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

        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

        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
     */

        }
    }

    /**
     * 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

        }

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

 */
public class SearchBody extends BaseSearchBody {

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

    /** The URL that failed during crawling */
    public String url;

    /** Minimum error count filter */
    public Integer errorCountMin;

    /** Maximum error count filter */
    public Integer errorCountMax;

    /** Property key for incremental crawling configuration. */
    public static final String INCREMENTAL_CRAWLING_PROPERTY = "crawling.incremental";

    /** Property key for crawling thread count configuration. */
    public static final String CRAWLING_THREAD_COUNT_PROPERTY = "crawling.thread.count";

    /** Property key for crawling user agent configuration. */

 * 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>

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 */

 */
package org.codelibs.fess.exception;

/**
 * Exception thrown when requested content cannot be found.
 * Typically used when a document or resource is not available during crawling or indexing.
 */
public class ContentNotFoundException extends FessSystemException {

    private static final long serialVersionUID = 1L;

    /**