java.awt.DefaultFocusTraversalPolicy#org.apache.pdfbox.pdmodel.PDDocument源码实例Demo

/**
 * @see #testAddLikeCccompanyImproved()
 */
private static ByteArrayOutputStream generatePdfFromStringImproved(String content) throws IOException {
    try (   PDDocument doc = new PDDocument();
            InputStream notoSansRegularResource = AddTextWithDynamicFonts.class.getResourceAsStream("NotoSans-Regular.ttf");
            InputStream notoSansCjkRegularResource = AddTextWithDynamicFonts.class.getResourceAsStream("NotoSansCJKtc-Regular.ttf")   ) {
        PDType0Font notoSansRegular = PDType0Font.load(doc, notoSansRegularResource);
        PDType0Font notoSansCjkRegular = PDType0Font.load(doc, notoSansCjkRegularResource);
        List<PDFont> fonts = Arrays.asList(notoSansRegular, notoSansCjkRegular);

        List<TextWithFont> fontifiedContent = fontify(fonts, content);

        PDPage page = new PDPage();
        doc.addPage(page);
        try (   PDPageContentStream contentStream = new PDPageContentStream(doc, page)) {
            contentStream.beginText();
            for (TextWithFont textWithFont : fontifiedContent) {
                textWithFont.show(contentStream, 12);
            }
            contentStream.endText();
        }
        ByteArrayOutputStream os = new ByteArrayOutputStream();
        doc.save(os);
        return os;
    }
}
 

private static PDImageXObject createJPEG(PDDocument document, BufferedImage image,
                                         float quality, int dpi) throws IOException
{
    // extract alpha channel (if any)
    BufferedImage awtColorImage = getColorImage(image);
    BufferedImage awtAlphaImage = getAlphaImage(image);

    // create XObject
    ByteArrayOutputStream baos = new ByteArrayOutputStream();
    encodeImageToJPEGStream(awtColorImage, quality, dpi, baos);
    ByteArrayInputStream byteStream = new ByteArrayInputStream(baos.toByteArray());
    
    PDImageXObject pdImage = new PDImageXObject(document, byteStream, 
            COSName.DCT_DECODE, awtColorImage.getWidth(), awtColorImage.getHeight(), 
            awtColorImage.getColorModel().getComponentSize(0),
            getColorSpaceFromAWT(awtColorImage));

    // alpha -> soft mask
    if (awtAlphaImage != null)
    {
        PDImage xAlpha = JPEGFactory.createFromImage(document, awtAlphaImage, quality);
        pdImage.getCOSObject().setItem(COSName.SMASK, xAlpha);
    }

    return pdImage;
}
 

public void merge(OutputStream outputStream, Iterable<PDDocument> inputs) throws IOException
{
    try
    {
        openDocument();
        for (PDDocument input: inputs)
        {
            merge(input);
        }
        if (currentContents != null) {
            currentContents.close();
            currentContents = null;
        }
        document.save(outputStream);
    }
    finally
    {
        closeDocument();
    }
    
}
 

/**
 * <a href="https://stackoverflow.com/questions/59031734/get-text-color-in-pdfbox">
 * Get text color in PDFBox
 * </a>
 * <p>
 * This test has already been executed for the original color text stripper class from my answer to
 * <a href="https://stackoverflow.com/questions/21430341/identifying-the-text-based-on-the-output-in-pdf-using-pdfbox">
 * Identifying the text based on the output in PDF using PDFBOX
 * </a>
 * </p>
 * 
 * @throws IOException
 */
@Test
public void testExtractFromFurzoSample() throws IOException {
    try (   InputStream resource = getClass().getResourceAsStream("furzo Sample.pdf");
            PDDocument document = Loader.loadPDF(resource) ) {
        PDFTextStripper stripper = new ColorTextStripper();
        String text = stripper.getText(document);

        Files.write(new File(RESULT_FOLDER, "furzo Sample.txt").toPath(), text.getBytes("UTF-8"));

        System.out.println("/// furzo Sample.pdf ///");
        System.out.println("Stripped text with color:");
        System.out.println(">>>");
        System.out.println(text);
        System.out.println("<<<");
    }
}
 

