/**
* Converts (X)HTML response to DOM object Tree. This version cares of charset of response.
*
* @param unicodeData
* @return
*/
private Document parseResponse(String unicodeData, XPathExtractor extractor)
throws UnsupportedEncodingException, IOException, ParserConfigurationException, SAXException,
TidyException {
// TODO: validate contentType for reasonable types?
// NOTE: responseData encoding is server specific
// Therefore we do byte -> unicode -> byte conversion
// to ensure UTF-8 encoding as required by XPathUtil
// convert unicode String -> UTF-8 bytes
byte[] utf8data = unicodeData.getBytes("UTF-8"); // $NON-NLS-1$
ByteArrayInputStream in = new ByteArrayInputStream(utf8data);
boolean isXML = JOrphanUtils.isXML(utf8data);
// this method assumes UTF-8 input data
return XPathUtil.makeDocument(
in,
false,
false,
extractor.useNameSpace(),
extractor.isTolerant(),
extractor.isQuiet(),
extractor.showWarnings(),
extractor.reportErrors(),
isXML,
extractor.isDownloadDTDs());
}
