Example usage for com.itextpdf.text.pdf PdfReader getNumberOfPages

List of usage examples for com.itextpdf.text.pdf PdfReader getNumberOfPages

  1. HOME
  2. Java
  3. com.itextpdf
  4. com.itextpdf.text.pdf.*
  5. PdfReader
  6. getNumberOfPages

Introduction

In this page you can find the example usage for com.itextpdf.text.pdf PdfReader getNumberOfPages.

Prototype

public int getNumberOfPages()

Source Link

Document

Gets the number of pages in the document.

Usage

From source file:org.archive.modules.extractor.ExtractorPDFContent.java

License:Apache License

protected boolean innerExtract(CrawlURI curi) {
    PdfReader documentReader;
    ArrayList<String> uris = new ArrayList<String>();

    try {//from   w w w.j  av  a 2  s.  co  m
        documentReader = new PdfReader(curi.getRecorder().getContentReplayInputStream());

        for (int i = 1; i <= documentReader.getNumberOfPages(); i++) { //Page numbers start at 1
            String pageParseText = extractPageText(documentReader, i);
            Matcher matcher = URLPattern.matcher(pageParseText);

            while (matcher.find()) {
                String prospectiveURL = pageParseText.substring(matcher.start(), matcher.end()).trim();

                //handle URLs wrapped in parentheses
                if (prospectiveURL.startsWith("(")) {
                    prospectiveURL = prospectiveURL.substring(1, prospectiveURL.length());
                    if (prospectiveURL.endsWith(")"))
                        prospectiveURL = prospectiveURL.substring(0, prospectiveURL.length() - 1);
                }

                uris.add(prospectiveURL);

                //parsetext URLs tend to end in a '.' if they are in a sentence, queue without trailing '.'
                if (prospectiveURL.endsWith(".") && prospectiveURL.length() > 2)
                    uris.add(prospectiveURL.substring(0, prospectiveURL.length() - 1));

                //Full regex allows newlines which seem to be common, also add match without newline in case we are wrong
                if (matcher.group(19) != null) {
                    String alternateURL = matcher.group(1) + "://"
                            + (matcher.group(2) != null ? matcher.group(2) : "") + matcher.group(6)
                            + matcher.group(13);

                    //Again, handle URLs wrapped in parentheses
                    if (prospectiveURL.startsWith("(") && alternateURL.endsWith(")"))
                        alternateURL = alternateURL.substring(0, alternateURL.length() - 1);

                    uris.add(alternateURL);
                }
            }
        }

    } catch (IOException e) {
        curi.getNonFatalFailures().add(e);
        return false;
    } catch (RuntimeException e) {
        curi.getNonFatalFailures().add(e);
        return false;
    }

    if (uris.size() < 1) {
        return true;
    }

    for (String uri : uris) {
        try {
            LinkContext lc = LinkContext.NAVLINK_MISC;
            Hop hop = Hop.NAVLINK;
            CrawlURI out = curi.createCrawlURI(uri, lc, hop);
            curi.getOutLinks().add(out);
        } catch (URIException e1) {
            logUriError(e1, curi.getUURI(), uri);
        }
    }

    numberOfLinksExtracted.addAndGet(uris.size());

    LOGGER.fine(curi + " has " + uris.size() + " links.");
    // Set flag to indicate that link extraction is completed.
    return true;
}

From source file:org.ednovo.gooru.domain.service.resource.ResourceServiceImpl.java

License:Open Source License

private static List<String> splitToChaptersAndSaveFiles(String newLocalUrl) {
    try {/*w w w.  ja va  2s. c o  m*/

        HashMap<Integer, String> chapters = new HashMap<Integer, String>();
        ArrayList<Integer> pages = new ArrayList<Integer>();

