Copyright	(c) Iavor S. Diatchki 2009
License	BSD3-style (see LICENSE)
Maintainer	emertens@galois.com
Stability	experimental
Portability	portable
Safe Haskell	Trustworthy
Language	Haskell2010

Codec.Binary.UTF8.Generic

Description

Synopsis

class (Num s, Ord s) => UTF8Bytes b s | b -> s where
- bsplit :: s -> b -> (b, b)
- bdrop :: s -> b -> b
- buncons :: b -> Maybe (Word8, b)
- elemIndex :: Word8 -> b -> Maybe s
- empty :: b
- null :: b -> Bool
- pack :: [Word8] -> b
- tail :: b -> b
decode :: UTF8Bytes b s => b -> Maybe (Char, s)
replacement_char :: Char
uncons :: UTF8Bytes b s => b -> Maybe (Char, b)
splitAt :: UTF8Bytes b s => s -> b -> (b, b)
take :: UTF8Bytes b s => s -> b -> b
drop :: UTF8Bytes b s => s -> b -> b
span :: UTF8Bytes b s => (Char -> Bool) -> b -> (b, b)
break :: UTF8Bytes b s => (Char -> Bool) -> b -> (b, b)
fromString :: UTF8Bytes b s => String -> b
toString :: UTF8Bytes b s => b -> String
foldl :: UTF8Bytes b s => (a -> Char -> a) -> a -> b -> a
foldr :: UTF8Bytes b s => (Char -> a -> a) -> a -> b -> a
length :: UTF8Bytes b s => b -> s
lines :: UTF8Bytes b s => b -> [b]
lines' :: UTF8Bytes b s => b -> [b]

Documentation

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

Methods

bsplit :: s -> b -> (b, b) Source #

bdrop :: s -> b -> b Source #

buncons :: b -> Maybe (Word8, b) Source #

elemIndex :: Word8 -> b -> Maybe s Source #

empty :: b Source #

null :: b -> Bool Source #

pack :: [Word8] -> b Source #

tail :: b -> b Source #

Instances

Instances details

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 #
UTF8Bytes ByteString Int64 Source #
Instance details Defined in Codec.Binary.UTF8.Generic Methods bsplit :: Int64 -> ByteString -> (ByteString, ByteString) Source # bdrop :: Int64 -> ByteString -> ByteString Source # buncons :: ByteString -> Maybe (Word8, ByteString) Source # elemIndex :: Word8 -> ByteString -> Maybe Int64 Source # empty :: ByteString Source # null :: ByteString -> Bool Source # pack :: [Word8] -> ByteString Source # tail :: ByteString -> ByteString Source #
UTF8Bytes [Word8] Int Source #
Instance details Defined in Codec.Binary.UTF8.Generic Methods bsplit :: Int -> [Word8] -> ([Word8], [Word8]) Source # bdrop :: Int -> [Word8] -> [Word8] Source # buncons :: [Word8] -> Maybe (Word8, [Word8]) Source # elemIndex :: Word8 -> [Word8] -> Maybe Int Source # empty :: [Word8] Source # null :: [Word8] -> Bool Source # pack :: [Word8] -> [Word8] Source # tail :: [Word8] -> [Word8] Source #

decode :: UTF8Bytes b s => b -> Maybe (Char, s) 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 :: UTF8Bytes b s => b -> Maybe (Char, b) Source #

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

splitAt :: UTF8Bytes b s => s -> b -> (b, b) Source #

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

take :: UTF8Bytes b s => s -> b -> b 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 :: UTF8Bytes b s => s -> b -> b 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 :: UTF8Bytes b s => (Char -> Bool) -> b -> (b, b) 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 :: UTF8Bytes b s => (Char -> Bool) -> b -> (b, b) 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.

fromString :: UTF8Bytes b s => String -> b Source #

Converts a Haskell string into a UTF8 encoded bytestring.

toString :: UTF8Bytes b s => b -> String Source #

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

foldl :: UTF8Bytes b s => (a -> Char -> a) -> a -> b -> a Source #

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

foldr :: UTF8Bytes b s => (Char -> a -> a) -> a -> b -> a Source #

Traverse a bytestring (right biased).

length :: UTF8Bytes b s => b -> s Source #

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

lines :: UTF8Bytes b s => b -> [b] 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' :: UTF8Bytes b s => b -> [b] 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.