Java Code Examples for org.apache.pdfbox.pdmodel.PDDocument#getDocumentCatalog()

/**
 * Extract the text from the form fields
 */
private void parseForm(PDDocument pdfDocument, StringBuffer content) throws IOException {
	PDDocumentCatalog docCatalog = pdfDocument.getDocumentCatalog();
	PDAcroForm acroForm = docCatalog.getAcroForm();

	if (acroForm == null)
		return;

	content.append("\n");

	List<PDField> fields = acroForm.getFields();
	log.debug("{} top-level fields were found on the form", fields.size());

	for (PDField field : fields) {
		content.append(field.getPartialName());
		content.append(" = ");
		content.append(field.getValueAsString());
		content.append(" \n ");
	}
}
 

void sanitize(RandomAccessRead source, OutputStream outputStream)
    throws IOException, BleachException {
  final PDDocument doc = getDocument(source);

  final PDDocumentCatalog docCatalog = doc.getDocumentCatalog();

  sanitizeNamed(doc, docCatalog.getNames());
  PDDocumentCatalogBleach catalogBleach = new PDDocumentCatalogBleach(this);
  catalogBleach.sanitize(docCatalog);
  sanitizeDocumentOutline(doc.getDocumentCatalog().getDocumentOutline());

  cosObjectBleach.sanitizeObjects(doc.getDocument().getObjects());

  doc.save(outputStream);
  doc.close();
}
 

public void setMetadata(PDDocument doc) throws Exception {
	PDDocumentCatalog catalog = doc.getDocumentCatalog();
	PDDocumentInformation info = doc.getDocumentInformation();
	GregorianCalendar cal = new GregorianCalendar();
	cal.setTime(now);
	XMPMetadata metadata = new XMPMetadata();
	XMPSchemaPDF pdfSchema = metadata.addPDFSchema();
	pdfSchema.setKeywords(info.getKeywords());
	pdfSchema.setProducer(info.getProducer());
	XMPSchemaBasic basicSchema = metadata.addBasicSchema();
	basicSchema.setModifyDate(cal);
	basicSchema.setCreateDate(cal);
	basicSchema.setCreatorTool(info.getCreator());
	basicSchema.setMetadataDate(cal);
	XMPSchemaDublinCore dcSchema = metadata.addDublinCoreSchema();
	dcSchema.setTitle(info.getTitle());
	dcSchema.addCreator("PDFBox");
	dcSchema.setDescription(info.getSubject());
	PDMetadata metadataStream = new PDMetadata(doc);
	metadataStream.importXMPMetadata(metadata);
	catalog.setMetadata(metadataStream);
}
 

/**
 * Imports OCProperties from source document to target document so hidden layers can still be
 * hidden after import.
 *
 * @param sourceDoc The source PDF document that contains the /OCProperties to be copied.
 * @throws IOException If an I/O error occurs.
 */
private void importOcProperties(PDDocument srcDoc) throws IOException
{
    PDDocumentCatalog srcCatalog = srcDoc.getDocumentCatalog();
    PDOptionalContentProperties srcOCProperties = srcCatalog.getOCProperties();
    if (srcOCProperties == null)
    {
        return;
    }

    PDDocumentCatalog dstCatalog = targetDoc.getDocumentCatalog();
    PDOptionalContentProperties dstOCProperties = dstCatalog.getOCProperties();

    if (dstOCProperties == null)
    {
        dstCatalog.setOCProperties(new PDOptionalContentProperties(
                (COSDictionary) cloner.cloneForNewDocument(srcOCProperties)));
    }
    else
    {
        cloner.cloneMerge(srcOCProperties, dstOCProperties);
    }
}
 

/**
 * <a href="https://stackoverflow.com/questions/46642994/how-to-create-pdf-package-using-pdfbox">
 * How to create pdf package using PdfBox?
 * </a>
 * <p>
 * This test implements the equivalent of the OP's code turning
 * a regular PDF into a portable collection.
 * </p>
 */
@Test
public void test() throws IOException {
    try (   InputStream resource = getClass().getResourceAsStream("/mkl/testarea/pdfbox2/sign/test.pdf"))
    {
        PDDocument pdDocument = Loader.loadPDF(resource);

