*/
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;

    /**

 * 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. */

import java.util.List;

import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.util.AccessResultCallback;

/**
 * Interface for data service operations related to access results.
 *
 * @param <RESULT> the type of access result
 */
public interface DataService<RESULT extends AccessResult<?>> {

    /**
     * Stores the given access result.
     *

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>

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 {

        assertTrue(Arrays.asList(result).contains(SuggestItem.Kind.DOCUMENT));
    }

    @Test
    public void testEmptySource() {
        // Test setEmptySource and related methods
        String[] text = { "test" };
        String[][] readings = { { "test" } };
        SuggestItem item = new SuggestItem(text, readings, null, 0L, 0L, 1.0f, null, null, null, SuggestItem.Kind.QUERY);

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>
 *
 * <p>The following parameters are managed:</p>
 * <ul>
 *   <li>{@link UrlQueue} - The queue of URLs to be crawled.</li>