Examples of org.apache.any23.cli.ExtractorDocumentation

org.apache.any23.source.DocumentSource
This class provides some command-line documentation about available extractors and their usage.

    public void testGZippedContent() throws IOException, URISyntaxException, ExtractionException {
        assumeOnlineAllowed();


        Any23 runner = new Any23();
        runner.setHTTPUserAgent("test-user-agent");
        HTTPClient httpClient = runner.getHTTPClient();
        DocumentSource source = new HTTPDocumentSource(
                httpClient,
                "http://products.semweb.bestbuy.com/y/products/7590289/"
        );
        ByteArrayOutputStream out = new ByteArrayOutputStream();

View Full Code Here

                configuration,
                new HTMLFixture(copyResourceToTempFile(file)).getOpener("http://nested.test.com"),
                extractorGroup,
                cth
        );
        instance.setMIMETypeDetector( new TikaMIMETypeDetector(new WhiteSpacesPurifier()) );
        return instance;
    }

View Full Code Here

                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 TikaMIMETypeDetector detector;


    @Before
    public void setUp() throws Exception {
        detector = new TikaMIMETypeDetector(new WhiteSpacesPurifier());
    }

View Full Code Here

    private String getFormatFromRequestOrNegotiation(HttpServletRequest request) {
        String fromRequest = getFormatFromRequest(request);
        if (fromRequest != null && !"".equals(fromRequest) && !"best".equals(fromRequest)) {
            return fromRequest;
        }
        MediaRangeSpec result = Any23Negotiator.getNegotiator().getBestMatch(request.getHeader("Accept"));
        if (result == null) {
            return null;
        }
        else if (RDFFormat.TURTLE.hasMIMEType(result.getMediaType())) {
            return "turtle";
        }
        else if (RDFFormat.N3.hasMIMEType(result.getMediaType())) {
            return "n3";
        }
        else if (RDFFormat.NQUADS.hasMIMEType(result.getMediaType())) {
            return "nq";
        }
        else if (RDFFormat.RDFXML.hasMIMEType(result.getMediaType())) {
            return "rdf";
        }
        else if (RDFFormat.NTRIPLES.hasMIMEType(result.getMediaType())) {
            return "nt";
        }
        else {
            return "turtle";    // shouldn't happen
        }

View Full Code Here

            );
            return;
        }
        log("Attempting conversion to '" + format + "' from POST body");
        responder.runExtraction(
                new ByteArrayDocumentSource(
                        req.getInputStream(),
                        Servlet.DEFAULT_BASE_URI,
                        getContentTypeHeader(req)
                ),
                eps,

View Full Code Here

        /*2*/ final String content = "@prefix foo: <http://example.org/ns#> .   " +
                                     "@prefix : <http://other.example.org/ns#> ." +
                                     "foo:bar foo: : .                          " +
                                     ":bar : foo:bar .                           ";
        //    The second argument of StringDocumentSource() must be a valid URI.
        /*3*/ DocumentSource source = new StringDocumentSource(content, "http://host.com/service");
        /*4*/ ByteArrayOutputStream out = new ByteArrayOutputStream();
        /*5*/ TripleHandler handler = new NTriplesWriter(out);
              try {
        /*6*/     runner.extract(source, handler);
              } finally {

View Full Code Here

        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();
        /*6*/ TripleHandler handler = new NTriplesWriter(out);

View Full Code Here

        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");


        Assert.assertTrue( any23.extract(source, reporting).hasMatchingExtractors() );
        try {

View Full Code Here

        assumeOnlineAllowed();


        Any23 runner = new Any23();
        runner.setHTTPUserAgent("test-user-agent");
        HTTPClient httpClient = runner.getHTTPClient();
        DocumentSource source = new HTTPDocumentSource(
                httpClient,
                "http://products.semweb.bestbuy.com/y/products/7590289/"
        );
        ByteArrayOutputStream out = new ByteArrayOutputStream();
        TripleHandler handler = new NTriplesWriter(out);

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.any23.cli.ExtractorDocumentation

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.cli.Tool

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.