        /** Call the split method with filename and page size as params **/
        PdfReader reader = new PdfReader(newLocalUrl);
        reader.consolidateNamedDestinations();
        List<HashMap<String, Object>> list = SimpleBookmark.getBookmark(reader);

        for (HashMap<String, Object> test : list) {
            String page = test.get(PAGE).toString();
            Integer num = Integer.parseInt(page.substring(0, page.indexOf(' ')));
            chapters.put(num, (String) test.get(_TITLE));
            pages.add(num);
        }

        int index = 1;
        List<String> chaptersUrls = new ArrayList<String>();
        for (Integer i : pages) {
            String chapterUrl = null;
            if (pages.size() != index) {
                chapterUrl = splitAndSaveChapter(newLocalUrl, i, pages.get(index), chapters.get(i));
            } else {
                chapterUrl = splitAndSaveChapter(newLocalUrl, i, reader.getNumberOfPages(), chapters.get(i));
            }
            index++;

            if (chapterUrl != null) {
                chaptersUrls.add(chapterUrl);
            }
        }
        return chaptersUrls;
    } catch (Exception ex) {
        return new ArrayList<String>();
    }
}

From source file:org.gmdev.pdftrick.engine.MergeFiles.java

License:Open Source License

/**
 * Materially multiple pdf files are written merged file on a disk 
 * @param list//  w  ww  .j  a  v a2 s.c o m
 * @param outputStream
 * @throws DocumentException
 * @throws IOException
 */
private void doMerge(List<StreamPwdContainer> list, OutputStream outputStream)
        throws DocumentException, IOException {
    HashMap<Integer, String> rotationFromPages = factory.getRotationFromPages();
    Document document = new Document();
    PdfWriter writer = PdfWriter.getInstance(document, outputStream);
    document.open();
    PdfContentByte cb = writer.getDirectContent();

    int z = 0;
    for (StreamPwdContainer boom : list) {

        InputStream in = boom.getIn();
        PdfReader reader = null;
        if (!boom.getPwd().equalsIgnoreCase("")) {
            reader = new PdfReader(in, boom.getPwd().getBytes());
        } else {
            reader = new PdfReader(in);
        }

        for (int i = 1; i <= reader.getNumberOfPages(); i++) {
            z++;
            int rotation = reader.getPageRotation(i);

            //set size
            Rectangle pageSize_ = reader.getPageSize(i);
            Rectangle pageSize = null;
            if (rotation == 270 || rotation == 90) {
                pageSize = new Rectangle(pageSize_.getHeight(), pageSize_.getWidth());
            } else {
                pageSize = pageSize_;
            }

            document.setPageSize(pageSize);
            writer.setCropBoxSize(pageSize);

            document.newPage();

            // import the page from source pdf
            PdfImportedPage page = writer.getImportedPage(reader, i);

            // add the page to the destination pdf
            if (rotation == 270) {
                cb.addTemplate(page, 0, 1.0f, -1.0f, 0, reader.getPageSizeWithRotation(i).getWidth(), 0);
                rotationFromPages.put(z, "" + rotation);
            } else if (rotation == 180) {
                cb.addTemplate(page, -1f, 0, 0, -1f, 0, 0);
                rotationFromPages.put(z, "" + rotation);
            } else if (rotation == 90) {
                cb.addTemplate(page, 0, -1f, 1f, 0, 0, reader.getPageSizeWithRotation(i).getHeight());
                rotationFromPages.put(z, "" + rotation);
            } else {
                cb.addTemplate(page, 1f, 0, 0, 1f, 0, 0);
            }
        }
        in.close();
    }
    outputStream.flush();
    document.close();
    outputStream.close();
}

From source file:org.gmdev.pdftrick.render.PdfRenderLeft.java

License:Open Source License

/**
 * Render pdf resultfile thumbs in a left_panel, using threads pool
 *///from   www  .ja  v a 2  s .c o m
public void pdfRender() {
    String imgPath = PdfTrickUtils.createImgFolder();
    int totPages = 0;

    // get the page number of the new generated pdf
    try {
        PdfReader reader = new PdfReader(factory.getResultFile());
        totPages = reader.getNumberOfPages();
        factory.setNumPages(totPages);
        reader.close();
    } catch (Exception e) {
        logger.error("Exception", e);
        PdfTrickMessages.append("ERROR", Consts.SENDLOG_MSG);
    }

