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

List of usage examples for org.apache.pdfbox.pdmodel PDDocument load

  1. HOME
  2. Java
  3. org.apache.pdfbox
  4. org.apache.pdfbox.pdmodel.*
  5. PDDocument
  6. 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:drakkar.mast.retrieval.parser.PdfParser.java

/**
 * Para extraer contenido del pdf//from   w w  w .  j  a  v a2 s . c om
 *
 * @param f
 * @return
 */
public boolean analyzePdfDocument(File f) {

    try {

        pdoc = PDDocument.load(f);

        if (!pdoc.isEncrypted() && pdoc.getCurrentAccessPermission().canExtractContent()
                && pdoc.getNumberOfPages() != 0) {

            this.numberPages = pdoc.getNumberOfPages();
            pdfText = new PDFTextStripper();

            swriter = new StringWriter();

            ////////////////////datos
            pinf = pdoc.getDocumentInformation();
            if (pinf == null) {
                OutputMonitor.printLine("The document does not have available information.",
                        OutputMonitor.INFORMATION_MESSAGE);
            } else {
                setTitle(pinf.getTitle());
                setAuthor(pinf.getAuthor());
                setNumberpages(pdoc.getNumberOfPages());
                setCalCreation(pinf.getCreationDate());
                setCalModification(pinf.getModificationDate());

                pdfText.writeText(pdoc, swriter);
                allContent = swriter.getBuffer().toString();
            }

            pdoc.close();
            swriter.close();

            return true;

        } else {
            OutputMonitor.printLine("Encrypted document.", OutputMonitor.INFORMATION_MESSAGE);
        }
    } catch (Exception ex) {
        OutputMonitor.printStream("", ex);
    } finally {
        if (pdoc != null) {
            try {
                pdoc.close();
            } catch (IOException ex) {
                OutputMonitor.printStream("IO", ex);
            }
        }
    }

    return false;
}

From source file:drakkar.mast.retrieval.parser.PdfParser.java

/**
 * Divide el contenido del pdf de 100 en 100 pginas de acuerdo al nmero
 * total para el motor de bsqueda Minion
 *
 * @param f/*  w  w  w  .  j a v a2  s  .co m*/
 * @param indexer indexador de Minion
 * @throws IOException
 */
public void divideTextforMinion(File f, SimpleIndexer indexer) throws IOException {
    pdoc = PDDocument.load(f);
    this.numberPages = pdoc.getNumberOfPages();

    if (!pdoc.isEncrypted() && pdoc.getCurrentAccessPermission().canExtractContent()
            && pdoc.getNumberOfPages() != 0) {

        String fragment = null;
        int start = 0, end = 0;
        int count = 0;

        if (this.numberPages > 100) {

            for (int i = 0; i < numberPages; i = i + 100) {
                count++; //para el key del document
                swriter = new StringWriter();
                pdfText = new PDFTextStripper();

                start = i;
                end = 99 + i;

                if (end > numberPages) {
                    end = numberPages;
                }

                pdfText.setStartPage(start);
                pdfText.setEndPage(end);
                pdfText.writeText(pdoc, swriter);

                fragment = swriter.getBuffer().toString();

                DocumentMinion docm = new DocumentMinion(indexer, f.getPath() + count);
                docm.addField("filepath", f.getAbsolutePath());
                docm.addField("name", f.getName());
                docm.addField("book", fragment);
                docm.closeDocument();

                swriter.close();
            }

            pdoc.close();

        } else { //si tiene menos de 100 pginas toma todo el texto como est

            swriter = new StringWriter();
            pdfText = new PDFTextStripper();

            pdfText.writeText(pdoc, swriter);
            fragment = swriter.getBuffer().toString();
            DocumentMinion docm = new DocumentMinion(indexer, f.getPath());
            docm.addField("filepath", f.getAbsolutePath());
            docm.addField("name", f.getName());
            docm.addField("book", fragment);
            docm.closeDocument();

            swriter.close();
            pdoc.close();
        }
    } else {
        OutputMonitor.printLine("Encrypted book.", OutputMonitor.INFORMATION_MESSAGE);
    }

    if (pdoc != null) {
        try {
            pdoc.close();
        } catch (IOException ex) {
            OutputMonitor.printStream("", ex);
        }
    }

}

From source file:drakkar.mast.retrieval.parser.PdfParser.java

/**
 * Divide el contenido del pdf de 100 en 100 pginas de acuerdo al nmero
 * total para el motor de bsqueda Lucene
 *
 * @param f//from w ww . j a  va  2  s.c  o m
 * @param doccs
 * @param doc
 * @param doclsi
 * @throws IOException
 */
public void divideTextforLucene(File f, DocumentLucene doccs, DocumentLucene doc, DocumentLucene doclsi)
        throws IOException {
    pdoc = PDDocument.load(f);
    this.numberPages = pdoc.getNumberOfPages();

    if (!pdoc.isEncrypted() && pdoc.getCurrentAccessPermission().canExtractContent()
            && pdoc.getNumberOfPages() != 0) {

        String fragment = null;
        int start = 0, end = 0;
        int count = 0;

        if (this.numberPages > 100) {

            for (int i = 0; i < numberPages; i = i + 100) {
                count++; //para el key del document
                swriter = new StringWriter();
                pdfText = new PDFTextStripper();

                start = i;
                end = 99 + i;

                if (end > numberPages) {
                    end = numberPages;
                }

                pdfText.setStartPage(start);
                pdfText.setEndPage(end);
                pdfText.writeText(pdoc, swriter);

                fragment = swriter.getBuffer().toString();

                doc.addField("filepath", f.getCanonicalPath());
                doccs.addField("filepathcs", f.getCanonicalPath());
                doc.addField("name", f.getName());
                doccs.addField("namecs", f.getName());
                doc.addField("book", fragment);
                doccs.addField("bookcs", fragment);
                ///////
                if (doclsi != null) {
                    doclsi.addField("book", fragment);

