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
     */

        final StringBuilder resultBuf = new StringBuilder();

        // purge crawling sessions
        try {
            crawlingInfoService.deleteBefore(systemHelper.getCurrentTimeAsLong());
        } catch (final Exception e) {
            logger.error("Failed to purge crawling sessions.", e);
            resultBuf.append(e.getMessage()).append("\n");
        }

        // purge search logs

        }

        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.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();
    }

        }
    }

    /**
     * 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.codelibs.fess.util.ComponentUtil;

/**
 * FessIntervalController extends DefaultIntervalController to provide
 * Fess-specific interval control functionality for web crawling operations.
 * This controller manages delays and timing for various crawling states
 * including processing delays, queue waiting times, and new URL discovery.
 */
public class FessIntervalController extends DefaultIntervalController {

    /**

    /**
     * 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;

 * 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>

        ComponentUtil.register(systemHelper, "systemHelper");
        ComponentUtil.setFessConfig(fessConfig);

        // Execute
        String result = purgeLogJob.execute();

        // Assert crawling info and status update were called
        assertTrue(deleteCrawlingInfoCalled[0]);
        assertTrue(updateJobLogStatusCalled[0]);

        // Assert other services were not called

import org.codelibs.fess.app.web.admin.crawlinginfo.EditForm;

/**
 * Request body class for crawling info edit operations in the admin REST API.
 * This class extends EditForm to inherit the necessary form validation and binding capabilities
 * for crawling information management operations.
 */
public class EditBody extends EditForm {

    /**
     * Default constructor.
     */