<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN" 
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<component name="urlQueueService"
		class="org.codelibs.fess.crawler.service.FessUrlQueueService">
		<arg>crawlerConfig</arg>
	</component>

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN" 
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<component name="crawlerConfig" class="org.codelibs.fess.crawler.util.FessCrawlerConfig">
		<property name="queueIndex">"fess_crawler.queue"</property>
		<property name="queueShards">5</property>
		<property name="queueReplicas">1</property>

import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.Crawler;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.OpenSearchAccessResult;
import org.codelibs.fess.crawler.entity.OpenSearchUrlQueue;
import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.crawler.service.UrlFilterService;

        return resultBuf.toString();

    }

    /**
     * Gets the count of currently running crawler jobs.
     * This method queries the scheduled jobs to count active crawler processes.
     * Used to enforce maximum concurrent crawler limits.
     *
     * @return the number of currently running crawler jobs
     */
    protected int getRunningJobCount() {
        final AtomicInteger counter = new AtomicInteger(0);

labels.wizard_button_register_again=Continu aanmaken
labels.wizard_button_register_next=Maken
labels.wizard_start_crawling_title=Start crawlen
labels.wizard_start_crawler_title=Crawler
labels.wizard_start_crawling_desc=U kunt nu beginnen met crawlen door op de knop "Start crawlen" te klikken.
labels.wizard_button_start_crawling=Start crawlen
labels.wizard_button_finish=Overslaan
labels.search_list_configuration=Zoeken
labels.search_list_button_delete=Verwijderen

     * 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;

/**

labels.crawling_info_delete_all_cancel=Anuluj
labels.crawling_info_thread_dump=Zrzut wątków
labels.crawling_info_CrawlerStartTime=Czas rozpoczęcia crawlera
labels.crawling_info_CrawlerEndTime=Czas zakończenia crawlera
labels.crawling_info_CrawlerExecTime=Czas wykonania crawlera
labels.crawling_info_CrawlerStatus=Status crawlera
labels.crawling_info_WebFsCrawlExecTime=Czas wykonania indeksowania (Web/Plik)

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,