master...d93151d · text

git.iko.soy/text

on d93151d help sign in

.hgtags+1

since splitsnapshots

unifiedsplit

@@ -64,3 +64,4 @@ f8a60279237c1c28e094868740d9188dd94fcc9e 1.2.0.0

64631fd055e27fa10983e17e9ad36d1b285b85c661 1.2.1.3

658221a68ed5ec37028357df9c6c25f52320e54ad9 1.2.2.0

66ce1c5ac65eb9f5580114b4e380092b05a485e95d 1.2.2.1

67+d72c634a91ffe27ec5cd03921dd53efc8129d8f6 1.2.2.2

Data/Text.hs+1−1

@@ -1099,8 +1099,8 @@ takeEnd n t@(Text arr off len)

1099iterNEnd :: Int -> Text -> Int

1100iterNEnd n t@(Text _arr _off len) = loop (len-1) n

1101 where loop i !m

1102+ | m <= 0 = i+1

1102 | i <= 0 = 0

1103 | i <= 0 = 0

1103− | m <= 1 = i

1104 | otherwise = loop (i+d) (m-1)

1105 where d = reverseIter_ t i

1106

Data/Text/Foreign.hs+1−1

@@ -108,7 +108,7 @@ takeWord16 (I16 n) t@(Text arr off len)

108 | n >= len || m >= len = t

109 | otherwise = Text arr off m

110 where

111− m | w < 0xDB00 || w > 0xD8FF = n

111+ m | w < 0xD800 || w > 0xDBFF = n

112 | otherwise = n+1

113 w = A.unsafeIndex arr (off+n-1)

114

Data/Text/Internal/Fusion/CaseMapping.hs+164−4

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

1{-# LANGUAGE Rank2Types #-}

2-- AUTOMATICALLY GENERATED - DO NOT EDIT

3-- Generated by scripts/CaseMapping.hs

4−-- CaseFolding-8.0.0.txt

4+-- CaseFolding-9.0.0.txt

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

5+-- Date: 2016-03-02, 18:54:54 GMT

6−-- SpecialCasing-8.0.0.txt

6+-- SpecialCasing-9.0.0.txt

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

7+-- Date: 2016-03-02, 18:55:13 GMT

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

10import Data.Char

@@ -371,6 +371,24 @@ foldMapping '\x13fb' s = Yield '\x13f3' (CC s '\x0000' '\x0000')

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

372-- CHEROKEE SMALL LETTER MV

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

374+-- CYRILLIC SMALL LETTER ROUNDED VE

375+foldMapping '\x1c80' s = Yield '\x0432' (CC s '\x0000' '\x0000')

376+-- CYRILLIC SMALL LETTER LONG-LEGGED DE

377+foldMapping '\x1c81' s = Yield '\x0434' (CC s '\x0000' '\x0000')

378+-- CYRILLIC SMALL LETTER NARROW O

379+foldMapping '\x1c82' s = Yield '\x043e' (CC s '\x0000' '\x0000')

380+-- CYRILLIC SMALL LETTER WIDE ES

381+foldMapping '\x1c83' s = Yield '\x0441' (CC s '\x0000' '\x0000')

382+-- CYRILLIC SMALL LETTER TALL TE

383+foldMapping '\x1c84' s = Yield '\x0442' (CC s '\x0000' '\x0000')

384+-- CYRILLIC SMALL LETTER THREE-LEGGED TE

385+foldMapping '\x1c85' s = Yield '\x0442' (CC s '\x0000' '\x0000')

386+-- CYRILLIC SMALL LETTER TALL HARD SIGN

387+foldMapping '\x1c86' s = Yield '\x044a' (CC s '\x0000' '\x0000')

388+-- CYRILLIC SMALL LETTER TALL YAT

389+foldMapping '\x1c87' s = Yield '\x0463' (CC s '\x0000' '\x0000')

390+-- CYRILLIC SMALL LETTER UNBLENDED UK

391+foldMapping '\x1c88' s = Yield '\xa64b' (CC s '\x0000' '\x0000')

374-- LATIN SMALL LETTER H WITH LINE BELOW

392-- LATIN SMALL LETTER H WITH LINE BELOW

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

393foldMapping '\x1e96' s = Yield '\x0068' (CC s '\x0331' '\x0000')

376-- LATIN SMALL LETTER T WITH DIAERESIS

394-- LATIN SMALL LETTER T WITH DIAERESIS

@@ -545,6 +563,8 @@ foldMapping '\x1ff6' s = Yield '\x03c9' (CC s '\x0342' '\x0000')

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

563foldMapping '\x1ff7' s = Yield '\x03c9' (CC s '\x0342' '\x03b9')

546-- GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI

564-- GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI

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

565foldMapping '\x1ffc' s = Yield '\x03c9' (CC s '\x03b9' '\x0000')

566+-- LATIN CAPITAL LETTER SMALL CAPITAL I

567+foldMapping '\xa7ae' s = Yield '\x026a' (CC s '\x0000' '\x0000')

548-- LATIN CAPITAL LETTER J WITH CROSSED-TAIL

568-- LATIN CAPITAL LETTER J WITH CROSSED-TAIL

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

569foldMapping '\xa7b2' s = Yield '\x029d' (CC s '\x0000' '\x0000')

550-- LATIN CAPITAL LETTER CHI

570-- LATIN CAPITAL LETTER CHI

@@ -737,6 +757,78 @@ foldMapping '\xfb15' s = Yield '\x0574' (CC s '\x056b' '\x0000')

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

757foldMapping '\xfb16' s = Yield '\x057e' (CC s '\x0576' '\x0000')

