* 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;

/**

        return id;
    }

    /*
     * (non-Javadoc)
     *
     * @see org.codelibs.fess.crawler.entity.UrlQueue#setId(IDTYPE)
     */
    @Override
    public void setId(final IDTYPE id) {
        this.id = id;
    }

    /*
     * (non-Javadoc)
     *
     * @see org.codelibs.fess.crawler.entity.UrlQueue#getSessionId()
     */
    @Override
    public String getSessionId() {

import org.codelibs.fess.crawler.entity.Sitemap;
import org.codelibs.fess.crawler.entity.SitemapSet;
import org.codelibs.fess.crawler.exception.ChildUrlsException;
import org.codelibs.fess.crawler.helper.SitemapsHelper;
import org.codelibs.fess.crawler.processor.ResponseProcessor;

import jakarta.annotation.Resource;

/**
 * A response processor implementation that handles sitemaps.

* [LastaFlute](https://github.com/lastaflute/lastaflute "LastaFlute"): Web-Framework
* [Lasta Job](https://github.com/lastaflute/lasta-job "Lasta Job"): Job-Scheduler
* [Fess Crawler](https://github.com/codelibs/fess-crawler "Fess Crawler"): Web-Crawler

    /** Indicates a general exception during crawling. */
    CRAWLING_EXCEPTION,
    /** Indicates no URL is available in the queue. */
    NO_URL_IN_QUEUE,
    /** Indicates the start of a crawler thread. */
    START_THREAD,
    /** Indicates the finish of a crawler thread. */
    FINISHED_THREAD,
    /** Indicates no response processor is available. */
    NO_RESPONSE_PROCESSOR,
    /** Indicates no rule is available for processing. */

     * Please note that the value of this tag is considered a hint and not a
     * command. Even though search engine crawlers may consider this information
     * when making decisions, they may crawl pages marked "hourly" less
     * frequently than that, and they may crawl pages marked "yearly" more
     * frequently than that. Crawlers may periodically crawl pages marked
     * "never" so that they can handle unexpected changes to those pages.
     */

    protected DynamicProperties systemProperties;

    /** Service for managing web crawler configurations */
    @Resource
    protected WebConfigService webConfigService;

    /** Service for managing file crawler configurations */
    @Resource
    protected FileConfigService fileConfigService;

    /** Helper for managing crawler processes */
    @Resource
    protected ProcessHelper processHelper;

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)

     * Document URL patterns to exclude from search index.
     */
    @CustomSize(maxKey = "form.admin.max.input.size")
    public String excludedDocUrls;

    /**
     * Additional configuration parameters for the crawler.
     */
    @CustomSize(maxKey = "form.admin.max.input.size")
    public String configParameter;

    /**
     * The maximum crawling depth from the starting URLs.
     */
    @Min(value = 0)

import org.codelibs.core.io.CopyUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

/**
 * <p>
 * FileTransformer stores the content of a crawled resource as a file on the file system.