Package org.apache.any23.extractor

Examples of org.apache.any23.extractor.ExampleInputOutput

137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
     * @throws ExtractionException
     */
    public void printReport(ExtractorRegistry registry) throws IOException, ExtractionException {
        for (String extractorName : registry.getAllNames()) {
            ExtractorFactory<?> factory = registry.getFactory(extractorName);
            ExampleInputOutput example = new ExampleInputOutput(factory);
            System.out.println("Extractor: " + extractorName);
            System.out.println("\ttype: " + getType(factory));
            System.out.println();
            final String exampleInput = example.getExampleInput();
            if(exampleInput == null) {
                System.out.println("(No Example Available)");
            } else {
                System.out.println("-------- Example Input  --------");
                System.out.println(exampleInput);
                System.out.println("-------- Example Output --------");
                String output = example.getExampleOutput();
                System.out.println(output == null || output.trim().length() == 0 ? "(No Output Generated)" : output);
            }
            System.out.println("================================");
            System.out.println();
        }
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
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
        InputStream input = new BufferedInputStream(this.getClass().getResourceAsStream(filename));
       
        Document document = new TagSoupParser(input, baseURI.stringValue()).getDOM();
        HCardExtractor hCardExtractor = new HCardExtractorFactory().createExtractor();
        ExtractionContext hcExtractionContext = new ExtractionContext(
                hCardExtractor.getDescription().getExtractorName(),
                baseURI
        );
        hCardExtractor.run(
                ExtractionParameters.newDefault(),
                hcExtractionContext,
                document,
                new ExtractionResultImpl(
                        hcExtractionContext,
                        hCardExtractor,
                        new RepositoryWriter(getConnection())
                )
        );
        XFNExtractor xfnExtractor = new XFNExtractorFactory().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
       
        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
TOP

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

  • 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.