Example usage for com.itextpdf.text.pdf PdfCopy PdfCopy

Introduction

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

Prototype

public PdfCopy(Document document, OutputStream os) throws DocumentException 

Source Link

Document

Constructor

Usage

From source file:oscar.dms.IncomingDocUtil.java

License:Open Source License

public static void extractPage(String queueId, String myPdfDir, String myPdfName, String pageNumbersToExtract)
        throws Exception {
    long lastModified;
    String filePathName, tempFilePathName;

    tempFilePathName = getIncomingDocumentFilePath(queueId, myPdfDir) + File.separator + "T" + myPdfName;
    filePathName = getIncomingDocumentFilePathName(queueId, myPdfDir, myPdfName);

    File f = new File(filePathName);
    lastModified = f.lastModified();/*from  w w  w  .  ja  v  a 2s. co m*/
    f.setReadOnly();

    String extractPath = getIncomingDocumentFilePath(queueId, myPdfDir) + File.separator;
    int index = myPdfName.toLowerCase().indexOf(".pdf");
    String myPdfNameF = myPdfName.substring(0, index);
    String myPdfNameExt = myPdfName.substring(index, myPdfName.length());

    ArrayList<String> extractList = new ArrayList<String>();
    int startPage, endPage;
    boolean cancelExtract = false;

    PdfReader reader = null;
    Document document = null;
    PdfCopy copy = null;
    PdfCopy extractCopy = null;

    try {
        reader = new PdfReader(filePathName);
        extractPath = extractPath + myPdfNameF + "E" + Integer.toString(reader.getNumberOfPages())
                + myPdfNameExt;

        for (int pgIndex = 0; pgIndex <= reader.getNumberOfPages(); pgIndex++) {
            extractList.add(pgIndex, "0");
        }

        String tmpPageNumbersToExtract = pageNumbersToExtract;
        String[] pageList = tmpPageNumbersToExtract.split(",");
        for (int i = 0; i < pageList.length; i++) {
            if (!pageList[i].isEmpty()) {
                String[] rangeList = pageList[i].split("-");
                if (rangeList.length > 2) {
                    cancelExtract = true;
                }
                for (int j = 0; j < rangeList.length; j++) {
                    if (!rangeList[j].matches("^[0-9]+$")) {
                        cancelExtract = true;
                    }
                }
                if (!cancelExtract) {
                    if (rangeList.length == 1) {
                        startPage = Integer.parseInt(rangeList[0], 10);
                        if (startPage > extractList.size() || startPage == 0) {
                            cancelExtract = true;
                        } else {
                            extractList.set(startPage, "1");
                        }
                    } else if (rangeList.length == 2) {
                        startPage = Integer.parseInt(rangeList[0], 10);
                        endPage = Integer.parseInt(rangeList[1], 10);

                        for (int k = startPage; k <= endPage; k++) {

                            if (k > extractList.size() || k == 0) {
                                cancelExtract = true;
                            } else {
                                extractList.set(k, "1");
                            }
                        }
                    }
                }
            }
        }
        if (!cancelExtract) {
            cancelExtract = true;
            for (int pageNumber = 1; pageNumber <= reader.getNumberOfPages(); pageNumber++) {
                if (!(extractList.get(pageNumber).equals("1"))) {
                    cancelExtract = false;
                }
            }
        }
        if (cancelExtract == true) {
            reader.close();
            throw new Exception(myPdfName + " : Invalid Pages to Extract " + pageNumbersToExtract);
        }

        document = new Document(reader.getPageSizeWithRotation(1));
        copy = new PdfCopy(document, new FileOutputStream(tempFilePathName));
        extractCopy = new PdfCopy(document, new FileOutputStream(extractPath));
        document.open();
        for (int pageNumber = 1; pageNumber <= reader.getNumberOfPages(); pageNumber++) {
            if (!(extractList.get(pageNumber).equals("1"))) {
                copy.addPage(copy.getImportedPage(reader, pageNumber));
            } else {
                extractCopy.addPage(copy.getImportedPage(reader, pageNumber));
            }
        }

