Example usage for org.apache.pdfbox.pdmodel PDDocument getDocumentCatalog

Introduction

In this page you can find the example usage for org.apache.pdfbox.pdmodel PDDocument getDocumentCatalog.

Prototype

public PDDocumentCatalog getDocumentCatalog()

Source Link

Document

This will get the document CATALOG.

Usage

From source file:Utilities.GlobalVar.java

public static void updateSeqNum(PDDocument doc, String cycle) throws IOException {
    int sequenceNum = 1;
    List pages = doc.getDocumentCatalog().getAllPages();

    for (int i = 0; i < pages.size(); i++) {
        PDPage page = (PDPage) pages.get(i);
        PDStream contents = page.getContents();
        PDFStreamParser parser = new PDFStreamParser(contents.getStream());
        parser.parse();/*  w  w  w.ja v  a 2 s.  co m*/
        List tokens = parser.getTokens();
        for (int j = 0; j < tokens.size(); j++) {
            Object next = tokens.get(j);
            if (next instanceof PDFOperator) {
                PDFOperator op = (PDFOperator) next;
                // Tj and TJ are the two operators that display strings in a PDF
                if (op.getOperation().equals("Tj")) {
                    // Tj takes one operator and that is the string
                    // to display so lets update that operator
                    COSString previous = (COSString) tokens.get(j - 1);
                    String string = previous.getString();
                    //                        System.out.println(string);
                    //                        System.out.println(string.charAt(5));
                    if (string.contains("/0")) {
                        String seq = cycle + "/" + GlobalVar.globalCountGenerator5Digit(sequenceNum);
                        string = string.replaceFirst(string, seq);
                        previous.reset();
                        previous.append(string.getBytes("ISO-8859-1"));
                        sequenceNum++;
                        break;
                    }
                    //Word you want to change. Currently this code changes word "Solr" to "Solr123"
                    previous.reset();
                    previous.append(string.getBytes("ISO-8859-1"));

                } else if (op.getOperation().equals("TJ")) {
                    COSArray previous = (COSArray) tokens.get(j - 1);
                    for (int k = 0; k < previous.size(); k++) {
                        Object arrElement = previous.getObject(k);
                        if (arrElement instanceof COSString) {
                            COSString cosString = (COSString) arrElement;
                            String string = cosString.getString();
                            //                                System.out.println(string);
                            if (string.contains("/00")) {
                                String seq = cycle + "/" + GlobalVar.globalCountGenerator5Digit(sequenceNum);
                                string = string.replaceFirst(string, seq);
                                cosString.reset();
                                cosString.append(string.getBytes("ISO-8859-1"));
                                sequenceNum++;
                                break;
                            }
                            // Currently this code changes word "Solr" to "Solr123"
                            cosString.reset();
                            cosString.append(string.getBytes("ISO-8859-1"));
                            //                                break;
                        }
                    }
                }
            }
        }
        // now that the tokens are updated we will replace the page content stream.
        PDStream updatedStream = new PDStream(doc);
        OutputStream out = updatedStream.createOutputStream();
        ContentStreamWriter tokenWriter = new ContentStreamWriter(out);
        tokenWriter.writeTokens(tokens);
        page.setContents(updatedStream);
    }
}

From source file:utilities.PDFUtilities.java

public static ArrayList<BufferedImage> extractPagesAsImage(File file) throws Exception {
    ArrayList<BufferedImage> images = new ArrayList<>();

    if (file != null) {
        PDDocument doc = PDDocument.load(file);
        List<PDPage> pages = doc.getDocumentCatalog().getAllPages();
        for (PDPage page : pages) {

            BufferedImage bImage = page.convertToImage(BufferedImage.TYPE_INT_RGB, 160);
            images.add(bImage);/* w ww.ja  va 2  s  .  c  o m*/
        }
    }
    return images;
}

From source file:vortext.TextHighlight.java

License:Apache License

@SuppressWarnings("unchecked")
public void initialize(final PDDocument pdf) throws IOException {
    resetEngine();/*  w  w w  . j  a v  a 2s .  co m*/
    document = pdf;
    if (document.isEncrypted()) {
        // We are expecting non-encrypted documents here, but it is common
        // for users to pass in a document that is encrypted with an empty
        // password (such a document appears to not be encrypted by
        // someone viewing the document, thus the confusion). We will
        // attempt to decrypt with the empty password to handle this case.
        //
        try {
            document.decrypt("");
        } catch (CryptographyException e) {
            throw new IllegalArgumentException("Error decrypting document, details: ", e);
        }
    }

    textAggregate = new TextAggregate(this.isSkipAllWhitespace(), this.isNormalizeText());

    if (getAddMoreFormatting()) {
        setParagraphEnd(getLineSeparator());
        setPageStart(getLineSeparator());
        setArticleStart(getLineSeparator());
        setArticleEnd(getLineSeparator());
    }
    startDocument(pdf);
    processPages(pdf.getDocumentCatalog().getAllPages());
    endDocument(pdf);
}

From source file:webhooks.core.services.util.ThumbnailUtil.java

License:Apache License

private static BufferedImage createPDFThumbnail(String filename, int thumbWidth, int thumbHeight)
        throws IOException {
    PDDocument document = PDDocument.load(new File(filename));
    List<?> pages = document.getDocumentCatalog().getAllPages();

    // get first page
    PDPage page = (PDPage) pages.get(0);

    PDRectangle mBox = page.findMediaBox();
    float scaling = thumbWidth / mBox.getWidth();

    Dimension pageDimension = new Dimension((int) mBox.getWidth(), (int) mBox.getHeight());

    BufferedImage thumbImg = new BufferedImage(thumbWidth, thumbHeight, BufferedImage.TYPE_INT_RGB);
    Graphics2D graphics = (Graphics2D) thumbImg.getGraphics();
    graphics.setBackground(new Color(255, 255, 255, 0)); // TRANSPARENT_WHITE
    graphics.clearRect(0, 0, thumbImg.getWidth(), thumbImg.getHeight());
    graphics.scale(scaling, scaling);//from w  w  w . j  a v  a  2  s .c om
    PageDrawer drawer = new PageDrawer();
    drawer.drawPage(graphics, page, pageDimension);

    return thumbImg;
}