pkg time, method (Time) AppendFormat([]uint8, string) []uint8
pkg unicode, const Version = "8.0.0"
pkg unicode, var Ahom *RangeTable
pkg unicode, var Anatolian_Hieroglyphs *RangeTable
pkg unicode, var Hatran *RangeTable
pkg unicode, var Multani *RangeTable
pkg unicode, var Old_Hungarian *RangeTable

        // Behavior is determined by static initialization, not runtime config
        byte[] unicodeHash = auth.getUnicodeHash(challenge);
        byte[] ansiHash = auth.getAnsiHash(challenge);

        // Unicode hash returns empty array due to static LM_COMPATIBILITY=3
        assertEquals(0, unicodeHash.length);
        // ANSI hash always returns 24 bytes
        assertEquals(24, ansiHash.length);
    }

        result = KuromojiCSVUtil.parse(value);
        assertEquals(2, result.length);
        assertEquals("with\rcarriage", result[0]);
        assertEquals("return", result[1]);

        // Unicode characters
        value = "\"日本語\",\"한국어\",\"中文\"";
        result = KuromojiCSVUtil.parse(value);
        assertEquals(3, result.length);
        assertEquals("日本語", result[0]);
        assertEquals("한국어", result[1]);

    static Stream<Arguments> nameProvider() {
        return Stream.of(Arguments.of("", "empty string is allowed"), Arguments.of(" ", "single space is preserved"),
                Arguments.of("复杂名.txt", "unicode name is preserved"), Arguments.of(null, "null name is passed through"));
    }

    @ParameterizedTest(name = "getName returns as-set: [{0}] - {1}")
    @MethodSource("nameProvider")

   *     encoded.
   */
  fun getEffectiveTldPlusOne(domain: String): String? {
    // We use UTF-8 in the list so we need to convert to Unicode.
    val unicodeDomain = IDN.toUnicode(domain)
    val domainLabels = splitDomain(unicodeDomain)

    val rule = findMatchingRule(domainLabels)
    if (domainLabels.size == rule.size && rule[0][0] != EXCEPTION_MARKER) {

 * lookups.
 *
 * <p>During construction, names are normalized in two ways:
 *
 * <ol>
 *   <li>ASCII uppercase characters are converted to lowercase.
 *   <li>Unicode dot separators other than the ASCII period ({@code '.'}) are converted to the ASCII
 *       period.
 * </ol>
 *
 * <p>The normalized values will be returned from {@link #toString()} and {@link #parts()}, and will

        assertEquals(messageWithSpecialChars, exception.getMessage());
    }

    public void test_unicodeInMessage() {
        // Test with Unicode characters in message
        String unicodeMessage = "オフセットが制限を超えました: 結果 範囲外 😱 ⚠️";
        ResultOffsetExceededException exception = new ResultOffsetExceededException(unicodeMessage);

        assertEquals(0x04, Smb2QueryDirectoryRequest.SMB2_INDEX_SPECIFIED);
        assertEquals(0x10, Smb2QueryDirectoryRequest.SMB2_REOPEN);
    }

    @Test
    @DisplayName("Test with Unicode filename")
    void testUnicodeFileName() {
        request = new Smb2QueryDirectoryRequest(mockConfig);
        String unicodeFileName = "テスト文件.txt";

        request.setFileName(unicodeFileName);

# Ideographic full stop (full-width period for Chinese, etc.) should be
# treated as a dot.
# U+3002 is mapped to U+002E (dot)
http://www.foo\u3002bar.com  s:http p:/ h:www.foo.bar.com

# Invalid unicode characters should fail...
# U+FDD0 is disallowed; %ef%b7%90 is U+FDD0
http://\ufdd0zyx.com

# ...This is the same as previous but escaped.
http://%ef%b7%90zyx.com

## Technology Stack

- **Java**: 21+ (configured via parent POM)
- **OpenSearch**: Latest (provided scope)
- **Apache Lucene**: Query parsing and text analysis
- **ICU4J**: Unicode text processing and normalization
- **JUnit 4**: Testing framework
- **Maven**: Build and dependency management

## Quick Start

### Prerequisites

- Java 21 or higher