    } catch (Exception e) {
        throw (e);
    } finally {
        try {
            if (copy != null) {
                copy.close();
            }
            if (extractCopy != null) {
                extractCopy.close();
            }

            if (document != null) {
                document.close();
            }

            if (reader != null) {
                reader.close();
            }

        } catch (Exception e) {
            throw (e);
        }
    }

    boolean success = f.delete();

    if (success) {
        File f1 = new File(tempFilePathName);
        f1.setLastModified(lastModified);
        success = f1.renameTo(new File(filePathName));
        if (!success) {
            throw new Exception("Error in renaming file from:" + tempFilePathName + "to " + filePathName);
        }

        File f2 = new File(extractPath);
        f2.setLastModified(lastModified);
    } else {
        throw new Exception("Error in deleting file:" + filePathName);
    }
}

---

From source file:pdfmt.pdf2image.java

License:Open Source License

/** 
 * Convert a PDF document to a TIF file 
 *//*from www  .  ja v  a 2s  .c  o  m*/
protected static void convert(String pdf, String tif, String destPdf) throws IOException {

    org.icepdf.core.pobjects.Document pdffile = new org.icepdf.core.pobjects.Document();

    try {
        pdffile.setFile(pdf);

    } catch (PDFException ex) {
        //  System.out.println("Error parsing PDF document " + ex); 
    } catch (PDFSecurityException ex) {
        //  System.out.println("Error encryption not supported " + ex); 
    } catch (FileNotFoundException ex) {
        // System.out.println("Error file not found " + ex); 
    } catch (IOException ex) {
        //  System.out.println("Error handling PDF document " + ex); 
    }

    int numPgs = pdffile.getNumberOfPages();

    try {
        // step 1: create new reader
        PdfReader r = new PdfReader(pdf);
        //  System.out.println("File Lenght:"  + r.getFileLength());
        RandomAccessFileOrArray raf = new RandomAccessFileOrArray(pdf);
        // System.out.println("Raf:" + raf);
        Document document = new Document(r.getPageSizeWithRotation(1));
        //           // step 2: create a writer that listens to the document
        PdfCopy writer = new PdfCopy(document, new FileOutputStream(destPdf));
        //           
        //           // step 3: we open the document
        document.open();
        //           // step 4: we add content
        PdfImportedPage page = null;
        //        
        //loop through each page and if the bs is larger than 20 than we know it is not blank.
        //if it is less than 20 than we don't include that blank page.

        float scale = 2.084f;
        float rotation = 0f;

        BufferedImage image[] = new BufferedImage[numPgs];

        for (int i = 0; i < numPgs; i++) {

            byte bContent[] = r.getPageContent(i + 1, raf);
            // System.out.println(bContent.toString());

            ByteArrayOutputStream bs = new ByteArrayOutputStream();
            //write the content to an output stream
            bs.write(bContent);

            //System.out.println("page content length of page " + i+1 + " = "
            //      + bs.size());

            /* 
             * Generate the image: 
             * Notes: 1275x1650 = 8.5 x 11 @ 150dpi ??? 
             */
            image[i] = (BufferedImage) pdffile.getPageImage(i, GraphicsRenderingHints.SCREEN,
                    Page.BOUNDARY_CROPBOX, rotation, scale);
            Iterator writers = ImageIO.getImageWritersByFormatName("TIFF");
            if (writers == null || !writers.hasNext()) {
                throw new RuntimeException("No writers for available.");

