while (!crawlerRunning) {
            ThreadUtil.sleepQuietly(crawlerWaitMillis);
        }
    }

    /**
     * Applies delay based on the configured interval rules.
     * This method calculates the appropriate delay for the current time
     * and applies it by sleeping the current thread.
     */
    public void delayByRules() {
        final long delay = getDelay();
        if (delay > 0) {

 * This class handles URL conversion based on duplicate host rules, allowing multiple
 * hostnames or URLs to be treated as equivalent for crawling and indexing purposes.
 * It maintains a list of DuplicateHost rules and applies them to URLs.
 *
 */
public class DuplicateHostHelper {
    private static final Logger logger = LogManager.getLogger(DuplicateHostHelper.class);

    /** List of duplicate host rules for URL conversion */

 * and processes them to create thumbnail images based on configured dimensions
 * and format settings.
 *
 * <p>The generator validates image MIME types, processes image data through
 * ImageIO operations, and applies scaling and cropping to generate thumbnails
 * that meet the specified size requirements.</p>
 *
 */
public class HtmlTagBasedGenerator extends BaseThumbnailGenerator {

 *
 * <p>The updater performs the following key operations:
 * <ul>
 * <li>Retrieves crawled documents from the data service</li>
 * <li>Transforms document data using appropriate transformers</li>
 * <li>Applies document boosting rules and click/favorite count enhancements</li>
 * <li>Sends processed documents to the search engine for indexing</li>
 * <li>Manages cleanup of processed crawler session data</li>
 * </ul>
 *

import org.lastaflute.core.message.UserMessages;
import org.opensearch.index.query.QueryBuilder;

/**
 * Query command implementation for handling Boost queries.
 * Processes Lucene BoostQuery objects and applies boost factors.
 */
public class BoostQueryCommand extends QueryCommand {
    /**
     * Default constructor for BoostQueryCommand.
     */
    public BoostQueryCommand() {
        super();
    }

            }
        } catch (final Exception e) {
            logger.warn("Failed to initialize TikaExtractor.", e);
        }
    }

    /**
     * Processes and normalizes a document title.
     * Applies text normalization using configured space characters and returns
     * a clean title suitable for indexing.
     *
     * @param responseData the response data from crawling (not currently used)

     * A directive consists of a user agent, crawl delay, allowed paths, and disallowed paths.
     */
    public static class Directive {
        /** The user agent string this directive applies to. */
        private final String userAgent;

        /** The crawl delay in seconds for this directive. */
        private int crawlDelay;

        /** The list of allowed path patterns for this directive. */

)
if NOT "%FESS_PROXY_PORT%" == "" (
set FESS_JAVA_OPTS=%FESS_JAVA_OPTS% -Dhttp.proxyPort=%FESS_PROXY_PORT%
set FESS_JAVA_OPTS=%FESS_JAVA_OPTS% -Dhttps.proxyPort=%FESS_PROXY_PORT%
)
REM http.nonProxyHosts applies to both HTTP and HTTPS connections.
REM There is no https.nonProxyHosts property in Java.
if NOT "%FESS_NON_PROXY_HOSTS%" == "" (
set FESS_JAVA_OPTS=%FESS_JAVA_OPTS% -Dhttp.nonProxyHosts=%FESS_NON_PROXY_HOSTS%
)

        if (logger.isDebugEnabled()) {
            logger.debug("Total documents added: {}", documentSize.get());
        }

    }

    /**
     * Processes a document through the ingest pipeline.
     * Applies all available ingesters to transform the document data.
     *
     * @param paramMap the data store parameters
     * @param dataMap the document data to process
     * @return the processed document data
     */

        }

        return url;
    }

    /**
     * Extracts and processes the site path from a URL with proper encoding handling.
     * Removes protocol, query parameters, and applies URL decoding based on encoding settings.
     *
     * @param u the URL string to process
     * @param encoding the character encoding to use for URL decoding
     * @return the processed site path, abbreviated if necessary