738-- ARMENIAN SMALL LIGATURE MEN XEH

758-- ARMENIAN SMALL LIGATURE MEN XEH

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

759foldMapping '\xfb17' s = Yield '\x0574' (CC s '\x056d' '\x0000')

760+-- OSAGE CAPITAL LETTER A

761+foldMapping '\x104b0' s = Yield '\x104d8' (CC s '\x0000' '\x0000')

762+-- OSAGE CAPITAL LETTER AI

763+foldMapping '\x104b1' s = Yield '\x104d9' (CC s '\x0000' '\x0000')

764+-- OSAGE CAPITAL LETTER AIN

765+foldMapping '\x104b2' s = Yield '\x104da' (CC s '\x0000' '\x0000')

766+-- OSAGE CAPITAL LETTER AH

767+foldMapping '\x104b3' s = Yield '\x104db' (CC s '\x0000' '\x0000')

768+-- OSAGE CAPITAL LETTER BRA

769+foldMapping '\x104b4' s = Yield '\x104dc' (CC s '\x0000' '\x0000')

770+-- OSAGE CAPITAL LETTER CHA

771+foldMapping '\x104b5' s = Yield '\x104dd' (CC s '\x0000' '\x0000')

772+-- OSAGE CAPITAL LETTER EHCHA

773+foldMapping '\x104b6' s = Yield '\x104de' (CC s '\x0000' '\x0000')

774+-- OSAGE CAPITAL LETTER E

775+foldMapping '\x104b7' s = Yield '\x104df' (CC s '\x0000' '\x0000')

776+-- OSAGE CAPITAL LETTER EIN

777+foldMapping '\x104b8' s = Yield '\x104e0' (CC s '\x0000' '\x0000')

778+-- OSAGE CAPITAL LETTER HA

779+foldMapping '\x104b9' s = Yield '\x104e1' (CC s '\x0000' '\x0000')

780+-- OSAGE CAPITAL LETTER HYA

781+foldMapping '\x104ba' s = Yield '\x104e2' (CC s '\x0000' '\x0000')

782+-- OSAGE CAPITAL LETTER I

783+foldMapping '\x104bb' s = Yield '\x104e3' (CC s '\x0000' '\x0000')

784+-- OSAGE CAPITAL LETTER KA

785+foldMapping '\x104bc' s = Yield '\x104e4' (CC s '\x0000' '\x0000')

786+-- OSAGE CAPITAL LETTER EHKA

787+foldMapping '\x104bd' s = Yield '\x104e5' (CC s '\x0000' '\x0000')

788+-- OSAGE CAPITAL LETTER KYA

789+foldMapping '\x104be' s = Yield '\x104e6' (CC s '\x0000' '\x0000')

790+-- OSAGE CAPITAL LETTER LA

791+foldMapping '\x104bf' s = Yield '\x104e7' (CC s '\x0000' '\x0000')

792+-- OSAGE CAPITAL LETTER MA

793+foldMapping '\x104c0' s = Yield '\x104e8' (CC s '\x0000' '\x0000')

794+-- OSAGE CAPITAL LETTER NA

795+foldMapping '\x104c1' s = Yield '\x104e9' (CC s '\x0000' '\x0000')

796+-- OSAGE CAPITAL LETTER O

797+foldMapping '\x104c2' s = Yield '\x104ea' (CC s '\x0000' '\x0000')

798+-- OSAGE CAPITAL LETTER OIN

799+foldMapping '\x104c3' s = Yield '\x104eb' (CC s '\x0000' '\x0000')

800+-- OSAGE CAPITAL LETTER PA

801+foldMapping '\x104c4' s = Yield '\x104ec' (CC s '\x0000' '\x0000')

802+-- OSAGE CAPITAL LETTER EHPA

803+foldMapping '\x104c5' s = Yield '\x104ed' (CC s '\x0000' '\x0000')

804+-- OSAGE CAPITAL LETTER SA

805+foldMapping '\x104c6' s = Yield '\x104ee' (CC s '\x0000' '\x0000')

806+-- OSAGE CAPITAL LETTER SHA

807+foldMapping '\x104c7' s = Yield '\x104ef' (CC s '\x0000' '\x0000')

808+-- OSAGE CAPITAL LETTER TA

809+foldMapping '\x104c8' s = Yield '\x104f0' (CC s '\x0000' '\x0000')

810+-- OSAGE CAPITAL LETTER EHTA

811+foldMapping '\x104c9' s = Yield '\x104f1' (CC s '\x0000' '\x0000')

812+-- OSAGE CAPITAL LETTER TSA

813+foldMapping '\x104ca' s = Yield '\x104f2' (CC s '\x0000' '\x0000')

814+-- OSAGE CAPITAL LETTER EHTSA

815+foldMapping '\x104cb' s = Yield '\x104f3' (CC s '\x0000' '\x0000')

816+-- OSAGE CAPITAL LETTER TSHA

817+foldMapping '\x104cc' s = Yield '\x104f4' (CC s '\x0000' '\x0000')

818+-- OSAGE CAPITAL LETTER DHA

819+foldMapping '\x104cd' s = Yield '\x104f5' (CC s '\x0000' '\x0000')

820+-- OSAGE CAPITAL LETTER U

821+foldMapping '\x104ce' s = Yield '\x104f6' (CC s '\x0000' '\x0000')

822+-- OSAGE CAPITAL LETTER WA

823+foldMapping '\x104cf' s = Yield '\x104f7' (CC s '\x0000' '\x0000')

824+-- OSAGE CAPITAL LETTER KHA

825+foldMapping '\x104d0' s = Yield '\x104f8' (CC s '\x0000' '\x0000')

826+-- OSAGE CAPITAL LETTER GHA

827+foldMapping '\x104d1' s = Yield '\x104f9' (CC s '\x0000' '\x0000')

