Safe Haskell	Safe-Inferred
Language	Haskell2010

Data.Monoid.Instances.ByteString.UTF8

Description

This module defines the ByteStringUTF8 newtype wrapper around ByteString, together with its TextualMonoid instance. The FactorialMonoid instance of a wrapped ByteStringUTF8 value differs from the original ByteString: the prime factors of the original value are its bytes, and for the wrapped value the prime factors are its valid UTF8 byte sequences. The following example session demonstrates the relationship:

> let utf8@(ByteStringUTF8 bs) = fromString "E=mc\xb2"
> bs
"E=mc\194\178"
> factors bs
["E","=","m","c","\194","\178"]
> utf8
"E=mc²"
> factors utf8
["E","=","m","c","²"]

The TextualMonoid instance follows the same logic, but it also decodes all valid UTF8 sequences into characters. Any invalid UTF8 byte sequence from the original ByteString is preserved as a single prime factor:

> let utf8'@(ByteStringUTF8 bs') = ByteStringUTF8 (Data.ByteString.map pred bs)
> bs'
"D<lb\193\177"
> factors bs'
["D","<","l","b","\193","\177"]
> utf8'
"D<lb\[193,177]"
> factors utf8'
["D","<","l","b","\[193,177]"]

Synopsis

newtype ByteStringUTF8 = ByteStringUTF8 ByteString
decode :: ByteString -> (ByteStringUTF8, ByteString)

