I am currently using the Apache FOP library to generate PDF's. I want these PDF's protected from copy-pasting, so people would have to use actual OCR libraries (or manual typing) to get the information on the PDF.
FOP apparently offers some security, which then is added as meta-data on the PDF, to protect from things like printing or copying, but this doesn't seem to work properly (can't disable the copy-pasting when printing is enabled, etc).
A possibility which seemed straight forward to me is basically somehow transforming all the text on the PDF's to images, but I can't find any information on the matter.
Obviously I don't care if the PDF is searchable or not. I just want to prevent people from copy-pasting while they should still be able to print it.
My current FOP code:
private static FopFactory fopFactory;
private static FopFactory initializeFactory() throws IOException,
SAXException {
if (fopFactory == null) {
File f = new File(SettingUtil.getSetting(LetterGeneratorSettings.FOP_CONFIG_LOCATION));
fopFactory = FopFactory.newInstance(f);
}
return fopFactory;
}
public static File generatePDFFromXML(File fopTemplate, File xmlSource,
File resultFileLocation) throws IOException {
try {
initializeFactory();
URL url = fopTemplate.toURI().toURL();
// creation of transform source
StreamSource transformSource = new StreamSource(url.openStream());
// create an instance of fop factory
// a user agent is needed for transformation
FOUserAgent foUserAgent = fopFactory.newFOUserAgent();
foUserAgent.getRendererOptions().put("encryption-params",
getEncryptionParams());
// to store output
ByteArrayOutputStream pdfoutStream = new ByteArrayOutputStream();
StreamSource source = new StreamSource(new ByteArrayInputStream(IOUtils.toByteArray(new FileInputStream(xmlSource))));
Transformer xslfoTransformer;
try {
TransformerFactory transfact = TransformerFactory.newInstance();
xslfoTransformer = transfact.newTransformer(transformSource);
// Construct fop with desired output format
Fop fop;
try {
fop = fopFactory.newFop(MimeConstants.MIME_PDF, foUserAgent, pdfoutStream);
// Resulting SAX events (the generated FO)
// must be piped through to FOP
Result res = new SAXResult(fop.getDefaultHandler());
// Start XSLT transformation and FOP processing
try {
// everything will happen here..
xslfoTransformer.transform(source, res);
// if you want to save PDF file use the following code
OutputStream out = new java.io.FileOutputStream(resultFileLocation);
out = new java.io.BufferedOutputStream(out);
FileOutputStream str = new FileOutputStream(resultFileLocation);
str.write(pdfoutStream.toByteArray());
str.close();
out.close();
} catch (TransformerException e) {
e.printStackTrace();
}
} catch (FOPException e) {
e.printStackTrace();
}
} catch (TransformerConfigurationException e) {
e.printStackTrace();
} catch (TransformerFactoryConfigurationError e) {
e.printStackTrace();
}
return resultFileLocation;
} catch (Exception ex) {
throw new IOException(ex);
}
}
private static PDFEncryptionParams getEncryptionParams() {
return new PDFEncryptionParams(null,
SettingUtil.getSetting(LetterGeneratorSettings.PDF_PASSWORD),
true, false, false, false, false);
}
The following is the contents of my fopconfig.xml
<fop version="1.0">
<!-- Strict user configuration -->
<strict-configuration>false</strict-configuration>
<!-- Strict FO validation -->
<strict-validation>false</strict-validation>
<!-- Base URL for resolving relative URLs -->
<base>./</base>
<!-- Font Base URL for resolving relative font URLs -->
<font-base>./</font-base>
<!-- Source resolution in dpi (dots/pixels per inch) for determining the size of pixels in SVG and bitmap images, default: 72dpi -->
<source-resolution>72</source-resolution>
<!-- Target resolution in dpi (dots/pixels per inch) for specifying the target resolution for generated bitmaps, default: 72dpi -->
<target-resolution>72</target-resolution>
<!-- default page-height and page-width, in case
value is specified as auto -->
<default-page-settings height="11in" width="8.26in"/>
<!-- etc. etc..... -->
</fop>
