https://en.wikipedia.org/wiki/Universal_Coded_Character_Set

ucs_code_point.cpp

#include <iostream>
#include <string>
#include <cassert>

# https://stackoverflow.com/questions/395832/how-to-get-code-point-number-for-a-given-character-in-a-utf-8-string
wchar_t utf8_char_to_ucs2(const unsigned char *utf8)
{
  if(!(utf8[0] & 0x80))      // 0xxxxxxx
    return (wchar_t)utf8[0];
  else if((utf8[0] & 0xE0) == 0xC0)  // 110xxxxx
    return (wchar_t)(((utf8[0] & 0x1F) << 6) | (utf8[1] & 0x3F));
  else if((utf8[0] & 0xF0) == 0xE0)  // 1110xxxx
    return (wchar_t)(((utf8[0] & 0x0F) << 12) | ((utf8[1] & 0x3F) << 6) | (utf8[2] & 0x3F));
  else
    return -1;  // uh-oh, UCS-2 can't handle code points this high
}

int main()
{    
    // Nº 12680 https://codepoints.net/U+3188
    auto result = utf8_char_to_ucs2(reinterpret_cast<const unsigned char*>(u8"ㆈ"));
    std::cout << result << " " << std::hex << result << std::endl;
    assert(result == 12680);
}