/**
* Parse any kind of document.
*
* @throws ApplicationException if there's no parser available for the type of resource.
* @param url - the URL to the document.
* @return an {@link IDocument} containing the fulltext and maybe metadata for the parsed
* document.
*/
public IDocument parse(final String url) throws ApplicationException {
ResourceParser parser = null;
if (EdocIndexMetadataFetcherTool.isEDocIndex(url)) {
parser = EdocParserImpl.getInstance();
} else if (getExtension(url).equals(EXT_PDF)) {
parser = PdfParserImpl.getInstance();
} else if (getExtension(url).equals(EXT_DOC)) {
parser = DocParserImpl.getInstance();
} else if (getExtension(url).equals(EXT_ODT)) {
parser = OdfParserImpl.getInstance();
} else if (getExtension(url).equals(EXT_XML)) {
parser = XmlParserImpl.getInstance();
} else if (getExtension(url).equals(EXT_HTM)
|| getExtension(url).equals(EXT_HTML)
|| getExtension(url).equals(EXT_XHTML)) {
parser = HtmlParserImpl.getInstance();
} else if (getExtension(url).equals(EXT_TXT)) {
parser = TxtParserImpl.getInstance();
}
if (parser != null) {
IDocument result = (IDocument) parser.parse("", url);
return result;
} else {
throw new ApplicationException(
"There's no parser available for this type of resource: " + getExtension(url));
}
}
public XmlParser newXmlParser(final File xmlFile, final Properties xmlProperties)
throws TransformerConfigurationException, ParserConfigurationException, SAXException,
IOException {
if (!xmlFile.exists()) {
throw new IllegalStateException(
String.format("The given xml file %s does not exist.", xmlFile.getAbsolutePath()));
}
final XmlParserImpl xmlParserImpl =
new XmlParserImpl(
xmlFile,
xmlProperties,
documentBuilderFactory.newDocumentBuilder(),
transformerFactory.newTransformer());
xmlParserImpl.open();
return xmlParserImpl;
}
