#include <iostream>#include <string>int main() {// char: 单字节字符，通常用于ASCIIchar c = 'A';char str[] = "Hello";// wchar_t: 宽字符，Windows上是2字节，Linux上是4字节wchar_t wc = L'中';wchar_t wstr[] = L"你好世界";// C++11新增的字符类型char16_t c16 = u'文';      // UTF-16字符char32_t c32 = U'字';      // UTF-32字符// C++20新增：char8_t，专门用于UTF-8// char8_t c8 = u8'A';std::cout << "char size: " << sizeof(char) << " bytes" << std::endl;std::cout << "wchar_t size: " << sizeof(wchar_t) << " bytes" << std::endl;std::cout << "char16_t size: " << sizeof(char16_t) << " bytes" << std::endl;std::cout << "char32_t size: " << sizeof(char32_t) << " bytes" << std::endl;return 0;}

2.2 字符串字面量前缀

// 不同编码的字符串字面量
auto s1 = "Hello";           // const char*，窄字符串
auto s2 = L"你好";           // const wchar_t*，宽字符串
auto s3 = u8"UTF-8字符串";   // const char*（C++20前）或 const char8_t*（C++20后）
auto s4 = u"UTF-16字符串";   // const char16_t*
auto s5 = U"UTF-32字符串";   // const char32_t*

三、常见编码问题及解决方案

3.1 中文乱码问题

问题代码：

#include <iostream>#include <string>int main() {std::string name = "张三";  // 可能出现乱码std::cout << "姓名：" << name << std::endl;return 0;}

解决方案：

方法一：确保源文件编码为UTF-8

// 1. 将源文件保存为UTF-8编码（无BOM）
// 2. 在编译时指定编码
// g++ -fexec-charset=UTF-8 main.cpp
// MSVC: /utf-8 编译选项
#include <iostream>#include <string>int main() {std::string name = u8"张三";  // 明确使用UTF-8std::cout << u8"姓名：" << name << std::endl;return 0;}

方法二：Windows控制台设置UTF-8

#include <iostream>#include <windows.h>int main() {// 设置控制台代码页为UTF-8SetConsoleOutputCP(65001);std::cout << u8"你好，世界！" << std::endl;return 0;}

3.2 跨平台编码转换

#include <iostream>#include <string>#include <locale>#include <codecvt>// UTF-8 转 UTF-16std::u16string utf8_to_utf16(const std::string& utf8_str) {std::wstring_convert<std::codecvt_utf8_utf16<char16_t>, char16_t> converter;return converter.from_bytes(utf8_str);}// UTF-16 转 UTF-8std::string utf16_to_utf8(const std::u16string& utf16_str) {std::wstring_convert<std::codecvt_utf8_utf16<char16_t>, char16_t> converter;return converter.to_bytes(utf16_str);}// UTF-8 转 wstring（Windows宽字符）std::wstring utf8_to_wstring(const std::string& utf8_str) {std::wstring_convert<std::codecvt_utf8<wchar_t>> converter;return converter.from_bytes(utf8_str);}// wstring 转 UTF-8std::string wstring_to_utf8(const std::wstring& wstr) {std::wstring_convert<std::codecvt_utf8<wchar_t>> converter;return converter.to_bytes(wstr);}int main() {std::string utf8_text = u8"C++编程";// 转换为UTF-16std::u16string utf16_text = utf8_to_utf16(utf8_text);std::cout << "UTF-16 length: " << utf16_text.length() << std::endl;// 转回UTF-8std::string converted_back = utf16_to_utf8(utf16_text);std::cout << "Converted back: " << converted_back << std::endl;return 0;}

