private int currentPageNumber;

    /**
     * Crawling information ID.
     */
    public String id;

    /**
     * Session ID for the crawling session.
     */
    public String sessionId;

    /**
     * Creation time of the crawling information.
     */
    public String createdTime;

    /**
     * Clears all pagination state and crawling information fields.

    }

    /**
     * Adds a document to the search index by crawling the specified URL and processing the content.
     * This method handles recursive crawling with depth and access count limits, follows redirects,
     * and processes child URLs discovered during crawling.
     *
     * @param paramMap the data store parameters containing crawling configuration

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

    /**
     * URL patterns to include during crawling.
     */
    @CustomSize(maxKey = "form.admin.max.input.size")
    public String includedUrls;

    /**
     * URL patterns to exclude during crawling.
     */
    @CustomSize(maxKey = "form.admin.max.input.size")
    public String excludedUrls;

    /**

        return ComponentUtil.getIngestFactory();
    }

    /**
     * Processes a result data object for web/file crawling.
     * Default implementation returns the target unchanged.
     *
     * @param target the result data to process
     * @param responseData the response data from crawling
     * @return the processed result data
     */

        }

        if (cae.isDebugEnabled()) {
            logger.debug("[{}] Crawling Access Exception at {}", failureUrlId, urlQueue.getUrl(), cae);
        } else if (cae.isInfoEnabled()) {
            logger.info("[{}] {}", failureUrlId, cae.getMessage());
        } else if (cae.isWarnEnabled()) {
            logger.warn("[{}] Crawling Access Exception at {}", failureUrlId, urlQueue.getUrl(), cae);

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

/**
 * Utility class for managing crawling parameters using ThreadLocal variables.
 * This class provides methods to set and get various parameters related to the crawling process.
 *
 * <p>This class is final and cannot be instantiated.</p>
 *
 * <p>The following parameters are managed:</p>
 * <ul>

import org.codelibs.fess.app.web.api.admin.BaseSearchBody;

/**
 * Search request body for file crawling configuration administration API.
 */
public class SearchBody extends BaseSearchBody {

    /**
     * Default constructor.
     */
    public SearchBody() {
        super();
    }

    /** Name of the file crawling configuration */
    public String name;

    /** File paths to crawl */
    public String paths;

import org.lastaflute.web.response.HtmlResponse;
import org.lastaflute.web.response.render.RenderData;
import org.lastaflute.web.ruts.process.ActionRuntime;

import jakarta.annotation.Resource;

/**
 * Admin action for Crawling Info management.
 *
 */
public class AdminCrawlinginfoAction extends FessAdminAction {

    /**
     * Default constructor.
     */
    public AdminCrawlinginfoAction() {
        super();
    }

/**
 * Parser for Google Search Appliance (GSA) configuration files.
 * This SAX-based parser reads GSA XML configuration files and converts them into
 * Fess configuration objects including web crawling configurations, file crawling
 * configurations, and label types for access control.
 *
 * <p>The parser handles the following GSA configuration elements:
 * <ul>
 * <li>Collections with good/bad URL patterns</li>

        }
    }

    /**
     * Processes a crawling request for a specific URL.
     * Executes the full crawling pipeline including client execution, rule processing,
     * transformation, and data extraction.
     *
     * @param crawlingConfig the crawling configuration to use
     * @param crawlingInfoId the crawling session ID
     * @param url the URL to process