Copyright	(c) 2008 2009 Tom Harper (c) 2009 2010 Bryan O'Sullivan (c) 2009 Duncan Coutts (c) 2021 Andrew Lelechenko
License	BSD-style
Maintainer	bos@serpentine.com
Stability	experimental
Portability	GHC
Safe Haskell	Safe-Inferred
Language	Haskell2010

Data.Text.Internal.Encoding.Utf8

Contents

Validation
Naive decoding

Description

Warning: this is an internal module, and does not have a stable API or name. Functions in this module may not check or enforce preconditions expected by public modules. Use at your own risk!

Basic UTF-8 validation and character manipulation.

Synopsis

utf8Length :: Char -> Int
utf8LengthByLeader :: Word8 -> Int
ord2 :: Char -> (Word8, Word8)
ord3 :: Char -> (Word8, Word8, Word8)
ord4 :: Char -> (Word8, Word8, Word8, Word8)
chr2 :: Word8 -> Word8 -> Char
chr3 :: Word8 -> Word8 -> Word8 -> Char
chr4 :: Word8 -> Word8 -> Word8 -> Word8 -> Char
validate1 :: Word8 -> Bool
validate2 :: Word8 -> Word8 -> Bool
validate3 :: Word8 -> Word8 -> Word8 -> Bool
validate4 :: Word8 -> Word8 -> Word8 -> Word8 -> Bool
newtype DecoderState = DecoderState Word8
utf8AcceptState :: DecoderState
utf8RejectState :: DecoderState
updateDecoderState :: Word8 -> DecoderState -> DecoderState
data DecoderResult
- = Accept !Char
- | Incomplete !DecoderState !CodePoint
- | Reject
newtype CodePoint = CodePoint Int
utf8DecodeStart :: Word8 -> DecoderResult
utf8DecodeContinue :: Word8 -> DecoderState -> CodePoint -> DecoderResult

Documentation

utf8Length :: Char -> Int Source #

Since: 2.0

utf8LengthByLeader :: Word8 -> Int Source #

Since: 2.0

ord2 :: Char -> (Word8, Word8) Source #

ord3 :: Char -> (Word8, Word8, Word8) Source #

ord4 :: Char -> (Word8, Word8, Word8, Word8) Source #

chr2 :: Word8 -> Word8 -> Char Source #

chr3 :: Word8 -> Word8 -> Word8 -> Char Source #

chr4 :: Word8 -> Word8 -> Word8 -> Word8 -> Char Source #

Validation

validate1 :: Word8 -> Bool Source #

validate2 :: Word8 -> Word8 -> Bool Source #

validate3 :: Word8 -> Word8 -> Word8 -> Bool Source #

validate4 :: Word8 -> Word8 -> Word8 -> Word8 -> Bool Source #

Naive decoding

newtype DecoderState Source #

Constructors

DecoderState Word8

Instances

Instances details

Show DecoderState Source #
Instance details Defined in Data.Text.Internal.Encoding.Utf8 Methods showsPrec :: Int -> DecoderState -> ShowS # show :: DecoderState -> String # showList :: [DecoderState] -> ShowS #
Eq DecoderState Source #
Instance details Defined in Data.Text.Internal.Encoding.Utf8 Methods (==) :: DecoderState -> DecoderState -> Bool # (/=) :: DecoderState -> DecoderState -> Bool #

utf8AcceptState :: DecoderState Source #

utf8RejectState :: DecoderState Source #

updateDecoderState :: Word8 -> DecoderState -> DecoderState Source #

data DecoderResult Source #

Since: 2.0

Constructors

Accept !Char
Incomplete !DecoderState !CodePoint
Reject

newtype CodePoint Source #

Constructors

CodePoint Int

utf8DecodeStart :: Word8 -> DecoderResult Source #

Since: 2.0

utf8DecodeContinue :: Word8 -> DecoderState -> CodePoint -> DecoderResult Source #

Since: 2.0