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

Example 11 with PDDocument

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

the class XMPUtil method readXMP.

/**
     * Try to read the given BibTexEntry from the XMP-stream of the given
     * inputstream containing a PDF-file.
     *
     * @param inputStream The inputstream to read from.
     * @return list of BibEntries retrieved from the stream. May be empty, but never null
     * @throws IOException Throws an IOException if the file cannot be read, so the user than remove a lock or cancel
     *                     the operation.
     */
public static List<BibEntry> readXMP(InputStream inputStream, XMPPreferences xmpPreferences) throws IOException {
    List<BibEntry> result = new LinkedList<>();
    try (PDDocument document = loadWithAutomaticDecryption(inputStream)) {
        Optional<XMPMetadata> meta = XMPUtil.getXMPMetadata(document);
        if (meta.isPresent()) {
            List<XMPSchema> schemas = meta.get().getSchemasByNamespaceURI(XMPSchemaBibtex.NAMESPACE);
            for (XMPSchema schema : schemas) {
                XMPSchemaBibtex bib = (XMPSchemaBibtex) schema;
                BibEntry entry = bib.getBibtexEntry();
                if (entry.getType() == null) {
                    entry.setType(BibEntry.DEFAULT_TYPE);
                }
                result.add(entry);
            }
            // If we did not find anything have a look if a Dublin Core exists
            if (result.isEmpty()) {
                schemas = meta.get().getSchemasByNamespaceURI(XMPSchemaDublinCore.NAMESPACE);
                for (XMPSchema schema : schemas) {
                    XMPSchemaDublinCore dc = (XMPSchemaDublinCore) schema;
                    Optional<BibEntry> entry = XMPUtil.getBibtexEntryFromDublinCore(dc, xmpPreferences);
                    if (entry.isPresent()) {
                        if (entry.get().getType() == null) {
                            entry.get().setType(BibEntry.DEFAULT_TYPE);
                        }
                        result.add(entry.get());
                    }
                }
            }
        }
        if (result.isEmpty()) {
            // If we did not find any XMP metadata, search for non XMP metadata
            PDDocumentInformation documentInformation = document.getDocumentInformation();
            Optional<BibEntry> entry = XMPUtil.getBibtexEntryFromDocumentInformation(documentInformation);
            entry.ifPresent(result::add);
        }
    }
    // return empty list, if no metadata was found
    if (result.isEmpty()) {
        return Collections.emptyList();
    }
    return result;
}

Example 12 with PDDocument

use of org.apache.pdfbox.pdmodel.PDDocument 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 13 with PDDocument

use of org.apache.pdfbox.pdmodel.PDDocument 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());
    }
}

Example 14 with PDDocument

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

the class XMPUtilTest method testResolveStrings2.

/**
     * A better testcase for resolveStrings. Makes sure that also the document information and dublin core are written
     * correctly.
     * <p/>
     * Data was contributed by Philip K.F. Hölzenspies (p.k.f.holzenspies [at] utwente.nl).
     *
     * @throws IOException
     * @throws TransformerException
     */
@Test
public void testResolveStrings2() throws IOException, TransformerException {
    try (BufferedReader fr = Files.newBufferedReader(Paths.get("src/test/resources/org/jabref/util/twente.bib"), StandardCharsets.UTF_8)) {
        ParserResult result = new BibtexParser(importFormatPreferences).parse(fr);
        Assert.assertEquals("Arvind", result.getDatabase().resolveForStrings("#Arvind#"));
        AuthorList originalAuthors = AuthorList.parse("Patterson, David and Arvind and Asanov\\'\\i{}c, Krste and Chiou, Derek and Hoe, James and Kozyrakis, Christos and Lu, S{hih-Lien} and Oskin, Mark and Rabaey, Jan and Wawrzynek, John");
        try {
            XMPUtil.writeXMP(pdfFile, result.getDatabase().getEntryByKey("Patterson06").get(), result.getDatabase(), xmpPreferences);
            // Test whether we the main function can load the bibtex correctly
            BibEntry b = XMPUtil.readXMP(pdfFile, xmpPreferences).get(0);
            Assert.assertNotNull(b);
            Assert.assertEquals(originalAuthors, AuthorList.parse(b.getField("author").get()));
            // Next check from Document Information
            try (PDDocument document = PDDocument.load(pdfFile.getAbsoluteFile())) {
                Assert.assertEquals(originalAuthors, AuthorList.parse(document.getDocumentInformation().getAuthor()));
                b = XMPUtil.getBibtexEntryFromDocumentInformation(document.getDocumentInformation()).get();
                Assert.assertEquals(originalAuthors, AuthorList.parse(b.getField("author").get()));
                // Now check from Dublin Core
                PDDocumentCatalog catalog = document.getDocumentCatalog();
                PDMetadata metaRaw = catalog.getMetadata();
                if (metaRaw == null) {
                    Assert.fail();
                    // To avoid warnings
                    return;
                }
                XMPMetadata meta = new XMPMetadata(XMLUtil.parse(metaRaw.createInputStream()));
                meta.addXMLNSMapping(XMPSchemaBibtex.NAMESPACE, XMPSchemaBibtex.class);
                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("David Patterson", dcSchema.getCreators().get(0));
                Assert.assertEquals("Arvind", dcSchema.getCreators().get(1));
                Assert.assertEquals("Krste Asanov\\'\\i{}c", dcSchema.getCreators().get(2));
                b = XMPUtil.getBibtexEntryFromDublinCore(dcSchema, xmpPreferences).get();
                Assert.assertNotNull(b);
                Assert.assertEquals(originalAuthors, AuthorList.parse(b.getField("author").get()));
            }
        } finally {
            if (!pdfFile.delete()) {
                System.err.println("Cannot delete temporary file");
            }
        }
    }
}

Example 15 with PDDocument

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

the class XMPUtilTest method readManually.

public static String readManually(File tempFile) throws IOException {
    try (PDDocument document = PDDocument.load(tempFile.getAbsoluteFile())) {
        if (document.isEncrypted()) {
            Assert.fail("Cannot add metadata to encrypted document.");
        }
        PDDocumentCatalog catalog = document.getDocumentCatalog();
        PDMetadata meta = catalog.getMetadata();
        if (meta == null) {
            return null;
        } else {
            try (InputStream is = meta.createInputStream();
                InputStreamReader reader = new InputStreamReader(is, StandardCharsets.UTF_8)) {
                // trim() for killing padding end-newline
                return CharStreams.toString(reader).trim();
            }
        }
    }
}