Document parse(String input, String baseUri, ParseErrorList errors) {
initialiseParse(input, baseUri, errors);
runParser();
// System.out.println("number of errors: "+errors.size());
for (int i = 0; i < errors.size(); i++) System.out.println(errors.get(i));
return doc;
}
void reset() {
doc.body().removeChildNodes();
reader = new CharacterReader(input, this);
this.errors = ParseErrorList.tracking(100);
tokeniser = new Tokeniser(reader, errors);
while (stack.size() > 2) stack.pollLast();
}
Document parse(String input, String baseUri) {
return parse(input, baseUri, ParseErrorList.tracking(100));
}
/**
* Parse HTML into a Document.
*
* @param html HTML to parse
* @param baseUri base URI of document (i.e. original fetch location), for resolving relative
* URLs.
* @return parsed Document
*/
public static Document parse(String html, String baseUri) {
TreeBuilder treeBuilder = new HtmlTreeBuilder();
return treeBuilder.parse(html, baseUri, ParseErrorList.noTracking());
}
public Document parseInput(String html, String baseUri) {
errors = isTrackErrors() ? ParseErrorList.tracking(maxErrors) : ParseErrorList.noTracking();
Document doc = treeBuilder.parse(html, baseUri, errors);
return doc;
}
/**
* Utility method to unescape HTML entities from a string
*
* @param string HTML escaped string
* @param inAttribute if the string is to be escaped in strict mode (as attributes are)
* @return an unescaped string
*/
public static String unescapeEntities(String string, boolean inAttribute) {
Tokeniser tokeniser = new Tokeniser(new CharacterReader(string), ParseErrorList.noTracking());
return tokeniser.unescapeEntities(inAttribute);
}
/**
* Parse a fragment of XML into a list of nodes.
*
* @param fragmentXml the fragment of XML to parse
* @param baseUri base URI of document (i.e. original fetch location), for resolving relative
* URLs.
* @return list of nodes parsed from the input XML.
*/
public static List<Node> parseXmlFragment(String fragmentXml, String baseUri) {
XmlTreeBuilder treeBuilder = new XmlTreeBuilder();
return treeBuilder.parseFragment(fragmentXml, baseUri, ParseErrorList.noTracking());
}
/**
* Parse a fragment of HTML into a list of nodes. The context element, if supplied, supplies
* parsing context.
*
* @param fragmentHtml the fragment of HTML to parse
* @param 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 baseUri base URI of document (i.e. original fetch location), for resolving relative
* URLs.
* @return list of nodes parsed from the input HTML. Note that the context element, if supplied,
* is not modified.
*/
public static List<Node> parseFragment(String fragmentHtml, Element context, String baseUri) {
HtmlTreeBuilder treeBuilder = new HtmlTreeBuilder();
return treeBuilder.parseFragment(fragmentHtml, context, baseUri, ParseErrorList.noTracking());
}
Document parse(final String input, final String baseUri) {
return parse(input, baseUri, ParseErrorList.noTracking());
}