828+-- OSAGE CAPITAL LETTER ZA

829+foldMapping '\x104d2' s = Yield '\x104fa' (CC s '\x0000' '\x0000')

830+-- OSAGE CAPITAL LETTER ZHA

831+foldMapping '\x104d3' s = Yield '\x104fb' (CC s '\x0000' '\x0000')

740-- OLD HUNGARIAN CAPITAL LETTER A

832-- OLD HUNGARIAN CAPITAL LETTER A

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

833foldMapping '\x10c80' s = Yield '\x10cc0' (CC s '\x0000' '\x0000')

742-- OLD HUNGARIAN CAPITAL LETTER AA

834-- OLD HUNGARIAN CAPITAL LETTER AA

@@ -839,4 +931,72 @@ foldMapping '\x10cb0' s = Yield '\x10cf0' (CC s '\x0000' '\x0000')

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

931foldMapping '\x10cb1' s = Yield '\x10cf1' (CC s '\x0000' '\x0000')

840-- OLD HUNGARIAN CAPITAL LETTER US

932-- OLD HUNGARIAN CAPITAL LETTER US

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

933foldMapping '\x10cb2' s = Yield '\x10cf2' (CC s '\x0000' '\x0000')

934+-- ADLAM CAPITAL LETTER ALIF

935+foldMapping '\x1e900' s = Yield '\x1e922' (CC s '\x0000' '\x0000')

936+-- ADLAM CAPITAL LETTER DAALI

937+foldMapping '\x1e901' s = Yield '\x1e923' (CC s '\x0000' '\x0000')

938+-- ADLAM CAPITAL LETTER LAAM

939+foldMapping '\x1e902' s = Yield '\x1e924' (CC s '\x0000' '\x0000')

940+-- ADLAM CAPITAL LETTER MIIM

941+foldMapping '\x1e903' s = Yield '\x1e925' (CC s '\x0000' '\x0000')

942+-- ADLAM CAPITAL LETTER BA

943+foldMapping '\x1e904' s = Yield '\x1e926' (CC s '\x0000' '\x0000')

944+-- ADLAM CAPITAL LETTER SINNYIIYHE

945+foldMapping '\x1e905' s = Yield '\x1e927' (CC s '\x0000' '\x0000')

946+-- ADLAM CAPITAL LETTER PE

947+foldMapping '\x1e906' s = Yield '\x1e928' (CC s '\x0000' '\x0000')

948+-- ADLAM CAPITAL LETTER BHE

949+foldMapping '\x1e907' s = Yield '\x1e929' (CC s '\x0000' '\x0000')

950+-- ADLAM CAPITAL LETTER RA

951+foldMapping '\x1e908' s = Yield '\x1e92a' (CC s '\x0000' '\x0000')

952+-- ADLAM CAPITAL LETTER E

953+foldMapping '\x1e909' s = Yield '\x1e92b' (CC s '\x0000' '\x0000')

954+-- ADLAM CAPITAL LETTER FA

955+foldMapping '\x1e90a' s = Yield '\x1e92c' (CC s '\x0000' '\x0000')

956+-- ADLAM CAPITAL LETTER I

957+foldMapping '\x1e90b' s = Yield '\x1e92d' (CC s '\x0000' '\x0000')

958+-- ADLAM CAPITAL LETTER O

959+foldMapping '\x1e90c' s = Yield '\x1e92e' (CC s '\x0000' '\x0000')

960+-- ADLAM CAPITAL LETTER DHA

961+foldMapping '\x1e90d' s = Yield '\x1e92f' (CC s '\x0000' '\x0000')

962+-- ADLAM CAPITAL LETTER YHE

963+foldMapping '\x1e90e' s = Yield '\x1e930' (CC s '\x0000' '\x0000')

964+-- ADLAM CAPITAL LETTER WAW

965+foldMapping '\x1e90f' s = Yield '\x1e931' (CC s '\x0000' '\x0000')

966+-- ADLAM CAPITAL LETTER NUN

967+foldMapping '\x1e910' s = Yield '\x1e932' (CC s '\x0000' '\x0000')

968+-- ADLAM CAPITAL LETTER KAF

969+foldMapping '\x1e911' s = Yield '\x1e933' (CC s '\x0000' '\x0000')

970+-- ADLAM CAPITAL LETTER YA

971+foldMapping '\x1e912' s = Yield '\x1e934' (CC s '\x0000' '\x0000')

972+-- ADLAM CAPITAL LETTER U

973+foldMapping '\x1e913' s = Yield '\x1e935' (CC s '\x0000' '\x0000')

974+-- ADLAM CAPITAL LETTER JIIM

975+foldMapping '\x1e914' s = Yield '\x1e936' (CC s '\x0000' '\x0000')

976+-- ADLAM CAPITAL LETTER CHI

977+foldMapping '\x1e915' s = Yield '\x1e937' (CC s '\x0000' '\x0000')

978+-- ADLAM CAPITAL LETTER HA

979+foldMapping '\x1e916' s = Yield '\x1e938' (CC s '\x0000' '\x0000')

980+-- ADLAM CAPITAL LETTER QAAF

981+foldMapping '\x1e917' s = Yield '\x1e939' (CC s '\x0000' '\x0000')

982+-- ADLAM CAPITAL LETTER GA

983+foldMapping '\x1e918' s = Yield '\x1e93a' (CC s '\x0000' '\x0000')

984+-- ADLAM CAPITAL LETTER NYA

985+foldMapping '\x1e919' s = Yield '\x1e93b' (CC s '\x0000' '\x0000')

986+-- ADLAM CAPITAL LETTER TU

987+foldMapping '\x1e91a' s = Yield '\x1e93c' (CC s '\x0000' '\x0000')

