Copyright	(c) Iavor S. Diatchki 2009
License	BSD3-style (see LICENSE)
Maintainer	emertens@galois.com
Stability	experimental
Portability	portable This module provides fast, validated encoding and decoding functions between 'ByteString's and 'String's. It does not exactly match the output of the Codec.Binary.UTF8.String output for invalid encodings as the number of replacement characters is sometimes longer.
Safe Haskell	Trustworthy
Language	Haskell2010

Data.ByteString.UTF8

Description

Synopsis

data ByteString
decode :: ByteString -> Maybe (Char, Int)
replacement_char :: Char
uncons :: ByteString -> Maybe (Char, ByteString)
splitAt :: Int -> ByteString -> (ByteString, ByteString)
take :: Int -> ByteString -> ByteString
drop :: Int -> ByteString -> ByteString
span :: (Char -> Bool) -> ByteString -> (ByteString, ByteString)
break :: (Char -> Bool) -> ByteString -> (ByteString, ByteString)
fromChar :: Char -> ByteString
fromString :: String -> ByteString
toString :: ByteString -> String
foldl :: (a -> Char -> a) -> a -> ByteString -> a
foldr :: (Char -> a -> a) -> a -> ByteString -> a
length :: ByteString -> Int
lines :: ByteString -> [ByteString]
lines' :: ByteString -> [ByteString]

Documentation

data ByteString #

A space-efficient representation of a Word8 vector, supporting many efficient operations.

A ByteString contains 8-bit bytes, or by using the operations from Data.ByteString.Char8 it can be interpreted as containing 8-bit characters.

Instances

Instances details

Data ByteString
Instance details Defined in Data.ByteString.Internal.Type Methods gfoldl :: (forall d b. Data d => c (d -> b) -> d -> c b) -> (forall g. g -> c g) -> ByteString -> c ByteString # gunfold :: (forall b r. Data b => c (b -> r) -> c r) -> (forall r. r -> c r) -> Constr -> c ByteString # toConstr :: ByteString -> Constr # dataTypeOf :: ByteString -> DataType # dataCast1 :: Typeable t => (forall d. Data d => c (t d)) -> Maybe (c ByteString) # dataCast2 :: Typeable t => (forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c ByteString) # gmapT :: (forall b. Data b => b -> b) -> ByteString -> ByteString # gmapQl :: (r -> r' -> r) -> r -> (forall d. Data d => d -> r') -> ByteString -> r # gmapQr :: forall r r'. (r' -> r -> r) -> r -> (forall d. Data d => d -> r') -> ByteString -> r # gmapQ :: (forall d. Data d => d -> u) -> ByteString -> [u] # gmapQi :: Int -> (forall d. Data d => d -> u) -> ByteString -> u # gmapM :: Monad m => (forall d. Data d => d -> m d) -> ByteString -> m ByteString # gmapMp :: MonadPlus m => (forall d. Data d => d -> m d) -> ByteString -> m ByteString # gmapMo :: MonadPlus m => (forall d. Data d => d -> m d) -> ByteString -> m ByteString #
IsString ByteString	Beware: `fromString` truncates multi-byte characters to octets. e.g. "枯朶に烏のとまりけり秋の暮" becomes �6k�nh~�Q��n�
Instance details Defined in Data.ByteString.Internal.Type Methods fromString :: String -> ByteString #
Monoid ByteString
Instance details Defined in Data.ByteString.Internal.Type Methods mempty :: ByteString # mappend :: ByteString -> ByteString -> ByteString # mconcat :: [ByteString] -> ByteString #
Semigroup ByteString
Instance details Defined in Data.ByteString.Internal.Type Methods (<>) :: ByteString -> ByteString -> ByteString # sconcat :: NonEmpty ByteString -> ByteString # stimes :: Integral b => b -> ByteString -> ByteString #
IsList ByteString	Since: bytestring-0.10.12.0
Instance details Defined in Data.ByteString.Internal.Type Associated Types type Item ByteString # Methods fromList :: [Item ByteString] -> ByteString # fromListN :: Int -> [Item ByteString] -> ByteString # toList :: ByteString -> [Item ByteString] #
Read ByteString
Instance details Defined in Data.ByteString.Internal.Type Methods readsPrec :: Int -> ReadS ByteString # readList :: ReadS [ByteString] # readPrec :: ReadPrec ByteString # readListPrec :: ReadPrec [ByteString] #
Show ByteString
Instance details Defined in Data.ByteString.Internal.Type Methods showsPrec :: Int -> ByteString -> ShowS # show :: ByteString -> String # showList :: [ByteString] -> ShowS #
NFData ByteString
Instance details Defined in Data.ByteString.Internal.Type Methods rnf :: ByteString -> () #
Eq ByteString
Instance details Defined in Data.ByteString.Internal.Type Methods (==) :: ByteString -> ByteString -> Bool # (/=) :: ByteString -> ByteString -> Bool #
Ord ByteString
Instance details Defined in Data.ByteString.Internal.Type Methods compare :: ByteString -> ByteString -> Ordering # (<) :: ByteString -> ByteString -> Bool # (<=) :: ByteString -> ByteString -> Bool # (>) :: ByteString -> ByteString -> Bool # (>=) :: ByteString -> ByteString -> Bool # max :: ByteString -> ByteString -> ByteString # min :: ByteString -> ByteString -> ByteString #
Lift ByteString	Since: bytestring-0.11.2.0
Instance details Defined in Data.ByteString.Internal.Type Methods lift :: Quote m => ByteString -> m Exp # liftTyped :: forall (m :: Type -> Type). Quote m => ByteString -> Code m ByteString #
UTF8Bytes ByteString Int Source #
Instance details Defined in Codec.Binary.UTF8.Generic Methods bsplit :: Int -> ByteString -> (ByteString, ByteString) Source # bdrop :: Int -> ByteString -> ByteString Source # buncons :: ByteString -> Maybe (Word8, ByteString) Source # elemIndex :: Word8 -> ByteString -> Maybe Int Source # empty :: ByteString Source # null :: ByteString -> Bool Source # pack :: [Word8] -> ByteString Source # tail :: ByteString -> ByteString Source #
type Item ByteString
Instance details Defined in Data.ByteString.Internal.Type type Item ByteString = Word8

