import org.codelibs.fess.crawler.rule.RuleManager;

/**
 * Implementation of the {@link RuleManager} interface.
 * Manages a list of rules for the crawler.
 * Provides methods to add, remove, check, and retrieve rules.
 *
 */
public class RuleManagerImpl implements RuleManager {

    /** The list of rules managed by this rule manager. */
    protected final List<Rule> ruleList = new ArrayList<>();

    /**

        this.urlFilter = urlFilter;
    }

    /**
     * Returns the rule manager.
     * @return The RuleManager instance.
     */
    public RuleManager getRuleManager() {
        return ruleManager;
    }

    /**
     * Sets the rule manager.
     * @param ruleManager The RuleManager instance to set.
     */

        extractorMap.put("pdf", new PdfExtractor());
        extractorMap.put("svg", new XmlExtractor());
    }

    /**
     * Initializes the extractor by starting the office manager.
     *
     * @throws CrawlerSystemException if the office manager is null or fails to start
     */
    @PostConstruct
    public void init() {
        if (officeManager == null) {

     * Test ruleManager getter and setter
     */
    public void test_ruleManager() {
        assertNull(crawlerContext.getRuleManager());

        TestRuleManager manager = new TestRuleManager();
        crawlerContext.setRuleManager(manager);
        assertSame(manager, crawlerContext.getRuleManager());

        crawlerContext.setRuleManager(null);
        assertNull(crawlerContext.getRuleManager());
    }

    /**

        this.urlFilter = urlFilter;
    }

    /**
     * Returns the rule manager.
     * @return The RuleManager.
     */
    public RuleManager getRuleManager() {
        return ruleManager;
    }

    /**
     * Sets the rule manager.
     * @param ruleManager The RuleManager.
     */
    public void setRuleManager(final RuleManager ruleManager) {

     * @return the rule associated with the given response data
     */
    Rule getRule(ResponseData responseData);

    /**
     * Adds a new rule to the rule manager.
     *
     * @param rule the rule to be added
     */
    void addRule(Rule rule);

    /**
     * Adds a rule to the specified index.
     *

import org.codelibs.core.lang.MethodUtil;

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

/**
 * A container implementation that manages the lifecycle and dependency injection of components
 * in a crawler application. This container supports both singleton and prototype component
 * instantiation patterns.
 *
 * <p>The container provides mechanisms for:

import jakarta.annotation.Resource;

/**
 * Creates and manages crawler clients for web crawling operations.
 * This class handles the registration and loading of crawler client factories and their associated clients.
 * <p>
 * The class maintains a mapping between regular expressions and component names, and manages a list
 * of crawler client factories with a configurable maximum size.
 * </p>
 *
 */

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

import org.codelibs.core.lang.StringUtil;

/**
 * Represents a robots.txt file parser and handler.
 * This class manages the rules defined in a robots.txt file, including user agent directives,
 * allowed/disallowed paths, crawl delays, and sitemap URLs.
 *
 * <p>The robots.txt protocol is implemented according to the standard specification,

 * <p>This class uses various utilities such as ReadingConverter, Normalizer, and SuggestAnalyzer
 * to process and analyze the input data.</p>
 *
 * <p>It also handles the exclusion of search words based on certain criteria and manages the
 * maximum length of analyzed content.</p>
 *
 * <p>Methods in this class may throw SuggesterException in case of failures during the parsing process.</p>
 *
 * <p>Usage example:</p>
 * <pre>
 * {@code