extractorMap.put("pdf", new PdfExtractor());
        extractorMap.put("svg", new XmlExtractor());
    }

    /**
     * Initializes the extractor by starting the office manager.
     *
     * @throws CrawlerSystemException if the office manager is null or fails to start
     */
    @PostConstruct
    public void init() {
        if (officeManager == null) {

        this.urlFilter = urlFilter;
    }

    /**
     * Returns the rule manager.
     * @return The RuleManager instance.
     */
    public RuleManager getRuleManager() {
        return ruleManager;
    }

    /**
     * Sets the rule manager.
     * @param ruleManager The RuleManager instance to set.
     */

            client.setMaxRetryCount(5);
            client.setRetryInterval(500);
        }).prototype("fsClient", FileSystemClient.class).prototype("ruleManager", RuleManagerImpl.class, manager -> {
            manager.addRule(container.getComponent("sitemapsRule"));
            manager.addRule(container.getComponent("fileRule"));
        })
                .prototype("accessResult", AccessResultImpl.class)
                .prototype("urlQueue", UrlQueueImpl.class)

 * <p>This class uses various utilities such as ReadingConverter, Normalizer, and SuggestAnalyzer
 * to process and analyze the input data.</p>
 *
 * <p>It also handles the exclusion of search words based on certain criteria and manages the
 * maximum length of analyzed content.</p>
 *
 * <p>Methods in this class may throw SuggesterException in case of failures during the parsing process.</p>
 *
 * <p>Usage example:</p>
 * <pre>
 * {@code

     * Test ruleManager getter and setter
     */
    public void test_ruleManager() {
        assertNull(crawlerContext.getRuleManager());

        TestRuleManager manager = new TestRuleManager();
        crawlerContext.setRuleManager(manager);
        assertSame(manager, crawlerContext.getRuleManager());

        crawlerContext.setRuleManager(null);
        assertNull(crawlerContext.getRuleManager());
    }

    /**

import java.util.List;
import java.util.Map;
import java.util.regex.Pattern;

import org.codelibs.core.lang.StringUtil;

/**
 * Represents a robots.txt file parser and handler.
 * This class manages the rules defined in a robots.txt file, including user agent directives,
 * allowed/disallowed paths, crawl delays, and sitemap URLs.
 *
 * <p>The robots.txt protocol is implemented according to the standard specification,

import org.codelibs.core.lang.MethodUtil;

import jakarta.annotation.PostConstruct;
import jakarta.annotation.PreDestroy;
import jakarta.annotation.Resource;

/**
 * A container implementation that manages the lifecycle and dependency injection of components
 * in a crawler application. This container supports both singleton and prototype component
 * instantiation patterns.
 *
 * <p>The container provides mechanisms for:

            }
        }
    }

    /**
     * Polls the next URL queue entry for the specified session.
     * This method manages local caches and fetches from OpenSearch when needed.
     *
     * @param sessionId The session ID.
     * @return The next URL queue entry, or null if none available.
     */
    @Override

 *       or {@link #storeChildUrl(String, String, float, int)}.</li>
 *   <li>Handling exceptions that may occur during the crawling process.</li>
 * </ol>
 *
 * <p>
 * The thread also manages the active thread count using {@code crawlerContext.activeThreadCountLock}
 * and provides methods for logging messages using {@link LogHelper}.
 * </p>
 *
 * <p>

 *   <li>useEPSVwithIPv4: Whether to use EPSV with IPv4.</li>
 *   <li>isImplicit: Whether to use implicit SSL/TLS encryption.</li>
 *   <li>trustManager: The trust manager to use for SSL/TLS connections ("all", "valid", or "none").</li>
 *   <li>enterLocalPassiveMode: Whether to enter local passive mode.</li>