List of usage examples for com.itextpdf.text.pdf PdfDictionary get
public PdfObject get(final PdfName key)
PdfObject associated to the specified key. From source file:be.roots.taconic.pricingguide.util.iTextUtil.java
License:Open Source License
public static byte[] embedFont(byte[] pdf, String fontFileName, String fontName) throws IOException, DocumentException { try (ByteArrayOutputStream baos = new ByteArrayOutputStream()) { // the font file RandomAccessFile raf = new RandomAccessFile(fontFileName, "r"); byte fontfile[] = new byte[(int) raf.length()]; raf.readFully(fontfile);//from w ww . j av a 2s . c o m raf.close(); // create a new stream for the font file PdfStream stream = new PdfStream(fontfile); stream.flateCompress(); stream.put(PdfName.LENGTH1, new PdfNumber(fontfile.length)); // create a reader object PdfReader reader = new PdfReader(pdf); int n = reader.getXrefSize(); PdfObject object; PdfDictionary font; PdfStamper stamper = new PdfStamper(reader, baos); PdfName fontname = new PdfName(fontName); for (int i = 0; i < n; i++) { object = reader.getPdfObject(i); if (object == null || !object.isDictionary()) continue; font = (PdfDictionary) object; if (PdfName.FONTDESCRIPTOR.equals(font.get(PdfName.TYPE1)) && fontname.equals(font.get(PdfName.FONTNAME))) { PdfIndirectObject objref = stamper.getWriter().addToBody(stream); font.put(PdfName.FONTFILE2, objref.getIndirectReference()); } } stamper.close(); reader.close(); return baos.toByteArray(); } }
From source file:com.betel.flowers.pdf.util.RemoveBlankPageFromPDF.java
public static void removeBlankPdfPages(String source, String destination) throws IOException, DocumentException { PdfReader r = null;/* www.j a va 2 s. c o m*/ RandomAccessSourceFactory rasf = null; RandomAccessFileOrArray raf = null; 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: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 va2s. 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
private List<Image> getImagesFromPdfDict(PdfDictionary dict, PdfReader doc) throws IOException { List<Image> images = new ArrayList<Image>(); PdfDictionary res = (PdfDictionary) (PdfReader.getPdfObject(dict.get(PdfName.RESOURCES))); PdfDictionary xobj = (PdfDictionary) (PdfReader.getPdfObject(res.get(PdfName.XOBJECT))); if (xobj != null) { for (PdfName name : xobj.getKeys()) { PdfObject obj = xobj.get(name); if (obj.isIndirect()) { PdfDictionary tg = (PdfDictionary) (PdfReader.getPdfObject(obj)); PdfName subtype = (PdfName) (PdfReader.getPdfObject(tg.get(PdfName.SUBTYPE))); if (PdfName.IMAGE.equals(subtype)) { int xrefIdx = ((PRIndirectReference) obj).getNumber(); PdfObject pdfObj = doc.getPdfObject(xrefIdx); PdfStream str = (PdfStream) (pdfObj); byte[] bytes = PdfReader.getStreamBytesRaw((PRStream) str); String filter = tg.get(PdfName.FILTER).toString(); String width = tg.get(PdfName.WIDTH).toString(); String height = tg.get(PdfName.HEIGHT).toString(); String bpp = tg.get(PdfName.BITSPERCOMPONENT).toString(); if ("/FlateDecode".equals(filter)) { bytes = PdfReader.FlateDecode(bytes, true); try { images.add(Image.getInstance(bytes)); } catch (BadElementException ex) { log.warn("problem to process FlatDecoded Image", ex); }/*from w w w .ja v a 2s . com*/ } else if (PdfName.FORM.equals(subtype) || PdfName.GROUP.equals(subtype)) { images.addAll(getImagesFromPdfDict(tg, doc)); } } } } } return images; }
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 *//* ww w. j a va 2s.c om*/ 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//from w ww .ja v a 2s . c om * * @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.mat.utils.pdftools.PdfExtractEmptyPages.java
