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

Introduction

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

Prototype

public static PDDocument load(byte[] input) throws IOException

Source Link

Document

Parses a PDF.

Usage

From source file:gov.nist.appvet.toolmgr.ToolServiceAdapter.java

License:Open Source License

public static String getPdfReportString(String reportPath, AppInfo appInfo) {
    File file = new File(reportPath);
    PDDocument pddDocument = null;//from  w  ww.  j av  a 2 s  . co  m
    PDFTextStripper textStripper = null;
    try {
        pddDocument = PDDocument.load(file);
        textStripper = new PDFTextStripper();
        textStripper.setStartPage(1);
        textStripper.setEndPage(1);
        final String report = textStripper.getText(pddDocument);
        return report;
    } catch (final IOException e) {
        appInfo.log.error(e.getMessage());
        return null;
    } finally {
        if (pddDocument != null) {
            try {
                pddDocument.close();
                pddDocument = null;
            } catch (IOException e) {
                appInfo.log.error(e.getMessage());
            }
        }
        textStripper = null;
        file = null;
    }
}

From source file:gui.dialog.PlainTextDialog.java

License:Apache License

/**
 *    @Method: pdfParser// w ww .  j  av a 2s .  c  o m
 * 
 *    input : File
 *  output: String
 *  
 *  Diese Methode liet den Text aus der Pdf Datei aus und gibt den Text als String zurck
 */
private String pdfParser(File pdfFile) {
    NDC.push("pdfParser");

    PDDocument document = null;
    try {
        document = PDDocument.load(pdfFile);
    } catch (IOException e) {
        logger.error("Could not load document", e);
        NDC.pop();
        return null;
    }

    if (document.isEncrypted()) {
        NDC.pop();
        return "Encrypted documents are not supported";
    }

    PDFTextStripper stripper;
    try {
        stripper = new PDFTextStripper();
    } catch (IOException e) {
        logger.error("Could not create stripper", e);
        NDC.pop();
        return null;
    }

    stripper.setStartPage(1);
    stripper.setEndPage(2);

    String text;
    try {
        text = stripper.getText(document);
    } catch (Exception e) {
        logger.error("Could not parse PDF", e);
        NDC.pop();
        return null;
    }
    NDC.pop();
    return text;
}

From source file:GUI.Helper.IOHelper.java

public static boolean getProjectImage(MainController mc) {
    FileChooser fc = new FileChooser();
    fc.setTitle("Select WZITS Project Image");
    fc.getExtensionFilters().addAll(/*from   w  ww .  j ava2  s.co m*/
            //new FileChooser.ExtensionFilter("All Images", "*.*"),
            new FileChooser.ExtensionFilter("JPG", "*.jpg"), new FileChooser.ExtensionFilter("PNG", "*.png"),
            new FileChooser.ExtensionFilter("PDF", "*.pdf"));
    File openFile = fc.showOpenDialog(MainController.getWindow()); //mc.getMainWindow()
    if (openFile != null) {
        if (fc.getSelectedExtensionFilter().getExtensions().get(0).equalsIgnoreCase("*.pdf")) {
            try {
                PDDocument doc = PDDocument.load(openFile);
                PDFRenderer pdfRenderer = new PDFRenderer(doc);
                BufferedImage image = pdfRenderer.renderImage(0);
                //ImageIOUtil.writeImage(image, "C:\\Users\\ltrask\\Documents\\test_image.png", 300);
                Image convertedImage = SwingFXUtils.toFXImage(image, null);
                mc.getProject().setProjPhoto(convertedImage);
                doc.close();
                return true;
            } catch (IOException e) {
                Alert al = new Alert(Alert.AlertType.ERROR);
                al.setTitle("WZITS Tool");
                al.setHeaderText("The selected PDF is password protected");
                al.showAndWait();
            }
        } else {
            try {
                mc.getProject().setProjPhoto(new Image(new FileInputStream(openFile)));
                return true;
            } catch (FileNotFoundException e) {

