License	BSD-style
Maintainer	Vincent Hanquez <vincent@snarc.org>
Stability	experimental
Portability	portable
Safe Haskell	None
Language	Haskell2010

Foundation.String

Description

Opaque packed String encoded in UTF8.

The type is an instance of IsString and IsList, which allow OverloadedStrings for string literal, and fromList to convert a [Char] (Prelude String) to a packed representation

{-# LANGUAGE OverloadedStrings #-}
s = "Hello World" :: String

s = fromList ("Hello World" :: Prelude.String) :: String

Each unicode code point is represented by a variable encoding of 1 to 4 bytes,

For more information about UTF8: https://en.wikipedia.org/wiki/UTF-8

Synopsis

Documentation

data String #

Opaque packed array of characters in the UTF8 encoding

Instances

IsList String #
Associated Types type Item String :: * # Methods fromList :: [Item String] -> String # fromListN :: Int -> [Item String] -> String # toList :: String -> [Item String] #
Eq String #
Methods (==) :: String -> String -> Bool # (/=) :: String -> String -> Bool #
Data String #
Methods gfoldl :: (forall d b. Data d => c (d -> b) -> d -> c b) -> (forall g. g -> c g) -> String -> c String # gunfold :: (forall b r. Data b => c (b -> r) -> c r) -> (forall r. r -> c r) -> Constr -> c String # toConstr :: String -> Constr # dataTypeOf :: String -> DataType # dataCast1 :: Typeable (* -> ) t => (forall d. Data d => c (t d)) -> Maybe (c String) # dataCast2 :: Typeable ( -> * -> *) t => (forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c String) # gmapT :: (forall b. Data b => b -> b) -> String -> String # gmapQl :: (r -> r' -> r) -> r -> (forall d. Data d => d -> r') -> String -> r # gmapQr :: (r' -> r -> r) -> r -> (forall d. Data d => d -> r') -> String -> r # gmapQ :: (forall d. Data d => d -> u) -> String -> [u] # gmapQi :: Int -> (forall d. Data d => d -> u) -> String -> u # gmapM :: Monad m => (forall d. Data d => d -> m d) -> String -> m String # gmapMp :: MonadPlus m => (forall d. Data d => d -> m d) -> String -> m String # gmapMo :: MonadPlus m => (forall d. Data d => d -> m d) -> String -> m String #
Ord String #
Methods compare :: String -> String -> Ordering # (<) :: String -> String -> Bool # (<=) :: String -> String -> Bool # (>) :: String -> String -> Bool # (>=) :: String -> String -> Bool # max :: String -> String -> String # min :: String -> String -> String #
Show String #
Methods showsPrec :: Int -> String -> ShowS # show :: String -> String # showList :: [String] -> ShowS #
IsString String #
Methods fromString :: String -> String #
Monoid String #
Methods mempty :: String # mappend :: String -> String -> String # mconcat :: [String] -> String #
Copy String #
Methods copy :: String -> String #
Buildable String #
Associated Types type Mutable String :: * -> * # type Step String :: * # Methods append :: PrimMonad prim => Element String -> Builder String (Mutable String) (Step String) prim () # build :: PrimMonad prim => Int -> Builder String (Mutable String) (Step String) prim () -> prim String #
Collection String #
Methods null :: String -> Bool # length :: String -> Int # elem :: (Eq a, (* ~ a) (Element String)) => Element String -> String -> Bool # notElem :: (Eq a, (* ~ a) (Element String)) => Element String -> String -> Bool # maximum :: (Ord a, (* ~ a) (Element String)) => NonEmpty String -> Element String # minimum :: (Ord a, (* ~ a) (Element String)) => NonEmpty String -> Element String # any :: (Element String -> Bool) -> String -> Bool # all :: (Element String -> Bool) -> String -> Bool #
