Java Code Examples for org.apache.pdfbox.pdmodel.PDPageTree#getCount()

public static List<PDImageXObject> getImageListFromPDF(PDDocument document,
        Integer startPage) throws Exception {
    List<PDImageXObject> imageList = new ArrayList<>();
    if (null != document) {
        PDPageTree pages = document.getPages();
        startPage = startPage == null ? 0 : startPage;
        int len = pages.getCount();
        if (startPage < len) {
            for (int i = startPage; i < len; ++i) {
                PDPage page = pages.get(i);
                Iterable<COSName> objectNames = page.getResources().getXObjectNames();
                for (COSName imageObjectName : objectNames) {
                    if (page.getResources().isImageXObject(imageObjectName)) {
                        imageList.add((PDImageXObject) page.getResources().getXObject(imageObjectName));
                    }
                }
            }
        }
    }
    return imageList;
}
 

public static void checkPdfSimilarity(PDDocument document1, PDDocument document2, float minSimilarity) throws IOException {
	PDPageTree samplePageTree = document1.getPages();
	PDPageTree checkPageTree = document2.getPages();

	assertEquals(checkPageTree.getCount(), samplePageTree.getCount());

	PDFRenderer sampleRenderer = new PDFRenderer(document1);
	PDFRenderer checkRenderer = new PDFRenderer(document2);

	for (int pageNumber = 0; pageNumber < checkPageTree.getCount(); pageNumber++) {
		BufferedImage sampleImage = sampleRenderer.renderImageWithDPI(pageNumber, DPI);
		BufferedImage checkImage = checkRenderer.renderImageWithDPI(pageNumber, DPI);
		
           // ImageIO.write(sampleImage, "png", new File("target\\sampleImage.png"));
           // ImageIO.write(checkImage, "png", new File("target\\checkImage.png"));
           
		float checkSimilarity = checkImageSimilarity(sampleImage, checkImage, CHECK_RESOLUTION);
		assertTrue(checkSimilarity >= minSimilarity, "The image similarity " + checkSimilarity + " is lower the allowed limit " + minSimilarity);
	}
}
 

private void removeImagesAlphaChannelUnsafe() {
    try {
        PDPageTree allPages = document.getDocumentCatalog().getPages();
        for (int i = 0; i < allPages.getCount(); i++) {
            PDPage page = allPages.get(i);
            processImagesFromResources(page.getResources());
        }
    } catch (Exception e) {
        e.printStackTrace();
    }
}
 

private void calculateObjectsInDocument(PDDocument document) throws IOException {
    this.pdfTextStripper = new PDFTextStripper();

    try {
        PDPageTree allPages = document.getDocumentCatalog().getPages();
        this.pageCount = allPages.getCount();
        for (int i = 0; i < allPages.getCount(); i++) {
            PDPage page = allPages.get(i);
            readObjectsOnPage(page);
            calculateTextLengthOnPage(document, i + 1);
        }
    } catch (Exception e) {
        e.printStackTrace();
    }
}
 

int determineSafe(PDDocument document, PDAnnotationWidget widget) throws IOException
{
    COSDictionary widgetObject = widget.getCOSObject();
    PDPageTree pages = document.getPages();
    for (int i = 0; i < pages.getCount(); i++)
    {
        for (PDAnnotation annotation : pages.get(i).getAnnotations())
        {
            COSDictionary annotationObject = annotation.getCOSObject();
            if (annotationObject.equals(widgetObject))
                return i;
        }
    }
    return -1;
}
 

/**
 * <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"));
    }
}
 

/**
 * Get previous page in the document.
 * 
 * @param document
 * @return {pageNum}
 */
private static int getPages(PDDocument document) {
	PDPageTree pages = document.getPages();
	return pages.getCount()-1;
}