List of usage examples for com.itextpdf.text.pdf PdfReader getPageN
public PdfDictionary getPageN(final int pageNum)
From source file:Separator.java
License:Apache License
public static void crop(String inFileName, String outFileName, int split, boolean vert) throws Exception { PdfReader reader = new PdfReader(new File(inFileName).getAbsolutePath()); String PDFName = outFileName.substring(outFileName.lastIndexOf("Folder\\") + 7, outFileName.indexOf(".pdf")); File fn = new File(scanFolder + PDFName + "\\" + PDFName + "_split_" + split + ".pdf"); fn.getParentFile().mkdirs();/* www . j a v a 2 s.co m*/ int count = reader.getNumberOfPages(); Document doc = new Document(); PdfCopy copy = new PdfCopy(doc, new FileOutputStream(fn.getAbsolutePath())); doc.open(); if (vert) { for (int i = 1; i <= count; i++) { reader.getPageN(i).put(PdfName.CROPBOX, new PdfRectangle(PageSize.LETTER)); copy.addPage(copy.getImportedPage(reader, i)); } } else { if (!doubSided) { for (int j = 1; j <= count; j++) { reader.getPageN(j).put(PdfName.CROPBOX, new PdfRectangle((new Rectangle(0, 180, 792, 792)))); PdfDictionary pageDict; int rot = reader.getPageRotation(j); pageDict = reader.getPageN(j); pageDict.put(PdfName.ROTATE, new PdfNumber(rot + 90)); copy.addPage(copy.getImportedPage(reader, j)); } } else { for (int j = 1; j <= count; j++) { reader.getPageN(j).put(PdfName.CROPBOX, new PdfRectangle(new Rectangle(0, 180, 792, 792))); PdfDictionary pageDict; pageDict = reader.getPageN(j); if (j % 2 == 0) { // even pageDict.put(PdfName.ROTATE, new PdfNumber(270)); } else { // odd pageDict.put(PdfName.ROTATE, new PdfNumber(90)); } copy.addPage(copy.getImportedPage(reader, j)); } } } doc.close(); }
From source file:at.laborg.briss.CropManager.java
License:Open Source License
private static void cropMultipliedFile(File source, CropJob cropJob) throws FileNotFoundException, DocumentException, IOException { PdfReader reader = new PdfReader(source.getAbsolutePath()); PdfStamper stamper = new PdfStamper(reader, new FileOutputStream(cropJob.getDestinationFile())); stamper.setMoreInfo(cropJob.getSourceMetaInfo()); PdfDictionary pageDict;/* ww w.j ava 2 s .c om*/ int newPageNumber = 1; for (int origPageNumber = 1; origPageNumber <= cropJob.getSourcePageCount(); origPageNumber++) { SingleCluster cluster = cropJob.getClusterCollection().getSingleCluster(origPageNumber); // if no crop was selected do nothing if (cluster.getRatiosList().size() == 0) { newPageNumber++; continue; } for (Float[] ratios : cluster.getRatiosList()) { pageDict = reader.getPageN(newPageNumber); List<Rectangle> boxes = new ArrayList<Rectangle>(); boxes.add(reader.getBoxSize(newPageNumber, "media")); boxes.add(reader.getBoxSize(newPageNumber, "crop")); int rotation = reader.getPageRotation(newPageNumber); Rectangle scaledBox = calculateScaledRectangle(boxes, ratios, rotation); PdfArray scaleBoxArray = new PdfArray(); scaleBoxArray.add(new PdfNumber(scaledBox.getLeft())); scaleBoxArray.add(new PdfNumber(scaledBox.getBottom())); scaleBoxArray.add(new PdfNumber(scaledBox.getRight())); scaleBoxArray.add(new PdfNumber(scaledBox.getTop())); pageDict.put(PdfName.CROPBOX, scaleBoxArray); pageDict.put(PdfName.MEDIABOX, scaleBoxArray); // increment the pagenumber newPageNumber++; } int[] range = new int[2]; range[0] = newPageNumber - 1; range[1] = cropJob.getSourcePageCount() + (newPageNumber - origPageNumber); SimpleBookmark.shiftPageNumbers(cropJob.getSourceBookmarks(), cluster.getRatiosList().size() - 1, range); } stamper.setOutlines(cropJob.getSourceBookmarks()); stamper.close(); reader.close(); }
From source file:at.laborg.briss.utils.DocumentCropper.java
License:Open Source License
