std::string utf8_str = "你好，世界"; // 合法，UTF-8 编码
std::cout << utf8_str.size() << " bytes\n"; // 输出可能是 15（每个汉字3字节）

#include <vector>
#include <cstdint>
<p>std::vector<uint32_t> utf8_to_codepoints(const std::string& str) {
std::vector<uint32_t> codepoints;
for (size_t i = 0; i < str.size();) {
uint8_t byte = str[i];
uint32_t codepoint;</p><pre class='brush:php;toolbar:false;'>    if ((byte & 0x80) == 0) {           // 0xxxxxxx: ASCII
        codepoint = byte;
        i += 1;
    } else if ((byte & 0xE0) == 0xC0) { // 110xxxxx
        codepoint = ((byte & 0x1F) << 6) | (str[i+1] & 0x3F);
        i += 2;
    } else if ((byte & 0xF0) == 0xE0) { // 1110xxxx
        codepoint = ((byte & 0x0F) << 12) | ((str[i+1] & 0x3F) << 6) | (str[i+2] & 0x3F);
        i += 3;
    } else if ((byte & 0xF8) == 0xF0) { // 11110xxx
        codepoint = ((byte & 0x07) << 18) | ((str[i+1] & 0x3F) << 12) | ((str[i+2] & 0x3F) << 6) | (str[i+3] & 0x3F);
        i += 4;
    } else {
        // 处理错误字节（如无效UTF-8）
        codepoint = 0xFFFD; // 替换符
        i += 1;
    }
    codepoints.push_back(codepoint);
}
return codepoints;

}

#ifdef _WIN32
#include <windows.h>
<p>std::wstring utf8_to_wstring(const std::string& utf8) {
int len = MultiByteToWideChar(CP_UTF8, 0, utf8.c_str(), -1, nullptr, 0);
std::wstring wide(len, 0);
MultiByteToWideChar(CP_UTF8, 0, utf8.c_str(), -1, &wide[0], len);
wide.pop_back(); // 移除末尾多余\0
return wide;
}</p><p>std::string wstring_to_utf8(const std::wstring& wstr) {
int len = WideCharToMultiByte(CP_UTF8, 0, wstr.c_str(), -1, nullptr, 0, nullptr, nullptr);
std::string utf8(len - 1, 0);
WideCharToMultiByte(CP_UTF8, 0, wstr.c_str(), -1, &utf8[0], len, nullptr, nullptr);
return utf8;
}</p><h1>endif</h1>

#include <boost/locale.hpp>
#include <iostream>
<p>std::string s = "Hello 世界";
std::cout << boost::locale::length(s) << " characters\n"; // 正确输出字符数</p><p>// 转大写（支持Unicode）
std::string upper = boost::locale::to_upper(s, "zh_CN.UTF-8");</p>