c++读取utf-8格式中英文混合string

最近项目中用到需要给出每一个字在string中的索引，但是又因为中文字符跟英文字符长度不一样，得分开处理，

在这里记录一下。

想要达到的效果如下：

将 “测试3.1415engEng”分割开

代码：

std::vector <std::string> splitEachChar(const string chars)
{
    std::vector<std::string> words;
    std::string input(chars);
    int len = input.length();
    int i = 0;
    
    while (i < len) {
      assert ((input[i] & 0xF8) <= 0xF0);
      int next = 1;
      if ((input[i] & 0x80) == 0x00) {
        std::cout << "one character: " << input[i] << std::endl;
      } else if ((input[i] & 0xE0) == 0xC0) {
        next = 2;
        std::cout << "two character: " << input.substr(i, next) << std::endl;
      } else if ((input[i] & 0xF0) == 0xE0) {
        next = 3;
        std::cout << "three character: " << input.substr(i, next) << std::endl;
      } else if ((input[i] & 0xF8) == 0xF0) {
        next = 4;
        std::cout << "four character: " << input.substr(i, next) << std::endl;
      }
      words.push_back(input.substr(i, next));
      i += next;
    }
    return words;
} 
void testtemp()
{
    string input;
    while (1)
    {
        getline(cin,input);
        if(input == "exit") break;
        cout<<"--------------------------------"<<endl;
        vector <std::string> ret = splitEachChar(input);

        cout<<input<<endl;
        for(auto it : ret)cout<<it<<endl;
        cout<<"--------------------------------"<<endl;
    }
}
int main()
{
    testtemp(); 
    return 0;
}

参考：

https://blog.csdn.net/cy_tec/article/details/87884177