/**
     * Extracts a list of TermQuery objects from the given Query object that match the specified fields.
     *
     * @param query the Query object to extract TermQuery objects from
     * @param fields an array of field names to match against the TermQuery objects
     * @return a list of TermQuery objects that match the specified fields, or an empty list if no matches are found
     */

 *
 */
public class HtmlXpathExtractor extends AbstractXmlExtractor {
    /**
     * Regular expression pattern to match the charset attribute in the meta tag of HTML documents.
     * The pattern captures the charset value specified in the content attribute of the meta tag.
     * Example: <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
     */

 *   <li>Extracting child URLs from the HTML content based on configured rules.</li>
 *   <li>Handling redirect URLs specified in the response headers.</li>
 * </ol>
 * <p>
 * The class also provides methods for configuring features and properties of the
 * underlying DOM parser, as well as defining rules for extracting child URLs
 * from specific HTML tags and attributes.
 * </p>
 *
 * <p>
 * <b>Configuration:</b>
 * </p>
 * <ul>

    /**
     * Constructs a new ExtractException with the specified detail message.
     *
     * @param message the detail message. The detail message is saved for later retrieval by the {@link #getMessage()} method.
     */
    public ExtractException(final String message) {
        super(message);
    }

    /**
     * Constructs a new ExtractException with the specified cause.
     *

        super(message, cause);
    }

    /**
     * Constructs a new exception with the specified detail message.
     *
     * @param message the detail message.
     */
    public ExecutionTimeoutException(final String message) {
        super(message);
    }

    /**
     * Constructs a new exception with the specified cause.
     *

    /**
     * Constructs a new SitemapsException with the specified detail message and cause.
     * @param message the detail message
     * @param cause the cause of the exception
     */
    public SitemapsException(final String message, final Throwable cause) {
        super(message, cause);
    }

    /**
     * Constructs a new SitemapsException with the specified detail message.
     * @param message the detail message
     */

    /**
     * Constructs a new SuggestIndexException with the specified detail message.
     * @param msg The detail message.
     */
    public SuggestIndexException(final String msg) {
        super(msg);
    }

    /**
     * Constructs a new SuggestIndexException with the specified cause.
     * @param cause The cause.
     */
    public SuggestIndexException(final Throwable cause) {

 * 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>
 * The class handles character encoding issues by attempting to use the specified charset.
 * If the specified charset is invalid, it falls back to UTF-8.
 * </p>
 *
 * <p>

                                .collect(Collectors.toList());
                    }
                });
    }

    /**
     * Adds an include URL filter for the specified session.
     *
     * @param sessionId The session ID.
     * @param url The URL pattern to include.
     */
    @Override
    public void addIncludeUrlFilter(final String sessionId, final String url) {

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.helper;

import org.codelibs.fess.crawler.log.LogType;

/**
 * Interface for logging helper.
 * Provides a method to log messages with a specified log type and additional objects.
 */
public interface LogHelper {

    /**