IndexedCollection String #
Methods (!) :: String -> Int -> Maybe (Element String) # findIndex :: (Element String -> Bool) -> String -> Maybe Int #
InnerFunctor String #
Methods imap :: (Element String -> Element String) -> String -> String #
Sequential String #
Methods take :: Int -> String -> String # revTake :: Int -> String -> String # drop :: Int -> String -> String # revDrop :: Int -> String -> String # splitAt :: Int -> String -> (String, String) # revSplitAt :: Int -> String -> (String, String) # splitOn :: (Element String -> Bool) -> String -> [String] # break :: (Element String -> Bool) -> String -> (String, String) # breakElem :: Element String -> String -> (String, String) # intersperse :: Element String -> String -> String # intercalate :: Element String -> String -> Element String # span :: (Element String -> Bool) -> String -> (String, String) # filter :: (Element String -> Bool) -> String -> String # partition :: (Element String -> Bool) -> String -> (String, String) # reverse :: String -> String # uncons :: String -> Maybe (Element String, String) # unsnoc :: String -> Maybe (String, Element String) # snoc :: String -> Element String -> String # cons :: Element String -> String -> String # find :: (Element String -> Bool) -> String -> Maybe (Element String) # sortBy :: (Element String -> Element String -> Ordering) -> String -> String # singleton :: Element String -> String # head :: NonEmpty String -> Element String # last :: NonEmpty String -> Element String # tail :: NonEmpty String -> String # init :: NonEmpty String -> String # isPrefixOf :: String -> String -> Bool # isSuffixOf :: String -> String -> Bool #
Zippable String #
Methods zipWith :: (Sequential a, Sequential b) => (Element a -> Element b -> Element String) -> a -> b -> String # zipWith3 :: (Sequential a, Sequential b, Sequential c) => (Element a -> Element b -> Element c -> Element String) -> a -> b -> c -> String # zipWith4 :: (Sequential a, Sequential b, Sequential c, Sequential d) => (Element a -> Element b -> Element c -> Element d -> Element String) -> a -> b -> c -> d -> String # zipWith5 :: (Sequential a, Sequential b, Sequential c, Sequential d, Sequential e) => (Element a -> Element b -> Element c -> Element d -> Element e -> Element String) -> a -> b -> c -> d -> e -> String # zipWith6 :: (Sequential a, Sequential b, Sequential c, Sequential d, Sequential e, Sequential f) => (Element a -> Element b -> Element c -> Element d -> Element e -> Element f -> Element String) -> a -> b -> c -> d -> e -> f -> String # zipWith7 :: (Sequential a, Sequential b, Sequential c, Sequential d, Sequential e, Sequential f, Sequential g) => (Element a -> Element b -> Element c -> Element d -> Element e -> Element f -> Element g -> Element String) -> a -> b -> c -> d -> e -> f -> g -> String #
Hashable String #
Methods hashMix :: Hasher st => String -> st -> st #
Arbitrary String #
Methods arbitrary :: Gen String #
type Item String #
type Item String = Char
type Element String #
type Element String = Char
type Mutable String #
type Mutable String
type Step String #
type Step String = Word8

