Package org.apache.any23.extractor

Examples of org.apache.any23.extractor.ExtractionException

443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
        );
        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(),
                        xfnExtractionContext,
                        document,
                        new ExtractionResultImpl(
                                xfnExtractionContext,
                                hCardExtractor,
                                new RepositoryWriter(getConnection())
                        )
                );
View Full Code Here
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
512
513
514
515
516
517
518
        );
        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,
                document,
                new ExtractionResultImpl(
                        adrExtractionContext,
                        adrExtractor,
                        new RepositoryWriter(getConnection())
                )
        );
View Full Code Here
529
530
531
532
533
534
535
536
537
538
539
        );
        hReviewExtractor.run(
                ExtractionParameters.newDefault(),
                hreviewExtractionContext,
                document,
                new ExtractionResultImpl(
                        hreviewExtractionContext,
                        hReviewExtractor,
                        new RepositoryWriter(getConnection())
                )
        );
View Full Code Here
89
90
91
92
93
94
95
96
97
98
99
        compositeTripleHandler.addChild(verifierTripleHandler);
        final CountingTripleHandler countingTripleHandler = new CountingTripleHandler();
        compositeTripleHandler.addChild(countingTripleHandler);
        final ByteArrayOutputStream out = new ByteArrayOutputStream();
        compositeTripleHandler.addChild( new NTriplesWriter(out) );
        final ExtractionResult extractionResult = new ExtractionResultImpl(
                extractionContext, extractor, compositeTripleHandler
        );
        extractor.run(extractionParameters, extractionContext, is, extractionResult);
        compositeTripleHandler.close();
        logger.info(out.toString());
View Full Code Here
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
     * @throws InstantiationException
     * @throws IllegalAccessException
     */
    @Test
    public void testDetectExtractorPlugins() throws IOException, InstantiationException, IllegalAccessException {
        final ExtractorGroup extractorGroup = manager.getApplicableExtractors(
                new ExtractorRegistryImpl(),
                HTML_SCRAPER_TARGET_DIR,  // Required to satisfy class dependencies.
                HTML_SCRAPER_DEPENDENCY_DIR,
                OFFICE_SCRAPER_TARGET_DIR
, OFFICE_SCRAPER_DEPENDENCY_DIR // Required to satisfy class dependencies.
        );
        assertEquals("Did not find the number of expected extractors", NUM_OF_EXTRACTORS ,        // HTMLScraper Plugin, OfficeScraper Plugin.
                extractorGroup.getNumOfExtractors()
        );
    }
View Full Code Here
325
326
327
328
329
330
331
332
333
334
            //for (ExtractorFactory<?> extractorFactory : initialExtractorGroup) {
            //    newFactoryList.add(extractorFactory);
            //}

            return new ExtractorGroup(newFactoryList);
        } finally {
            logger.info(report.toString());
        }
    }
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
     * @throws IllegalAccessException
     */
    @Test
    public void testDetectExtractorPlugins() throws IOException, InstantiationException, IllegalAccessException {
        final ExtractorGroup extractorGroup = manager.getApplicableExtractors(
                new ExtractorRegistryImpl(),
                HTML_SCRAPER_TARGET_DIR,  // Required to satisfy class dependencies.
                HTML_SCRAPER_DEPENDENCY_DIR,
                OFFICE_SCRAPER_TARGET_DIR
, OFFICE_SCRAPER_DEPENDENCY_DIR // Required to satisfy class dependencies.
        );
View Full Code Here
161
162
163
164
165
166
167
168
169
170
171
172
     * @throws IOException
     */
    // TODO: MimeType detector to null forces the execution of all extractors, but extraction
    //       tests should be based on mimetype detection.
    protected void extract(String resource) throws ExtractionException, IOException {
        SingleDocumentExtraction ex = new SingleDocumentExtraction(
            new HTMLFixture(copyResourceToTempFile(resource)).getOpener(baseURI.toString()),
            getExtractorFactory(), new RepositoryWriter(conn)
        );
        ex.setMIMETypeDetector(null);
        report = ex.run();
    }
View Full Code Here
240
241
242
243
244
245
246
247
248
249
250
        final ModifiableConfiguration configuration = DefaultConfiguration.copy();
        configuration.setProperty("any23.extraction.metadata.domain.per.entity", "on");
        SingleDocumentExtraction instance =  new SingleDocumentExtraction(
                configuration,
                new HTMLFixture(copyResourceToTempFile(file)).getOpener("http://nested.test.com"),
                extractorGroup,
                cth
        );
        instance.setMIMETypeDetector( new TikaMIMETypeDetector(new WhiteSpacesPurifier()) );
        return instance;
View Full Code Here
46
47
48
49
50
51
52
53
54
55
56
    private Extractor extractor;
    private TripleHandler mockTripleHandler;

    @Before
    public void setUp() {
        extractor = new TitleExtractor();
        mockTripleHandler = Mockito.mock(TripleHandler.class);
        extractionResult  = new ExtractionResultImpl(
                new ExtractionContext("test-extractor-name", TEST_URI),
                extractor,
                mockTripleHandler
View Full Code Here
TOP

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

  • 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.