Java Code Examples for org.apache.pdfbox.pdmodel.PDResources#getXObject()

private void processImagesFromResources(PDResources resources) throws IOException {
    for (COSName xObjectName : resources.getXObjectNames()) {
        PDXObject xObject = resources.getXObject(xObjectName);

        if (xObject instanceof PDFormXObject) {
            processImagesFromResources(((PDFormXObject) xObject).getResources());
        } else if (xObject instanceof PDImageXObject) {
            PDImageXObject img = (PDImageXObject) xObject;
            if (!img.getImage().getColorModel().hasAlpha())
                return;

            PDImageXObject cpy = makeImageObjectCopy(img);
            resources.put(xObjectName, cpy);
            imagesWereChanged = true;
        }
    }
}
 

private void extractFontResources(PDResources resources) throws IOException {
    for (COSName key : resources.getFontNames()) {
        PDFont font = resources.getFont(key);
        extractStrategy.extract(font);
    }

    for (COSName name : resources.getXObjectNames()) {
        PDXObject xobject = resources.getXObject(name);
        if (xobject instanceof PDFormXObject) {
            PDFormXObject xObjectForm = (PDFormXObject) xobject;
            PDResources formResources = xObjectForm.getResources();

            if (formResources != null)
                extractFontResources(formResources);
        }
    }
}
 

private void getImagesFromResources(PDResources resources) throws IOException {
    for (COSName xObjectName : resources.getXObjectNames()) {
        PDXObject xObject = resources.getXObject(xObjectName);

        if (xObject instanceof PDFormXObject) {
            getImagesFromResources(((PDFormXObject) xObject).getResources());
        } else if (xObject instanceof PDImageXObject) {
            //((PDImageXObject) xObject).getImage();
            imagesCount++;
        }
    }
}
 

@Override
public int handleCurrentPage() {
    int index = 0;
    try {
        PDPage page = doc.getPage(currentParameters.currentPage - 1);  // 0-based
        PDResources pdResources = page.getResources();
        Iterable<COSName> iterable = pdResources.getXObjectNames();
        if (iterable != null) {
            Iterator<COSName> pageIterator = iterable.iterator();
            while (pageIterator.hasNext()) {
                if (task.isCancelled()) {
                    break;
                }
                COSName cosName = pageIterator.next();
                if (!pdResources.isImageXObject(cosName)) {
                    continue;
                }
                PDImageXObject pdxObject = (PDImageXObject) pdResources.getXObject(cosName);
                String namePrefix = FileTools.getFilePrefix(currentParameters.currentSourceFile.getName())
                        + "_page" + currentParameters.currentPage + "_index" + index;
                String suffix = pdxObject.getSuffix();
                File tFile = makeTargetFile(namePrefix, "." + suffix, currentParameters.currentTargetPath);
                ImageFileWriters.writeImageFile(pdxObject.getImage(), suffix, tFile.getAbsolutePath());
                targetFileGenerated(tFile);
                if (isPreview) {
                    break;
                }
                index++;
            }
        }

    } catch (Exception e) {
        logger.error(e.toString());
    }
    return index;
}
 

protected int extractPage() {
    int index = 0;
    try {
        PDPage page = doc.getPage(currentParameters.currentPage - 1);  // 0-based
        PDResources pdResources = page.getResources();
        Iterable<COSName> iterable = pdResources.getXObjectNames();
        if (iterable != null) {
            Iterator<COSName> pageIterator = iterable.iterator();
            while (pageIterator.hasNext()) {
                if (task.isCancelled()) {
                    break;
                }
                COSName cosName = pageIterator.next();
                if (!pdResources.isImageXObject(cosName)) {
                    continue;
                }
                PDImageXObject pdxObject = (PDImageXObject) pdResources.getXObject(cosName);
                BufferedImage bufferedImage = pdxObject.getImage();
                if (handleImage(bufferedImage)) {
                    lastImage = bufferedImage;
                    if (isPreview) {
                        break;
                    }
                    index++;
                }
            }
        }

    } catch (Exception e) {
        logger.error(e.toString());
    }
    return index;
}
 

