Example usage for org.apache.pdfbox.pdmodel PDDocument load

List of usage examples for org.apache.pdfbox.pdmodel PDDocument load

  1. HOME
  2. Java
  3. org.apache.pdfbox
  4. org.apache.pdfbox.pdmodel.*
  5. PDDocument
  6. load

Introduction

In this page you can find the example usage for org.apache.pdfbox.pdmodel PDDocument load.

Prototype

public static PDDocument load(byte[] input, String password) throws IOException

Source Link

Document

Parses a PDF.

Usage

From source file:ShowSignature.java

License:Apache License

private void showSignature(String[] args) throws IOException, CertificateException {
    if (args.length != 2) {
        usage();/*from   w  w w  .  j a v a 2 s  . co  m*/
    } else {
        String password = args[0];
        String infile = args[1];
        PDDocument document = null;
        try {
            document = PDDocument.load(new File(infile), password);
            if (!document.isEncrypted()) {
                System.err.println("Warning: Document is not encrypted.");
            }

            COSDictionary trailer = document.getDocument().getTrailer();
            COSDictionary root = (COSDictionary) trailer.getDictionaryObject(COSName.ROOT);
            COSDictionary acroForm = (COSDictionary) root.getDictionaryObject(COSName.ACRO_FORM);
            COSArray fields = (COSArray) acroForm.getDictionaryObject(COSName.FIELDS);
            for (int i = 0; i < fields.size(); i++) {
                COSDictionary field = (COSDictionary) fields.getObject(i);
                COSName type = field.getCOSName(COSName.FT);
                if (COSName.SIG.equals(type)) {
                    COSDictionary cert = (COSDictionary) field.getDictionaryObject(COSName.V);
                    if (cert != null) {
                        System.out.println("Certificate found");
                        System.out.println("Name=" + cert.getDictionaryObject(COSName.NAME));
                        System.out.println("Modified=" + cert.getDictionaryObject(COSName.M));
                        COSName subFilter = (COSName) cert.getDictionaryObject(COSName.SUB_FILTER);
                        if (subFilter != null) {
                            if (subFilter.getName().equals("adbe.x509.rsa_sha1")) {
                                COSString certString = (COSString) cert
                                        .getDictionaryObject(COSName.getPDFName("Cert"));
                                byte[] certData = certString.getBytes();
                                CertificateFactory factory = CertificateFactory.getInstance("X.509");
                                ByteArrayInputStream certStream = new ByteArrayInputStream(certData);
                                Collection<? extends Certificate> certs = factory
                                        .generateCertificates(certStream);
                                System.out.println("certs=" + certs);
                            } else if (subFilter.getName().equals("adbe.pkcs7.sha1")) {
                                COSString certString = (COSString) cert.getDictionaryObject(COSName.CONTENTS);
                                byte[] certData = certString.getBytes();
                                CertificateFactory factory = CertificateFactory.getInstance("X.509");
                                ByteArrayInputStream certStream = new ByteArrayInputStream(certData);
                                Collection<? extends Certificate> certs = factory
                                        .generateCertificates(certStream);
                                System.out.println("certs=" + certs);
                            } else {
                                System.err.println("Unknown certificate type:" + subFilter);
                            }
                        } else {
                            throw new IOException("Missing subfilter for cert dictionary");
                        }
                    } else {
                        System.out.println("Signature found, but no certificate");
                    }
                }
            }
        } finally {
            if (document != null) {
                document.close();
            }
        }
    }
}

From source file:com.ackpdfbox.app.PDFToImage.java

License:Apache License

/**
 * Infamous main method./*from   ww  w.  j  av  a 2s. co m*/
 *
 * @param args Command line arguments, should be one and a reference to a file.
 *
 * @throws IOException If there is an error parsing the document.
 */
public static void main(String[] args) throws IOException {
    // suppress the Dock icon on OS X
    System.setProperty("apple.awt.UIElement", "true");

