InputStream stream, ContentHandler handler,
Metadata metadata, ParseContext context)
throws IOException, SAXException, TikaException {
PDDocument pdfDocument = null;
TemporaryResources tmp = new TemporaryResources();
//config from context, or default if not set via context
PDFParserConfig localConfig = context.get(PDFParserConfig.class, defaultConfig);
try {
// PDFBox can process entirely in memory, or can use a temp file
// for unpacked / processed resources
// Decide which to do based on if we're reading from a file or not already
TikaInputStream tstream = TikaInputStream.cast(stream);
if (tstream != null && tstream.hasFile()) {
// File based, take that as a cue to use a temporary file
RandomAccess scratchFile = new RandomAccessFile(tmp.createTemporaryFile(), "rw");
if (localConfig.getUseNonSequentialParser() == true) {
pdfDocument = PDDocument.loadNonSeq(new CloseShieldInputStream(stream), scratchFile);
} else {
pdfDocument = PDDocument.load(new CloseShieldInputStream(stream), scratchFile, true);
}
} else {
// Go for the normal, stream based in-memory parsing
if (localConfig.getUseNonSequentialParser() == true) {
pdfDocument = PDDocument.loadNonSeq(new CloseShieldInputStream(stream), new RandomAccessBuffer());
} else {
pdfDocument = PDDocument.load(new CloseShieldInputStream(stream), true);
}
}
if (pdfDocument.isEncrypted()) {
String password = null;
// Did they supply a new style Password Provider?
PasswordProvider passwordProvider = context.get(PasswordProvider.class);
if (passwordProvider != null) {
password = passwordProvider.getPassword(metadata);
}
// Fall back on the old style metadata if set
if (password == null && metadata.get(PASSWORD) != null) {
password = metadata.get(PASSWORD);
}
// If no password is given, use an empty string as the default
if (password == null) {
password = "";
}
try {
pdfDocument.decrypt(password);
} catch (Exception e) {
// Ignore
}
}
metadata.set(Metadata.CONTENT_TYPE, "application/pdf");
extractMetadata(pdfDocument, metadata);
if (handler != null) {
PDF2XHTML.process(pdfDocument, handler, context, metadata, localConfig);
}
} finally {
if (pdfDocument != null) {
pdfDocument.close();
}
tmp.dispose();
}
}