6eaebff...master · text

git.iko.soy/text

on master help sign in

.hgtags+2

since splitsnapshots

unifiedsplit

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

6278227a84740b70dcd4cf7a65f3bcf603d87e48e2 1.2.1.1

6340f268e6735749ef36f487e1d928eaa957bb431d 1.2.1.2

64631fd055e27fa10983e17e9ad36d1b285b85c661 1.2.1.3

65+8221a68ed5ec37028357df9c6c25f52320e54ad9 1.2.2.0

66+ce1c5ac65eb9f5580114b4e380092b05a485e95d 1.2.2.1

Data/Text.hs+12−9

@@ -238,6 +238,7 @@ import Data.ByteString (ByteString)

238import qualified Data.Text.Lazy as L

239import Data.Int (Int64)

240#endif

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

241#if __GLASGOW_HASKELL__ >= 708

242#if __GLASGOW_HASKELL__ >= 708

242import qualified GHC.Exts as Exts

243import qualified GHC.Exts as Exts

243#endif

244#endif

@@ -485,8 +486,8 @@ head t = S.head (stream t)

485uncons :: Text -> Maybe (Char, Text)

486uncons :: Text -> Maybe (Char, Text)

486uncons t@(Text arr off len)

487uncons t@(Text arr off len)

487 | len <= 0 = Nothing

488 | len <= 0 = Nothing

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

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

490+ in (c, text arr (off+d) (len-d))

489− where Iter c d = iter t 0

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

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

491

492

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

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

@@ -571,7 +572,9 @@ isSingleton = S.isSingleton . stream

571-- Subject to fusion.

572-- Subject to fusion.

572length :: Text -> Int

573length :: Text -> Int

573length t = S.length (stream t)

574length t = S.length (stream t)

574−{-# INLINE length #-}

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.

575

578

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

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

577-- Subject to fusion.

580-- Subject to fusion.

@@ -590,32 +593,32 @@ compareLength t n = S.compareLengthI (stream t) n

590

593

591{-# RULES

594{-# RULES

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

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

593− (==) (length t) n = compareLength t n == EQ

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

594 #-}

597 #-}

595

598

596{-# RULES

599{-# RULES

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

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

598− (/=) (length t) n = compareLength t n /= EQ

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

599 #-}

602 #-}

600

603

601{-# RULES

604{-# RULES

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

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

603− (<) (length t) n = compareLength t n == LT

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

604 #-}

607 #-}

605

608

606{-# RULES

609{-# RULES

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

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

608− (<=) (length t) n = compareLength t n /= GT

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

609 #-}

612 #-}

610

613

611{-# RULES

614{-# RULES

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

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

613− (>) (length t) n = compareLength t n == GT

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

614 #-}

617 #-}

615

618

616{-# RULES

619{-# RULES

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

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

618− (>=) (length t) n = compareLength t n /= LT

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

619 #-}

622 #-}

620

623

621-- -----------------------------------------------------------------------------

624-- -----------------------------------------------------------------------------

Data/Text/Array.hs+5−4

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

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

21--

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

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

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

24-- naming.

25module Data.Text.Array

26 (

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

74#endif

75import GHC.Base (ByteArray#, MutableByteArray#, Int(..),

76 indexWord16Array#, newByteArray#,

77− unsafeCoerce#, writeWord16Array#)

77+ unsafeFreezeByteArray#, writeWord16Array#)

78import GHC.ST (ST(..), runST)

79import GHC.Word (Word16(..))

80import Prelude hiding (length, read)

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

130

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

132unsafeFreeze :: MArray s -> ST s Array

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

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

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

134+ case unsafeFreezeByteArray# maBA s1# of

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

135#if defined(ASSERTS)

136#if defined(ASSERTS)

136 maLen

137 maLen

137#endif

138#endif

Data/Text/Encoding.hs+7−18

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

55 , encodeUtf32LE

56 , encodeUtf32BE

58−#if MIN_VERSION_bytestring(0,10,4)

59 -- * Encoding Text using ByteString Builders

58 -- * Encoding Text using ByteString Builders

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

61− -- @bytestring >= 0.10.4.0@.

