try {
            robotsTxt = robotsTxtHelper.parse(in, "UTF-8");
        } finally {
            CloseableUtil.closeQuietly(in);
        }

        // Should handle unicode content
        assertNotNull(robotsTxt);
        assertFalse(robotsTxt.allows("/test/", "TestBot"));
    }

    return new StringAsImmutableList(checkNotNull(string));
  }

  /**
   * Returns a view of the specified {@code CharSequence} as a {@code List<Character>}, viewing
   * {@code sequence} as a sequence of Unicode code units. The view does not support any
   * modification operations, but reflects any changes to the underlying character sequence.
   *
   * @param sequence the character sequence to view as a {@code List} of characters

            capabilities |= CAP_EXTENDED_SECURITY; // & doesn't copy high bit
        }

        if ((capabilities & SmbConstants.CAP_UNICODE) == 0) {
            // server doesn't want unicode
            if (FORCE_UNICODE) {
                capabilities |= SmbConstants.CAP_UNICODE;
            } else {
                useUnicode = false;
                flags2 &= 0xFFFF ^ SmbConstants.FLAGS2_UNICODE;

        assertEquals(expected, id); // Should not be truncated
    }

    @Test
    public void testCreateSuggestTextIdWithUnicodeCharacters() {
        // Test with various Unicode characters that may encode differently
        String unicodeText = "日本語テスト🎌🗾こんにちは世界";
        String id = SuggestUtil.createSuggestTextId(unicodeText);
        assertNotNull(id);
        assertTrue(id.length() <= 445);

# Whether to remove duplicate terms in documents.
crawler.document.duplicate.term.removed=false
# Unicode space characters for document parsing.
crawler.document.space.chars=u0009u000Au000Bu000Cu000Du001Cu001Du001Eu001Fu0020u00A0u1680u180Eu2000u2001u2002u2003u2004u2005u2006u2007u2008u2009u200Au200Bu200Cu202Fu205Fu3000uFEFFuFFFDu00B6
# Unicode full stop characters for document parsing.
crawler.document.fullstop.chars=u002eu06d4u2e3cu3002

 * either {@link Character} or {@link Arrays}.
 *
 * <p>All the operations in this class treat {@code char} values strictly numerically; they are
 * neither Unicode-aware nor locale-dependent.
 *
 * <p>See the Guava User Guide article on <a
 * href="https://github.com/google/guava/wiki/PrimitivesExplained">primitive utilities</a>.
 *
 * @author Kevin Bourrillion
 * @since 1.0
 */

        verify(mockNdrBuffer).enc_ndr_referent(dnsDomainInfo.sid, 1);

        verify(mockDeferredNdrBuffer, times(9)).enc_ndr_long(anyInt()); // 3 enc_ndr_long for each of 3 unicode strings
        verify(mockDeferredNdrBuffer, times(3)).enc_ndr_long(0);
        verify(mockDeferredNdrBuffer, times(3)).advance(anyInt());

# IdnaMappingTable.txt
# Date: 2023-08-10, 22:32:27 GMT
# © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# Unicode IDNA Compatible Preprocessing for UTS #46
# Version: 15.1.0
#
# For documentation and usage, see https://www.unicode.org/reports/tr46
#

     * The value is, e.g. u0009u000Au000Bu000Cu000Du001Cu001Du001Eu001Fu0020u00A0u1680u180Eu2000u2001u2002u2003u2004u2005u2006u2007u2008u2009u200Au200Bu200Cu202Fu205Fu3000uFEFFuFFFDu00B6 <br>
     * comment: Unicode space characters for document parsing.
     * @return The value of found property. (NotNull: if not found, exception but basically no way)
     */
    String getCrawlerDocumentSpaceChars();

    /**

- [security] Vulnerability in golang.org/x/text/encoding/unicode ([#92219](https://github.com/kubernetes/kubernetes/pull/92219), [@voor](https://github.com/voor)) [SIG API Machinery, CLI, Cloud Provider, Cluster Lifecycle, Instrumentation and Node]

### Other (Cleanup or Flake)