Documentation

newtype ByteStringUTF8 Source #

Constructors

ByteStringUTF8 ByteString

Instances

Instances details

Data ByteStringUTF8 Source #
Instance details Defined in Data.Monoid.Instances.ByteString.UTF8 Methods gfoldl :: (forall d b. Data d => c (d -> b) -> d -> c b) -> (forall g. g -> c g) -> ByteStringUTF8 -> c ByteStringUTF8 # gunfold :: (forall b r. Data b => c (b -> r) -> c r) -> (forall r. r -> c r) -> Constr -> c ByteStringUTF8 # toConstr :: ByteStringUTF8 -> Constr # dataTypeOf :: ByteStringUTF8 -> DataType # dataCast1 :: Typeable t => (forall d. Data d => c (t d)) -> Maybe (c ByteStringUTF8) # dataCast2 :: Typeable t => (forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c ByteStringUTF8) # gmapT :: (forall b. Data b => b -> b) -> ByteStringUTF8 -> ByteStringUTF8 # gmapQl :: (r -> r' -> r) -> r -> (forall d. Data d => d -> r') -> ByteStringUTF8 -> r # gmapQr :: forall r r'. (r' -> r -> r) -> r -> (forall d. Data d => d -> r') -> ByteStringUTF8 -> r # gmapQ :: (forall d. Data d => d -> u) -> ByteStringUTF8 -> [u] # gmapQi :: Int -> (forall d. Data d => d -> u) -> ByteStringUTF8 -> u # gmapM :: Monad m => (forall d. Data d => d -> m d) -> ByteStringUTF8 -> m ByteStringUTF8 # gmapMp :: MonadPlus m => (forall d. Data d => d -> m d) -> ByteStringUTF8 -> m ByteStringUTF8 # gmapMo :: MonadPlus m => (forall d. Data d => d -> m d) -> ByteStringUTF8 -> m ByteStringUTF8 #
IsString ByteStringUTF8 Source #
Instance details Defined in Data.Monoid.Instances.ByteString.UTF8 Methods fromString :: String -> ByteStringUTF8 #
Monoid ByteStringUTF8 Source #	O(n)
Instance details Defined in Data.Monoid.Instances.ByteString.UTF8 Methods mempty :: ByteStringUTF8 # mappend :: ByteStringUTF8 -> ByteStringUTF8 -> ByteStringUTF8 # mconcat :: [ByteStringUTF8] -> ByteStringUTF8 #
Semigroup ByteStringUTF8 Source #	O(n)
Instance details Defined in Data.Monoid.Instances.ByteString.UTF8 Methods (<>) :: ByteStringUTF8 -> ByteStringUTF8 -> ByteStringUTF8 # sconcat :: NonEmpty ByteStringUTF8 -> ByteStringUTF8 # stimes :: Integral b => b -> ByteStringUTF8 -> ByteStringUTF8 #
Show ByteStringUTF8 Source #
Instance details Defined in Data.Monoid.Instances.ByteString.UTF8 Methods showsPrec :: Int -> ByteStringUTF8 -> ShowS # show :: ByteStringUTF8 -> String # showList :: [ByteStringUTF8] -> ShowS #
Eq ByteStringUTF8 Source #
Instance details Defined in Data.Monoid.Instances.ByteString.UTF8 Methods (==) :: ByteStringUTF8 -> ByteStringUTF8 -> Bool # (/=) :: ByteStringUTF8 -> ByteStringUTF8 -> Bool #
Ord ByteStringUTF8 Source #
Instance details Defined in Data.Monoid.Instances.ByteString.UTF8 Methods compare :: ByteStringUTF8 -> ByteStringUTF8 -> Ordering # (<) :: ByteStringUTF8 -> ByteStringUTF8 -> Bool # (<=) :: ByteStringUTF8 -> ByteStringUTF8 -> Bool # (>) :: ByteStringUTF8 -> ByteStringUTF8 -> Bool # (>=) :: ByteStringUTF8 -> ByteStringUTF8 -> Bool # max :: ByteStringUTF8 -> ByteStringUTF8 -> ByteStringUTF8 # min :: ByteStringUTF8 -> ByteStringUTF8 -> ByteStringUTF8 #
FactorialMonoid ByteStringUTF8 Source #
Instance details Defined in Data.Monoid.Instances.ByteString.UTF8 Methods splitPrimePrefix :: ByteStringUTF8 -> Maybe (ByteStringUTF8, ByteStringUTF8) Source # splitPrimeSuffix :: ByteStringUTF8 -> Maybe (ByteStringUTF8, ByteStringUTF8) Source # inits :: ByteStringUTF8 -> [ByteStringUTF8] Source # tails :: ByteStringUTF8 -> [ByteStringUTF8] Source # span :: (ByteStringUTF8 -> Bool) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8) Source # break :: (ByteStringUTF8 -> Bool) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8) Source # split :: (ByteStringUTF8 -> Bool) -> ByteStringUTF8 -> [ByteStringUTF8] Source # takeWhile :: (ByteStringUTF8 -> Bool) -> ByteStringUTF8 -> ByteStringUTF8 Source # dropWhile :: (ByteStringUTF8 -> Bool) -> ByteStringUTF8 -> ByteStringUTF8 Source # spanMaybe :: s -> (s -> ByteStringUTF8 -> Maybe s) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8, s) Source # spanMaybe' :: s -> (s -> ByteStringUTF8 -> Maybe s) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8, s) Source # splitAt :: Int -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8) Source # drop :: Int -> ByteStringUTF8 -> ByteStringUTF8 Source # take :: Int -> ByteStringUTF8 -> ByteStringUTF8 Source #
LeftGCDMonoid ByteStringUTF8 Source #	O(prefixLength)
Instance details Defined in Data.Monoid.Instances.ByteString.UTF8 Methods commonPrefix :: ByteStringUTF8 -> ByteStringUTF8 -> ByteStringUTF8 Source # stripCommonPrefix :: ByteStringUTF8 -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8, ByteStringUTF8) Source #
MonoidNull ByteStringUTF8 Source #	O(1)
