Package org.apache.any23.extractor

Examples of org.apache.any23.extractor.SingleDocumentExtractionReport

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
289
290
291
292
293
294
295
296
297
298
299
300
301
302
    ) throws IOException, ExtractionException {
        final SingleDocumentExtraction ex = new SingleDocumentExtraction(configuration, in, factories, outputHandler);
        ex.setMIMETypeDetector(mimeTypeDetector);
        ex.setLocalCopyFactory(streamCache);
        ex.setParserEncoding(encoding);
        final SingleDocumentExtractionReport sder = ex.run(eps);
        return new ExtractionReport(
                ex.getMatchingExtractors(),
                ex.getParserEncoding(),
                ex.getDetectedMIMEType(),
                sder.getValidationReport(),
                sder.getExtractorToIssues()
        );
    }
View Full Code Here
293
294
295
296
297
298
299
300
301
302
303
304
305
306
    ) throws IOException, ExtractionException {
        final SingleDocumentExtraction ex = new SingleDocumentExtraction(configuration, in, factories, outputHandler);
        ex.setMIMETypeDetector(mimeTypeDetector);
        ex.setLocalCopyFactory(streamCache);
        ex.setParserEncoding(encoding);
        final SingleDocumentExtractionReport sder = ex.run(eps);
        return new ExtractionReport(
                ex.getMatchingExtractors(),
                ex.getParserEncoding(),
                ex.getDetectedMIMEType(),
                sder.getValidationReport(),
                sder.getExtractorToIssues()
        );
    }
View Full Code Here
290
291
292
293
294
295
296
297
298
299
300
301
302
303
    ) throws IOException, ExtractionException {
        final SingleDocumentExtraction ex = new SingleDocumentExtraction(configuration, in, factories, outputHandler);
        ex.setMIMETypeDetector(mimeTypeDetector);
        ex.setLocalCopyFactory(streamCache);
        ex.setParserEncoding(encoding);
        final SingleDocumentExtractionReport sder = ex.run(eps);
        return new ExtractionReport(
                ex.getMatchingExtractors(),
                ex.getParserEncoding(),
                ex.getDetectedMIMEType(),
                sder.getValidationReport(),
                sder.getExtractorToIssues()
        );
    }
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
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
        }
        FormatWriter fw = factory.getRdfWriter(byteOutStream);
        fw.setAnnotated(annotate);
        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
270
271
272
273
274
275
276
277
278
279
280
                return 2000;
            }
        });
        ByteArrayOutputStream byteArrayOutputStream = new ByteArrayOutputStream();
        TripleHandler handler = new RDFXMLWriter(byteArrayOutputStream);
        TripleHandler rdfWriter = new IgnoreAccidentalRDFa(handler);
        ReportingTripleHandler reporting = new ReportingTripleHandler(rdfWriter);

        DocumentSource source = getDocumentSourceFromResource(
                    "/html/rdfa/ansa_2010-02-26_12645863.html",
                    "http://host.com/service");
View Full Code Here
553
554
555
556
557
558
559
560
561
562
563
     */
    private ExtractionReport detectAndExtract(String in) throws Exception {
        Any23 any23 = new Any23();
        ByteArrayOutputStream out = new ByteArrayOutputStream();
        ReportingTripleHandler outputHandler = new ReportingTripleHandler(
                new IgnoreAccidentalRDFa(
                        new IgnoreTitlesOfEmptyDocuments(
                                new NTriplesWriter(out)
                        )
                )
        );
View Full Code Here
324
325
326
327
328
329
330
331
332
333
        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
TOP

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

  • 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.