62 , encodeUtf8Builder

59 , encodeUtf8Builder

63 , encodeUtf8BuilderEscaped

60 , encodeUtf8BuilderEscaped

64−#endif

65 ) where

61 ) where

67#if __GLASGOW_HASKELL__ >= 702

63#if __GLASGOW_HASKELL__ >= 702

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

70import Control.Monad.ST (unsafeIOToST, unsafeSTToIO)

66import Control.Monad.ST (unsafeIOToST, unsafeSTToIO)

71#endif

67#endif

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−

83import Control.Exception (evaluate, try)

69import Control.Exception (evaluate, try)

84import Control.Monad.ST (runST)

70import Control.Monad.ST (runST)

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

85import Data.ByteString as B

72import Data.ByteString as B

86import Data.ByteString.Internal as B hiding (c2w)

73import Data.ByteString.Internal as B hiding (c2w)

87import Data.Text.Encoding.Error (OnDecodeError, UnicodeException, strictDecode)

74import Data.Text.Encoding.Error (OnDecodeError, UnicodeException, strictDecode)

88import Data.Text.Internal (Text(..), safe, text)

75import Data.Text.Internal (Text(..), safe, text)

89import Data.Text.Internal.Private (runText)

76import Data.Text.Internal.Private (runText)

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

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

91import Data.Text.Internal.Unsafe.Shift (shiftR)

78import Data.Text.Internal.Unsafe.Shift (shiftR)

92import Data.Text.Show ()

79import Data.Text.Show ()

93import Data.Text.Unsafe (unsafeDupablePerformIO)

80import Data.Text.Unsafe (unsafeDupablePerformIO)

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

98import Foreign.Ptr (Ptr, minusPtr, nullPtr, plusPtr)

85import Foreign.Ptr (Ptr, minusPtr, nullPtr, plusPtr)

99import Foreign.Storable (Storable, peek, poke)

86import Foreign.Storable (Storable, peek, poke)

100import GHC.Base (ByteArray#, MutableByteArray#)

87import 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

101import qualified Data.Text.Array as A

92import qualified Data.Text.Array as A

102import qualified Data.Text.Internal.Encoding.Fusion as E

93import qualified Data.Text.Internal.Encoding.Fusion as E

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

103import qualified Data.Text.Internal.Fusion as F

95import qualified Data.Text.Internal.Fusion as F

104

105#include "text_cbits.h"

97#include "text_cbits.h"

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

315decodeUtf8' = unsafeDupablePerformIO . try . evaluate . decodeUtf8With strictDecode

307decodeUtf8' = unsafeDupablePerformIO . try . evaluate . decodeUtf8With strictDecode

316{-# INLINE decodeUtf8' #-}

308{-# INLINE decodeUtf8' #-}

317

309

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

319−

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

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

321encodeUtf8Builder :: Text -> B.Builder

311encodeUtf8Builder :: Text -> B.Builder

322encodeUtf8Builder = encodeUtf8BuilderEscaped (BP.liftFixedToBounded BP.word8)

312encodeUtf8Builder = encodeUtf8BuilderEscaped (BP.liftFixedToBounded BP.word8)

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

377 outerLoop i (B.BufferRange op ope)

367 outerLoop i (B.BufferRange op ope)

378 where

368 where

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

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

380−#endif

381

370

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

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

383encodeUtf8 :: Text -> ByteString

372encodeUtf8 :: Text -> ByteString

Data/Text/Internal/Builder.hs+3−1

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

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

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

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

10--

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

12-- Stability : experimental

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

242 !t = Text arr o u

243 ts <- inlineInterleaveST (k b)

244 return $! t : ts

245+{-# INLINE [1] flush #-}

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

245

247

246------------------------------------------------------------------------

248------------------------------------------------------------------------

247

249

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

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

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

5−-- License: BSD3

5+-- License: BSD-style

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

7-- Stability: experimental

8-- Portability: portable

Data/Text/Internal/Fusion.hs+27−17

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

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

99unstream :: Stream Char -> Text

100unstream (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.