Instance details Defined in Data.Monoid.Instances.ByteString.UTF8 Methods null :: ByteStringUTF8 -> Bool Source #
PositiveMonoid ByteStringUTF8 Source #
Instance details Defined in Data.Monoid.Instances.ByteString.UTF8
TextualMonoid ByteStringUTF8 Source #
Instance details Defined in Data.Monoid.Instances.ByteString.UTF8 Methods fromText :: Text -> ByteStringUTF8 Source # singleton :: Char -> ByteStringUTF8 Source # splitCharacterPrefix :: ByteStringUTF8 -> Maybe (Char, ByteStringUTF8) Source # characterPrefix :: ByteStringUTF8 -> Maybe Char Source # map :: (Char -> Char) -> ByteStringUTF8 -> ByteStringUTF8 Source # concatMap :: (Char -> ByteStringUTF8) -> ByteStringUTF8 -> ByteStringUTF8 Source # toString :: (ByteStringUTF8 -> String) -> ByteStringUTF8 -> String Source # toText :: (ByteStringUTF8 -> Text) -> ByteStringUTF8 -> Text Source # any :: (Char -> Bool) -> ByteStringUTF8 -> Bool Source # all :: (Char -> Bool) -> ByteStringUTF8 -> Bool Source # foldl :: (a -> ByteStringUTF8 -> a) -> (a -> Char -> a) -> a -> ByteStringUTF8 -> a Source # foldl' :: (a -> ByteStringUTF8 -> a) -> (a -> Char -> a) -> a -> ByteStringUTF8 -> a Source # foldr :: (ByteStringUTF8 -> a -> a) -> (Char -> a -> a) -> a -> ByteStringUTF8 -> a Source # scanl :: (Char -> Char -> Char) -> Char -> ByteStringUTF8 -> ByteStringUTF8 Source # scanl1 :: (Char -> Char -> Char) -> ByteStringUTF8 -> ByteStringUTF8 Source # scanr :: (Char -> Char -> Char) -> Char -> ByteStringUTF8 -> ByteStringUTF8 Source # scanr1 :: (Char -> Char -> Char) -> ByteStringUTF8 -> ByteStringUTF8 Source # mapAccumL :: (a -> Char -> (a, Char)) -> a -> ByteStringUTF8 -> (a, ByteStringUTF8) Source # mapAccumR :: (a -> Char -> (a, Char)) -> a -> ByteStringUTF8 -> (a, ByteStringUTF8) Source # takeWhile :: (ByteStringUTF8 -> Bool) -> (Char -> Bool) -> ByteStringUTF8 -> ByteStringUTF8 Source # dropWhile :: (ByteStringUTF8 -> Bool) -> (Char -> Bool) -> ByteStringUTF8 -> ByteStringUTF8 Source # break :: (ByteStringUTF8 -> Bool) -> (Char -> Bool) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8) Source # span :: (ByteStringUTF8 -> Bool) -> (Char -> Bool) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8) Source # spanMaybe :: s -> (s -> ByteStringUTF8 -> Maybe s) -> (s -> Char -> Maybe s) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8, s) Source # spanMaybe' :: s -> (s -> ByteStringUTF8 -> Maybe s) -> (s -> Char -> Maybe s) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8, s) Source # split :: (Char -> Bool) -> ByteStringUTF8 -> [ByteStringUTF8] Source # find :: (Char -> Bool) -> ByteStringUTF8 -> Maybe Char Source # elem :: Char -> ByteStringUTF8 -> Bool Source # foldl_ :: (a -> Char -> a) -> a -> ByteStringUTF8 -> a Source # foldl_' :: (a -> Char -> a) -> a -> ByteStringUTF8 -> a Source # foldr_ :: (Char -> a -> a) -> a -> ByteStringUTF8 -> a Source # takeWhile_ :: Bool -> (Char -> Bool) -> ByteStringUTF8 -> ByteStringUTF8 Source # dropWhile_ :: Bool -> (Char -> Bool) -> ByteStringUTF8 -> ByteStringUTF8 Source # break_ :: Bool -> (Char -> Bool) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8) Source # span_ :: Bool -> (Char -> Bool) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8) Source # spanMaybe_ :: s -> (s -> Char -> Maybe s) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8, s) Source # spanMaybe_' :: s -> (s -> Char -> Maybe s) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8, s) Source #
LeftCancellative ByteStringUTF8 Source #
Instance details Defined in Data.Monoid.Instances.ByteString.UTF8
LeftReductive ByteStringUTF8 Source #	O(n)
Instance details Defined in Data.Monoid.Instances.ByteString.UTF8 Methods isPrefixOf :: ByteStringUTF8 -> ByteStringUTF8 -> Bool Source # stripPrefix :: ByteStringUTF8 -> ByteStringUTF8 -> Maybe ByteStringUTF8 Source #
Factorial ByteStringUTF8 Source #
Instance details Defined in Data.Monoid.Instances.ByteString.UTF8 Methods factors :: ByteStringUTF8 -> [ByteStringUTF8] Source # primePrefix :: ByteStringUTF8 -> ByteStringUTF8 Source # primeSuffix :: ByteStringUTF8 -> ByteStringUTF8 Source # foldl :: (a -> ByteStringUTF8 -> a) -> a -> ByteStringUTF8 -> a Source # foldl' :: (a -> ByteStringUTF8 -> a) -> a -> ByteStringUTF8 -> a Source # foldr :: (ByteStringUTF8 -> a -> a) -> a -> ByteStringUTF8 -> a Source # length :: ByteStringUTF8 -> Int Source # foldMap :: Monoid n => (ByteStringUTF8 -> n) -> ByteStringUTF8 -> n Source # reverse :: ByteStringUTF8 -> ByteStringUTF8 Source #

decode :: ByteString -> (ByteStringUTF8, ByteString) Source #

Takes a raw ByteString chunk and returns a pair of ByteStringUTF8 decoding the prefix of the chunk and the remaining suffix that is either null or contains the incomplete last character of the chunk.