*/
    public IdnDnsResolver() {
        super();
    }

    /**
     * Resolves the given host name to an array of IP addresses.
     * The host name is first converted to ASCII using IDN before resolution.
     *
     * @param host the host name to resolve
     * @return an array of IP addresses for the host
     * @throws UnknownHostException if the host name cannot be resolved
     */

     * @param obj The object to wrap
     * @return A PooledObject wrapping the given object
     */
    @Override
    public PooledObject<T> wrap(final T obj) {
        return new DefaultPooledObject<>(obj);
    }

    /**
     * Destroys a pooled object and notifies the destroy listener if set.
     * @param p The pooled object to destroy
     * @throws Exception if destruction fails
     */

 */
package org.codelibs.fess.crawler.entity;

/**
 * The UrlQueue interface represents a queue of URLs to be processed by a web crawler.
 * It provides methods to get and set various properties of a URL queue entry.
 *
 * @param <IDTYPE> the type of the identifier for the URL queue entry
 */
public interface UrlQueue<IDTYPE> {

    /**
     * Retrieves the unique identifier of the URL queue.
     *

        } catch (final Exception e) {
            throw new CrawlerSystemException("Failed to create XPath instance.", e);
        }
    }

    /**
     *  Use an XPath string to select a nodelist.
     *  XPath namespace prefixes are resolved from the contextNode.
     *
     *  @param contextNode The node to start searching from.
     *  @param expression A valid XPath string.

 * and adds them as child URLs to be crawled.
 *
 * <p>
 * This class uses a {@link SitemapsHelper} to parse the sitemap XML or text.
 * It then iterates through the sitemaps in the SitemapSet, extracts the URL
 * from each sitemap, and creates a new {@link RequestData} object for each URL.
 * These RequestData objects are added to a set of child URLs, which are then

    }

    /**
     * A path to store downloaded files. The default path is a current
     * directory.
     */
    protected String path;

    /**
     * A string to replace ?.
     */
    protected String questionStr = "_QUEST_";

    /**
     * A string to replace :.
     */
    protected String colonStr = "_CLN_";

    /**
     * A string to replace ;.
     */

import io.minio.errors.XmlParserException;

/**
 * Handler for the "storage" protocol, allowing access to objects stored in a MinIO-compatible storage service.
 * This handler extends {@link URLStreamHandler} to provide a way to open connections to storage objects
 * using URLs with the "storage" protocol.
 *
 * <p>
 * The URL format is expected to be: {@code storage://bucketName/objectName}.
 * The bucket name and object name are extracted from the URL.

 * possible readings.
 * </p>
 *
 * <p>
 * The class also utilizes ICU4J's {@link com.ibm.icu.text.Transliterator} to convert full-width characters
 * to half-width and to convert any characters to lowercase, ensuring consistency in the output.
 * </p>
 *
 * <p>
 * Example:
 * For the input "キャ", the converter might return a list containing "kya".

import org.codelibs.fess.crawler.processor.ResponseProcessor;

/**
 * The Rule interface defines the contract for implementing rules that can be applied to
 * response data in a web crawler. Implementations of this interface should provide logic
 * to determine if a given response data matches the rule, retrieve the rule's identifier,
 * and obtain the associated response processor.
 */
public interface Rule extends Serializable {

 * </p>
 * <ul>
 *   <li><b>featureMap:</b> A map of features to be set on the DOM parser.</li>
 *   <li><b>propertyMap:</b> A map of properties to be set on the DOM parser.</li>
 *   <li><b>childUrlRuleMap:</b> A map of HTML tag names to attribute names, used
 *       to extract child URLs.</li>
 *   <li><b>defaultEncoding:</b> The default character encoding to use if none is
 *       specified in the HTML content.</li>