public void endElement(java.lang.String uri, java.lang.String localName, java.lang.String qName)
throws SAXException {
try {
if (qName.equals("p") || qName.equals("description")) {
writer.write(getText());
accumulator.setLength(0);
}
if (qName.equals("description")) {
counting = false;
}
if (!counting) {
writer.write(getText());
accumulator.setLength(0);
writer.write("</" + qName + ">\n");
} else {
if (qName.equals("row")) {
accumulator.append(" ");
}
if (qName.equals("p")) {
writer.write("\n");
accumulator.append(" ");
}
}
} catch (Exception e) {
// e.printStackTrace();
throw new GrobidException("An exception occured while running Grobid.", e);
}
}
public static void main(String[] args) {
if (args.length <= 0) {
System.out.println("Usage: java ExtractorDriver url");
return;
}
try {
XMLReader parser = XMLReaderFactory.createXMLReader();
// Since this just writes onto the console, it's best
// to use the system default encoding, which is what
// we get by not specifying an explicit encoding here.
Writer out = new OutputStreamWriter(System.out);
ContentHandler handler = new TextExtractor(out);
parser.setContentHandler(handler);
// parser.parse("file:////c://myxml.xml");
parser.parse(args[0]);
out.flush();
} catch (Exception e) {
System.err.println(e);
}
}
// Wrap I/O exceptions in SAX exceptions, to
// suit handler signature requirements
private void emit(String s) throws SAXException {
try {
out.write(s);
out.flush();
} catch (IOException e) {
throw new SAXException("I/O error", e);
}
}
public void endDocument() throws SAXException {
try {
out.write(eol);
out.flush();
out = null;
} catch (IOException e) {
throw new SAXException("I/O error", e); // NOT LOCALIZABLE
}
}
// Start a new line
// and indent the next line appropriately
private void nl() throws SAXException {
String lineEnd = System.getProperty("line.separator");
try {
out.write(lineEnd);
for (int i = 0; i < indentLevel; i++) out.write(indentString);
} catch (IOException e) {
throw new SAXException("I/O error", e);
}
}
// helpers ... wrap I/O exceptions in SAX exceptions, to
// suit handler signature requirements
private void emit(String s) throws SAXException {
try {
if (s.equals("MULTIPLICITY")) { // NOT LOCALIZABLE
int i = 0;
}
out.write(s);
out.flush();
} catch (IOException e) {
throw new SAXException("I/O error", e); // NOT LOCALIZABLE
}
}
public void endDocument() throws SAXException {
nl();
try {
out.flush();
} catch (IOException e) {
throw new SAXException("I/O error", e);
}
}
// ===========================================================
// SAX DocumentHandler methods
// ===========================================================
public void setDocumentLocator(Locator l) {
// Save this to resolve relative URIs or to give diagnostics.
try {
out.flush();
} catch (IOException e) {
// Ignore errors
}
}
public void startElement(String namespaceURI, String localName, String qName, Attributes atts)
throws SAXException {
try {
// we output the remaining text
if (!counting) {
writer.write(getText());
accumulator.setLength(0);
}
if (!counting) {
writer.write("<" + qName);
int length = atts.getLength();
// Process each attribute
for (int i = 0; i < length; i++) {
// Get names and values for each attribute
String name = atts.getQName(i);
String value = atts.getValue(i);
if ((name != null) && (value != null)) {
writer.write(" " + name + "=\"" + value + "\"");
}
}
writer.write(">");
}
if (qName.equals("description")) {
offset = 0;
counting = true;
} else if (qName.equals("patent-document")) {
counting = false;
}
} catch (Exception e) {
// e.printStackTrace();
throw new GrobidException("An exception occured while running Grobid.", e);
}
}