Clang - UTF-8 code units (bytes)
int main() {
/*xxx*/int x=xx; // codepoints=11+3=14, utf8units=11+3=14, utf16units=11+3=14, clusters=11+3=14
/*日本語*/int x=xx; // codepoints=11+3=14, utf8units=11+9=20, utf16units=11+3=14, clusters=11+3=14
/*👩💻*/int x=xx; // codepoints=11+3=14, utf8units=11+11=22, utf16units=11+5=16, clusters=11+1=12
}