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

/**
 * MimeTypeException is a custom exception class that extends CrawlerSystemException.
 * It is used to indicate exceptions related to MIME type handling during the crawling process.
 * This exception can be thrown with a message, a cause, or both.
 */
public class MimeTypeException extends CrawlerSystemException {

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.exception;

/**
 * RobotsTxtException is an exception class that represents an error related to robots.txt processing during web crawling.
 * It extends CrawlerSystemException and provides constructors to create instances with a message and/or a cause.
 *
 */

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

/**
 * Utility class for character-related operations.
 */
public final class CharUtil {
    /**
     * Private constructor to prevent instantiation of this utility class.
     */
    private CharUtil() {
    }

    /**

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

/**
 * MaxLengthExceededException is thrown when the content length exceeds the maximum allowed length.
 * It extends CrawlingAccessException, indicating a crawling-related access issue.
 *
 */
public class MaxLengthExceededException extends CrawlingAccessException {

    private static final long serialVersionUID = 1L;

    /**

import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.FileUtil;

/**
 * A custom InputStream that wraps a temporary file. This class ensures that the temporary file
 * is deleted when the stream is closed.
 */
public class TemporaryFileInputStream extends InputStream {
    private static final Logger logger = LogManager.getLogger(TemporaryFileInputStream.class);

    private final File tempFile;

 * check if a tokenizer is enabled. It also includes methods to create a token
 * stream and extract reading information from the stream's attributes, although
 * the tokenizer-related functionality is currently commented out.
 * </p>
 */
public class KatakanaConverter implements ReadingConverter {

    /** The transliterator for Hiragana-Katakana conversion. */

     *
     * @param client the OpenSearch client to use for the operation
     * @param settings the suggest settings to apply
     * @param index the name of the index from which documents will be deleted
     * @param queryBuilder the query that defines which documents to delete
     * @return a result object containing information about the delete operation
     */

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.xml.sax.Attributes;
import org.xml.sax.InputSource;
import org.xml.sax.helpers.DefaultHandler;

/**
 * Utility class for XML-related operations.
 *
 * This class provides methods to escape special characters in XML strings,
 * strip invalid XML characters, and parse XML content into a map of data.
 *
 * <p>

     * @param settings the settings for the suggest feature, including timeouts and scroll settings
     * @param index the name of the index from which documents should be deleted
     * @param queryBuilder the query used to identify documents to delete
     * @return true if the operation completes successfully
     * @throws SuggesterException if any error occurs during the delete operation
     */

import org.codelibs.fess.suggest.exception.SuggestSettingsException;
import org.opensearch.core.common.Strings;
import org.opensearch.transport.client.Client;

/**
 * The BadWordSettings class manages the settings related to bad words.
 * It allows adding, deleting, and retrieving bad words from the settings.
 * It also supports loading default bad words from a file.
 */
public class BadWordSettings {