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:org.modeshape.sequencer.pdf.PdfBasicMetadata.java

License:Apache License

public boolean check() throws Exception {
    try (PDDocument document = PDDocument.load(in)) {
        PDDocumentCatalog catalog = document.getDocumentCatalog();
        PDPageable pageable = new PDPageable(document);
        PageFormat firstPage = pageable.getPageFormat(0);

        encrypted = document.isEncrypted();
        pageCount = document.getNumberOfPages();
        orientation = ORIENTATION_STRINGS[firstPage.getOrientation()];
        version = String.valueOf(document.getDocument().getVersion());
        String catalogVersion = catalog.getVersion();
        if (catalogVersion != null && !catalogVersion.isEmpty()) {
            // According to specs version saved here should be determining instead
            // the version in header. It is barely used, though.
            version = catalogVersion;/*www  .  j a va 2s  .  c  om*/
        }

        if (!encrypted) {
            PDDocumentInformation metadata = document.getDocumentInformation();
            author = metadata.getAuthor();
            creationDate = metadata.getCreationDate();
            creator = metadata.getCreator();
            keywords = metadata.getKeywords();
            modificationDate = metadata.getModificationDate();
            producer = metadata.getProducer();
            subject = metadata.getSubject();
            title = metadata.getTitle();
        }

        // extract all attached files from all pages
        int pageNumber = 0;
        for (Object page : catalog.getAllPages()) {
            pageNumber += 1;
            PdfPageMetadata pageMetadata = new PdfPageMetadata();
            pageMetadata.setPageNumber(pageNumber);
            for (PDAnnotation annotation : ((PDPage) page).getAnnotations()) {
                if (annotation instanceof PDAnnotationFileAttachment) {
                    PdfAttachmentMetadata attachmentMetadata = new PdfAttachmentMetadata();

                    PDAnnotationFileAttachment fann = (PDAnnotationFileAttachment) annotation;
                    PDComplexFileSpecification fileSpec = (PDComplexFileSpecification) fann.getFile();
                    PDEmbeddedFile embeddedFile = fileSpec.getEmbeddedFile();

                    attachmentMetadata.setSubject(fann.getSubject());
                    attachmentMetadata.setName(fileSpec.getFilename());
                    attachmentMetadata.setCreationDate(embeddedFile.getCreationDate());
                    attachmentMetadata.setModificationDate(embeddedFile.getModDate());
                    attachmentMetadata.setMimeType(embeddedFile.getSubtype());
                    attachmentMetadata.setData(embeddedFile.getByteArray());

                    pageMetadata.addAttachment(attachmentMetadata);
                }
            }
            pages.add(pageMetadata);
        }
        return true;
    }
}

From source file:org.modeshape.sequencer.pdf.PdfXmpMetadata.java

License:Apache License

public boolean check() throws Exception {
    try (PDDocument document = PDDocument.load(in)) {
        Boolean encrypted = document.isEncrypted();

        if (encrypted) {
            return false;
        }/*  w  w w . j ava 2 s  . com*/

        PDDocumentCatalog catalog = document.getDocumentCatalog();
        PDMetadata metadata = catalog.getMetadata();
        if (metadata == null) {
            return false;
        }

        DomXmpParser xmpParser = new DomXmpParser();
        try (InputStream is = metadata.createInputStream()) {
            XMPMetadata xmp = xmpParser.parse(is);
            XMPBasicSchema basicSchema = xmp.getXMPBasicSchema();
            if (basicSchema != null) {
                baseURL = basicSchema.getBaseURL();
                createDate = basicSchema.getCreateDate();
                creatorTool = basicSchema.getCreatorTool();
                if (basicSchema.getIdentifiers() != null) {
                    identifier.addAll(basicSchema.getIdentifiers());
                }
                metadataDate = basicSchema.getMetadataDate();
                modifyDate = basicSchema.getModifyDate();
                nickname = basicSchema.getNickname();
                rating = basicSchema.getRating();
                label = basicSchema.getLabel();
                return true;
            }
            return false;
        }

    }
}

From source file:org.mustangproject.ZUGFeRD.MustangReaderWriterTest.java

License:Open Source License

private void checkPdfA3B(File tempFile) throws IOException, InvalidPasswordException {
    try (PDDocument doc = PDDocument.load(tempFile)) {
        PDMetadata metadata = doc.getDocumentCatalog().getMetadata();
        InputStream exportXMPMetadata = metadata.exportXMPMetadata();
        byte[] xmpBytes = new byte[exportXMPMetadata.available()];
        exportXMPMetadata.read(xmpBytes);
        final XMPMetadata xmp = new DomXmpParser().parse(xmpBytes);
        PDFAIdentificationSchema pdfaid = xmp.getPDFIdentificationSchema();
        assertEquals(pdfaid.getPart().intValue(), 3);
        assertEquals(pdfaid.getConformance(), "U");
    } catch (XmpParsingException e) {
        throw new IllegalStateException("Failed to read PDF", e);
    }/*from   w ww  . j a va 2s  .co m*/
}

From source file:org.mustangproject.ZUGFeRD.ZUGFeRDExporter.java

License:Open Source License

/**
 * @deprecated Use the factory method {@link #createFromPDFA3(String)} instead
 *//* w  w w . j  av  a  2 s .co  m*/
@Deprecated
public void loadPDFA3(String filename) throws IOException {
    doc = PDDocument.load(new File(filename));
}

