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

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

/**
 * The RuleManager interface provides methods to manage rules for processing response data.
 * It allows adding, retrieving, and removing rules, as well as checking for their existence.
 */
public interface RuleManager {

    /**

package org.codelibs.fess.crawler.interval.impl;

import java.util.Map;

import org.codelibs.core.lang.ThreadUtil;

/**
 * Default implementation of the IntervalController.
 * This class provides a default way to manage delays between crawler operations.
 * It allows setting delays before processing, after processing, when no URLs are in the queue,
 * and when waiting for new URLs.
 * The delays are configurable via constructor parameters.
 *

/**
 * Helper class for managing content length limits based on MIME types.
 * It allows setting default and MIME type-specific maximum content lengths.
 * The class provides methods to add, retrieve, and manage these limits.
 */
public class ContentLengthHelper {
    /**
     * Constructs a new ContentLengthHelper.
     */
    public ContentLengthHelper() {
        // Default constructor
    }

 *
 * <p>This class provides methods to initialize settings, get and set individual settings,
 * and manage various types of settings such as array settings, analyzer settings, bad word settings,
 * and elevate word settings.</p>
 *
 * <p>It also includes a nested TimeoutSettings class to manage various timeout configurations.</p>
 *
 * <p>Usage example:</p>
 * <pre>
 * {@code
 * Client client = ...;

 * including adding include and exclude URL patterns, deleting patterns,
 * and retrieving lists of compiled URL patterns. It utilizes a
 * {@link MemoryDataHelper} to store and manage the URL patterns in memory.
 *
 */
public class UrlFilterServiceImpl implements UrlFilterService {

    /**
     * Creates a new UrlFilterServiceImpl instance.
     */
    public UrlFilterServiceImpl() {

import com.fasterxml.jackson.databind.ObjectMapper;

/**
 * PasswordBasedExtractor is an abstract base class for extractors that can handle password-protected files.
 * It provides functionality to manage passwords for different file patterns using regular expressions.
 *
 * <p>The extractor supports two types of password management:
 * <ul>
 *   <li>Static passwords configured via {@link #addPassword(String, String)}</li>

import org.dbflute.optional.OptionalEntity;

import jakarta.annotation.Resource;

/**
 * Service class for managing failure URLs that occur during web crawling.
 * Provides functionality to store, retrieve, and manage failed crawling attempts
 * with their associated error information.
 */
public class FailureUrlService {

    /** Logger instance for this class */

import jakarta.annotation.Resource;

/**
 * Factory class for managing and retrieving {@link Extractor} instances.
 * This class provides methods to add, retrieve, and manage extractors based on a key.
 * It also includes a builder for creating extractors.
 *
 * <p>
 * The factory maintains a map of keys to an array of {@link Extractor} objects.

 *       Initializes the ElevateWordSettings with the provided settings, client, index name, and settings ID.</li>
 * </ul>
 *
 * <p>Dependencies:</p>
 * <ul>
 *   <li>{@code ArraySettings} - Used to manage the array settings for elevate words.</li>
 *   <li>{@code SuggestSettings} - The suggestion settings.</li>
 *   <li>{@code Client} - The client used for accessing the settings.</li>
 * </ul>
 *
 * <p>Logging:</p>
 * <ul>

 * modify the internal data structures. The internal maps are also declared as {@code volatile}
 * to ensure visibility of changes across threads.
 *
 * <p>The class also provides methods to manage URL patterns for inclusion and exclusion, which
 * are stored as {@code Pattern} objects.
 */
public class MemoryDataHelper {
    /** Map of session IDs to URL queues for managing crawling queues. */