Function CodePointToUtf8

test/common/gtest/gtest.cpp:3231–3257

Converts a Unicode code point to a narrow string in UTF-8 encoding. code_point parameter is of type UInt32 because wchar_t may not be wide enough to contain a code point. If the code_point is not a valid Unicode code point (i.e. outside of Unicode range U+0 to U+10FFFF) it will be converted to "(Invalid Unicode 0xXXXXXXXX)".

// (i.e. outside of Unicode range U+0 to U+10FFFF) it will be converted
// to "(Invalid Unicode 0xXXXXXXXX)".
std::string CodePointToUtf8(UInt32 code_point) {
  if (code_point > kMaxCodePoint4) {
    return "(Invalid Unicode 0x" + String::FormatHexInt(code_point) + ")";
  }

  char str[5];  // Big enough for the largest valid code point.
  if (code_point <= kMaxCodePoint1) {
    str[1] = '\0';
    str[0] = static_cast<char>(code_point);                          // 0xxxxxxx
  } else if (code_point <= kMaxCodePoint2) {
    str[2] = '\0';
    str[1] = static_cast<char>(0x80 | ChopLowBits(&code_point, 6));  // 10xxxxxx
    str[0] = static_cast<char>(0xC0 | code_point);                   // 110xxxxx
  } else if (code_point <= kMaxCodePoint3) {
    str[3] = '\0';
    str[2] = static_cast<char>(0x80 | ChopLowBits(&code_point, 6));  // 10xxxxxx
    str[1] = static_cast<char>(0x80 | ChopLowBits(&code_point, 6));  // 10xxxxxx
    str[0] = static_cast<char>(0xE0 | code_point);                   // 1110xxxx
  } else {  // code_point <= kMaxCodePoint4
    str[4] = '\0';
    str[3] = static_cast<char>(0x80 | ChopLowBits(&code_point, 6));  // 10xxxxxx
    str[2] = static_cast<char>(0x80 | ChopLowBits(&code_point, 6));  // 10xxxxxx
    str[1] = static_cast<char>(0x80 | ChopLowBits(&code_point, 6));  // 10xxxxxx
    str[0] = static_cast<char>(0xF0 | code_point);                   // 11110xxx
  }
  return str;
}

// The following two functions only make sense if the the system
// uses UTF-16 for wide string encoding. All supported systems