Examples of org.apache.any23.extractor.ExampleInputOutput

org.apache.any23.extractor.ExtractionResultImpl
A reporter for example input and output of an extractor. Example input is part of every extractor's metadata; example output is obtained by running the extractor on its own example input. This is useful as a documentation device. @author Richard Cyganiak (richard@cyganiak.de)

        );
    }
    
    private ExtractionParameters getExtractionParameters(HttpServletRequest request) {
        final ValidationMode mode = getValidationMode(request);
        return new ExtractionParameters(DefaultConfiguration.singleton(), mode);
    }

View Full Code Here

        final String FILE = "test2-workbook.xls";
        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);

View Full Code Here

        CompositeTripleHandler compositeTH1 = new CompositeTripleHandler();
        compositeTH1.addChild(cth1);
        compositeTH1.addChild(ctw1);
        try {
            runner.extract(
                    new ExtractionParameters(
                            DefaultConfiguration.singleton(),
                            ValidationMode.None
                    ),
                    source,
                    compositeTH1
            );
        } finally {
            compositeTH1.close();
        }
        logger.info(baos.toString());
        Assert.assertEquals("Unexpected number of triples.", EXPECTED_TRIPLES, cth1.getCount() );


        baos.reset();
        CountingTripleHandler cth2 = new CountingTripleHandler();
        NTriplesWriter ctw2 = new NTriplesWriter(baos);
        CompositeTripleHandler compositeTH2 = new CompositeTripleHandler();
        compositeTH2.addChild(cth2);
        compositeTH2.addChild(ctw2);
        runner.extract(
                new ExtractionParameters(
                        DefaultConfiguration.singleton(),
                        ValidationMode.ValidateAndFix
                ),
                source,
                compositeTH2

View Full Code Here

        RDFXMLWriter ctw1 = new RDFXMLWriter(baos);
        CompositeTripleHandler compositeTH1 = new CompositeTripleHandler();
        compositeTH1.addChild(cth1);
        compositeTH1.addChild(ctw1);
        runner.extract(
                new ExtractionParameters(
                        DefaultConfiguration.singleton(),
                        ValidationMode.None, true
                ),
                source,
                compositeTH1
        );
        compositeTH1.close();
        logger.debug("Out1: " + baos.toString());
        Assert.assertEquals("Unexpected number of triples.", EXPECTED_TRIPLES + 3, cth1.getCount() );


        baos.reset();
        CountingTripleHandler cth2 = new CountingTripleHandler();
        NTriplesWriter ctw2 = new NTriplesWriter(baos);
        CompositeTripleHandler compositeTH2 = new CompositeTripleHandler();
        compositeTH2.addChild(cth2);
        compositeTH2.addChild(ctw2);
        runner.extract(
                new ExtractionParameters(
                        DefaultConfiguration.singleton(),
                        ValidationMode.ValidateAndFix, false),
                source,
                compositeTH2
        );

View Full Code Here

                String.format("Invalid value '%s' for '%s' parameter.", validationMode, PARAMETER)
        );
    }
    
    private ExtractionParameters getExtractionParameters(HttpServletRequest request) {
        final ValidationMode mode = getValidationMode(request);
        return new ExtractionParameters(DefaultConfiguration.singleton(), mode);
    }

View Full Code Here

    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(),
                    extractionContext,
                    this.getClass().getResourceAsStream("/org/apache/any23/extractor/rdf/testMalformedLiteral"),
                    result
            );
        } finally {
            logger.debug(baos.toString());
            th.close();
            result.close();
        }
    }

View Full Code Here

    }


    @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
        );

View Full Code Here

        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

    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(),
                    extractionContext,
                    this.getClass().getResourceAsStream("/org/apache/any23/extractor/rdf/testMalformedLiteral"),
                    result
            );
        } finally {
            logger.debug(baos.toString());
            th.close();
            result.close();
        }
    }

View Full Code Here

        );
        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

0 1 2 3 4 5 6 7 8 9

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

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.