}

        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();
    }

    /**
     * Default constructor.
     */
    public MailForm() {
        // Default constructor
    }

    /** The incremental crawling setting. */
    public String incrementalCrawling;

    /** The day for cleanup setting. */
    public String dayForCleanup;

    /** The crawling thread count setting. */
    public String crawlingThreadCount;

    /** The search log setting. */
    public String searchLog;

/**
 * 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>

    public void setSessionIdList(final List<String> sessionIdList) {
        this.sessionIdList = sessionIdList;
    }

    /**
     * Sets the flag indicating whether crawling should be finished.
     *
     * @param finishCrawling true if crawling should be finished, false otherwise
     */
    public void setFinishCrawling(final boolean finishCrawling) {
        this.finishCrawling = finishCrawling;
    }

    /**

        }
    }

    /**
     * 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

import org.dbflute.optional.OptionalEntity;

import jakarta.annotation.Resource;

/**
 * Service class for managing failure URLs that occur during web crawling.
 * Provides functionality to store, retrieve, and manage failed crawling attempts
 * with their associated error information.
 */
public class FailureUrlService {

    /** Logger instance for this class */

 * This class extends the base CrawlerThread and provides Fess-specific functionality for
 * crawling and indexing documents, including incremental crawling capabilities, content
 * modification checking, and integration with the Fess search engine backend.
 *
 * <p>Key features include:</p>
 * <ul>
 * <li>Incremental crawling support with last-modified timestamp checking</li>
 * <li>Document expiration handling</li>