101− let mlen = upperBound 4 len

105+ let mlen = upperBound 4 len + 1

102 arr0 <- A.new mlen

106 arr0 <- A.new mlen

103− let outer arr top = loop

107+ let outer !arr !maxi = encode

104 where

108 where

105− loop !s !i =

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

110+ encode !si !di =

106− case next0 s of

111+ case next0 si of

107− Done -> done arr i

112+ Done -> done arr di

108− Skip s' -> loop s' i

113+ Skip si' -> encode si' di

109− Yield x s'

114+ Yield c si'

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

115+ -- simply check for the worst case

111− let top' = (top + 1) `shiftL` 1

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

112− arr' <- A.new top'

125+ arr' <- A.new newlen

113− A.copyM arr' 0 arr 0 top

126+ A.copyM arr' 0 arr 0 di

114− outer arr' top' s i

127+ outer arr' (newlen - 1) si di

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

128+

116− loop s' (i+d)

117− where j | ord x < 0x10000 = i

118− | otherwise = i + 1

119− outer arr0 mlen s0 0

129+ outer arr0 (mlen - 1) s0 0

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

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

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

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

122

132

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

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

1{-# LANGUAGE Rank2Types #-}

2-- AUTOMATICALLY GENERATED - DO NOT EDIT

3-- Generated by scripts/CaseMapping.hs

4−-- CaseFolding-7.0.0.txt

4+-- CaseFolding-8.0.0.txt

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

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

6−-- SpecialCasing-7.0.0.txt

6+-- SpecialCasing-8.0.0.txt

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

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

9module Data.Text.Internal.Fusion.CaseMapping where

10import Data.Char

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

337foldMapping '\x01f0' s = Yield '\x006a' (CC s '\x030c' '\x0000')

338-- COMBINING GREEK YPOGEGRAMMENI

339foldMapping '\x0345' s = Yield '\x03b9' (CC s '\x0000' '\x0000')

340−-- GREEK CAPITAL LETTER YOT

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

342-- GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS

340-- GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS

343foldMapping '\x0390' s = Yield '\x03b9' (CC s '\x0308' '\x0301')

341foldMapping '\x0390' s = Yield '\x03b9' (CC s '\x0308' '\x0301')

344-- GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS

342-- GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS

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

359foldMapping '\x03f1' s = Yield '\x03c1' (CC s '\x0000' '\x0000')

357foldMapping '\x03f1' s = Yield '\x03c1' (CC s '\x0000' '\x0000')

360-- GREEK LUNATE EPSILON SYMBOL

358-- GREEK LUNATE EPSILON SYMBOL

361foldMapping '\x03f5' s = Yield '\x03b5' (CC s '\x0000' '\x0000')

359foldMapping '\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')

370-- ARMENIAN SMALL LIGATURE ECH YIWN

360-- ARMENIAN SMALL LIGATURE ECH YIWN

371foldMapping '\x0587' s = Yield '\x0565' (CC s '\x0582' '\x0000')

361foldMapping '\x0587' s = Yield '\x0565' (CC s '\x0582' '\x0000')

372−-- GEORGIAN CAPITAL LETTER YN

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

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

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

374−-- GEORGIAN CAPITAL LETTER AEN

372+-- CHEROKEE SMALL LETTER MV

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

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

376-- LATIN SMALL LETTER H WITH LINE BELOW

374-- LATIN SMALL LETTER H WITH LINE BELOW

377foldMapping '\x1e96' s = Yield '\x0068' (CC s '\x0331' '\x0000')

375foldMapping '\x1e96' s = Yield '\x0068' (CC s '\x0331' '\x0000')

