/**
* 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();
}
}
void doOCROnCurrentPage() throws IOException, TikaException, SAXException {
if (config.getOCRStrategy().equals(NO_OCR)) {
return;
}
TesseractOCRConfig tesseractConfig =
context.get(TesseractOCRConfig.class, DEFAULT_TESSERACT_CONFIG);
TesseractOCRParser tesseractOCRParser = new TesseractOCRParser();
if (!tesseractOCRParser.hasTesseract(tesseractConfig)) {
throw new TikaException(
"Tesseract is not available. "
+ "Please set the OCR_STRATEGY to NO_OCR or configure Tesseract correctly");
}
PDFRenderer renderer = new PDFRenderer(pdDocument);
TemporaryResources tmp = new TemporaryResources();
try {
BufferedImage image = renderer.renderImage(pageIndex, 2.0f, config.getOCRImageType());
Path tmpFile = tmp.createTempFile();
try (OutputStream os = Files.newOutputStream(tmpFile)) {
// TODO: get output format from TesseractConfig
ImageIOUtil.writeImage(image, config.getOCRImageFormatName(), os, config.getOCRDPI());
}
try (InputStream is = TikaInputStream.get(tmpFile)) {
tesseractOCRParser.parseInline(is, xhtml, tesseractConfig);
}
} catch (IOException e) {
handleCatchableIOE(e);
} catch (SAXException e) {
throw new IOExceptionWithCause("error writing OCR content from PDF", e);
} finally {
tmp.dispose();
}
}
