import org.codelibs.core.lang.StringUtil;

/**
 * The CrawlerContainer interface provides methods for managing components
 * within a crawler container. It includes methods to retrieve components,
 * check availability, and destroy the container. Additionally, it provides
 * a default method to initialize the container with specific protocol handlers.
 *
 */
public interface CrawlerContainer {

    /**
     * Retrieves a component by its name.

     */
    public CrawlerContainer getCrawlerContainer() {
        return crawlerContainer;
    }

    /**
     * Sets the crawler container.
     *
     * @param crawlerContainer The crawler container to set
     */
    public void setCrawlerContainer(final CrawlerContainer crawlerContainer) {
        this.crawlerContainer = crawlerContainer;
    }

    /**

 * Provides common functionality such as access to CrawlerContainer components
 * and registration with the ExtractorFactory.
 *
 * <p>
 * This class handles the retrieval of essential crawler components like
 * {@link MimeTypeHelper} and {@link ExtractorFactory} from the
 * {@link CrawlerContainer}. It also provides a convenient method for
 * registering the extractor with the {@link ExtractorFactory}.

    protected String ruleId;

    /** The response processor. */
    protected ResponseProcessor responseProcessor;

    /** The crawler container. */
    @Resource
    protected transient CrawlerContainer crawlerContainer;

    /**
     * Constructs a new AbstractRule.
     */
    public AbstractRule() {
        // NOP
    }

    /**
     * Registers this rule with the {@link RuleManager}.
     *

 * the parsing of the response body.
 * </p>
 */
public class SitemapsResponseProcessor implements ResponseProcessor {
    /** The crawler container for component lookup. */
    @Resource
    protected CrawlerContainer crawlerContainer;

    /**
     * Creates a new SitemapsResponseProcessor instance.
     */
    public SitemapsResponseProcessor() {
        super();
    }

    /**

    private static final Logger logger = LogManager.getLogger(CrawlerClientCreator.class);

    /** Container for managing crawler components */
    @Resource
    protected CrawlerContainer crawlerContainer;

    /** Map of regular expressions to component names */
    protected Map<String, String> clientMap = new LinkedHashMap<>();

    /** List of registered crawler client factories */

package org.codelibs.fess.crawler.container;

import org.lastaflute.di.core.factory.SingletonLaContainerFactory;

/**
 * LastaFlute implementation of {@link CrawlerContainer}.
 *
 * @author shinsuke
 *
 */
public class LastaCrawlerContainer implements CrawlerContainer {

    /**
     * Creates a new instance of LastaCrawlerContainer.
     */
    public LastaCrawlerContainer() {
        initialize();
    }

        // NOP
    }

    private static final Logger logger = LogManager.getLogger(UrlFilterImpl.class);

    /**
     * The crawler container.
     */
    @Resource
    protected CrawlerContainer crawlerContainer;

    /**
     * The URL pattern.
     */
    protected String urlPattern = "^(.*:/+)([^/]*)(.*)$";

    /**
     * The include filtering pattern.
     */

 * </p>
 *
 * <p>
 * It depends on CrawlerContainer to get ExtractorFactory.
 * </p>
 */
public class TextTransformer extends AbstractTransformer {
    private static final Logger logger = LogManager.getLogger(TextTransformer.class);

    /**
     * The crawler container.
     */
    @Resource
    protected CrawlerContainer crawlerContainer;

    /**
     * The name of the charset.
     */

    private static final Logger logger = LogManager.getLogger(CrawlerClientFactory.class);

    /**
     * The crawler container.
     */
    @Resource
    protected CrawlerContainer crawlerContainer;

    /**
     * A map of regular expression patterns to crawler clients.
     */
    protected Map<Pattern, CrawlerClient> clientMap = new LinkedHashMap<>();

    /**