    String password = "";
    String pdfFile = null;
    String outputPrefix = null;
    String imageFormat = "jpg";
    int startPage = 1;
    int endPage = Integer.MAX_VALUE;
    String color = "rgb";
    int dpi;
    float cropBoxLowerLeftX = 0;
    float cropBoxLowerLeftY = 0;
    float cropBoxUpperRightX = 0;
    float cropBoxUpperRightY = 0;
    boolean showTime = false;
    try {
        dpi = Toolkit.getDefaultToolkit().getScreenResolution();
    } catch (HeadlessException e) {
        dpi = 96;
    }
    for (int i = 0; i < args.length; i++) {
        if (args[i].equals(PASSWORD)) {
            i++;
            if (i >= args.length) {
                usage();
            }
            password = args[i];
        } else if (args[i].equals(START_PAGE)) {
            i++;
            if (i >= args.length) {
                usage();
            }
            startPage = Integer.parseInt(args[i]);
        } else if (args[i].equals(END_PAGE)) {
            i++;
            if (i >= args.length) {
                usage();
            }
            endPage = Integer.parseInt(args[i]);
        } else if (args[i].equals(PAGE)) {
            i++;
            if (i >= args.length) {
                usage();
            }
            startPage = Integer.parseInt(args[i]);
            endPage = Integer.parseInt(args[i]);
        } else if (args[i].equals(IMAGE_TYPE) || args[i].equals(FORMAT)) {
            i++;
            imageFormat = args[i];
        } else if (args[i].equals(OUTPUT_PREFIX) || args[i].equals(PREFIX)) {
            i++;
            outputPrefix = args[i];
        } else if (args[i].equals(COLOR)) {
            i++;
            color = args[i];
        } else if (args[i].equals(RESOLUTION) || args[i].equals(DPI)) {
            i++;
            dpi = Integer.parseInt(args[i]);
        } else if (args[i].equals(CROPBOX)) {
            i++;
            cropBoxLowerLeftX = Float.valueOf(args[i]);
            i++;
            cropBoxLowerLeftY = Float.valueOf(args[i]);
            i++;
            cropBoxUpperRightX = Float.valueOf(args[i]);
            i++;
            cropBoxUpperRightY = Float.valueOf(args[i]);
        } else if (args[i].equals(TIME)) {
            showTime = true;
        } else {
            if (pdfFile == null) {
                pdfFile = args[i];
            }
        }
    }
    if (pdfFile == null) {
        usage();
    } else {
        if (outputPrefix == null) {
            outputPrefix = pdfFile.substring(0, pdfFile.lastIndexOf('.'));
        }

        PDDocument document = null;
        try {
            document = PDDocument.load(new File(pdfFile), password);

            ImageType imageType = null;
            if ("bilevel".equalsIgnoreCase(color)) {
                imageType = ImageType.BINARY;
            } else if ("gray".equalsIgnoreCase(color)) {
                imageType = ImageType.GRAY;
            } else if ("rgb".equalsIgnoreCase(color)) {
                imageType = ImageType.RGB;
            } else if ("rgba".equalsIgnoreCase(color)) {
                imageType = ImageType.ARGB;
            }

            if (imageType == null) {
                System.err.println("Error: Invalid color.");
                System.exit(2);
            }

            //if a CropBox has been specified, update the CropBox:
            //changeCropBoxes(PDDocument document,float a, float b, float c,float d)
            if (cropBoxLowerLeftX != 0 || cropBoxLowerLeftY != 0 || cropBoxUpperRightX != 0
                    || cropBoxUpperRightY != 0) {
                changeCropBox(document, cropBoxLowerLeftX, cropBoxLowerLeftY, cropBoxUpperRightX,
                        cropBoxUpperRightY);
            }

            long startTime = System.nanoTime();

            // render the pages
            boolean success = true;
            endPage = Math.min(endPage, document.getNumberOfPages());
            PDFRenderer renderer = new PDFRenderer(document);
            for (int i = startPage - 1; i < endPage; i++) {
                BufferedImage image = renderer.renderImageWithDPI(i, dpi, imageType);
                String fileName = outputPrefix + (i + 1) + "." + imageFormat;
                success &= ImageIOUtil.writeImage(image, fileName, dpi);
            }

            // performance stats
            long endTime = System.nanoTime();
            long duration = endTime - startTime;
            int count = 1 + endPage - startPage;
            if (showTime) {
                System.err.printf("Rendered %d page%s in %dms\n", count, count == 1 ? "" : "s",
                        duration / 1000000);
            }

            if (!success) {
                System.err.println("Error: no writer found for image format '" + imageFormat + "'");
                System.exit(1);
            }
        } finally {
            if (document != null) {
                document.close();
            }
        }
    }
}

