Data.Monoid.Instances.ByteString.UTF8

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]"]

Documentation

newtype ByteStringUTF8

Constructors

ByteStringUTF8 ByteString

Instances

Eq ByteStringUTF8

Defined in Data.Monoid.Instances.ByteString.UTF8

Methods

(==) :: ByteStringUTF8 -> ByteStringUTF8 -> Bool

(/=) :: ByteStringUTF8 -> ByteStringUTF8 -> Bool

Ord ByteStringUTF8

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

Show ByteStringUTF8

Defined in Data.Monoid.Instances.ByteString.UTF8

Methods

showsPrec :: Int -> ByteStringUTF8 -> ShowS

show :: ByteStringUTF8 -> String

showList :: [ByteStringUTF8] -> ShowS

IsString ByteStringUTF8

Defined in Data.Monoid.Instances.ByteString.UTF8

Methods

fromString :: String -> ByteStringUTF8

Semigroup ByteStringUTF8

O(n)

Defined in Data.Monoid.Instances.ByteString.UTF8

Methods

(<>) :: ByteStringUTF8 -> ByteStringUTF8 -> ByteStringUTF8

sconcat :: NonEmpty ByteStringUTF8 -> ByteStringUTF8

stimes :: Integral b => b -> ByteStringUTF8 -> ByteStringUTF8

Monoid ByteStringUTF8

O(n)

Defined in Data.Monoid.Instances.ByteString.UTF8

Methods

mempty :: ByteStringUTF8

mappend :: ByteStringUTF8 -> ByteStringUTF8 -> ByteStringUTF8

mconcat :: [ByteStringUTF8] -> ByteStringUTF8

PositiveMonoid ByteStringUTF8

Defined in Data.Monoid.Instances.ByteString.UTF8

MonoidNull ByteStringUTF8

O(1)

Defined in Data.Monoid.Instances.ByteString.UTF8

Methods

null :: ByteStringUTF8 -> Bool

LeftCancellative ByteStringUTF8

Defined in Data.Monoid.Instances.ByteString.UTF8

LeftReductive ByteStringUTF8

O(n)

Defined in Data.Monoid.Instances.ByteString.UTF8

Methods

isPrefixOf :: ByteStringUTF8 -> ByteStringUTF8 -> Bool

stripPrefix :: ByteStringUTF8 -> ByteStringUTF8 -> Maybe ByteStringUTF8

LeftGCDMonoid ByteStringUTF8

O(prefixLength)

Defined in Data.Monoid.Instances.ByteString.UTF8

Methods

commonPrefix :: ByteStringUTF8 -> ByteStringUTF8 -> ByteStringUTF8

stripCommonPrefix :: ByteStringUTF8 -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8, ByteStringUTF8)

Factorial ByteStringUTF8

Defined in Data.Monoid.Instances.ByteString.UTF8

Methods

factors :: ByteStringUTF8 -> [ByteStringUTF8]

primePrefix :: ByteStringUTF8 -> ByteStringUTF8

primeSuffix :: ByteStringUTF8 -> ByteStringUTF8

foldl :: (a -> ByteStringUTF8 -> a) -> a -> ByteStringUTF8 -> a

foldl' :: (a -> ByteStringUTF8 -> a) -> a -> ByteStringUTF8 -> a

foldr :: (ByteStringUTF8 -> a -> a) -> a -> ByteStringUTF8 -> a

length :: ByteStringUTF8 -> Int

foldMap :: Monoid n => (ByteStringUTF8 -> n) -> ByteStringUTF8 -> n

reverse :: ByteStringUTF8 -> ByteStringUTF8

FactorialMonoid ByteStringUTF8

Defined in Data.Monoid.Instances.ByteString.UTF8

Methods

splitPrimePrefix :: ByteStringUTF8 -> Maybe (ByteStringUTF8, ByteStringUTF8)

splitPrimeSuffix :: ByteStringUTF8 -> Maybe (ByteStringUTF8, ByteStringUTF8)

inits :: ByteStringUTF8 -> [ByteStringUTF8]

tails :: ByteStringUTF8 -> [ByteStringUTF8]

span :: (ByteStringUTF8 -> Bool) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8)

break :: (ByteStringUTF8 -> Bool) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8)

split :: (ByteStringUTF8 -> Bool) -> ByteStringUTF8 -> [ByteStringUTF8]

