Examples with PDDocumentCatalog org.apache.pdfbox.pdmodel.PDDocumentCatalog used on opensource projects

Example 1 with PDDocumentCatalog

use of org.apache.pdfbox.pdmodel.PDDocumentCatalog in project mustangproject by ZUGFeRD.

the class ZUGFeRDExporterFromA1Factory method makePDFA3compliant.

private void makePDFA3compliant(PDDocument doc) throws IOException {
    String fullProducer = producer + " (via mustangproject.org " + Version.VERSION + ")";
    PDDocumentCatalog cat = doc.getDocumentCatalog();
    PDMetadata metadata = new PDMetadata(doc);
    cat.setMetadata(metadata);
    XMPMetadata xmp = XMPMetadata.createXMPMetadata();
    PDFAIdentificationSchema pdfaid = new PDFAIdentificationSchema(xmp);
    xmp.addSchema(pdfaid);
    DublinCoreSchema dc = xmp.createAndAddDublinCoreSchema();
    dc.addCreator(creator);
    XMPBasicSchema xsb = xmp.createAndAddXMPBasicSchema();
    xsb.setCreatorTool(creator);
    xsb.setCreateDate(GregorianCalendar.getInstance());
    // PDDocumentInformation pdi=doc.getDocumentInformation();
    PDDocumentInformation pdi = new PDDocumentInformation();
    pdi.setProducer(fullProducer);
    pdi.setAuthor(creator);
    doc.setDocumentInformation(pdi);
    AdobePDFSchema pdf = xmp.createAndAddAdobePDFSchema();
    pdf.setProducer(fullProducer);
    /*
        *
        * To be on the safe side, we use level B without Markinfo because we
        * can not guarantee that the user correctly tagged the templates for
        * the PDF.
        */
    try {
        //$NON-NLS-1$ //$NON-NLS-1$
        pdfaid.setConformance(conformanceLevel.getLetter());
    } catch (BadFieldValueException ex) {
        // however the enum enforces that the conformance level is valid.
        throw new Error(ex);
    }
    pdfaid.setPart(3);
    if (attachZugferdHeaders) {
        addZugferdXMP(xmp);
    /*
								 * this is the only line where we do something
								 * Zugferd-specific, i.e. add PDF metadata
								 * specifically for Zugferd, not generically for
								 * a embedded file
								 */
    }
    try {
        metadata.importXMPMetadata(serializeXmpMetadata(xmp));
    } catch (TransformerException e) {
        throw new ZUGFeRDExportException("Could not export XmpMetadata", e);
    }
}

Example 2 with PDDocumentCatalog

use of org.apache.pdfbox.pdmodel.PDDocumentCatalog in project Gargoyle by callakrsos.

the class PDFUtil method toImage.

/**
	 * @작성자 : KYJ
	 * @작성일 : 2017. 2. 20.
	 * @param pdfFile
	 * @param handler
	 * @throws IOException
	 */
public static void toImage(PdfToImageHandler handler) throws IOException {
    File pdfFile = handler.getPdfFile();
    try (PDDocument doc = PDDocument.load(pdfFile)) {
        PDFRenderer pdfRenderer = new PDFRenderer(doc);
        PDDocumentCatalog catal = doc.getDocumentCatalog();
        PDPageTree pages = catal.getPages();
        int totalPageCount = pages.getCount();
        int start = handler.getStartPage();
        int end = handler.getEndPage();
        //페이지 유효성 검증
        if (start > end) {
            throw new RuntimeException(String.format("Invalide page index start : %d end : %d", start, end));
        }
        if (start == -1)
            start = 0;
        if (end == -1)
            end = totalPageCount;
        if (end > totalPageCount) {
            end = totalPageCount;
        }
        // 파일 디렉토리 검증
        File outputDir = handler.getOutputDir();
        if (!outputDir.isDirectory()) {
            throw new RuntimeException("OutputDir is not Directory.");
        }
        //디렉토리가 없으면 생성
        if (!outputDir.exists())
            outputDir.mkdirs();
        for (int currentPage = start; currentPage < totalPageCount; currentPage++) {
            if (currentPage > end)
                break;
            BufferedImage renderImage = pdfRenderer.renderImage(currentPage);
            handler.write(outputDir, currentPage, renderImage);
        }
    }
}

Example 3 with PDDocumentCatalog

use of org.apache.pdfbox.pdmodel.PDDocumentCatalog in project tika by apache.

the class AbstractPDF2XHTML method extractAcroForm.

void extractAcroForm(PDDocument pdf) throws IOException, SAXException, TikaException {
    //Thank you, Ben Litchfield, for org.apache.pdfbox.examples.fdf.PrintFields
    //this code derives from Ben's code
    PDDocumentCatalog catalog = pdf.getDocumentCatalog();
    if (catalog == null)
        return;
    PDAcroForm form = catalog.getAcroForm();
    if (form == null)
        return;
    //if it has xfa, try that.
    //if it doesn't exist or there's an exception,
    //go with traditional AcroForm
    PDXFAResource pdxfa = form.getXFA();
    if (pdxfa != null) {
        //if successful, return
        XFAExtractor xfaExtractor = new XFAExtractor();
        InputStream is = null;
        try {
            is = new BufferedInputStream(new ByteArrayInputStream(pdxfa.getBytes()));
        } catch (IOException e) {
            EmbeddedDocumentUtil.recordEmbeddedStreamException(e, metadata);
        }
        if (is != null) {
            try {
                xfaExtractor.extract(is, xhtml, metadata, context);
                return;
            } catch (XMLStreamException e) {
                //if there was an xml parse exception in xfa, try the AcroForm
                EmbeddedDocumentUtil.recordException(e, metadata);
            } finally {
                IOUtils.closeQuietly(is);
            }
        }
    }
    @SuppressWarnings("rawtypes") List fields = form.getFields();
    if (fields == null)
        return;
    @SuppressWarnings("rawtypes") ListIterator itr = fields.listIterator();
    if (itr == null)
        return;
    xhtml.startElement("div", "class", "acroform");
    xhtml.startElement("ol");
    while (itr.hasNext()) {
        Object obj = itr.next();
        if (obj != null && obj instanceof PDField) {
            processAcroField((PDField) obj, 0);
        }
    }
    xhtml.endElement("ol");
    xhtml.endElement("div");
}

