List of usage examples for com.itextpdf.text.pdf PdfReader getInfo
public HashMap<String, String> getInfo()
HashMap of String. From source file:net.ionescu.jhocr2pdf.Jhocr2pdf.java
License:Open Source License
/** * @param args//from w w w.ja v a 2 s . c o m * The arguments are: * [options] output_pdf * The name of the output PDF file with the added OCR information must be the last argument * Other * flags: * -i pdf_file PDF file containing the TIFF images * -hocr html_file hOCR file generated by Tesseract * -visible render the text above the image (mostry for debugging) * -font font_path path to the font file to use * -hocrnameformat string to use to construct the name of the hocr file depending on page number * * Usage example: * java -jar jhorc2pdf.jar -font /usr/share/fonts/truetype/ttf-dejavu/DejaVuSans.ttf -i input.pdf -hocr input.html output.pdf * * @throws SAXException * @throws IOException * @throws DocumentException */ public static void main(String[] args) throws SAXException, IOException, DocumentException { /* * process input parameters * * -visible -font font_path inputPDF inputOCR outputPDF */ boolean visible = false; String fontPath = null; String fileNameFormat = null; String inputPDF = null; String inputHOCR = null; String outputPDF = null; for (int i = 0; i < args.length; i++) { if (args[i].startsWith("-")) { switch (args[i]) { case "-visible": visible = true; break; case "-font": fontPath = args[++i]; break; case "-hocrnameformat": fileNameFormat = args[++i]; break; case "-i": inputPDF = args[++i]; break; case "-hocr": inputHOCR = args[++i]; break; default: System.err.println("Invalid parameter: " + args[i]); System.exit(1); } } else { if (i < args.length - 1) { System.err.println("Ouput file name should be the last argument"); System.exit(1); } outputPDF = args[i]; } } log.fine("load the PDF file, initialize the Stamper"); PdfReader reader = new PdfReader(inputPDF); PdfStamper stamper = new PdfStamper(reader, new FileOutputStream(outputPDF)); Map<String, String> info = reader.getInfo(); info.put("Title", new File(outputPDF).getName()); stamper.setMoreInfo(info); Jhocr2pdf ocrStamp = new Jhocr2pdf(stamper, visible, fontPath); if (null != fileNameFormat) { log.fine("iterate through all the pages looking for separate hocr files"); for (int i = 1, maxPages = reader.getNumberOfPages() + 1; i < maxPages; i++) { String hocrFileName = String.format(fileNameFormat, i); try { ocrStamp.parse(hocrFileName, i); } catch (SAXException saxException) { System.err.println("Error processing hocr file: " + hocrFileName); throw saxException; } } } else { ocrStamp.parse(inputHOCR, -1); } stamper.close(); }
From source file:net.pflaeging.PortableSigner.PDFSigner.java
License:Open Source License
/** Creates a new instance of DoSignPDF */ public void doSignPDF(String pdfInputFileName, String pdfOutputFileName, String pkcs12FileName, String password, Boolean signText, String signLanguage, String sigLogo, Boolean finalize, String sigComment, String signReason, String signLocation, Boolean noExtraPage, float verticalPos, float leftMargin, float rightMargin, Boolean signLastPage, byte[] ownerPassword) throws PDFSignerException { try {/* w w w . java2 s .co m*/ //System.out.println("-> DoSignPDF <-"); //System.out.println("Eingabedatei: " + pdfInputFileName); //System.out.println("Ausgabedatei: " + pdfOutputFileName); //System.out.println("Signaturdatei: " + pkcs12FileName); //System.out.println("Signaturblock?: " + signText); //System.out.println("Sprache der Blocks: " + signLanguage); //System.out.println("Signaturlogo: " + sigLogo); System.err.println("Position V:" + verticalPos + " L:" + leftMargin + " R:" + rightMargin); Rectangle signatureBlock; java.security.Security.insertProviderAt(new org.bouncycastle.jce.provider.BouncyCastleProvider(), 2); pkcs12 = new GetPKCS12(pkcs12FileName, password); PdfReader reader = null; try { // System.out.println("Password:" + ownerPassword.toString()); if (ownerPassword == null) reader = new PdfReader(pdfInputFileName); else reader = new PdfReader(pdfInputFileName, ownerPassword); } catch (IOException e) { /* MODIFY BY: Denis Torresan Main.setResult( java.util.ResourceBundle.getBundle( "net/pflaeging/PortableSigner/i18n").getString( "CouldNotBeOpened"), true, e.getLocalizedMessage()); */ throw new PDFSignerException(java.util.ResourceBundle.getBundle("net/pflaeging/PortableSigner/i18n") .getString("CouldNotBeOpened"), true, e.getLocalizedMessage()); } FileOutputStream fout = null; try { fout = new FileOutputStream(pdfOutputFileName); } catch (FileNotFoundException e) { /* MODIFY BY: Denis Torresan Main.setResult( java.util.ResourceBundle.getBundle("net/pflaeging/PortableSigner/i18n").getString("CouldNotBeWritten"), true, e.getLocalizedMessage()); */ throw new PDFSignerException(java.util.ResourceBundle.getBundle("net/pflaeging/PortableSigner/i18n") .getString("CouldNotBeWritten"), true, e.getLocalizedMessage()); } PdfStamper stp = null; try { Date datum = new Date(System.currentTimeMillis()); int pages = reader.getNumberOfPages(); Rectangle size = reader.getPageSize(pages); stp = PdfStamper.createSignature(reader, fout, '\0', null, true); HashMap<String, String> pdfInfo = reader.getInfo(); // thanks to Markus Feisst String pdfInfoProducer = ""; if (pdfInfo.get("Producer") != null) { pdfInfoProducer = pdfInfo.get("Producer").toString(); pdfInfoProducer = pdfInfoProducer + " (signed with PortableSigner " + Version.release + ")"; } else { pdfInfoProducer = "Unknown Producer (signed with PortableSigner " + Version.release + ")"; } pdfInfo.put("Producer", pdfInfoProducer); //System.err.print("++ Producer:" + pdfInfo.get("Producer").toString()); stp.setMoreInfo(pdfInfo); ByteArrayOutputStream baos = new ByteArrayOutputStream(); XmpWriter xmp = new XmpWriter(baos, pdfInfo); xmp.close(); stp.setXmpMetadata(baos.toByteArray()); if (signText) { String greet, signator, datestr, ca, serial, special, note, urn, urnvalue; int specialcount = 0; int sigpage; int rightMarginPT, leftMarginPT; float verticalPositionPT; ResourceBundle block = ResourceBundle .getBundle("net/pflaeging/PortableSigner/Signatureblock_" + signLanguage); greet = block.getString("greeting"); signator = block.getString("signator"); datestr = block.getString("date"); ca = block.getString("issuer"); serial = block.getString("serial"); special = block.getString("special"); note = block.getString("note"); urn = block.getString("urn"); urnvalue = block.getString("urnvalue"); //sigcomment = block.getString(signLanguage + "-comment"); // upper y float topy = size.getTop(); System.err.println("Top: " + topy * ptToCm); // right x float rightx = size.getRight(); System.err.println("Right: " + rightx * ptToCm); if (!noExtraPage) { sigpage = pages + 1; stp.insertPage(sigpage, size); // 30pt left, 30pt right, 20pt from top rightMarginPT = 30; leftMarginPT = 30; verticalPositionPT = topy - 20; } else { if (signLastPage) { sigpage = pages; } else { sigpage = 1; } System.err.println("Page: " + sigpage); rightMarginPT = Math.round(rightMargin / ptToCm); leftMarginPT = Math.round(leftMargin / ptToCm); verticalPositionPT = topy - Math.round(verticalPos / ptToCm); } if (!GetPKCS12.atEgovOID.equals("")) { specialcount = 1; } PdfContentByte content = stp.getOverContent(sigpage); float[] cellsize = new float[2]; cellsize[0] = 100f; // rightx = width of page // 60 = 2x30 margins // cellsize[0] = description row // cellsize[1] = 0 // 70 = logo width cellsize[1] = rightx - rightMarginPT - leftMarginPT - cellsize[0] - cellsize[1] - 70; // Pagetable = Greeting, signatureblock, comment // sigpagetable = outer table // consist: greetingcell, signatureblock , commentcell PdfPTable signatureBlockCompleteTable = new PdfPTable(2); PdfPTable signatureTextTable = new PdfPTable(2); PdfPCell signatureBlockHeadingCell = new PdfPCell( new Paragraph(new Chunk(greet, new Font(Font.FontFamily.HELVETICA, 12)))); signatureBlockHeadingCell.setPaddingBottom(5); signatureBlockHeadingCell.setColspan(2); signatureBlockHeadingCell.setBorderWidth(0f); signatureBlockCompleteTable.addCell(signatureBlockHeadingCell); // inner table start // Line 1 signatureTextTable.addCell( new Paragraph(new Chunk(signator, new Font(Font.FontFamily.HELVETICA, 10, Font.BOLD)))); signatureTextTable.addCell( new Paragraph(new Chunk(GetPKCS12.subject, new Font(Font.FontFamily.COURIER, 10)))); // Line 2 signatureTextTable.addCell( new Paragraph(new Chunk(datestr, new Font(Font.FontFamily.HELVETICA, 10, Font.BOLD)))); signatureTextTable.addCell( new Paragraph(new Chunk(datum.toString(), new Font(Font.FontFamily.COURIER, 10)))); // Line 3 signatureTextTable.addCell( new Paragraph(new Chunk(ca, new Font(Font.FontFamily.HELVETICA, 10, Font.BOLD)))); signatureTextTable.addCell( new Paragraph(new Chunk(GetPKCS12.issuer, new Font(Font.FontFamily.COURIER, 10)))); // Line 4 signatureTextTable.addCell( new Paragraph(new Chunk(serial, new Font(Font.FontFamily.HELVETICA, 10, Font.BOLD)))); signatureTextTable.addCell(new Paragraph( new Chunk(GetPKCS12.serial.toString(), new Font(Font.FontFamily.COURIER, 10)))); // Line 5 if (specialcount == 1) { signatureTextTable.addCell(new Paragraph( new Chunk(special, new Font(Font.FontFamily.HELVETICA, 10, Font.BOLD)))); signatureTextTable.addCell(new Paragraph( new Chunk(GetPKCS12.atEgovOID, new Font(Font.FontFamily.COURIER, 10)))); } signatureTextTable.addCell( new Paragraph(new Chunk(urn, new Font(Font.FontFamily.HELVETICA, 10, Font.BOLD)))); signatureTextTable .addCell(new Paragraph(new Chunk(urnvalue, new Font(Font.FontFamily.COURIER, 10)))); signatureTextTable.setTotalWidth(cellsize); System.err.println( "signatureTextTable Width: " + cellsize[0] * ptToCm + " " + cellsize[1] * ptToCm); // inner table end signatureBlockCompleteTable.setHorizontalAlignment(PdfPTable.ALIGN_CENTER); Image logo; // System.out.println("Logo:" + sigLogo + ":"); if (sigLogo == null || "".equals(sigLogo)) { logo = Image.getInstance( getClass().getResource("/net/pflaeging/PortableSigner/SignatureLogo.png")); } else { logo = Image.getInstance(sigLogo); } PdfPCell logocell = new PdfPCell(); logocell.setVerticalAlignment(PdfPCell.ALIGN_MIDDLE); logocell.setHorizontalAlignment(PdfPCell.ALIGN_CENTER); logocell.setImage(logo); signatureBlockCompleteTable.addCell(logocell); PdfPCell incell = new PdfPCell(signatureTextTable); incell.setBorderWidth(0f); signatureBlockCompleteTable.addCell(incell); PdfPCell commentcell = new PdfPCell( new Paragraph(new Chunk(sigComment, new Font(Font.FontFamily.HELVETICA, 10)))); PdfPCell notecell = new PdfPCell( new Paragraph(new Chunk(note, new Font(Font.FontFamily.HELVETICA, 10, Font.BOLD)))); //commentcell.setPaddingTop(10); //commentcell.setColspan(2); // commentcell.setBorderWidth(0f); if (!sigComment.equals("")) { signatureBlockCompleteTable.addCell(notecell); signatureBlockCompleteTable.addCell(commentcell); } float[] cells = { 