/** Array of fields that can be used for faceted search */
    protected String[] facetFields;

    /** Set of fields that can be used for faceted search for O(1) lookup */
    protected Set<String> facetFieldSet;

    /** Array of fields that can be used for sorting search results */
    protected String[] sortFields;

    /** Set of fields that can be used for sorting for O(1) lookup */

    /**
     * LDAP base DN (Distinguished Name) for user searches.
     * Defines the root of the LDAP directory tree for user lookups.
     */
    @Size(max = 1000)
    public String ldapBaseDn;

    /**
     * LDAP filter for finding user accounts.
     * Defines the search filter used to locate user accounts in LDAP.
     */
    @Size(max = 1000)
    public String ldapAccountFilter;

    /**

 * </p>
 * <ul>
 *   <li>ftpConfigSystemKey: The system key used to configure the FTPClientConfig.</li>
 *   <li>ftpConfigServerLanguageCode: The language code used by the FTP server.</li>
 *   <li>ftpConfigServerTimeZoneId: The time zone ID of the FTP server.</li>
 *   <li>activeExternalHost: The external IP address to use for active mode FTP.</li>
 *   <li>activeMinPort: The minimum port number for active mode FTP.</li>

     * a clean title suitable for indexing.
     *
     * @param responseData the response data from crawling (not currently used)
     * @param title the raw title text to process
     * @param dataMap additional data map (not currently used)
     * @return the normalized title, or empty string if title is null
     */

    /**
     * Prefix used to identify regex patterns in related content terms.
     * When a term starts with this prefix, it is treated as a regular expression
     * pattern rather than an exact match term.
     */
    protected String regexPrefix = "regex:";

    /**
     * Placeholder string used in regex-based related content templates.

    }

    /**
     * Checks if the given URL is a file path protocol that requires directory and permission handling.
     * Used for incremental crawling directory detection and file permission processing.
     *
     * @param url the URL to check
     * @return true if the URL uses a file path protocol (smb, smb1, file, ftp, s3, gcs)
     */
    public boolean isFilePathProtocol(final String url) {

     */
    private int httpStatusCode;

    /**
     * The content cache that stores the response content.
     */
    private ContentCache contentCache;

    /**
     * The encoding used for the response content.
     */
    private String encoding;

    /**
     * The exception that occurred while accessing the content, if any.
     */
    private Exception contentException;

    /**

 *   <li>Manages crawl delay settings per user agent</li>
 *   <li>Stores sitemap URLs listed in robots.txt</li>
 * </ul>
 *
 * <p>The class uses case-insensitive pattern matching for user agents and supports
 * wildcard characters (*) in user agent strings. When multiple directives match a user agent,
 * the most specific (longest) match is used.</p>
 *
 */
public class RobotsTxt {

    /**
     * Retrieves web crawling configurations with various filtering options.
     *
     * @param withLabelType whether to include label type information (currently not used in implementation)
     * @param withRoleType whether to include role type information (currently not used in implementation)
     * @param available whether to filter only available configurations

import org.codelibs.fess.dict.DictionaryItem;

import jakarta.annotation.PostConstruct;

/**
 * Creator for character mapping dictionary files.
 * Handles the creation and management of character mapping dictionaries used for text normalization.
 */
public class CharMappingCreator extends DictionaryCreator {
    private static final Logger logger = LogManager.getLogger(CharMappingCreator.class);

    /**