*/
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
    }

 */
package org.codelibs.fess.suggest.index.contents.document;

import java.io.Closeable;
import java.util.Map;

/**
 * Interface for reading documents and extracting their contents into a map.
 * Implementations of this interface should provide the logic for reading
 * documents and converting them into a key-value structure.
 *

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

import com.ibm.icu.text.Transliterator;

/**
 * Converts Katakana characters to their corresponding Alphabet representations.
 *
 * <p>
 * This class implements the {@link ReadingConverter} interface and provides a method to convert a given
 * Katakana string into a list of possible Alphabet readings. It uses a predefined mapping of Katakana
 * characters to their Alphabet equivalents, handling both single and double Katakana character combinations.

/**
 * 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>
 *

 * {@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.
     */

 * </p>
 *
 * <p>
 * The reader supports limiting the number of documents read based on a percentage of the total documents
 * or a fixed number. It also allows filtering documents based on their size, using the {@code limitOfDocumentSize}
 * parameter.
 * </p>
 *
 * <p>
 * The reader uses a queue to buffer documents read from Elasticsearch, and it retries failed requests
 * up to a maximum number of times.