988+-- ADLAM CAPITAL LETTER NHA

989+foldMapping '\x1e91b' s = Yield '\x1e93d' (CC s '\x0000' '\x0000')

990+-- ADLAM CAPITAL LETTER VA

991+foldMapping '\x1e91c' s = Yield '\x1e93e' (CC s '\x0000' '\x0000')

992+-- ADLAM CAPITAL LETTER KHA

993+foldMapping '\x1e91d' s = Yield '\x1e93f' (CC s '\x0000' '\x0000')

994+-- ADLAM CAPITAL LETTER GBE

995+foldMapping '\x1e91e' s = Yield '\x1e940' (CC s '\x0000' '\x0000')

996+-- ADLAM CAPITAL LETTER ZAL

997+foldMapping '\x1e91f' s = Yield '\x1e941' (CC s '\x0000' '\x0000')

998+-- ADLAM CAPITAL LETTER KPO

999+foldMapping '\x1e920' s = Yield '\x1e942' (CC s '\x0000' '\x0000')

1000+-- ADLAM CAPITAL LETTER SHA

1001+foldMapping '\x1e921' s = Yield '\x1e943' (CC s '\x0000' '\x0000')

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

1002foldMapping c s = Yield (toLower c) (CC s '\0' '\0')

Data/Text/Internal/Fusion/Common.hs+10−9

@@ -107,7 +107,7 @@ import Prelude (Bool(..), Char, Eq(..), Int, Integral, Maybe(..),

107import qualified Data.List as L

108import qualified Prelude as P

109import Data.Bits (shiftL)

110−import Data.Char (isLetter)

110+import Data.Char (isLetter, isSpace)

111import Data.Int (Int64)

112import Data.Text.Internal.Fusion.Types

113import Data.Text.Internal.Fusion.CaseMapping (foldMapping, lowerMapping, titleMapping,

@@ -462,15 +462,16 @@ toTitle (Stream next0 s0 len) = Stream next (CC (False :*: s0) '\0' '\0') len

462 where

463 next (CC (letter :*: s) '\0' _) =

464 case next0 s of

465− Done -> Done

465+ Done -> Done

466− Skip s' -> Skip (CC (letter :*: s') '\0' '\0')

466+ Skip s' -> Skip (CC (letter :*: s') '\0' '\0')

467 Yield c s'

468− | letter' -> if letter

468+ | nonSpace -> if letter

469− then lowerMapping c (letter' :*: s')

469+ then lowerMapping c (nonSpace :*: s')

470− else titleMapping c (letter' :*: s')

470+ else titleMapping c (letter' :*: s')

471− | otherwise -> Yield c (CC (letter' :*: s') '\0' '\0')

471+ | otherwise -> Yield c (CC (letter' :*: s') '\0' '\0')

472+ where nonSpace = P.not (isSpace c)

472− where letter' = isLetter c

473+ letter' = isLetter c

473− next (CC s a b) = Yield a (CC s b '\0')

474+ next (CC s a b) = Yield a (CC s b '\0')

474{-# INLINE [0] toTitle #-}

475{-# INLINE [0] toTitle #-}

475

476

476data Justify i s = Just1 !i !s

477data Justify i s = Just1 !i !s

Data/Text/Lazy.hs+4−3

@@ -1153,9 +1153,10 @@ takeWhile p t0 = takeWhile' t0

1153takeWhileEnd :: (Char -> Bool) -> Text -> Text

1154takeWhileEnd p = takeChunk empty . L.reverse . toChunks

1155 where takeChunk acc [] = acc

1156− takeChunk acc (t:ts) = if T.length t' < T.length t

1156+ takeChunk acc (t:ts)

1157− then (Chunk t' acc)

1157+ | T.lengthWord16 t' < T.lengthWord16 t

1158+ = chunk t' acc

1158− else takeChunk (Chunk t' acc) ts

1159+ | otherwise = takeChunk (Chunk t' acc) ts

1159 where t' = T.takeWhileEnd p t

1160 where t' = T.takeWhileEnd p t

1160{-# INLINE takeWhileEnd #-}

1161{-# INLINE takeWhileEnd #-}

1161

1162

Data/Text/Lazy/Read.hs+3−3

@@ -68,9 +68,9 @@ decimal txt

68 go n d = (n * 10 + fromIntegral (digitToInt d))

70-- | Read a hexadecimal integer, consisting of an optional leading

71−-- @\"0x\"@ followed by at least one decimal digit. Input is consumed

71+-- @\"0x\"@ followed by at least one hexadecimal digit. Input is

72−-- until a non-hex-digit or end of string is reached. This function

72+-- consumed until a non-hex-digit or end of string is reached.

73−-- is case insensitive.

73+-- This function is case insensitive.

74--

75-- This function does not handle leading sign characters. If you need

76-- to handle signed input, use @'signed' 'hexadecimal'@.

Data/Text/Read.hs+3−3

@@ -67,9 +67,9 @@ decimal txt

67 go n d = (n * 10 + fromIntegral (digitToInt d))

69-- | Read a hexadecimal integer, consisting of an optional leading

70−-- @\"0x\"@ followed by at least one decimal digit. Input is consumed

70+-- @\"0x\"@ followed by at least one hexadecimal digit. Input is

71−-- until a non-hex-digit or end of string is reached. This function

71+-- consumed until a non-hex-digit or end of string is reached.

72−-- is case insensitive.

72+-- This function is case insensitive.

73--

74-- This function does not handle leading sign characters. If you need

75-- to handle signed input, use @'signed' 'hexadecimal'@.

changelog.md+27−1

@@ -1,10 +1,36 @@

1+1.2.3.0

3+* Bug fix: the lazy `takeWhileEnd` function violated the

4+ [lazy text invariant](https://github.com/bos/text/blob/1.2.3.0/Data/Text/Internal/Lazy.hs#L51).

