List of usage examples for org.apache.pdfbox.pdmodel.common.filespecification PDComplexFileSpecification getFilename
public String getFilename()
Preferred method for getting the filename.
From source file:dev.ztgnrw.ExtractEmbeddedFiles.java
License:Apache License
/** * This is the main method./*from w ww . j a va 2 s. c om*/ * * @param args The command line arguments. * * @throws IOException If there is an error parsing the document. */ public static void extractEmbeddedFiles(String file) throws IOException { PDDocument document = null; try { File pdfFile = new File(file); String filePath = pdfFile.getParent() + System.getProperty("file.separator"); document = PDDocument.load(pdfFile); PDDocumentNameDictionary namesDictionary = new PDDocumentNameDictionary(document.getDocumentCatalog()); PDEmbeddedFilesNameTreeNode efTree = namesDictionary.getEmbeddedFiles(); if (efTree != null) { Map<String, PDComplexFileSpecification> names = efTree.getNames(); if (names != null) { extractFiles(names, filePath); } else { List<PDNameTreeNode<PDComplexFileSpecification>> kids = efTree.getKids(); for (PDNameTreeNode<PDComplexFileSpecification> node : kids) { names = node.getNames(); extractFiles(names, filePath); } } } // extract files from annotations for (PDPage page : document.getPages()) { for (PDAnnotation annotation : page.getAnnotations()) { if (annotation instanceof PDAnnotationFileAttachment) { PDAnnotationFileAttachment annotationFileAttachment = (PDAnnotationFileAttachment) annotation; PDComplexFileSpecification fileSpec = (PDComplexFileSpecification) annotationFileAttachment .getFile(); PDEmbeddedFile embeddedFile = getEmbeddedFile(fileSpec); extractFile(filePath, fileSpec.getFilename(), embeddedFile); } } } } finally { if (document != null) { document.close(); } } }
From source file:org.modeshape.sequencer.pdf.PdfBasicMetadata.java
License:Apache License
public boolean check() throws Exception { try (PDDocument document = PDDocument.load(in)) { PDDocumentCatalog catalog = document.getDocumentCatalog(); PDPageable pageable = new PDPageable(document); PageFormat firstPage = pageable.getPageFormat(0); encrypted = document.isEncrypted(); pageCount = document.getNumberOfPages(); orientation = ORIENTATION_STRINGS[firstPage.getOrientation()]; version = String.valueOf(document.getDocument().getVersion()); String catalogVersion = catalog.getVersion(); if (catalogVersion != null && !catalogVersion.isEmpty()) { // According to specs version saved here should be determining instead // the version in header. It is barely used, though. version = catalogVersion;/*from w w w. j av a 2 s . c o m*/ } if (!encrypted) { PDDocumentInformation metadata = document.getDocumentInformation(); author = metadata.getAuthor(); creationDate = metadata.getCreationDate(); creator = metadata.getCreator(); keywords = metadata.getKeywords(); modificationDate = metadata.getModificationDate(); producer = metadata.getProducer(); subject = metadata.getSubject(); title = metadata.getTitle(); } // extract all attached files from all pages int pageNumber = 0; for (Object page : catalog.getAllPages()) { pageNumber += 1; PdfPageMetadata pageMetadata = new PdfPageMetadata(); pageMetadata.setPageNumber(pageNumber); for (PDAnnotation annotation : ((PDPage) page).getAnnotations()) { if (annotation instanceof PDAnnotationFileAttachment) { PdfAttachmentMetadata attachmentMetadata = new PdfAttachmentMetadata(); PDAnnotationFileAttachment fann = (PDAnnotationFileAttachment) annotation; PDComplexFileSpecification fileSpec = (PDComplexFileSpecification) fann.getFile(); PDEmbeddedFile embeddedFile = fileSpec.getEmbeddedFile(); attachmentMetadata.setSubject(fann.getSubject()); attachmentMetadata.setName(fileSpec.getFilename()); attachmentMetadata.setCreationDate(embeddedFile.getCreationDate()); attachmentMetadata.setModificationDate(embeddedFile.getModDate()); attachmentMetadata.setMimeType(embeddedFile.getSubtype()); attachmentMetadata.setData(embeddedFile.getByteArray()); pageMetadata.addAttachment(attachmentMetadata); } } pages.add(pageMetadata); } return true; } }
From source file:org.pdfmetamodifier.IOHelper.java
License:Apache License
private static void extractFile(final File outputDir, final PDComplexFileSpecification fileSpec) throws IOException { final File file = new File(outputDir.getAbsolutePath() + File.separatorChar + fileSpec.getFilename()); final PDEmbeddedFile embeddedFile = getEmbeddedFile(fileSpec); Files.write(file.toPath(), embeddedFile.toByteArray()); }