import org.codelibs.fess.app.service.FailureUrlService;
import org.codelibs.fess.crawler.CrawlerContext;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.exception.MultipleCrawlingAccessException;
import org.codelibs.fess.crawler.helper.impl.LogHelperImpl;
import org.codelibs.fess.crawler.log.LogType;
import org.codelibs.fess.exception.ContainerNotAvailableException;

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

import java.io.ByteArrayInputStream;
import java.io.InputStream;

import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.Sitemap;
import org.codelibs.fess.crawler.entity.SitemapSet;
import org.codelibs.fess.crawler.entity.SitemapUrl;

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.extractor;

import java.io.InputStream;
import java.util.Map;

import org.codelibs.fess.crawler.entity.ExtractData;

/**
 * The Extractor interface defines methods for extracting text data from an input stream.

        helper.setCrawlerWaitMillis(50);

        // Test when crawler is running
        assertTrue(helper.isCrawlerRunning());
        long start = System.currentTimeMillis();
        helper.checkCrawlerStatus();
        long end = System.currentTimeMillis();
        assertTrue(end - start < 100); // Should return quickly

        // Test when crawler is not running
        helper.setCrawlerRunning(false);

<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />

	<component name="robotsTxtHelper" class="org.codelibs.fess.crawler.helper.RobotsTxtHelper"
		instance="prototype">
	</component>

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

import org.codelibs.fess.util.ComponentUtil;

/**
 * Fess-specific crawler configuration that extends OpenSearchCrawlerConfig.
 * This class provides configuration settings for the Fess crawler including
 * index names, shard counts, and replica counts for queue, data, and filter indices.
 */

	<modelVersion>4.0.0</modelVersion>
	<artifactId>fess-crawler-opensearch</artifactId>
	<packaging>jar</packaging>
	<name>Fess Crawler OpenSearch</name>
	<parent>
		<groupId>org.codelibs.fess</groupId>
		<artifactId>fess-crawler-parent</artifactId>
		<version>15.3.0-SNAPSHOT</version>
		<relativePath>../pom.xml</relativePath>
	</parent>
	<build>
		<plugins>

import org.codelibs.core.lang.ThreadUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.ChildUrlsException;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl;

 */
package org.codelibs.fess.crawler.client.fs;

import java.io.File;
import java.util.Date;
import java.util.Set;

import org.codelibs.core.io.InputStreamUtil;
import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.RequestData;

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 Specifications:
 * <ul>
 * <li><a href=