Java Code Examples for com.itextpdf.text.pdf.PdfReader#getPageN()

/**
 * <a href="http://stackoverflow.com/questions/43870545/filling-a-pdf-with-itextsharp-and-then-hiding-the-base-layer">
 * Filling a PDF with iTextsharp and then hiding the base layer
 * </a>
 * <p>
 * This test shows how to remove all content.
 * </p>
 */
@Test
public void testRemoveContent() throws IOException, DocumentException
{
    try (   InputStream resource = getClass().getResourceAsStream("document.pdf");
            OutputStream result = new FileOutputStream(new File(RESULT_FOLDER, "document-removedContent.pdf")))
    {
        PdfReader pdfReader = new PdfReader(resource);
        for (int page = 1; page <= pdfReader.getNumberOfPages(); page++)
        {
            PdfDictionary pageDictionary = pdfReader.getPageN(page);
            pageDictionary.remove(PdfName.CONTENTS);
        }
        new PdfStamper(pdfReader, result).close();
    }
}
 

/**
 * <a href="http://stackoverflow.com/questions/34394199/i-cant-rotate-my-page-from-existing-pdf">
 * I can't rotate my page from existing PDF
 * </a>
 * <p>
 * Switching between portrait and landscape like this obviously will cut off some parts of the page.
 * </p>
 */
@Test
public void testSwitchOrientation() throws DocumentException, IOException
{
    try (InputStream resourceStream = getClass().getResourceAsStream("/mkl/testarea/itext5/extract/n2013.00849449.pdf"))
    {
        PdfReader reader = new PdfReader(resourceStream);
        int n = reader.getNumberOfPages();
        PdfDictionary pageDict;
        for (int i = 1; i <= n; i++) {
            Rectangle rect = reader.getPageSize(i);
            Rectangle crop = reader.getCropBox(i);
            pageDict = reader.getPageN(i);
            pageDict.put(PdfName.MEDIABOX, new PdfArray(new float[] {rect.getBottom(), rect.getLeft(), rect.getTop(), rect.getRight()}));
            pageDict.put(PdfName.CROPBOX, new PdfArray(new float[] {crop.getBottom(), crop.getLeft(), crop.getTop(), crop.getRight()}));
        }
        PdfStamper stamper = new PdfStamper(reader, new FileOutputStream(new File(RESULT_FOLDER, "n2013.00849449-switch.pdf")));
        stamper.close();
        reader.close();
    }
}
 

/**
 * This method edits the immediate contents of a page, i.e. its content stream.
 * It explicitly does not descent into form xobjects, patterns, or annotations.
 */
public void editPage(PdfStamper pdfStamper, int pageNum) throws IOException {
    PdfReader pdfReader = pdfStamper.getReader();
    PdfDictionary page = pdfReader.getPageN(pageNum);
    byte[] pageContentInput = ContentByteUtils.getContentBytesForPage(pdfReader, pageNum);
    page.remove(PdfName.CONTENTS);
    editContent(pageContentInput, page.getAsDict(PdfName.RESOURCES), pdfStamper.getUnderContent(pageNum));
}
 

/**
 * <a href="http://stackoverflow.com/questions/37275267/how-to-make-pdf-annotation-as-read-only-using-itext">
 * how to make pdf annotation as read only using itext?
 * </a>
 * <br/>
 * test-annotated.pdf <i>simple PDF with sticky note</i>
 * 
 * <p>
 * This test shows how to set the read-only flags of all annotations of a document.
 * </p>
 */
@Test
public void testMarkAnnotationsReadOnly() throws IOException, DocumentException
{
    try (   InputStream resourceStream = getClass().getResourceAsStream("test-annotated.pdf");
            OutputStream outputStream = new FileOutputStream(new File(RESULT_FOLDER, "test-annotated-ro.pdf"))    )
    {
        PdfReader reader = new PdfReader(resourceStream);
        PdfStamper stamper = new PdfStamper(reader, outputStream);

