PlainText.hs

{-|
Description:    Tokenization rules for characters which should not be processed further, without an exit condition.

Copyright:      (c) 2020 Sam May
License:        MPL-2.0
Maintainer:     ag.eitilt@gmail.com

Stability:      stable
Portability:    portable
-}
module Web.Mangrove.Parse.Tokenize.PlainText
    ( tokenPlainText
    ) where


import Web.Mangrove.Parse.Common.Error
import Web.Mangrove.Parse.Tokenize.Common
import Web.Willow.Common.Encoding.Character


-- | __HTML:__
--      @[PLAINTEXT state]
--      (https://html.spec.whatwg.org/multipage/parsing.html#plaintext-state)@
-- 
-- The parsing instructions rooted in the 'PlainTextState' section of the state
-- machine.
tokenPlainText :: Tokenizer (TokenizerOutput Token)
tokenPlainText = tokenizer Nothing
    [ if_ (== '\NUL') $ emit ([UnexpectedNullCharacter], Character replacementChar)
    , elseChar $ \c -> emit ([], Character c)
    ]