注意：std::codecvt 在C++17中被标记为废弃，建议在新项目中使用第三方库如ICU、iconv或C++20的新特性。

3.3 文件读写编码问题

#include <iostream>#include <fstream>#include <string>#include <codecvt>#include <locale>// 写入UTF-8文件void writeUTF8File(const std::string& filename, const std::string& content) {std::ofstream file(filename, std::ios::binary);if (file.is_open()) {// 写入UTF-8 BOM（可选，但有些程序需要）// const char bom[] = {0xEF, 0xBB, 0xBF};// file.write(bom, sizeof(bom));file << content;file.close();std::cout << "文件写入成功" << std::endl;}}// 读取UTF-8文件std::string readUTF8File(const std::string& filename) {std::ifstream file(filename, std::ios::binary);std::string content;if (file.is_open()) {// 读取整个文件file.seekg(0, std::ios::end);size_t size = file.tellg();file.seekg(0, std::ios::beg);content.resize(size);file.read(&content[0], size);file.close();// 检查并跳过UTF-8 BOMif (content.size() >= 3 &&static_cast<unsigned char>(content[0]) == 0xEF &&static_cast<unsigned char>(content[1]) == 0xBB &&static_cast<unsigned char>(content[2]) == 0xBF) {content = content.substr(3);}}return content;}int main() {std::string text = u8"这是一段中文文本\n包含多行内容";writeUTF8File("test_utf8.txt", text);std::string read_text = readUTF8File("test_utf8.txt");std::cout << "读取的内容：\n" << read_text << std::endl;return 0;}

3.4 字符串长度计算

#include <iostream>#include <string>// 计算UTF-8字符串的实际字符数（非字节数）size_t utf8_length(const std::string& str) {size_t length = 0;for (size_t i = 0; i < str.size(); ) {unsigned char c = static_cast<unsigned char>(str[i]);if (c < 0x80) {// 单字节字符（ASCII）i += 1;} else if ((c & 0xE0) == 0xC0) {// 双字节字符i += 2;} else if ((c & 0xF0) == 0xE0) {// 三字节字符（大多数中文）i += 3;} else if ((c & 0xF8) == 0xF0) {// 四字节字符（emoji等）i += 4;} else {// 无效编码，跳过i += 1;}length++;}return length;}int main() {std::string text = u8"Hello世界";std::cout << "字节数：" << text.size() << std::endl;std::cout << "字符数：" << utf8_length(text) << std::endl;// 输出：// 字节数：16// 字符数：8return 0;}

四、实用工具类封装

#include <iostream>#include <string>#include <vector>class EncodingHelper {public:// 判断是否为UTF-8编码static bool isValidUTF8(const std::string& str) {for (size_t i = 0; i < str.size(); ) {unsigned char c = static_cast<unsigned char>(str[i]);int bytes = 0;if (c < 0x80) {bytes = 1;} else if ((c & 0xE0) == 0xC0) {bytes = 2;} else if ((c & 0xF0) == 0xE0) {bytes = 3;} else if ((c & 0xF8) == 0xF0) {bytes = 4;} else {return false;  // 无效的UTF-8序列}// 检查后续字节for (int j = 1; j < bytes; j++) {if (i + j >= str.size()) return false;unsigned char next = static_cast<unsigned char>(str[i + j]);if ((next & 0xC0) != 0x80) return false;}i += bytes;}return true;}// 截取UTF-8字符串（按字符数，非字节数）static std::string substr(const std::string& str, size_t start, size_t count) {std::vector<size_t> char_positions;char_positions.push_back(0);for (size_t i = 0; i < str.size(); ) {unsigned char c = static_cast<unsigned char>(str[i]);if (c < 0x80) i += 1;else if ((c & 0xE0) == 0xC0) i += 2;else if ((c & 0xF0) == 0xE0) i += 3;else if ((c & 0xF8) == 0xF0) i += 4;else i += 1;if (i < str.size()) {char_positions.push_back(i);}}if (start >= char_positions.size()) return "";size_t start_pos = char_positions[start];size_t end_pos = (start + count < char_positions.size())? char_positions[start + count]: str.size();return str.substr(start_pos, end_pos - start_pos);}};int main() {std::string text = u8"C++编程语言学习";std::cout << "原始文本：" << text << std::endl;std::cout << "是否为有效UTF-8："<< (EncodingHelper::isValidUTF8(text) ? "是" : "否") << std::endl;// 截取"编程语言"（从第3个字符开始，取4个字符）std::string sub = EncodingHelper::substr(text, 3, 4);std::cout << "截取结果：" << sub << std::endl;return 0;}

五、最佳实践建议

5.1 编码规范

统一使用UTF-8：在所有源文件、配置文件中使用UTF-8编码
明确字符串字面量：使用 u8 前缀明确标识UTF-8字符串
编译器设置：配置编译器使用UTF-8编码
- GCC/Clang: -fexec-charset=UTF-8
- MSVC: /utf-8

5.2 跨平台开发

// 跨平台的控制台设置函数
void setupConsoleEncoding() {
#ifdef _WIN32
#include <windows.h>SetConsoleOutputCP(CP_UTF8);SetConsoleCP(CP_UTF8);#endif}int main() {setupConsoleEncoding();std::cout << u8"跨平台中文显示测试" << std::endl;return 0;}