/**
* Configure schema validation as recommended by the JAXP 1.2 spec. The <code>properties</code>
* object may contains information about the schema local and language.
*
* @param properties parser optional info
*/
private static void configureOldXerces(SAXParser parser, Properties properties)
throws ParserConfigurationException, SAXNotSupportedException {
String schemaLocation = (String) properties.get("schemaLocation");
String schemaLanguage = (String) properties.get("schemaLanguage");
try {
if (schemaLocation != null) {
parser.setProperty(JAXP_SCHEMA_LANGUAGE, schemaLanguage);
parser.setProperty(JAXP_SCHEMA_SOURCE, schemaLocation);
}
} catch (SAXNotRecognizedException e) {
log.info(parser.getClass().getName() + ": " + e.getMessage() + " not supported.");
}
}
@Override
public String parseFulltext(String html) {
if (!judge(html)) return null;
Parser theParser = null;
HTMLSchema theSchema = null;
XMLReader r;
if (theParser == null) theParser = new Parser();
r = theParser;
theSchema = new HTMLSchema();
try {
r.setProperty(Parser.schemaProperty, theSchema);
r.setFeature(Parser.namespacesFeature, false);
} catch (SAXNotRecognizedException e) {
logger.fatal(e.getMessage());
return null;
} catch (SAXNotSupportedException e) {
logger.fatal(e.getMessage());
return null;
}
RejuvenationResearchParserHandler h = new RejuvenationResearchParserHandler();
r.setContentHandler(h);
InputStream fin = new ByteArrayInputStream(html.getBytes());
InputSource s = new InputSource(fin);
s.setEncoding("utf8");
try {
r.parse(s);
fin.close();
return h.getContent();
} catch (IOException e) {
logger.fatal(e.getMessage());
} catch (SAXException e) {
logger.fatal(e.getMessage());
}
return null;
}
/**
* Retrieves a cached XMLReader for this thread, or creates a new XMLReader, if the existing
* reader is in use. When the caller no longer needs the reader, it must release it with a call to
* {@link #releaseXMLReader}.
*/
public synchronized XMLReader getXMLReader() throws SAXException {
XMLReader reader;
if (m_readers == null) {
// When the m_readers.get() method is called for the first time
// on a thread, a new XMLReader will automatically be created.
m_readers = new ThreadLocal();
}
if (m_inUse == null) {
m_inUse = new HashMap();
}
// If the cached reader for this thread is in use, construct a new
// one; otherwise, return the cached reader unless it isn't an
// instance of the class set in the 'org.xml.sax.driver' property
reader = (XMLReader) m_readers.get();
boolean threadHasReader = (reader != null);
String factory = SecuritySupport.getSystemProperty(property);
if (threadHasReader
&& m_inUse.get(reader) != Boolean.TRUE
&& (factory == null || reader.getClass().getName().equals(factory))) {
m_inUse.put(reader, Boolean.TRUE);
} else {
try {
try {
// According to JAXP 1.2 specification, if a SAXSource
// is created using a SAX InputSource the Transformer or
// TransformerFactory creates a reader via the
// XMLReaderFactory if setXMLReader is not used
reader = XMLReaderFactory.createXMLReader();
try {
reader.setFeature(XMLConstants.FEATURE_SECURE_PROCESSING, _secureProcessing);
} catch (SAXNotRecognizedException e) {
System.err.println("Warning: " + reader.getClass().getName() + ": " + e.getMessage());
}
} catch (Exception e) {
try {
// If unable to create an instance, let's try to use
// the XMLReader from JAXP
if (m_parserFactory == null) {
m_parserFactory = FactoryImpl.getSAXFactory(m_useServicesMechanism);
m_parserFactory.setNamespaceAware(true);
}
reader = m_parserFactory.newSAXParser().getXMLReader();
} catch (ParserConfigurationException pce) {
throw pce; // pass along pce
}
}
try {
reader.setFeature(NAMESPACES_FEATURE, true);
reader.setFeature(NAMESPACE_PREFIXES_FEATURE, false);
} catch (SAXException se) {
// Try to carry on if we've got a parser that
// doesn't know about namespace prefixes.
}
} catch (ParserConfigurationException ex) {
throw new SAXException(ex);
} catch (FactoryConfigurationError ex1) {
throw new SAXException(ex1.toString());
} catch (NoSuchMethodError ex2) {
} catch (AbstractMethodError ame) {
}
// Cache the XMLReader if this is the first time we've created
// a reader for this thread.