decode :: ByteString -> Maybe (Char, Int) Source #

Try to extract a character from a byte string. Returns Nothing if there are no more bytes in the byte string. Otherwise, it returns a decoded character and the number of bytes used in its representation. Errors are replaced by character '\0xFFFD'.

replacement_char :: Char Source #

This character is used to mark errors in a UTF8 encoded string.

uncons :: ByteString -> Maybe (Char, ByteString) Source #

Get the first character of a byte string, if any. Malformed characters are replaced by '\0xFFFD'.

splitAt :: Int -> ByteString -> (ByteString, ByteString) Source #

Split after a given number of characters. Negative values are treated as if they are 0.

take :: Int -> ByteString -> ByteString Source #

take n s returns the first n characters of s. If s has less than n characters, then we return the whole of s.

drop :: Int -> ByteString -> ByteString Source #

drop n s returns the s without its first n characters. If s has less than n characters, then we return an empty string.

span :: (Char -> Bool) -> ByteString -> (ByteString, ByteString) Source #

Split a string into two parts: the first is the longest prefix that contains only characters that satisfy the predicate; the second part is the rest of the string. Invalid characters are passed as '\0xFFFD' to the predicate.

break :: (Char -> Bool) -> ByteString -> (ByteString, ByteString) Source #

Split a string into two parts: the first is the longest prefix that contains only characters that do not satisfy the predicate; the second part is the rest of the string. Invalid characters are passed as '\0xFFFD' to the predicate.

fromChar :: Char -> ByteString Source #

Converts a Haskell char into a UTF8 encoded bytestring.

fromString :: String -> ByteString Source #

Converts a Haskell string into a UTF8 encoded bytestring.

toString :: ByteString -> String Source #

Convert a UTF8 encoded bytestring into a Haskell string. Invalid characters are replaced with '\0xFFFD'.

foldl :: (a -> Char -> a) -> a -> ByteString -> a Source #

Traverse a bytestring (left biased). This function is strict in the accumulator.

foldr :: (Char -> a -> a) -> a -> ByteString -> a Source #

Traverse a bytestring (right biased).

length :: ByteString -> Int Source #

Counts the number of characters encoded in the bytestring. Note that this includes replacement characters.

lines :: ByteString -> [ByteString] Source #

Split a string into a list of lines. Lines are terminated by '\n' or the end of the string. Empty lines may not be terminated by the end of the string. See also lines'.

lines' :: ByteString -> [ByteString] Source #

Split a string into a list of lines. Lines are terminated by '\n' or the end of the string. Empty lines may not be terminated by the end of the string. This function preserves the terminators. See also lines.