* It uses an Extractor to extract the text from the response body based on the MIME type.
 * The extracted text is then converted into a byte array using the specified charset encoding.
 * It also provides a method to retrieve the extracted data as a String from an AccessResultData object.
 *
 * <p>

import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.crawler.service.UrlQueueService;

/**
 * Utility class for managing crawling parameters using ThreadLocal variables.
 * This class provides methods to set and get various parameters related to the crawling process.
 *
 * <p>This class is final and cannot be instantiated.</p>
 *

 * It also provides methods to add custom features and properties to the {@link DOMParser}.
 * </p>
 * <p>
 * The encoding of the HTML document is automatically detected using a regular expression that matches the charset attribute in the meta tag.
 * </p>
 *
 */
public class HtmlXpathExtractor extends AbstractXmlExtractor {
    /**

 * to delete all access results for a given session, and to delete all access results.
 * </p>
 *
 * <p>
 * The class is a singleton, and is injected using the {@link Resource} annotation.
 * </p>
 *
 */
public class DataServiceImpl implements DataService<AccessResultImpl<Long>> {

    /** Counter for generating unique IDs */

      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
      PARTICULAR PURPOSE. You are solely responsible for determining the
      appropriateness of using or redistributing the Work and assume any
      risks associated with Your exercise of permissions under this License.

   8. Limitation of Liability. In no event and under no legal theory,

 * It processes the response data based on the HTTP status code and configured transformer.
 * </p>
 *
 * <p>
 * It handles successful responses by transforming the data using a {@link Transformer}
 * and storing the result. It also handles "Not Modified" responses by creating an empty
 * result and storing it. Unsuccessful responses are logged for debugging purposes.
 * </p>
 *
 * <p>

import io.minio.messages.Item;
import io.minio.messages.Tags;
import jakarta.annotation.Resource;

/**
 * A crawler client implementation for accessing and retrieving content from storage systems using MinIO.
 * This client supports operations on object storage systems compatible with S3 protocol.
 *
 * <p>This client requires the following initialization parameters:
 * <ul>

 *
 * <p>Protected Methods:
 * <ul>
 * <li>{@link #createArraySettingsIndexName(String)}: Creates the name for the array settings index.</li>
 * <li>{@link #createId(String, Object)}: Creates a unique ID for a key-value pair using Base64 encoding.</li>
 * <li>{@link #getFromArrayIndex(String, String, String)}: Retrieves an array of maps from the index based on the key.</li>

 *
 * <p>Supported languages are defined in the SUPPORTED_LANGUAGES array.</p>
 *
 * <p>Inner class:</p>
 * <ul>
 *   <li>DefaultContentsAnalyzer: Implements the SuggestAnalyzer interface to analyze text and retrieve tokens using
 *       the configured analyzers.</li>
 * </ul>
 *
 * <p>Protected static class:</p>
 * <ul>
 *   <li>FieldAnalyzerMapping: Holds the analyzer names for different types of analysis (reading, reading term,

            if (port == -1) {
                port = DEFAULT_FTP_PORT;
            }
            return port;
        }

        /**
         * Constructs a complete FTP URL using the host and port from this FtpInfo
         * and the specified path.
         *
         * @param path The path to append to the URL
         * @return The complete FTP URL
         */