Java PDXObject类代码示例

import org.apache.pdfbox.pdmodel.graphics.PDXObject; //导入依赖的package包/类
public static void findPhoto(String path,int empId) throws IOException, SQLException, Error{
		// Loading an existing document
		int imageFound=0;
		File file = new File(path);
		PDDocument document=PDDocument.load(file);
		PDPageTree list=document.getPages();
		for(PDPage page:list){						//check in all pages of pdf
			PDResources pdResources=page.getResources();		//get all resources
			for(COSName cosName:pdResources.getXObjectNames())		//loop for all resources
			{
				PDXObject pdxObject=pdResources.getXObject(cosName);
				 if (pdxObject instanceof PDImageXObject) {			//check that the resource is image
		                BufferedImage br=((PDImageXObject) pdxObject).getImage();
		                RgbImage im = RgbImageJ2se.toRgbImage(br);
		                // step #3 - convert image to greyscale 8-bits
		                RgbAvgGray toGray = new RgbAvgGray();
		                toGray.push(im);
		                // step #4 - initialize face detector with correct Haar profile
		                InputStream is  = ExtractPhoto.class.getResourceAsStream("/haar/HCSB.txt");
		                Gray8DetectHaarMultiScale detectHaar = new Gray8DetectHaarMultiScale(is, 1,40);
		                // step #5 - apply face detector to grayscale image
		                List<Rect> result= detectHaar.pushAndReturn(toGray.getFront());
		                if(result.size()!=0)
		                {
		                database.StorePhoto.storePhoto(empId,br);
		                imageFound=1;
		                break;
		                }
				 }
			}
			if(imageFound==1)
				break;
}
		System.out.println(imageFound);
		if(imageFound!=1){
			BufferedImage in = ImageIO.read(ExtractPhoto.class.getResource("/images/nopic.jpg"));
            database.StorePhoto.storePhoto(empId,in);
		}
	document.close();	
	}
 

import org.apache.pdfbox.pdmodel.graphics.PDXObject; //导入依赖的package包/类
private List<RenderedImage> getImagesFromResources(PDResources resources) throws IOException {

        List<RenderedImage> images = new ArrayList<>();
        for (COSName xObjectName : resources.getXObjectNames()) {
            PDXObject xObject = resources.getXObject(xObjectName);
            if (xObject instanceof PDImageXObject) {
                images.add(((PDImageXObject) xObject).getImage());
            } else if (xObject instanceof PDFormXObject) {
                images.addAll(getImagesFromResources(((PDFormXObject) xObject).getResources()));
            }
        }
        return images;
    }
 

import org.apache.pdfbox.pdmodel.graphics.PDXObject; //导入依赖的package包/类
@Override
public void put(COSObject indirect, PDXObject xobject) throws IOException {
    final int length = xobject.getStream().getLength();
    if (length > Environment.getMaxImageSize()) {
        LOG.trace("Not caching image with Size: {}", length);
        return;
    }
    if (xobject instanceof PDImageXObject) {
        PDImageXObject imageObj = (PDImageXObject) xobject;
        if (imageObj.getWidth() * imageObj.getHeight() > Environment.getMaxImageSize()) {
            return;
        }
    }
    this.xobjects.put(indirect, new SoftReference(xobject));
}
 

import org.apache.pdfbox.pdmodel.graphics.PDXObject; //导入依赖的package包/类
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);
        }
    }
}
 

import org.apache.pdfbox.pdmodel.graphics.PDXObject; //导入依赖的package包/类
/**
 * <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 = PDDocument.load(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++;
        }
    }
}
 

import org.apache.pdfbox.pdmodel.graphics.PDXObject; //导入依赖的package包/类
/**
 * <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 = PDDocument.load(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++;
        }
    }
}
 

import org.apache.pdfbox.pdmodel.graphics.PDXObject; //导入依赖的package包/类
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)
                processFontResources(formResources, table);
        }
    }

}
 

import org.apache.pdfbox.pdmodel.graphics.PDXObject; //导入依赖的package包/类
protected void processImageOperation(List<COSBase> arguments) throws IOException
{
    COSName objectName = (COSName)arguments.get( 0 );
    PDXObject xobject = getResources().getXObject( objectName );
    if (xobject instanceof PDImageXObject)
    {
        PDImageXObject pdfImage = (PDImageXObject) xobject;
        BufferedImage outputImage = pdfImage.getImage();
        outputImage = rotateImage(outputImage);

        ImageResource imageData = new ImageResource(getTitle(), outputImage);