License:Mozilla Public License
/** * <h4>FeatureDomain:</h4>//w w w .j a v a 2 s. c o m * PublishingTools * <h4>FeatureDescription:</h4> * reads readerOrig and adds pages to writerRemoved if empty, or to * writerTrimmed if not empty * <h4>FeatureResult:</h4> * <ul> * <li>updates writerTrimmed - add all pages which are not empty * <li>updates writerRemoved - add all empty pages * </ul> * <h4>FeatureKeywords:</h4> * PDF Publishing * @param origFileName - orig filename of the sourcepdf * @param readerOrig - reader of source * @param writerTrimmed - writer for trimmed pages * @param writerRemoved - writer for empty pages * @param flgTrim - ?? * @return - count of trimmed pages * @throws Exception */ public static int addTrimmedPages(String origFileName, PdfReader readerOrig, PdfCopy writerTrimmed, PdfCopy writerRemoved, boolean flgTrim) throws Exception { PdfImportedPage page = null; int countTrimmedPages = 0; //loop each page for (int i = 1; i <= readerOrig.getNumberOfPages(); i++) { boolean flgIsEmpty = true; // get dictionary PdfDictionary pageDict = readerOrig.getPageN(i); // every pdf-version has its own way :-( char version = readerOrig.getPdfVersion(); if (version == '3') { // PDF-Version: 3 // examine the resource dictionary for /Font or // /XObject keys. If either are present, they're almost // certainly actually used on the page -> not blank. PdfObject myObj = pageDict.get(PdfName.RESOURCES); PdfDictionary resDict = null; if (myObj instanceof PdfDictionary) { resDict = (PdfDictionary) myObj; } else { resDict = (PdfDictionary) PdfReader.getPdfObject(myObj); } if (resDict != null) { flgIsEmpty = resDict.get(PdfName.FONT) == null && resDict.get(PdfName.XOBJECT) == null; if (LOGGER.isInfoEnabled()) { if (flgIsEmpty) { LOGGER.info("probably empty page " + i + " Version: 1." + version + " FONT/XOBJECT found in File:" + origFileName); } else { LOGGER.info("normal page " + i + " Version: 1." + version + " no FONT/XOBJECT found in File:" + origFileName); } } } } else if (version == '4') { // PDF-Version: 4 // check the contentsize. // get the page content byte bContent[] = readerOrig.getPageContent(i); ByteArrayOutputStream bs = new ByteArrayOutputStream(); // write the content to an output stream bs.write(bContent); flgIsEmpty = true; if (bs.size() > blankPdfsize) { if (LOGGER.isInfoEnabled()) LOGGER.info("normal page " + i + " Version: 1." + version + " BS:" + bs.size() + " File:" + origFileName); flgIsEmpty = false; } else { if (LOGGER.isInfoEnabled()) LOGGER.info("probably empty page " + i + " Version: 1." + version + " BS:" + bs.size() + " File:" + origFileName); } } else if (version == '5') { // PDF-Version: 5 // check the contentsize. // get the page content byte bContent[] = readerOrig.getPageContent(i); ByteArrayOutputStream bs = new ByteArrayOutputStream(); // write the content to an output stream bs.write(bContent); flgIsEmpty = true; if (bs.size() > blankPdfsize_v5) { if (LOGGER.isInfoEnabled()) LOGGER.info("normal page " + i + " Version: 1." + version + " BS:" + bs.size() + " File:" + origFileName); flgIsEmpty = false; } else { if (LOGGER.isInfoEnabled()) LOGGER.info("probably empty page " + i + " Version: 1." + version + " BS:" + bs.size() + " File:" + origFileName); } } // add page to removed or trimmed document if (!flgIsEmpty || !flgTrim) { if (LOGGER.isInfoEnabled()) LOGGER.info("add page " + i); page = writerTrimmed.getImportedPage(readerOrig, i); writerTrimmed.addPage(page); countTrimmedPages++; } else { if (LOGGER.isInfoEnabled()) LOGGER.info("skip page " + i + " Version: 1." + version + " File:" + origFileName); if (writerRemoved != null) { page = writerRemoved.getImportedPage(readerOrig, i); writerRemoved.addPage(page); } } } return countTrimmedPages; }