From source file:com.jaeksoft.searchlib.parser.PdfParser.java

License:Open Source License

@Override
protected void parseContent(StreamLimiter streamLimiter, final LanguageEnum lang) throws IOException {
    PdfOcrContext context = new PdfOcrContext();
    context.lang = lang;/* w  w  w  . j a  v a2  s .  co  m*/
    String fileName = null;
    try {
        String ghostScriptBinaryPath = getStringProperty(ClassPropertyEnum.GHOSTSCRIPT_BINARYPATH);
        context.ghostScript = StringUtils.isEmpty(ghostScriptBinaryPath) ? null
                : new GhostScript(ghostScriptBinaryPath);
        fileName = streamLimiter.getFile().getName();
        context.pdfFile = streamLimiter.getFile();
        context.pdf = PDDocument.load(context.pdfFile, null);
        try {
            if (context.pdf.isEncrypted())
                context.pdfPassword = decrypt(context.pdf, context.pdfFile);
        } catch (Exception e) {
            Logging.warn("PDFBox decryption failed " + fileName);
            IOUtils.closeQuietly(context.pdf);
            context.pdf = null;
        }
        ParserResultItem result = getNewParserResultItem();
        result.addField(ParserFieldEnum.pdfcrack_password, context.pdfPassword);
        if (context.pdf != null)
            extractMetaData(result, context.pdf);
        int charCount = 0;
        if (context.ghostScript == null) {
            if (context.pdf != null)
                charCount = extractTextContent(result, context.pdf);
        } else
            charCount = extractTextContent(result, context);
        if (charCount == 0 && context.pdf != null)
            extractImagesForOCR(result, context);
        result.langDetection(10000, ParserFieldEnum.content);
    } catch (SearchLibException e) {
        throw new IOException("Failed on " + fileName, e);
    } catch (InterruptedException e) {
        throw new IOException("Failed on " + fileName, e);
    } catch (java.util.concurrent.ExecutionException e) {
        throw new IOException("Failed on " + fileName, e);
    } finally {
        if (context.pdf != null)
            context.pdf.close();
    }
}

From source file:com.qwazr.library.pdfbox.PdfBoxParser.java

License:Apache License

@Override
public void parseContent(final MultivaluedMap<String, String> parameters, final InputStream inputStream,
        String extension, final String mimeType, final ParserResultBuilder resultBuilder) throws Exception {
    parseContent(PDDocument.load(inputStream, getPassword(parameters)), resultBuilder);
}

From source file:com.qwazr.library.pdfbox.PdfBoxParser.java

License:Apache License

@Override
public void parseContent(final MultivaluedMap<String, String> parameters, final Path filePath, String extension,
        final String mimeType, final ParserResultBuilder resultBuilder) throws Exception {
    parseContent(PDDocument.load(filePath.toFile(), getPassword(parameters)), resultBuilder);
}

From source file:com.trollworks.gcs.pdfview.PdfDockable.java

License:Open Source License

public PdfDockable(PdfRef pdfRef, int page, String highlight) {
    super(new BorderLayout());
    mFile = pdfRef.getFile();//w w w . ja  va 2  s . c  o m
    int pageCount = 9999;
    try {
        mPdf = PDDocument.load(pdfRef.getFile(), MemoryUsageSetting.setupMixed(50 * 1024 * 1024));
        pageCount = mPdf.getNumberOfPages();
    } catch (Exception exception) {
        Log.error(exception);
    }
    mToolbar = new Toolbar();

    mZoomInButton = new IconButton(StdImage.get("ZoomIn"), //$NON-NLS-1$
            formatWithKey(SCALE_DOC_UP, KeyStroke.getKeyStroke('=')), () -> mPanel.zoomIn());
    mToolbar.add(mZoomInButton);
    mZoomOutButton = new IconButton(StdImage.get("ZoomOut"), //$NON-NLS-1$
            formatWithKey(SCALE_DOC_DOWN, KeyStroke.getKeyStroke('-')), () -> mPanel.zoomOut());
    mToolbar.add(mZoomOutButton);
    mActualSizeButton = new IconButton(StdImage.get("ActualSize"), //$NON-NLS-1$
            formatWithKey(ACTUAL_SIZE, KeyStroke.getKeyStroke('1')), () -> mPanel.actualSize());
    mToolbar.add(mActualSizeButton);
    mZoomStatus = new JLabel("100%"); //$NON-NLS-1$
    mToolbar.add(mZoomStatus);