@Override
   public void fill(PDDocument pdDocument, PDPageContentStream contentStream,
    Position upperLeft, float width, float height, Color color,
    DrawListener drawListener) throws IOException {

add(pdDocument, contentStream, upperLeft, width, height);

if (color != null) {
    contentStream.setNonStrokingColor(color);
}
CompatibilityHelper.fillNonZero(contentStream);

if (drawListener != null) {
    drawListener.drawn(this, upperLeft, width, height);
}

   }
 

public static void main(String[] args) throws IOException {
	// Create a new empty document
	PDDocument document = new PDDocument();

	// Create a new blank page and add it to the document
	PDPage blankPage = new PDPage();
	document.addPage( blankPage );

	// Save the newly created document
	document.save("/home/lili/data/BlankPage.pdf");

	// finally make sure that the document is properly
	// closed.
	document.close();

}
 

public static void main(String[] args) throws InvalidPasswordException, IOException {
    try (PDDocument document = PDDocument.load(new File("/home/lili/data/test.pdf"))) {
        if (!document.isEncrypted()) {
            PDFTextStripper tStripper = new PDFTextStripper();
            // 如果想抽取某一页或者某几页，可以使用下面的方法限定范围。
            // 目前是抽取所有页
            tStripper.setStartPage(0);
            tStripper.setEndPage(document.getNumberOfPages());
            String pdfFileInText = tStripper.getText(document);
            String lines[] = pdfFileInText.split("\\r?\\n"); 
            for (String line : lines) {
                System.out.println(line);  
            } 
        }
    }
}
 

/**
 * Creates a COS stream from raw (encoded) data.
 */
private static COSStream createRawStream(PDDocument document, InputStream rawInput)
        throws IOException
{
    COSStream stream = document.getDocument().createCOSStream();
    OutputStream output = null;
    try
    {
        output = stream.createRawOutputStream();
        IOUtils.copy(rawInput, output);
    }
    finally
    {
        if (output != null)
        {
            output.close();
        }
    }
    return stream;
}
 

/**
 * <a href="https://stackoverflow.com/questions/56938135/pdfbox-inconsistent-pdtextfield-autosize-behavior-after-setvalue">
 * PDFBox Inconsistent PDTextField Autosize Behavior after setValue
 * </a>
 * <br/>
 * <a href="http://www.filedropper.com/0postfontload">
 * 0.pdf
 * </a>
 * <p>
 * Indeed, some fields look weird after fill-in; for some fields
 * this is due to weird pre-existing appearance streams. These can
 * be fixed as in {@link #testFill0DropOldAppearance()}.
 * </p>
 * @see #testFill0DropOldAppearance()
 * @see #testFill0DropOldAppearanceNoCombNoMax()
 * @see #testFill0DropOldAppearanceNoCombNoMaxNoMultiLine()
 */
@Test
public void testFill0LikeXenyal() throws IOException {
    try (   InputStream originalStream = getClass().getResourceAsStream("0.pdf");
            InputStream fontStream = getClass().getResourceAsStream("Lato-Regular.ttf"))
    {
        PDDocument doc = Loader.loadPDF(originalStream);
        PDAcroForm acroForm = doc.getDocumentCatalog().getAcroForm();

        PDType0Font font = PDType0Font.load(doc, fontStream, false);
        String font_name = acroForm.getDefaultResources().add(font).getName();

        for (PDField field : acroForm.getFieldTree()) {
            if (field instanceof PDTextField) {
                PDTextField textField = (PDTextField) field;
                textField.setDefaultAppearance(String.format("/%s 0 Tf 0 g", font_name));
                textField.setValue("Test");
            }
        }
        

        doc.save(new File(RESULT_FOLDER, "0-filledLikeXenyal.pdf"));
        doc.close();
    }        
}
 

@Test
public void testShouldReturnIndexedDocumentWhenParameterCorrect() throws IOException {
    String mediaType = "application/pdf+test";
    final String MEDIA_TYPE = "mediaType";
    PDFParser parser = Mockito.mock(PDFParser.class);
    COSDocument cosDoc = Mockito.mock(COSDocument.class);
    PDFTextStripper pdfTextStripper = Mockito.mock(PDFTextStripper.class);
    Mockito.doThrow(IOException.class).when(cosDoc).close();
    Mockito.when(parser.getDocument()).thenReturn(new COSDocument()).thenReturn(cosDoc);
    Mockito.when(pdfTextStripper.getText(new PDDocument())).thenReturn("");
    PDFIndexer pdfIndexer = new PDFIndexerWrapper(parser, pdfTextStripper);