data Encoding #

Various String Encoding that can be use to convert to and from bytes

Constructors

ASCII7
UTF8
UTF16
UTF32
ISO_8859_1

Instances

Bounded Encoding #
Methods minBound :: Encoding # maxBound :: Encoding #
Enum Encoding #
Methods succ :: Encoding -> Encoding # pred :: Encoding -> Encoding # toEnum :: Int -> Encoding # fromEnum :: Encoding -> Int # enumFrom :: Encoding -> [Encoding] # enumFromThen :: Encoding -> Encoding -> [Encoding] # enumFromTo :: Encoding -> Encoding -> [Encoding] # enumFromThenTo :: Encoding -> Encoding -> Encoding -> [Encoding] #
Eq Encoding #
Methods (==) :: Encoding -> Encoding -> Bool # (/=) :: Encoding -> Encoding -> Bool #
Data Encoding #
Methods gfoldl :: (forall d b. Data d => c (d -> b) -> d -> c b) -> (forall g. g -> c g) -> Encoding -> c Encoding # gunfold :: (forall b r. Data b => c (b -> r) -> c r) -> (forall r. r -> c r) -> Constr -> c Encoding # toConstr :: Encoding -> Constr # dataTypeOf :: Encoding -> DataType # dataCast1 :: Typeable (* -> ) t => (forall d. Data d => c (t d)) -> Maybe (c Encoding) # dataCast2 :: Typeable ( -> * -> *) t => (forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c Encoding) # gmapT :: (forall b. Data b => b -> b) -> Encoding -> Encoding # gmapQl :: (r -> r' -> r) -> r -> (forall d. Data d => d -> r') -> Encoding -> r # gmapQr :: (r' -> r -> r) -> r -> (forall d. Data d => d -> r') -> Encoding -> r # gmapQ :: (forall d. Data d => d -> u) -> Encoding -> [u] # gmapQi :: Int -> (forall d. Data d => d -> u) -> Encoding -> u # gmapM :: Monad m => (forall d. Data d => d -> m d) -> Encoding -> m Encoding # gmapMp :: MonadPlus m => (forall d. Data d => d -> m d) -> Encoding -> m Encoding # gmapMo :: MonadPlus m => (forall d. Data d => d -> m d) -> Encoding -> m Encoding #
Ord Encoding #
Methods compare :: Encoding -> Encoding -> Ordering # (<) :: Encoding -> Encoding -> Bool # (<=) :: Encoding -> Encoding -> Bool # (>) :: Encoding -> Encoding -> Bool # (>=) :: Encoding -> Encoding -> Bool # max :: Encoding -> Encoding -> Encoding # min :: Encoding -> Encoding -> Encoding #
Show Encoding #
Methods showsPrec :: Int -> Encoding -> ShowS # show :: Encoding -> String # showList :: [Encoding] -> ShowS #

fromBytes :: Encoding -> UArray Word8 -> (String, Maybe ValidationFailure, UArray Word8) #

Convert a ByteArray to a string assuming a specific encoding.

It returns a 3-tuple of:

The string that has been succesfully converted without any error
An optional validation error
The remaining buffer that hasn't been processed (either as a result of an error, or because the encoded sequence is not fully available)

Considering a stream of data that is fetched chunk by chunk, it's valid to assume that some sequence might fall in a chunk boundary. When converting chunks, if the error is Nothing and the remaining buffer is not empty, then this buffer need to be prepended to the next chunk

fromBytesLenient :: UArray Word8 -> (String, UArray Word8) #

Convert a UTF8 array of bytes to a String.

If there's any error in the stream, it will automatically insert replacement bytes to replace invalid sequences.

In the case of sequence that fall in the middle of 2 chunks, the remaining buffer is supposed to be preprended to the next chunk, and resume the parsing.

fromBytesUnsafe :: UArray Word8 -> String #

Convert a Byte Array representing UTF8 data directly to a string without checking for UTF8 validity

If the input contains invalid sequences, it will trigger runtime async errors when processing data.

In doubt, use fromBytes

toBytes :: Encoding -> String -> UArray Word8 #

Convert a String to a bytearray in a specific encoding

if the encoding is UTF8, the underlying buffer is returned without extra allocation or any processing

In any other encoding, some allocation and processing are done to convert.

data ValidationFailure #

Possible failure related to validating bytes of UTF8 sequences.

Constructors

InvalidHeader
InvalidContinuation
MissingByte

Instances

Eq ValidationFailure #
Methods (==) :: ValidationFailure -> ValidationFailure -> Bool # (/=) :: ValidationFailure -> ValidationFailure -> Bool #
Show ValidationFailure #
Methods showsPrec :: Int -> ValidationFailure -> ShowS # show :: ValidationFailure -> String # showList :: [ValidationFailure] -> ShowS #
Exception ValidationFailure #
Methods toException :: ValidationFailure -> SomeException # fromException :: SomeException -> Maybe ValidationFailure # displayException :: ValidationFailure -> String #

lines :: String -> [String] #

Split lines in a string using newline as separation

words :: String -> [String] #

Split words in a string using spaces as separation

words "Hello Foundation"

Hello, Foundation