    mPageField = new EditorField(new DefaultFormatterFactory(new IntegerFormatter(1, pageCount, false)),
            event -> {
                if (mPanel != null) {
                    int pageIndex = ((Integer) mPageField.getValue()).intValue() - 1;
                    int newPageIndex = mPanel.goToPageIndex(pageIndex, null);
                    if (pageIndex != newPageIndex) {
                        mPageField.setValue(Integer.valueOf(newPageIndex + 1));
                    } else {
                        mPanel.requestFocusInWindow();
                    }
                }
            }, SwingConstants.RIGHT, Integer.valueOf(page), Integer.valueOf(9999), null);
    mToolbar.add(mPageField, Toolbar.LAYOUT_EXTRA_BEFORE);
    mPageStatus = new JLabel("/ -"); //$NON-NLS-1$
    mToolbar.add(mPageStatus);
    mPreviousPageButton = new IconButton(StdImage.get("PageUp"), //$NON-NLS-1$
            formatWithKey(PREVIOUS_PAGE, KeyStroke.getKeyStroke(KeyEvent.VK_UP, 0)),
            () -> mPanel.previousPage());
    mToolbar.add(mPreviousPageButton);
    mNextPageButton = new IconButton(StdImage.get("PageDown"), //$NON-NLS-1$
            formatWithKey(NEXT_PAGE, KeyStroke.getKeyStroke(KeyEvent.VK_DOWN, 0)), () -> mPanel.nextPage());
    mToolbar.add(mNextPageButton);

    add(mToolbar, BorderLayout.NORTH);
    mPanel = new PdfPanel(this, mPdf, pdfRef, page, highlight);
    add(new JScrollPane(mPanel), BorderLayout.CENTER);

    setFocusCycleRoot(true);
    setFocusTraversalPolicy(new DefaultFocusTraversalPolicy());
}

From source file:com.yiyihealth.util.PDF2Image.java

License:Apache License

/**
 * Infamous main method./*  ww  w. j  ava 2 s  .c  o m*/
 *
 * @param args Command line arguments, should be one and a reference to a file.
 *
 * @throws IOException If there is an error parsing the document.
 */
public static void main(String[] args) throws IOException {
    // suppress the Dock icon on OS X
    System.setProperty("apple.awt.UIElement", "true");

    String password = "";
    String pdfFile = null;
    String outputPrefix = null;
    String imageFormat = "jpg";
    int startPage = 1;
    int endPage = Integer.MAX_VALUE;
    String color = "rgb";
    int dpi;
    float cropBoxLowerLeftX = 0;
    float cropBoxLowerLeftY = 0;
    float cropBoxUpperRightX = 0;
    float cropBoxUpperRightY = 0;
    boolean showTime = false;
    try {
        dpi = Toolkit.getDefaultToolkit().getScreenResolution();
    } catch (HeadlessException e) {
        dpi = 96;
    }
    for (int i = 0; i < args.length; i++) {
        if (args[i].equals(PASSWORD)) {
            i++;
            if (i >= args.length) {
                usage();
            }
            password = args[i];
        } else if (args[i].equals(START_PAGE)) {
            i++;
            if (i >= args.length) {
                usage();
            }
            startPage = Integer.parseInt(args[i]);
        } else if (args[i].equals(END_PAGE)) {
            i++;
            if (i >= args.length) {
                usage();
            }
            endPage = Integer.parseInt(args[i]);
        } else if (args[i].equals(PAGE)) {
            i++;
            if (i >= args.length) {
                usage();
            }
            startPage = Integer.parseInt(args[i]);
            endPage = Integer.parseInt(args[i]);
        } else if (args[i].equals(IMAGE_TYPE) || args[i].equals(FORMAT)) {
            i++;
            imageFormat = args[i];
        } else if (args[i].equals(OUTPUT_PREFIX) || args[i].equals(PREFIX)) {
            i++;
            outputPrefix = args[i];
        } else if (args[i].equals(COLOR)) {
            i++;
            color = args[i];
        } else if (args[i].equals(RESOLUTION) || args[i].equals(DPI)) {
            i++;
            dpi = Integer.parseInt(args[i]);
        } else if (args[i].equals(CROPBOX)) {
            i++;
            cropBoxLowerLeftX = Float.valueOf(args[i]);
            i++;
            cropBoxLowerLeftY = Float.valueOf(args[i]);
            i++;
            cropBoxUpperRightX = Float.valueOf(args[i]);
            i++;
            cropBoxUpperRightY = Float.valueOf(args[i]);
        } else if (args[i].equals(TIME)) {
            showTime = true;
        } else {
            if (pdfFile == null) {
                pdfFile = args[i];
            }
        }
    }
    if (pdfFile == null) {
        usage();
    } else {
        if (outputPrefix == null) {
            outputPrefix = pdfFile.substring(0, pdfFile.lastIndexOf('.'));
        }

        PDDocument document = null;
        try {
            document = PDDocument.load(new File(pdfFile), password);