/**
 * Check if there is a translation needed to place the annotations content.
 * 
 * @param appearanceStream
 * @return the need for a translation transformation.
 */
private boolean resolveNeedsTranslation(PDAppearanceStream appearanceStream)
{
    boolean needsTranslation = true;

    PDResources resources = appearanceStream.getResources();
    if (resources != null && resources.getXObjectNames().iterator().hasNext())
    {
        Iterator<COSName> xObjectNames = resources.getXObjectNames().iterator();

        while (xObjectNames.hasNext())
        {
            try
            {
                // if the BBox of the PDFormXObject does not start at 0,0
                // there is no need do translate as this is done by the BBox definition.
                PDXObject xObject = resources.getXObject(xObjectNames.next());
                if (xObject instanceof PDFormXObject)
                {
                    PDRectangle bbox = ((PDFormXObject)xObject).getBBox();
                    float llX = bbox.getLowerLeftX();
                    float llY = bbox.getLowerLeftY();
                    if (Float.compare(llX, 0) != 0 && Float.compare(llY, 0) != 0)
                    {
                        needsTranslation = false;
                    }
                }
            }
            catch (IOException e)
            {
                // we can safely ignore the exception here
                // as this might only cause a misplacement
            }
        }
        return needsTranslation;
    }
    
    return true;
}
 

void removeToUnicodeMaps(PDResources pdResources) throws IOException
{
    COSDictionary resources = pdResources.getCOSObject();

    COSDictionary fonts = asDictionary(resources, COSName.FONT);
    if (fonts != null)
    {
        for (COSBase object : fonts.getValues())
        {
            while (object instanceof COSObject)
                object = ((COSObject)object).getObject();
            if (object instanceof COSDictionary)
            {
                COSDictionary font = (COSDictionary)object;
                font.removeItem(COSName.TO_UNICODE);
            }
        }
    }

    for (COSName name : pdResources.getXObjectNames())
    {
        PDXObject xobject = pdResources.getXObject(name);
        if (xobject instanceof PDFormXObject)
        {
            PDResources xobjectPdResources = ((PDFormXObject)xobject).getResources();
            removeToUnicodeMaps(xobjectPdResources);
        }
    }
}
 

/**
 * <a href="http://stackoverflow.com/questions/40531871/how-can-i-check-if-pdf-page-is-imagescanned-by-pdfbox-xpdf">
 * How can I check if PDF page is image(scanned) by PDFBOX, XPDF
 * </a>
 * <br/>
 * <a href="https://drive.google.com/file/d/0B9izTHWJQ7xlT2ZoQkJfbGRYcFE">
 * 10948.pdf
 * </a>
 * <p>
 * The only special thing about the two images returned for the sample PDF is that
 * one image is merely a mask used for the other image, and the other image is the
 * actual image used on the PDF page. If one only wants the images immediately used
 * in the page content, one also has to scan the page content.
 * </p>
 */
@Test
public void testExtractPageImageResources10948() throws IOException
{
    try (   InputStream resource = getClass().getResourceAsStream("10948.pdf"))
    {
        PDDocument document = Loader.loadPDF(resource);
        int page = 1;
        for (PDPage pdPage : document.getPages())
        {
            PDResources resources = pdPage.getResources();
            if (resource != null)
            {
                int index = 0;
                for (COSName cosName : resources.getXObjectNames())
                {
                    PDXObject xobject = resources.getXObject(cosName);
                    if (xobject instanceof PDImageXObject)
                    {
                        PDImageXObject image = (PDImageXObject)xobject;
                        File file = new File(RESULT_FOLDER, String.format("10948-%s-%s.%s", page, index, image.getSuffix()));
                        ImageIO.write(image.getImage(), image.getSuffix(), file);
                        index++;
                    }
                }
            }
            page++;
        }
    }
}
 

