/**
   * Substitute: A character that may be substituted for a character which is determined to be
   * invalid or in error.
   *
   * @since 8.0
   */
  public static final byte SUB = 26;

  /**
   * Escape: A control character intended to provide code extension (supplementary characters) in
   * general information interchange. The Escape character itself is a prefix affecting the

   *
   * @param replacementMap a map of characters to their escaped representations
   * @param safeMin the lowest character value in the safe range
   * @param safeMax the highest character value in the safe range
   * @param unsafeReplacement the default replacement for unsafe characters or null if no default
   *     replacement is required
   */
  protected ArrayBasedUnicodeEscaper(
      Map<Character, String> replacementMap,
      int safeMin,

 *
 *  * In queries, ' ' is encoded to '+' and '+' is encoded to "%2B".
 *
 *  * Characters in `encodeSet` are percent-encoded.
 *
 *  * Control characters and non-ASCII characters are percent-encoded.
 *
 *  * All other characters are copied without transformation.
 *
 * @param alreadyEncoded true to leave '%' as-is; false to convert it to '%25'.

    return total;
  }

  /**
   * Discards {@code n} characters of data from the reader. This method will block until the full
   * amount has been skipped. Does not close the reader.
   *
   * @param reader the reader to read from
   * @param n the number of characters to skip
   * @throws EOFException if this stream reaches the end before skipping all the characters
   * @throws IOException if an I/O error occurs
   */

         *
         * This method reads characters from the reader and processes them according to the following rules:
         * - ISO control characters and space characters are treated as spaces.
         * - Alphanumeric characters (0-9, A-Z, a-z) are appended to the buffer.
         * - Symbol characters (!-/, :-@, [-`, {-~) are appended to the buffer.

    // which means they are treated as pairs of safe characters).
    builder.setSafeRange(Character.MIN_VALUE, '\uFFFD');
    // Unsafe characters are replaced with the Unicode replacement character.
    builder.setUnsafeReplacement("\uFFFD");

    /*
     * Except for \n, \t, and \r, all ASCII control characters are replaced with the Unicode
     * replacement character.
     *

    }

    /**
     * Strips invalid XML characters from the input string.
     *
     * This method removes characters that are not allowed in XML documents
     * according to the XML 1.0 specification. Valid characters include:
     * - Tab (0x9)
     * - Line feed (0xA)
     * - Carriage return (0xD)
     * - Any character between 0x20 and 0xD7FF
     * - Any character between 0xE000 and 0xFFFD

        for (char c : validChars.toCharArray()) {
            assertTrue("Character '" + c + "' should be a valid URL character", CharUtil.isUrlChar(c));
        }
    }

    public void test_isUrlChar_boundaryChars() {
        // Test boundary characters for ranges
        assertTrue(CharUtil.isUrlChar('a')); // first lowercase

   *
   * @param seq the sequence of characters from which to decode the code point
   * @param index the index of the first character to decode
   * @param end the index beyond the last valid character to decode
   * @return the Unicode code point for the given index or the negated value of the trailing high
   *     surrogate character at the end of the sequence
   */
  protected static int codePointAt(CharSequence seq, int index, int end) {

/**
 * Represents a single character mapping rule that defines how input characters are mapped to output characters
 * for text analysis and search processing. This class is used in character mapping dictionaries to transform
 * text during indexing and search operations.
 *
 * <p>Each mapping item consists of one or more input character sequences that are mapped to a single output