private static void cropMultipliedFile(final CropDefinition cropDefinition, final File multipliedDocument, final PdfMetaInformation pdfMetaInformation) throws DocumentException, IOException { PdfReader reader = new PdfReader(multipliedDocument.getAbsolutePath()); PdfStamper stamper = new PdfStamper(reader, new FileOutputStream(cropDefinition.getDestinationFile())); stamper.setMoreInfo(pdfMetaInformation.getSourceMetaInfo()); PdfDictionary pageDict;/*from w ww . j av a2 s . c o m*/ int newPageNumber = 1; for (int sourcePageNumber = 1; sourcePageNumber <= pdfMetaInformation .getSourcePageCount(); sourcePageNumber++) { List<Float[]> rectangleList = cropDefinition.getRectanglesForPage(sourcePageNumber); // if no crop was selected do nothing if (rectangleList.isEmpty()) { newPageNumber++; continue; } for (Float[] ratios : rectangleList) { pageDict = reader.getPageN(newPageNumber); List<Rectangle> boxes = new ArrayList<Rectangle>(); boxes.add(reader.getBoxSize(newPageNumber, "media")); boxes.add(reader.getBoxSize(newPageNumber, "crop")); int rotation = reader.getPageRotation(newPageNumber); Rectangle scaledBox = RectangleHandler.calculateScaledRectangle(boxes, ratios, rotation); PdfArray scaleBoxArray = createScaledBoxArray(scaledBox); pageDict.put(PdfName.CROPBOX, scaleBoxArray); pageDict.put(PdfName.MEDIABOX, scaleBoxArray); // increment the pagenumber newPageNumber++; } int[] range = new int[2]; range[0] = newPageNumber - 1; range[1] = pdfMetaInformation.getSourcePageCount() + (newPageNumber - sourcePageNumber); SimpleBookmark.shiftPageNumbers(pdfMetaInformation.getSourceBookmarks(), rectangleList.size() - 1, range); } stamper.setOutlines(pdfMetaInformation.getSourceBookmarks()); stamper.close(); reader.close(); }
From source file:com.betel.flowers.pdf.util.RemoveBlankPageFromPDF.java
public static void removeBlankPdfPages(String source, String destination) throws IOException, DocumentException { PdfReader r = null; RandomAccessSourceFactory rasf = null; RandomAccessFileOrArray raf = null;/*www. j a va 2s. c o m*/ Document document = null; PdfCopy writer = null; try { r = new PdfReader(source); // deprecated // RandomAccessFileOrArray raf // = new RandomAccessFileOrArray(pdfSourceFile); // itext 5.4.1 rasf = new RandomAccessSourceFactory(); raf = new RandomAccessFileOrArray(rasf.createBestSource(source)); document = new Document(r.getPageSizeWithRotation(1)); writer = new PdfCopy(document, new FileOutputStream(destination)); document.open(); PdfImportedPage page = null; for (int i = 1; i <= r.getNumberOfPages(); i++) { // first check, examine the resource dictionary for /Font or // /XObject keys. If either are present -> not blank. PdfDictionary pageDict = r.getPageN(i); PdfDictionary resDict = (PdfDictionary) pageDict.get(PdfName.RESOURCES); boolean noFontsOrImages = true; if (resDict != null) { noFontsOrImages = resDict.get(PdfName.FONT) == null && resDict.get(PdfName.XOBJECT) == null; } if (!noFontsOrImages) { byte bContent[] = r.getPageContent(i, raf); ByteArrayOutputStream bs = new ByteArrayOutputStream(); bs.write(bContent); if (bs.size() > BLANK_THRESHOLD) { page = writer.getImportedPage(r, i); writer.addPage(page); } } } } finally { if (document != null) { document.close(); } if (writer != null) { writer.close(); } if (raf != null) { raf.close(); } if (r != null) { r.close(); } } }
From source file:com.cib.statementstamper.windows.StatementStamperMainWindow.java
License:Open Source License
protected ByteArrayOutputStream doStamper(ByteArrayOutputStream baos) throws IOException, DocumentException { map.clear();//from w w w . j a va 2s .c om ByteArrayOutputStream baosFinal = new ByteArrayOutputStream(); PdfReader reader = new PdfReader(baos.toByteArray()); PdfContentStreamProcessor processor = new PdfContentStreamProcessor(this); for (int i = 1; i <= reader.getNumberOfPages(); i++) { actualPage = i; PdfDictionary pageDic = reader.getPageN(i); PdfDictionary resourcesDic = pageDic.getAsDict(PdfName.RESOURCES); processor.processContent(ContentByteUtils.getContentBytesForPage(reader, i), resourcesDic); } Document newDocument = new Document(PageSize.A4); PdfWriter