*/
public class EncodingHelper {

    /** The default encoding to use when no mapping is found */
    protected String defaultEncoding;

    /** Map of encoding names to their preferred forms */
    protected Map<String, String> encodingMap = new HashMap<>();

    /**
     * Constructs a new EncodingHelper.
     */
    public EncodingHelper() {
        // Default constructor
    }

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

/**
 * The RuleManager interface provides methods to manage rules for processing response data.
 * It allows adding, retrieving, and removing rules, as well as checking for their existence.
 */
public interface RuleManager {

    /**
     * Retrieves the rule associated with the given response data.
     *
     * @param responseData the response data for which the rule is to be retrieved

 * {@link CrawlerContainer}. It also provides a convenient method for
 * registering the extractor with the {@link ExtractorFactory}.
 * </p>
 *
 * <p>
 * Subclasses should implement the actual extraction logic in their own
 * methods, leveraging the helper methods provided by this abstract class.
 * </p>
 *
 */
public abstract class AbstractExtractor implements Extractor {

    /** The crawler container. */
    @Resource

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>
 *
 */

public final class XmlUtil {

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

    private XmlUtil() {
    }

    /**
     * Escapes special characters in the given XML string to their corresponding
     * XML entities. This method replaces the following characters:
     * <ul>
     *   <li>&amp; with &amp;amp;</li>
     *   <li>&lt; with &amp;lt;</li>
     *   <li>&gt; with &amp;gt;</li>

    protected String outputEncoding = Constants.UTF_8;

    /** Map of input file extensions to output extensions. */
    private final Map<String, String> extensionMap = new HashMap<>();

    /** Map of output extensions to their corresponding extractors. */
    private final Map<String, Extractor> extractorMap = new HashMap<>();

    /**
     * Constructs a new JodExtractor and initializes the extension and extractor mappings.
     */

/**
 * Helper class for converting URLs based on a set of predefined rules.
 *
 * <p>This class provides functionality to convert URLs by replacing parts of the URL
 * based on a map of target strings and their corresponding replacements. It allows
 * adding new conversion rules, setting the entire conversion map, and converting
 * URLs using these rules.</p>
 *

    protected Map<String, String> propertyMap = new HashMap<>();

    /** XPath expression for extracting content from the document body. */
    protected String contentXpath = "//BODY";

    /** Map of metadata field names to their corresponding XPath expressions. */
    protected Map<String, String> metadataXpathMap = new HashMap<>();

    /** Thread-local instance of XPathAPI for thread-safe XPath evaluation. */

      use, offer to sell, sell, import, and otherwise transfer the Work,
      where such license applies only to those patent claims licensable
      by such Contributor that are necessarily infringed by their
      Contribution(s) alone or by combination of their Contribution(s)
      with the Work to which such Contribution(s) was submitted. If You
      institute patent litigation against any entity (including a

 * the most specific (longest) match is used.</p>
 *
 */
public class RobotsTxt {
    private static final String ALL_BOTS = "*";

    /** Map of user agent patterns to their corresponding directives. */
    protected final Map<Pattern, Directive> directiveMap = new LinkedHashMap<>();

    /** List of sitemap URLs found in the robots.txt file. */