Package org.apache.any23.cli

Examples of org.apache.any23.cli.MicrodataParser$MicrodataParserDocumentSourceConverter

305
306
307
308
309
310
311
312
313
314
315
    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
244
245
246
247
248
249
250
251
                configuration,
                new HTMLFixture(copyResourceToTempFile(file)).getOpener("http://nested.test.com"),
                extractorGroup,
                cth
        );
        instance.setMIMETypeDetector( new TikaMIMETypeDetector(new WhiteSpacesPurifier()) );
        return instance;
    }
View Full Code Here
244
245
246
247
248
249
250
251
                configuration,
                new HTMLFixture(copyResourceToTempFile(file)).getOpener("http://nested.test.com"),
                extractorGroup,
                cth
        );
        instance.setMIMETypeDetector( new TikaMIMETypeDetector(new WhiteSpacesPurifier()) );
        return instance;
    }
View Full Code Here
55
56
57
58
59
60
61
    private TikaMIMETypeDetector detector;

    @Before
    public void setUp() throws Exception {
        detector = new TikaMIMETypeDetector(new WhiteSpacesPurifier());
    }
View Full Code Here
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
    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
114
115
116
117
118
119
120
121
122
123
124
            );
            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
189
190
191
192
193
194
195
196
197
198
199
        /*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
221
222
223
224
225
226
227
228
229
230
231
        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
273
274
275
276
277
278
279
280
281
282
283
        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
306
307
308
309
310
311
312
313
314
315
316
        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
TOP

Related Classes of org.apache.any23.cli.MicrodataParser$MicrodataParserDocumentSourceConverter

  • 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
    • Copyright © 2018 www.massapicom. All rights reserved.
    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.