import java.util.List;

import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.TokenizerFactory;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.opensearch.core.common.Strings;

import com.ibm.icu.text.Transliterator;

/**
 * {@link KatakanaConverter} converts input strings to katakana representation.
 * It utilizes a transliterator to convert hiragana to katakana and can optionally

 */
package org.codelibs.opensearch.extension.analysis;

import org.apache.lucene.analysis.TokenStream;
import org.codelibs.analysis.en.AlphaNumWordFilter;
import org.opensearch.common.settings.Settings;
import org.opensearch.env.Environment;
import org.opensearch.index.IndexSettings;
import org.opensearch.index.analysis.AbstractTokenFilterFactory;

import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.common.PDNameTreeNode;
import org.apache.pdfbox.pdmodel.common.filespecification.PDComplexFileSpecification;
import org.apache.pdfbox.pdmodel.common.filespecification.PDEmbeddedFile;
import org.apache.pdfbox.pdmodel.common.filespecification.PDFileSpecification;
import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotation;

import org.codelibs.fess.crawler.util.OpenSearchCrawlerConfig;
import org.opensearch.action.DocWriteRequest.OpType;
import org.opensearch.index.query.QueryBuilders;

import com.google.common.cache.CacheBuilder;
import com.google.common.cache.CacheLoader;
import com.google.common.cache.LoadingCache;

import jakarta.annotation.PostConstruct;

/**
 * OpenSearchUrlFilterService is an implementation of {@link UrlFilterService} for OpenSearch.
 */

 */
package org.codelibs.opensearch.extension.analysis;

import org.apache.lucene.analysis.TokenStream;
import org.codelibs.analysis.ja.KanjiNumberFilter;
import org.opensearch.common.settings.Settings;
import org.opensearch.env.Environment;
import org.opensearch.index.IndexSettings;
import org.opensearch.index.analysis.AbstractTokenFilterFactory;

import java.util.Set;

import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.ja.tokenattributes.PartOfSpeechAttribute;
import org.codelibs.analysis.ja.PosConcatenationFilter;
import org.opensearch.common.settings.Settings;
import org.opensearch.env.Environment;
import org.opensearch.index.IndexSettings;
import org.opensearch.index.analysis.AbstractTokenFilterFactory;
import org.opensearch.index.analysis.Analysis;

 * governing permissions and limitations under the License.
 */
package org.codelibs.opensearch.extension.analysis;

import org.apache.lucene.analysis.TokenStream;
import org.opensearch.common.settings.Settings;
import org.opensearch.env.Environment;
import org.opensearch.index.IndexSettings;
import org.opensearch.index.analysis.AbstractTokenFilterFactory;

 */
package org.codelibs.opensearch.extension.analysis;

import java.io.Reader;

import org.codelibs.analysis.ja.ProlongedSoundMarkCharFilter;
import org.opensearch.common.settings.Settings;
import org.opensearch.env.Environment;
import org.opensearch.index.IndexSettings;
import org.opensearch.index.analysis.AbstractCharFilterFactory;

 * governing permissions and limitations under the License.
 */
package org.codelibs.opensearch.extension.analysis;

import org.apache.lucene.analysis.Tokenizer;
import org.opensearch.common.settings.Settings;
import org.opensearch.env.Environment;
import org.opensearch.index.IndexSettings;
import org.opensearch.index.analysis.AbstractTokenizerFactory;

/**
 * Factory for {@link NGramSynonymTokenizer}.

import jakarta.annotation.Resource;

/**
 * Abstract base class for implementing {@link Rule} interfaces.
 * Provides common functionality and properties for crawler rules.
 *
 * <p>
 * This class handles the registration of rules with the {@link RuleManager}
 * and provides getter and setter methods for common properties such as
 * {@code ruleId} and {@code responseProcessor}.
 * </p>
 *
 * <p>