/**
* Creates a SAX XMLReader.
*
* @return <code>XMLReader</code> a SAX2 parser.
* @throws Exception if no parser can be created.
*/
protected XMLReader createParser() throws Exception {
XMLReader parser = null;
// Try using JAXP...
// Note we need JAXP 1.1, and if JAXP 1.0 is all that's
// available then the getXMLReader call fails and we skip
// to the hard coded default parser
try {
Class factoryClass = Class.forName("javax.xml.parsers.SAXParserFactory");
// MODIFIED: Added (Class[]) and (Object[]) cast sentences in "null" parameters
// to avoid warnings during compilation
// factory = SAXParserFactory.newInstance();
Method newParserInstance = factoryClass.getMethod("newInstance", (Class[]) null);
Object factory = newParserInstance.invoke(null, (Object[]) null);
// jaxpParser = factory.newSAXParser();
Method newSAXParser = factoryClass.getMethod("newSAXParser", (Class[]) null);
Object jaxpParser = newSAXParser.invoke(factory, (Object[]) null);
// parser = jaxpParser.getXMLReader();
Class parserClass = jaxpParser.getClass();
Method getXMLReader = parserClass.getMethod("getXMLReader", (Class[]) null);
parser = (XMLReader) getXMLReader.invoke(jaxpParser, (Object[]) null);
} catch (ClassNotFoundException e) {
// e.printStackTrace();
} catch (InvocationTargetException e) {
// e.printStackTrace();
} catch (NoSuchMethodException e) {
// e.printStackTrace();
} catch (IllegalAccessException e) {
// e.printStackTrace();
}
// Check to see if we got a parser yet, if not, try to use a
// hard coded default
if (parser == null) {
parser = XMLReaderFactory.createXMLReader("org.apache.xerces.parsers.SAXParser");
}
return parser;
}
/**
* Process one file.
*
* <p>\u0040param xmlFileName Input file name to check for part of speech/lemma mismatches..
*/
protected static void processOneFile(String xmlFileName) {
try {
// Report document being processed.
System.out.println(
"(" + ++currentDocNumber + "/" + docsToProcess + ") " + "processing " + xmlFileName);
// Create filter to strip <w> and <c>
// elements.
XMLFilter filter = new StripAllWordElementsFilter(XMLReaderFactory.createXMLReader());
// Strip path from input file name.
String strippedFileName = FileNameUtils.stripPathName(xmlFileName);
strippedFileName = FileNameUtils.changeFileExtension(strippedFileName, "");
// Generate output file name.
String xmlOutputFileName =
new File(outputDirectoryName, strippedFileName + ".xml").getAbsolutePath();
// Make sure output directory exists.
FileUtils.createPathForFile(xmlOutputFileName);
// Copy input xml to output xml,
// stripping <w> and <c> elements.
new FilterAdornedFile(xmlFileName, xmlOutputFileName, filter);
// Read it back and fix spacing.
String fixedXML = FileUtils.readTextFile(xmlOutputFileName, "utf-8");
fixedXML = fixedXML.replaceAll("(\\s+)", " ");
fixedXML = fixedXML.replaceAll(" ([\\.?!,;:\\)])", "\u00241");
fixedXML = fixedXML.replaceAll("\\( ", "(");
fixedXML = fixedXML.replaceAll("\u00b6 ", "\u00b6");
fixedXML = fixedXML.replaceAll("__NS1:", "");
fixedXML = fixedXML.replaceAll("__NS1", "");
/*
fixedXML =
fixedXML.replaceAll
(
"</__NS1:" ,
""
);
*/
// Emit unadorned XML.
SAXBuilder builder = new SAXBuilder();
Document document = builder.build(new StringReader(fixedXML));
new AdornedXMLWriter(document, xmlOutputFileName);
} catch (Exception e) {
System.out.println(" Error: " + e.getMessage());
e.printStackTrace();
}
}
