Package org.apache.any23.extractor

Examples of org.apache.any23.extractor.ExtractionContext

77
78
79
80
81
82
83
84
85
86
87
        processFile(FILE);
    }

    private void processFile(String resource) throws IOException, ExtractionException, TripleHandlerException {
        final ExtractionParameters extractionParameters = ExtractionParameters.newDefault();
        final ExtractionContext extractionContext = new ExtractionContext(
                extractor.getDescription().getExtractorName(),
                RDFUtils.uri("file://" + resource)
        );
        final InputStream is = this.getClass().getResourceAsStream(resource);
        final CompositeTripleHandler compositeTripleHandler = new CompositeTripleHandler();
View Full Code Here
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
                System.getProperty("test.data", "src/test/resources") +
                        "/html/" + filename);

        Document document = new TagSoupParser(new FileInputStream(file), baseURI.stringValue()).getDOM();
        HCardExtractor hCardExtractor = HCardExtractor.factory.createExtractor();
        ExtractionContext hcExtractionContext = new ExtractionContext(
                hCardExtractor.getDescription().getExtractorName(),
                baseURI
        );
        hCardExtractor.run(
                ExtractionParameters.newDefault(),
                hcExtractionContext,
                document,
                new ExtractionResultImpl(
                        hcExtractionContext,
                        hCardExtractor,
                        new RepositoryWriter(getConnection())
                )
        );
        XFNExtractor xfnExtractor = XFNExtractor.factory.createExtractor();
        ExtractionContext xfnExtractionContext = new ExtractionContext(
                xfnExtractor.getDescription().getExtractorName(),
                baseURI
        );
        xfnExtractor.run(
                        ExtractionParameters.newDefault(),
View Full Code Here
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
        File file = new File(
                System.getProperty("test.data", "src/test/resources/") + filename);

        Document document = new TagSoupParser(new FileInputStream(file), baseURI.stringValue()).getDOM();
        HCardExtractor hCardExtractor = HCardExtractor.factory.createExtractor();
        ExtractionContext hCardExtractionContext = new ExtractionContext(
                hCardExtractor.getDescription().getExtractorName(), baseURI
        );
        hCardExtractor.run(
                ExtractionParameters.newDefault(),
                hCardExtractionContext,
                document,
                new ExtractionResultImpl(
                        hCardExtractionContext,
                        hCardExtractor, new RepositoryWriter(getConnection())
                )
        );

        GeoExtractor geoExtractor = GeoExtractor.factory.createExtractor();
        ExtractionContext geoExtractionContext = new ExtractionContext(
                geoExtractor.getDescription().getExtractorName(), baseURI
        );
        geoExtractor.run(
                ExtractionParameters.newDefault(),
                geoExtractionContext,
                document,
                new ExtractionResultImpl(
                        geoExtractionContext,
                        geoExtractor,
                        new RepositoryWriter(getConnection())
                )
        );

        AdrExtractor adrExtractor = AdrExtractor.factory.createExtractor();
        ExtractionContext adrExtractionContext = new ExtractionContext(
                adrExtractor.getDescription().getExtractorName(), baseURI
        );
        adrExtractor.run(
                ExtractionParameters.newDefault(),
                adrExtractionContext,
View Full Code Here
523
524
525
526
527
528
529
530
531
532
533
        extractHCardAndRelated(filename);
        File file = new File(
                System.getProperty("test.data", "src/test/resources/") + filename);
        Document document = new TagSoupParser(new FileInputStream(file), baseURI.stringValue()).getDOM();
        HReviewExtractor hReviewExtractor = HReviewExtractor.factory.createExtractor();
        ExtractionContext hreviewExtractionContext = new ExtractionContext(
                hReviewExtractor.getDescription().getExtractorName(), baseURI
        );
        hReviewExtractor.run(
                ExtractionParameters.newDefault(),
                hreviewExtractionContext,
View Full Code Here
69
70
71
72
73
74
75
76
77
78
79
    public void testTypedLiteralIncompatibleValueSupport()
    throws IOException, ExtractionException, TripleHandlerException {
        final URI uri = RDFUtils.uri("http://host.com/test-malformed-literal.turtle");
        ByteArrayOutputStream baos = new ByteArrayOutputStream();
        final TripleHandler th = new RDFXMLWriter(baos);
        final ExtractionContext extractionContext = new ExtractionContext("turtle-extractor", uri);
        final ExtractionResult result = new ExtractionResultImpl(extractionContext, extractor, th);
        extractor.setStopAtFirstError(false);
        try {
            extractor.run(
                    ExtractionParameters.newDefault(),
View Full Code Here
51
52
53
54
55
56
57
58
59
60
61
        final ExtractorDescription ed = mock(ExtractorDescription.class);
        when(ed.getExtractorName()).thenReturn(FAKE_EXTRACTOR_NAME);
        when(extractor.getDescription()).thenReturn(ed);

