Package org.apache.any23.configuration

Examples of org.apache.any23.configuration.ModifiableConfiguration

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
       
        InputStream input = new BufferedInputStream(this.getClass().getResourceAsStream(filename));

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

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

        AdrExtractor adrExtractor = new AdrExtractorFactory().createExtractor();
        ExtractionContext adrExtractionContext = new ExtractionContext(
                adrExtractor.getDescription().getExtractorName(), baseURI
        );
        adrExtractor.run(
                ExtractionParameters.newDefault(),
                adrExtractionContext,
View Full Code Here
522
523
524
525
526
527
528
529
530
531
532
    private void extractHRevAndRelated(String filename) throws ExtractionException, IOException {
        extractHCardAndRelated(filename);
        InputStream input = new BufferedInputStream(this.getClass().getResourceAsStream(filename));
        Document document = new TagSoupParser(input, baseURI.stringValue()).getDOM();
        HReviewExtractor hReviewExtractor = new HReviewExtractorFactory().createExtractor();
        ExtractionContext hreviewExtractionContext = new ExtractionContext(
                hReviewExtractor.getDescription().getExtractorName(), baseURI
        );
        hReviewExtractor.run(
                ExtractionParameters.newDefault(),
                hreviewExtractionContext,
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
83
84
85
86
87
88
89
90
        try {
            final URI documentURI = context.getDocumentURI();
            final Workbook workbook = createWorkbook(documentURI, in);
            processWorkbook(documentURI, workbook, er);
        } catch (Exception e) {
            throw new ExtractionException("An error occurred while extracting MS Excel content.", e);
        }
    }
View Full Code Here
69
70
71
72
73
74
75
76
        final String uri = getInputURIFromRequest(req);
        if (uri == null) {
            responder.sendError(404, "Missing URI in GET request. Try /format/http://example.com/myfile", report);
            return;
        }
        final ExtractionParameters eps = getExtractionParameters(req);
        responder.runExtraction(createHTTPDocumentSource(responder, uri, report), eps, format, report, annotate);
    }
View Full Code Here
88
89
90
91
92
93
94
95
96
97
98
        final String format = getFormatFromRequestOrNegotiation(req);
        if (format == null) {
            responder.sendError(406, "Client accept header does not include a supported output format", report);
            return;
        }
        final ExtractionParameters eps = getExtractionParameters(req);
        if ("application/x-www-form-urlencoded".equals(getContentTypeHeader(req))) {
            if (uri != null) {
                log("Attempting conversion to '" + format + "' from URI <" + uri + ">");
                responder.runExtraction(createHTTPDocumentSource(responder, uri, report), eps, format, report, annotate);
                return;
View Full Code Here
261
262
263
264
265
266
267
        );
    }
   
    private ExtractionParameters getExtractionParameters(HttpServletRequest request) {
        final ValidationMode mode = getValidationMode(request);
        return new ExtractionParameters(DefaultConfiguration.singleton(), mode);
    }
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
        final String FILE = "test2-workbook.xls";
        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);
View Full Code Here
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
        CompositeTripleHandler compositeTH1 = new CompositeTripleHandler();
        compositeTH1.addChild(cth1);
        compositeTH1.addChild(ctw1);
        try {
            runner.extract(
                    new ExtractionParameters(
                            DefaultConfiguration.singleton(),
                            ValidationMode.None
                    ),
                    source,
                    compositeTH1
            );
        } finally {
            compositeTH1.close();
        }
        logger.info(baos.toString());
        Assert.assertEquals("Unexpected number of triples.", EXPECTED_TRIPLES, cth1.getCount() );

        baos.reset();
        CountingTripleHandler cth2 = new CountingTripleHandler();
        NTriplesWriter ctw2 = new NTriplesWriter(baos);
        CompositeTripleHandler compositeTH2 = new CompositeTripleHandler();
        compositeTH2.addChild(cth2);
        compositeTH2.addChild(ctw2);
        runner.extract(
                new ExtractionParameters(
                        DefaultConfiguration.singleton(),
                        ValidationMode.ValidateAndFix
                ),
                source,
                compositeTH2
View Full Code Here
TOP

Related Classes of org.apache.any23.configuration.ModifiableConfiguration

  • 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
    • 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.