6+* Spec compliance: `toCaseFold` now follows the Unicode 9.0 spec

7+ (updated from 8.0)

10+1.2.2.2

11+

12+* The `toTitle` function now correctly handles letters that

13+ immediately follow punctuation. Before, `"there's"` would turn into

14+ `"There'S"`. Now, it becomes `"There's"`.

15+

16+* The implementation of unstreaming is faster, resulting in operations

17+ such as `map` and `intersperse` speeding up by up to 30%, with

18+ smaller code generated.

19+

20+* The optimised length comparison function is now more likely to be

21+ used after some rewrite rule tweaking.

22+

23+* Bug fix: an off-by-one bug in `takeEnd` is fixed.

24+

25+* Bug fix: a logic error in `takeWord16` is fixed.

26+

11.2.2.1

271.2.2.1

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

29* 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

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

5 maintainers apologizes for the churn.

31 maintainers apologizes for the churn.

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

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

8 (updated from 7.0)

34 (updated from 7.0)

10* An STG lint error has been fixed

36* An STG lint error has been fixed

tests/Tests/Properties.hs+48−20

@@ -11,7 +11,7 @@ module Tests.Properties

11import Control.Applicative ((<$>), (<*>))

12import Control.Arrow ((***), second)

13import Data.Bits ((.&.))

14−import Data.Char (chr, isDigit, isHexDigit, isLower, isSpace, isUpper, ord)

14+import Data.Char (chr, isDigit, isHexDigit, isLower, isSpace, isLetter, isUpper, ord)

15import Data.Int (Int8, Int16, Int32, Int64)

16import Data.Monoid (Monoid(..))

17import Data.String (IsString(fromString))

@@ -23,6 +23,7 @@ import Data.Text.Internal.Search (indices)

23import Data.Text.Lazy.Read as TL

24import Data.Text.Read as T

25import Data.Word (Word, Word8, Word16, Word32, Word64)

26+import Data.Maybe (mapMaybe)

26import Numeric (showEFloat, showFFloat, showGFloat, showHex)

27import Numeric (showEFloat, showFFloat, showGFloat, showHex)

27import Prelude hiding (replicate)

28import Prelude hiding (replicate)

28import Test.Framework (Test, testGroup)

29import Test.Framework (Test, testGroup)

@@ -30,6 +31,7 @@ import Test.Framework.Providers.QuickCheck2 (testProperty)

30import Test.QuickCheck hiding ((.&.))

31import Test.QuickCheck hiding ((.&.))

31import Test.QuickCheck.Monadic

32import Test.QuickCheck.Monadic

32import Test.QuickCheck.Property (Property(..))

33import Test.QuickCheck.Property (Property(..))

34+import Test.QuickCheck.Unicode (char)

33import Tests.QuickCheckUtils

35import Tests.QuickCheckUtils

34import Tests.Utils

36import Tests.Utils

35import Text.Show.Functions ()

37import Text.Show.Functions ()

@@ -37,6 +39,7 @@ import qualified Control.Exception as Exception

37import qualified Data.Bits as Bits (shiftL, shiftR)

39import qualified Data.Bits as Bits (shiftL, shiftR)

