/**
     * The feature for external general entities in XML.
     */
    public static final String FEATURE_EXTERNAL_GENERAL_ENTITIES = "http://xml.org/sax/features/external-general-entities";

    /**
     * Feature for external parameter entities in XML.
     */

    /** Indicates processing a child URL due to an exception. */
    PROCESS_CHILD_URL_BY_EXCEPTION,
    /** Indicates an access exception during crawling. */
    CRAWLING_ACCESS_EXCEPTION,
    /** Indicates a general exception during crawling. */
    CRAWLING_EXCEPTION,
    /** Indicates no URL is available in the queue. */
    NO_URL_IN_QUEUE,
    /** Indicates the start of a crawler thread. */
    START_THREAD,

  </mime-type>

  <mime-type type="application/sereal">
    <_comment>Sereal binary serialization format</_comment>
    <tika:link>https://github.com/Sereal/Sereal/blob/master/sereal_spec.pod</tika:link>
    <glob pattern="*.srl"/>
  </mime-type>
  <mime-type type="application/sereal;version=1">
    <sub-class-of type="application/sereal"/>
    <magic priority="50">

     * both sources differently.
     */
    private String lastmod;

    /**
     * How frequently the page is likely to change. This value provides general
     * information to search engines and may not correlate exactly to how often
     * they crawl the page. Valid values are:
     * <ul>
     * <li>always</li>
     * <li>hourly</li>
     * <li>daily</li>

 *     <li>Handle duplicated file paths by appending a counter.</li>
 *     <li>Store the file path in the result data.</li>
 *     <li>Retrieve the stored file as a File object.</li>
 * </ul>
 *
 * <p>
 * The class uses several configurable properties to customize the file storage behavior,
 * such as the base path, replacement strings for special characters in URLs,

    }

    /**
     * Returns the most specific directive matching the given user agent.
     * The method finds the longest matching user agent pattern in the directives,
     * excluding the general "*" pattern which matches all bots.
     *
     * @param userAgent the user agent string to match against directives,
     *                 can be null (treated as empty string)

 *
 * <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.
 *

 * It uses XPath expressions to extract data from the XML and stores it in a ResultData object.
 * </p>
 *
 * <p>
 * This class provides several configuration options to customize the XML parsing process, such as:
 * </p>
 * <ul>
 *   <li>Namespace awareness</li>
 *   <li>Coalescing</li>
 *   <li>Entity expansion</li>
 *   <li>Ignoring comments and whitespace</li>