Package org.apache.any23.cli

Examples of org.apache.any23.cli.ExtractorDocumentation


    @Test
    public void testExtractionParameters() throws IOException, ExtractionException, TripleHandlerException {
        final int EXPECTED_TRIPLES  = 6;
        Any23 runner = new Any23();
        DocumentSource source = getDocumentSourceFromResource(
                "/org/apache/any23/validator/missing-og-namespace.html",
                "http://www.test.com"
        );

        ByteArrayOutputStream baos = new ByteArrayOutputStream();
View Full Code Here


    @Test
    public void testExtractionParametersWithNestingDisabled()
    throws IOException, ExtractionException, TripleHandlerException {
        final int EXPECTED_TRIPLES = 19;
        Any23 runner = new Any23();
        DocumentSource source = getDocumentSourceFromResource(
                "/microformats/nested-microformats-a1.html",
                "http://www.test.com"
        );

        ByteArrayOutputStream baos = new ByteArrayOutputStream();
View Full Code Here

    }

    @Test
    public void testExceptionPropagation() throws IOException {
        Any23 any23 = new Any23();
        DocumentSource source = getDocumentSourceFromResource(
                "/application/turtle/geolinkeddata.ttl",
                "http://www.test.com"
        );
        CountingTripleHandler cth1 = new CountingTripleHandler();
        try {
View Full Code Here

    @Test
    public void testXMLMimeTypeManagement() throws IOException, ExtractionException {
        final String documentURI = "http://www.test.com/resource.xml";
        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());
View Full Code Here

    @Test
    public void testAbstractMethodErrorIssue186_1() throws IOException, ExtractionException{
        final Any23 runner = new Any23();
        final String content = FileUtils.readResourceContent("/html/rdfa/rdfa-issue186-1.xhtml");
        final DocumentSource source = new StringDocumentSource(content, "http://base.com");
        final ByteArrayOutputStream out = new ByteArrayOutputStream();
        final TripleHandler handler = new NTriplesWriter(out);
        runner.extract(source, handler);
        String n3 = out.toString("UTF-8");
        logger.debug(n3);
View Full Code Here

    @Test
    public void testAbstractMethodErrorIssue186_2() throws IOException, ExtractionException{
        final Any23 runner = new Any23();
        final String content = FileUtils.readResourceContent("/html/rdfa/rdfa-issue186-2.xhtml");
        final DocumentSource source = new StringDocumentSource(content, "http://richard.cyganiak.de/");
        final ByteArrayOutputStream out = new ByteArrayOutputStream();
        final TripleHandler handler = new NTriplesWriter(out);
        runner.extract(source, handler);
        final String n3 = out.toString("UTF-8");
        logger.debug(n3);
View Full Code Here

        final ModifiableConfiguration modifiableConf = DefaultConfiguration.copy();
        modifiableConf.setProperty("any23.extraction.metadata.timesize", "off");
        final Any23 any23 = new Any23(modifiableConf);

        final String content = FileUtils.readResourceContent("/rdf/rdf-issue183.ttl");
        final DocumentSource source = new StringDocumentSource(content, "http://base.com");
        final ByteArrayOutputStream out = new ByteArrayOutputStream();
        final TripleHandler handler = new NTriplesWriter(out);
        any23.extract(source, handler);
        handler.close();
        final String n3 = out.toString("UTF-8");
View Full Code Here

     * @param expectedContent
     * @throws Exception
     */
    private void assertEncodingDetection(String encoding, String input, String expectedContent)
    throws Exception {
        DocumentSource fileDocumentSource = getDocumentSourceFromResource(input);
        Any23 any23;
        RepositoryConnection conn;
        RepositoryWriter repositoryWriter;
       
        any23 = new Any23();
View Full Code Here

    private File getFile() {
        return file;
    }

    public DocumentSource getOpener(String baseURI) {
        return new FileDocumentSource(getFile(), baseURI);
    }
View Full Code Here

        assertContains("<http://www.w3.org/1999/02/22-rdf-syntax-ns#type>", response.getContent());
    }

    @Test
    public void testResponseWithReport() throws Exception {
        content = new FileDocumentSource(
                new File("src/test/resources/org/apache/any23/servlet/missing-og-namespace.html")
        ).readStream();
        acceptHeader = "text/plain";
        HttpTester response = doGetRequest("/best/http://foo.com?validation-mode=validate-fix&report=on");
        Assert.assertEquals(200, response.getStatus());
View Full Code Here

TOP

Related Classes of org.apache.any23.cli.ExtractorDocumentation

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.