}

    public void test_isUrlChar_notAllowed() {
        // Test characters that are not allowed
        assertFalse(CharUtil.isUrlChar(' ')); // space
        assertFalse(CharUtil.isUrlChar('\t')); // tab
        assertFalse(CharUtil.isUrlChar('\n')); // newline
        assertFalse(CharUtil.isUrlChar('\r')); // carriage return
        assertFalse(CharUtil.isUrlChar('<')); // less than

text/html                      html htm         # HTML Document
text/plain                     txt ini log in cfg m4 sh     # Plain Text File
text/richtext                  rtx              # Rich Text File
text/tab-separated-values      tsv              #
text/x-setext                  etx              #
text/x-sgml                    sgml sgm         # SGML Document
video/mpeg                     mpeg mpg mpe     # MPEG Movie File

    }

    @Test
    @DisplayName("Should handle special characters in delimiter")
    void testJoinWithSpecialCharDelimiter() {
        String result = StringUtil.join("\\t", "tab", "separated", "values");
        assertEquals("tab\\tseparated\\tvalues", result);
    }

    @Test
    @DisplayName("Should handle Unicode characters in delimiter")
    void testJoinWithUnicodeDelimiter() {

"'+e+'"');i[e]()}}))},l(t,null,[{key:"VERSION",get:function(){return"4.6.2"}}]),t}();o.default(document).on("click.bs.tab.data-api",'[data-toggle="tab"], [data-toggle="pill"], [data-toggle="list"]',(function(t){t.preventDefault(),ge._jQueryInterface.call(o.default(this),"show")})),o.default.fn.tab=ge._jQueryInterface,o.default.fn.tab.Constructor=ge,o.default.fn.tab.noConflict=function(){return o.default.fn.tab=re,ge._jQueryInterface};var me="bs.toast",pe=o.default.fn.toast,_e="hide",ve="show",ye="showing",be="c...

    }

    /**
     * Test extraction with special characters and control characters.
     */
    public void test_getText_withSpecialCharacters_handlesCorrectly() {
        final String specialContent = "Tab\there\nNewline\rCarriage return\0Null byte";
        final InputStream in = new ByteArrayInputStream(specialContent.getBytes());

        final ExtractData result = textExtractor.getText(in, null);

      ','.code.toByte() -> {
        // Consume ','.
        readByte()
        commaFound = true
      }

      ' '.code.toByte(), '\t'.code.toByte() -> {
        readByte()
        // Consume space or tab.
      }

      else -> break@loop
    }
  }
  return commaFound
}

private fun Buffer.startsWith(prefix: Byte): Boolean = !exhausted() && this[0] == prefix

/**

 * This extractor provides better structured data extraction compared to Tika's generic text extraction.
 *
 * <p>Features:
 * <ul>
 *   <li>Automatic delimiter detection (comma, tab, semicolon, pipe)</li>
 *   <li>Header row detection and extraction</li>
 *   <li>Column name to data value association</li>
 *   <li>Quoted field handling</li>
 *   <li>Column names as metadata</li>

   * the XML specification.
   *
   * <p>This escaper does not escape non-ASCII characters to their numeric character references
   * (NCR). However, horizontal tab {@code '\t'}, line feed {@code '\n'} and carriage return {@code
   * '\r'} are escaped to a corresponding NCR {@code "&#x9;"}, {@code "&#xA;"}, and {@code "&#xD;"}

  /**
   * <a href="http://www.iana.org/assignments/media-types/text/tab-separated-values">Tab separated
   * values</a>.
   *
   * @since 15.0
   */
  public static final MediaType TSV_UTF_8 = createConstantUtf8(TEXT_TYPE, "tab-separated-values");

  public static final MediaType VCARD_UTF_8 = createConstantUtf8(TEXT_TYPE, "vcard");

  /**

text/html                      html htm         # HTML Document
text/plain                     txt ini log in cfg m4 sh     # Plain Text File
text/richtext                  rtx              # Rich Text File
text/tab-separated-values      tsv              #
text/x-setext                  etx              #
text/x-sgml                    sgml sgm         # SGML Document
video/mpeg                     mpeg mpg mpe     # MPEG Movie File