/** Prefix used to identify role-based permissions */
    protected String rolePrefix = "{role}";

    /** Prefix used to identify group-based permissions */
    protected String groupPrefix = "{group}";

    /** Prefix used to identify user-based permissions */
    protected String userPrefix = "{user}";

    /** Prefix used to identify allow permissions */
    protected String allowPrefix = "(allow)";

    }

    /**
     * Sets the 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.
     *
     * @param regexPrefix the prefix string to identify regex patterns (default: "regex:")
     */
    public void setRegexPrefix(final String regexPrefix) {

public class CrawlJob extends ExecJob {

    private static final Logger logger = LogManager.getLogger(CrawlJob.class);

    /**
     * The namespace identifier for the crawling session.
     * Used to organize and identify crawling activities in the system.
     * Defaults to the system crawling info name.
     */
    protected String namespace = Constants.CRAWLING_INFO_SYSTEM_NAME;

    /**

organization-specific certificate authority.

By default `HeldCertificate` instances expire after 24 hours. Use `duration()` to adjust.

By default server certificates need to identify which hostnames they're trusted for. You may add as
many as necessary with `addSubjectAlternativeName()`. This mechanism also supports a very limited

/**
 * Represents a tag configuration for pruning HTML content during document processing.
 * This class defines tag patterns that match HTML elements based on tag name, CSS class, ID, or custom attributes.
 * It is used to identify and remove unwanted HTML elements from crawled documents.
 */
public class PrunedTag {
    /** The HTML tag name to match (e.g., "div", "span", "p") */
    private final String tag;
    /** The ID attribute value to match */

     * Returns the pattern used to extract encoding information from content.
     * @return The encoding pattern.
     */
    protected abstract Pattern getEncodingPattern();

    /**
     * Returns the pattern used to identify tags in the content.
     * @return The tag pattern.
     */
    protected abstract Pattern getTagPattern();

    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {

        this.commandDestroyTimeout = commandDestroyTimeout;
    }

    /**
     * Gets file extension from MIME type for creating temp files with proper extensions.
     * This helps ImageMagick correctly identify file formats.
     * @param mimeType The MIME type of the content.
     * @return The file extension including the dot (e.g., ".gif"), or empty string if unknown.
     */

     * @param settings the settings for the suggest feature, including timeouts and scroll settings
     * @param index the name of the index from which documents should be deleted
     * @param queryBuilder the query used to identify documents to delete
     * @return true if the operation completes successfully
     * @throws SuggesterException if any error occurs during the delete operation
     */

 *   <li><b>preloadSizeForCharset:</b> The number of bytes to read from the input
 *       stream to determine the character set encoding.</li>
 *   <li><b>invalidUrlPattern:</b> A regular expression pattern used to identify
 *       invalid URLs.</li>
 * </ul>
 *
 * <p>
 * <b>Usage:</b>
 * </p>
 * <p>
 * The {@code transform} method is the main entry point for transforming an HTML

            return name + ":" + version;
        }
    }

    /**
     * Enumeration of different artifact types supported by Fess.
     * Each type has a specific ID prefix used to identify artifacts of that type.
     */
    public enum ArtifactType {
        /** Data store plugins */
        DATA_STORE("fess-ds"), //
        /** Theme plugins */
        THEME("fess-theme"), //