        COSDictionary collectionDictionary = new COSDictionary();
        collectionDictionary.setName(COSName.TYPE, "Collection");
        collectionDictionary.setName("View", "T");
        PDDocumentCatalog catalog = pdDocument.getDocumentCatalog();
        catalog.getCOSObject().setItem("Collection", collectionDictionary);

        pdDocument.save(new File(RESULT_FOLDER, "test-collection.pdf"));
    }
}
 

/**
 * <a href="https://stackoverflow.com/questions/52059931/pdfbox-setvalue-for-multiple-pdtextfield">
 * PDFBox setValue for multiple PDTextField
 * </a>
 * <br/>
 * <a href="https://ufile.io/z8jzj">
 * testform.pdf
 * </a>
 * <p>
 * Cannot reproduce the issue.
 * </p>
 */
@Test
public void testFillLikeJuvi() throws IOException {
    try (   InputStream originalStream = getClass().getResourceAsStream("testform.pdf") ) {
        PDDocument document = Loader.loadPDF(originalStream);
        PDDocumentCatalog docCatalog = document.getDocumentCatalog();
        PDAcroForm acroForm = docCatalog.getAcroForm();

        PDTextField field = (PDTextField) acroForm.getField("Check1");
        field.setValue("1111");

        PDTextField field2 = (PDTextField) acroForm.getField("Check2");
        field2.setValue("2222");

        PDTextField field3 = (PDTextField) acroForm.getField("HelloWorld");
        field3.setValue("HelloWorld");

        document.save(new File(RESULT_FOLDER, "testform-filled.pdf"));
        document.close();
    }
}
 

/**
 * Method to check if the target image's colro space is present in the document's catalog
 * @param pdDocument {@link PDDocument} to check color profiles in
 * @param image {@link DSSDocument} image
 * @throws IOException in case of image reading error
 */
protected void checkColorSpace(PDDocument pdDocument, DSSDocument image) throws IOException {
	if (image != null) {
        PDDocumentCatalog catalog = pdDocument.getDocumentCatalog();
        List<PDOutputIntent> profiles = catalog.getOutputIntents();
        if (Utils.isCollectionEmpty(profiles)) {
        	LOG.warn("No color profile is present in the document. Not compatible with PDF/A");
        	return;
        }
			
		String colorSpaceName = getColorSpaceName(image);
   		if (COSName.DEVICECMYK.getName().equals(colorSpaceName) && isProfilePresent(profiles, RGB_PROFILE_NAME)) {
   			LOG.warn("A CMYK image will be added to an RGB color space PDF. Be aware: not compatible with PDF/A.");
   		} else if (COSName.DEVICERGB.getName().equals(colorSpaceName) && isProfilePresent(profiles, CMYK_PROFILE_NAME)) {
   			LOG.warn("An RGB image will be added to a CMYK color space PDF. Be aware: not compatible with PDF/A.");
   		}
	}
}
 

/**
     * <a href="https://stackoverflow.com/questions/46433388/pdfbox-could-not-find-font-helv">
     * PDFbox Could not find font: /Helv
     * </a>
     * <br/>
     * <a href="https://drive.google.com/file/d/0B2--NSDOiujoR3hOZFYteUl2UE0/view?usp=sharing">
     * 4.pdf
     * </a>
     * <p>
     * The cause is a combination of the OP and the source PDF not providing
     * a default appearance for the text field and PDFBox providing defaults
     * inconsequentially.
     * </p>
     * <p>
     * This is fixed here by setting the default appearance explicitly.
     * </p>
     */
    @Test
    public void testAddFieldLikeEugenePodoliako() throws IOException {
        try (   InputStream originalStream = getClass().getResourceAsStream("4.pdf") )
        {
            PDDocument pdf = Loader.loadPDF(originalStream);
            PDDocumentCatalog docCatalog = pdf.getDocumentCatalog();
            PDAcroForm acroForm = docCatalog.getAcroForm();
            PDPage page = pdf.getPage(0);

            PDTextField textBox = new PDTextField(acroForm);
            textBox.setPartialName("SampleField");
            acroForm.getFields().add(textBox);
            PDAnnotationWidget widget = textBox.getWidgets().get(0);
            PDRectangle rect = new PDRectangle(0, 0, 0, 0);
            widget.setRectangle(rect);
            widget.setPage(page);
//  Unnecessary code from OP
//            widget.setAppearance(acroForm.getFields().get(0).getWidgets().get(0).getAppearance());
//  Fix added to set default appearance accordingly
            textBox.setDefaultAppearance(acroForm.getFields().get(0).getCOSObject().getString("DA"));

            widget.setPrinted(false);

            page.getAnnotations().add(widget);

            acroForm.refreshAppearances();
            acroForm.flatten();
            pdf.save(new File(RESULT_FOLDER, "4-add-field.pdf"));
            pdf.close();
        }
    }
 