        for (int page = 1; page <= reader.getNumberOfPages(); page++)
        {
            PdfDictionary pageDictionary = reader.getPageN(page);
            PdfArray annotationArray = pageDictionary.getAsArray(PdfName.ANNOTS);
            if (annotationArray == null)
                continue;
            for (PdfObject object : annotationArray)
            {
                PdfObject directObject = PdfReader.getPdfObject(object);
                if (directObject instanceof PdfDictionary)
                {
                    PdfDictionary annotationDictionary = (PdfDictionary) directObject;
                    PdfNumber flagsNumber = annotationDictionary.getAsNumber(PdfName.F);
                    int flags = flagsNumber != null ? flagsNumber.intValue() : 0;
                    flags |= PdfAnnotation.FLAGS_READONLY;
                    annotationDictionary.put(PdfName.F, new PdfNumber(flags));
                }
            }
        }

        stamper.close();
    }
}
 

@Test
public void testWithStamper() throws DocumentException, IOException
{
    InputStream resourceStream = getClass().getResourceAsStream("test.pdf");
    try
    {
        PdfReader reader = new PdfReader(resourceStream);
        PdfStamper stamper = new PdfStamper(reader, new FileOutputStream(new File(RESULT_FOLDER, "test-trimmed-stamper.pdf")));
        
        // Go through all pages
        int n = reader.getNumberOfPages();
        for (int i = 1; i <= n; i++)
        {
            Rectangle pageSize = reader.getPageSize(i);
            Rectangle rect = getOutputPageSize(pageSize, reader, i);

            PdfDictionary page = reader.getPageN(i);
            page.put(PdfName.CROPBOX, new PdfArray(new float[]{rect.getLeft(), rect.getBottom(), rect.getRight(), rect.getTop()}));
            stamper.markUsed(page);
        }
        stamper.close();
    }
    finally
    {
        if (resourceStream != null)
            resourceStream.close();
    }
}
 

@Test
public void testWithStamperTopBottom() throws DocumentException, IOException
{
    InputStream resourceStream = getClass().getResourceAsStream("test.pdf");
    try
    {
        PdfReader reader = new PdfReader(resourceStream);
        PdfStamper stamper = new PdfStamper(reader, new FileOutputStream(new File(RESULT_FOLDER, "test-trimmed-stamper-top-bottom.pdf")));
        
        // Go through all pages
        int n = reader.getNumberOfPages();
        for (int i = 1; i <= n; i++)
        {
            Rectangle pageSize = reader.getPageSize(i);
            Rectangle rect = getOutputPageSize2(pageSize, reader, i);

            PdfDictionary page = reader.getPageN(i);
            page.put(PdfName.CROPBOX, new PdfArray(new float[]{rect.getLeft(), rect.getBottom(), rect.getRight(), rect.getTop()}));
            stamper.markUsed(page);
        }
        stamper.close();
    }
    finally
    {
        if (resourceStream != null)
            resourceStream.close();
    }
}
 

@Test
public void testWithStamperCentered() throws DocumentException, IOException
{
    InputStream resourceStream = getClass().getResourceAsStream("test.pdf");
    try
    {
        PdfReader reader = new PdfReader(resourceStream);
        PdfStamper stamper = new PdfStamper(reader, new FileOutputStream(new File(RESULT_FOLDER, "test-trimmed-stamper-centered.pdf")));
        
        // Go through all pages
        int n = reader.getNumberOfPages();
        for (int i = 1; i <= n; i++)
        {
            Rectangle pageSize = reader.getPageSize(i);
            Rectangle rect = getOutputPageSize3(pageSize, reader, i);

            PdfDictionary page = reader.getPageN(i);
            page.put(PdfName.CROPBOX, new PdfArray(new float[]{rect.getLeft(), rect.getBottom(), rect.getRight(), rect.getTop()}));
            stamper.markUsed(page);
        }
        stamper.close();
    }
    finally
    {
        if (resourceStream != null)
            resourceStream.close();
    }
}
 

@Test
public void testWithStamperExtFinder() throws DocumentException, IOException
{
    InputStream resourceStream = getClass().getResourceAsStream("test.pdf");
    try
    {
        PdfReader reader = new PdfReader(resourceStream);
        PdfStamper stamper = new PdfStamper(reader, new FileOutputStream(new File(RESULT_FOLDER, "test-trimmed-stamper-ext.pdf")));
        