378-- LATIN SMALL LETTER T WITH DIAERESIS

376-- LATIN SMALL LETTER T WITH DIAERESIS

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

547foldMapping '\x1ff7' s = Yield '\x03c9' (CC s '\x0342' '\x03b9')

545foldMapping '\x1ff7' s = Yield '\x03c9' (CC s '\x0342' '\x03b9')

548-- GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI

546-- GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI

549foldMapping '\x1ffc' s = Yield '\x03c9' (CC s '\x03b9' '\x0000')

547foldMapping '\x1ffc' s = Yield '\x03c9' (CC s '\x03b9' '\x0000')

550−-- COPTIC CAPITAL LETTER BOHAIRIC KHEI

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

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')

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

558−-- LATIN CAPITAL LETTER B WITH FLOURISH

550+-- LATIN CAPITAL LETTER CHI

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

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

560−-- LATIN CAPITAL LETTER F WITH STROKE

552+-- LATIN CAPITAL LETTER BETA

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

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

562−-- LATIN CAPITAL LETTER VOLAPUK AE

554+-- LATIN CAPITAL LETTER OMEGA

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

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

564−-- LATIN CAPITAL LETTER VOLAPUK OE

556+-- CHEROKEE SMALL LETTER A

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

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

566−-- LATIN CAPITAL LETTER VOLAPUK UE

558+-- CHEROKEE SMALL LETTER E

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

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

568−-- LATIN CAPITAL LETTER H WITH HOOK

560+-- CHEROKEE SMALL LETTER I

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

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

570−-- LATIN CAPITAL LETTER REVERSED OPEN E

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

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

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

572−-- LATIN CAPITAL LETTER SCRIPT G

700+-- CHEROKEE SMALL LETTER TSV

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

702+-- CHEROKEE SMALL LETTER WA

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

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

574−-- LATIN CAPITAL LETTER L WITH BELT

704+-- CHEROKEE SMALL LETTER WE

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

706+-- CHEROKEE SMALL LETTER WI

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

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

576−-- LATIN CAPITAL LETTER TURNED K

708+-- CHEROKEE SMALL LETTER WO

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

710+-- CHEROKEE SMALL LETTER WU

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

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

578−-- LATIN CAPITAL LETTER TURNED T

712+-- CHEROKEE SMALL LETTER WV

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

714+-- CHEROKEE SMALL LETTER YA

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

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

580-- LATIN SMALL LIGATURE FF

716-- LATIN SMALL LIGATURE FF

581foldMapping '\xfb00' s = Yield '\x0066' (CC s '\x0066' '\x0000')

717foldMapping '\xfb00' s = Yield '\x0066' (CC s '\x0066' '\x0000')

582-- LATIN SMALL LIGATURE FI

718-- LATIN SMALL LIGATURE FI

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

601foldMapping '\xfb16' s = Yield '\x057e' (CC s '\x0576' '\x0000')

737foldMapping '\xfb16' s = Yield '\x057e' (CC s '\x0576' '\x0000')

602-- ARMENIAN SMALL LIGATURE MEN XEH

738-- ARMENIAN SMALL LIGATURE MEN XEH

603foldMapping '\xfb17' s = Yield '\x0574' (CC s '\x056d' '\x0000')

739foldMapping '\xfb17' s = Yield '\x0574' (CC s '\x056d' '\x0000')

604−-- WARANG CITI CAPITAL LETTER NGAA

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

606−-- WARANG CITI CAPITAL LETTER A

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

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

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

608−-- WARANG CITI CAPITAL LETTER WI

766+-- OLD HUNGARIAN CAPITAL LETTER EG

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

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

610−-- WARANG CITI CAPITAL LETTER YU

768+-- OLD HUNGARIAN CAPITAL LETTER EGY

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

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

612−-- WARANG CITI CAPITAL LETTER YA

770+-- OLD HUNGARIAN CAPITAL LETTER EH

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

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

614−-- WARANG CITI CAPITAL LETTER YO

772+-- OLD HUNGARIAN CAPITAL LETTER I

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

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

616−-- WARANG CITI CAPITAL LETTER II

774+-- OLD HUNGARIAN CAPITAL LETTER II

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

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')

