}

    /**
     * Stores crawling information and parameters for the specified session.
     * Creates a new crawling info record if none exists or if create flag is true.
     * Also stores any accumulated information parameters and clears the info map.
     *
     * @param sessionId the session ID for the crawling information
     * @param create if true, creates a new crawling info regardless of existing records

        
        // Configure crawling parameters
        crawler.addUrl("https://example.com");
        crawler.crawlerContext.setMaxAccessCount(100);
        crawler.crawlerContext.setNumOfThread(5);
        crawler.urlFilter.addInclude("https://example.com/.*");
        
        // Execute crawling
        String sessionId = crawler.execute();
        System.out.println("Crawling completed. Session ID: " + sessionId);
    }
}

            logger.debug("Crawling access exception at url: {}", urlQueue.getUrl(), e);
        } else if (e.isInfoEnabled()) {
            logger.info(e.getMessage());
        } else if (e.isWarnEnabled()) {
            logger.warn("Crawling access exception at url: {}", urlQueue.getUrl(), e);
        } else if (e.isErrorEnabled()) {
            logger.error("Crawling access exception at url: {}", urlQueue.getUrl(), e);

    }

    /**
     * Stores (inserts or updates) a crawling information record.
     * Sets up the store conditions including creation time if not already set,
     * then performs an insert or update operation with immediate refresh.
     *
     * @param crawlingInfo the crawling information entity to store
     * @throws FessSystemException if the crawling information is null
     */

import org.codelibs.fess.crawler.service.UrlQueueService;

import jakarta.annotation.Resource;

/**
 * The Crawler class is the main class for web crawling. It manages the crawling process,
 * including adding URLs to the queue, filtering URLs, managing crawler threads,
 * and handling the overall crawling lifecycle.
 *
 * <p>It implements the Runnable interface to be executed in a separate thread,

                .status(ApiResult.Status.OK)
                .result());
    }

    /**
     * Retrieves a specific crawling info log by ID.
     *
     * @param id the ID of the crawling info log to retrieve
     * @return JSON response containing the crawling info log data
     */
    // GET /api/admin/crawlinginfo/log/{id}
    @Execute
    public JsonResponse<ApiResult> get$log(final String id) {

 * Each enum constant represents a specific event or state in the crawler's execution.
 */
public enum LogType {
    /** Indicates the start of a crawling process. */
    START_CRAWLING,
    /** Indicates the cleanup phase of crawling. */
    CLEANUP_CRAWLING,
    /** Indicates an unsupported URL was encountered when crawling started. */
    UNSUPPORTED_URL_AT_CRAWLING_STARTED,

    @CustomSize(maxKey = "form.admin.max.input.size")
    public String paths;

    /** The paths to include during crawling (pattern-based). */
    @CustomSize(maxKey = "form.admin.max.input.size")
    public String includedPaths;

    /** The paths to exclude during crawling (pattern-based). */
    @CustomSize(maxKey = "form.admin.max.input.size")
    public String excludedPaths;

labels.createdTime=Created Time
labels.depth=Depth
labels.excludedPaths=Excluded Paths for Crawling
labels.excludedUrls=Excluded URLs for Crawling
labels.excludedDocPaths=Excluded Paths for Searching
labels.excludedDocUrls=Excluded URLs for Searching
labels.hostname=Hostname
labels.id=ID
labels.includedPaths=Included Paths for Crawling
labels.includedUrls=Included URLs for Crawling
labels.includedDocPaths=Included Paths for Searching

    /**
     * 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;

    /**
     * Array of web crawling configuration IDs to process.