        // Go through all pages
        int n = reader.getNumberOfPages();
        for (int i = 1; i <= n; i++)
        {
            Rectangle pageSize = reader.getPageSize(i);
            Rectangle rect = getOutputPageSize4(pageSize, reader, i);

            PdfDictionary page = reader.getPageN(i);
            page.put(PdfName.CROPBOX, new PdfArray(new float[]{rect.getLeft(), rect.getBottom(), rect.getRight(), rect.getTop()}));
            stamper.markUsed(page);
        }
        stamper.close();
    }
    finally
    {
        if (resourceStream != null)
            resourceStream.close();
    }
}
 

/**
 * This methods creates a copy of the source document containing each page twice,
 * once with the cropbox limited to the left half page, once to the right one.
 */
void splitIntoHalfPages(InputStream source, File target) throws IOException, DocumentException
{
    final PdfReader reader = new PdfReader(source);
    
    try (   OutputStream targetStream = new FileOutputStream(target)    )
    {
        Document document = new Document();
        PdfCopy copy = new PdfCopy(document, targetStream);
        document.open();

        for (int page = 1; page <= reader.getNumberOfPages(); page++)
        {
            PdfDictionary pageN = reader.getPageN(page);
            Rectangle cropBox = reader.getCropBox(page);
            PdfArray leftBox = new PdfArray(new float[]{cropBox.getLeft(), cropBox.getBottom(), (cropBox.getLeft() + cropBox.getRight()) / 2.0f, cropBox.getTop()});
            PdfArray rightBox = new PdfArray(new float[]{(cropBox.getLeft() + cropBox.getRight()) / 2.0f, cropBox.getBottom(), cropBox.getRight(), cropBox.getTop()});

            PdfImportedPage importedPage = copy.getImportedPage(reader, page);
            pageN.put(PdfName.CROPBOX, leftBox);
            copy.addPage(importedPage);
            pageN.put(PdfName.CROPBOX, rightBox);
            copy.addPage(importedPage);
        }
        
        document.close();
    }
    finally
    {
        reader.close();
    }
}
 

/**
 * <a href="https://stackoverflow.com/questions/48601115/pdf-shrink-causing-change-in-orientation">
 * PDF Shrink causing change in Orientation
 * </a>
 * <p>
 * Sample.PDF - retrieved via e-mail
 * </p>
 * <p>
 * This issue is just another result of iText adding rotations to the
 * transformation matrices at the start of undercontent and overcontent
 * of rotated pages: Due to the nature of the literal the OP adds to
 * the undercontent, this rotation bleeds through and also affects the
 * original content.
 * </p>
 */
@Test
public void testShrinkSample() throws IOException, DocumentException {
    float xPercentage = 0.3F;
    float yPercentage = 0.6F;
    try (   InputStream resource = getClass().getResourceAsStream("Sample.PDF");
            OutputStream result = new FileOutputStream(new File(RESULT_FOLDER, "Sample-shrunken.PDF"))) {
        PdfReader reader = new PdfReader(resource);
        PdfStamper stamper = new PdfStamper(reader, result);
        //vvv
        stamper.setRotateContents(false);
        //^^^
        for (int p = 1; p <= 1; p++) {
            float offsetX = (reader.getPageSize(p).getWidth() * (1 - xPercentage)) / 2;
            float offsetY = (reader.getPageSize(p).getHeight() * (1 - yPercentage)) / 2;
            PdfDictionary page;
            PdfArray crop;
            PdfArray media;
            page = reader.getPageN(p);
            System.out.println("reader.getPateRoatation-->"+reader.getPageRotation(p));
            media = page.getAsArray(PdfName.CROPBOX);
            if (media == null) {
                media = page.getAsArray(PdfName.MEDIABOX);
            }
            crop = new PdfArray();
            crop.add(new PdfNumber(0));
            crop.add(new PdfNumber(0));
            crop.add(new PdfNumber(media.getAsNumber(2).floatValue()));
            crop.add(new PdfNumber(media.getAsNumber(3).floatValue()));
            page.put(PdfName.MEDIABOX, crop);
            page.put(PdfName.CROPBOX, crop);
            Rectangle mediabox = reader.getPageSize(p);
            stamper.getUnderContent(p).setLiteral(
                    String.format("\nq %s %s %s %s %s %s cm\nq\n",
                    xPercentage, mediabox.getLeft(),mediabox.getBottom(), yPercentage,  offsetX, offsetY));
            stamper.getOverContent(p).setLiteral("\nQ\nQ\n");           
        }
        stamper.close();
        reader.close();
    }
}
 

