/**
* Delegates the call to the matching component parser.
*
* <p>Potential {@link RuntimeException}s, {@link IOException}s and {@link SAXException}s
* unrelated to the given input stream and content handler are automatically wrapped into {@link
* TikaException}s to better honor the {@link Parser} contract.
*/
public void parse(
InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context)
throws IOException, SAXException, TikaException {
Parser parser = getParser(metadata, context);
TemporaryResources tmp = new TemporaryResources();
try {
TikaInputStream taggedStream = TikaInputStream.get(stream, tmp);
TaggedContentHandler taggedHandler =
handler != null ? new TaggedContentHandler(handler) : null;
if (parser instanceof ParserDecorator) {
metadata.add(
"X-Parsed-By", ((ParserDecorator) parser).getWrappedParser().getClass().getName());
} else {
metadata.add("X-Parsed-By", parser.getClass().getName());
}
try {
parser.parse(taggedStream, taggedHandler, metadata, context);
} catch (RuntimeException e) {
throw new TikaException("Unexpected RuntimeException from " + parser, e);
} catch (IOException e) {
taggedStream.throwIfCauseOf(e);
throw new TikaException("TIKA-198: Illegal IOException from " + parser, e);
} catch (SAXException e) {
if (taggedHandler != null) taggedHandler.throwIfCauseOf(e);
throw new TikaException("TIKA-237: Illegal SAXException from " + parser, e);
}
} finally {
tmp.dispose();
}
}
public CompositeParser(
MediaTypeRegistry registry,
List<Parser> parsers,
Collection<Class<? extends Parser>> excludeParsers) {
if (excludeParsers == null || excludeParsers.isEmpty()) {
this.parsers = parsers;
} else {
this.parsers = new ArrayList<Parser>();
for (Parser p : parsers) {
if (!isExcluded(excludeParsers, p.getClass())) {
this.parsers.add(p);
}
}
}
this.registry = registry;
}