Examples of org.apache.any23.writer.ReportingTripleHandler

org.apache.any23.writer.ReportingTripleHandler
A {@link TripleHandler} that collectsvarious information about the extraction process, such as the extractors used and the total number of triples. @author Richard Cyganiak (richard@cyganiak.de)

        outputMediaType = WriterRegistry.getMimeType( fw.getClass() );
        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

            }
        });
        ByteArrayOutputStream byteArrayOutputStream = new ByteArrayOutputStream();
        TripleHandler handler = new RDFXMLWriter(byteArrayOutputStream);
        TripleHandler rdfWriter = new IgnoreAccidentalRDFa(handler);
        ReportingTripleHandler reporting = new ReportingTripleHandler(rdfWriter);


        DocumentSource source = new FileDocumentSource(
                new File("src/test/resources/html/rdfa/ansa_2010-02-26_12645863.html"),
                    "http://host.com/service");

View Full Code Here

        final String contentType = "application/xml";
        final String in = StreamUtils.asString( this.getClass().getResourceAsStream("any23-xml-mimetype.xml") );
        final DocumentSource doc = new StringDocumentSource(in, documentURI, contentType);
        final Any23 any23 = new Any23();
        final CountingTripleHandler cth = new CountingTripleHandler(false);
        final ReportingTripleHandler rth = new ReportingTripleHandler(cth);
        final ExtractionReport report = any23.extract(doc, rth);
        Assert.assertFalse(report.hasMatchingExtractors());
        Assert.assertEquals(0, cth.getCount());
    }

View Full Code Here

    public void testXMLMimeTypeManagementViaURL() throws IOException, ExtractionException {
        assumeOnlineAllowed();
        final Any23 any23 = new Any23();
        any23.setHTTPUserAgent("test-user-agent");
        final CountingTripleHandler cth = new CountingTripleHandler(false);
        final ReportingTripleHandler rth = new ReportingTripleHandler(cth);
        final ExtractionReport report = any23.extract("http://www.nativeremedies.com/XML/combos.xml", rth);
        Assert.assertFalse(report.hasMatchingExtractors());
        Assert.assertEquals(0, cth.getCount());
    }

View Full Code Here

            }
        });
        ByteArrayOutputStream byteArrayOutputStream = new ByteArrayOutputStream();
        TripleHandler handler = new NTriplesWriter(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

                .getResourceAsStream("any23-xml-mimetype.xml"));
        final DocumentSource doc = new StringDocumentSource(in, documentURI,
                contentType);
        final Any23 any23 = new Any23();
        final CountingTripleHandler cth = new CountingTripleHandler(false);
        final ReportingTripleHandler rth = new ReportingTripleHandler(cth);
        final ExtractionReport report = any23.extract(doc, rth);
        Assert.assertFalse(report.hasMatchingExtractors());
        Assert.assertEquals(0, cth.getCount());
    }

View Full Code Here

            ExtractionException {
        assumeOnlineAllowed();
        final Any23 any23 = new Any23();
        any23.setHTTPUserAgent("test-user-agent");
        final CountingTripleHandler cth = new CountingTripleHandler(false);
        final ReportingTripleHandler rth = new ReportingTripleHandler(cth);
        final ExtractionReport report = any23.extract(
                "http://www.nativeremedies.com/XML/combos.xml", rth);
        Assert.assertFalse(report.hasMatchingExtractors());
        Assert.assertEquals(0, cth.getCount());
    }

View Full Code Here

    public void testBlankNodesViaURL() throws IOException, ExtractionException {
        assumeOnlineAllowed();
        final Any23 any23 = new Any23();
        any23.setHTTPUserAgent("test-user-agent");
        final CountingTripleHandler cth = new CountingTripleHandler(false);
        final ReportingTripleHandler rth = new ReportingTripleHandler(cth);
        final ExtractionReport report = any23.extract(
                "http://www.usarab.org/news/?tag=england", rth);
        Assert.assertTrue(report.hasMatchingExtractors());
    }

View Full Code Here

     * @throws ExtractionException
     */
    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))));
        return any23.extract(in, "http://host.com/path", outputHandler);
    }

View Full Code Here

            tripleHandler = new IgnoreAccidentalRDFa(new IgnoreTitlesOfEmptyDocuments(tripleHandler),
                                                     true    // suppress stylesheet triples.
                                                     );
        }


        reportingTripleHandler = new ReportingTripleHandler(tripleHandler);


        final Configuration configuration = DefaultConfiguration.singleton();
        extractionParameters =
                pedantic
                        ?

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

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

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

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.