true,
            false,
            Pattern.compile("COMMON DEVELOPMENT AND DISTRIBUTION LICENSE.*Version 1.1", Pattern.DOTALL)
        ),
        new LicenseMatcher("ICU", true, false, Pattern.compile("ICU License - ICU 1.8.1 and later", Pattern.DOTALL)),
        new LicenseMatcher(
            "MIT",
            true,
            false,
            Pattern.compile(
                ("\n"

    "com_google_testing_compile",
    "com_google_truth",
    "com_squareup_javapoet",
    "coremltools",
    "cython",
    "fft2d",
    "flatbuffers",
    "gif",
    "hexagon_nn",
    "icu",
    "inception_v1",
    "jpegxl",
    "junit",
    "kissfft",
    "libjpeg_turbo",
    "libwebp",
    "linenoise",
    "mobile_multibox",
    "mobile_ssd",
    "nccl_archive",

  ':modules:percolator',
  ':modules:rank-eval',
  ':modules:reindex',
  ':modules:repository-url',
  ':modules:systemd',
  ':modules:tasks',
  ':modules:transport-netty4',
  ':plugins:analysis-icu',
  ':plugins:analysis-kuromoji',
  ':plugins:analysis-nori',
  ':plugins:analysis-phonetic',
  ':plugins:analysis-smartcn',
  ':plugins:analysis-stempel',
  ':plugins:analysis-ukrainian',

important to a subset of users, especially if it requires extra dependencies.

The canonical example of this is the ICU analysis plugin. It is important for
folks who want the fairly language neutral ICU analyzer but the library to
implement the analyzer is 11MB so we don't ship it with Elasticsearch by
default.

 * 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.
 *

# 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__",

			<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

   * 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