From a0973d09a5b4f6a08b35c0b3de371c895d7d847a Mon Sep 17 00:00:00 2001 From: Alec Theriault Date: Thu, 31 Jan 2019 15:37:58 -0800 Subject: Remove `Documentation.Haddock.Utf8` The circumstances under which this module appeared are completely gone. The Hyperlinker backend no longer needs this module (it uses the more efficient `Encoding` module from `ghc`). Why no deprecation? Because this module really shouldn't exist! - It isn't used in `haddock-library`/`haddock-api` anymore - It was copy pasted directly from `utf8-string` - Folks seeking a boot-lib only solution can use `ghc`'s `Encoding` --- haddock-library/CHANGES.md | 5 +- haddock-library/haddock-library.cabal | 5 +- haddock-library/src/Documentation/Haddock/Utf8.hs | 74 ---------------------- .../test/Documentation/Haddock/Utf8Spec.hs | 14 ---- 4 files changed, 5 insertions(+), 93 deletions(-) delete mode 100644 haddock-library/src/Documentation/Haddock/Utf8.hs delete mode 100644 haddock-library/test/Documentation/Haddock/Utf8Spec.hs (limited to 'haddock-library') diff --git a/haddock-library/CHANGES.md b/haddock-library/CHANGES.md index 971d8dc7..265579ca 100644 --- a/haddock-library/CHANGES.md +++ b/haddock-library/CHANGES.md @@ -1,7 +1,10 @@ -## TBA +## Changes in version 1.8.0 * Support inline markup in markdown-style links (#875) + * Remove now unused `Documentation.Haddock.Utf8` module. + This module was anyways copied from the `utf8-string` package. + ## Changes in version 1.7.0 * Make `Documentation.Haddock.Parser.Monad` an internal module diff --git a/haddock-library/haddock-library.cabal b/haddock-library/haddock-library.cabal index b19642ab..b24db5d4 100644 --- a/haddock-library/haddock-library.cabal +++ b/haddock-library/haddock-library.cabal @@ -1,6 +1,6 @@ cabal-version: 2.2 name: haddock-library -version: 1.7.0 +version: 1.8.0 synopsis: Library exposing some functionality of Haddock. description: Haddock is a documentation-generation tool for Haskell @@ -45,7 +45,6 @@ library Documentation.Haddock.Markup Documentation.Haddock.Parser Documentation.Haddock.Types - Documentation.Haddock.Utf8 other-modules: Documentation.Haddock.Parser.Util @@ -71,8 +70,6 @@ test-suite spec Documentation.Haddock.Parser.UtilSpec Documentation.Haddock.ParserSpec Documentation.Haddock.Types - Documentation.Haddock.Utf8 - Documentation.Haddock.Utf8Spec build-depends: , base-compat ^>= 0.9.3 || ^>= 0.10.0 diff --git a/haddock-library/src/Documentation/Haddock/Utf8.hs b/haddock-library/src/Documentation/Haddock/Utf8.hs deleted file mode 100644 index 3f75e53b..00000000 --- a/haddock-library/src/Documentation/Haddock/Utf8.hs +++ /dev/null @@ -1,74 +0,0 @@ -module Documentation.Haddock.Utf8 (encodeUtf8, decodeUtf8) where -import Data.Bits ((.|.), (.&.), shiftL, shiftR) -import qualified Data.ByteString as BS -import Data.Char (chr, ord) -import Data.Word (Word8) - --- | Helper that encodes and packs a 'String' into a 'BS.ByteString' -encodeUtf8 :: String -> BS.ByteString -encodeUtf8 = BS.pack . encode - --- | Helper that unpacks and decodes a 'BS.ByteString' into a 'String' -decodeUtf8 :: BS.ByteString -> String -decodeUtf8 = decode . BS.unpack - --- Copy/pasted functions from Codec.Binary.UTF8.String for encoding/decoding --- | Character to use when 'encode' or 'decode' fail for a byte. -replacementCharacter :: Char -replacementCharacter = '\xfffd' - --- | Encode a Haskell String to a list of Word8 values, in UTF8 format. -encode :: String -> [Word8] -encode = concatMap (map fromIntegral . go . ord) - where - go oc - | oc <= 0x7f = [oc] - - | oc <= 0x7ff = [ 0xc0 + (oc `shiftR` 6) - , 0x80 + oc .&. 0x3f - ] - - | oc <= 0xffff = [ 0xe0 + (oc `shiftR` 12) - , 0x80 + ((oc `shiftR` 6) .&. 0x3f) - , 0x80 + oc .&. 0x3f - ] - | otherwise = [ 0xf0 + (oc `shiftR` 18) - , 0x80 + ((oc `shiftR` 12) .&. 0x3f) - , 0x80 + ((oc `shiftR` 6) .&. 0x3f) - , 0x80 + oc .&. 0x3f - ] - --- | Decode a UTF8 string packed into a list of Word8 values, directly to String -decode :: [Word8] -> String -decode [ ] = "" -decode (c:cs) - | c < 0x80 = chr (fromEnum c) : decode cs - | c < 0xc0 = replacementCharacter : decode cs - | c < 0xe0 = multi1 - | c < 0xf0 = multi_byte 2 0xf 0x800 - | c < 0xf8 = multi_byte 3 0x7 0x10000 - | c < 0xfc = multi_byte 4 0x3 0x200000 - | c < 0xfe = multi_byte 5 0x1 0x4000000 - | otherwise = replacementCharacter : decode cs - where - multi1 = case cs of - c1 : ds | c1 .&. 0xc0 == 0x80 -> - let d = ((fromEnum c .&. 0x1f) `shiftL` 6) .|. fromEnum (c1 .&. 0x3f) - in if d >= 0x000080 then toEnum d : decode ds - else replacementCharacter : decode ds - _ -> replacementCharacter : decode cs - - multi_byte :: Int -> Word8 -> Int -> String - multi_byte i mask overlong = aux i cs (fromEnum (c .&. mask)) - where - aux 0 rs acc - | overlong <= acc && acc <= 0x10ffff && - (acc < 0xd800 || 0xdfff < acc) && - (acc < 0xfffe || 0xffff < acc) = chr acc : decode rs - | otherwise = replacementCharacter : decode rs - - aux n (r:rs) acc - | r .&. 0xc0 == 0x80 = aux (n-1) rs - $ shiftL acc 6 .|. fromEnum (r .&. 0x3f) - - aux _ rs _ = replacementCharacter : decode rs diff --git a/haddock-library/test/Documentation/Haddock/Utf8Spec.hs b/haddock-library/test/Documentation/Haddock/Utf8Spec.hs deleted file mode 100644 index 47e12704..00000000 --- a/haddock-library/test/Documentation/Haddock/Utf8Spec.hs +++ /dev/null @@ -1,14 +0,0 @@ -module Documentation.Haddock.Utf8Spec (main, spec) where - -import Test.Hspec -import Test.QuickCheck -import Documentation.Haddock.Utf8 - -main :: IO () -main = hspec spec - -spec :: Spec -spec = do - describe "decodeUtf8" $ do - it "is inverse to encodeUtf8" $ do - property $ \xs -> (decodeUtf8 . encodeUtf8) xs `shouldBe` xs -- cgit v1.2.3