Java Code Examples for org.apache.pdfbox.pdmodel.PDPage#getAnnotations()

/**
 * Update the StructParents and StructParent values in a PDPage.
 *
 * @param page the new page
 * @param structParentOffset the offset which should be applied
 */
private void updateStructParentEntries(PDPage page, int structParentOffset) throws IOException
{
    if (page.getStructParents() >= 0)
    {
        page.setStructParents(page.getStructParents() + structParentOffset);
    }
    List<PDAnnotation> annots = page.getAnnotations();
    List<PDAnnotation> newannots = new ArrayList<PDAnnotation>();
    for (PDAnnotation annot : annots)
    {
        if (annot.getStructParent() >= 0)
        {
            annot.setStructParent(annot.getStructParent() + structParentOffset);
        }
        newannots.add(annot);
    }
    page.setAnnotations(newannots);
}
 

private void processAnnotations(PDPage imported) throws IOException
{
    List<PDAnnotation> annotations = imported.getAnnotations();
    for (PDAnnotation annotation : annotations)
    {
        if (annotation instanceof PDAnnotationLink)
        {
            PDAnnotationLink link = (PDAnnotationLink)annotation;   
            PDDestination destination = link.getDestination();
            if (destination == null && link.getAction() != null)
            {
                PDAction action = link.getAction();
                if (action instanceof PDActionGoTo)
                {
                    destination = ((PDActionGoTo)action).getDestination();
                }
            }
            if (destination instanceof PDPageDestination)
            {
                // TODO preserve links to pages within the splitted result  
                ((PDPageDestination) destination).setPage(null);
            }
        }
        // TODO preserve links to pages within the splitted result  
        annotation.setPage(null);
    }
}
 

void removeWidgets(PDField targetField) throws IOException {
    if (targetField instanceof PDTerminalField) {
        List<PDAnnotationWidget> widgets = ((PDTerminalField)targetField).getWidgets();
        for (PDAnnotationWidget widget : widgets) {
            PDPage page = widget.getPage();
            if (page != null) {
                List<PDAnnotation> annotations = page.getAnnotations();
                boolean removed = false;
                for (PDAnnotation annotation : annotations) {
                    if (annotation.getCOSObject().equals(widget.getCOSObject()))
                    {
                        removed = annotations.remove(annotation);
                        break;
                    }
                }
                if (!removed)
                    System.out.println("Inconsistent annotation definition: Page annotations do not include the target widget.");
            } else {
                System.out.println("Widget annotation does not have an associated page; cannot remove widget.");
                // TODO: In this case iterate all pages and try to find and remove widget in all of them
            }
        }
    } else if (targetField instanceof PDNonTerminalField) {
        List<PDField> childFields = ((PDNonTerminalField)targetField).getChildren();
        for (PDField field : childFields)
            removeWidgets(field);
    } else {
        System.out.println("Target field is neither terminal nor non-terminal; cannot remove widgets.");
    }
}
 

/**
 * <a href="https://stackoverflow.com/questions/45812696/pdfbox-delete-comment-maintain-strikethrough">
 * PDFBox delete comment maintain strikethrough
 * </a>
 * <br/>
 * <a href="https://expirebox.com/files/3d955e6df4ca5874c38dbf92fc43b5af.pdf">
 * only_fields.pdf
 * </a>
 * <a href="https://file.io/DTvqhC">
 * (alternative download)
 * </a>
 * <p>
 * Due to a bug in the <code>COSArrayList</code> usage for page annotations,
 * the indirect reference to the annotation in question is not removed from
 * the actual page annotations array.
 * </p>
 */
@Test
public void testRemoveLikeStephan() throws IOException {
    try (InputStream resource = getClass().getResourceAsStream("only_fields.pdf")) {
        PDDocument document = Loader.loadPDF(resource);
        List<PDAnnotation> annotations = new ArrayList<>();
        PDPageTree allPages = document.getDocumentCatalog().getPages();

        for (int i = 0; i < allPages.getCount(); i++) {
            PDPage page = allPages.get(i);
            annotations = page.getAnnotations();

            List<PDAnnotation> annotationToRemove = new ArrayList<PDAnnotation>();

            if (annotations.size() < 1)
                continue;
            else {
                for (PDAnnotation annotation : annotations) {

                    if (annotation.getContents() != null
                            && annotation.getContents().equals("Sample Strikethrough")) {
                        annotationToRemove.add(annotation);
                    }
                }
                annotations.removeAll(annotationToRemove);
            }
        }

        document.save(new File(RESULT_FOLDER, "only_fields-removeLikeStephan.pdf"));
    }
}
 

/**
 * <a href="https://stackoverflow.com/questions/45812696/pdfbox-delete-comment-maintain-strikethrough">
 * PDFBox delete comment maintain strikethrough
 * </a>
 * <br/>
 * <a href="https://expirebox.com/files/3d955e6df4ca5874c38dbf92fc43b5af.pdf">
 * only_fields.pdf
 * </a>
 * <a href="https://file.io/DTvqhC">
 * (alternative download)
 * </a>
 * <p>
 * The OP only wanted the comment removed, not the strike-through. Thus, we must
 * not remove the annotation but merely the comment building attributes.
 * </p>
 */
@Test
public void testRemoveLikeStephanImproved() throws IOException {
    final COSName POPUP = COSName.getPDFName("Popup");
    try (InputStream resource = getClass().getResourceAsStream("only_fields.pdf")) {
        PDDocument document = Loader.loadPDF(resource);
        List<PDAnnotation> annotations = new ArrayList<>();
        PDPageTree allPages = document.getDocumentCatalog().getPages();

        List<COSObjectable> objectsToRemove = new ArrayList<>();

        for (int i = 0; i < allPages.getCount(); i++) {
            PDPage page = allPages.get(i);
            annotations = page.getAnnotations();

            for (PDAnnotation annotation : annotations) {
                if ("StrikeOut".equals(annotation.getSubtype()))
                {
                    COSDictionary annotationDict = annotation.getCOSObject();
                    COSBase popup = annotationDict.getItem(POPUP);
                    annotationDict.removeItem(POPUP);
                    annotationDict.removeItem(COSName.CONTENTS); // plain text comment
                    annotationDict.removeItem(COSName.RC);       // rich text comment
                    annotationDict.removeItem(COSName.T);        // author

                    if (popup != null)
                        objectsToRemove.add(popup);
                }
            }

            annotations.removeAll(objectsToRemove);
        }

        document.save(new File(RESULT_FOLDER, "only_fields-removeImproved.pdf"));
    }
}
 

private void sanitizePage(PDPage page) throws IOException {
  for (PDAnnotation annotation : page.getAnnotations()) {
    annotationBleach.sanitizeAnnotation(annotation);
    sanitizePageActions(page.getActions());
  }
}