// 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);
    }
}

 * <ul>
 * <li>Web crawling - crawls web sites and web content</li>
 * <li>File system crawling - crawls file systems and documents</li>
 * <li>Data store crawling - crawls databases and other data sources</li>
 * <li>Combined crawling - runs multiple crawling types simultaneously</li>
 * </ul>
 *
 * <p>Command line usage:
 * <pre>
 * java org.codelibs.fess.exec.Crawler [options...]

    }

    /**
     * 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
     */

        if (e.isDebugEnabled()) {
            logger.debug("Crawling Access Exception at {}", urlQueue.getUrl(), e);
        } else if (e.isInfoEnabled()) {
            logger.info(e.getMessage());
        } else if (e.isWarnEnabled()) {
            logger.warn("Crawling Access Exception at " + urlQueue.getUrl(), e);
        } else if (e.isErrorEnabled()) {
            logger.error("Crawling Access Exception at " + urlQueue.getUrl(), e);
        }

import com.google.common.cache.Cache;
import com.google.common.cache.CacheBuilder;

import jakarta.annotation.PostConstruct;

/**
 * Helper class for managing crawling configurations.
 * Provides functionality to store, retrieve, and manage different types of crawling configurations
 * including web, file, and data configurations. Supports caching and session-based configuration management.
 */
public class CrawlingConfigHelper {

/**
 * Helper class for managing data crawling operations in Fess.
 * This class coordinates the execution of data store crawling processes,
 * managing multiple concurrent crawling threads and handling the indexing
 * of crawled documents into the search engine.
 *
 * <p>The DataIndexHelper supports:</p>
 * <ul>
 *   <li>Concurrent crawling of multiple data configurations</li>

    @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

                .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,