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

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

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

Introduction

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

Prototype

public boolean isEncrypted()

Source Link

Document

This will tell if this document is encrypted or not.

Usage

From source file:org.opencps.util.ExtractTextLocations.java

License:Open Source License

public ExtractTextLocations(String fullPath) throws IOException {

    PDDocument document = null;

    try {//from ww w .  ja v  a 2  s . c  om
        File input = new File(fullPath);
        document = PDDocument.load(input);

        if (document.isEncrypted()) {
            try {
                document.decrypt(StringPool.BLANK);
            } catch (Exception e) {
                _log.error(e);
            }
        }

        // ExtractTextLocations printer = new ExtractTextLocations();

        List allPages = document.getDocumentCatalog().getAllPages();
        if (allPages != null && allPages.size() > 0) {
            PDPage page = (PDPage) allPages.get(0);

            PDStream contents = page.getContents();
            if (contents != null) {
                this.processStream(page, page.findResources(), page.getContents().getStream());
            }

            PDRectangle pageSize = page.findMediaBox();
            if (pageSize != null) {
                setPageWidth(pageSize.getWidth());
                setPageHeight(pageSize.getHeight());
                setPageLLX(pageSize.getLowerLeftX());
                setPageURX(pageSize.getUpperRightX());
                setPageLLY(pageSize.getLowerLeftY());
                setPageURY(pageSize.getUpperRightY());
            }
        }
    } catch (Exception e) {
        _log.error(e);
    } finally {
        if (document != null) {
            document.close();
        }
    }
}

From source file:org.paxle.parser.pdf.impl.PdfParser.java

License:Open Source License

public IParserDocument parse(URI location, String charset, InputStream fileIn)
        throws ParserException, UnsupportedEncodingException, IOException {
    IParserDocument parserDoc = null;//  w  w  w.ja v a  2 s.  c  om
    PDDocument pddDoc = null;

    try {
        final IParserContext pc = this.contextLocal.getCurrentContext();
        final ICommandProfile cmdProfile = pc.getCommandProfile();

        // create an empty document         
        parserDoc = pc.createDocument();

        // parse it
        final PDFParser parser = new PDFParser(fileIn);
        parser.parse();
        pddDoc = parser.getPDDocument();

        // check document encryption
        if (pddDoc.isEncrypted()) {
            if (this.logger.isDebugEnabled()) {
                this.logger.debug(String.format("Document '%s' is encrypted.", location));
            }

            // determine the decryption password
            String pwd = "";
            if (cmdProfile != null) {
                String tmp = (String) cmdProfile.getProperty("org.paxle.parser.pdf.impl.decryptionPassword");
                if (tmp != null)
                    pwd = tmp;
            }

            // try to open document with the given password
            try {
                final StandardDecryptionMaterial dm = new StandardDecryptionMaterial(pwd);
                pddDoc.openProtection(dm);
                final AccessPermission accessPermission = pddDoc.getCurrentAccessPermission();

                if (accessPermission == null || !accessPermission.canExtractContent()) {
                    if (this.logger.isInfoEnabled()) {
                        this.logger.debug(
                                String.format("No permission to extract content of document '%s'.", location));
                    }
                    parserDoc.setStatus(IParserDocument.Status.FAILURE, "PDF Document is encrypted.");
                    return parserDoc;
                }
            } catch (Throwable e) {
                this.logger.error(String.format("Unable to decrypt document '%s'.", location), e);
                parserDoc.setStatus(IParserDocument.Status.FAILURE, String
                        .format("Unable to decrypt document. %s: %s", e.getClass().getName(), e.getMessage()));
                return parserDoc;
            }
        }

        // extract metadata
        this.extractMetaData(parserDoc, pddDoc);

        // extract text
        final PDFTextStripper stripper = new PDFTextStripper();

        // XXX: we could limit the amount of parsed pages via crawling-profile properties?
        // stripper.setStartPage(startPageValue);
        // stripper.setEndPage(endPageValue);

        final Writer pdocWriter = parserDoc.getTextWriter();
        stripper.writeText(pddDoc, pdocWriter);
        pdocWriter.flush();

        // extracting URIs
        this.extractURLs(parserDoc, pddDoc);

