return i > 0 && unicode.IsDigit(ch)
}

func (t *Tokenizer) Text() string {
	switch t.tok {
	case LSH:
		return "<<"
	case RSH:
		return ">>"
	case ARR:
		return "->"
	case ROT:
		return "@>"
	}
	return t.s.TokenText()
}

func (t *Tokenizer) File() string {
	return t.base.Filename()
}

func (t *Tokenizer) Base() *src.PosBase {
	return t.base
}

    static {
        setup(defaultCtype);
    }

    /**
     * {@link Tokenizer}を作成します。
     *
     * @param str
     *            文字列。{@literal null}であってはいけません
     */
    public Tokenizer(final String str) {
        this(str, defaultCtype);
    }

    /**
     * {@link Tokenizer}を作成します。
     *
     * @param str
     *            文字列。{@literal null}であってはいけません
     * @param ctype

                tokenizer.setReader(inputPending);
            }
            tokenizer.reset();
        }

        @Override
        public boolean incrementToken() throws IOException {
            return tokenizer.incrementToken();
        }

        @Override
        public void end() throws IOException {
            tokenizer.end();
        }

        @Override

        final Tokenizer tokenizer;
        if (trimRootToken && hasDots) {
            tokenizer = new Tokenizer(expression);
            tokenizer.nextPropertyName();
            if (tokenizer.getPosition() == EOF) {
                return null;
            }
        } else {
            tokenizer = new Tokenizer("." + expression);
        }

          "type": "custom",
          "tokenizer": "standard",
          "filter": [
            "truncate20_filter",
            "lowercase",
            "arabic_stop",
            "arabic_normalization",
            "arabic_keywords",
            "arabic_override",
            "arabic_stemmer"
          ]
        },
        "armenian_analyzer": {
          "tokenizer":  "standard",
          "filter": [

    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");

    checkNotNull(input);
    Tokenizer tokenizer = new Tokenizer(input);
    try {
      String type = tokenizer.consumeToken(TOKEN_MATCHER);
      consumeSeparator(tokenizer, '/');
      String subtype = tokenizer.consumeToken(TOKEN_MATCHER);
      ImmutableListMultimap.Builder<String, String> parameters = ImmutableListMultimap.builder();
      while (tokenizer.hasMore()) {
        consumeSeparator(tokenizer, ';');

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;

            @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;

/**