/**
 * <a href="https://stackoverflow.com/questions/55355800/acroform-text-field-not-align-to-right">
 * acroform text field not align to right
 * </a>
 * <br/>
 * <a href="https://drive.google.com/uc?id=1jFbsYGFOnx8EMiHgDsE8LQtfwJHSa5Gh&export=download">
 * form.pdf 
 * </a> as "formBee2.pdf"
 * <p>
 * Indeed, the way the OP does this, quadding does not apply.
 * But see {@link #testAlignLikeBeeImproved()}.
 * </p>
 */
@Test
public void testAlignLikeBee() throws IOException {
    try (   InputStream resource = getClass().getResourceAsStream("formBee2.pdf")    ) {
        PDDocument document = Loader.loadPDF(resource);
        PDDocumentCatalog documentCatalog = document.getDocumentCatalog();
        PDAcroForm acroForm = documentCatalog.getAcroForm();

        acroForm.getField("NewRentWithoutChargesChf").setValue("1.00");
        ((PDTextField) acroForm.getField("NewRentWithoutChargesChf")).setQ(PDVariableText.QUADDING_RIGHT);

        document.save(new File(RESULT_FOLDER, "formBee2-AlignLikeBee.pdf"));        
        document.close();
    }
}
 

/**
 * <a href="https://stackoverflow.com/questions/55355800/acroform-text-field-not-align-to-right">
 * acroform text field not align to right
 * </a>
 * <br/>
 * <a href="https://drive.google.com/uc?id=1jFbsYGFOnx8EMiHgDsE8LQtfwJHSa5Gh&export=download">
 * form.pdf 
 * </a> as "formBee2.pdf"
 * <p>
 * Indeed, in {@link #testAlignLikeBee()} quadding does not apply.
 * But by changing the order of field value setting and quadding
 * value setting it suddenly does apply.
 * </p>
 */
@Test
public void testAlignLikeBeeImproved() throws IOException {
    try (   InputStream resource = getClass().getResourceAsStream("formBee2.pdf")    ) {
        PDDocument document = Loader.loadPDF(resource);
        PDDocumentCatalog documentCatalog = document.getDocumentCatalog();
        PDAcroForm acroForm = documentCatalog.getAcroForm();

        ((PDTextField) acroForm.getField("NewRentWithoutChargesChf")).setQ(PDVariableText.QUADDING_RIGHT);
        acroForm.getField("NewRentWithoutChargesChf").setValue("1.00");

        document.save(new File(RESULT_FOLDER, "formBee2-AlignLikeBeeImproved.pdf"));        
        document.close();
    }
}
 

public static byte[] getParsableXFAForm(InputStream file)
{
    if (file == null)
        return null;
    PDDocument doc;
    PDDocumentCatalog catalog;
    PDAcroForm acroForm;

    PDXFAResource xfa;
    try
    {
        // String pass = null;
        doc = Loader.loadPDF(file);
        if (doc == null)
            return null;
        // flattenPDF(doc);
        doc.setAllSecurityToBeRemoved(true);
        // System.out.println("Security " + doc.isAllSecurityToBeRemoved());
        catalog = doc.getDocumentCatalog();
        if (catalog == null)
        {
            doc.close();
            return null;
        }
        acroForm = catalog.getAcroForm();
        if (acroForm == null)
        {
            doc.close();
            return null;
        }
        xfa = acroForm.getXFA();
        if (xfa == null)
        {
            doc.close();
            return null;
        }
        // TODO return byte[]
        byte[] xfaBytes = xfa.getBytes();
        doc.close();
        return xfaBytes;
    } catch (IOException e)
    {
        // handle IOException
        // happens when the file is corrupt.
        e.printStackTrace();
        System.out.println("XFAUtils-getParsableXFAForm-IOException");
        return null;
    }
}
 

public synchronized void setPdf(PDDocument pdf) 
  {
  	listImagePages.clear();
      if (pdf == null)
      	return ;
try 
{
	if (pdf.isEncrypted())
	{
		logger.info("Failed attempt at previewing an encrypted PDF");
		return ;
	}
	PDDocumentCatalog cat = pdf.getDocumentCatalog() ;
	@SuppressWarnings("unchecked")
	List<PDPage> pages = cat.getAllPages() ;
       if (pages != null && !pages.isEmpty()) 
       {
       	for (PDPage page : pages)
       	{
       		listImagePages.add(page.convertToImage()) ;
       		if (listImagePages.size() >= maxPageToPreview)
       			break ;
       	}
       } 
} 
catch (IOException e) 
{
	logger.error("Error occurred while opening the pdf document", e);
}
finally 
{
	if (pdf != null)
	{
		try 
		{
			pdf.close();
		} 
		catch (IOException ex) 
		{
			logger.error("Error occurred while closing the pdf document", ex);
		}
	}
}
      repaint();
  }