word (Word8)

65+import Data.Monoid (mappend, mempty)

66+import qualified Data.ByteString.Builder as B

67+import qualified Data.ByteString.Builder.Extra as B (safeStrategy, toLazyByteStringWith)

68+import qualified Data.ByteString.Builder.Prim as BP

69+#endif

6670import qualified Data.Text as T

6771import qualified Data.Text.Encoding as TE

6872import qualified Data.Text.Internal.Lazy.Encoding.Fusion as E

@@ -142,6 +146,7 @@ decodeUtf8' bs = unsafeDupablePerformIO $ do

142146{-# INLINE decodeUtf8' #-}

143147

144148encodeUtf8 :: Text -> B.ByteString

149+#if MIN_VERSION_bytestring(0,10,4)

145150encodeUtf8 Empty = B.empty

146151encodeUtf8 lt@(Chunk t _) =

147152 B.toLazyByteStringWith strategy B.empty $ encodeUtf8Builder lt

@@ -156,13 +161,18 @@ encodeUtf8 lt@(Chunk t _) =

156161

157162encodeUtf8Builder :: Text -> B.Builder

158163encodeUtf8Builder =

159− foldrChunks (\c b -> TE.encodeUtf8Builder c `mappend` b) Data.Monoid.mempty

164+ foldrChunks (\c b -> TE.encodeUtf8Builder c `mappend` b) mempty

160165

161166{-# INLINE encodeUtf8BuilderEscaped #-}

162167encodeUtf8BuilderEscaped :: BP.BoundedPrim Word8 -> Text -> B.Builder

163168encodeUtf8BuilderEscaped prim =

164169 foldrChunks (\c b -> TE.encodeUtf8BuilderEscaped prim c `mappend` b) mempty

165170

171+#else

172+encodeUtf8 (Chunk c cs) = B.Chunk (TE.encodeUtf8 c) (encodeUtf8 cs)

173+encodeUtf8 Empty = B.Empty

174+#endif

175+

166176-- | Decode text from little endian UTF-16 encoding.

167177decodeUtf16LEWith :: OnDecodeError -> B.ByteString -> Text

168178decodeUtf16LEWith onErr bs = F.unstream (E.streamUtf16LE onErr bs)

Data/Text/Lazy/Read.hs+2−4

@@ -1,7 +1,5 @@

11{-# LANGUAGE OverloadedStrings, CPP #-}

2−#if __GLASGOW_HASKELL__ >= 704

3−{-# LANGUAGE Safe #-}

4−#elif __GLASGOW_HASKELL__ >= 702

2+#if __GLASGOW_HASKELL__ >= 702

53{-# LANGUAGE Trustworthy #-}

64#endif

@@ -56,7 +54,7 @@ decimal :: Integral a => Reader a

5654{-# SPECIALIZE decimal :: Reader Int32 #-}

5755{-# SPECIALIZE decimal :: Reader Int64 #-}

5856{-# SPECIALIZE decimal :: Reader Integer #-}

59−{-# SPECIALIZE decimal :: Reader Data.Word.Word #-}

57+{-# SPECIALIZE decimal :: Reader Word #-}

6058{-# SPECIALIZE decimal :: Reader Word8 #-}

6159{-# SPECIALIZE decimal :: Reader Word16 #-}

6260{-# SPECIALIZE decimal :: Reader Word32 #-}

Data/Text/Read.hs+1−1

@@ -55,7 +55,7 @@ decimal :: Integral a => Reader a

5555{-# SPECIALIZE decimal :: Reader Int32 #-}

5656{-# SPECIALIZE decimal :: Reader Int64 #-}

5757{-# SPECIALIZE decimal :: Reader Integer #-}

58−{-# SPECIALIZE decimal :: Reader Data.Word.Word #-}

58+{-# SPECIALIZE decimal :: Reader Word #-}

5959{-# SPECIALIZE decimal :: Reader Word8 #-}

6060{-# SPECIALIZE decimal :: Reader Word16 #-}

6161{-# SPECIALIZE decimal :: Reader Word32 #-}

benchmarks/haskell/Benchmarks.hs+1−1

@@ -53,7 +53,7 @@ benchmarks = do

5353 , Mul.benchmark

5454 , Pure.benchmark "tiny" (tf "tiny.txt")