/**
 * <a href="http://stackoverflow.com/questions/41090131/searching-pdf-for-a-specific-string-in-javascript-action-in-itext">
 * Searching PDF for a specific string in JavaScript action in iText
 * </a>
 * <br/>
 * <a href="http://www21.zippyshare.com/v/RDdOJI97/file.html">
 * file.pdf
 * </a>
 * <p>
 * This test shows how to process the immediate JavaScript code in annotation actions.
 * </p> 
 */
@Test
public void testSearchJsActionInFile() throws IOException
{
    try (   InputStream resource = getClass().getResourceAsStream("file.pdf")   )
    {
        System.out.println("file.pdf - Looking for special JavaScript actions.");
        // Reads and parses a PDF document
        PdfReader reader = new PdfReader(resource);

        // For each PDF page
        for (int i = 1; i <= reader.getNumberOfPages(); i++)
        {
            System.out.printf("\nPage %d\n", i);
            // Get a page a PDF page
            PdfDictionary page = reader.getPageN(i);
            // Get all the annotations of page i
            PdfArray annotsArray = page.getAsArray(PdfName.ANNOTS);

            // If page does not have annotations
            if (annotsArray == null)
            {
                System.out.printf("No annotations.\n", i);
                continue;
            }

            // For each annotation
            for (int j = 0; j < annotsArray.size(); ++j)
            {
                System.out.printf("Annotation %d - ", j);

                // For current annotation
                PdfDictionary curAnnot = annotsArray.getAsDict(j);

                // check if has JS as described below
                PdfDictionary annotationAction = curAnnot.getAsDict(PdfName.A);
                if (annotationAction == null)
                {
                    System.out.print("no action");
                }
                // test if it is a JavaScript action
                else if (PdfName.JAVASCRIPT.equals(annotationAction.get(PdfName.S)))
                {
                    PdfObject scriptObject = annotationAction.getDirectObject(PdfName.JS);
                    if (scriptObject == null)
                    {
                        System.out.print("missing JS entry");
                        continue;
                    }
                    final String script;
                    if (scriptObject.isString())
                        script = ((PdfString)scriptObject).toUnicodeString();
                    else if (scriptObject.isStream())
                    {
                        try (   ByteArrayOutputStream baos = new ByteArrayOutputStream()    )
                        {
                            ((PdfStream)scriptObject).writeContent(baos);
                            script = baos.toString("ISO-8859-1");
                        }
                    }
                    else
                    {
                        System.out.println("malformed JS entry");
                        continue;
                    }

                    if (script.contains("if (this.hostContainer) { try {"))
                        System.out.print("contains test string - ");

                    System.out.printf("\n---\n%s\n---", script);
                    // what here?
                }
                else
                {
                    System.out.print("no JavaScript action");
                }
                System.out.println();
            }
        }
    }
}
 

/**
 * <a href="https://stackoverflow.com/questions/49370352/how-do-i-get-a-get-destination-page-of-a-link-in-pdf-file">
 * How do I get a get destination page of a link in PDF file?
 * </a>
 * <br/>
 * local-link.pdf - output of the test {@link CreateLink}.
 * <p>
 * This test shows how to access data of the target page, once by
 * directly reading from the page dictionary referenced from the
 * link destination, once by first determining the page number and
 * then using {@link PdfReader} helper methods.
 * </p>
 */
@Test
public void testDetermineTargetPage() throws IOException {
    try (   InputStream src = getClass().getResourceAsStream("local-link.pdf")  ) {
        PdfReader reader = new PdfReader(src);
        PdfDictionary page = reader.getPageN(1);
        PdfArray annots = page.getAsArray(PdfName.ANNOTS); 
        for (int i = 0; i < annots.size(); i++) {
            PdfDictionary annotation = annots.getAsDict(i);
            if (PdfName.LINK.equals(annotation.getAsName(PdfName.SUBTYPE))) {
                PdfArray d = annotation.getAsArray(PdfName.DEST);
                if (d == null) {
                    PdfDictionary action = annotation.getAsDict(PdfName.A);
                    if (action != null)
                        d = action.getAsArray(PdfName.D);
                }
                    
                if (d != null && d.size() > 0) {
                    System.out.println("Next destination -");
                    PdfIndirectReference pageReference = d.getAsIndirectObject(0);