writer = PdfWriter.getInstance(newDocument, baosFinal); newDocument.open(); PdfContentByte canvas = writer.getDirectContent(); // Font myFont = FontFactory.getFont(FontFactory.COURIER, 7, Font.BOLD); Iterator<Entry<Integer, Map<Float, StringBuffer>>> it = map.entrySet().iterator(); while (it.hasNext()) { Map.Entry<Integer, Map<Float, StringBuffer>> pairs = (Map.Entry<Integer, Map<Float, StringBuffer>>) it .next(); Iterator<Entry<Float, StringBuffer>> iter = pairs.getValue().entrySet().iterator(); while (iter.hasNext()) { Map.Entry<Float, StringBuffer> actualEntry = iter.next(); canvas.beginText(); canvas.setFontAndSize(myFontBase, 7); canvas.showTextAligned(Element.ALIGN_LEFT, actualEntry.getValue().toString(), 25, actualEntry.getKey() + 60, 0); canvas.endText(); } newDocument.newPage(); } newDocument.close(); reader = new PdfReader(baosFinal.toByteArray()); PdfReaderContentParser parser = new PdfReaderContentParser(reader); TextMarginFinder finder; for (int i = 1; i <= reader.getNumberOfPages(); i++) { finder = parser.processContent(i, new TextMarginFinder()); if (finder.getLly() <= 68) { getWindow().showNotification("Hiba", "A(z) " + i + ".ik oldalon tl sok a szveg !!!", Notification.TYPE_ERROR_MESSAGE); return null; } } reader = new PdfReader(baosFinal.toByteArray()); PdfStamper stamper = new PdfStamper(reader, baosFinal); int n = reader.getNumberOfPages(); for (int i = 1; i <= n; i++) { PdfContentByte overContent = stamper.getOverContent(i); overContent.addImage(logo, 131, 0, 0, 32, 44, 775); getFooterTable(i, n).writeSelectedRows(0, -1, 27, 68, stamper.getOverContent(i)); // ez a jo getIspLogoTable(i, n).writeSelectedRows(0, -1, 425, 45, stamper.getOverContent(i)); } stamper.close(); reader.close(); return baosFinal; }
From source file:commentextractor.CommentExtractorApp.java
License:GNU General Public License
static String extractComments(String filename, int first, int last) { StringBuffer output = null;// w w w. j a va2 s. c o m try { PdfReader reader = new PdfReader(filename); if (last >= reader.getNumberOfPages() || (last == -1)) { last = reader.getNumberOfPages(); } output = new StringBuffer(1024); for (int i = first; i <= last; i++) { PdfDictionary page = reader.getPageN(i); PdfArray annotsArray = null; if (page.getAsArray(PdfName.ANNOTS) == null) { continue; } annotsArray = page.getAsArray(PdfName.ANNOTS); for (ListIterator<PdfObject> iter = annotsArray.listIterator(); iter.hasNext();) { PdfDictionary annot = (PdfDictionary) PdfReader.getPdfObject(iter.next()); PdfString content = (PdfString) PdfReader.getPdfObject(annot.get(PdfName.CONTENTS)); if (content != null) { output.append("----------\n"); output.append("Page " + i); output.append("\n"); output.append(content.toUnicodeString().replaceAll("\r", "\r\n")); output.append("\n"); } } } } catch (Exception e) { Logger.getLogger(CommentExtractorApp.class.getName()).log(Level.SEVERE, null, e); } return new String(output); }
From source file:cz.muni.pdfjbim.PdfImageExtractor.java
License:Apache License
/** * Extracts JBIG2Images from Input stream even if they are stored together with global dictionary in separate PDF object * doesn't work yet, its in development stage * @param is/*from w w w.ja v a 2 s .c o m*/ * @throws PdfRecompressionException * @deprecated */ public void extractJbig2Images(InputStream is) throws PdfRecompressionException { if (is == null) { throw new IllegalArgumentException("InputStream not given"); } PdfReader pdfReader = null; try { pdfReader = new PdfReader(is); for (int i = 0; i <= pdfReader.getNumberOfPages(); i++) { PdfDictionary d = pdfReader.getPageN(i); PdfIndirectReference ir = d.getAsIndirectObject(PdfName.CONTENTS); PdfObject o = pdfReader.getPdfObject(ir.getNumber()); PdfStream stream = (PdfStream) o; PdfObject pdfsubtype = stream.get(PdfName.SUBTYPE); if (pdfsubtype != null && pdfsubtype.toString().equals(PdfName.IMAGE.toString())) { byte[] img = PdfReader.getStreamBytesRaw((PRStream) stream); OutputStream out = new FileOutputStream( new File("pdfRecompressor", String.format("%1$05d", i) + ".jpg")); out.write(img); out.flush(); out.close(); } } } catch (IOException ex) { log.error("IOException caught while trying to extract jbig2 images from PDF", ex); throw new PdfRecompressionException("IOException caught while trying to extract jbig2 images from PDF", ex); } finally { if (pdfReader != null) { pdfReader.close(); } } }
