*/
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;

/**

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.
 *

        assertFalse(robotsTxt.allows("/aaa", "Crawler"));
        assertTrue(robotsTxt.allows("/bbb", "Crawler"));
        assertTrue(robotsTxt.allows("/ccc", "Crawler"));
        assertTrue(robotsTxt.allows("/ddd", "Crawler"));
        assertTrue(robotsTxt.allows("/aaa", "Crawler/1.0"));
        assertFalse(robotsTxt.allows("/bbb", "Crawler/1.0"));
        assertTrue(robotsTxt.allows("/ccc", "Crawler/1.0"));

import com.google.common.cache.LoadingCache;

import jakarta.annotation.PostConstruct;
import jakarta.annotation.PreDestroy;

/**
 * Helper class for managing crawler statistics and performance metrics.
 * This class provides functionality to track, record, and report statistics
 * about crawler operations including timing data, performance metrics, and
 * operational events. It uses an internal cache to maintain statistics

    /**
     * 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.
     *

 * 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

import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.builder.RequestDataBuilder;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.exception.ChildUrlsException;

/**
 * Form class for crawling configuration wizard in the admin interface.
 * Contains validation constraints for creating new crawling configurations.
 */
public class CrawlingConfigForm {

    /**
     * Creates a new form instance.
     */
    public CrawlingConfigForm() {
        // Default constructor
    }

    /**
     * Name of the crawling configuration.
     */
    @Required

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

/**
 * LogType defines the different types of log messages that can be generated during the crawling process.
 * Each enum constant represents a specific event or state in the crawler's execution.
 */
public enum LogType {
    /** Indicates the start of a crawling process. */
    START_CRAWLING,
    /** Indicates the cleanup phase of crawling. */
    CLEANUP_CRAWLING,

    /** The key of the message: Start Crawling */
    public static final String LABELS_wizard_start_crawling_title = "{labels.wizard_start_crawling_title}";

    /** The key of the message: Crawler */
    public static final String LABELS_wizard_start_crawler_title = "{labels.wizard_start_crawler_title}";

    /** The key of the message: You can start crawling now by clicking "Start Crawling" button. */