-- Hoogle documentation, generated by Haddock -- See Hoogle, http://www.haskell.org/hoogle/ -- | An "attoparsec"-based HTML tokenizer -- -- This library can be used as a basis for complex HTML parsers, or for -- streaming. E.g., by composing it with the "list-t-attoparsec" -- library you can produce a token stream, thus becoming able to -- implement a highly efficient stream-parser, which works in a single -- pass, constant memory and is capable of early termination. -- "list-t-html-parser" is such a parser. @package html-tokenizer @version 0.4.1 module HTMLTokenizer -- | An HTML token. data Token -- | A Doctype declaration. Token_Doctype :: Text -> Token -- | An opening tag. Token_OpeningTag :: OpeningTag -> Token -- | A closing tag. Token_ClosingTag :: Identifier -> Token -- | A text between tags. Token_Text :: Text -> Token -- | Contents of a comment. Token_Comment :: Text -> Token -- | An opening tag name, attributes and whether it is closed. type OpeningTag = (Identifier, [Attribute], Bool) -- | A case-insensitive identifier. data Identifier Identifier :: (Maybe (CI Text)) -> (CI Text) -> Identifier -- | A tag attribute identifier and a value. type Attribute = (Identifier, Maybe Text) -- | A token parser. -- -- Does not decode entities. token :: Parser Token instance Data.Data.Data HTMLTokenizer.Token instance GHC.Generics.Generic HTMLTokenizer.Token instance GHC.Classes.Eq HTMLTokenizer.Token instance GHC.Classes.Ord HTMLTokenizer.Token instance GHC.Show.Show HTMLTokenizer.Token instance Data.Data.Data HTMLTokenizer.Identifier instance GHC.Generics.Generic HTMLTokenizer.Identifier instance GHC.Classes.Eq HTMLTokenizer.Identifier instance GHC.Classes.Ord HTMLTokenizer.Identifier instance GHC.Show.Show HTMLTokenizer.Identifier instance Data.String.IsString HTMLTokenizer.Identifier