                }

                swriter.close();
            }

            pdoc.close();

        } else { //si tiene menos de 100 pginas toma todo el texto como est

            swriter = new StringWriter();
            pdfText = new PDFTextStripper();

            //index
            pdfText.writeText(pdoc, swriter);
            fragment = swriter.getBuffer().toString();
            doc.addField("filepath", f.getCanonicalPath());
            doccs.addField("filepathcs", f.getCanonicalPath());
            doc.addField("name", f.getName());
            doccs.addField("namecs", f.getName());
            doc.addField("book", fragment);
            doccs.addField("bookcs", fragment);

            if (doclsi != null) {
                doclsi.addField("book", fragment);

            }
            swriter.close();
            pdoc.close();
        }
    } else {
        OutputMonitor.printLine("Encrypted book.", OutputMonitor.INFORMATION_MESSAGE);
    }

    if (pdoc != null) {
        try {
            pdoc.close();
        } catch (IOException ex) {
            OutputMonitor.printStream("", ex);
        }
    }

}

From source file:editorframework.PDDocumentAdapter.java

public PDDocumentAdapter(String fileName) {
    try {//from  w w  w .  j  ava 2s.  c  om

        this.pdPanel = new PDFPagePanel();
        pdDocument = PDDocument.load(fileName);

        allPages = pdDocument.getDocumentCatalog().getAllPages();
    } catch (IOException ex) {
        Logger.getLogger(PDDocumentAdapter.class.getName()).log(Level.SEVERE, null, ex);
    }

}

From source file:editorframework.PDDocumentAdapter.java

public boolean open(String fileName) {

    try {//from   w w  w .j a va2 s.  co  m
        pdDocument = PDDocument.load(new FileInputStream(fileName));

        allPages = pdDocument.getDocumentCatalog().getAllPages();
        return true;
    } catch (IOException ex) {
        Logger.getLogger(PDDocumentAdapter.class.getName()).log(Level.SEVERE, null, ex);
    }
    return false;
}

From source file:editorframework.pdfbox.OpenTextPDF.java

public PDDocument openPDF(String pdfFilename) {
    //openPDF(fileName);
    PDDocument document = null;/*from w  ww.jav  a  2  s .c  o  m*/
    try {
        document = PDDocument.load(new File(pdfFilename));
        return document;
    } catch (IOException ex) {
        Logger.getLogger(OpenTextPDFAdapter.class.getName()).log(Level.SEVERE, null, ex);
    }
    return null;
}

From source file:editorframework.pdfbox.PDFBoxDocumentAdaptee.java

private static PDDocument parseDocument(String filename) throws IOException {
    PDDocument document = PDDocument.load(filename);
    if (document.isEncrypted()) {
        try {//  www . ja va 2s  .  com
            document.decrypt("");
        } catch (org.apache.pdfbox.exceptions.CryptographyException e) {
            e.printStackTrace();
        }
    }

    return document;
}

From source file:editorframework.pdfbox.testes.MyPDFBox.java

private void init() {
    JFrame jFrame = new JFrame();
    jFrame.setDefaultCloseOperation(JFrame.EXIT_ON_CLOSE);
    try {/*from   w  w w.  j  av  a  2s  .  com*/
        final PDDocument doc = PDDocument.load(new File("./simple.pdf"));
        List<PDPage> allPages = doc.getDocumentCatalog().getAllPages();
        PDPage page = (PDPage) allPages.get(1);
        setPage(page);
        jFrame.setBackground(Color.DARK_GRAY);
        setLayout(new FlowLayout());
        jFrame.add(this);
        jFrame.setBounds(40, 40, getWidth() + 100, getHeight() + 50);
        jFrame.setVisible(true);
        jFrame.addWindowListener(new WindowAdapter() {
            @Override
            public void windowClosing(WindowEvent e) {
                try {
                    doc.close();
                } catch (IOException e1) {
                    e1.printStackTrace();
                }
            }
        });
    } catch (IOException e) {
        System.out.println(e.toString());
    }
    //doc.close();
}

From source file:editorframework.pdfbox.testes.PDFReaderAdaptor.java

License:Apache License

private static PDDocument parseDocument(InputStream input) throws IOException {
    PDDocument document = PDDocument.load(input);
    if (document.isEncrypted()) {
        try {//from  www .ja v  a2s  . c o m
            document.decrypt("");
        } catch (org.apache.pdfbox.exceptions.CryptographyException e) {
            e.printStackTrace();
        }
    }

    return document;
}

From source file:editorframework.pdfbox.testes.TestesComPDFBox.java

public static void transformarPDFemImagem() throws IOException {

    //OPCAO 1 transformar o pdfpage em bufered image, e exibir no JFrame normal
    PDDocument document = PDDocument.load(new File("./simple.pdf"));
    List<PDPage> allPages = document.getDocumentCatalog().getAllPages();

    PDPage firstPage = allPages.get(0);/* w ww.  j  ava2 s .  c o  m*/
    BufferedImage bi = firstPage.convertToImage();
    File outputfile = new File("image.jpg");
    ImageIO.write(bi, "jpg", outputfile);

}