        Rectangle2D bounds = calculateImagePosition(pdfImage);
        float x = (float) bounds.getX();
        float y = (float) bounds.getY();

        renderImage(x, y, (float) bounds.getWidth(), (float) bounds.getHeight(), imageData);
    }
}
 

import org.apache.pdfbox.pdmodel.graphics.PDXObject; //导入依赖的package包/类
@Override
public PDXObject getXObject(COSObject indirect) throws IOException {
    SoftReference<PDXObject> xobject = this.xobjects.get(indirect);
    if (xobject != null) {
        return xobject.get();
    }
    return null;
}
 

import org.apache.pdfbox.pdmodel.graphics.PDXObject; //导入依赖的package包/类
/**
 * This is used to handle an operation.
 *
 * @param operator The operation to perform.
 * @param operands The list of arguments.
 * @throws IOException If there is an error processing the operation.
 */
@Override
protected void processOperator(Operator operator, List<COSBase> operands) throws IOException {
    String operation = operator.getName();
    if (INVOKE_OPERATOR.equals(operation)) {
        COSName objectName = (COSName) operands.get(0);
        PDXObject xobject = getResources().getXObject(objectName);
        if (xobject instanceof PDImageXObject) {

            PDImageXObject image = (PDImageXObject) xobject;
            Matrix ctmNew = getGraphicsState().getCurrentTransformationMatrix();

            Image im = new Image();
            im.setPage(currentPage);
            im.setXPosition(ctmNew.getTranslateX());
            im.setYPosition(ctmNew.getTranslateY());
            im.setOriginalHeight(image.getHeight());
            im.setOriginalWidth(image.getWidth());
            im.setRenderedWidth(Math.round(ctmNew.getScaleX()));
            im.setRenderedHeight(Math.round(ctmNew.getScaleY()));
            images.add(im);

            if (!output.exists()) output.mkdirs();
            // TODO enable option to set the output format. right now it uses original which means: tiff needs extra dependency and tiff are HUGE!
            // String extension = "png";
            String extension = image.getSuffix();
            File out = new File(output, basename + "-" + currentPage + "-" + count + "." + extension);

            ImageIO.write(image.getImage(), extension, new FileOutputStream(out));
            count++;

        } else if (xobject instanceof PDFormXObject) {
            PDFormXObject form = (PDFormXObject) xobject;
            showForm(form);
        }
    } else {
        super.processOperator(operator, operands);
    }
}
 

import org.apache.pdfbox.pdmodel.graphics.PDXObject; //导入依赖的package包/类
@Override
protected boolean removeEldestEntry(final Entry<COSObject, SoftReference<PDXObject>> eldest) {
    return size() > Environment.getNrOfImagesToCache();
}
 

import org.apache.pdfbox.pdmodel.graphics.PDXObject; //导入依赖的package包/类
@Override
public PDXObject getXObject(final COSObject indirect) throws IOException {
    return null;
}
 

import org.apache.pdfbox.pdmodel.graphics.PDXObject; //导入依赖的package包/类
@Override
public void put(final COSObject indirect, final PDXObject xobject) throws IOException {}
 

import org.apache.pdfbox.pdmodel.graphics.PDXObject; //导入依赖的package包/类
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);
        }
    }
}
 

import org.apache.pdfbox.pdmodel.graphics.PDXObject; //导入依赖的package包/类
@Override
public void process(Operator operator, List<COSBase> arguments)
    throws IOException {
  // Get the name of the PDXOject.
  COSName name = (COSName) arguments.get(0);

  // Get the PDXObject.
  PDXObject xobject = context.getResources().getXObject(name);

  if (xobject instanceof PDFormXObject) {
    context.processStream((PDFormXObject) xobject);
  } else if(xobject instanceof PDImageXObject) {
    PDImageXObject image = (PDImageXObject) xobject;

    int imageWidth = image.getWidth();
    int imageHeight = image.getHeight();

    Matrix ctm = context.getCurrentTransformationMatrix().clone();
    AffineTransform ctmAT = ctm.createAffineTransform();
    ctmAT.scale(1f / imageWidth, 1f / imageHeight);
    Matrix at = new Matrix(ctmAT);

    Rectangle boundBox = SimpleRectangle.from2Vertices(
        new SimplePoint(ctm.getTranslateX(), ctm.getTranslateY()),
        new SimplePoint(ctm.getTranslateX() + at.getScaleX() * imageWidth,
            ctm.getTranslateY() + at.getScaleY() * imageHeight));

    // Rectangle boundBox = new SimpleRectangle();
    // boundBox.setMinX(ctm.getTranslateX());
    // boundBox.setMinY(ctm.getTranslateY());
    // boundBox.setMaxX(ctm.getTranslateX() + at.getScaleX() * imageWidth);
    // boundBox.setMaxY(ctm.getTranslateY() + at.getScaleY() * imageHeight);

    PdfBoxColor exclusiveColor = getExclusiveColor(image.getImage());

    if (exclusiveColor != null) {
      PdfBoxShape shape = new PdfBoxShape(context.getCurrentPage());
      shape.setRectangle(boundBox);
      shape.setColor(exclusiveColor);
      context.showShape(shape);
    } else {
      PdfBoxFigure figure = new PdfBoxFigure(context.getCurrentPage());
      figure.setRectangle(boundBox);
      context.showFigure(figure);
    }
  }
}