    // system of thread that call native function and renderizing pdf cover in png images 
    boolean runPool = true;
    int division = totPages / 3;
    if (totPages < 3) {
        runPool = false;
        division = totPages;
    }

    DivisionThumb divisionThumbs = new DivisionThumb(division, imgPath);
    factory.gettContainer().setDivisionThumbs(divisionThumbs);

    Thread divisionThumbsThread = new Thread(divisionThumbs, "divisionThumbsThread");
    factory.gettContainer().setDivisionThumbsThread(divisionThumbsThread);
    divisionThumbsThread.start();

    if (runPool) {
        ExecPool execPool = new ExecPool(totPages, division, imgPath);
        factory.gettContainer().setExecPool(execPool);

        Thread execPoolThread = new Thread(execPool, "execPoolThread");
        factory.gettContainer().setExecPoolThread(execPoolThread);
        execPoolThread.start();
    }

    // thread that search and showing thumbnails 
    ShowThumbs showThumbs = new ShowThumbs();
    factory.gettContainer().setShowThumbs(showThumbs);

    Thread showThumbsThread = new Thread(showThumbs, "showThumbsThread");
    factory.gettContainer().setShowThumbsThread(showThumbsThread);
    showThumbsThread.start();
}

From source file:org.h819.commons.file.MyPDFUtils.java

/**
 * ??//from   w ww .ja va 2 s. co m
 *
 * @param srcPdf         ?
 * @param destPdf        
 * @param waterMarkText  ?
 * @param waterMarkImage ?
 */
public static void addWaterMarkFile(File srcPdf, File destPdf, String waterMarkText, File waterMarkImage)
        throws IOException, DocumentException {

    if (waterMarkText == null && waterMarkImage == null)
        throw new FileNotFoundException(waterMarkText + " " + waterMarkImage + " all null.");

    if (srcPdf == null || !srcPdf.exists() || !srcPdf.isFile())
        throw new FileNotFoundException("pdf file :  '" + srcPdf + "' does not exsit.");

    if (!FilenameUtils.getExtension(srcPdf.getAbsolutePath()).toLowerCase().equals("pdf"))
        return;

    if (waterMarkImage != null) {
        if (!waterMarkImage.exists() || !waterMarkImage.isFile())
            throw new FileNotFoundException("img file :  '" + srcPdf + "' does not exsit.");

        if (!FilenameUtils.getExtension(waterMarkImage.getAbsolutePath()).toLowerCase().equals("png"))
            throw new FileNotFoundException("image file '" + srcPdf
                    + "'  not png.(???? pdf )");
    }

    PdfReader reader = getPdfReader(srcPdf);

    int n = reader.getNumberOfPages();
    PdfStamper stamper = getPdfStamper(srcPdf, destPdf);

    //
    //        HashMap<String, String> moreInfo = new HashMap<String, String>();
    //        moreInfo.put("Author", "H819 create");
    //        moreInfo.put("Producer", "H819 Producer");
    //        Key = CreationDate, Value = D:20070425182920
    //        Key = Producer, Value = TH-OCR 2000 (C++/Win32)
    //        Key = Author, Value = TH-OCR 2000
    //        Key = Creator, Value = TH-OCR PDF Writer

    // stamp.setMoreInfo(moreInfo);

    // text
    Phrase text = null;
    if (waterMarkText != null) {
        //
        Font bfont = getPdfFont();
        bfont.setSize(35);
        bfont.setColor(new BaseColor(192, 192, 192));
        text = new Phrase(waterMarkText, bfont);
    }
    // image watermark
    Image img = null;
    float w = 0;
    float h = 0;
    if (waterMarkImage != null) {
        img = Image.getInstance(waterMarkImage.getAbsolutePath());
        w = img.getScaledWidth();
        h = img.getScaledHeight();
        //  img.
        img.setRotationDegrees(45);