From source file:org.mustangproject.ZUGFeRD.ZUGFeRDExporter.java

License:Open Source License

public static ZUGFeRDExporter createFromPDFA3(String filename) throws IOException {
    return new ZUGFeRDExporter(PDDocument.load(new File(filename)));
}

From source file:org.mustangproject.ZUGFeRD.ZUGFeRDExporter.java

License:Open Source License

/**
 * @deprecated Use the factory method {@link #createFromPDFA3(InputStream)}
 * instead/* w  w w .  ja  v a  2 s.  com*/
 */
@Deprecated
public void loadPDFA3(InputStream file) throws IOException {
    doc = PDDocument.load(file);
}

From source file:org.mustangproject.ZUGFeRD.ZUGFeRDExporter.java

License:Open Source License

public static ZUGFeRDExporter createFromPDFA3(InputStream pdfSource) throws IOException {
    return new ZUGFeRDExporter(PDDocument.load(pdfSource));
}

From source file:org.mustangproject.ZUGFeRD.ZUGFeRDExporterFromA3Factory.java

License:Open Source License

/**
 * Makes A PDF/A3a-compliant document from a PDF-A1 compliant document (on the
 * metadata level, this will not e.g. convert graphics to JPG-2000)
 *
 * @param pdfFilename filename of an PDF/A1 compliant document
 *///w w  w.  ja  v a 2  s  .com
public ZUGFeRDExporter load(String pdfFilename) throws IOException {

    ensurePDFIsValidPDFA(new FileDataSource(pdfFilename));
    ZUGFeRDExporter zugFeRDExporter;
    PDDocument doc = PDDocument.load(new File(pdfFilename));
    zugFeRDExporter = new ZUGFeRDExporter(doc);
    zugFeRDExporter.setZUGFeRDVersion(ZFVersion);
    zugFeRDExporter.setZUGFeRDConformanceLevel(zugferdConformanceLevel);
    zugFeRDExporter.setCreator(creator);
    // Use creator as default for compatibility
    zugFeRDExporter.setCreatorTool(creatorTool != null ? creatorTool : creator);
    zugFeRDExporter.setProducer(producer);
    zugFeRDExporter.setAttachZUGFeRDHeaders(attachZUGFeRDHeaders);
    zugFeRDExporter.setPDFA3(ensurePDFisUpgraded);

    return zugFeRDExporter;

}

From source file:org.mustangproject.ZUGFeRD.ZUGFeRDExporterFromA3Factory.java

License:Open Source License

/**
 * Makes A PDF/A3a-compliant document from a PDF-A1 compliant document (on the
 * metadata level, this will not e.g. convert graphics to JPG-2000)
 *
 * @param pdfBinary binary of a PDF/A1 compliant document
 *//* ww  w  .j  a  v  a2  s.  co  m*/
public ZUGFeRDExporter load(byte[] pdfBinary) throws IOException {
    ensurePDFIsValidPDFA(new ByteArrayDataSource(new ByteArrayInputStream(pdfBinary)));
    ZUGFeRDExporter zugFeRDExporter;
    PDDocument doc = PDDocument.load(pdfBinary);
    zugFeRDExporter = new ZUGFeRDExporter(doc);
    zugFeRDExporter.setZUGFeRDVersion(ZFVersion);
    zugFeRDExporter.setZUGFeRDConformanceLevel(zugferdConformanceLevel);
    zugFeRDExporter.setCreator(creator);
    zugFeRDExporter.setProducer(producer);
    zugFeRDExporter.setAttachZUGFeRDHeaders(attachZUGFeRDHeaders);
    zugFeRDExporter.setPDFA3(ensurePDFisUpgraded);

    return zugFeRDExporter;
}

From source file:org.mustangproject.ZUGFeRD.ZUGFeRDImporter.java

License:Open Source License

/**
 * Extracts a ZUGFeRD invoice from a PDF document represented by an input
 * stream. Errors are reported via exception handling.
 *
 * @param pdfStream a inputstream of a pdf file
 *///w w w. j  ava 2 s.c  o m
private void extractLowLevel(InputStream pdfStream) throws IOException {
    try (PDDocument doc = PDDocument.load(pdfStream)) {
        // PDDocumentInformation info = doc.getDocumentInformation();
        PDDocumentNameDictionary names = new PDDocumentNameDictionary(doc.getDocumentCatalog());
        //start
        InputStream XMP = doc.getDocumentCatalog().getMetadata().exportXMPMetadata();

        xmpString = convertStreamToString(XMP);

        PDEmbeddedFilesNameTreeNode etn = names.getEmbeddedFiles();
        if (etn == null) {
            return;
        }

        Map<String, PDComplexFileSpecification> efMap = etn.getNames();
        // String filePath = "/tmp/";

        if (efMap != null) {
            extractFiles(efMap); // see
            // https://memorynotfound.com/apache-pdfbox-extract-embedded-file-pdf-document/
        } else {

            List<PDNameTreeNode<PDComplexFileSpecification>> kids = etn.getKids();
            for (PDNameTreeNode<PDComplexFileSpecification> node : kids) {
                Map<String, PDComplexFileSpecification> namesL = node.getNames();
                extractFiles(namesL);
            }
        }
    }
}