            }
        }
    }
    return false;
}

From source file:GUI.Helper.IOHelper.java

public static Image openImage(MainController mc) {
    FileChooser fc = new FileChooser();
    fc.setTitle("Select WZITS Project Image");
    fc.getExtensionFilters().addAll(new FileChooser.ExtensionFilter("JPG", "*.jpg"),
            new FileChooser.ExtensionFilter("PNG", "*.png"), new FileChooser.ExtensionFilter("PDF", "*.pdf"));
    File openFile = fc.showOpenDialog(mc.getWindow()); //mc.getMainWindow()
    if (openFile != null) {
        if (fc.getSelectedExtensionFilter().getExtensions().get(0).equalsIgnoreCase("*.pdf")) {
            try {
                PDDocument doc = PDDocument.load(openFile);
                PDFRenderer pdfRenderer = new PDFRenderer(doc);
                BufferedImage image = pdfRenderer.renderImage(0);
                Image convertedImage = SwingFXUtils.toFXImage(image, null);
                doc.close();/*from   ww w.  j av  a 2  s.  c o  m*/
                return convertedImage;
            } catch (IOException e) {
                Alert al = new Alert(Alert.AlertType.ERROR);
                al.setTitle("WZITS Tool");
                al.setHeaderText("The selected PDF is password protected");
                al.showAndWait();
            }
        } else {
            try {
                return new Image(new FileInputStream(openFile));
            } catch (FileNotFoundException e) {

            }
        }
    }
    return null;
}

From source file:helper.PdfText.java

License:Apache License

/**
 * @param pdfFile this file will be extracted.
 * @return the plain text of the pdf/*from   w  w w . j a  v  a  2 s. c  o m*/
 */
public String toString(InputStream pdfFile) {
    PDDocument doc = null;
    try {

        doc = PDDocument.load(pdfFile);
        PDFTextStripper stripper = new PDFTextStripper();
        String text = stripper.getText(doc);
        return text;
    } catch (IOException e) {
        throw new HttpArchiveException(500, e);
    } catch (Exception e) {
        throw new HttpArchiveException(500, e);
    } finally {
        if (doc != null) {
            try {
                doc.close();
            } catch (IOException e) {
                logger.warn("", e);
            }
        }
    }
}

From source file:helper.ThumbnailGenerator.java

License:Open Source License

private static File generateThumbnailFromPdf(InputStream in, int size, String name) {
    PDDocument document = null;/*  w  w w .  j  a  v  a2  s  . c  om*/
    try {
        document = PDDocument.load(in);
        BufferedImage tmpImage = writeImageFirstPage(document, BufferedImage.TYPE_INT_RGB, size);
        return createFileFromImage(tmpImage, size, name);
    } catch (Exception e) {
        throw new RuntimeException(e);
    } finally {
        if (document != null) {
            try {
                document.close();
            } catch (IOException e) {
            }
        }
    }
}

From source file:idp.pdf_converter.java

public static void pdf_converter(File file) throws IOException {
    PDDocument document = PDDocument.load(file);
    PDFRenderer pdfRenderer = new PDFRenderer(document);
    String path = System.getProperty("user.dir") + "\\src\\main\\temp\\images\\";
    for (int page = 0; page < document.getNumberOfPages(); ++page) {
        BufferedImage bim = pdfRenderer.renderImageWithDPI(page, 300, ImageType.GRAY);
        ImageIOUtil.writeImage(bim, path + file.getName() + "-" + (page + 1) + ".png", 300);
    }//from w w  w . jav a2 s.  c  o m
    document.close();
}

From source file:impresionXML.impresion.pdf.JPDFManejo.java

public PDDocument getDocumento() throws Exception {
    if (document == null) {
        if (msPDFFile.indexOf("://") >= 0) {
            document = PDDocument.load(new URL(msPDFFile));
        } else {//from   www .j ava 2 s . c  o m
            document = PDDocument.load(msPDFFile);
        }
        if (document.isEncrypted()) {
            document.decrypt(getPassword());
        }
    }
    return document;
}

From source file:indexer.Indexer.java

public static int getPDFPages(String fileLoc) throws IOException {
    PDDocument doc = PDDocument.load(new File(fileLoc));
    int count = doc.getNumberOfPages();
    return count;
}

From source file:indexer.Indexer.java

public static void writePDF(String file_location, Map<String, Set> map) throws IOException {
    PDFMergerUtility finalDoc = new PDFMergerUtility();
    PDDocument document = PDDocument.load(file_location);
    PDPage page = (PDPage) document.getDocumentCatalog().getAllPages().get(0);
    PDPageContentStream contentStream = new PDPageContentStream(document, page, true, true);
    contentStream.beginText();/*www.j av  a  2  s . c  o m*/
    contentStream.setFont(PDType1Font.HELVETICA, 12);

    for (Map.Entry<String, Set> entry : map.entrySet()) {
        contentStream.drawString(entry.getKey() + "- " + entry.getValue().toString());
    }

    contentStream.endText();
    contentStream.close();
    ByteArrayOutputStream out = new ByteArrayOutputStream();
    try {
        document.save(out);
    } catch (COSVisitorException ex) {
        Logger.getLogger(Indexer.class.getName()).log(Level.SEVERE, null, ex);
    }
    finalDoc.addSource(new ByteArrayInputStream(out.toByteArray()));
    document.close();
}