            }
            ImageWriter myWriter = (ImageWriter) writers.next();
            myWriter.setOutput(new FileImageOutputStream(new File(tif)));
            myWriter.prepareWriteSequence(null);
            ImageTypeSpecifier imageType = ImageTypeSpecifier.createFromRenderedImage(image[i]);
            IIOMetadata imageMetadata = myWriter.getDefaultImageMetadata(imageType, null);
            imageMetadata = createImageMetadata(imageMetadata);
            myWriter.writeToSequence(new IIOImage(image[i], null, imageMetadata), null);

            myWriter.dispose();
            image[i] = null;
            myWriter = null;

            FileInputStream in = new FileInputStream(tif);
            FileChannel channel = in.getChannel();
            ByteBuffer buffer = ByteBuffer.allocate((int) channel.size());
            channel.read(buffer);
            Image imageBlank;

            imageBlank = load(buffer.array());

            BufferedImage bufferedImage = imageToBufferedImage(imageBlank);
            boolean isBlank;
            isBlank = isBlank(bufferedImage);
            // System.out.println("isblank "+ isBlank);

            if (isBlank == false) {

                page = writer.getImportedPage(r, i + 1);
                writer.addPage(page);

            }
            bs.close();

            System.gc();
        }

        document.close();
        writer.close();
        raf.close();
        r.close();

    } catch (Exception e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    }

}

---

From source file:pdfmt.RemoveBlankPdf.java

License:Open Source License

/**
 * Convert a PDF document to a TIF file.
 * /* w  w w .j a  va 2s.co  m*/
 * @param pdf
 *            the pdf
 * @param tif
 *            the tif
 * @param destPdf
 *            the dest pdf
 * @throws IOException
 *             Signals that an I/O exception has occurred.
 */
protected void convert(String pdf, String tif, String destPdf) throws IOException {

    startTime = System.currentTimeMillis();
    logger.info("In the boolean convert(String pdf, String tif, String destPdf)");
    org.icepdf.core.pobjects.Document pdffile = new org.icepdf.core.pobjects.Document();

    try {

        pdffile.setFile(pdf);

    } catch (PDFException ex) {
        // System.out.println("Error parsing PDF document " + ex);
    } catch (PDFSecurityException ex) {
        // System.out.println("Error encryption not supported " + ex);
    } catch (FileNotFoundException ex) {
        // System.out.println("Error file not found " + ex);
    } catch (IOException ex) {
        // System.out.println("Error handling PDF document " + ex);
    }

    int numPgs = pdffile.getNumberOfPages();
    msg.setText(".....::::: Converting pages please wait :::::.....");
    addComponent(contentPane, msg, 10, 110, 200, 18);

    try {
        // step 1: create new reader
        PdfReader r = new PdfReader(pdf);
        // System.out.println("File Lenght:" + r.getFileLength());
        RandomAccessFileOrArray raf = new RandomAccessFileOrArray(pdf);
        // System.out.println("Raf:" + raf);
        Document document = new Document(r.getPageSizeWithRotation(1));
        // // step 2: create a writer that listens to the document
        PdfCopy writer = new PdfCopy(document, new FileOutputStream(destPdf));
        //           
        // // step 3: we open the document
        document.open();
        // // step 4: we add content
        PdfImportedPage page = null;

        float scale = 2.084f;
        float rotation = 0f;

        BufferedImage image[] = new BufferedImage[numPgs];

        // -------- CHANGE
        jprogress.setMaximum(numPgs);
        // -------- CHANGE

        for (int i = 0; i < numPgs; i++) {

            // -------- CHANGE
            jprogress.setValue(i + 1);
            // -------- CHANGE

            byte bContent[] = r.getPageContent(i + 1, raf);
            // System.out.println(bContent.toString());

            ByteArrayOutputStream bs = new ByteArrayOutputStream();
            // write the content to an output stream
            bs.write(bContent);

            // System.out.println("page content length of page " + i+1 +
            // " = "
            // + bs.size());