Example 4 with PDDocumentCatalog

use of org.apache.pdfbox.pdmodel.PDDocumentCatalog in project jabref by JabRef.

the class XMPUtil method getXMPMetadata.

/**
     * @return empty Optional if no metadata has been found
     */
private static Optional<XMPMetadata> getXMPMetadata(PDDocument document) throws IOException {
    PDDocumentCatalog catalog = document.getDocumentCatalog();
    PDMetadata metaRaw = catalog.getMetadata();
    if (metaRaw == null) {
        return Optional.empty();
    }
    Document parseResult;
    try (InputStream is = metaRaw.createInputStream()) {
        parseResult = XMLUtil.parse(is);
    }
    XMPMetadata meta = new XMPMetadata(parseResult);
    meta.addXMLNSMapping(XMPSchemaBibtex.NAMESPACE, XMPSchemaBibtex.class);
    return Optional.of(meta);
}

Example 5 with PDDocumentCatalog

use of org.apache.pdfbox.pdmodel.PDDocumentCatalog in project jabref by JabRef.

the class XMPUtilTest method testReadWriteDC.

@Test
public void testReadWriteDC() throws IOException, TransformerException {
    List<BibEntry> l = new LinkedList<>();
    l.add(t3BibtexEntry());
    XMPUtil.writeXMP(pdfFile, l, null, true, xmpPreferences);
    try (PDDocument document = PDDocument.load(pdfFile.getAbsoluteFile())) {
        if (document.isEncrypted()) {
            Assert.fail("Cannot add metadata to encrypted document.");
        }
        Assert.assertEquals("Kelly Clarkson and Ozzy Osbourne", document.getDocumentInformation().getAuthor());
        Assert.assertEquals("Hypersonic ultra-sound", document.getDocumentInformation().getTitle());
        Assert.assertEquals("Huey Duck and Dewey Duck and Louie Duck", document.getDocumentInformation().getCustomMetadataValue("bibtex/editor"));
        Assert.assertEquals("Clarkson06", document.getDocumentInformation().getCustomMetadataValue("bibtex/bibtexkey"));
        Assert.assertEquals("peanut, butter, jelly", document.getDocumentInformation().getKeywords());
        assertEqualsBibtexEntry(t3BibtexEntry(), XMPUtil.getBibtexEntryFromDocumentInformation(document.getDocumentInformation()).get());
        PDDocumentCatalog catalog = document.getDocumentCatalog();
        PDMetadata metaRaw = catalog.getMetadata();
        if (metaRaw == null) {
            Assert.fail();
            return;
        }
        XMPMetadata meta = new XMPMetadata(XMLUtil.parse(metaRaw.createInputStream()));
        meta.addXMLNSMapping(XMPSchemaBibtex.NAMESPACE, XMPSchemaBibtex.class);
        // Check Dublin Core
        List<XMPSchema> schemas = meta.getSchemasByNamespaceURI("http://purl.org/dc/elements/1.1/");
        Assert.assertEquals(1, schemas.size());
        XMPSchemaDublinCore dcSchema = (XMPSchemaDublinCore) schemas.iterator().next();
        Assert.assertNotNull(dcSchema);
        Assert.assertEquals("Hypersonic ultra-sound", dcSchema.getTitle());
        Assert.assertEquals("1982-07", dcSchema.getSequenceList("dc:date").get(0));
        Assert.assertEquals("Kelly Clarkson", dcSchema.getCreators().get(0));
        Assert.assertEquals("Ozzy Osbourne", dcSchema.getCreators().get(1));
        Assert.assertEquals("Huey Duck", dcSchema.getContributors().get(0));
        Assert.assertEquals("Dewey Duck", dcSchema.getContributors().get(1));
        Assert.assertEquals("Louie Duck", dcSchema.getContributors().get(2));
        Assert.assertEquals("InProceedings".toLowerCase(), dcSchema.getTypes().get(0).toLowerCase());
        Assert.assertTrue(dcSchema.getRelationships().contains("bibtex/bibtexkey/Clarkson06"));
        Assert.assertEquals("peanut", dcSchema.getSubjects().get(0));
        Assert.assertEquals("butter", dcSchema.getSubjects().get(1));
        Assert.assertEquals("jelly", dcSchema.getSubjects().get(2));
        /**
             * Bibtexkey, Journal, pdf, booktitle
             */
        Assert.assertEquals(4, dcSchema.getRelationships().size());
        assertEqualsBibtexEntry(t3BibtexEntry(), XMPUtil.getBibtexEntryFromDublinCore(dcSchema, xmpPreferences).get());
    }
}