        // extracting embedded files
        this.extractEmbeddedFiles(location, parserDoc, pddDoc);

        parserDoc.setStatus(IParserDocument.Status.OK);
        return parserDoc;
    } catch (Throwable e) {
        throw new ParserException("Error parsing pdf document. " + e.getMessage(), e);
    } finally {
        if (pddDoc != null)
            try {
                pddDoc.close();
            } catch (Exception e) {
                this.logger.error(e);
            }
    }
}

From source file:org.pdfgal.pdfgal.validator.impl.PDFGalValidatorImpl.java

License:Open Source License

@Override
public boolean isEncrypted(final String path) {

    boolean result = false;

    PDDocument document;
    try {// www  . j  a  va 2 s.  c o m
        document = PDDocument.load(path);
        result = document.isEncrypted();
        document.close();
    } catch (final IOException e) {
        result = false;
    }

    return result;
}

From source file:org.pdfmetamodifier.IOHelper.java

License:Apache License

/**
 * Save Outlines (bookmarks).//  ww w  .  ja v  a  2  s  .c om
 * 
 * @param pdfFile
 *            Source PDF file.
 * @param outlinesFile
 *            File with Outlines (bookmarks) in user-frendly format.
 * @throws IOException
 */
/*
 * See:
 *      https://svn.apache.org/viewvc/pdfbox/trunk/examples/src/main/java/org/apache/pdfbox/examples/pdmodel/PrintBookmarks.java?view=markup
 */
public static void saveOutlines(final File pdfFile, final File outlinesFile) throws IOException {
    PDDocument document = null;
    try {
        // Read PDF file.
        document = PDDocument.load(pdfFile);
        if (document.isEncrypted()) {
            throw new IOException("Document is encrypted.");
        }

        // Get data from PDF file.
        final PDDocumentCatalog catalog = document.getDocumentCatalog();

        final PDDocumentOutline outlines = catalog.getDocumentOutline();

        final PDPageTree pages = catalog.getPages();

        final PDDocumentNameDictionary namesDictionary = new PDDocumentNameDictionary(catalog);
        final PDDestinationNameTreeNode destinations = namesDictionary.getDests();

        // Convert.
        final List<String> lines = OutlineHelper.outlinesToLineList(outlines, pages, destinations);

        // Write line list into the text file.
        Files.write(outlinesFile.toPath(), lines);
    } finally {
        if (document != null) {
            document.close();
        }
    }
}

From source file:org.pdfmetamodifier.IOHelper.java

License:Apache License

/**
 * Update Outlines (bookmarks)./*from   ww w.  j a  v a  2s .  com*/
 * 
 * @param pdfFile
 *            Source PDF file.
 * @param outlinesFile
 *            File with Outlines (bookmarks) in user-frendly format.
 * @throws IOException
 */
/*
 * See:
 *      https://svn.apache.org/viewvc/pdfbox/trunk/examples/src/main/java/org/apache/pdfbox/examples/pdmodel/CreateBookmarks.java?view=markup
 */
public static void updateOutlines(final File pdfFile, final File outlinesFile) throws IOException {
    // Read bookmark list from text file.
    final List<String> lines = Files.readAllLines(outlinesFile.toPath());

    PDDocument document = null;
    try {
        // Open PDF file.
        document = PDDocument.load(pdfFile);
        if (document.isEncrypted()) {
            throw new IOException("Document is encrypted.");
        }

        // Get data from PDF file.
        final PDDocumentCatalog catalog = document.getDocumentCatalog();

        final PDPageTree pages = catalog.getPages();

        // Convert.
        final PDDocumentOutline outlines = OutlineHelper.lineListToOutlines(pages, lines);

        // Set outlines.
        catalog.setDocumentOutline(outlines);

        // Create temporary PDF file for result.
        if (TEMP_PDF.exists()) {
            TEMP_PDF.delete();
        }

        // Save result to temporary PDF file.
        document.save(TEMP_PDF);

        // Replace original PDF file.
        pdfFile.delete();
        Files.move(Paths.get(TEMP_PDF.toURI()), Paths.get(pdfFile.toURI()));
    } finally {
        if (document != null) {
            document.close();
        }
    }
}

