codepointsToUtf8 function

List<int?> codepointsToUtf8(List<int?> codepoints, [ int offset = 0, int? length ])

Encode code points as UTF-8 code units.

Implementation

List<int?> codepointsToUtf8(List<int?> codepoints, [int offset = 0, int? length]) {
  var source = ListRange(codepoints, offset, length);

  var encodedLength = 0;
  for (var value in source) {
    if (null == value) {
      continue;
    }
    if (value < 0 || value > UNICODE_VALID_RANGE_MAX) {
      encodedLength += 3;
    } else if (value <= _UTF8_ONE_BYTE_MAX) {
      encodedLength++;
    } else if (value <= _UTF8_TWO_BYTE_MAX) {
      encodedLength += 2;
    } else if (value <= _UTF8_THREE_BYTE_MAX) {
      encodedLength += 3;
    } else if (value <= UNICODE_VALID_RANGE_MAX) {
      encodedLength += 4;
    }
  }

  var encoded = <int?>[]..length = encodedLength;
  var insertAt = 0;
  for (var value in source) {
    if (null == value) {
      continue;
    }

    if (value < 0 || value > UNICODE_VALID_RANGE_MAX) {
      encoded.setRange(insertAt, insertAt + 3, [0xef, 0xbf, 0xbd]);
      insertAt += 3;
    } else if (value <= _UTF8_ONE_BYTE_MAX) {
      encoded[insertAt] = value;
      insertAt++;
    } else if (value <= _UTF8_TWO_BYTE_MAX) {
      encoded[insertAt] = _UTF8_FIRST_BYTE_OF_TWO_BASE |
          (_UTF8_FIRST_BYTE_OF_TWO_MASK &
              _addToEncoding(insertAt, 1, value, encoded)!);
      insertAt += 2;
    } else if (value <= _UTF8_THREE_BYTE_MAX) {
      encoded[insertAt] = _UTF8_FIRST_BYTE_OF_THREE_BASE |
          (_UTF8_FIRST_BYTE_OF_THREE_MASK &
              _addToEncoding(insertAt, 2, value, encoded)!);
      insertAt += 3;
    } else if (value <= UNICODE_VALID_RANGE_MAX) {
      encoded[insertAt] = _UTF8_FIRST_BYTE_OF_FOUR_BASE |
          (_UTF8_FIRST_BYTE_OF_FOUR_MASK &
              _addToEncoding(insertAt, 3, value, encoded)!);
      insertAt += 4;
    }
  }
  return encoded;
}