        final TripleHandler th = mock(TripleHandler.class);
        final ExtractionContext extractionContext = new ExtractionContext(
                extractor.getDescription().getExtractorName(),
                new URIImpl("http://fake.document.uri")
        );
        final ExtractionResult er = new ExtractionResultImpl(extractionContext, extractor, th);
        er.notifyIssue(IssueReport.IssueLevel.Fatal  , "Fake fatal error.", 1, 2);
View Full Code Here
55
56
57
58
59
60
61
62
63
64
65
    private void checkTriple(String predicate, VerificationMode verificationMode)
    throws TripleHandlerException {
        final String DOCUMENT_URI = "http://an.html.page";
        final TripleHandler mockTripleHandler = mock(TripleHandler.class);
        final ValueFactory valueFactory = new ValueFactoryImpl();
        ExtractionContext extractionContext = new ExtractionContext(
                "test-extractor",
                valueFactory.createURI(DOCUMENT_URI)
        );
        final IgnoreAccidentalRDFa ignoreAccidentalRDFa = new IgnoreAccidentalRDFa(mockTripleHandler, true);
        ignoreAccidentalRDFa.openContext(extractionContext);
View Full Code Here
50
51
52
53
54
55
56
57
58
59
60
        handler.expectNamespace("ex", "http://example.com/", "test", docURI, null);
        handler.expectTriple(s, p, o, null, "test", docURI, null);
        handler.expectCloseContext("test", docURI, null);
        handler.expectEndDocument(docURI);

        ExtractionContext context = new ExtractionContext("test", docURI);
        blocker.openContext(context);
        blocker.blockContext(context);
        blocker.receiveNamespace("ex", "http://example.com/", context);
        blocker.receiveTriple(s, p, o, null, context);
        blocker.closeContext(context);
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
    @Test
    public void testRun() throws IOException, ExtractionException {
        final InputStream is = this.getClass().getResourceAsStream("html-scraper-extractor-test.html");
        final ExtractionResult extractionResult = mock(ExtractionResult.class);
        final URI pageURI = ValueFactoryImpl.getInstance().createURI("http://fake/test/page/testrun");
        final ExtractionContext extractionContext = new ExtractionContext(
                extractor.getDescription().getExtractorName(),
                pageURI
        );
        extractor.run(ExtractionParameters.newDefault(), extractionContext, is, extractionResult);
View Full Code Here
77
78
79
80
81
82
83
84
85
86
87
        processFile(FILE);
    }

    private void processFile(String resource) throws IOException, ExtractionException, TripleHandlerException {
        final ExtractionParameters extractionParameters = ExtractionParameters.newDefault();
        final ExtractionContext extractionContext = new ExtractionContext(
                extractor.getDescription().getExtractorName(),
                RDFUtils.uri("file://" + resource)
        );
        final InputStream is = this.getClass().getResourceAsStream(resource);
        final CompositeTripleHandler compositeTripleHandler = new CompositeTripleHandler();
View Full Code Here
TOP

Related Classes of org.apache.any23.extractor.ExtractionContext

  • 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.