From source file:org.pdfmetamodifier.IOHelper.java

License:Apache License

/**
 * Save Metadata.//from ww w .ja  v a  2s.c  om
 * 
 * @param pdfFile
 *            Source PDF file.
 * @param metadataFile
 *            File with Metadata in user-frendly format.
 * @throws IOException
 */
/*
 * See:
 *      https://svn.apache.org/viewvc/pdfbox/trunk/examples/src/main/java/org/apache/pdfbox/examples/pdmodel/ExtractMetadata.java?view=markup
 */
public static void saveMetadata(final File pdfFile, final File metadataFile) throws IOException {
    PDDocument document = null;
    try {
        // Read PDF file.
        document = PDDocument.load(pdfFile);
        if (document.isEncrypted()) {
            throw new IOException("Document is encrypted.");
        }

        // Get data from PDF file.
        final PDDocumentInformation information = document.getDocumentInformation();

        // Convert.
        final List<String> lines = MetadataHelper.metadataToLineList(information);

        // Write line list into the text file.
        Files.write(metadataFile.toPath(), lines);
    } finally {
        if (document != null) {
            document.close();
        }
    }
}

From source file:org.pdfmetamodifier.IOHelper.java

License:Apache License

/**
 * Update Metadata.//  w w  w .j a  v a  2 s.  c om
 * 
 * @param pdfFile
 *            Source PDF file.
 * @param metadataFile
 *            File with Metadata in user-frendly format.
 * @throws IOException
 */
/*
 * See:
 *      https://svn.apache.org/viewvc/pdfbox/trunk/examples/src/main/java/org/apache/pdfbox/examples/pdmodel/ExtractMetadata.java?view=markup
 */
public static void updateMetadata(final File pdfFile, final File metadataFile) throws IOException {
    // Read bookmark list from text file.
    final List<String> lines = Files.readAllLines(metadataFile.toPath());

    PDDocument document = null;
    try {
        // Open PDF file.
        document = PDDocument.load(pdfFile);
        if (document.isEncrypted()) {
            throw new IOException("Document is encrypted.");
        }

        // Convert.
        final PDDocumentInformation information = MetadataHelper.stringListToMetadata(lines);

        // Set Metadata.
        document.setDocumentInformation(information);

        // Create temporary PDF file for result.
        if (TEMP_PDF.exists()) {
            TEMP_PDF.delete();
        }

        // Save result to temporary PDF file.
        document.save(TEMP_PDF);

        // Replace original PDF file.
        pdfFile.delete();
        Files.move(Paths.get(TEMP_PDF.toURI()), Paths.get(pdfFile.toURI()));
    } finally {
        if (document != null) {
            document.close();
        }
    }
}

From source file:org.pdfmetamodifier.IOHelper.java

License:Apache License

/**
 * Save all Attached (embedded) files to some directory.
 * // w  w w  .j  av a 2s  .c o m
 * @param pdfFile
 *            Source PDF file.
 * @param outputDir
 *            Target directory.
 * @throws IOException
 */
/*
 * See:
 *      https://svn.apache.org/viewvc/pdfbox/trunk/examples/src/main/java/org/apache/pdfbox/examples/pdmodel/ExtractEmbeddedFiles.java?view=markup
 */
public static void saveAttachments(final File pdfFile, final File outputDir) throws IOException {
    PDDocument document = null;
    try {
        // Read PDF file.
        document = PDDocument.load(pdfFile);
        if (document.isEncrypted()) {
            throw new IOException("Document is encrypted.");
        }

        // Extract Embedded (attached) files.
        final PDDocumentNameDictionary documentNameDictionary = new PDDocumentNameDictionary(
                document.getDocumentCatalog());
        final PDEmbeddedFilesNameTreeNode embeddedFilesNameTree = documentNameDictionary.getEmbeddedFiles();
        if (embeddedFilesNameTree != null) {
            extractFiles(outputDir, embeddedFilesNameTree.getNames());

            final List<PDNameTreeNode<PDComplexFileSpecification>> kids = embeddedFilesNameTree.getKids();
            if (kids != null) {
                for (PDNameTreeNode<PDComplexFileSpecification> nameTreeNode : kids) {
                    extractFiles(outputDir, nameTreeNode.getNames());
                }
            }
        }

