Java PDPage.getResources方法代码示例

import org.apache.pdfbox.pdmodel.PDPage; //导入方法依赖的package包/类
/**
 * <a href="http://stackoverflow.com/questions/42032729/render-type3-font-character-as-image-using-pdfbox">
 * Render Type3 font character as image using PDFBox
 * </a>
 * <br/>
 * <a href="https://drive.google.com/file/d/0B0f6X4SAMh2KRDJTbm4tb3E1a1U/view">
 * 4700198773.pdf
 * </a>
 * from
 * <a href="http://stackoverflow.com/questions/37754112/extract-text-with-custom-font-result-non-readble">
 * extract text with custom font result non readble
 * </a>
 * <p>
 * This test shows how one can render individual Type 3 font glyphs as bitmaps.
 * Unfortunately PDFBox out-of-the-box does not provide a class to render contents
 * of arbitrary XObjects, merely for rendering pages; thus, we simply create a page
 * with the glyph in question and render that page.   
 * </p>
 * <p>
 * As the OP did not provide a sample PDF, we simply use one from another
 * stackoverflow question. There obviously might remain issues with the
 * OP's files.
 * </p>
 */
@Test
public void testRenderSdnList() throws IOException
{
    try (   InputStream resource = getClass().getResourceAsStream("sdnlist.pdf"))
    {
        PDDocument document = PDDocument.load(resource);

        PDPage page = document.getPage(1);
        PDResources pageResources = page.getResources();
        COSName f1Name = COSName.getPDFName("R144");
        PDType3Font fontF1 = (PDType3Font) pageResources.getFont(f1Name);
        Map<String, Integer> f1NameToCode = fontF1.getEncoding().getNameToCodeMap();

        COSDictionary charProcsDictionary = fontF1.getCharProcs();
        for (COSName key : charProcsDictionary.keySet())
        {
            COSStream stream = (COSStream) charProcsDictionary.getDictionaryObject(key);
            PDType3CharProc charProc = new PDType3CharProc(fontF1, stream);
            PDRectangle bbox = charProc.getGlyphBBox();
            if (bbox == null)
                bbox = charProc.getBBox();
            Integer code = f1NameToCode.get(key.getName());

            if (code != null)
            {
                PDDocument charDocument = new PDDocument();
                PDPage charPage = new PDPage(bbox);
                charDocument.addPage(charPage);
                charPage.setResources(pageResources);
                PDPageContentStream charContentStream = new PDPageContentStream(charDocument, charPage);
                charContentStream.beginText();
                charContentStream.setFont(fontF1, bbox.getHeight());
                charContentStream.getOutput().write(String.format("<%2X> Tj\n", code).getBytes());
                charContentStream.endText();
                charContentStream.close();

                File result = new File(RESULT_FOLDER, String.format("sdnlist-%s-%s.png", key.getName(), code));
                PDFRenderer renderer = new PDFRenderer(charDocument);
                BufferedImage image = renderer.renderImageWithDPI(0, 96);
                ImageIO.write(image, "PNG", result);
                charDocument.save(new File(RESULT_FOLDER, String.format("sdnlist-%s-%s.pdf", key.getName(), code)));
                charDocument.close();
            }
        }
    }
}
 

import org.apache.pdfbox.pdmodel.PDPage; //导入方法依赖的package包/类
/**
 * <a href="http://stackoverflow.com/questions/42032729/render-type3-font-character-as-image-using-pdfbox">
 * Render Type3 font character as image using PDFBox
 * </a>
 * <br/>
 * <a href="https://drive.google.com/file/d/0B0f6X4SAMh2KRDJTbm4tb3E1a1U/view">
 * 4700198773.pdf
 * </a>
 * from
 * <a href="http://stackoverflow.com/questions/37754112/extract-text-with-custom-font-result-non-readble">
 * extract text with custom font result non readble
 * </a>
 * <p>
 * This test shows how one can render individual Type 3 font glyphs as bitmaps.
 * Unfortunately PDFBox out-of-the-box does not provide a class to render contents
 * of arbitrary XObjects, merely for rendering pages; thus, we simply create a page
 * with the glyph in question and render that page.   
 * </p>
 * <p>
 * As the OP did not provide a sample PDF, we simply use one from another
 * stackoverflow question. There obviously might remain issues with the
 * OP's files.
 * </p>
 */
@Test
public void testRender4700198773() throws IOException
{
    try (   InputStream resource = getClass().getResourceAsStream("4700198773.pdf"))
    {
        PDDocument document = PDDocument.load(resource);