618−-- WARANG CITI CAPITAL LETTER UU

826+-- OLD HUNGARIAN 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')

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

648−-- WARANG CITI CAPITAL LETTER AM

828+-- OLD HUNGARIAN CAPITAL LETTER NIKOLSBURG UE

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')

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

652−-- WARANG CITI CAPITAL LETTER PU

830+-- OLD HUNGARIAN CAPITAL LETTER RUDIMENTA UE

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')

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

656−-- WARANG CITI CAPITAL LETTER HOLO

832+-- OLD HUNGARIAN CAPITAL LETTER EV

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

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

658−-- WARANG CITI CAPITAL LETTER HORR

834+-- OLD HUNGARIAN CAPITAL LETTER EZ

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

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

660−-- WARANG CITI CAPITAL LETTER HAR

836+-- OLD HUNGARIAN CAPITAL LETTER EZS

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

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

662−-- WARANG CITI CAPITAL LETTER SSUU

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

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')

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

666−-- WARANG CITI CAPITAL LETTER VIYO

840+-- OLD HUNGARIAN CAPITAL LETTER US

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

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

668foldMapping c s = Yield (toLower c) (CC s '\0' '\0')

842foldMapping c s = Yield (toLower c) (CC s '\0' '\0')

Data/Text/Internal/Fusion/Common.hs+3−3

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

669-- ** Generating and unfolding streams

670

671replicateCharI :: Integral a => a -> Char -> Stream Char

672−replicateCharI n c

672+replicateCharI !n !c

673 | n < 0 = empty

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

675 where

676− next i | i >= n = Done

676+ next !i | i >= n = Done

677− | otherwise = Yield c (i + 1)

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

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

679

680data RI s = RI !s {-# UNPACK #-} !Int64

Data/Text/Lazy.hs+2−2

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

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

546 #-}

547

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

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

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

550init :: Text -> Text

551init (Chunk t0 ts0) = go t0 ts0

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

581isSingleton = S.isSingleton . stream

582{-# INLINE isSingleton #-}

583

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

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

585-- non-empty. Subject to fusion.

586last :: Text -> Char

587last Empty = emptyError "last"

Data/Text/Lazy/Builder.hs+1−1

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

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

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

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

12--

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

14-- Stability : experimental

Data/Text/Lazy/Builder/Int.hs+1−1

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

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

10−-- License: BSD3

10+-- License: BSD-style

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

12-- Stability: experimental

13-- Portability: portable

Data/Text/Lazy/Encoding.hs+5−15

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

46 , encodeUtf32LE

47 , encodeUtf32BE

49−#if MIN_VERSION_bytestring(0,10,4)

50 -- * Encoding Text using ByteString Builders

49 -- * Encoding Text using ByteString Builders

51 , encodeUtf8Builder

50 , encodeUtf8Builder

52 , encodeUtf8BuilderEscaped

51 , encodeUtf8BuilderEscaped

53−#endif

54 ) where

52 ) where

56import Control.Exception (evaluate, try)

54import Control.Exception (evaluate, try)

55+import Data.Monoid (Monoid(..))

57import Data.Text.Encoding.Error (OnDecodeError, UnicodeException, strictDecode)

56import Data.Text.Encoding.Error (OnDecodeError, UnicodeException, strictDecode)

58import Data.Text.Internal.Lazy (Text(..), chunk, empty, foldrChunks)

57import Data.Text.Internal.Lazy (Text(..), chunk, empty, foldrChunks)

59−import qualified Data.ByteString as S

60−import qualified Data.ByteString.Lazy as B

61−import qualified Data.ByteString.Lazy.Internal as B

62−import qualified Data.ByteString.Unsafe as B

63−#if MIN_VERSION_bytestring(0,10,4)

64import Data.Word (Word8)

58import Data.Word (Word8)

65−import Data.Monoid (Monoid(..))