                    // Work with target dictionary directly
                    PdfDictionary pageDict = d.getAsDict(0);
                    PdfArray boxArray = pageDict.getAsArray(PdfName.CROPBOX);
                    if (boxArray == null) {
                        boxArray = pageDict.getAsArray(PdfName.MEDIABOX);
                    }
                    Rectangle box = PdfReader.getNormalizedRectangle(boxArray);
                    System.out.printf("* Target page object %s has cropbox %s\n", pageReference, box);

                    // Work via page number
                    for (int pageNr = 1; pageNr <= reader.getNumberOfPages(); pageNr++) {
                        PRIndirectReference pp = reader.getPageOrigRef(pageNr);
                        if (pp.getGeneration() == pageReference.getGeneration() && pp.getNumber() == pageReference.getNumber()) {
                            System.out.printf("* Target page %s has cropbox %s\n", pageNr, reader.getCropBox(pageNr));
                            break;
                        }
                    }
                }
            }
        }
    }
}
 

private static void cropMultipliedFile(File source, CropJob cropJob) throws DocumentException,
    IOException {

    PdfReader reader = new PdfReader(source.getAbsolutePath());
    PdfStamper stamper = new PdfStamper(reader, new FileOutputStream(cropJob.getDestinationFile()));
    stamper.setMoreInfo(cropJob.getSourceMetaInfo());

    PdfDictionary pageDict;
    int newPageNumber = 1;
    for (int origPageNumber = 1; origPageNumber <= cropJob.getSourcePageCount(); origPageNumber++) {
        SingleCluster cluster = cropJob.getClusterCollection().getSingleCluster(origPageNumber);

        // if no crop was selected do nothing
        if (cluster.getRatiosList().size() == 0) {
            newPageNumber++;
            continue;
        }

        for (Float[] ratios : cluster.getRatiosList()) {

            pageDict = reader.getPageN(newPageNumber);

            List<Rectangle> boxes = new ArrayList<Rectangle>();
            boxes.add(reader.getBoxSize(newPageNumber, "media"));
            boxes.add(reader.getBoxSize(newPageNumber, "crop"));
            int rotation = reader.getPageRotation(newPageNumber);

            Rectangle scaledBox = calculateScaledRectangle(boxes, ratios, rotation);

            PdfArray scaleBoxArray = new PdfArray();
            scaleBoxArray.add(new PdfNumber(scaledBox.getLeft()));
            scaleBoxArray.add(new PdfNumber(scaledBox.getBottom()));
            scaleBoxArray.add(new PdfNumber(scaledBox.getRight()));
            scaleBoxArray.add(new PdfNumber(scaledBox.getTop()));

            pageDict.put(PdfName.CROPBOX, scaleBoxArray);
            pageDict.put(PdfName.MEDIABOX, scaleBoxArray);
            // increment the pagenumber
            newPageNumber++;
        }
        int[] range = new int[2];
        range[0] = newPageNumber - 1;
        range[1] = cropJob.getSourcePageCount() + (newPageNumber - origPageNumber);
        SimpleBookmark.shiftPageNumbers(cropJob.getSourceBookmarks(), cluster.getRatiosList().size() - 1, range);
    }
    stamper.setOutlines(cropJob.getSourceBookmarks());
    stamper.close();
    reader.close();
}
 

private static void cropMultipliedFile(final CropDefinition cropDefinition, final File multipliedDocument,
                                       final PdfMetaInformation pdfMetaInformation) throws DocumentException, IOException {

    PdfReader reader = new PdfReader(multipliedDocument.getAbsolutePath());