        // Extract Embedded (attached) from annotations.
        for (PDPage page : document.getPages()) {
            for (PDAnnotation annotation : page.getAnnotations()) {
                if (annotation instanceof PDAnnotationFileAttachment) {
                    final PDAnnotationFileAttachment fileAttach = (PDAnnotationFileAttachment) annotation;

                    final PDComplexFileSpecification fileSpec = (PDComplexFileSpecification) fileAttach
                            .getFile();
                    extractFile(outputDir, fileSpec);
                }
            }
        }
    } finally {
        if (document != null) {
            document.close();
        }
    }
}

From source file:org.pdfmetamodifier.IOHelper.java

License:Apache License

/**
 * Remove all Attached (embedded) files.
 * /*from  w w w .j av  a 2  s  .  c o m*/
 * @param pdfFile
 *            Source PDF file.
 * @throws IOException
 */
public static void removeAttachments(final File pdfFile) throws IOException {
    PDDocument document = null;
    try {
        // Read PDF file.
        document = PDDocument.load(pdfFile);
        if (document.isEncrypted()) {
            throw new IOException("Document is encrypted.");
        }

        // Clean the tree to the document catalog.
        document.getDocumentCatalog().setNames(null);

        // Create temporary PDF file for result.
        if (TEMP_PDF.exists()) {
            TEMP_PDF.delete();
        }

        // Save result to temporary PDF file.
        document.save(TEMP_PDF);

        // Replace original PDF file.
        pdfFile.delete();
        Files.move(Paths.get(TEMP_PDF.toURI()), Paths.get(pdfFile.toURI()));
    } finally {
        if (document != null) {
            document.close();
        }
    }
}

From source file:org.pdfmetamodifier.IOHelper.java

License:Apache License

/**
 * Add new Attached (embedded) files./*  w  w  w.  j  av  a2s  . c om*/
 * 
 * @param pdfFile
 *            Source PDF file.
 * @param attachmentFiles
 *            Files that will be attached (embedded).
 * @throws IOException
 */
/*
 * See:
 *      https://svn.apache.org/viewvc/pdfbox/trunk/examples/src/main/java/org/apache/pdfbox/examples/pdmodel/EmbeddedFiles.java?view=markup
 */
public static void addAttachments(final File pdfFile, final List<File> attachmentFiles) throws IOException {
    PDDocument document = null;
    try {
        // Read PDF file.
        document = PDDocument.load(pdfFile);
        if (document.isEncrypted()) {
            throw new IOException("Document is encrypted.");
        }

        // Embedded (attached) files are stored in a named tree.
        final PDEmbeddedFilesNameTreeNode root = new PDEmbeddedFilesNameTreeNode();
        final List<PDEmbeddedFilesNameTreeNode> kids = new ArrayList<PDEmbeddedFilesNameTreeNode>();
        root.setKids(kids);

        // Add the tree to the document catalog.
        final PDDocumentNameDictionary namesDictionary = new PDDocumentNameDictionary(
                document.getDocumentCatalog());
        namesDictionary.setEmbeddedFiles(root);
        document.getDocumentCatalog().setNames(namesDictionary);

        // For all Embedded (attached) files.
        for (File file : attachmentFiles) {
            final String filename = file.getName();

            // First create the file specification, which holds the Embedded (attached) file.
            final PDComplexFileSpecification complexFileSpecification = new PDComplexFileSpecification();
            complexFileSpecification.setFile(filename);

            // Create a dummy file stream, this would probably normally be a FileInputStream.
            final ByteArrayInputStream fileStream = new ByteArrayInputStream(Files.readAllBytes(file.toPath()));
            final PDEmbeddedFile embededFile = new PDEmbeddedFile(document, fileStream);
            complexFileSpecification.setEmbeddedFile(embededFile);

            // Create a new tree node and add the Embedded (attached) file.
            final PDEmbeddedFilesNameTreeNode embeddedFilesNameTree = new PDEmbeddedFilesNameTreeNode();
            embeddedFilesNameTree.setNames(Collections.singletonMap(filename, complexFileSpecification));

            // Add the new node as kid to the root node.
            kids.add(embeddedFilesNameTree);
        }

        // Create temporary PDF file for result.
        if (TEMP_PDF.exists()) {
            TEMP_PDF.delete();
        }

        // Save result to temporary PDF file.
        document.save(TEMP_PDF);

        // Replace original PDF file.
        pdfFile.delete();
        Files.move(Paths.get(TEMP_PDF.toURI()), Paths.get(pdfFile.toURI()));
    } finally {
        if (document != null) {
            document.close();
        }
    }
}