38import qualified Data.ByteString as B

40import qualified Data.ByteString as B

39import qualified Data.ByteString.Lazy as BL

41import qualified Data.ByteString.Lazy as BL

42+import qualified Data.Char as C

40import qualified Data.List as L

43import qualified Data.List as L

41import qualified Data.Text as T

44import qualified Data.Text as T

42import qualified Data.Text.Encoding as E

45import qualified Data.Text.Encoding as E

@@ -60,10 +63,10 @@ t_pack_unpack = (T.unpack . T.pack) `eq` id

60tl_pack_unpack = (TL.unpack . TL.pack) `eq` id

63tl_pack_unpack = (TL.unpack . TL.pack) `eq` id

61t_stream_unstream = (S.unstream . S.stream) `eq` id

64t_stream_unstream = (S.unstream . S.stream) `eq` id

62tl_stream_unstream = (SL.unstream . SL.stream) `eq` id

65tl_stream_unstream = (SL.unstream . SL.stream) `eq` id

63−t_reverse_stream t = (S.reverse . S.reverseStream) t == t

66+t_reverse_stream t = (S.reverse . S.reverseStream) t === t

64−t_singleton c = [c] == (T.unpack . T.singleton) c

67+t_singleton c = [c] === (T.unpack . T.singleton) c

65−tl_singleton c = [c] == (TL.unpack . TL.singleton) c

68+tl_singleton c = [c] === (TL.unpack . TL.singleton) c

66−tl_unstreamChunks x = f 11 x == f 1000 x

69+tl_unstreamChunks x = f 11 x === f 1000 x

67 where f n = SL.unstreamChunks n . S.streamList

70 where f n = SL.unstreamChunks n . S.streamList

68tl_chunk_unchunk = (TL.fromChunks . TL.toChunks) `eq` id

71tl_chunk_unchunk = (TL.fromChunks . TL.toChunks) `eq` id

69tl_from_to_strict = (TL.fromStrict . TL.toStrict) `eq` id

72tl_from_to_strict = (TL.fromStrict . TL.toStrict) `eq` id

@@ -74,13 +77,13 @@ encodeL1 = B.pack . map (fromIntegral . fromEnum) . T.unpack

74encodeLazyL1 :: TL.Text -> BL.ByteString

77encodeLazyL1 :: TL.Text -> BL.ByteString

75encodeLazyL1 = BL.fromChunks . map encodeL1 . TL.toChunks

78encodeLazyL1 = BL.fromChunks . map encodeL1 . TL.toChunks

77−t_ascii t = E.decodeASCII (E.encodeUtf8 a) == a

80+t_ascii t = E.decodeASCII (E.encodeUtf8 a) === a

78 where a = T.map (\c -> chr (ord c `mod` 128)) t

81 where a = T.map (\c -> chr (ord c `mod` 128)) t

79−tl_ascii t = EL.decodeASCII (EL.encodeUtf8 a) == a

82+tl_ascii t = EL.decodeASCII (EL.encodeUtf8 a) === a

80 where a = TL.map (\c -> chr (ord c `mod` 128)) t

83 where a = TL.map (\c -> chr (ord c `mod` 128)) t

81−t_latin1 t = E.decodeLatin1 (encodeL1 a) == a

84+t_latin1 t = E.decodeLatin1 (encodeL1 a) === a

82 where a = T.map (\c -> chr (ord c `mod` 256)) t

85 where a = T.map (\c -> chr (ord c `mod` 256)) t

83−tl_latin1 t = EL.decodeLatin1 (encodeLazyL1 a) == a

86+tl_latin1 t = EL.decodeLatin1 (encodeLazyL1 a) === a

84 where a = TL.map (\c -> chr (ord c `mod` 256)) t

87 where a = TL.map (\c -> chr (ord c `mod` 256)) t

85t_utf8 = forAll genUnicode $ (E.decodeUtf8 . E.encodeUtf8) `eq` id

88t_utf8 = forAll genUnicode $ (E.decodeUtf8 . E.encodeUtf8) `eq` id

86t_utf8' = forAll genUnicode $ (E.decodeUtf8' . E.encodeUtf8) `eq` (id . Right)

89t_utf8' = forAll genUnicode $ (E.decodeUtf8' . E.encodeUtf8) `eq` (id . Right)

@@ -111,7 +114,7 @@ t_utf8_undecoded = forAll genUnicode $ \t ->

111 let b = E.encodeUtf8 t

114 let b = E.encodeUtf8 t

112 ls = concatMap (leftover . E.encodeUtf8 . T.singleton) . T.unpack $ t

115 ls = concatMap (leftover . E.encodeUtf8 . T.singleton) . T.unpack $ t

113 leftover = (++ [B.empty]) . init . tail . B.inits

116 leftover = (++ [B.empty]) . init . tail . B.inits

114− in (map snd . feedChunksOf 1 E.streamDecodeUtf8) b == ls

117+ in (map snd . feedChunksOf 1 E.streamDecodeUtf8) b === ls

115

118

116data Badness = Solo | Leading | Trailing

119data Badness = Solo | Leading | Trailing

117 deriving (Eq, Show)

120 deriving (Eq, Show)

@@ -201,8 +204,8 @@ t_mconcat = unsquare $

201 mconcat `eq` (unpackS . mconcat . L.map T.pack)

204 mconcat `eq` (unpackS . mconcat . L.map T.pack)

202tl_mconcat = unsquare $

205tl_mconcat = unsquare $

203 mconcat `eq` (unpackS . mconcat . L.map TL.pack)

206 mconcat `eq` (unpackS . mconcat . L.map TL.pack)

204−t_mempty = mempty == (unpackS (mempty :: T.Text))

207+t_mempty = mempty === (unpackS (mempty :: T.Text))

205−tl_mempty = mempty == (unpackS (mempty :: TL.Text))

208+tl_mempty = mempty === (unpackS (mempty :: TL.Text))

206t_IsString = fromString `eqP` (T.unpack . fromString)

209t_IsString = fromString `eqP` (T.unpack . fromString)

207tl_IsString = fromString `eqP` (TL.unpack . fromString)

210tl_IsString = fromString `eqP` (TL.unpack . fromString)

208

211

@@ -326,6 +329,19 @@ t_toUpper_upper t = p (T.toUpper t) >= p t

326 where p = T.length . T.filter isUpper

329 where p = T.length . T.filter isUpper

327tl_toUpper_upper t = p (TL.toUpper t) >= p t

330tl_toUpper_upper t = p (TL.toUpper t) >= p t

328 where p = TL.length . TL.filter isUpper

331 where p = TL.length . TL.filter isUpper

332+t_toTitle_title t = all (<= 1) (caps w)

333+ where caps = fmap (T.length . T.filter isUpper) . T.words . T.toTitle

334+ -- TIL: there exist uppercase-only letters

335+ w = T.filter (\c -> if C.isUpper c then C.toLower c /= c else True) t

336+t_toTitle_1stNotLower = and . notLow . T.toTitle . T.filter stable

337+ where notLow = mapMaybe (fmap (not . isLower) . (T.find isLetter)) . T.words

338+ -- Surprise! The Spanish/Portuguese ordinal indicators changed

339+ -- from category Ll (letter, lowercase) to Lo (letter, other)

340+ -- in Unicode 7.0

341+ -- Oh, and there exist lowercase-only letters (see previous test)

342+ stable c = if isLower c

343+ then C.toUpper c /= c

344+ else c /= '\170' && c /= '\186'

329

345

330justifyLeft k c xs = xs ++ L.replicate (k - length xs) c

346justifyLeft k c xs = xs ++ L.replicate (k - length xs) c

331justifyRight m n xs = L.replicate (m - length xs) n ++ xs

347justifyRight m n xs = L.replicate (m - length xs) n ++ xs

@@ -514,12 +530,20 @@ s_takeWhile p = L.takeWhile p `eqP` (unpackS . S.takeWhile p)

514s_takeWhile_s p = L.takeWhile p `eqP` (unpackS . S.unstream . S.takeWhile p)

530s_takeWhile_s p = L.takeWhile p `eqP` (unpackS . S.unstream . S.takeWhile p)