70, cellsize[0] + cellsize[1] }; signatureBlockCompleteTable.setTotalWidth(cells); System.err.println( "signatureBlockCompleteTable Width: " + cells[0] * ptToCm + " " + cells[1] * ptToCm); signatureBlockCompleteTable.writeSelectedRows(0, 4 + specialcount, leftMarginPT, verticalPositionPT, content); System.err.println( "signatureBlockCompleteTable Position " + 30 * ptToCm + " " + (topy - 20) * ptToCm); signatureBlock = new Rectangle(30 + signatureBlockCompleteTable.getTotalWidth() - 20, topy - 20 - 20, 30 + signatureBlockCompleteTable.getTotalWidth(), topy - 20); // ////// // AcroFields af = reader.getAcroFields(); // ArrayList names = af.getSignatureNames(); // for (int k = 0; k < names.size(); ++k) { // String name = (String) names.get(k); // System.out.println("Signature name: " + name); // System.out.println("\tSignature covers whole document: " + af.signatureCoversWholeDocument(name)); // System.out.println("\tDocument revision: " + af.getRevision(name) + " of " + af.getTotalRevisions()); // PdfPKCS7 pk = af.verifySignature(name); // X509Certificate tempsigner = pk.getSigningCertificate(); // Calendar cal = pk.getSignDate(); // Certificate pkc[] = pk.getCertificates(); // java.util.ResourceBundle tempoid = // java.util.ResourceBundle.getBundle("net/pflaeging/PortableSigner/SpecialOID"); // String tmpEgovOID = ""; // // for (Enumeration<String> o = tempoid.getKeys(); o.hasMoreElements();) { // String element = o.nextElement(); // // System.out.println(element + ":" + oid.getString(element)); // if (tempsigner.getNonCriticalExtensionOIDs().contains(element)) { // if (!tmpEgovOID.equals("")) { // tmpEgovOID += ", "; // } // tmpEgovOID += tempoid.getString(element) + " (OID=" + element + ")"; // } // } // //System.out.println("\tSigniert von: " + PdfPKCS7.getSubjectFields(pk.getSigningCertificate())); // System.out.println("\tSigniert von: " + tempsigner.getSubjectX500Principal().toString()); // System.out.println("\tDatum: " + cal.getTime().toString()); // System.out.println("\tAusgestellt von: " + tempsigner.getIssuerX500Principal().toString()); // System.out.println("\tSeriennummer: " + tempsigner.getSerialNumber()); // if (!tmpEgovOID.equals("")) { // System.out.println("\tVerwaltungseigenschaft: " + tmpEgovOID); // } // System.out.println("\n"); // System.out.println("\tDocument modified: " + !pk.verify()); //// Object fails[] = PdfPKCS7.verifyCertificates(pkc, kall, null, cal); //// if (fails == null) { //// System.out.println("\tCertificates verified against the KeyStore"); //// } else { //// System.out.println("\tCertificate failed: " + fails[1]); //// } // } // // ////// } else { signatureBlock = new Rectangle(0, 0, 0, 0); // fake definition } PdfSignatureAppearance sap = stp.getSignatureAppearance(); // sap.setCrypto(GetPKCS12.privateKey, GetPKCS12.certificateChain, null, // PdfSignatureAppearance.WINCER_SIGNED ); sap.setCrypto(GetPKCS12.privateKey, GetPKCS12.certificateChain, null, null); sap.setReason(signReason); sap.setLocation(signLocation); // if (signText) { // sap.setVisibleSignature(signatureBlock, // pages + 1, "PortableSigner"); // } if (finalize) { sap.setCertificationLevel(PdfSignatureAppearance.CERTIFIED_NO_CHANGES_ALLOWED); } else { sap.setCertificationLevel(PdfSignatureAppearance.NOT_CERTIFIED); } stp.close(); /* MODIFY BY: Denis Torresan Main.setResult( java.util.ResourceBundle.getBundle("net/pflaeging/PortableSigner/i18n").getString("IsGeneratedAndSigned"), false, ""); */ } catch (Exception e) { /* MODIFY BY: Denis Torresan Main.setResult( java.util.ResourceBundle.getBundle("net/pflaeging/PortableSigner/i18n").getString("ErrorWhileSigningFile"), true, e.getLocalizedMessage()); */ throw new PDFSignerException(java.util.ResourceBundle.getBundle("net/pflaeging/PortableSigner/i18n") .getString("ErrorWhileSigningFile"), true, e.getLocalizedMessage()); } } catch (KeyStoreException kse) { /* MODIFY BY: Denis Torresan Main.setResult(java.util.ResourceBundle.getBundle("net/pflaeging/PortableSigner/i18n").getString("ErrorCreatingKeystore"), true, kse.getLocalizedMessage()); */ throw new PDFSignerException(java.util.ResourceBundle.getBundle("net/pflaeging/PortableSigner/i18n") .getString("ErrorCreatingKeystore"), true, kse.getLocalizedMessage()); } }
From source file:net.sf.regain.crawler.preparator.PdfItextPreparator.java
License:Open Source License
/** * Prpariert ein Dokument fr die Indizierung. * * @param rawDocument Das zu prpariernde Dokument. * @throws net.sf.regain.RegainException Wenn die Prparation fehl schlug. *//* w w w .j av a 2 s . co m*/ @SuppressWarnings("unchecked") public void prepare(RawDocument rawDocument) throws RegainException { String url = rawDocument.getUrl(); InputStream stream = null; PdfReader reader = null; try { // Create a InputStream that reads the content. stream = rawDocument.getContentAsStream(); // Parse the content reader = new PdfReader(stream); if (reader.isEncrypted()) { reader = new PdfReader(stream, OWNER_PASSWORD); } PdfReaderContentParser parser = new PdfReaderContentParser(reader); TextExtractionStrategy strategy; StringBuilder stringBuilder = new StringBuilder(); for (int i = 1; i <= reader.getNumberOfPages(); i++) { strategy = parser.processContent(i, new SimpleTextExtractionStrategy()); stringBuilder.append(strategy.getResultantText()); } setCleanedContent(stringBuilder.toString()); // Get metadata Map<String, String> info = reader.getInfo(); StringBuilder metaData = new StringBuilder(); metaData.append("p."); metaData.append(Integer.toString(reader.getNumberOfPages())); metaData.append(" "); // Check if fields are null String author = info.get("Author"); String creator = info.get("Creator"); String subject = info.get("Subject"); String keywords = info.get("Keywords"); String title = info.get("Title"); if (author != null) { metaData.append(author); metaData.append(" "); } if (creator != null) { metaData.append(creator); metaData.append(" "); } if (subject != null) { metaData.append(subject); metaData.append(" "); } if (keywords != null) { metaData.append(keywords); metaData.append(" "); } if (title != null) { setTitle(title); } setCleanedMetaData(metaData.toString()); if (log.isDebugEnabled()) { log.debug("Extracted meta data ::" + getCleanedMetaData() + ":: from " + rawDocument.getUrl()); } } catch (IOException exc) { throw new RegainException("Error reading document: " + url, exc); } catch (Exception exc) { // They didn't supply a password and the default of "" was wrong. throw new RegainException("Unknown error parsing document: " + url, exc); } finally { if (stream != null) { try { stream.close(); } catch (Exception exc) { } } if (reader != null) { try { reader.close(); } catch (Exception exc) { } } } }
From source file:org.ednovo.gooru.domain.service.resource.ResourceServiceImpl.java
License:Open Source License
