Package org.apache.any23.source

Examples of org.apache.any23.source.DocumentSource

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);
        runner.extract(source, handler);
        String n3 = out.toString("UTF-8");
View Full Code Here
327
328
329
330
331
332
333
334
335
336
337
        // ?doc <http://www.w3.org/1999/xhtml/vocab#icon> <https://any23.googlecode.com/favicon.ico> .
        // ?doc <http://www.w3.org/1999/xhtml/vocab#stylesheet> <https://any23.googlecode.com/design/style.css>  .

        final int EXPECTED_TRIPLES = 9;
        Any23 runner = new Any23();
        DocumentSource source = getDocumentSourceFromResource(
                "/org/apache/any23/validator/missing-og-namespace.html",
                "http://www.test.com");

        ByteArrayOutputStream baos = new ByteArrayOutputStream();
View Full Code Here
368
369
370
371
372
373
374
375
376
377
378
    @Test
    public void testExtractionParametersWithNestingDisabled()
            throws IOException, ExtractionException, TripleHandlerException {
        final int EXPECTED_TRIPLES = 19;
        Any23 runner = new Any23();
        DocumentSource source = getDocumentSourceFromResource(
                "/microformats/nested-microformats-a1.html",
                "http://www.test.com");

        ByteArrayOutputStream baos = new ByteArrayOutputStream();
View Full Code Here
406
407
408
409
410
411
412
413
414
415
416
    }

    @Test
    public void testExceptionPropagation() throws IOException {
        Any23 any23 = new Any23();
        DocumentSource source = getDocumentSourceFromResource(
                "/application/turtle/geolinkeddata.ttl", "http://www.test.com");
        CountingTripleHandler cth1 = new CountingTripleHandler();
        try {
            any23.extract(source, cth1);
        } catch (ExtractionException e) {
View Full Code Here
430
431
432
433
434
435
436
437
438
439
440
            ExtractionException {
        final String documentURI = "http://www.test.com/resource.xml";
        final String contentType = "application/xml";
        final String in = StreamUtils.asString(this.getClass()
                .getResourceAsStream("any23-xml-mimetype.xml"));
        final DocumentSource doc = new StringDocumentSource(in, documentURI,
                contentType);
        final Any23 any23 = new Any23();
        final CountingTripleHandler cth = new CountingTripleHandler(false);
        final ReportingTripleHandler rth = new ReportingTripleHandler(cth);
        final ExtractionReport report = any23.extract(doc, rth);
View Full Code Here
488
489
490
491
492
493
494
495
496
497
498
    public void testAbstractMethodErrorIssue186_1() throws IOException,
            ExtractionException {
        final Any23 runner = new Any23();
        final String content = FileUtils
                .readResourceContent("/html/rdfa/rdfa-issue186-1.xhtml");
        final DocumentSource source = new StringDocumentSource(content,
                "http://base.com");
        final ByteArrayOutputStream out = new ByteArrayOutputStream();
        final TripleHandler handler = new NTriplesWriter(out);
        runner.extract(source, handler);
        String n3 = out.toString("UTF-8");
View Full Code Here
503
504
505
506
507
508
509
510
511
512
513
    public void testAbstractMethodErrorIssue186_2() throws IOException,
            ExtractionException {
        final Any23 runner = new Any23();
        final String content = FileUtils
                .readResourceContent("/html/rdfa/rdfa-issue186-2.xhtml");
        final DocumentSource source = new StringDocumentSource(content,
                "http://richard.cyganiak.de/");
        final ByteArrayOutputStream out = new ByteArrayOutputStream();
        final TripleHandler handler = new NTriplesWriter(out);
        runner.extract(source, handler);
        final String n3 = out.toString("UTF-8");
View Full Code Here
521
522
523
524
525
526
527
528
529
530
531
        modifiableConf.setProperty("any23.extraction.metadata.timesize", "off");
        final Any23 any23 = new Any23(modifiableConf);

        final String content = FileUtils
                .readResourceContent("/rdf/rdf-issue183.ttl");
        final DocumentSource source = new StringDocumentSource(content,
                "http://base.com");
        final ByteArrayOutputStream out = new ByteArrayOutputStream();
        final TripleHandler handler = new NTriplesWriter(out);
        any23.extract(source, handler);
        handler.close();
View Full Code Here
608
609
610
611
612
613
614
615
616
617
618
     * @param expectedContent
     * @throws Exception
     */
    private void assertEncodingDetection(String encoding, String input, String expectedContent)
    throws Exception {
        DocumentSource fileDocumentSource = getDocumentSourceFromResource(input);
        Any23 any23;
        RepositoryConnection conn = null;
        RepositoryWriter repositoryWriter = null;
       
        any23 = new Any23();
View Full Code Here
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
        if (document.isEmpty()) {
            throw new IllegalArgumentException("No input document URL specified");
        }
        InputStream documentInputInputStream = null;
        try {
            final DocumentSource documentSource = document.get(0);
            documentInputInputStream = documentSource.openInputStream();
            final TagSoupParser tagSoupParser = new TagSoupParser(
                    documentInputInputStream,
                    documentSource.getDocumentURI()
            );
            org.apache.any23.extractor.microdata.MicrodataParser.getMicrodataAsJSON(tagSoupParser.getDOM(), System.out);
        } finally {
            if (documentInputInputStream != null) StreamUtils.closeGracefully(documentInputInputStream);
        }
View Full Code Here
TOP

Related Classes of org.apache.any23.source.DocumentSource

  • 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.