Data.String.UTF8

Representation

data UTF8 string

The type of strings that are represented using the UTF8 encoding. The parameter is the type of the container for the representation.

Instances

Eq string => Eq (UTF8 string)

Defined in Data.String.UTF8

Methods

(==) :: UTF8 string -> UTF8 string -> Bool

(/=) :: UTF8 string -> UTF8 string -> Bool

Ord string => Ord (UTF8 string)

Defined in Data.String.UTF8

Methods

compare :: UTF8 string -> UTF8 string -> Ordering

(<) :: UTF8 string -> UTF8 string -> Bool

(<=) :: UTF8 string -> UTF8 string -> Bool

(>) :: UTF8 string -> UTF8 string -> Bool

(>=) :: UTF8 string -> UTF8 string -> Bool

max :: UTF8 string -> UTF8 string -> UTF8 string

min :: UTF8 string -> UTF8 string -> UTF8 string

UTF8Bytes string index => Show (UTF8 string)

Defined in Data.String.UTF8

Methods

showsPrec :: Int -> UTF8 string -> ShowS

show :: UTF8 string -> String

showList :: [UTF8 string] -> ShowS

UTF8Bytes string index => IsString (UTF8 string)

Defined in Data.String.UTF8

Methods

fromString :: String -> UTF8 string

class (Num s, Ord s) => UTF8Bytes b s | b -> s

Minimal complete definition

bsplit, bdrop, buncons, elemIndex, empty, null, pack, tail

Instances

UTF8Bytes ByteString Int64

Defined in Codec.Binary.UTF8.Generic

Methods

bsplit :: Int64 -> ByteString -> (ByteString, ByteString)

bdrop :: Int64 -> ByteString -> ByteString

buncons :: ByteString -> Maybe (Word8, ByteString)

elemIndex :: Word8 -> ByteString -> Maybe Int64

empty :: ByteString

null :: ByteString -> Bool

pack :: [Word8] -> ByteString

tail :: ByteString -> ByteString

UTF8Bytes ByteString Int

Defined in Codec.Binary.UTF8.Generic

Methods

bsplit :: Int -> ByteString -> (ByteString, ByteString)

bdrop :: Int -> ByteString -> ByteString

buncons :: ByteString -> Maybe (Word8, ByteString)

elemIndex :: Word8 -> ByteString -> Maybe Int

empty :: ByteString

null :: ByteString -> Bool

pack :: [Word8] -> ByteString

tail :: ByteString -> ByteString

UTF8Bytes [Word8] Int

Defined in Codec.Binary.UTF8.Generic

Methods

bsplit :: Int -> [Word8] -> ([Word8], [Word8])

bdrop :: Int -> [Word8] -> [Word8]

buncons :: [Word8] -> Maybe (Word8, [Word8])

elemIndex :: Word8 -> [Word8] -> Maybe Int

empty :: [Word8]

null :: [Word8] -> Bool

pack :: [Word8] -> [Word8]

tail :: [Word8] -> [Word8]

fromString :: UTF8Bytes string index => String -> UTF8 string

Converts a Haskell string into a UTF8 encoded string. Complexity: linear.

toString :: UTF8Bytes string index => UTF8 string -> String

Convert a UTF8 encoded string into a Haskell string. Invalid characters are replaced by replacement_char. Complexity: linear.

fromRep :: string -> UTF8 string

toRep :: UTF8 string -> string

replacement_char :: Char

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

Character based operations

uncons :: UTF8Bytes string index => UTF8 string -> Maybe (Char, UTF8 string)

Get the first character of a byte string, if any. Invalid characters are replaced by replacement_char.

splitAt :: UTF8Bytes string index => index -> UTF8 string -> (UTF8 string, UTF8 string)

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

take :: UTF8Bytes string index => index -> UTF8 string -> UTF8 string

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 :: UTF8Bytes string index => index -> UTF8 string -> UTF8 string

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 :: UTF8Bytes string index => (Char -> Bool) -> UTF8 string -> (UTF8 string, UTF8 string)

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 :: UTF8Bytes string index => (Char -> Bool) -> UTF8 string -> (UTF8 string, UTF8 string)

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 replacement_char to the predicate.

foldl :: UTF8Bytes string index => (a -> Char -> a) -> a -> UTF8 string -> a

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

foldr :: UTF8Bytes string index => (Char -> a -> a) -> a -> UTF8 string -> a

Traverse a bytestring (right biased).

length :: UTF8Bytes string index => UTF8 string -> index

Counts the number of characters encoded in the bytestring. Note that this includes replacement characters. The function is linear in the number of bytes in the representation.

lines :: UTF8Bytes string index => UTF8 string -> [UTF8 string]

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' :: UTF8Bytes string index => UTF8 string -> [UTF8 string]

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.

Representation based operations

null :: UTF8Bytes string index => UTF8 string -> Bool

Checks if there are no more bytes in the underlying representation.

decode :: UTF8Bytes string index => UTF8 string -> Maybe (Char, index)

Extract the first character for the underlying representation, if one is available. It also returns the number of bytes used in the representation of the character. See also uncons.

byteSplitAt :: UTF8Bytes string index => index -> UTF8 string -> (UTF8 string, UTF8 string)

Split after a given number of bytes in the underlying representation. See also splitAt.

byteTake :: UTF8Bytes string index => index -> UTF8 string -> UTF8 string

Take only the given number of bytes from the underlying representation. See also take.

byteDrop :: UTF8Bytes string index => index -> UTF8 string -> UTF8 string

Drop the given number of bytes from the underlying representation. See also drop.