* and handling the overall crawling lifecycle.
 *
 * <p>It implements the Runnable interface to be executed in a separate thread,
 * and the AutoCloseable interface to ensure resources are properly released after use.
 *
 * <p>The crawler uses several services and components, such as UrlQueueService, DataService,
 * UrlFilter, RuleManager, CrawlerContainer, IntervalController, and CrawlerClientFactory,
 * to perform its tasks.
 *

        /**
         * The class of the component to instantiate.
         */
        protected Class<T> cls;

        /**
         * The initializer function to be called after component creation.
         */
        protected Consumer<T> initializer;

        /**
         * The container instance.
         */
        protected StandardCrawlerContainer container;

        /**

    }

    @Test
    public void testCreateSuggestTextIdWithLongText() {
        // Test text that exceeds maximum length after encoding
        StringBuilder sb = new StringBuilder();
        for (int i = 0; i < 500; i++) {
            sb.append("0123456789");
        }
        String longText = sb.toString();

        assertEquals(3, ruleManager.getRuleCount());

        // Remove rule
        assertTrue(ruleManager.removeRule(rule2));
        assertEquals(2, ruleManager.getRuleCount());

        // Get rule after removal
        matched = ruleManager.getRule(responseData);
        assertNull(matched); // No matching rule now

        // Add rule4 which matches
        ruleManager.addRule(rule4);

        assertEquals(2, removedSitemaps.length);
        assertEquals("http://example.com/sitemap.xml", removedSitemaps[0]);
        assertEquals("http://test.com/sitemap.xml", removedSitemaps[1]);

        // Should be null after removal
        assertNull(crawlerContext.removeSitemaps());

        // Test with null
        crawlerContext.addSitemaps(null);
        assertNull(crawlerContext.removeSitemaps());

            logger.warn("Could not get urls: (" + xpath + ", " + attr + ")", e);
        }
        return urlList;
    }

    /**
     * Adds a child URL to the URL list after processing and validation.
     *
     * @param urlList the list to add the URL to
     * @param url the base URL for resolving relative URLs
     * @param attrValue the attribute value containing the URL

f[j],fb.test(h.type||"")&&!L.access(h,"globalEval")&&n.contains(i,h)&&(h.src?n._evalUrl&&n._evalUrl(h.src):n.globalEval(h.textContent.replace(hb,"")))}return this}}),n.each({appendTo:"append",prependTo:"prepend",insertBefore:"before",insertAfter:"after",replaceAll:"replaceWith"},function(a,b){n.fn[a]=function(a){for(var c,d=[],e=n(a),g=e.length-1,h=0;g>=h;h++)c=h===g?this:this.clone(!0),n(e[h])[b](c),f.apply(d,c.get());return this.pushStack(d)}});var qb,rb={};function sb(b,c){var d,e=n(c.createE...