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

---
name: Bug report
about: A reproducible problem
title: ''
labels: bug
assignees: ''

---

Good bug reports include a failing test! Writing a test helps you to isolate and describe the problem, and it helps us to fix it fast. Bug reports without a failing test or reproduction steps are likely to be closed.

Here’s an example test to get you started.

        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

 */
package org.codelibs.fess.app.web.admin.crawlinginfo;

/**
 * The search form for Crawling Info.
 */
public class SearchForm {

    /**
     * Default constructor for SearchForm.
     */
    public SearchForm() {
    }

    /**
     * The session ID field for searching crawling information.
     */
    public String sessionId;

        }

        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();
    }

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 */

  ----------

  Home Page:          https://maven.apache.org
  Downloads:          https://maven.apache.org/download.html
  Release Notes:      https://maven.apache.org/docs/history.html
  Mailing Lists:      https://maven.apache.org/mailing-lists.html
  Source Code:        https://gitbox.apache.org/repos/asf/maven.git
  Issue Tracking:     https://issues.apache.org/jira/browse/MNG

        }
    }

    /**
     * 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