From source file:de.offis.health.icardea.cied.pdf.extractor.PDFiText5Extractor.java
License:GNU General Public License
@SuppressWarnings("unchecked") public java.util.List getBookmarkTitlesAsText() { java.util.List bookmarkContent = null; if (pdfReader != null) { //bookmarkContent = SimpleBookmark.getBookmark(pdfReader); PdfDictionary catalog = pdfReader.getCatalog(); if (catalog != null) { PdfObject rootPdfObject = PdfReader.getPdfObjectRelease(catalog.get(PdfName.OUTLINES)); if (rootPdfObject != null && rootPdfObject.isDictionary()) { PdfDictionary rootOutlinesPdfDictionary = (PdfDictionary) rootPdfObject; /*//from ww w. j ava 2 s .c o m * If it doesn't exist create the List and populate it, * otherwise just return the already existing List. */ if (bookmarkTextList == null) { bookmarkTextList = new ArrayList<String>(); // Populate the List populateBookmarkTextList(rootOutlinesPdfDictionary, ""); } // end if } } // end if } return bookmarkContent; }
From source file:de.offis.health.icardea.cied.pdf.extractor.PDFiText5Extractor.java
License:GNU General Public License
/** * This method will populate the text bookmark list. * //from ww w.jav a 2 s . c om * @param rootOutlinesPdfDictionary The node element for the bookmark item. * @param indentionString The base indention string to be used. */ @SuppressWarnings("unchecked") private void populateBookmarkTextList(PdfDictionary rootOutlinesPdfDictionary, String indentionString) { PdfDictionary outlineItemPdfDictionary = (PdfDictionary) PdfReader .getPdfObjectRelease(rootOutlinesPdfDictionary.get(PdfName.FIRST)); while (outlineItemPdfDictionary != null) { PdfString bookmarkTitle = (PdfString) PdfReader .getPdfObjectRelease(outlineItemPdfDictionary.get(PdfName.TITLE)); bookmarkTextList.add(indentionString + bookmarkTitle.toUnicodeString()); logger.trace(indentionString + bookmarkTitle.toUnicodeString()); /* * Recursive call to fill List */ populateBookmarkTextList(outlineItemPdfDictionary, indentionString + bookmarkIndentionString()); /* * Get next outline item */ outlineItemPdfDictionary = (PdfDictionary) PdfReader .getPdfObjectRelease(outlineItemPdfDictionary.get(PdfName.NEXT)); } // end while }
From source file:mkl.testarea.itext5.pdfcleanup.PdfCleanUpRenderListener.java
License:Open Source License
public void renderImage(ImageRenderInfo renderInfo) { List<Rectangle> areasToBeCleaned = getImageAreasToBeCleaned(renderInfo); if (areasToBeCleaned == null) { chunks.add(new PdfCleanUpContentChunk.Image(false, null)); } else {//w w w . ja v a 2 s . c o m try { PdfImageObject pdfImage = renderInfo.getImage(); byte[] imageBytes = processImage(pdfImage.getImageAsBytes(), areasToBeCleaned); if (renderInfo.getRef() == null && pdfImage != null) { // true => inline image PdfDictionary dict = pdfImage.getDictionary(); PdfObject imageMask = dict.get(PdfName.IMAGEMASK); Image image = Image.getInstance(imageBytes); if (imageMask == null) { imageMask = dict.get(PdfName.IM); } if (imageMask != null && imageMask.equals(PdfBoolean.PDFTRUE)) { image.makeMask(); } PdfContentByte canvas = getContext().getCanvas(); canvas.addImage(image, 1, 0, 0, 1, 0, 0, true); } else if (pdfImage != null && imageBytes != pdfImage.getImageAsBytes()) { chunks.add(new PdfCleanUpContentChunk.Image(true, imageBytes)); } } catch (Exception e) { throw new RuntimeException(e); } } }