5555 , Pure.benchmark "ascii" (tf "ascii-small.txt")

56− -- , Pure.benchmark "france" (tf "france.html")

56+ , Pure.benchmark "france" (tf "france.html")

5757 , Pure.benchmark "russian" (tf "russian-small.txt")

5858 , Pure.benchmark "japanese" (tf "japanese.txt")

5959 , ReadNumbers.benchmark (tf "numbers.txt")

benchmarks/haskell/Benchmarks/Pure.hs−7

@@ -262,13 +262,6 @@ benchmark kind fp = do

262262 , benchBSL $ nf (BL.map toUpper) bla

263263 , benchS $ nf (L.map toUpper) sa

264264 ]

265− , bgroup "uncons"

266− [ benchT $ nf T.uncons ta

267− , benchTL $ nf TL.uncons tla

268− , benchBS $ nf BS.uncons bsa

269− , benchBSL $ nf BL.uncons bla

270− , benchS $ nf L.uncons sa

271− ]

272265 , bgroup "words"

273266 [ benchT $ nf T.words ta

274267 , benchTL $ nf TL.words tla

benchmarks/haskell/Benchmarks/ReadNumbers.hs+5−2

@@ -25,7 +25,8 @@ import Data.List (foldl')

2525import Numeric (readDec, readFloat, readHex)

2626import qualified Data.ByteString.Char8 as B

2727import qualified Data.ByteString.Lazy.Char8 as BL

28−import qualified Data.ByteString.Lex.Fractional as B

28+import qualified Data.ByteString.Lex.Double as B

29+import qualified Data.ByteString.Lex.Lazy.Double as BL

2930import qualified Data.Text as T

3031import qualified Data.Text.IO as T

3132import qualified Data.Text.Lazy as TL

@@ -62,10 +63,12 @@ benchmark fp = do

6263 whnf (double . text TL.rational) tl

6364

6465 , bench "DecimalByteString" $ whnf (int . byteString B.readInt) b

65− , bench "DoubleByteString" $ whnf (double . byteString B.readDecimal) b

66+ , bench "DoubleByteString" $ whnf (double . byteString B.readDouble) b

6667

6768 , bench "DecimalLazyByteString" $

6869 whnf (int . byteString BL.readInt) bl

70+ , bench "DoubleLazyByteString" $

71+ whnf (double . byteString BL.readDouble) bl

6972 ]

7073 where

7174 -- Used for fixing types

benchmarks/haskell/Benchmarks/Stream.hs+5−16

@@ -18,11 +18,11 @@ import qualified Data.Text.Encoding as T

1818import qualified Data.Text.Encoding.Error as E

1919import qualified Data.Text.Internal.Encoding.Fusion as T

2020import qualified Data.Text.Internal.Encoding.Fusion.Common as F

21−import qualified Data.Text.Internal.Fusion as F

21+import qualified Data.Text.Internal.Fusion as T

2222import qualified Data.Text.IO as T

2323import qualified Data.Text.Lazy.Encoding as TL

2424import qualified Data.Text.Internal.Lazy.Encoding.Fusion as TL

25−import qualified Data.Text.Internal.Lazy.Fusion as FL

25+import qualified Data.Text.Internal.Lazy.Fusion as TL

2626import qualified Data.Text.Lazy.IO as TL

2727

2828instance NFData a => NFData (Stream a) where

@@ -53,25 +53,14 @@ benchmark fp = do

5353 !utf32beL = TL.encodeUtf32BE tl

5454

5555 -- For the functions which operate on streams

56− let !s = F.stream t

56+ let !s = T.stream t

5757

5858 return $ bgroup "Stream"