takeWhile :: (ByteStringUTF8 -> Bool) -> ByteStringUTF8 -> ByteStringUTF8

dropWhile :: (ByteStringUTF8 -> Bool) -> ByteStringUTF8 -> ByteStringUTF8

spanMaybe :: s -> (s -> ByteStringUTF8 -> Maybe s) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8, s)

spanMaybe' :: s -> (s -> ByteStringUTF8 -> Maybe s) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8, s)

splitAt :: Int -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8)

drop :: Int -> ByteStringUTF8 -> ByteStringUTF8

take :: Int -> ByteStringUTF8 -> ByteStringUTF8

TextualMonoid ByteStringUTF8

Defined in Data.Monoid.Instances.ByteString.UTF8

Methods

fromText :: Text -> ByteStringUTF8

singleton :: Char -> ByteStringUTF8

splitCharacterPrefix :: ByteStringUTF8 -> Maybe (Char, ByteStringUTF8)

characterPrefix :: ByteStringUTF8 -> Maybe Char

map :: (Char -> Char) -> ByteStringUTF8 -> ByteStringUTF8

concatMap :: (Char -> ByteStringUTF8) -> ByteStringUTF8 -> ByteStringUTF8

toString :: (ByteStringUTF8 -> String) -> ByteStringUTF8 -> String

toText :: (ByteStringUTF8 -> Text) -> ByteStringUTF8 -> Text

any :: (Char -> Bool) -> ByteStringUTF8 -> Bool

all :: (Char -> Bool) -> ByteStringUTF8 -> Bool

foldl :: (a -> ByteStringUTF8 -> a) -> (a -> Char -> a) -> a -> ByteStringUTF8 -> a

foldl' :: (a -> ByteStringUTF8 -> a) -> (a -> Char -> a) -> a -> ByteStringUTF8 -> a

foldr :: (ByteStringUTF8 -> a -> a) -> (Char -> a -> a) -> a -> ByteStringUTF8 -> a

scanl :: (Char -> Char -> Char) -> Char -> ByteStringUTF8 -> ByteStringUTF8

scanl1 :: (Char -> Char -> Char) -> ByteStringUTF8 -> ByteStringUTF8

scanr :: (Char -> Char -> Char) -> Char -> ByteStringUTF8 -> ByteStringUTF8

scanr1 :: (Char -> Char -> Char) -> ByteStringUTF8 -> ByteStringUTF8

mapAccumL :: (a -> Char -> (a, Char)) -> a -> ByteStringUTF8 -> (a, ByteStringUTF8)

mapAccumR :: (a -> Char -> (a, Char)) -> a -> ByteStringUTF8 -> (a, ByteStringUTF8)

takeWhile :: (ByteStringUTF8 -> Bool) -> (Char -> Bool) -> ByteStringUTF8 -> ByteStringUTF8

dropWhile :: (ByteStringUTF8 -> Bool) -> (Char -> Bool) -> ByteStringUTF8 -> ByteStringUTF8

break :: (ByteStringUTF8 -> Bool) -> (Char -> Bool) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8)

span :: (ByteStringUTF8 -> Bool) -> (Char -> Bool) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8)

spanMaybe :: s -> (s -> ByteStringUTF8 -> Maybe s) -> (s -> Char -> Maybe s) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8, s)

spanMaybe' :: s -> (s -> ByteStringUTF8 -> Maybe s) -> (s -> Char -> Maybe s) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8, s)

split :: (Char -> Bool) -> ByteStringUTF8 -> [ByteStringUTF8]

find :: (Char -> Bool) -> ByteStringUTF8 -> Maybe Char

elem :: Char -> ByteStringUTF8 -> Bool

foldl_ :: (a -> Char -> a) -> a -> ByteStringUTF8 -> a

foldl_' :: (a -> Char -> a) -> a -> ByteStringUTF8 -> a

foldr_ :: (Char -> a -> a) -> a -> ByteStringUTF8 -> a

takeWhile_ :: Bool -> (Char -> Bool) -> ByteStringUTF8 -> ByteStringUTF8

dropWhile_ :: Bool -> (Char -> Bool) -> ByteStringUTF8 -> ByteStringUTF8

break_ :: Bool -> (Char -> Bool) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8)

span_ :: Bool -> (Char -> Bool) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8)

spanMaybe_ :: s -> (s -> Char -> Maybe s) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8, s)

spanMaybe_' :: s -> (s -> Char -> Maybe s) -> ByteStringUTF8 -> (ByteStringUTF8, ByteStringUTF8, s)

decode :: ByteString -> (ByteStringUTF8, ByteString)

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.