            ImageType imageType = null;
            if ("bilevel".equalsIgnoreCase(color)) {
                imageType = ImageType.BINARY;
            } else if ("gray".equalsIgnoreCase(color)) {
                imageType = ImageType.GRAY;
            } else if ("rgb".equalsIgnoreCase(color)) {
                imageType = ImageType.RGB;
            } else if ("rgba".equalsIgnoreCase(color)) {
                imageType = ImageType.ARGB;
            }

            if (imageType == null) {
                System.err.println("Error: Invalid color.");
                System.exit(2);
            }

            //if a CropBox has been specified, update the CropBox:
            //changeCropBoxes(PDDocument document,float a, float b, float c,float d)
            if (cropBoxLowerLeftX != 0 || cropBoxLowerLeftY != 0 || cropBoxUpperRightX != 0
                    || cropBoxUpperRightY != 0) {
                changeCropBox(document, cropBoxLowerLeftX, cropBoxLowerLeftY, cropBoxUpperRightX,
                        cropBoxUpperRightY);
            }

            long startTime = System.nanoTime();

            // render the pages
            boolean success = true;
            endPage = Math.min(endPage, document.getNumberOfPages());
            PDFRenderer renderer = new PDFRenderer(document);
            for (int i = startPage - 1; i < endPage; i++) {
                BufferedImage image = renderer.renderImageWithDPI(i, dpi, imageType);
                String fileName = outputPrefix + "_" + (i + 1) + "." + imageFormat;
                success &= ImageIOUtil.writeImage(image, fileName, dpi);
            }

            // performance stats
            long endTime = System.nanoTime();
            long duration = endTime - startTime;
            int count = 1 + endPage - startPage;
            if (showTime) {
                System.err.printf("Rendered %d page%s in %dms\n", count, count == 1 ? "" : "s",
                        duration / 1000000);
            }

            if (!success) {
                System.err.println("Error: no writer found for image format '" + imageFormat + "'");
                System.exit(1);
            }
        } finally {
            if (document != null) {
                document.close();
            }
        }
    }
}

From source file:cz.incad.kramerius.k5indexer.KrameriusPDFDocument.java

private void setDocument() throws Exception {
    try {/*from   w w w. j  a  v  a2  s  .c om*/
        closeDocument();
        PDDocument pdDocument = PDDocument.load(stream,
                KConfiguration.getInstance().getConfiguration().getString("convert.pdfPassword"));
    } catch (Exception ex) {
        closeDocument();
        logger.log(Level.WARNING, "Cannot parse PDF document", ex);
    }

}

From source file:de.catma.document.source.contenthandler.PDFContentHandler.java

License:Open Source License

public void load(InputStream is) throws IOException {
    PDDocument document = null;/* ww  w. j  a  va2s  . co  m*/
    try {
        document = PDDocument.load(is, false);

        if (document.isEncrypted()) {
            throw new IOException("can not open pdf document because it is encrypted");
        }

        AccessPermission ap = document.getCurrentAccessPermission();
        if (!ap.canExtractContent()) {
            throw new IOException("You do not have permission to extract text");
        }

        PDFTextStripper stripper = new PDFTextStripper("UTF-8");

        stripper.setForceParsing(false);
        stripper.setSortByPosition(false);
        stripper.setShouldSeparateByBeads(true);
        stripper.setStartPage(1);
        stripper.setEndPage(Integer.MAX_VALUE);

        ByteArrayOutputStream os = new ByteArrayOutputStream();
        Writer w = new OutputStreamWriter(os);
        try {
            stripper.writeText(document, w);
        } finally {
            w.close();
        }
        // some pdfs seem to include non valid unicode characters
        // and this causes problems when converting text to HTML
        // for GUI delivery and during indexing 
        setContent(os.toString().replaceAll("[^\\x09\\x0A\\x0D\\x20-\\uD7FF\\uE000-\\uFFFD\\u10000-\\u10FFFF]",
                "?"));
    } finally {
        if (document != null) {
            document.close();
        }
    }
}

From source file:dk.defxws.fedoragsearch.server.TransformerToText.java

License:Open Source License

public int getPdfPagesCount_(byte[] doc) throws Exception {
    String password = "";
    PDDocument pdDoc = null;//from  w w w .jav  a  2s  .c om
    // extract PDF document's textual content
    try {
        pdDoc = PDDocument.load(new ByteArrayInputStream(doc), password);
        return pdDoc.getNumberOfPages();
    } catch (Exception e) {
        throw new Exception("Cannot parse PDF document", e);
    } finally {
        closePDDocument(pdDoc);
    }
}