//                                                                           Attribute
    //

    /**
     * The helper for related content.
     */
    @Resource
    protected RelatedContentHelper relatedContentHelper;

    /**
     * The helper for related queries.
     */
    @Resource
    protected RelatedQueryHelper relatedQueryHelper;

        }
        return new DefaultQueryBuilder(boolQuery);
    }

    /**
     * Builds a match phrase query, with special handling for single CJK characters.
     * For single CJK characters in title or content fields, uses prefix query instead.
     * @param f The field name.
     * @param text The text to search for.
     * @return The appropriate query builder.
     */

            }
        }
        return null;
    }

    /**
     * Logs script execution to the audit log.
     *
     * @param script the script content that was executed
     * @param result the execution result (e.g., "success" or "failure:ExceptionType")
     */
    protected void logScriptExecution(final String script, final String result) {

    }

    private ApiAdminSchedulerAction createActionWithMockService(final ScheduledJob scheduledJob) throws Exception {
        final ApiAdminSchedulerAction action = new ApiAdminSchedulerAction();

        // Inject mock ScheduledJobService via reflection
        final ScheduledJobService mockService = new ScheduledJobService() {
            @Override
            public OptionalEntity<ScheduledJob> getScheduledJob(final String id) {

        /** Indicates that a general exception occurred during processing. */
        EXCEPTION,
        /** Indicates that processing of a URL has finished. */
        FINISHED,
        /** Indicates that content was successfully parsed. */
        PARSED,
        /** Indicates that a URL was prepared for crawling. */
        PREPARED,
        /** Indicates that a URL redirect was encountered. */
        REDIRECTED,

                || url.startsWith("s3:") || url.startsWith("gcs:");
    }

    /**
     * Checks if the given URL represents a file system path for content serving.
     * Used to determine if special handling is needed for file system URLs.
     *
     * @param url the URL to check
     * @return true if the URL is a file system path (file, smb, smb1, ftp, storage, s3, gcs)

        br.addElement("");
        br.addElement("While, you can override the boundary limit size");
        br.addElement(" in " + getClass().getSimpleName() + ".");
        br.addItem("Content Type");
        br.addElement(contentType);
        br.addItem("Boundary Size");
        br.addElement(boundarySize);
        br.addItem("Limit Size");
        br.addElement(limitSize);

            @Override
            public String getIndexFieldTitle() {
                return "title";
            }

            @Override
            public String getIndexFieldContent() {
                return "content";
            }

            @Override
            public String getIndexFieldId() {
                return "_id";
            }

            @Override
            public String getIndexFieldDocId() {

 * This class serves as the entry point for crawling web content, file systems, and data stores.
 * It manages the crawling lifecycle, including initialization, execution coordination,
 * monitoring, and cleanup operations.
 *
 * <p>The crawler can operate in different modes based on command-line options:
 * <ul>
 * <li>Web crawling - crawls web sites and web content</li>
 * <li>File system crawling - crawls file systems and documents</li>

    }

    /**
     * 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.
     */
    protected String getExtensionFromMimeType(final String mimeType) {
        if (mimeType == null) {