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);
    }

    /**
     * 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}.

        "tokenizer" : "standard"
      },
      "reading_term_analyzer_mk" : {
        "type" : "custom",
        "tokenizer" : "standard"
      },
      "normalize_analyzer_mk" : {
        "type" : "custom",
        "tokenizer" : "keyword",
        "char_filter" : ["mapping_char"],
        "filter" : ["lowercase"]
      },
      "contents_analyzer_mk" : {
        "type" : "custom",
        "tokenizer" : "standard",

        "tokenizer" : "standard"
      },
      "reading_term_analyzer_mk" : {
        "type" : "custom",
        "tokenizer" : "standard"
      },
      "normalize_analyzer_mk" : {
        "type" : "custom",
        "tokenizer" : "keyword",
        "char_filter" : ["mapping_char"],
        "filter" : ["lowercase"]
      },
      "contents_analyzer_mk" : {
        "type" : "custom",
        "tokenizer" : "standard",

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

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

        "tokenizer" : "standard"
      },
      "reading_term_analyzer_mk" : {
        "type" : "custom",
        "tokenizer" : "standard"
      },
      "normalize_analyzer_mk" : {
        "type" : "custom",
        "tokenizer" : "keyword",
        "char_filter" : ["mapping_char"],
        "filter" : ["lowercase"]
      },
      "contents_analyzer_mk" : {
        "type" : "custom",
        "tokenizer" : "standard",

        "tokenizer" : "standard"
      },
      "reading_term_analyzer_mk" : {
        "type" : "custom",
        "tokenizer" : "standard"
      },
      "normalize_analyzer_mk" : {
        "type" : "custom",
        "tokenizer" : "keyword",
        "char_filter" : ["mapping_char"],
        "filter" : ["lowercase"]
      },
      "contents_analyzer_mk" : {
        "type" : "custom",
        "tokenizer" : "standard",

    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");

 * 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>
 */