        PDPage page = document.getPage(0);
        PDResources pageResources = page.getResources();
        COSName f1Name = COSName.getPDFName("F1");
        PDType3Font fontF1 = (PDType3Font) pageResources.getFont(f1Name);
        Map<String, Integer> f1NameToCode = fontF1.getEncoding().getNameToCodeMap();

        COSDictionary charProcsDictionary = fontF1.getCharProcs();
        for (COSName key : charProcsDictionary.keySet())
        {
            COSStream stream = (COSStream) charProcsDictionary.getDictionaryObject(key);
            PDType3CharProc charProc = new PDType3CharProc(fontF1, stream);
            PDRectangle bbox = charProc.getGlyphBBox();
            if (bbox == null)
                bbox = charProc.getBBox();
            Integer code = f1NameToCode.get(key.getName());

            if (code != null)
            {
                PDDocument charDocument = new PDDocument();
                PDPage charPage = new PDPage(bbox);
                charDocument.addPage(charPage);
                charPage.setResources(pageResources);
                PDPageContentStream charContentStream = new PDPageContentStream(charDocument, charPage);
                charContentStream.beginText();
                charContentStream.setFont(fontF1, bbox.getHeight());
                charContentStream.getOutput().write(String.format("<%2X> Tj\n", code).getBytes());
                charContentStream.endText();
                charContentStream.close();

                File result = new File(RESULT_FOLDER, String.format("4700198773-%s-%s.png", key.getName(), code));
                PDFRenderer renderer = new PDFRenderer(charDocument);
                BufferedImage image = renderer.renderImageWithDPI(0, 96);
                ImageIO.write(image, "PNG", result);
                charDocument.save(new File(RESULT_FOLDER, String.format("4700198773-%s-%s.pdf", key.getName(), code)));
                charDocument.close();
            }
        }
    }
}
 

import org.apache.pdfbox.pdmodel.PDPage; //导入方法依赖的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.PDPage; //导入方法依赖的package包/类
/**
 * <a href="https://stackoverflow.com/questions/45895768/pdfbox-2-0-7-extracttext-not-working-but-1-8-13-does-and-pdfreader-as-well">
 * PDFBox 2.0.7 ExtractText not working but 1.8.13 does and PDFReader as well
 * </a>
 * <br/>
 * <a href="https://wetransfer.com/downloads/214674449c23713ee481c5a8f529418320170827201941/b2bea6">
 * test-2.pdf
 * </a>
 * <p>
 * Due to the broken <b>ToUnicode</b> maps the output of immediate text
 * extraction from this document is unsatisfying, cf. {@link #testTest2()}.
 * It can be improved by removing these <b>ToUnicode</b> maps as this test
 * shows.
 * </p>
 */
@Test
public void testNoToUnicodeTest2() throws IOException
{
    try (   InputStream resource = getClass().getResourceAsStream("test-2.pdf")    )
    {
        PDDocument document = PDDocument.load(resource);

        for (int pageNr = 0; pageNr < document.getNumberOfPages(); pageNr++)
        {
            PDPage page = document.getPage(pageNr);
            PDResources resources = page.getResources();
            removeToUnicodeMaps(resources);
        }

        PDFTextStripper stripper = new PDFTextStripper();
        String text = stripper.getText(document);

        System.out.printf("\n*\n* test-2.pdf without ToUnicode\n*\n%s\n", text);
        Files.write(new File(RESULT_FOLDER, "test-2_NoToUnicode.txt").toPath(), Collections.singleton(text));
    }
}
 

import org.apache.pdfbox.pdmodel.PDPage; //导入方法依赖的package包/类
private static void buildImgKeyToImageObjMapping(PDPage page) throws IOException {
    PDResources resources = page.getResources();
    Map images = resources.getImages();

    if(images != null) {
        Iterator imageIter = images.keySet().iterator();

        while(imageIter.hasNext()) {
            String key = (String)imageIter.next();
            PDXObjectImage image = (PDXObjectImage)images.get(key);
            mapImgKeyToImageObj.put(key, image);
        }
    }
}
 

import org.apache.pdfbox.pdmodel.PDPage; //导入方法依赖的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.PDPage; //导入方法依赖的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++;
        }
    }
}