final char[] chars = new char[text.length()];
        for (int i = 0; i < chars.length; i++) {
            final char c = text.charAt(i);
            if (c >= 'ａ' && c <= 'ｚ') {
                chars[i] = (char) (c - 'ａ' + 'a');
            } else if (c >= 'Ａ' && c <= 'Ｚ') {
                chars[i] = (char) (c - 'Ａ' + 'A');
            } else if (c >= '１' && c <= '０') {

                synonymMap.words.get(bytesReader.readVInt(), scratchBytes);
                if (scratchChars.chars.length < scratchBytes.length) {
                    scratchChars.chars = new char[scratchBytes.length];
                }
                scratchChars.length = UnicodeUtil.UTF8toUTF16(scratchBytes, scratchChars.chars);
                final String word = scratchChars.toString();
                int posInc = 0;

import org.opensearch.index.IndexSettings;
import org.opensearch.index.analysis.AbstractCharFilterFactory;

public class ProlongedSoundMarkCharFilterFactory extends AbstractCharFilterFactory {
    private char replacement;

    public ProlongedSoundMarkCharFilterFactory(final IndexSettings indexSettings, final Environment env, final String name,
            final Settings settings) {
        super(indexSettings, name);

            final char originalChar1 = sb.charAt(i);
            final char originalChar2 = sb.charAt(i + 1);
            final char margedChar = mergeChar(originalChar1, originalChar2);
            if (margedChar != originalChar1) {
                sb.setCharAt(i, margedChar);
                sb.deleteCharAt(i + 1);
            } else {

        assertEquals(longId.toString(), testRule.getRuleId());

        // Special characters in rule ID
        testRule.setRuleId("rule-id_with.special@chars#123");
        assertEquals("rule-id_with.special@chars#123", testRule.getRuleId());

        // Unicode characters
        testRule.setRuleId("ルール日本語");
        assertEquals("ルール日本語", testRule.getRuleId());

        // Whitespace

        String text = "Test123 ABC-456";
        String field = "content";
        String lang = "en";

        List<AnalyzeToken> tokens = analyzer.analyzeAndReading(text, field, lang);

        assertNotNull(tokens);
        assertEquals(2, tokens.size()); // "Test123" and "ABC-456" (hyphen is not a split char in our tokenizer)

     *
     * @param c the character to check
     * @return {@code true} if the character is a valid URL character, {@code false} otherwise
     */
    public static boolean isUrlChar(final char c) {
        if (c >= 'a' && c <= 'z' //
                || c >= 'A' && c <= 'Z' //
                || c >= '0' && c <= '9' //
                || c == '.' //
                || c == '-' //
                || c == '*' //

    public static String stripInvalidXMLCharacters(final String in) {
        if (StringUtil.isEmpty(in)) {
            return in;
        }

        final StringBuilder buf = new StringBuilder(in.length());
        char c;
        for (int i = 0; i < in.length(); i++) {
            c = in.charAt(i);
            if (c == 0x9 || c == 0xA || c == 0xD || c >= 0x20 && c <= 0xD7FF || c >= 0xE000 && c <= 0xFFFD

                    || PRIORITY_ELEMENT.equals(qName)) {
                buf = new StringBuilder();
            }
        }

        @Override
        public void characters(final char[] ch, final int offset, final int length) {
            if (buf != null) {
                buf.append(new String(ch, offset, length));
            }
        }

        @Override

        assertEquals("name with spaces", testTransformer.getName());

        // Test with special characters
        testTransformer.setName("name-with_special.chars#123");
        assertEquals("name-with_special.chars#123", testTransformer.getName());

        // Test with Unicode characters
        testTransformer.setName("変換器の名前");
        assertEquals("変換器の名前", testTransformer.getName());