if (!threadHasReader) {
m_readers.set(reader);
m_inUse.put(reader, Boolean.TRUE);
}
}
try {
// reader is cached, but this property might have been reset
reader.setProperty(XMLConstants.ACCESS_EXTERNAL_DTD, _accessExternalDTD);
} catch (SAXException se) {
System.err.println("Warning: " + reader.getClass().getName() + ": " + se.getMessage());
}
try {
if (_xmlSecurityManager != null) {
for (XMLSecurityManager.Limit limit : XMLSecurityManager.Limit.values()) {
reader.setProperty(limit.apiProperty(), _xmlSecurityManager.getLimitValueAsString(limit));
}
if (_xmlSecurityManager.printEntityCountInfo()) {
reader.setProperty(XalanConstants.JDK_ENTITY_COUNT_INFO, XalanConstants.JDK_YES);
}
}
} catch (SAXException se) {
System.err.println("Warning: " + reader.getClass().getName() + ": " + se.getMessage());
}
return reader;
}
public Phylogeny[] parse() throws IOException, PhylogenyParserException {
reset();
final TolXmlHandler handler = new TolXmlHandler();
final SAXParserFactory factory = SAXParserFactory.newInstance();
factory.setNamespaceAware(true);
try {
if (!ForesterUtil.isEmpty(getSchemaLocation())) {
factory.setFeature(SAX_FEATURES_VALIDATION, true);
factory.setFeature(APACHE_FEATURES_VALIDATION_SCHEMA, true);
factory.setFeature(APACHE_FEATURES_VALIDATION_SCHEMA_FULL, true);
}
} catch (final SAXNotRecognizedException e) {
e.printStackTrace();
throw new PhylogenyParserException("sax not recognized exception: " + e.getMessage());
} catch (final SAXNotSupportedException e) {
e.printStackTrace();
throw new PhylogenyParserException("sax not supported exception: " + e.getMessage());
} catch (final ParserConfigurationException e) {
e.printStackTrace();
throw new PhylogenyParserException("parser _configuration exception: " + e.getMessage());
} catch (final Exception e) {
e.printStackTrace();
throw new PhylogenyParserException("error while configuring sax parser: " + e.getMessage());
}
try {
final SAXParser parser = factory.newSAXParser();
if (!ForesterUtil.isEmpty(getSchemaLocation())) {
parser.setProperty(JAXP_SCHEMA_LANGUAGE, W3C_XML_SCHEMA);
parser.setProperty(JAXP_SCHEMA_SOURCE, getSchemaLocation());
parser.setProperty(APACHE_PROPERTIES_SCHEMA_EXTERNAL_LOCATION, getSchemaLocation());
}
final XMLReader xml_reader = parser.getXMLReader();
xml_reader.setContentHandler(handler);
xml_reader.setErrorHandler(new TolParserErrorHandler());
if (getSource() instanceof File) {
if (!getSource().toString().toLowerCase().endsWith(".zip")) {
xml_reader.parse(new InputSource(new FileReader((File) getSource())));
} else {
final Reader reader = getReaderFromZipFile();
if (reader == null) {
throw new PhylogenyParserException(
"Zip file \"" + getSource() + "\" appears not to contain any entries");
}
xml_reader.parse(new InputSource(reader));
}
} else if (getSource() instanceof InputSource) {
xml_reader.parse((InputSource) getSource());
} else if (getSource() instanceof InputStream) {
if (!isZippedInputstream()) {
final InputStream is = (InputStream) getSource();
final Reader reader = new InputStreamReader(is);
xml_reader.parse(new InputSource(reader));
} else {
final ZipInputStream zip_is = new ZipInputStream((InputStream) getSource());
zip_is.getNextEntry();
final Reader reader = new InputStreamReader(zip_is);
if (reader == null) {
throw new PhylogenyParserException(
"Zip input stream \"" + getSource() + "\" appears not to contain any data");
}
xml_reader.parse(new InputSource(reader));
}
} else if (getSource() instanceof String) {
final File file = new File(getSource().toString());
final Reader reader = new FileReader(file);
xml_reader.parse(new InputSource(reader));
} else if (getSource() instanceof StringBuffer) {
final StringReader string_reader = new StringReader(getSource().toString());
xml_reader.parse(new InputSource(string_reader));
} else {
throw new PhylogenyParserException(
"attempt to parse object of unsupported type: \"" + getSource().getClass() + "\"");
}
} catch (final SAXException sax_exception) {
throw new PhylogenyParserException(
"Failed to parse [" + getSource() + "]: " + sax_exception.getMessage());
} catch (final ParserConfigurationException parser_config_exception) {
throw new PhylogenyParserException(
"Failed to parse ["
+ getSource()
+ "] Problem with xml parser _configuration: "
+ parser_config_exception.getMessage());
} catch (final IOException e) {
throw new PhylogenyParserException(
"Problem with input source [" + getSource() + "]: \n" + e.getMessage());
} catch (final Exception e) {
e.printStackTrace();
throw new PhylogenyParserException(
"Failed to parse [" + getSource() + "]: " + e.getMessage());
} catch (final Error err) {
err.printStackTrace();
throw new PhylogenyParserException("Severe error: " + err.getMessage());
}
final Phylogeny[] ps = new Phylogeny[handler.getPhylogenies().size()];
int i = 0;
for (final Phylogeny phylogeny : handler.getPhylogenies()) {
ps[i++] = phylogeny;
}
return ps;
}