static {
        setup(defaultCtype);
    }

    /**
     * Creates a {@link Tokenizer}.
     *
     * @param str
     *            The string. Must not be {@literal null}.
     */
    public Tokenizer(final String str) {
        this(str, defaultCtype);
    }

    /**
     * Creates a {@link Tokenizer}.
     *
     * @param str
     *            The string. Must not be {@literal null}.

            if (handler == null) {
                final String path = System.getProperty(HANDLER_PKGS_PROPERTY);
                final StringTokenizer tokenizer = new StringTokenizer(path, "|");
                while (tokenizer.hasMoreTokens()) {
                    final String provider = tokenizer.nextToken().trim();
                    if (provider.equals("jcifs.smb1")) {
                        continue;
                    }

    public void testEOF() throws Exception {
        final Tokenizer tokenizer = new Tokenizer("");
        assertThat(tokenizer.nextToken(), is(Tokenizer.TT_EOF));
        assertThat(tokenizer.nextToken(), is(Tokenizer.TT_EOF));
    }

    /**
     * @throws Exception
     */
    @Test
    public void testWhitespace() throws Exception {
        final Tokenizer tokenizer = new Tokenizer("\t       \n");

import java.io.IOException;
import java.io.StringReader;
import java.util.HashSet;
import java.util.List;
import java.util.Set;

import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.ja.JapaneseTokenizer;
import org.apache.lucene.analysis.ja.JapaneseTokenizer.Mode;
import org.apache.lucene.analysis.ja.dict.UserDictionary;
import org.apache.lucene.analysis.util.CSVUtil;

 * use a tokenizer to process the input.
 *
 * <p>
 * The class provides methods to initialize the converter, convert strings, and
 * 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>
 */

      "number_of_shards": 1,
      "number_of_replicas": 0,
      "auto_expand_replicas": "0-1"
    },
    "analysis": {
      "analyzer": {
        "standard_analyzer": {
          "type": "custom",
          "tokenizer": "standard",
          "filter": [
            "cjk_width",
            "asciifolding",
            "lowercase",
            "stop",
            "stemmer"
          ]
        }
      }
    }
  }

            if (handler == null) {
                final String path = System.getProperty(HANDLER_PKGS_PROPERTY);
                final StringTokenizer tokenizer = new StringTokenizer(path, "|");
                while (tokenizer.hasMoreTokens()) {
                    final String provider = tokenizer.nextToken().trim();
                    if (provider.equals("jcifs")) {
                        continue;
                    }

            @Override
            protected TokenStreamComponents createComponents(final String fieldName) {
                final Tokenizer tokenizer = new KeywordTokenizer();
                final TokenStream stream = ignoreCase ? new LowerCaseFilter(tokenizer) : tokenizer;
                return new TokenStreamComponents(tokenizer, stream);
            }
        };
    }

 * either express or implied. See the License for the specific language
 * 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;

/**

      "number_of_shards": 1,
      "number_of_replicas": 0,
      "auto_expand_replicas": "0-1"
    },
    "analysis": {
      "analyzer": {
        "standard_analyzer": {
          "type": "custom",
          "tokenizer": "standard",
          "filter": [
            "cjk_width",
            "asciifolding",
            "lowercase",
            "stop",
            "stemmer"
          ]
        }
      }
    }
  }