/** * @param mainFileUrl/*from w w w.j a v a 2 s . c om*/ * : PDF file that has to be splitted * @param splittedPageSize * : Page size of each splitted files */ private static String splitAndSaveChapter(String mainFileUrl, int pageBeginNum, int pageEndNum, String name) { try { PdfReader reader = new PdfReader(mainFileUrl); int splittedPageSize = pageEndNum - pageBeginNum + 1; int pageNum = pageBeginNum; String chapterUrl = mainFileUrl.substring(0, mainFileUrl.indexOf(DOT_PDF)) + "-" + name + DOT_PDF; Document document = new Document(reader.getPageSizeWithRotation(1)); FileOutputStream fos = new FileOutputStream(chapterUrl); PdfCopy writer = new PdfCopy(document, fos); Map<String, String> info = reader.getInfo(); document.open(); if ((info != null) && (info.get(_AUTHOR) != null)) { document.addAuthor(info.get(_AUTHOR)); } document.addTitle(name); for (int offset = 0; offset < splittedPageSize && (pageNum + offset) < pageEndNum; offset++) { PdfImportedPage page = writer.getImportedPage(reader, pageNum + offset); writer.addPage(page); } document.close(); writer.close(); return chapterUrl; } catch (Exception e) { e.printStackTrace(); return null; } }
From source file:org.pdfsam.pdf.DefaultITextLoader.java
License:Open Source License
public void accept(PdfReader reader, PdfDocumentDescriptor descriptor) { descriptor.pages(reader.getNumberOfPages()); descriptor.setVersion(new PdfVersionAdapter(Character.toString(reader.getPdfVersion())).getEnumValue()); Map<String, String> info = reader.getInfo(); descriptor.setInformationDictionary(info); Optional.ofNullable(PdfDate.decode(info.get("CreationDate"))).map(FORMATTER::format) .ifPresent(c -> descriptor.putInformation("FormattedCreationDate", c)); }
From source file:org.pdfsam.pdf.ITextPdfLoadService.java
License:Open Source License
public void load(Collection<PdfDocumentDescriptor> toLoad) { LOG.debug(DefaultI18nContext.getInstance().i18n("Loading")); for (PdfDocumentDescriptor current : toLoad) { if (!current.isInvalid()) { LOG.trace("Loading {}", current.getFileName()); PdfReader reader = null; try { current.moveStatusTo(LOADING); reader = current.toPdfFileSource().open(new DefaultPdfSourceOpener()); current.setPages(reader.getNumberOfPages()); current.setVersion(String.format("1.%c", reader.getPdfVersion())); current.setInformationDictionary(reader.getInfo()); if (current.hasPassword()) { current.moveStatusTo(LOADED_WITH_USER_PWD_DECRYPTION); } else { current.moveStatusTo(LOADED); }// w ww . j a v a 2s. c o m } catch (TaskWrongPasswordException twpe) { current.moveStatusTo(ENCRYPTED); LOG.warn("User password required for '{}'", current.getFileName(), twpe); } catch (Exception e) { LOG.error("An error occured loading the document '{}'", current.getFileName(), e); current.moveStatusTo(WITH_ERRORS); } finally { try { nullSafeClosePdfReader(reader); } catch (RuntimeException e) { LOG.warn("An error occured closing the document", e); } } } else { LOG.trace("Skipping invalid document {}", current.getFileName()); } } LOG.debug(DefaultI18nContext.getInstance().i18n("Documents loaded")); }
From source file:org.sejda.impl.itext5.component.PdfStamperHandler.java
License:Open Source License
/** * Creates a new instance initializing the inner {@link PdfStamper} instance. * /* w w w .j av a 2s . co m*/ * @param reader * input reader * @param ouputFile * {@link File} to stamp on * @param version * version for the created stamper, if null the version number is taken from the input {@link PdfReader} * @throws TaskException * in case of error */ public PdfStamperHandler(PdfReader reader, File ouputFile, PdfVersion version) throws TaskException { try { ouputStream = new FileOutputStream(ouputFile); if (version != null) { stamper = new PdfStamper(reader, ouputStream, version.getVersionAsCharacter()); } else { stamper = new PdfStamper(reader, ouputStream); } Map<String, String> meta = reader.getInfo(); meta.put(PdfMetadataKey.CREATOR.getKey(), Sejda.CREATOR); stamper.setMoreInfo(meta); } catch (DocumentException e) { throw new TaskException("An error occurred opening the PdfStamper.", e); } catch (IOException e) { throw new TaskIOException("An IO error occurred opening the PdfStamper.", e); } }
