/// <summary>
/// Test if the input HTML has only tags and attributes allowed by the Whitelist.
/// </summary>
/// <remarks>
/// Useful for form validation. The input HTML should
/// still be run through the cleaner to set up enforced attributes, and to tidy the output.
/// </remarks>
/// <param name="bodyHtml">HTML to test</param>
/// <param name="whitelist">whitelist to test against</param>
/// <returns>true if no tags or attributes were removed; false otherwise</returns>
/// <seealso cref="Clean(string, Supremes.Safety.Whitelist)"></seealso>
public static bool IsValid(string bodyHtml, Whitelist whitelist)
{
Document dirty = ParseBodyFragment(bodyHtml, string.Empty);
Cleaner cleaner = new Cleaner(whitelist);
return cleaner.IsValid(dirty);
}
internal CleaningVisitor(Cleaner _enclosing, Element root, Element destination)
{
this._enclosing = _enclosing;
// current element to append nodes to
this.root = root;
this.destination = destination;
}
/// <summary>
/// Get safe HTML from untrusted input HTML,
/// by parsing input HTML and filtering it through a white-list of permitted tags and attributes.
/// </summary>
/// <param name="bodyHtml">input untrusted HTML (body fragment)</param>
/// <param name="baseUri">URL to resolve relative URLs against</param>
/// <param name="whitelist">white-list of permitted HTML elements</param>
/// <param name="outputSettings">document output settings; use to control pretty-printing and entity escape modes</param>
/// <returns>safe HTML (body fragment)</returns>
/// <seealso cref="Supremes.Safety.Cleaner.Clean(Supremes.Nodes.Document)">Supremes.Safety.Cleaner.Clean(Supremes.Nodes.Document)</seealso>
public static string Clean(string bodyHtml, string baseUri, Whitelist whitelist, DocumentOutputSettings outputSettings)
{
Document dirty = ParseBodyFragment(bodyHtml, baseUri);
Cleaner cleaner = new Cleaner(whitelist);
Document clean = cleaner.Clean(dirty);
clean.OutputSettings = outputSettings;
return clean.Body.Html;
}
public void HandlesFramesets()
{
string dirty = "<html><head><script></script><noscript></noscript></head><frameset><frame src=\"foo\" /><frame src=\"foo\" /></frameset></html>";
string clean = Dcsoup.Clean(dirty, Whitelist.Basic);
Assert.AreEqual("", clean); // nothing good can come out of that
Document dirtyDoc = Dcsoup.Parse(dirty);
Document cleanDoc = new Cleaner(Whitelist.Basic).Clean(dirtyDoc);
Assert.IsFalse(cleanDoc == null);
Assert.AreEqual(0, cleanDoc.Body.ChildNodeSize);
}