import org.codelibs.core.timer.TimeoutTask;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.client.AccessTimeoutTarget;
import org.codelibs.fess.crawler.client.http.Authentication;
import org.codelibs.fess.crawler.client.http.RequestHeader;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.ExtractException;

import com.google.common.base.Charsets;

import org.codelibs.fess.crawler.client.CrawlerClientFactory;
import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.exception.ChildUrlsException;

import java.util.regex.Pattern;

import org.apache.commons.io.input.BOMInputStream;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.RobotsTxt;
import org.codelibs.fess.crawler.entity.RobotsTxt.Directive;
import org.codelibs.fess.crawler.exception.RobotsTxtException;

/**
 * Robots.txt Parser following RFC 9309 specification.
 *

import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.builder.RequestDataBuilder;
import org.codelibs.fess.crawler.client.AbstractCrawlerClient;
import org.codelibs.fess.crawler.client.AccessTimeoutTarget;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.ChildUrlsException;

* [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

labels.crawling_info_CrawlerStartTime=Crawler-Startzeit
labels.crawling_info_CrawlerEndTime=Crawler-Endzeit
labels.crawling_info_CrawlerExecTime=Crawler-Ausführungszeit
labels.crawling_info_CrawlerStatus=Crawler-Status
labels.crawling_info_WebFsCrawlExecTime=Crawl-Ausführungszeit (Web/Datei)
labels.crawling_info_WebFsCrawlStartTime=Crawl-Startzeit (Web/Datei)
labels.crawling_info_WebFsCrawlEndTime=Crawl-Endzeit (Web/Datei)

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

import static org.mockito.Mockito.times;
import static org.mockito.Mockito.verify;
import static org.mockito.Mockito.when;

import java.util.ArrayList;
import java.util.List;
import java.util.regex.Pattern;

import org.codelibs.fess.crawler.helper.MemoryDataHelper;
import org.dbflute.utflute.core.PlainTestCase;

labels.crawling_info_CrawlerStartTime=Crawler Start Time
labels.crawling_info_CrawlerEndTime=Crawler End Time
labels.crawling_info_CrawlerExecTime=Crawler Execution Time
labels.crawling_info_CrawlerStatus=Crawler Status
labels.crawling_info_WebFsCrawlExecTime=Crawl Execution Time (Web/File)
labels.crawling_info_WebFsCrawlStartTime=Crawl Start Time (Web/File)
labels.crawling_info_WebFsCrawlEndTime=Crawl End Time (Web/File)

    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;

    /** The document paths to exclude from search results (pattern-based). */
    @CustomSize(maxKey = "form.admin.max.input.size")
    public String excludedDocPaths;

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

    /** The maximum crawling depth (0 to 2147483647, 0 means unlimited). */
    @Min(value = 0)
    @Max(value = 2147483647)