* It extends the {@link RuntimeException} class and provides constructors
 * to create an exception instance with a message, a cause, or both.
 *
 * <p>Usage examples:</p>
 * <pre>
 * throw new SuggesterException("An error occurred");
 * throw new SuggesterException(new IOException("IO error"));
 * throw new SuggesterException("An error occurred", new IOException("IO error"));
 * </pre>

        Crawler crawler = container.getComponent("crawler");
        
        // Configure crawling parameters
        crawler.addUrl("https://example.com");
        crawler.crawlerContext.setMaxAccessCount(100);
        crawler.crawlerContext.setNumOfThread(5);
        crawler.urlFilter.addInclude("https://example.com/.*");
        
        // Execute crawling
        String sessionId = crawler.execute();

    public void test_statefulTransformer() {
        StatefulTransformer transformer = new StatefulTransformer("statefulTransformer");

        // Process multiple URLs
        String[] urls = { "http://example1.com", "http://example2.com", "http://example3.com" };

        for (String url : urls) {
            ResponseData responseData = new ResponseData();
            responseData.setUrl(url);

    <tika:link>https://www.ietf.org/staging/draft-tuexen-opsawg-pcapng-02.html</tika:link>
    <magic priority="60">
      <match value="0x0A0D0D0A" type="string" offset="0">
        <!-- Could only find examples of the second. I have not tested the first -->
        <match value="0xa1b2c3d4" type="big32" offset="8" />
        <match value="0x4d3c2b1a" type="string" offset="8" />
      </match>
    </magic>

http://www.example.com/
http://www.example.com/catalog?item=12&desc=vacation_hawaii
http://www.example.com/catalog?item=73&desc=vacation_new_zealand
http://www.example.com/catalog?item=74&desc=vacation_newfoundland

sitemap1.xml http://www.example.com/ 2005-01-01 monthly 0.8 http://www.example.com/catalog?item=12&desc=vacation_hawaii weekly http://www.example.com/catalog?item=73&desc=vacation_new_zealand 2004-12-23 weekly http://www.example.com/catalog?item=74&desc=vacation_newfoundland 2004-12-23T18:00:15+00:00 0.3 http://www.example.com/catalog?item=83&desc=vacation_usa 2004-11-23...

        responseData.setUrl("http://example.com/");
        responseData.setMimeType("text/html");
        return responseData;
    }

    private ResponseData getTestData2() {
        final ResponseData responseData = new ResponseData();
        responseData.setHttpStatusCode(200);
        responseData.setUrl("https://example.com/");
        responseData.setMimeType("text/html");

        assertEquals("2005-01-01", sitemaps[0].getLastmod());
        assertEquals("http://www.example.com/", sitemaps[0].getLoc());
        assertEquals("monthly", ((SitemapUrl) sitemaps[0]).getChangefreq());
        assertEquals("0.8", ((SitemapUrl) sitemaps[0]).getPriority());

        assertNull(sitemaps[1].getLastmod());
        assertEquals("http://www.example.com/catalog?item=12&desc=vacation_hawaii", sitemaps[1].getLoc());

<address xmlns:hoge="http://www.example.com/hoge">
        <item sex="male" custid="A12345">
                <name>鈴木太郎</name>
                <access kind="email"></access>
                <access kind="url">http://www.taro.com/</access>
                <image file="taro.png" />
        </item>
        <item sex="male" custid="B23456">
                <name>佐藤二朗</name>
                <access kind="email">******@****.***</access>

        String[] sitemaps = new String[] { "http://example.com/sitemap.xml", "http://test.com/sitemap.xml" };
        crawlerContext.addSitemaps(sitemaps);

        // Remove and verify
        String[] removedSitemaps = crawlerContext.removeSitemaps();
        assertNotNull(removedSitemaps);
        assertEquals(2, removedSitemaps.length);
        assertEquals("http://example.com/sitemap.xml", removedSitemaps[0]);