std::mbrtoc16

#include <iostream>
#include <iomanip>
#include <clocale>
#include <cstring>
#include <cwchar>
#include <cuchar>
 
int main()
{
    std::setlocale(LC_ALL, "en_US.utf8");
 
    std::string str = u8"z\u00df\u6c34\U0001F34C"; // or u8"zß水?"
 
    std::cout << "Processing " << str.size() << " bytes: [ " << std::showbase;
    for(unsigned char c: str) std::cout << std::hex << +c << ' ';
    std::cout << "]\n";
 
    std::mbstate_t state{}; // zero-initialized to initial state
    char16_t c16;
    const char *ptr = &str[0], *end = &str[0] + str.size();
 
    while(int rc = std::mbrtoc16(&c16, ptr, end - ptr, &state))
    {   
        std::cout << "Next UTF-16 char: " << std::hex << c16 << " obtained from ";
        if(rc == -3)
            std::cout << "earlier surrogate pair\n";
        else if(rc > 0) {
            std::cout << std::dec << rc << " bytes [ ";
            for(int n = 0; n < rc; ++n)
                std::cout << std::hex << +(unsigned char)ptr[n] << ' ';
            std::cout << "]\n";
            ptr += rc;
        } else break;
    }
}

Processing 10 bytes: [ 0x7a 0xc3 0x9f 0xe6 0xb0 0xb4 0xf0 0x9f 0x8d 0x8c ]
Next UTF-16 char: 0x7a obtained from 1 bytes [ 0x7a ]
Next UTF-16 char: 0xdf obtained from 2 bytes [ 0xc3 0x9f ]
Next UTF-16 char: 0x6c34 obtained from 3 bytes [ 0xe6 0xb0 0xb4 ]
Next UTF-16 char: 0xd83c obtained from 4 bytes [ 0xf0 0x9f 0x8d 0x8c ]
Next UTF-16 char: 0xdf4c obtained from earlier surrogate pair

 © cppreference.com