urlFilter.init(sessionId);

        // Without any patterns, all URLs should match
        assertTrue(urlFilter.match("https://example.com/"));
        assertTrue(urlFilter.match("https://test.com/page"));
        assertTrue(urlFilter.match("ftp://files.com/document.pdf"));
        assertTrue(urlFilter.match("file:///home/user/file.txt"));
    }

    /**
     * Test match with complex URL patterns
     */

            final String content = data.getContent();
            logger.info(content);
            assertTrue(content.contains("Exkursion und Museumsbesuch"));
            assertTrue(content.contains("Fahrt nach Baruth"));
            assertTrue(content.contains("Technische Universität"));
        }
    }

    public void test_getText_null() {
        try {

        assertTrue(extractorFactory.getExtractor(key) instanceof TikaExtractor);

        // key = "application/vnd.ms-publisher";
        // assertTrue(extractorFactory.getExtractor(key) instanceof
        // TikaExtractor);

        key = "application/pdf";
        assertTrue(extractorFactory.getExtractor(key) instanceof PdfExtractor);

        key = "application/x-lha";

        assertTrue(auth.matches("ftp://hostname:21/test/aaa.html"));
        assertTrue(auth.matches("ftp://hostname/test/aaa.html"));
        assertTrue(auth.matches("ftp://hostname:21/test"));
        assertTrue(auth.matches("ftp://hostname/test"));
        assertTrue(auth.matches("ftp://hostname:21"));
        assertTrue(auth.matches("ftp://hostname"));
        assertTrue(auth.matches("ftp://hostname:21/"));

        // INITIALIZING < RUNNING < DONE (based on ordinal)
        assertTrue(CrawlerStatus.INITIALIZING.compareTo(CrawlerStatus.RUNNING) < 0);
        assertTrue(CrawlerStatus.INITIALIZING.compareTo(CrawlerStatus.DONE) < 0);
        assertTrue(CrawlerStatus.RUNNING.compareTo(CrawlerStatus.DONE) < 0);

        // Reverse comparisons
        assertTrue(CrawlerStatus.RUNNING.compareTo(CrawlerStatus.INITIALIZING) > 0);

        regexRule.addRule("url", Pattern.compile("http:.*"));
        regexRule.addRule("mimeType", Pattern.compile("text/html"));

        assertTrue(regexRule.match(getTestData1()));
        assertTrue(regexRule.match(getTestData2()));
        assertTrue(regexRule.match(getTestData3()));
        assertTrue(regexRule.match(getTestData4()));
    }

    public void test_match_url() {
        final RegexRule regexRule = new RegexRule();

        assert (analyzerNames.size() > 4);
        assertTrue(analyzerNames.contains(settings.analyzer().getContentsAnalyzerName("", "")));
        assertTrue(analyzerNames.contains(settings.analyzer().getContentsReadingAnalyzerName("", "")));
        assertTrue(analyzerNames.contains(settings.analyzer().getReadingAnalyzerName("", "")));
        assertTrue(analyzerNames.contains(settings.analyzer().getReadingTermAnalyzerName("", "")));

import static org.junit.Assert.assertTrue;

import org.junit.Test;

public class SuggestRequestTest {
    @Test
    public void test_isHiraganaQuery() throws Exception {
        SuggestRequest request = new SuggestRequest();
        assertTrue(request.isHiraganaQuery("あ"));
        assertTrue(request.isHiraganaQuery("あおぞら"));
        assertTrue(request.isHiraganaQuery("けんさく"));

            assertTrue(robotsTxt.allows("/aaa", userAgent));
            assertTrue(robotsTxt.allows("/private/", userAgent));
            assertTrue(robotsTxt.allows("/private/index.html", userAgent));
            assertTrue(robotsTxt.allows("/help/", userAgent));
            assertTrue(robotsTxt.allows("/help.html", userAgent));
            assertTrue(robotsTxt.allows("/help/faq.html", userAgent));

        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("本文1"));
        assertTrue(content.contains("本文2"));
        assertTrue(content.contains("画像1"));
        assertTrue(content.contains("画像2"));
        assertTrue(content.contains("タイトル1"));
        assertTrue(content.contains("タイトル2"));
        assertTrue(content.contains("リンク1"));
    }

    public void test_getHtml_empty() {