59+import qualified Data.ByteString as S

66import qualified Data.ByteString.Builder as B

60import qualified Data.ByteString.Builder as B

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

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

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

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

69−#endif

63+import qualified Data.ByteString.Lazy as B

64+import qualified Data.ByteString.Lazy.Internal as B

65+import qualified Data.ByteString.Unsafe as B

70import qualified Data.Text as T

66import qualified Data.Text as T

71import qualified Data.Text.Encoding as TE

67import qualified Data.Text.Encoding as TE

72import qualified Data.Text.Internal.Lazy.Encoding.Fusion as E

68import qualified Data.Text.Internal.Lazy.Encoding.Fusion as E

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

146{-# INLINE decodeUtf8' #-}

142{-# INLINE decodeUtf8' #-}

147

143

148encodeUtf8 :: Text -> B.ByteString

144encodeUtf8 :: Text -> B.ByteString

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

150encodeUtf8 Empty = B.empty

145encodeUtf8 Empty = B.empty

151encodeUtf8 lt@(Chunk t _) =

146encodeUtf8 lt@(Chunk t _) =

152 B.toLazyByteStringWith strategy B.empty $ encodeUtf8Builder lt

147 B.toLazyByteStringWith strategy B.empty $ encodeUtf8Builder lt

@@ -168,11 +163,6 @@ encodeUtf8BuilderEscaped :: BP.BoundedPrim Word8 -> Text -> B.Builder

168encodeUtf8BuilderEscaped prim =

163encodeUtf8BuilderEscaped prim =

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

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

170

165

171−#else

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

173−encodeUtf8 Empty = B.Empty

174−#endif

175−

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

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

177decodeUtf16LEWith :: OnDecodeError -> B.ByteString -> Text

167decodeUtf16LEWith :: OnDecodeError -> B.ByteString -> Text

178decodeUtf16LEWith onErr bs = F.unstream (E.streamUtf16LE onErr bs)

168decodeUtf16LEWith onErr bs = F.unstream (E.streamUtf16LE onErr bs)

benchmarks/haskell/Benchmarks.hs+1−1

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

53 , Mul.benchmark

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

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

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

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

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

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

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

benchmarks/haskell/Benchmarks/Pure.hs+7

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

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

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

264 ]

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+ ]

265 , bgroup "words"

272 , bgroup "words"

266 [ benchT $ nf T.words ta

273 [ benchT $ nf T.words ta

267 , benchTL $ nf TL.words tla

274 , benchTL $ nf TL.words tla

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

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

18import qualified Data.Text.Encoding.Error as E

19import qualified Data.Text.Internal.Encoding.Fusion as T

20import qualified Data.Text.Internal.Encoding.Fusion.Common as F

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

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

22import qualified Data.Text.IO as T

23import qualified Data.Text.Lazy.Encoding as TL

24import qualified Data.Text.Internal.Lazy.Encoding.Fusion as TL

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

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

26import qualified Data.Text.Lazy.IO as TL

28instance NFData a => NFData (Stream a) where

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

53 !utf32beL = TL.encodeUtf32BE tl

55 -- For the functions which operate on streams

56− let !s = T.stream t

56+ let !s = F.stream t

58 return $ bgroup "Stream"

60 -- Fusion

61 [ bgroup "stream" $

62− [ bench "Text" $ nf T.stream t

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

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

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

64 ]

75 ]

