<components namespace="fessCrawler">
	<include path="crawler/container.xml"/>
	<include path="crawler/client.xml"/>
	<include path="crawler/rule.xml"/>
	<include path="crawler/filter.xml"/>
	<include path="crawler/interval.xml"/>
	<include path="crawler/extractor.xml"/>
	<include path="crawler/mimetype.xml"/>
	<include path="crawler/encoding.xml"/>
	<include path="crawler/urlconverter.xml"/>
	<include path="crawler/log.xml"/>

/*
 [Crawler Notification]
 Crawler notification mail.
*/
subject: [FESS] Crawler completed: /*pmb.hostname*/
>>>
--- Server Info ---
Host Name: /*pmb.hostname:orElse('Unknown')*/
Job Name: /*pmb.jobname:orElse('Unknown')*/

--- Web/FileSystem Crawler ---
Start Time: /*pmb.webFsCrawlStartTime:orElse('-')*/
End Time:   /*pmb.webFsCrawlEndTime:orElse('-')*/
Exec Time:  /*pmb.webFsCrawlExecTime:orElse('-')*/ ms

--- Web/FileSystem Indexer ---

            crawler1.getCrawlerContext().setMaxAccessCount(maxCount);
            crawler1.getCrawlerContext().setNumOfThread(numOfThread);

            final Crawler crawler2 = getComponent(Crawler.class);
            crawler2.setBackground(true);
            ((UrlFilterImpl) crawler2.urlFilter).setIncludeFilteringPattern("$1$2$3.*");
            crawler2.addUrl(url2);
            crawler2.getCrawlerContext().setMaxAccessCount(maxCount);

     * Datetime format.
     *
     * By providing the last modification timestamp, you enable search engine
     * crawlers to retrieve only a subset of the Sitemaps in the index i.e. a
     * crawler may only retrieve Sitemaps that were modified since a certain
     * date. This incremental Sitemap fetching mechanism allows for the rapid
     * discovery of new URLs on very large sites.

 */
package org.codelibs.fess.crawler.processor;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.processor.impl.DefaultResponseProcessor;

 */
package org.codelibs.fess.crawler;

import java.util.Set;
import java.util.concurrent.atomic.AtomicLong;

import org.codelibs.core.collection.LruHashSet;
import org.codelibs.fess.crawler.filter.UrlFilter;
import org.codelibs.fess.crawler.interval.IntervalController;
import org.codelibs.fess.crawler.rule.RuleManager;

/**

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.exception;

/**
 * Exception thrown during the extraction process in the crawler.
 * This exception indicates a failure or error that occurred while extracting content from a crawled resource.
 * It extends {@link org.codelibs.fess.crawler.exception.CrawlerSystemException} and provides constructors

    /**
     * Add an url pattern as a target.
     *
     * @param urlPattern Regular expression that is crawled
     */
    void addInclude(String urlPattern);

    /**
     * Add an url pattern as a non-target.
     *
     * @param urlPattern Regular expression that is not crawled
     */
    void addExclude(String urlPattern);

    /**
     * Process an url when it's added as a seed url.
     *

import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.entity.UrlQueueImpl;
import org.codelibs.fess.crawler.helper.MemoryDataHelper;
import org.codelibs.fess.crawler.service.UrlQueueService;

import jakarta.annotation.Resource;

/**
 * Implementation of the {@link UrlQueueService} interface.
 * This class provides methods for managing a queue of URLs to be crawled,

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.util;

import org.codelibs.fess.crawler.CrawlerContext;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.crawler.service.UrlQueueService;

/**