5959

6060 -- Fusion

6161 [ bgroup "stream" $

62− [ bench "Text" $ nf F.stream t

63− , bench "LazyText" $ nf FL.stream tl

64− ]

65− -- must perform exactly the same as stream above due to

66− -- stream/unstream (i.e. stream after unstream) fusion

67− , bgroup "stream-fusion" $

68− [ bench "Text" $ nf (F.stream . F.unstream . F.stream) t

69− , bench "LazyText" $ nf (FL.stream . FL.unstream . FL.stream) tl

70− ]

71− -- measure the overhead of unstream after stream

72− , bgroup "stream-unstream" $

73− [ bench "Text" $ nf (F.unstream . F.stream) t

74− , bench "LazyText" $ nf (FL.unstream . FL.stream) tl

62+ [ bench "Text" $ nf T.stream t

63+ , bench "LazyText" $ nf TL.stream tl

7564 ]

7665

7766 -- Encoding.Fusion

benchmarks/text-benchmarks.cabal+3−13

@@ -3,7 +3,7 @@ version: 0.0.0.0

33synopsis: Benchmarks for the text package

44description: Benchmarks for the text package

55homepage: https://bitbucket.org/bos/text

6−license: BSD2

6+license: BSD3

77license-file: ../LICENSE

88author: Jasper Van der Jeugt <jaspervdj@gmail.com>,

99 Bryan O'Sullivan <bos@serpentine.com>,

@@ -15,11 +15,6 @@ build-type: Simple

1515

1616cabal-version: >=1.2

1717

18−flag bytestring-builder

19− description: Depend on the bytestring-builder package for backwards compatibility.

20− default: False

21− manual: False

22−

2318flag llvm

2419 description: use LLVM

2520 default: False

@@ -38,7 +33,8 @@ executable text-benchmarks

3833 build-depends: base == 4.*,

3934 binary,

4035 blaze-builder,

41− bytestring-lexing >= 0.5.0,

36+ bytestring,

37+ bytestring-lexing,

4238 containers,

4339 criterion >= 0.10.0.0,

4440 deepseq,

@@ -50,12 +46,6 @@ executable text-benchmarks

5046 utf8-string,

5147 vector

5248

53− if flag(bytestring-builder)

54− build-depends: bytestring >= 0.9 && < 0.10.4,

55− bytestring-builder >= 0.10.4

56− else

57− build-depends: bytestring >= 0.10.4

58−

5949executable text-multilang

6050 hs-source-dirs: haskell

6151 main-is: Multilang.hs

changelog.md+1−28

@@ -1,33 +1,6 @@

1−1.2.2.1

2−

3−* The switch to `integer-pure` in 1.2.2.0 was apparently mistaken.

4− The build flag has been renamed accordingly. Your army of diligent

5− maintainers apologizes for the churn.

6−

7−* Spec compliance: toCaseFold now follows the Unicode 8.0 spec

8− (updated from 7.0)

9−

10−* An STG lint error has been fixed

11−

12−1.2.2.0

13−

14−* The `integer-simple` package, upon which this package optionally

15− depended, has been replaced with `integer-pure`. The build flag has

16− been renamed accordingly.

17−

18−* Bug fix: For the `Binary` instance, If UTF-8 decoding fails during a

19− `get`, the error is propagated via `fail` instead of an uncatchable

20− crash.