            /*
             * Generate the image: Notes: 1275x1650 = 8.5 x 11 @ 150dpi ???
             */
            image[i] = (BufferedImage) pdffile.getPageImage(i, GraphicsRenderingHints.SCREEN,
                    Page.BOUNDARY_CROPBOX, rotation, scale);
            Iterator writers = ImageIO.getImageWritersByFormatName("TIFF");
            if (writers == null || !writers.hasNext()) {
                throw new RuntimeException("No writers for available.");

            }
            ImageWriter myWriter = (ImageWriter) writers.next();
            myWriter.setOutput(new FileImageOutputStream(new File(tif)));
            myWriter.prepareWriteSequence(null);
            ImageTypeSpecifier imageType = ImageTypeSpecifier.createFromRenderedImage(image[i]);
            IIOMetadata imageMetadata = myWriter.getDefaultImageMetadata(imageType, null);
            imageMetadata = createImageMetadata(imageMetadata);
            myWriter.writeToSequence(new IIOImage(image[i], null, imageMetadata), null);

            myWriter.dispose();
            image[i] = null;
            myWriter = null;

            FileInputStream in = new FileInputStream(tif);
            FileChannel channel = in.getChannel();
            ByteBuffer buffer = ByteBuffer.allocate((int) channel.size());
            channel.read(buffer);
            Image imageBlank;

            imageBlank = load(buffer.array());

            BufferedImage bufferedImage = imageToBufferedImage(imageBlank);
            boolean isBlank;
            isBlank = isBlank(bufferedImage);
            // System.out.println("isblank "+ isBlank);
            boolean hasContent = false;
            File file = new File(TEMP_DIR + TEMP_EXTR_TEXT);

            try {
                FileWriter fileWriter = new FileWriter(file);

                PageText pageText = pdffile.getPageText(i);
                if (pageText != null && pageText.getPageLines() != null) {
                    fileWriter.write(pageText.toString());
                }

                // close the writer
                fileWriter.close();
                System.out.println(file.length());
                if (file.length() > 20) {
                    hasContent = true;

                }
                file.delete();

                System.out.println(TEMP_TIFF + " deleted");
            } catch (IOException e) {

                e.printStackTrace();
            }

            if (isBlank == false && hasContent == true) {

                page = writer.getImportedPage(r, i + 1);
                writer.addPage(page);

            }
            bs.close();
            in.close();
            File ft = new File(TEMP_DIR + TEMP_TIFF);
            boolean check = ft.delete();
            if (check == true) {
                System.out.println("Deleted");
            } else {
                System.out.println("Stuck");
            }
            System.gc();

        }

        document.close();
        writer.close();
        raf.close();
        r.close();
        stopTime = System.currentTimeMillis();
        logger.info("Exit boolean convert(String pdf, String tif, String destPdf) with time:    "
                + ((stopTime - startTime) / 1000));

    } catch (Exception e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    }

}

---

From source file:spntoolsdata.pdf.util.RemoveBlankPageFromPDF.java

public static void removeBlankPdfPages(String source, String destination)
        throws IOException, DocumentException {
    PdfReader r = null;// w w  w .  j a  v a  2s. 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:uk.ac.tgac.conan.core.service.impl.PdfOperationsServiceImpl.java

License:Open Source License

@Override
public void extractPage(File in, File out, int page) throws IOException, DocumentException {

    log.debug("Starting PDF page extraction");

    Document document = new Document();

    // Create a reader for the input file
    PdfReader reader = new PdfReader(new FileInputStream(in));

    if (page > reader.getNumberOfPages())
        throw new IndexOutOfBoundsException("Page number " + page + " does not exist in " + in.getPath());

    // Create a copier for the output file
    PdfCopy copy = new PdfCopy(document, new FileOutputStream(out));

    log.debug("PDF extraction resources created");

    document.open();// ww w  .ja v  a 2s  .c  om

    copy.addPage(copy.getImportedPage(reader, page));

    document.close();

    log.debug("Starting PDF page extracted successfully");
}

---

• «
• 1
• 2
• 3
• 4
• 5
• »