*
 * <p>
 * It provides methods to set and retrieve the server address, port, username,
 * password, and domain. Additionally, it offers a method to construct a path
 * prefix for SMB URLs based on the configured server and port.
 * </p>
 *
 * <p>
 * The path prefix is in the format "smb://server:port/", where the port is
 * included only if it's greater than 0. If the server is not set, the path

        public QueueHolder() {
            // Default constructor
        }

        /**
         * The queue for URLs waiting to be crawled.
         */
        protected Queue<OpenSearchUrlQueue> waitingQueue = new ConcurrentLinkedQueue<>();

        /**
         * The queue for URLs currently being crawled.
         */
        protected Queue<OpenSearchUrlQueue> crawlingQueue = new ConcurrentLinkedQueue<>();
    }

/**
 * Utility class for text normalization and processing.
 *
 * This class provides methods to normalize text by reading characters from a provided Reader
 * and processing them according to specific rules. The main functionality is encapsulated
 * within the nested {@link TextNormalizeContext} class.
 *
 * <p>The text normalization process includes:
 * <ul>

     */
    public void removeChildUrl(final RequestData url) {
        childUrlSet.remove(url);
    }

    /**
     * Gets the set of child URLs discovered from this response.
     *
     * @return the set of child URLs
     */
    public Set<RequestData> getChildUrlSet() {
        return childUrlSet;
    }

    /**

import java.util.List;

import org.codelibs.fess.crawler.entity.UrlQueue;

/**
 * Service interface for managing URL queues.
 * Provides methods for adding, retrieving, and managing URLs within a crawling session.
 *
 * @param <QUEUE> the type of URL queue
 */
public interface UrlQueueService<QUEUE extends UrlQueue<?>> {

    /**
     * Updates the session ID.
     *

 *   <li>Coalescing</li>
 *   <li>Entity expansion</li>
 *   <li>Ignoring comments and whitespace</li>
 *   <li>Validation</li>
 *   <li>XInclude awareness</li>
 * </ul>
 *
 * <p>
 * It also allows defining field rules using XPath expressions to extract specific data from the XML document and map it to fields in the ResultData.
 * The extracted data is then formatted into an XML structure suitable for indexing.
 * </p>
 *
 * <p>

 *   <li>writeTimeout - Write timeout in milliseconds (default: 10000)</li>
 *   <li>readTimeout - Read timeout in milliseconds (default: 10000)</li>
 * </ul>
 *
 * <p>The client supports URLs in the format: {@code storage://bucket-name/object-path}
 *
 * <p>Features:
 * <ul>
 *   <li>Automatic initialization of MinIO client</li>
 *   <li>Support for HEAD and GET operations</li>

 * It extends CrawlerSystemException and provides functionality to set and check the log level for the exception.
 *
 * <p>
 * This exception can be thrown when there are problems accessing URLs, files, or any other resources needed for crawling.
 * It includes constructors to handle messages, causes, or both.
 * </p>
 *
 * <p>

    /** Map of session IDs to include URL patterns for filtering URLs. */
    protected volatile Map<String, List<Pattern>> includeUrlPatternMap = new HashMap<>();

    /** Map of session IDs to exclude URL patterns for filtering URLs. */
    protected volatile Map<String, List<Pattern>> excludeUrlPatternMap = new HashMap<>();

    /**

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.entity;

/**
 * The UrlQueue interface represents a queue of URLs to be processed by a web crawler.
 * It provides methods to get and set various properties of a URL queue entry.
 *
 * @param <IDTYPE> the type of the identifier for the URL queue entry
 */
public interface UrlQueue<IDTYPE> {