-- Hoogle documentation, generated by Haddock
-- See Hoogle, http://www.haskell.org/hoogle/


-- | A high-performance HTML tokenizer
--   
--   This package provides a fast and reasonably robust HTML5 tokenizer
--   built upon the <tt>attoparsec</tt> library. The parsing strategy is
--   based upon the HTML5 parsing specification with few deviations.
--   
--   For instance,
--   
--   <pre>
--   &gt;&gt;&gt; parseTokens "&lt;div&gt;&lt;h1 class=widget&gt;Hello World&lt;/h1&gt;&lt;br/&gt;"
--   [TagOpen "div" [],
--   TagOpen "h1" [Attr "class" "widget"],
--   ContentText "Hello World",
--   TagClose "h1",
--   TagSelfClose "br" []]
--   </pre>
--   
--   The package targets similar use-cases to the venerable
--   <tt>tagsoup</tt> library, but is significantly more efficient,
--   achieving parsing speeds of over 80 megabytes per second on modern
--   hardware and typical web documents. Here are some typical performance
--   numbers taken from parsing a Wikipedia article of moderate length:
--   
--   <pre>
--   benchmarking Forced/tagsoup fast Text
--   time                 186.1 ms   (175.3 ms .. 194.6 ms)
--   0.999 R²   (0.995 R² .. 1.000 R²)
--   mean                 191.7 ms   (188.9 ms .. 198.3 ms)
--   std dev              5.053 ms   (1.092 ms .. 6.809 ms)
--   variance introduced by outliers: 14% (moderately inflated)
--   
--   benchmarking Forced/tagsoup normal Text
--   time                 189.7 ms   (182.8 ms .. 197.7 ms)
--   0.999 R²   (0.998 R² .. 1.000 R²)
--   mean                 196.5 ms   (193.1 ms .. 202.1 ms)
--   std dev              5.481 ms   (2.141 ms .. 7.383 ms)
--   variance introduced by outliers: 14% (moderately inflated)
--   
--   benchmarking Forced/html-parser
--   time                 15.81 ms   (15.75 ms .. 15.89 ms)
--   1.000 R²   (1.000 R² .. 1.000 R²)
--   mean                 15.72 ms   (15.66 ms .. 15.77 ms)
--   std dev              140.9 μs   (113.6 μs .. 174.5 μs)
--   </pre>
@package html-parse
@version 0.2.0.2


-- | This is a performance-oriented HTML tokenizer aim at web-crawling
--   applications. It follows the HTML5 parsing specification quite
--   closely, so it behaves reasonable well on ill-formed documents from
--   the open Web.
module Text.HTML.Parser

-- | Parse a lazy list of tokens from strict <a>Text</a>.
parseTokens :: Text -> [Token]

-- | Parse a lazy list of tokens from lazy <a>Text</a>.
parseTokensLazy :: Text -> [Token]

-- | Parse a single <a>Token</a>.
token :: Parser Token

-- | An HTML token
data Token

-- | An opening tag. Attribute ordering is arbitrary.
TagOpen :: !TagName -> [Attr] -> Token

-- | A self-closing tag.
TagSelfClose :: !TagName -> [Attr] -> Token

-- | A closing tag.
TagClose :: !TagName -> Token

-- | The content between tags.
ContentText :: !Text -> Token

-- | A single character of content
ContentChar :: !Char -> Token

-- | Contents of a comment.
Comment :: !Builder -> Token

-- | Doctype
Doctype :: !Text -> Token

-- | A tag name (e.g. <tt>body</tt>)
type TagName = Text

-- | An attribute name (e.g. <tt>href</tt>)
type AttrName = Text

-- | The value of an attribute
type AttrValue = Text

-- | An attribute of a tag
data Attr
Attr :: !AttrName -> !AttrValue -> Attr

-- | See <a>renderToken</a>.
renderTokens :: [Token] -> Text

-- | (Somewhat) canonical string representation of <a>Token</a>.
renderToken :: Token -> Text

-- | See <a>renderAttr</a>.
renderAttrs :: [Attr] -> Text

-- | Does not escape quotation in attribute values!
renderAttr :: Attr -> Text

-- | Meld neighoring <a>ContentChar</a> and <a>ContentText</a> constructors
--   together and drops empty text elements.
canonicalizeTokens :: [Token] -> [Token]
instance GHC.Generics.Generic Text.HTML.Parser.Token
instance GHC.Classes.Eq Text.HTML.Parser.Token
instance GHC.Classes.Ord Text.HTML.Parser.Token
instance GHC.Show.Show Text.HTML.Parser.Token
instance GHC.Classes.Ord Text.HTML.Parser.Attr
instance GHC.Classes.Eq Text.HTML.Parser.Attr
instance GHC.Show.Show Text.HTML.Parser.Attr
instance Control.DeepSeq.NFData Text.HTML.Parser.Token

module Text.HTML.Tree
tokensToForest :: [Token] -> Either ParseTokenForestError (Forest Token)
data ParseTokenForestError
ParseTokenForestErrorBracketMismatch :: PStack -> (Maybe Token) -> ParseTokenForestError
data PStack
PStack :: Forest Token -> [(Token, Forest Token)] -> PStack
[_pstackToplevelSiblings] :: PStack -> Forest Token
[_pstackParents] :: PStack -> [(Token, Forest Token)]
nonClosing :: [Text]
tokensFromForest :: Forest Token -> [Token]
tokensFromTree :: Tree Token -> [Token]
instance GHC.Show.Show Text.HTML.Tree.ParseTokenForestError
instance GHC.Classes.Eq Text.HTML.Tree.ParseTokenForestError
instance GHC.Show.Show Text.HTML.Tree.PStack
instance GHC.Classes.Eq Text.HTML.Tree.PStack