Examples of org.apache.any23.extractor.rdfa.RDFa11ParserException

org.apache.any23.http.HTTPClient
Exception class raised by {@link RDFa11Parser}. @author Michele Mostarda (mostarda@fbk.eu)

     * @throws IOException
     */
    // TODO: MimeType detector to null forces the execution of all extractors, but extraction
    //       tests should be based on mimetype detection.
    protected void extract(String resource) throws ExtractionException, IOException {
        SingleDocumentExtraction ex = new SingleDocumentExtraction(
            new HTMLFixture(copyResourceToTempFile(resource)).getOpener(baseURI.toString()),
            getExtractorFactory(), new RepositoryWriter(conn)
        );
        ex.setMIMETypeDetector(null);
        report = ex.run();
    }

View Full Code Here


        final ModifiableConfiguration configuration = DefaultConfiguration.copy();
        configuration.setProperty("any23.extraction.metadata.domain.per.entity", "on");
        SingleDocumentExtraction instance =  new SingleDocumentExtraction(
                configuration,
                new HTMLFixture(copyResourceToTempFile(file)).getOpener("http://nested.test.com"),
                extractorGroup,
                cth
        );
        instance.setMIMETypeDetector( new TikaMIMETypeDetector(new WhiteSpacesPurifier()) );
        return instance;

View Full Code Here

    private Extractor extractor;
    private TripleHandler mockTripleHandler;


    @Before
    public void setUp() {
        extractor = new TitleExtractor();
        mockTripleHandler = Mockito.mock(TripleHandler.class);
        extractionResult  = new ExtractionResultImpl(
                new ExtractionContext("test-extractor-name", TEST_URI),
                extractor,
                mockTripleHandler

View Full Code Here

        }
        FormatWriter fw = factory.getRdfWriter(byteOutStream);
        fw.setAnnotated(annotate);
        outputMediaType = factory.getMimeType();
        List<TripleHandler> tripleHandlers = new ArrayList<TripleHandler>();
        tripleHandlers.add(new IgnoreAccidentalRDFa(fw));
        tripleHandlers.add(new CountingTripleHandler());
        rdfWriter = new CompositeTripleHandler(tripleHandlers);
        reporter = new ReportingTripleHandler(rdfWriter);
        rdfWriter = new IgnoreAccidentalRDFa(
            new IgnoreTitlesOfEmptyDocuments(reporter),
            true    // suppress stylesheet triples.
        );
        return true;
    }

View Full Code Here

                return 2000;
            }
        });
        ByteArrayOutputStream byteArrayOutputStream = new ByteArrayOutputStream();
        TripleHandler handler = new RDFXMLWriter(byteArrayOutputStream);
        TripleHandler rdfWriter = new IgnoreAccidentalRDFa(handler);
        ReportingTripleHandler reporting = new ReportingTripleHandler(rdfWriter);


        DocumentSource source = getDocumentSourceFromResource(
                    "/html/rdfa/ansa_2010-02-26_12645863.html",
                    "http://host.com/service");

View Full Code Here

     */
    private ExtractionReport detectAndExtract(String in) throws Exception {
        Any23 any23 = new Any23();
        ByteArrayOutputStream out = new ByteArrayOutputStream();
        ReportingTripleHandler outputHandler = new ReportingTripleHandler(
                new IgnoreAccidentalRDFa(
                        new IgnoreTitlesOfEmptyDocuments(
                                new NTriplesWriter(out)
                        )
                )
        );

View Full Code Here

        tripleHandlers.add(new IgnoreAccidentalRDFa(fw));
        tripleHandlers.add(new CountingTripleHandler());
        rdfWriter = new CompositeTripleHandler(tripleHandlers);
        reporter = new ReportingTripleHandler(rdfWriter);
        rdfWriter = new IgnoreAccidentalRDFa(
            new IgnoreTitlesOfEmptyDocuments(reporter),
            true    // suppress stylesheet triples.
        );
        return true;
    }

View Full Code Here

    private ExtractionReport detectAndExtract(String in) throws Exception {
        Any23 any23 = new Any23();
        ByteArrayOutputStream out = new ByteArrayOutputStream();
        ReportingTripleHandler outputHandler = new ReportingTripleHandler(
                new IgnoreAccidentalRDFa(
                        new IgnoreTitlesOfEmptyDocuments(
                                new NTriplesWriter(out)
                        )
                )
        );
        return any23.extract(in, "http://host.com/path", outputHandler);

View Full Code Here

     */
    @Test
    public void testProgrammaticExtraction() throws ExtractionException, IOException, URISyntaxException {
        Any23 any23 = new Any23();
        any23.setHTTPUserAgent("Any23-Servlet");
        any23.setHTTPClient(new DefaultHTTPClient() {
            @Override
            protected int getConnectionTimeout() {
                return 5000;
            }

View Full Code Here

    public void testDemoCodeSnippet2() throws Exception{
        assumeOnlineAllowed();


        /*1*/ Any23 runner = new Any23();
        /*2*/ runner.setHTTPUserAgent("test-user-agent");
        /*3*/ HTTPClient httpClient = runner.getHTTPClient();
        /*4*/ DocumentSource source = new HTTPDocumentSource(
                 httpClient,
                 "http://dbpedia.org/resource/Trento"
              );
        /*5*/ ByteArrayOutputStream out = new ByteArrayOutputStream();

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.any23.extractor.rdfa.RDFa11ParserException

org.apache.any23.AbstractAny23TestBase

org.apache.any23.Any23

org.apache.any23.Any23Test

org.apache.any23.cli.ExtractorDocumentation

org.apache.any23.cli.MicrodataParser

org.apache.any23.cli.MicrodataParser$MicrodataParserDocumentSourceConverter

org.apache.any23.cli.MimeDetector

org.apache.any23.cli.MimeDetector$MimeDetectorDocumentSourceConverter

org.apache.any23.cli.Rover

org.apache.any23.configuration.ModifiableConfiguration

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.