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, String password) throws IOException 

Source Link

Document

Parses a PDF.

Usage

From source file:org.apache.tika.parser.pdf.PDFPureJavaParser.java

License:Apache License

public void parse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context)
        throws IOException, SAXException, TikaException {

    PDFPureJavaParserConfig localConfig = context.get(PDFPureJavaParserConfig.class, defaultConfig);

    PDDocument pdfDocument = null;/*from  w  w  w  .j  a va 2 s .  c o m*/

    String password = "";
    try {
        // PDFBox can process entirely in memory, or can use a temp file
        //  for unpacked / processed resources
        // Decide which to do based on if we're reading from a file or not already
        //TODO: make this configurable via MemoryUsageSetting
        TikaInputStream tstream = TikaInputStream.cast(stream);
        password = getPassword(metadata, context);
        if (tstream != null && tstream.hasFile()) {
            // File based -- send file directly to PDFBox
            pdfDocument = PDDocument.load(tstream.getPath().toFile(), password);
        } else {
            pdfDocument = PDDocument.load(new CloseShieldInputStream(stream), password);
        }
        metadata.set(PDF.IS_ENCRYPTED, Boolean.toString(pdfDocument.isEncrypted()));

        metadata.set(Metadata.CONTENT_TYPE, MEDIA_TYPE.toString());
        extractMetadata(pdfDocument, metadata, context);
        AccessChecker checker = localConfig.getAccessChecker();
        checker.check(metadata);
        if (handler != null) {
            if (shouldHandleXFAOnly(pdfDocument, localConfig)) {
                handleXFAOnly(pdfDocument, handler, metadata, context);
            } else if (localConfig.getOcrStrategy().equals(PDFPureJavaParserConfig.OCR_STRATEGY.OCR_ONLY)) {
                metadata.add("X-Parsed-By", "org.apache.tika.parser.ocr.TesseractOCRParser");
                // No-ops. Do not support OCR parser.
            } else {
                if (localConfig.getOcrStrategy()
                        .equals(PDFPureJavaParserConfig.OCR_STRATEGY.OCR_AND_TEXT_EXTRACTION)) {
                    metadata.add("X-Parsed-By", "org.apache.tika.parser.ocr.TesseractOCRParser");
                }
                PDF2XHTMLPureJava.process(pdfDocument, handler, context, metadata, localConfig);
            }
        }
    } catch (InvalidPasswordException e) {
        metadata.set(PDF.IS_ENCRYPTED, "true");
        throw new EncryptedDocumentException(e);
    } catch (final PdfTimeoutException e) {
        throw new TikaPdfTimeoutException("PdfTimeoutException", e);
    } finally {
        if (pdfDocument != null) {
            pdfDocument.close();
        }
    }
}

---

From source file:org.codelibs.fess.crawler.extractor.impl.PdfExtractor.java

License:Apache License

@Override
public ExtractData getText(final InputStream in, final Map<String, String> params) {
    if (in == null) {
        throw new CrawlerSystemException("The inputstream is null.");
    }//from   w w  w. j a  v a  2  s  .com

    synchronized (pdfBoxLockObj) {
        final String password = getPassword(params);
        try (PDDocument document = PDDocument.load(in, password)) {
            final ByteArrayOutputStream baos = new ByteArrayOutputStream();
            final Writer output = new OutputStreamWriter(baos, encoding);
            final PDFTextStripper stripper = new PDFTextStripper();
            final AtomicBoolean done = new AtomicBoolean(false);
            final PDDocument doc = document;
            final Set<Exception> exceptionSet = new HashSet<>();
            final Thread task = new Thread(() -> {
                try {
                    stripper.writeText(doc, output);
                } catch (final Exception e) {
                    exceptionSet.add(e);
                } finally {
                    done.set(true);
                }
            });
            task.setDaemon(true);
            task.start();
            task.join(timeout);
            if (!done.get()) {
                for (int i = 0; i < 100 && !done.get(); i++) {
                    task.interrupt();
                    Thread.sleep(50);
                }
                throw new ExtractException("PDFBox process cannot finish in " + timeout + " sec.");
            } else if (!exceptionSet.isEmpty()) {
                throw exceptionSet.iterator().next();
            }
            output.flush();
            final ExtractData extractData = new ExtractData(baos.toString(encoding));
            extractMetadata(document, extractData);
            return extractData;
        } catch (final Exception e) {
            throw new ExtractException(e);
        }
    }
}

---

From source file:org.geomajas.plugin.printing.document.DefaultDocumentTest.java

License:Open Source License

@Test
public void testToImage() throws Exception {
    testRender();//from  w  w w  . jav a2  s  .  c o  m
    PDDocument pdf = PDDocument.load(new File("target/test.pdf"), true);
    PDFRenderer renderer = new PDFRenderer(pdf);
    BufferedImage bufferedImage = renderer.renderImageWithDPI(0, 144);
    pdf.close();
    ImageIO.write(bufferedImage, "PNG", new File("target/test.png"));
}

---

From source file:org.geomajas.plugin.printing.document.SinglePageDocument.java

License:Open Source License

private void writeDocument(OutputStream outputStream, Format format, int dpi)
        throws IOException, DocumentException, PrintingException {
    if (format == Format.PDF) {
        baos.writeTo(outputStream);//  www. ja va2s  .c  o  m
    } else {
        PDDocument pdf = PDDocument.load(new ByteArrayInputStream(baos.toByteArray()), true);
        PDFRenderer renderer = new PDFRenderer(pdf);
        BufferedImage bufferedImage = renderer.renderImageWithDPI(0, dpi);
        pdf.close();
        if (format == Format.PNG) {
            final String formatName = format.getExtension();
            for (Iterator<ImageWriter> iw = ImageIO.getImageWritersByFormatName(formatName); iw.hasNext();) {
                ImageWriter writer1 = iw.next();
                ImageWriteParam writeParam = writer1.getDefaultWriteParam();
                ImageTypeSpecifier typeSpecifier = ImageTypeSpecifier
                        .createFromBufferedImageType(BufferedImage.TYPE_INT_ARGB);
                IIOMetadata metadata = writer1.getDefaultImageMetadata(typeSpecifier, writeParam);
                if (metadata.isReadOnly() || !metadata.isStandardMetadataFormatSupported()) {
                    continue;
                }

                setDPI(metadata);
                // Write bufferedImage to outputStream
                final ImageOutputStream stream = ImageIO.createImageOutputStream(outputStream);
                try {
                    writer1.setOutput(stream);
                    writer1.write(metadata, new IIOImage(bufferedImage, null, metadata), writeParam);
                } finally {
                    stream.flush();
                    stream.close();
                }
                break;
            }
        } else {
            ImageIO.write(bufferedImage, format.getExtension(), outputStream);
        }

    }
}

---

• «
• 1
• 2
• 3
• »