    // should return the default media type when media type is not defined in file2Index
    IndexDocument pdf = pdfIndexer.getIndexedDocument(file2Index);
    if (!"application/pdf".equals(pdf.getFields().get(MEDIA_TYPE).get(0))) {
        Assert.fail();
    }

    // should return the media type we have set in the file2Index even if error occurs in finally block
    file2Index.mediaType = mediaType;
    pdf = pdfIndexer.getIndexedDocument(file2Index);
    if (!mediaType.equals(pdf.getFields().get(MEDIA_TYPE).get(0))) {
        Assert.fail();
    }

}
 

/**
 * <a href="http://stackoverflow.com/questions/41071142/pdfbox-remove-a-single-field-from-pdf">
 * PDFBox: Remove a single field from PDF
 * </a>
 * <br/>
 * <a href="https://www.dropbox.com/s/oyv1vjyhkmao1t1/input.pdf?dl=0">
 * input.pdf
 * </a>
 * <p>
 * This method applies the {@link HelloSignManipulator} to the sample document
 * and clears the field <code>var1001</code> (<i>address1</i>).
 * </p>
 */
@Test
public void testClearAddress1Input() throws IOException
{
    try (   InputStream resource = getClass().getResourceAsStream("input.pdf");
            PDDocument pdDocument = Loader.loadPDF(resource)   )
    {
        HelloSignAnalyzer helloSignAnalyzer = new HelloSignAnalyzer(pdDocument);

        HelloSignManipulator helloSignManipulator = new HelloSignManipulator(helloSignAnalyzer);

        helloSignManipulator.clearFields(Collections.singleton("var1001"));
        
        pdDocument.save(new File(RESULT_FOLDER, "input-clear-address1.pdf"));
    }
}
 

@Override
public float print(PDDocument document, PDPageContentStream stream, int pageNumber, float startX, float startY,
                   float allowedWidth) throws IOException {
    if (title != null) {
        throw new IllegalStateException("title not implemented!");
    }
    float y = startY;
    int i = 0;

    float lineY = 0;
    for (ReportElement[] line : elements) {
        float lineHeight = getLineHeight(line, allowedWidth) + pdfStyleSheet.getLineDistance();
        y = printLine(document, stream, pageNumber, startX, y, allowedWidth, line, lineY);
        placeFirstBorder = i == 0;
        placeLastBorder = i == elements.length - 1;
        placeBorders(stream, startY, y, startX, allowedWidth);
        i++;
        lineY += lineHeight;
    }
    return y;
}
 

/**
 * <a href="http://stackoverflow.com/questions/41767351/create-pkcs7-signature-from-file-digest">
 * Create pkcs7 signature from file digest
 * </a>
 * <p>
 * A minimal signing frame work merely requiring a {@link SignatureInterface}
 * instance.
 * </p>
 */
void sign(PDDocument document, OutputStream output, SignatureInterface signatureInterface) throws IOException
{
    PDSignature signature = new PDSignature();
    signature.setFilter(PDSignature.FILTER_ADOBE_PPKLITE);
    signature.setSubFilter(PDSignature.SUBFILTER_ADBE_PKCS7_DETACHED);
    signature.setName("Example User");
    signature.setLocation("Los Angeles, CA");
    signature.setReason("Testing");
    signature.setSignDate(Calendar.getInstance());
    document.addSignature(signature);
    ExternalSigningSupport externalSigning =
            document.saveIncrementalForExternalSigning(output);
    // invoke external signature service
    byte[] cmsSignature = signatureInterface.sign(externalSigning.getContent());
    // set signature bytes received from the service
    externalSigning.setSignature(cmsSignature);
}
 

@Test
public void testPdfBox() throws IOException {

    File pdfFile = new File(PdfHelper.PDF_TEST_RESOURCES + "pdf/1.pdf");
    File outDir = new File("target");
    
    PDDocument document = PDDocument.load(pdfFile);
    @SuppressWarnings("unchecked")
    List<PDPage> pages = document.getDocumentCatalog().getAllPages();
    int imageId = 0;
    for (PDPage page : pages) {
        for (PDXObjectImage img : page.getResources().getImages().values()) {
            
            int height = img.getHeight();
            int width = img.getWidth();
            