21−

22−* New function: `takeWhileEnd`

23−

24−* New instances for the `Text` types:

25− * if `base` >= 4.7: `PrintfArg`

26− * if `base` >= 4.9: `Semigroup`

27−

2811.2.1.3

292

30−* Bug fix: As it turns out, moving the literal rewrite rules to simplifier

3+* Bug fix: As it turns out, moving the literal rewrite rules to simplifier

314 phase 2 does not prevent competition with the `unpack` rule, which is

325 also active in this phase. Unfortunately this was hidden due to a silly

336 test environment mistake. Moving literal rules back to phase 1 finally

tests/literal-rule-test.sh+1−1

@@ -6,7 +6,7 @@ function check_firings() {

66 rule=$1

77 expected=$2

88 build="ghc -O -ddump-rule-firings LiteralRuleTest.hs"

9− build="$build -i.. -I../include"

9+ build="$build -i.. -I../include -DMIN_VERSION_bytestring(a,b,c)=1"

1010 touch LiteralRuleTest.hs

1111 echo -n "Want to see $expected firings of rule $rule... " >&2

1212 firings=$($build 2>&1 | grep "Rule fired: $rule\$" | wc -l)

tests/text-tests.cabal+1−1

@@ -3,7 +3,7 @@ version: 0.0.0.0

33synopsis: Functional tests for the text package

44description: Functional tests for the text package

55homepage: https://github.com/bos/text

6−license: BSD2

6+license: BSD3

77license-file: ../LICENSE

88author: Jasper Van der Jeugt <jaspervdj@gmail.com>,

99 Bryan O'Sullivan <bos@serpentine.com>,

text.cabal+6−19

@@ -1,5 +1,5 @@

11name: text

2−version: 1.2.2.1

2+version: 1.2.1.3

33homepage: https://github.com/bos/text

44bug-reports: https://github.com/bos/text/issues

55synopsis: An efficient packed Unicode text type.

@@ -31,7 +31,7 @@ description:

3131 the @text-icu@ package:

3232 <http://hackage.haskell.org/package/text-icu>

3333

34−license: BSD2

34+license: BSD3

3535license-file: LICENSE

3636author: Bryan O'Sullivan <bos@serpentine.com>

3737maintainer: Bryan O'Sullivan <bos@serpentine.com>

@@ -64,11 +64,6 @@ extra-source-files:

6464 tests/scripts/*.sh

6565 tests/text-tests.cabal

6666

67−flag bytestring-builder

68− description: Depend on the bytestring-builder package for backwards compatibility.

69− default: False

70− manual: False

71−

7267flag developer

7368 description: operate in developer mode

7469 default: False

@@ -76,8 +71,6 @@ flag developer

7671

7772flag integer-simple

7873 description: Use the simple integer library instead of GMP

79− default: False

80− manual: False

8174

8275library

8376 c-sources: cbits/cbits.c

@@ -138,11 +131,10 @@ library

138131 deepseq >= 1.1.0.0,

139132 ghc-prim >= 0.2

140133

141− if flag(bytestring-builder)

142− build-depends: bytestring >= 0.9 && < 0.10.4,

143− bytestring-builder >= 0.10.4

134+ if impl(ghc >= 7.7)

135+ build-depends: bytestring >= 0.10.4.0

144136 else

145− build-depends: bytestring >= 0.10.4

137+ build-depends: bytestring >= 0.9

146138

147139 cpp-options: -DHAVE_DEEPSEQ

148140 ghc-options: -Wall -fwarn-tabs -funbox-strict-fields -O2

@@ -177,6 +169,7 @@ test-suite tests

177169 array,

178170 base,

179171 binary,

172+ bytestring,

180173 deepseq,

181174 directory,

182175 ghc-prim,

@@ -186,12 +179,6 @@ test-suite tests

186179 test-framework-hunit >= 0.2,

187180 test-framework-quickcheck2 >= 0.2

188181

189− if flag(bytestring-builder)

190− build-depends: bytestring >= 0.9 && < 0.10.4,

191− bytestring-builder >= 0.10.4

192− else

193− build-depends: bytestring >= 0.10.4

194−

195182 if flag(integer-simple)

196183 cpp-options: -DINTEGER_SIMPLE

197184 build-depends: integer-simple >= 0.1 && < 0.5