    }

    // transparency
    PdfGState gs1 = new PdfGState();
    gs1.setFillOpacity(0.5f);
    // properties
    PdfContentByte over;
    Rectangle pageSize;
    float x, y;
    // loop over every page
    for (int i = 1; i <= n; i++) {
        pageSize = reader.getPageSizeWithRotation(i);
        x = (pageSize.getLeft() + pageSize.getRight()) / 2;
        y = (pageSize.getTop() + pageSize.getBottom()) / 2;
        //  pdf pdf ???
        over = stamper.getOverContent(i);
        // ?
        // over = stamp.getUnderContent(i);
        // ?? over.beginText(); over.endText(); ?
        // ,?,:????
        over.saveState(); //??
        over.setGState(gs1);

        if (waterMarkText != null && waterMarkImage != null) { // 
            if (i % 2 == 1) {
                ColumnText.showTextAligned(over, Element.ALIGN_CENTER, text, x, y, 45);
            } else
                over.addImage(img, w, 0, 0, h, x - (w / 2), y - (h / 2));
        } else if (waterMarkText != null) { //?

            ColumnText.showTextAligned(over, Element.ALIGN_CENTER, text, x, y, 45);
            //?? ,?, :?????
            // ...

        } else { //?
            over.addImage(img, w, 0, 0, h, x - (w / 2), y - (h / 2));
        }

        over.restoreState();//???
    }

    stamper.close();
    reader.close();

}

From source file:org.h819.commons.file.MyPDFUtils.java

/**
 * ? pdf ??//from  w w w  . j a va  2  s . com
 *
 * @param srcPdfFile  the original PDF
 * @param descPdfFile the resulting PDF
 * @throws java.io.IOException
 * @throws DocumentException
 */
public static void compressPdf(File srcPdfFile, File descPdfFile) throws IOException, DocumentException {

    if (srcPdfFile == null || !srcPdfFile.exists())
        throw new IOException("src pdf file '" + srcPdfFile + "' does not exsit.");

    PdfReader reader = getPdfReader(srcPdfFile);
    PdfStamper stamper = new PdfStamper(reader, new FileOutputStream(descPdfFile.getAbsoluteFile()),
            PdfWriter.VERSION_1_7);

    stamper.getWriter().setCompressionLevel(9);
    int total = reader.getNumberOfPages() + 1;
    for (int i = 1; i < total; i++) {
        reader.setPageContent(i, reader.getPageContent(i));
    }
    stamper.setFullCompression();
    stamper.close();
    reader.close();
}

From source file:org.h819.commons.file.MyPDFUtils.java

/**
 * ?pdf/*w w w.j  av a2s .  co  m*/
 *
 * @param srcPdfFile  the original PDF
 * @param descPdfFile the resulting PDF
 * @throws java.io.IOException
 * @throws DocumentException
 */
public static void decompressPdf(File srcPdfFile, File descPdfFile) throws IOException, DocumentException {

    if (srcPdfFile == null || !srcPdfFile.exists())
        throw new IOException("src pdf file '" + srcPdfFile + "' does not exsit.");

    PdfReader reader = getPdfReader(srcPdfFile);
    PdfStamper stamper = new PdfStamper(reader, new FileOutputStream(descPdfFile.getAbsoluteFile()));
    stamper.getWriter().setCompressionLevel(PdfStream.NO_COMPRESSION);
    int total = reader.getNumberOfPages() + 1;
    for (int i = 1; i < total; i++) {
        reader.setPageContent(i, reader.getPageContent(i));
    }
    stamper.close();
    reader.close();

}

From source file:org.h819.commons.file.MyPDFUtils.java

/**
 * ?//  ww w .java2 s. c  o  m
 * <p>
 * ? iText in Action 2nd EditionChapter 6: Working with existing PDFs
 * Concatenate
 * </p>
 *
 * @param files  ?
 * @param result ??
 * @throws DocumentException
 * @throws java.io.IOException
 */
public static void merge(File[] files, File result) throws DocumentException, IOException {
    // step 1
    Document document = new Document();
    // step 2