            System.out.println(img.getCOSStream().toString());
            
            img.write2file(new File(outDir, imageId++ + "."
                    + img.getSuffix()));
        }
    }
}
 

/**
 * Gets PDF Page Count.
 *
 * @param inputPdfFile input file
 * @return number of pages
 */
public static int getPdfPageCount(File inputPdfFile) {
    PDDocument document = null;
    try {
        document = PDDocument.load(inputPdfFile);
        return document.getNumberOfPages();
    } catch (IOException ioe) {
        logger.error("Error counting PDF pages => " + ioe);
        return - 1;
    } finally {
        if (document != null) {
            try {
                document.close();
            } catch (Exception e) {
            }
        }
    }
}
 

void printSubwords(PDDocument document, String searchTerm) throws IOException
{
    System.out.printf("* Looking for '%s'\n", searchTerm);
    for (int page = 1; page <= document.getNumberOfPages(); page++)
    {
        List<TextPositionSequence> hits = findSubwords(document, page, searchTerm);
        for (TextPositionSequence hit : hits)
        {
            if (!searchTerm.equals(hit.toString()))
                System.out.printf("  Invalid (%s) ", hit.toString());
            TextPosition lastPosition = hit.textPositionAt(hit.length() - 1);
            System.out.printf("  Page %s at %s, %s with width %s and last letter '%s' at %s, %s\n",
                    page, hit.getX(), hit.getY(), hit.getWidth(),
                    lastPosition.getUnicode(), lastPosition.getXDirAdj(), lastPosition.getYDirAdj());
        }
    }
}
 

private int splitByFilesNumber(PDDocument source) {
    try {
        int total = currentParameters.toPage - currentParameters.fromPage + 1;
        int len;
        if (total % filesNumber == 0) {
            len = total / filesNumber;
        } else {
            len = total / filesNumber + 1;
        }
        Splitter splitter = new Splitter();
        splitter.setStartPage(currentParameters.fromPage);  // 1-based
        splitter.setEndPage(currentParameters.toPage);  // 1-based
        splitter.setMemoryUsageSetting(AppVariables.pdfMemUsage);
        splitter.setSplitAtPage(len);
        List<PDDocument> docs = splitter.split(source);
        return writeFiles(docs);
    } catch (Exception e) {
        logger.error(e.toString());
        return 0;
    }
}
 

/**
 * <a href="https://stackoverflow.com/questions/54956720/how-to-replace-a-space-with-a-word-while-extract-the-data-from-pdf-using-pdfbox">
 * How to replace a space with a word while extract the data from PDF using PDFBox
 * </a>
 * <br/>
 * <a href="https://drive.google.com/open?id=10ZkdPlGWzMJeahwnQPzE6V7s09d1nvwq">
 * test.pdf
 * </a> as "testWPhromma.pdf"
 * <p>
 * This test shows how to, in principle, extract tagged text.
 * </p>
 */
@Test
public void testExtractTestWPhromma() throws IOException {
    System.out.printf("\n\n===\n%s\n===\n", "testWPhromma.pdf");
    try (   InputStream resource = getClass().getResourceAsStream("testWPhromma.pdf")) {
        PDDocument document = Loader.loadPDF(resource);

        Map<PDPage, Map<Integer, PDMarkedContent>> markedContents = new HashMap<>();

        for (PDPage page : document.getPages()) {
            PDFMarkedContentExtractor extractor = new PDFMarkedContentExtractor();
            extractor.processPage(page);

            Map<Integer, PDMarkedContent> theseMarkedContents = new HashMap<>();
            markedContents.put(page, theseMarkedContents);
            for (PDMarkedContent markedContent : extractor.getMarkedContents()) {
                theseMarkedContents.put(markedContent.getMCID(), markedContent);
            }
        }

        PDStructureNode root = document.getDocumentCatalog().getStructureTreeRoot();
        showStructure(root, markedContents);
    }
}
 

private PDDocument getDocument(RandomAccessRead source) throws IOException, BleachException {
  PDDocument doc;
  for (String pwd : COMMON_PASSWORDS) {
    ScratchFile scratchFile = new ScratchFile(MEMORY_USAGE_SETTING);
    doc = testPassword(scratchFile, source, pwd);
    if (doc != null) {
      LOGGER.debug("Password was guessed: '{}'", pwd);
      doc.protect(new StandardProtectionPolicy(pwd, pwd, doc.getCurrentAccessPermission()));
      return doc;
    }
    scratchFile.close();
  }