From source file:cz.muni.pdfjbim.PdfImageProcessor.java
License:Apache License
/** * replace images by they recompressed version according to JBIG2 standard * positions and image data given in imagesData * @param pdfName represents name of original PDF file * @param os represents output stream for writing changed PDF file * @param imagesData contains compressed images according to JBIG2 standard and informations about them * @throws PdfRecompressionException if version of PDF is lower than 1.4 or was catch DocumentException or IOException *///from w w w . j a v a 2 s. c o m public void replaceImageUsingIText(String pdfName, OutputStream os, Jbig2ForPdf imagesData) throws PdfRecompressionException { if (pdfName == null) { throw new NullPointerException("pdfName"); } if (os == null) { throw new NullPointerException("os"); } if (imagesData == null) { throw new NullPointerException("imagesData is null => nothing to recompress"); } Map<PdfObjId, PdfImage> jbig2Images = imagesData.getMapOfJbig2Images(); PdfReader pdf; PdfStamper stp = null; try { pdf = new PdfReader(pdfName); stp = new PdfStamper(pdf, os); PdfWriter writer = stp.getWriter(); int version; if ((version = Integer.parseInt(String.valueOf(pdf.getPdfVersion()))) < 4) { writer.setPdfVersion(PdfWriter.PDF_VERSION_1_4); } Iterator itImages = jbig2Images.values().iterator(); String key; if (itImages.hasNext()) { PdfImage myImg = (PdfImage) itImages.next(); key = myImg.getPdfImageInformation().getKey(); } else { key = "im0"; } for (int pageNum = 1; pageNum <= pdf.getNumberOfPages(); pageNum++) { PdfDictionary pg = pdf.getPageN(pageNum); PdfDictionary resPg = (PdfDictionary) PdfReader.getPdfObject(pg.get(PdfName.RESOURCES)); PdfDictionary xobjResPg = (PdfDictionary) PdfReader.getPdfObject(resPg.get(PdfName.XOBJECT)); PdfObject obj = null; if (xobjResPg != null) { for (Iterator it = xobjResPg.getKeys().iterator(); it.hasNext();) { PdfObject pdfObjIndirect = xobjResPg.get((PdfName) it.next()); if (pdfObjIndirect.isIndirect()) { PdfDictionary pdfObj2 = (PdfDictionary) PdfReader.getPdfObject(pdfObjIndirect); PdfDictionary xobj2Res = (PdfDictionary) PdfReader .getPdfObject(pdfObj2.get(PdfName.RESOURCES)); if (xobj2Res != null) { for (Iterator it2 = xobj2Res.getKeys().iterator(); it2.hasNext();) { PdfObject resObj = xobj2Res.get((PdfName) it2.next()); } PdfDictionary xobj = (PdfDictionary) PdfReader .getPdfObject(xobj2Res.get(PdfName.XOBJECT)); if (xobj == null) { continue; } obj = xobj.get(new PdfName(key)); } else { obj = xobjResPg.get(new PdfName(key)); if (obj == null) { obj = pdfObjIndirect; } } } } } if ((obj != null) && (obj.isIndirect())) { PdfDictionary tg = (PdfDictionary) PdfReader.getPdfObject(obj); if (tg == null) { continue; } PdfName type = (PdfName) PdfReader.getPdfObject(tg.get(PdfName.SUBTYPE)); if (PdfName.IMAGE.equals(type)) { PRIndirectReference ref = (PRIndirectReference) obj; PdfObjId imId = new PdfObjId(ref.getNumber(), ref.getGeneration()); PdfImage jbImage = jbig2Images.get(imId); if (jbImage == null) { continue; } PdfImageInformation jbImageInfo = jbImage.getPdfImageInformation(); Image img = Image.getInstance(jbImageInfo.getWidth(), jbImageInfo.getHeight(), jbImage.getImageData(), imagesData.getGlobalData()); PdfReader.killIndirect(obj); Image maskImage = img.getImageMask(); if (maskImage != null) { writer.addDirectImageSimple(maskImage); } writer.addDirectImageSimple(img, (PRIndirectReference) obj); } } } stp.close(); } catch (IOException ioEx) { throw new PdfRecompressionException(ioEx); } catch (DocumentException dEx) { throw new PdfRecompressionException(dEx); } finally { Tools.deleteFilesFromList(imagesData.getJbFiles().toArray(new File[0])); } }
