List of usage examples for org.apache.pdfbox.pdmodel PDDocumentCatalog getPageLayout
public PageLayout getPageLayout()
From source file:org.nuxeo.pdf.PDFInfo.java
License:Open Source License
/** * After building the object with the correct constructor, and after * possibly having set some parsing property (<code>setParseWithXMP()</code> * for example), this method will extract the information from the PDF. * <p>/*from w w w. j a v a 2 s.co m*/ * After extraction, caller get the info: Either all of them ( * <code>toHashMap()</code> or <code>toString()</code>) or individual info * (see all getters) * * @throws ClientException * * @since 5.9.5 */ public void run() throws ClientException { // In case the caller calls several time the run() method if (!alreadyParsed) { fileName = pdfBlob.getFilename(); // Getting the file size os ok only if the blob is already backed by // a // File. If it is pure Stream, we give up File pdfFile = BlobHelper.getFileFromBlob(pdfBlob); if (pdfFile == null) { fileSize = -1; } else { fileSize = pdfFile.length(); } try { pdfDoc = PDDocument.load(pdfBlob.getStream()); isEncrypted = pdfDoc.isEncrypted(); if (isEncrypted) { pdfDoc.openProtection(new StandardDecryptionMaterial(password)); } numberOfPages = pdfDoc.getNumberOfPages(); PDDocumentCatalog docCatalog = pdfDoc.getDocumentCatalog(); pageLayout = checkNotNull(docCatalog.getPageLayout()); pdfVersion = "" + pdfDoc.getDocument().getVersion(); PDDocumentInformation docInfo = pdfDoc.getDocumentInformation(); author = checkNotNull(docInfo.getAuthor()); contentCreator = checkNotNull(docInfo.getCreator()); keywords = checkNotNull(docInfo.getKeywords()); creationDate = docInfo.getCreationDate(); modificationDate = docInfo.getModificationDate(); producer = checkNotNull(docInfo.getProducer()); subject = checkNotNull(docInfo.getSubject()); title = checkNotNull(docInfo.getTitle()); // Getting dimension is a bit tricky mediaBoxWidthInPoints = -1; mediaBoxHeightInPoints = -1; cropBoxWidthInPoints = -1; cropBoxHeightInPoints = -1; List<PDPage> allPages = docCatalog.getAllPages(); boolean gotMediaBox = false; boolean gotCropBox = false; for (PDPage page : allPages) { if (page != null) { PDRectangle r = page.findMediaBox(); if (r != null) { mediaBoxWidthInPoints = r.getWidth(); mediaBoxHeightInPoints = r.getHeight(); gotMediaBox = true; } r = page.findCropBox(); if (r != null) { cropBoxWidthInPoints = r.getWidth(); cropBoxHeightInPoints = r.getHeight(); gotCropBox = true; } } if (gotMediaBox && gotCropBox) { break; } } if (doXMP) { xmp = null; PDMetadata metadata = docCatalog.getMetadata(); if (metadata != null) { xmp = ""; InputStream xmlInputStream = metadata.createInputStream(); InputStreamReader isr = new InputStreamReader(xmlInputStream); BufferedReader reader = new BufferedReader(isr); String line; do { line = reader.readLine(); if (line != null) { xmp += line + "\n"; } } while (line != null); reader.close(); } } } catch (IOException | BadSecurityHandlerException | CryptographyException e) { throw new ClientException(/* * "Cannot get PDF info: " + * e.getMessage(), */e); } finally { if (pdfDoc != null) { try { pdfDoc.close(); } catch (IOException e) { // Ignore } pdfDoc = null; } alreadyParsed = true; } } }