From source file:renamergroup.FileFinderThread.java
public void run() { while (!renamerframe.fileExploreEnded() || !fileList.isEmpty()) { try {/* ww w .j a v a 2 s . c om*/ String fileDir = fileList.poll(); if (fileDir == null) continue; PdfReader reader = new PdfReader(fileDir); Map<String, String> info = reader.getInfo(); String author = info.get("Author"); String title = info.get("Title"); String subject = info.get("Subject"); String keywords = info.get("Keywords"); if (mainframe.isMatched(author, "author") || mainframe.isMatched(title, "title") || mainframe.isMatched(subject, "subject") || mainframe.isMatched(keywords, "keywords")) { renamerframe.initListToRename(fileDir); } info.clear(); reader.close(); } catch (IOException ex) { System.out.println(ex.getMessage()); } } }
From source file:uk.bl.wa.tika.parser.pdf.itext.PDFParser.java
License:Apache License
private static void extractMetadata(PdfReader reader, Metadata metadata) { try {/*from w w w .j a v a 2 s .c o m*/ HashMap<String, String> map = reader.getInfo(); // Clone the PDF info: for (String key : map.keySet()) { metadata.set(key.toLowerCase(), map.get(key)); } // Add other data of interest: metadata.set("pdf:version", "1." + reader.getPdfVersion()); metadata.set("pdf:numPages", "" + reader.getNumberOfPages()); metadata.set("pdf:cryptoMode", "" + getCryptoModeAsString(reader)); metadata.set("pdf:openedWithFullPermissions", "" + reader.isOpenedWithFullPermissions()); metadata.set("pdf:encrypted", "" + reader.isEncrypted()); metadata.set("pdf:metadataEncrypted", "" + reader.isMetadataEncrypted()); metadata.set("pdf:128key", "" + reader.is128Key()); metadata.set("pdf:tampered", "" + reader.isTampered()); // Also grap XMP metadata, if present: byte[] xmpmd = reader.getMetadata(); if (xmpmd != null) { // This is standard Tika code for parsing standard stuff from the XMP: JempboxExtractor extractor = new JempboxExtractor(metadata); extractor.parse(new ByteArrayInputStream(xmpmd)); // This is custom XMP-handling code: XMPMetadata xmp = XMPMetadata.load(new ByteArrayInputStream(xmpmd)); // There is a special class for grabbing data in the PDF schema - not sure it will add much here: // Could parse xmp:CreatorTool and pdf:Producer etc. etc. out of here. //XMPSchemaPDF pdfxmp = xmp.getPDFSchema(); // Added a PDF/A schema class: xmp.addXMLNSMapping(XMPSchemaPDFA.NAMESPACE, XMPSchemaPDFA.class); XMPSchemaPDFA pdfaxmp = (XMPSchemaPDFA) xmp.getSchemaByClass(XMPSchemaPDFA.class); if (pdfaxmp != null) { metadata.set("pdfaid:part", pdfaxmp.getPart()); metadata.set("pdfaid:conformance", pdfaxmp.getConformance()); String version = "A-" + pdfaxmp.getPart() + pdfaxmp.getConformance().toLowerCase(); //metadata.set("pdfa:version", version ); metadata.set("pdf:version", version); } } // Attempt to determine Adobe extension level: PdfDictionary extensions = reader.getCatalog().getAsDict(PdfName.EXTENSIONS); if (extensions != null) { PdfDictionary adobeExt = extensions.getAsDict(PdfName.ADBE); if (adobeExt != null) { PdfName baseVersion = adobeExt.getAsName(PdfName.BASEVERSION); int el = adobeExt.getAsNumber(PdfName.EXTENSIONLEVEL).intValue(); metadata.set("pdf:version", baseVersion.toString().substring(1) + " Adobe Extension Level " + el); } } // Ensure the normalised metadata are mapped in: if (map.get("Title") != null) metadata.set(Metadata.TITLE, map.get("Title")); if (map.get("Author") != null) metadata.set(Metadata.AUTHOR, map.get("Author")); } catch (Exception e) { System.err.println("PDFParser.extractMetadata() caught Exception: " + e.getMessage()); e.printStackTrace(); } }