  // @TODO: fetch password from config?

  throw new BleachException("PDF is protected with an unknown password");
}
 

/**
 * Constructor.
 *
 * @param doc The document that this form is part of.
 */
public PDAcroForm(PDDocument doc)
{
    document = doc;
    dictionary = new COSDictionary();
    dictionary.setItem(COSName.FIELDS, new COSArray());
}
 

/**
 * <a href="http://stackoverflow.com/questions/39720305/ufffd-is-not-available-in-this-fonts-encoding-winansiencoding">
 * U+FFFD is not available in this font's encoding: WinAnsiEncoding
 * </a>
 * <p>
 * The issue cannot be reproduced.
 * </p>
 */
@Test
public void testFillLikeStDdt() throws IOException
{
    try (   InputStream originalStream = getClass().getResourceAsStream("FillFormField.pdf") )
    {
        PDDocument pdfDocument = Loader.loadPDF(originalStream);
        PDAcroForm acroForm = pdfDocument.getDocumentCatalog().getAcroForm();

        if (acroForm != null)
        {
            List<PDField> fields = acroForm.getFields();
            for (PDField field : fields) {
                switch (field.getPartialName()) {
                    case "Title" /*"devices"*/:
                        field.setValue("Ger�t");
                        field.setReadOnly(true);
                        break;
                }
            }
            acroForm.flatten(fields, true);
        }

        pdfDocument.save(new File(RESULT_FOLDER, "FillFormFieldStDdt.pdf"));
        pdfDocument.close();
    }
}
 

/**
 * Constructor.
 *
 * @param doc The document that this form is part of.
 */
public PDAcroForm(PDDocument doc)
{
    document = doc;
    dictionary = new COSDictionary();
    dictionary.setItem(COSName.FIELDS, new COSArray());
}
 

/**
   * Overlay a generated PDF document with another PDF (containing the company
   * stationary for example)
   *
   * @param context
   * @param generatedDocumentMendixObject The document to overlay
   * @param overlayMendixObject The document containing the overlay
* @param onTopOfContent if true, puts overlay position in the foreground, otherwise in the background
   * @return boolean
   * @throws IOException
   */
  public static boolean overlayPdf(IContext context, IMendixObject generatedDocumentMendixObject, IMendixObject overlayMendixObject, boolean onTopOfContent) throws IOException {
      LOG.trace("Retrieve generated document");
      try (
              PDDocument inputDoc = PDDocument.load(Core.getFileDocumentContent(context, generatedDocumentMendixObject));
              PDDocument overlayDoc = PDDocument.load(Core.getFileDocumentContent(context, overlayMendixObject));
              ByteArrayOutputStream baos = new ByteArrayOutputStream()) {
          LOG.trace("Overlay PDF start, retrieve overlay PDF");

          LOG.trace("Perform overlay");
          Overlay overlay = new Overlay();
          overlay.setInputPDF(inputDoc);
          overlay.setDefaultOverlayPDF(overlayDoc);
          if (onTopOfContent == true) {
              overlay.setOverlayPosition(Overlay.Position.FOREGROUND);
          } else {
              overlay.setOverlayPosition(Overlay.Position.BACKGROUND);
          }

          LOG.trace("Save result in output stream");

          overlay.overlay(new HashMap<>()).save(baos);

          LOG.trace("Duplicate result in input stream");
          try (InputStream overlayedContent = new ByteArrayInputStream(baos.toByteArray())) {
              LOG.trace("Store result in original document");
              Core.storeFileDocumentContent(context, generatedDocumentMendixObject, overlayedContent);
          }
      }