515sf_takeWhile q p = (L.takeWhile p . L.filter q) `eqP`

531sf_takeWhile q p = (L.takeWhile p . L.filter q) `eqP`

516 (unpackS . S.takeWhile p . S.filter q)

532 (unpackS . S.takeWhile p . S.filter q)

533+noMatch = do

534+ c <- char

535+ d <- suchThat char (/= c)

536+ return (c,d)

517t_takeWhile p = L.takeWhile p `eqP` (unpackS . T.takeWhile p)

537t_takeWhile p = L.takeWhile p `eqP` (unpackS . T.takeWhile p)

518tl_takeWhile p = L.takeWhile p `eqP` (unpackS . TL.takeWhile p)

538tl_takeWhile p = L.takeWhile p `eqP` (unpackS . TL.takeWhile p)

519t_takeWhileEnd p = (L.reverse . L.takeWhile p . L.reverse) `eqP`

539t_takeWhileEnd p = (L.reverse . L.takeWhile p . L.reverse) `eqP`

520 (unpackS . T.takeWhileEnd p)

540 (unpackS . T.takeWhileEnd p)

541+t_takeWhileEnd_null t = forAll noMatch $ \(c,d) -> T.null $

542+ T.takeWhileEnd (==d) (T.snoc t c)

521tl_takeWhileEnd p = (L.reverse . L.takeWhile p . L.reverse) `eqP`

543tl_takeWhileEnd p = (L.reverse . L.takeWhile p . L.reverse) `eqP`

522 (unpackS . TL.takeWhileEnd p)

544 (unpackS . TL.takeWhileEnd p)

545+tl_takeWhileEnd_null t = forAll noMatch $ \(c,d) -> TL.null $

546+ TL.takeWhileEnd (==d) (TL.snoc t c)

523s_dropWhile p = L.dropWhile p `eqP` (unpackS . S.dropWhile p)

547s_dropWhile p = L.dropWhile p `eqP` (unpackS . S.dropWhile p)

524s_dropWhile_s p = L.dropWhile p `eqP` (unpackS . S.unstream . S.dropWhile p)

548s_dropWhile_s p = L.dropWhile p `eqP` (unpackS . S.unstream . S.dropWhile p)

525sf_dropWhile q p = (L.dropWhile p . L.filter q) `eqP`

549sf_dropWhile q p = (L.dropWhile p . L.filter q) `eqP`

@@ -720,7 +744,7 @@ tl_indices (NotEmpty s) = lazyIndices s `eq` S.indices s

720 conc = T.concat . TL.toChunks

744 conc = T.concat . TL.toChunks

721t_indices_occurs = unsquare $ \(NotEmpty t) ts ->

745t_indices_occurs = unsquare $ \(NotEmpty t) ts ->

722 let s = T.intercalate t ts

746 let s = T.intercalate t ts

723− in Slow.indices t s == indices t s

747+ in Slow.indices t s === indices t s

724

748

725-- Bit shifts.

749-- Bit shifts.

726shiftL w = forAll (choose (0,width-1)) $ \k -> Bits.shiftL w k == U.shiftL w k

750shiftL w = forAll (choose (0,width-1)) $ \k -> Bits.shiftL w k == U.shiftL w k

@@ -812,18 +836,18 @@ tb_formatRealFloat_double (a::Double) = tb_formatRealFloat a

812-- Reading.

836-- Reading.

813

837

814t_decimal (n::Int) s =

838t_decimal (n::Int) s =

815− T.signed T.decimal (T.pack (show n) `T.append` t) == Right (n,t)

839+ T.signed T.decimal (T.pack (show n) `T.append` t) === Right (n,t)

816 where t = T.dropWhile isDigit s

840 where t = T.dropWhile isDigit s

817tl_decimal (n::Int) s =

841tl_decimal (n::Int) s =

818− TL.signed TL.decimal (TL.pack (show n) `TL.append` t) == Right (n,t)

842+ TL.signed TL.decimal (TL.pack (show n) `TL.append` t) === Right (n,t)

819 where t = TL.dropWhile isDigit s

843 where t = TL.dropWhile isDigit s

820t_hexadecimal m s ox =

844t_hexadecimal m s ox =

821− T.hexadecimal (T.concat [p, T.pack (showHex n ""), t]) == Right (n,t)

845+ T.hexadecimal (T.concat [p, T.pack (showHex n ""), t]) === Right (n,t)

822 where t = T.dropWhile isHexDigit s

846 where t = T.dropWhile isHexDigit s

823 p = if ox then "0x" else ""

847 p = if ox then "0x" else ""

824 n = getPositive m :: Int

848 n = getPositive m :: Int

825tl_hexadecimal m s ox =

849tl_hexadecimal m s ox =

826− TL.hexadecimal (TL.concat [p, TL.pack (showHex n ""), t]) == Right (n,t)

850+ TL.hexadecimal (TL.concat [p, TL.pack (showHex n ""), t]) === Right (n,t)

827 where t = TL.dropWhile isHexDigit s

851 where t = TL.dropWhile isHexDigit s

828 p = if ox then "0x" else ""

852 p = if ox then "0x" else ""

829 n = getPositive m :: Int

853 n = getPositive m :: Int

@@ -867,11 +891,11 @@ tl_write_read_line e m b t = write_read head TL.filter TL.hPutStrLn

867

891

868t_dropWord16 m t = dropWord16 m t `T.isSuffixOf` t

892t_dropWord16 m t = dropWord16 m t `T.isSuffixOf` t

869t_takeWord16 m t = takeWord16 m t `T.isPrefixOf` t

893t_takeWord16 m t = takeWord16 m t `T.isPrefixOf` t

870−t_take_drop_16 m t = T.append (takeWord16 n t) (dropWord16 n t) == t

894+t_take_drop_16 m t = T.append (takeWord16 n t) (dropWord16 n t) === t

871 where n = small m

895 where n = small m

872t_use_from t = monadicIO $ assert . (==t) =<< run (useAsPtr t fromPtr)

896t_use_from t = monadicIO $ assert . (==t) =<< run (useAsPtr t fromPtr)

873

897

874−t_copy t = T.copy t == t

898+t_copy t = T.copy t === t

875

899

876-- Regression tests.

