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.

    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}.
     *

 * 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}.

        // Default constructor
    }

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

    /**
     * The name of the component to be retrieved from the CrawlerContainer.
     */
    protected String componentName;

    /**
     * The listener that is called when a pooled object is destroyed.
     */

     *
     * @param crawlerContainer the crawler container
     * @param in the input stream to extract data from
     * @param params the parameters for the extraction process
     */
    protected ExtractorBuilder(final CrawlerContainer crawlerContainer, final InputStream in, final Map<String, String> params) {
        this.crawlerContainer = crawlerContainer;
        this.in = in;
        this.params = params;

 * 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();
    }

    /**

        assertNotNull(deserializedRule.getResponseProcessor());

        // Note: crawlerContainer is transient (marked with @Resource)
        // so it won't be serialized
        assertNull(deserializedRule.crawlerContainer);
    }

    /**
     * Test with null CrawlerContainer
     */
    public void test_nullCrawlerContainer() {

 * </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(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 */

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

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

    /** Transformer used to transform response data */
    protected Transformer transformer;

    /** HTTP status codes considered successful */
    protected int[] successfulHttpCodes;