From source file:cz.muni.pdfjbim.PdfImageReplacer.java
License:Apache License
/** * replace images by they recompressed version according to JBIG2 standard positions and image * data given in imagesData//w w w . ja v a 2 s.com * * @param originalPdf represents name of original PDF file * @param os represents output stream for writing changed PDF file * @param imagesData contains compressed images according to JBIG2 standard and informations * about them * @throws PdfRecompressionException if version of PDF is lower than 1.4 or was catch * DocumentException or IOException */ public void replaceImageUsingIText(InputStream originalPdf, OutputStream os, List<Jbig2ForPdf> imagesDataList) throws PdfRecompressionException { if (originalPdf == null) { throw new NullPointerException("pdfName"); } if (os == null) { throw new NullPointerException("os"); } if (imagesDataList == null) { throw new NullPointerException("imagesData is null => nothing to recompress"); } log.info("Replacing old images in PDF with their equivalent encoded according to standard JBIG2"); PdfReader pdf; PdfStamper stp = null; try { pdf = new PdfReader(originalPdf); stp = new PdfStamper(pdf, os); PdfWriter writer = stp.getWriter(); int version; if ((version = Integer.parseInt(String.valueOf(pdf.getPdfVersion()))) < 4) { log.debug("PDF version of original PDF was {} => changing to PDF version 1.4", pdf.getPdfVersion()); writer.setPdfVersion(PdfWriter.PDF_VERSION_1_4); } for (Jbig2ForPdf imagesData : imagesDataList) { Map<PdfObjId, PdfImage> jbig2Images = imagesData.getMapOfJbig2Images(); Iterator itImages = jbig2Images.values().iterator(); String key; if (itImages.hasNext()) { PdfImage myImg = (PdfImage) itImages.next(); key = myImg.getPdfImageInformation().getKey(); } else { key = "im0"; } for (int pageNum = 1; pageNum <= pdf.getNumberOfPages(); pageNum++) { PdfDictionary pg = pdf.getPageN(pageNum); PdfDictionary resPg = (PdfDictionary) PdfReader.getPdfObject(pg.get(PdfName.RESOURCES)); PdfDictionary xobjResPg = (PdfDictionary) PdfReader.getPdfObject(resPg.get(PdfName.XOBJECT)); PdfObject obj = null; if (xobjResPg != null) { for (Iterator it = xobjResPg.getKeys().iterator(); it.hasNext();) { PdfObject pdfObjIndirect = xobjResPg.get((PdfName) it.next()); if (pdfObjIndirect.isIndirect()) { PdfDictionary pdfObj2 = (PdfDictionary) PdfReader.getPdfObject(pdfObjIndirect); PdfDictionary xobj2Res = (PdfDictionary) PdfReader .getPdfObject(pdfObj2.get(PdfName.RESOURCES)); if (xobj2Res != null) { for (Iterator it2 = xobj2Res.getKeys().iterator(); it2.hasNext();) { PdfObject resObj = xobj2Res.get((PdfName) it2.next()); } PdfDictionary xobj = (PdfDictionary) PdfReader .getPdfObject(xobj2Res.get(PdfName.XOBJECT)); if (xobj == null) { continue; } obj = xobj.get(new PdfName(key)); } else { obj = xobjResPg.get(new PdfName(key)); if (obj == null) { obj = pdfObjIndirect; } } } } } if ((obj != null) && (obj.isIndirect())) { PdfDictionary tg = (PdfDictionary) PdfReader.getPdfObject(obj); if (tg == null) { continue; } PdfName type = (PdfName) PdfReader.getPdfObject(tg.get(PdfName.SUBTYPE)); if (PdfName.IMAGE.equals(type)) { PRIndirectReference ref = (PRIndirectReference) obj; PdfObjId imId = new PdfObjId(ref.getNumber(), ref.getGeneration()); PdfImage jbImage = jbig2Images.get(imId); if (jbImage == null) { continue; } log.debug("Replacing image {}", jbImage); PdfImageInformation jbImageInfo = jbImage.getPdfImageInformation(); Image img = Image.getInstance(jbImageInfo.getWidth(), jbImageInfo.getHeight(), jbImage.getImageData(), imagesData.getGlobalData()); PdfReader.killIndirect(obj); Image maskImage = img.getImageMask(); if (maskImage != null) { writer.addDirectImageSimple(maskImage); } writer.addDirectImageSimple(img, (PRIndirectReference) obj); } } } } } catch (IOException ioEx) { throw new PdfRecompressionException(ioEx); } catch (DocumentException dEx) { throw new PdfRecompressionException(dEx); } finally { log.debug("Deleting temporary files created during process of PDF recompression"); for (Jbig2ForPdf imagesData : imagesDataList) { Tools.deleteFilesFromList(imagesData.getJbFiles().toArray(new File[0])); } try { if (stp != null) { stp.close(); } } catch (DocumentException ex) { log.error("Exception thrown while closing stream", ex); } catch (IOException ex) { log.error("Exception thrown while closing stream", ex); } } }
From source file:de.gbv.marginalia.Marginalia.java
License:Open Source License
/** * Inspect a PDF file and write the info to a writer * @param writer Writer to a text file/*from w w w . j a va 2s . c o m*/ * @param filename Path to the PDF file * @throws IOException */ public static void inspect(PrintWriter writer, String filename) throws IOException, SAXException { // writer.println(filename); writer.flush(); PdfReader reader = new PdfReader(filename); ContentHandler xmlhandler = new SimpleXMLWriter(writer); xmlhandler.startDocument(); SimpleXMLCreator xml = new SimpleXMLCreator(xmlhandler, Annotation.namespaces, true); /* writer.println("Number of pages: "+reader.getNumberOfPages()); Rectangle mediabox = reader.getPageSize(1); writer.print("Size of page 1: ["); writer.print(mediabox.getLeft()); writer.print(','); writer.print(mediabox.getBottom()); writer.print(','); writer.print(mediabox.getRight()); writer.print(','); writer.print(mediabox.getTop()); writer.println("]"); writer.print("Rotation of page 1: "); writer.println(reader.getPageRotation(1)); writer.print("Page size with rotation of page 1: "); writer.println(reader.getPageSizeWithRotation(1)); writer.println(); writer.flush(); */ List<Annotation> annots = new LinkedList<Annotation>(); xml.startElement("annots"); // TODO: The following elements may be added: // - optionally write <f href="Document.pdf"/> // - optionally write <ids original="ID" modified="ID" /> xml.startElement("m", "pages"); for (int pageNum = 1; pageNum <= reader.getNumberOfPages(); pageNum++) { PdfDictionary pageDic = reader.getPageN(pageNum); Map<String, String> attr = new HashMap<String, String>(); attr.put("number", "" + pageNum); attr.put("rotate", "" + reader.getPageRotation(pageNum)); Rectangle mediabox = reader.getPageSize(pageNum); attr.put("left", "" + mediabox.getLeft()); attr.put("bottom", "" + mediabox.getBottom()); attr.put("right", "" + mediabox.getRight()); attr.put("top", "" + mediabox.getTop()); xml.contentElement("m", "page", "", attr); PdfArray rawannots = pageDic.getAsArray(PdfName.ANNOTS); if (rawannots == null || rawannots.isEmpty()) { // writer.println("page "+pageNum+" contains no annotations"); continue; } // writer.println("page "+pageNum+" has "+rawannots.size()+" annotations"); for (int i = 0; i < rawannots.size(); i++) { PdfObject obj = rawannots.getDirectObject(i); if (!obj.isDictionary()) continue; Annotation a = new Annotation((PdfDictionary) obj, pageNum); annots.add(a); } /** // Now we have all highlight and similar annotations, we need // to find out what words are actually highlighted! PDF in fact // is a dump format to express documents. // For some hints see // http://stackoverflow.com/questions/4028240/extract-each-column-of-a-pdf-file // We could reuse code from LocationTextExtractionStrategy (TODO) // LocationTextExtractionStrategy extr = new LocationTextExtractionStrategy(); String fulltext = PdfTextExtractor.getTextFromPage(reader,pageNum);//,extr writer.println(fulltext); */ } xml.endElement(); for (Annotation a : annots) { a.serializeXML(xmlhandler); } // TODO: add page information (page size and orientation) xml.endAll(); }