900-- Regression tests.

877s_filter_eq s = S.filter p t == S.streamList (filter p s)

901s_filter_eq s = S.filter p t == S.streamList (filter p s)

@@ -1030,7 +1054,9 @@ tests =

1030 testProperty "tl_toLower_lower" tl_toLower_lower,

1054 testProperty "tl_toLower_lower" tl_toLower_lower,

1031 testProperty "t_toUpper_length" t_toUpper_length,

1055 testProperty "t_toUpper_length" t_toUpper_length,

1032 testProperty "t_toUpper_upper" t_toUpper_upper,

1056 testProperty "t_toUpper_upper" t_toUpper_upper,

1033− testProperty "tl_toUpper_upper" tl_toUpper_upper

1057+ testProperty "tl_toUpper_upper" tl_toUpper_upper,

1058+ testProperty "t_toTitle_title" t_toTitle_title,

1059+ testProperty "t_toTitle_1stNotLower" t_toTitle_1stNotLower

1034 ],

1060 ],

1035

1061

1036 testGroup "justification" [

1062 testGroup "justification" [

@@ -1147,7 +1173,9 @@ tests =

1147 testProperty "t_takeWhile" t_takeWhile,

1173 testProperty "t_takeWhile" t_takeWhile,

1148 testProperty "tl_takeWhile" tl_takeWhile,

1174 testProperty "tl_takeWhile" tl_takeWhile,

1149 testProperty "t_takeWhileEnd" t_takeWhileEnd,

1175 testProperty "t_takeWhileEnd" t_takeWhileEnd,

1176+ testProperty "t_takeWhileEnd_null" t_takeWhileEnd_null,

1150 testProperty "tl_takeWhileEnd" tl_takeWhileEnd,

1177 testProperty "tl_takeWhileEnd" tl_takeWhileEnd,

1178+ testProperty "tl_takeWhileEnd_null" tl_takeWhileEnd_null,

1151 testProperty "sf_dropWhile" sf_dropWhile,

1179 testProperty "sf_dropWhile" sf_dropWhile,

1152 testProperty "s_dropWhile" s_dropWhile,

1180 testProperty "s_dropWhile" s_dropWhile,

1153 testProperty "s_dropWhile_s" s_dropWhile_s,

1181 testProperty "s_dropWhile_s" s_dropWhile_s,

tests/Tests/QuickCheckUtils.hs+1−1

@@ -106,7 +106,7 @@ smallArbitrary = sized $ \n -> resize (smallish n) arbitrary

106 where smallish = round . (sqrt :: Double -> Double) . fromIntegral . abs

107

108instance Arbitrary T.Text where

109− arbitrary = T.pack `fmap` arbitrary

109+ arbitrary = T.pack `fmap` string

110 shrink = map T.pack . shrink . T.unpack

111

112instance Arbitrary TL.Text where

tests/text-tests.cabal+18−3

@@ -20,6 +20,11 @@ flag hpc

20 default: False

21 manual: True

23+flag bytestring-builder

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

25+ default: False

26+ manual: False

27+

23executable text-tests

28executable text-tests

24 main-is: Tests.hs

29 main-is: Tests.hs

@@ -48,16 +53,21 @@ executable text-tests

48 HUnit >= 1.2,

53 HUnit >= 1.2,

49 QuickCheck >= 2.7,

54 QuickCheck >= 2.7,

50 base == 4.*,

55 base == 4.*,

51− bytestring,

52 deepseq,

56 deepseq,

53 directory,

57 directory,

54− quickcheck-unicode,

58+ quickcheck-unicode >= 1.0.1.0,

55 random,

59 random,

56 test-framework >= 0.4,

60 test-framework >= 0.4,

57 test-framework-hunit >= 0.2,

61 test-framework-hunit >= 0.2,

58 test-framework-quickcheck2 >= 0.2,

62 test-framework-quickcheck2 >= 0.2,

59 text-tests

63 text-tests

65+ if flag(bytestring-builder)

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

67+ bytestring-builder >= 0.10.4

68+ else

69+ build-depends: bytestring >= 0.10.4

70+

61executable text-tests-stdio

71executable text-tests-stdio

62 main-is: Tests/IO.hs

72 main-is: Tests/IO.hs

@@ -137,7 +147,12 @@ library

137 array,

147 array,

138 base == 4.*,

148 base == 4.*,

139 binary,

149 binary,

140− bytestring,

141 deepseq,

150 deepseq,

142 ghc-prim,

151 ghc-prim,

143 integer-gmp

152 integer-gmp

153+

154+ if flag(bytestring-builder)

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

156+ bytestring-builder >= 0.10.4

157+ else

158+ build-depends: bytestring >= 0.10.4

text.cabal+2−2

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

1name: text

2−version: 1.2.2.1

2+version: 1.2.3.0

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

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

5synopsis: An efficient packed Unicode text type.

@@ -180,7 +180,7 @@ test-suite tests

180 deepseq,

181 directory,

182 ghc-prim,

183− quickcheck-unicode,

183+ quickcheck-unicode >= 1.0.1.0,

184 random,

185 test-framework >= 0.4,

186 test-framework-hunit >= 0.2,