public Document ParseInput(string html, string baseUri)
{
_errors = IsTrackErrors ? ParseErrorList.Tracking(_maxErrors) : ParseErrorList.NoTracking();
Document doc = _treeBuilder.Parse(html, baseUri, _errors);
return(doc);
}
public virtual Document Parse(string input, string baseUri, ParseErrorList errors)
{
InitialiseParse(input, baseUri, errors);
RunParser();
return(_doc);
}
protected ParseErrorList _errors; // null when not tracking errors
protected virtual void InitialiseParse(string input, string baseUri, ParseErrorList errors)
{
if (input == null)
{
throw new ArgumentNullException("String input must not be null");
}
if (baseUri == null)
{
throw new ArgumentNullException("BaseURI must not be null");
}
_doc = new Document(baseUri);
_reader = new CharacterReader(input);
_errors = errors;
_tokeniser = new Tokeniser(_reader, errors);
_stack = new DescendableLinkedList <Element>();
this._baseUri = baseUri;
}
public Document Parse(string input, string baseUri)
{
return(Parse(input, baseUri, ParseErrorList.NoTracking()));
}
protected override void InitialiseParse(string input, string baseUri, ParseErrorList errors)
{
base.InitialiseParse(input, baseUri, errors);
_stack.AddLast(_doc); // place the document onto the stack. differs from HtmlTreeBuilder (not on stack)
}
public Tokeniser(CharacterReader reader, ParseErrorList errors)
{
this._reader = reader;
this._errors = errors;
}
// static parse functions below
/// <summary>
/// Parse HTML into a Document.
/// </summary>
/// <param name="html">HTML to parse</param>
/// <param name="baseUri">base URI of document (i.e. original fetch location), for resolving relative URLs.</param>
/// <returns>parsed Document</returns>
public static Document Parse(string html, string baseUri)
{
HtmlTreeBuilder treeBuilder = new HtmlTreeBuilder();
return(treeBuilder.Parse(html, baseUri, ParseErrorList.NoTracking()));
}
/// <summary>
/// Utility method to unescape HTML entities from a string
/// </summary>
/// <param name="s">HTML escaped string</param>
/// <param name="inAttribute">If the string is to be escaped in strict mode (as attributes are)</param>
/// <returns>An unescaped string</returns>
public static string UnescapeEntities(string s, bool inAttribute)
{
Tokeniser tokeniser = new Tokeniser(new CharacterReader(s), ParseErrorList.NoTracking());
return(tokeniser.UnescapeEntities(inAttribute));
}
/// <summary>
/// Parse a fragment of HTML into a list of nodes. The context element, if supplied, supplies parsing context.
/// </summary>
/// <param name="fragmentHtml">the fragment of HTML to parse</param>
/// <param name="context">(optional) the element that this HTML fragment is being parsed for (i.e. for inner HTML). This provides stack context (for implicit element creation).</param>
/// <param name="baseUri">base URI of document (i.e. original fetch location), for resolving relative URLs.</param>
/// <returns>list of nodes parsed from the input HTML. Note that the context element, if supplied, is not modified.</returns>
public static IList <Node> ParseFragment(string fragmentHtml, Element context, string baseUri)
{
HtmlTreeBuilder treeBuilder = new HtmlTreeBuilder();
return(treeBuilder.ParseFragment(fragmentHtml, context, baseUri, ParseErrorList.NoTracking()));
}
public IList <Node> ParseFragment(string inputFragment, Element context, string baseUri, ParseErrorList errors)
{
// context may be null
_state = HtmlTreeBuilderState.Initial;
InitialiseParse(inputFragment, baseUri, errors);
_contextElement = context;
_fragmentParsing = true;
Element root = null;
if (context != null)
{
if (context.OwnerDocument != null) // quirks setup:
{
_doc.QuirksMode(context.OwnerDocument.QuirksMode());
}
// initialise the tokeniser state:
string contextTag = context.TagName();
if (StringUtil.In(contextTag, "title", "textarea"))
{
_tokeniser.Transition(TokeniserState.RcData);
}
else if (StringUtil.In(contextTag, "iframe", "noembed", "noframes", "style", "xmp"))
{
_tokeniser.Transition(TokeniserState.RawText);
}
else if (contextTag.Equals("script"))
{
_tokeniser.Transition(TokeniserState.ScriptData);
}
else if (contextTag.Equals(("noscript")))
{
_tokeniser.Transition(TokeniserState.Data); // if scripting enabled, rawtext
}
else if (contextTag.Equals("plaintext"))
{
_tokeniser.Transition(TokeniserState.Data);
}
else
{
_tokeniser.Transition(TokeniserState.Data); // default
}
root = new Element(Tag.ValueOf("html"), baseUri);
_doc.AppendChild(root);
_stack.AddFirst(root);
ResetInsertionMode();
// todo: setup form element to nearest form on context (up ancestor chain)
}
RunParser();
if (context != null)
{
return(root.ChildNodes);
}
else
{
return(_doc.ChildNodes);
}
}
public override Document Parse(string input, string baseUri, ParseErrorList errors)
{
_state = HtmlTreeBuilderState.Initial;
return(base.Parse(input, baseUri, errors));
}