66 -- Encoding.Fusion

77 -- Encoding.Fusion

benchmarks/text-benchmarks.cabal+12−2

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

3synopsis: Benchmarks for the text package

4description: Benchmarks for the text package

5homepage: https://bitbucket.org/bos/text

6−license: BSD3

6+license: BSD2

7license-file: ../LICENSE

8author: Jasper Van der Jeugt <jaspervdj@gmail.com>,

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

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

16cabal-version: >=1.2

18+flag bytestring-builder

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

20+ default: False

21+ manual: False

22+

18flag llvm

23flag llvm

19 description: use LLVM

24 description: use LLVM

20 default: False

25 default: False

@@ -33,7 +38,6 @@ executable text-benchmarks

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

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

34 binary,

39 binary,

35 blaze-builder,

40 blaze-builder,

36− bytestring,

37 bytestring-lexing >= 0.5.0,

41 bytestring-lexing >= 0.5.0,

38 containers,

42 containers,

39 criterion >= 0.10.0.0,

43 criterion >= 0.10.0.0,

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

46 utf8-string,

50 utf8-string,

47 vector

51 vector

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+

49executable text-multilang

59executable text-multilang

50 hs-source-dirs: haskell

60 hs-source-dirs: haskell

51 main-is: Multilang.hs

61 main-is: Multilang.hs

changelog.md+28−1

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

1+1.2.2.1

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.

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

8+ (updated from 7.0)

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+

11.2.1.3

281.2.1.3

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

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

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

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

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

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

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

33 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() {

6 rule=$1

7 expected=$2

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

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

9+ build="$build -i.. -I../include"

10 touch LiteralRuleTest.hs

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

12 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

3synopsis: Functional tests for the text package

4description: Functional tests for the text package

5homepage: https://github.com/bos/text

6−license: BSD3

6+license: BSD2

7license-file: ../LICENSE

8author: Jasper Van der Jeugt <jaspervdj@gmail.com>,

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

text.cabal+19−6

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

1name: text

2−version: 1.2.1.3

2+version: 1.2.2.1

3homepage: https://github.com/bos/text

4bug-reports: https://github.com/bos/text/issues

5synopsis: An efficient packed Unicode text type.

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

31 the @text-icu@ package:

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

34−license: BSD3

34+license: BSD2

35license-file: LICENSE

36author: Bryan O'Sullivan <bos@serpentine.com>

37maintainer: Bryan O'Sullivan <bos@serpentine.com>

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

64 tests/scripts/*.sh

65 tests/text-tests.cabal

67+flag bytestring-builder

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

69+ default: False

70+ manual: False

71+

67flag developer

72flag developer

68 description: operate in developer mode

73 description: operate in developer mode

69 default: False

74 default: False

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

72flag integer-simple

77flag integer-simple

73 description: Use the simple integer library instead of GMP

78 description: Use the simple integer library instead of GMP

79+ default: False

80+ manual: False

75library

82library

76 c-sources: cbits/cbits.c

83 c-sources: cbits/cbits.c

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

131 deepseq >= 1.1.0.0,

138 deepseq >= 1.1.0.0,

132 ghc-prim >= 0.2

139 ghc-prim >= 0.2

133

140

134− if impl(ghc >= 7.7)

141+ if flag(bytestring-builder)

135− build-depends: bytestring >= 0.10.4.0

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

143+ bytestring-builder >= 0.10.4

136 else

144 else

137− build-depends: bytestring >= 0.9

145+ build-depends: bytestring >= 0.10.4

138

146

139 cpp-options: -DHAVE_DEEPSEQ

147 cpp-options: -DHAVE_DEEPSEQ

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

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

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

169 array,

177 array,

170 base,

178 base,

171 binary,

179 binary,

172− bytestring,

173 deepseq,

180 deepseq,

174 directory,

181 directory,

175 ghc-prim,

182 ghc-prim,

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

179 test-framework-hunit >= 0.2,

186 test-framework-hunit >= 0.2,

180 test-framework-quickcheck2 >= 0.2

187 test-framework-quickcheck2 >= 0.2

181

188

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+

182 if flag(integer-simple)

195 if flag(integer-simple)

183 cpp-options: -DINTEGER_SIMPLE

196 cpp-options: -DINTEGER_SIMPLE

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

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