      LOG.trace("Overlay PDF end");
      return true;
  }
 

/**
 * create the second sample document from the PDF file format specification.
 *
 * @param input
 *            The PDF path to add the information to.
 * @param details
 *            The details to be added.
 *
 * @throws IOException
 *             If there is an error writing the data.
 */
public static void addInformation(Path input, ExportDetails details) throws IOException {
	try (PDDocument doc = PDDocument.load(input.toFile())) {
		if (details.getPageNumbering() != null) {
			writePageNumbering(doc, PDType1Font.HELVETICA_BOLD, 16.0f, details.getPageNumbering());
		}
		if (details.getFrontpageDetails() != null) {
			writeFrontpageDetails(doc, PDType1Font.HELVETICA_BOLD, 18.0f, details.getFrontpageDetails());
		}
		doc.save(input.toFile());
	}
}
 

@Test
public void vri() throws Exception {
	String path = "/validation/Signature-P-HU_MIC-3.pdf";
	String vriValue = "C41B1DBFE0E816D8A6F99A9DB98FD43960A5CF45";

	PDDocument pdDoc = PDDocument.load(getClass().getResourceAsStream(path));
	List<PDSignature> signatureDictionaries = pdDoc.getSignatureDictionaries();
	assertTrue(Utils.isCollectionNotEmpty(signatureDictionaries));
	PDSignature pdSignature = signatureDictionaries.get(0);
	byte[] contents = pdSignature.getContents(getClass().getResourceAsStream(path));
	byte[] digest = DSSUtils.digest(DigestAlgorithm.SHA1, contents);
	assertEquals(vriValue, Utils.upperCase(Utils.toHex(digest)));

	// We can't use CMSSignedData, the pdSignature content is trimmed (000000)
}
 

public static void drawImage(final BufferedImage image,
    final PDDocument document, final PDPageContentStream contentStream,
    Position upperLeft, final float width, final float height)
    throws IOException {
PDXObjectImage cachedImage = getCachedImage(document, image);
float x = upperLeft.getX();
float y = upperLeft.getY() - height;
contentStream.drawXObject(cachedImage, x, y, width, height);
   }
 

private PDDocument removeText(PDPage page) throws IOException {

        PDFStreamParser parser = new PDFStreamParser(page);
        parser.parse();
        List<Object> tokens = parser.getTokens();
        List<Object> newTokens = new ArrayList<>();
        for (Object token : tokens) {
            if (token instanceof Operator) {
                Operator op = (Operator) token;
                if (op.getName().equals("TJ") || op.getName().equals("Tj")) {
                    //remove the one argument to this operator
                    newTokens.remove(newTokens.size() - 1);
                    continue;
                }
            }
            newTokens.add(token);
        }

        PDDocument document = new PDDocument();
        PDPage newPage = document.importPage(page);
        newPage.setResources(page.getResources());

        PDStream newContents = new PDStream(document);
        OutputStream out = newContents.createOutputStream(COSName.FLATE_DECODE);
        ContentStreamWriter writer = new ContentStreamWriter(out);
        writer.writeTokens(newTokens);
        out.close();
        newPage.setContents(newContents);
        return document;
    }
 

private COSObject getByObjectNumber(PDDocument pdDocument, Long objectNumber) {
	List<COSObject> objects = pdDocument.getDocument().getObjects();
	for (COSObject cosObject : objects) {
		if (cosObject.getObjectNumber() == objectNumber) {
			return cosObject;
		}
	}
	return null;
}
 

@Test
public void createTitleBlockForDocumentIterationTest() throws Exception {
    DocumentTitleBlockData documentTitleData = new DocumentTitleBlockData(documentIteration, new Locale("en"));
    byte[] titleBlock = new TitleBlockWriter(documentTitleData).createTitleBlock();
    PDDocument loadedDocument = PDDocument.load(titleBlock);
    Assert.assertNotNull(loadedDocument);
    String text = new PDFTextStripper().getText(loadedDocument);
    loadedDocument.close();
    Assert.assertFalse(text.isEmpty());
    Assert.assertTrue(text.contains(user.getLogin()));
    Assert.assertTrue(text.contains(documentIteration.getId()));
    Assert.assertTrue(text.contains(documentIteration.getDocumentRevision().getDescription()));
}
 

/**
 * Creates a PDDocument and adds the page parameter to it and keeps this as a template in the
 * PDF template Structure.
 *
 * @param page
 * @throws IOException
 */
@Override
public void createTemplate(PDPage page) throws IOException
{
    PDDocument template = new PDDocument();
    template.addPage(page);
    pdfStructure.setTemplate(template);
}