/**
 * <a href="http://stackoverflow.com/questions/40531871/how-can-i-check-if-pdf-page-is-imagescanned-by-pdfbox-xpdf">
 * How can I check if PDF page is image(scanned) by PDFBOX, XPDF
 * </a>
 * <br/>
 * <a href="https://drive.google.com/open?id=0B9izTHWJQ7xlYi1XN1BxMmZEUGc">
 * 10948.pdf
 * </a>, renamed "10948-new.pdf" here to prevent a collision
 * <p>
 * Here the code extracts no image at all because the images are not immediate page
 * resources but wrapped in form xobjects.
 * </p>
 */
@Test
public void testExtractPageImageResources10948New() throws IOException
{
    try (   InputStream resource = getClass().getResourceAsStream("10948-new.pdf"))
    {
        PDDocument document = Loader.loadPDF(resource);
        int page = 1;
        for (PDPage pdPage : document.getPages())
        {
            PDResources resources = pdPage.getResources();
            if (resource != null)
            {
                int index = 0;
                for (COSName cosName : resources.getXObjectNames())
                {
                    PDXObject xobject = resources.getXObject(cosName);
                    if (xobject instanceof PDImageXObject)
                    {
                        PDImageXObject image = (PDImageXObject)xobject;
                        File file = new File(RESULT_FOLDER, String.format("10948-new-%s-%s.%s", page, index, image.getSuffix()));
                        ImageIO.write(image.getImage(), image.getSuffix(), file);
                        index++;
                    }
                }
            }
            page++;
        }
    }
}
 

private void processFontResources(PDResources resources, FontTable table) throws IOException
{
    String fontNotSupportedMessage = "Font: {} skipped because type '{}' is not supported.";

    for (COSName key : resources.getFontNames())
    {
        PDFont font = resources.getFont(key);
        if (font instanceof PDTrueTypeFont)
        {
            table.addEntry( font);
            log.debug("Font: " + font.getName() + " TTF");
        }
        else if (font instanceof PDType0Font)
        {
            PDCIDFont descendantFont = ((PDType0Font) font).getDescendantFont();
            if (descendantFont instanceof PDCIDFontType2)
                table.addEntry(font);
            else
                log.warn(fontNotSupportedMessage, font.getName(), font.getClass().getSimpleName());
        }
        else if (font instanceof PDType1CFont)
            table.addEntry(font);
        else
            log.warn(fontNotSupportedMessage, font.getName(), font.getClass().getSimpleName());
    }

    for (COSName name : resources.getXObjectNames())
    {
        PDXObject xobject = resources.getXObject(name);
        if (xobject instanceof PDFormXObject)
        {
            PDFormXObject xObjectForm = (PDFormXObject) xobject;
            PDResources formResources = xObjectForm.getResources();
            if (formResources != null && formResources != resources && formResources.getCOSObject() != resources.getCOSObject())
                processFontResources(formResources, table);
        }
    }

}
 

@Override
public int handleCurrentPage() {
    int count = 0;
    try {
        PDPage sourcePage = doc.getPage(currentParameters.currentPage - 1);  // 0-based
        PDResources pdResources = sourcePage.getResources();
        pdResources.getXObjectNames();
        Iterable<COSName> iterable = pdResources.getXObjectNames();
        if (iterable == null) {
            return 0;
        }
        Iterator<COSName> pageIterator = iterable.iterator();
        while (pageIterator.hasNext()) {
            if (task.isCancelled()) {
                break;
            }
            COSName cosName = pageIterator.next();
            if (!pdResources.isImageXObject(cosName)) {
                continue;
            }
            PDImageXObject pdxObject = (PDImageXObject) pdResources.getXObject(cosName);
            BufferedImage sourceImage = pdxObject.getImage();
            PDImageXObject newObject = null;
            if (format == PdfImageFormat.Tiff) {
                ImageBinary imageBinary = new ImageBinary(sourceImage, threshold);
                imageBinary.setIsDithering(ditherCheck.isSelected());
                BufferedImage newImage = imageBinary.operate();
                newImage = ImageBinary.byteBinary(newImage);
                newObject = CCITTFactory.createFromImage(doc, newImage);

            } else if (format == PdfImageFormat.Jpeg) {
                newObject = JPEGFactory.createFromImage(doc, sourceImage, jpegQuality / 100f);
            }
            if (newObject != null) {
                pdResources.put(cosName, newObject);
                count++;
            }
            if (isPreview) {
                break;
            }
        }
        if (copyAllCheck.isSelected()) {
            targetDoc.getPage(currentParameters.currentPage - 1).setResources(pdResources);
        } else {
            targetDoc.addPage(sourcePage);
        }
    } catch (Exception e) {
        logger.error(e.toString());
    }
    return count;

}