StringBuilder sb = new StringBuilder();
      for (int j = 0; j < charCount; j++) {
        int codePoint;
        // discard illegal surrogate "codepoints"
        do {
          codePoint = rnd.nextInt(maxCodePoint.value);
        } while (Character.isSurrogate((char) codePoint));
        sb.appendCodePoint(codePoint);
      }
      strings[i] = sb.toString();
    }
  }

  @Benchmark

      MAX_LOW_SURROGATE, MAX_HIGH_SURROGATE, MIN_LOW_SURROGATE, MIN_HIGH_SURROGATE,
    };
    for (char surrogate : surrogates) {
      builder.add(newString(surrogate));
      builder.add(newString(surrogate, 'n'));
      builder.add(newString('n', surrogate));
      builder.add(newString(surrogate, surrogate));
    }
    builder.add(newString(MIN_LOW_SURROGATE, MAX_HIGH_SURROGATE));
    ILL_FORMED_STRINGS = builder.build();
  }

    pos: Int,
    limit: Int,
  ): List<Int> {
    val result = mutableListOf<Int>()
    var i = pos
    while (i < limit) {
      val c = this[i]
      result +=
        when {
          c.isSurrogate() -> {
            val low = (if (i + 1 < limit) this[i + 1] else '\u0000')
            if (c.isLowSurrogate() || !low.isLowSurrogate()) {
              '?'.code
            } else {
              i++

    // into the range of surrogate characters, but if they do we must not test
    // any values in that range. To see why, consider the case where:
    // safeMin <= {hi,lo} <= safeMax
    // where {hi,lo} are characters forming a surrogate pair such that:
    // codePointOf(hi, lo) > safeMax
    // which would result in the surrogate pair being (wrongly) considered safe.

   *             surrogate is returned.</b>
   *         <li><b>If the next character was a valid low surrogate, the code point value of the
   *             high/low surrogate pair is returned.</b>
   *         <li>If the next character was not a low surrogate value, then {@link
   *             IllegalArgumentException} is thrown.
   *       </ol>

   * Specifically "\r" (carriage return) is preserved in the output, which may result in it being
   * silently converted to "\n" when the XML is parsed.
   *
   * <p>This escaper does not treat surrogate pairs specially and does not perform Unicode
   * validation on its input.
   */
  public static Escaper xmlContentEscaper() {
    return XML_CONTENT_ESCAPER;
  }

  /**

        };
    EscaperAsserts.assertBasic(surrogateEscaper);

    // A surrogate pair defining a code point within the safe range.
    String safeInput = "\uD800\uDC00"; // 0x10000
    assertThat(surrogateEscaper.escape(safeInput)).isEqualTo(safeInput);

    // A surrogate pair defining a code point outside the safe range (but both
    // of the surrogate characters lie within the safe range). It is important

        }
      } else {
        // and everything else is replaced with FFFD.
        assertEscaping(xmlEscaper, "\uFFFD", ch);
      }
    }

    // Test _all_ allowed characters (including surrogate values).
    for (char ch = 0x20; ch <= 0xFFFD; ch++) {
      // There are a small number of cases to consider, so just do it manually.
      if (ch == '&') {
        assertEscaping(xmlEscaper, "&amp;", ch);

   * for use with it (such as all-ASCII text) and for simple debugging text. When using this method,
   * consider the following:
   *
   * <ul>
   *   <li>it may split surrogate pairs
   *   <li>it may split characters and combining characters
   *   <li>it does not consider word boundaries
   *   <li>if truncating for display to users, there are other considerations that must be taken

    }
  }

  /**
   * This verifies that putUnencodedChars(String) and hashUnencodedChars(String) are equivalent,
   * even for funny strings composed by (possibly unmatched, and mostly illegal) surrogate
   * characters. (But doesn't test that they do the right thing - just their consistency).
   */
  private static void assertHashStringWithSurrogatesEquivalence(
      HashFunction hashFunction, Random random) {