Package org.apache.any23.writer

Examples of org.apache.any23.writer.RepositoryWriter

322
323
324
325
326
327
328
329
330
331
332
        outputMediaType = factory.getMimeType();
        List<TripleHandler> tripleHandlers = new ArrayList<TripleHandler>();
        tripleHandlers.add(new IgnoreAccidentalRDFa(fw));
        tripleHandlers.add(new CountingTripleHandler());
        rdfWriter = new CompositeTripleHandler(tripleHandlers);
        reporter = new ReportingTripleHandler(rdfWriter);
        rdfWriter = new IgnoreAccidentalRDFa(
            new IgnoreTitlesOfEmptyDocuments(reporter),
            true    // suppress stylesheet triples.
        );
        return true;
View Full Code Here
163
164
165
166
167
168
169
170
171
172
    // 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
230
231
232
233
234
235
236
237
238
239
240
    }

    private SingleDocumentExtraction getInstance(String file) throws FileNotFoundException, IOException {
        baos = new ByteArrayOutputStream();
        rdfxmlWriter = new RDFXMLWriter(baos);
        repositoryWriter = new RepositoryWriter(conn);

        final CompositeTripleHandler cth = new CompositeTripleHandler();
        cth.addChild(rdfxmlWriter);
        cth.addChild(repositoryWriter);
View Full Code Here
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
                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
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
519
520
                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
532
533
534
535
536
537
538
539
540
                hreviewExtractionContext,
                document,
                new ExtractionResultImpl(
                        hreviewExtractionContext,
                        hReviewExtractor,
                        new RepositoryWriter(getConnection())
                )
        );
    }
View Full Code Here
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
    private void assertEncodingDetection(String encoding, String input, String expectedContent)
    throws Exception {
        DocumentSource fileDocumentSource = getDocumentSourceFromResource(input);
        Any23 any23;
        RepositoryConnection conn;
        RepositoryWriter repositoryWriter;
       
        any23 = new Any23();
        Sail store = new MemoryStore();
        store.initialize();
        conn = new SailRepository(store).getConnection();
        repositoryWriter = new RepositoryWriter(conn);
        Assert.assertTrue( any23.extract(fileDocumentSource, repositoryWriter, encoding).hasMatchingExtractors() );

        RepositoryResult<Statement> statements = conn.getStatements(null, vDCTERMS.title, null, false);
        try {
            while (statements.hasNext()) {
                Statement statement = statements.next();
                printStatement(statement);
                org.junit.Assert.assertTrue(statement.getObject().stringValue().contains(expectedContent));
            }
        } finally {
            statements.close();
        }

        fileDocumentSource = null;
        any23 = null;
        conn.close();
        repositoryWriter.close();
    }
View Full Code Here
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
                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(),
                        xfnExtractionContext,
                        document,
                        new ExtractionResultImpl(
                                xfnExtractionContext,
                                hCardExtractor,
                                new RepositoryWriter(getConnection())
                        )
                );
    }
View Full Code Here
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
519
520
                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,
                document,
                new ExtractionResultImpl(
                        adrExtractionContext,
                        adrExtractor,
                        new RepositoryWriter(getConnection())
                )
        );

    }
View Full Code Here
533
534
535
536
537
538
539
540
541
                hreviewExtractionContext,
                document,
                new ExtractionResultImpl(
                        hreviewExtractionContext,
                        hReviewExtractor,
                        new RepositoryWriter(getConnection())
                )
        );
    }
View Full Code Here
TOP

Related Classes of org.apache.any23.writer.RepositoryWriter

  • 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.