    /**
     * PdfCopy  PdfSmartCopy 
     *
     * PdfCopy???
     *
     * PdfSmartCopy??????
     */
    //
    // PdfCopy copy = new PdfCopy(document, new FileOutputStream(result));
    PdfSmartCopy copy = new PdfSmartCopy(document, new FileOutputStream(result));
    // step 3
    document.open();
    // step 4
    PdfReader reader;
    int n;
    // loop over the documents you want to concatenate
    for (int i = 0; i < files.length; i++) {
        reader = getPdfReader(files[i]);
        // loop over the pages in that document
        n = reader.getNumberOfPages();
        for (int page = 0; page < n;) {
            copy.addPage(copy.getImportedPage(reader, ++page));
        }
        copy.freeReader(reader);
    }
    // step 5
    document.close();
}

From source file:org.h819.commons.file.MyPDFUtils.java

/**
 * pdf??? getPageCount()/*from  w w  w .j ava 2  s  .c o m*/
 *
 * @param srcPDFFileDir 
 * @return
 * @throws IOException
 */
private static void countNumberOfPagesOfDir(File srcPDFFileDir) throws IOException {

    if (srcPDFFileDir == null || !srcPDFFileDir.isDirectory())
        throw new FileNotFoundException(srcPDFFileDir + "'is null or dose not exist.");

    Collection<File> listPDFs = FileUtils.listFiles(srcPDFFileDir, null, true);
    for (File f : listPDFs) {

        // 
        if (f.isDirectory())
            countNumberOfPagesOfDir(f);

        if (!FilenameUtils.getExtension(f.getName().toUpperCase()).equals("PDF"))
            continue;
        // System.out.println(f.getPath());
        // we create a reader for a certain document
        PdfReader reader = getPdfReader(f);
        // we retrieve the total number of pages
        // 
        if (reader.isEncrypted())
            continue;

        numberOfPagesOfDirectory = numberOfPagesOfDirectory + reader.getNumberOfPages();

    }
}

From source file:org.jfree.chart.swt.ChartPdf.java

License:Open Source License

public static void saveChartAsPDF(File file, JFreeChart chart, int width, int height)
        throws DocumentException, FileNotFoundException, IOException {
    if (chart != null) {
        boolean success = false;
        String old = null;/* ww  w .  j  a va  2  s . c  o m*/
        File oldFile = null;
        boolean append = file.exists();
        if (append) {
            old = file.getAbsolutePath() + ".old"; //$NON-NLS-1$
            oldFile = new File(old);
            oldFile.delete();
            file.renameTo(oldFile);
        }
        try (BufferedOutputStream out = new BufferedOutputStream(new FileOutputStream(file))) {
            // convert chart to PDF with iText:
            Rectangle pagesize = new Rectangle(width, height);
            if (append) {
                PdfReader reader = new PdfReader(old);
                PdfStamper stamper = new PdfStamper(reader, out);
                try {
                    int n = reader.getNumberOfPages() + 1;
                    stamper.insertPage(n, pagesize);
                    PdfContentByte overContent = stamper.getOverContent(n);
                    writeChart(chart, width, height, overContent);
                    ColumnText ct = new ColumnText(overContent);
                    ct.setSimpleColumn(width - 50, 50, width - 12, height, 150, Element.ALIGN_RIGHT);
                    Paragraph paragraph = new Paragraph(String.valueOf(n),
                            new Font(FontFamily.HELVETICA, 9, Font.NORMAL, BaseColor.DARK_GRAY));
                    paragraph.setAlignment(Element.ALIGN_RIGHT);
                    ct.addElement(paragraph);
                    ct.go();
                    success = true;
                } finally {
                    stamper.close();
                    reader.close();
                    oldFile.delete();
                }
            } else {
                Document document = new Document(pagesize, 50, 50, 50, 50);
                document.addCreationDate();
                document.addCreator(Constants.APPLICATION_NAME);
                document.addAuthor(System.getProperty("user.name")); //$NON-NLS-1$
                try {
                    PdfWriter writer = PdfWriter.getInstance(document, out);
                    document.open();
                    writeChart(chart, width, height, writer.getDirectContent());
                    success = true;
                } finally {
                    document.close();
                }
            }
        }
        if (!success) {
            file.delete();
            if (oldFile != null)
                oldFile.renameTo(file);
        }
    }
}