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

import com.ibm.icu.text.Transliterator;

/**
 * ICUNormalizer is a class that implements the Normalizer interface and provides
 * functionality to normalize text using ICU4J's Transliterator.
 *

			<releases>
				<enabled>false</enabled>
			</releases>
			<snapshots>
				<enabled>true</enabled>
			</snapshots>
		</repository>
	</repositories>
	<dependencies>
		<dependency>
			<groupId>com.ibm.icu</groupId>
			<artifactId>icu4j</artifactId>
			<version>${icu4j.version}</version>
		</dependency>
		<dependency>
			<groupId>org.codelibs</groupId>
			<artifactId>corelib</artifactId>

 */
package org.codelibs.fess.suggest.converter;

import java.io.IOException;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

import com.ibm.icu.text.Transliterator;

/**
 * Converts Katakana characters to their corresponding Alphabet representations.
 *
 * <p>
 * This class implements the {@link ReadingConverter} interface and provides a method to convert a given

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

import org.opensearch.action.admin.indices.analyze.AnalyzeAction.AnalyzeToken;
import org.opensearch.core.common.Strings;
import org.opensearch.transport.client.Client;

import com.ibm.icu.text.Transliterator;

/**
 * AnalyzerConverter is a class that implements the ReadingConverter interface.
 * It is responsible for converting text using specified language analyzers.

import org.opensearch.monitor.os.OsProbe;

import com.google.common.cache.CacheBuilder;
import com.google.common.cache.CacheLoader;
import com.google.common.cache.LoadingCache;
import com.ibm.icu.util.ULocale;

import jakarta.annotation.PostConstruct;
import jakarta.annotation.PreDestroy;

/**
 * Helper class for system-level operations and utilities.

# copybara:comment_end

PACKAGE_STATIC_DEPS = [
    "//:__subpackages__",
    "@gif//:__subpackages__",
    "@highwayhash//:__subpackages__",
    "@hwloc//:__subpackages__",
    "@icu//:__subpackages__",
    "@libjpeg_turbo//:__subpackages__",
    "@llvm-project//:__subpackages__",
    "@png//:__subpackages__",
    "@sobol_data//:__subpackages__",
    "@stablehlo//:__subpackages__",

import com.github.jknack.handlebars.Template;
import com.github.jknack.handlebars.io.FileTemplateLoader;
import com.google.common.cache.Cache;
import com.google.common.cache.CacheBuilder;
import com.ibm.icu.text.SimpleDateFormat;

import jakarta.annotation.PostConstruct;
import jakarta.servlet.ServletContext;
import jakarta.servlet.SessionTrackingMode;
import jakarta.servlet.http.HttpServletRequest;

		<dependency>
			<groupId>org.apache.commons</groupId>
			<artifactId>commons-lang3</artifactId>
			<version>${commons.lang3.version}</version>
		</dependency>
		<dependency>
			<groupId>com.ibm.icu</groupId>
			<artifactId>icu4j</artifactId>
			<version>${icu4j.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.tika</groupId>
			<artifactId>tika-langdetect-optimaize</artifactId>

   * SPACE_SEPARATOR, LINE_SEPARATOR, PARAGRAPH_SEPARATOR, CONTROL, FORMAT, SURROGATE, and
   * PRIVATE_USE according to ICU4J.
   *
   * <p>See also the Unicode Default_Ignorable_Code_Point property (available via ICU).
   *
   * @deprecated Most invisible characters are supplementary characters; see the class
   *     documentation.
   * @since 19.0 (since 1.0 as constant {@code INVISIBLE})
   */
  @Deprecated