    PdfStamper stamper = new PdfStamper(reader, new FileOutputStream(cropDefinition.getDestinationFile()));
    stamper.setMoreInfo(pdfMetaInformation.getSourceMetaInfo());

    PdfDictionary pageDict;
    int newPageNumber = 1;

    for (int sourcePageNumber = 1; sourcePageNumber <= pdfMetaInformation.getSourcePageCount(); sourcePageNumber++) {

        List<Float[]> rectangleList = cropDefinition.getRectanglesForPage(sourcePageNumber);

        // if no crop was selected do nothing
        if (rectangleList.isEmpty()) {
            newPageNumber++;
            continue;
        }

        for (Float[] ratios : rectangleList) {

            pageDict = reader.getPageN(newPageNumber);

            List<Rectangle> boxes = new ArrayList<Rectangle>();
            boxes.add(reader.getBoxSize(newPageNumber, "media"));
            boxes.add(reader.getBoxSize(newPageNumber, "crop"));
            int rotation = reader.getPageRotation(newPageNumber);

            Rectangle scaledBox = RectangleHandler.calculateScaledRectangle(boxes, ratios, rotation);

            PdfArray scaleBoxArray = createScaledBoxArray(scaledBox);

            pageDict.put(PdfName.CROPBOX, scaleBoxArray);
            pageDict.put(PdfName.MEDIABOX, scaleBoxArray);
            // increment the pagenumber
            newPageNumber++;
        }
        int[] range = new int[2];
        range[0] = newPageNumber - 1;
        range[1] = pdfMetaInformation.getSourcePageCount() + (newPageNumber - sourcePageNumber);
        SimpleBookmark.shiftPageNumbers(pdfMetaInformation.getSourceBookmarks(), rectangleList.size() - 1, range);
    }
    stamper.setOutlines(pdfMetaInformation.getSourceBookmarks());
    stamper.close();
    reader.close();
}
 

/**
 * <p>
 * This method restricts the media boxes of the pages in the given {@link PdfReader}
 * to the actual content found by the {@link MarginFinder} extended render listener.
 * </p>
 * <p>
 * It essentially is copied from the {@link TestTrimPdfPage} methods
 * {@link TestTrimPdfPage#testWithStamperExtFinder()} and
 * {@link TestTrimPdfPage#getOutputPageSize4(Rectangle, PdfReader, int)}.
 * In contrast to the code there this method manipulates
 * the media box because this is the only box respected by
 * {@link PdfWriter#getImportedPage(PdfReader, int)}.
 * </p>
 */
static void cropPdf(PdfReader reader) throws IOException
{
    int n = reader.getNumberOfPages();
    for (int i = 1; i <= n; i++)
    {
        PdfReaderContentParser parser = new PdfReaderContentParser(reader);
        MarginFinder finder = parser.processContent(i, new MarginFinder());
        Rectangle rect = new Rectangle(finder.getLlx(), finder.getLly(), finder.getUrx(), finder.getUry());

        PdfDictionary page = reader.getPageN(i);
        page.put(PdfName.MEDIABOX, new PdfArray(new float[]{rect.getLeft(), rect.getBottom(), rect.getRight(), rect.getTop()}));
    }
}
 

/**
 * <a href="https://stackoverflow.com/questions/47101222/how-to-decode-image-with-asciihexdecode">
 * How to decode image with /ASCIIHexDecode
 * </a>
 * <br/>
 * <a href="https://1drv.ms/b/s!AjcEvFO-aWLMkbtXNVl_rmUXv6nnBQ">
 * test.pdf
 * </a>
 * <p>
 * The issue can be reproduced. Without studying the format
 * of the integrated image in detail, though, it is hard to
 * tell whether this is a bug in iText or a bug in the PDF.
 * </p>
 */
@Test
public void testExtractImageLikeSteveB() throws IOException
{
    try (InputStream resource = getClass().getResourceAsStream("testSteveB.pdf")) {
        PdfReader reader = new PdfReader(resource);
        for (int pageNumber = 1; pageNumber <= reader.getNumberOfPages(); pageNumber++)
        {
            PdfDictionary dictionary = reader.getPageN(pageNumber);
            FindImages(reader, dictionary);
        }
    }
}