多字节编码转为UTF8编码 & UTF8编码转为多字节

最新推荐文章于 2025-07-10 19:51:14 发布

原创最新推荐文章于 2025-07-10 19:51:14 发布 · 6.9k 阅读

3 ·

本内容遵循CC 4.0 BY-SA版权协议

标签

#null #string #delete

C++数据类型转换专栏收录该内容

11 篇文章

订阅专栏

这篇博客介绍了如何在C++中将GBK编码转换为UTF8编码，以及将UTF8编码转换回GBK编码。通过使用Windows API函数MultiByteToWideChar和WideCharToMultiByte实现转换，并在main函数中给出了示例代码。

开发环境：VS2008

#include <iostream>
#include <windows.h>
#include <string>

void ConvertGBKToUtf8(std::string& amp, std::string strGBK)
{
int len=MultiByteToWideChar(CP_ACP, 0, (LPCSTR)strGBK.c_str(), -1, NULL,0);
unsigned short * wszUtf8 = new unsigned short[len+1];
memset(wszUtf8, 0, len * 2 + 2);
MultiByteToWideChar(CP_ACP, 0, (LPCSTR)strGBK.c_str(), -1, (LPWSTR)wszUtf8, len);
len = WideCharToMultiByte(CP_UTF8, 0, (LPCWSTR)wszUtf8, -1, NULL, 0, NULL, NULL);
char *szUtf8=new char[len + 1];
memset(szUtf8, 0, len + 1);
WideCharToMultiByte (CP_UTF8, 0, (LPCWSTR)wszUtf8, -1, szUtf8, len, NULL,NULL);
//strGBK = szUtf8;
amp=szUtf8;
delete[] szUtf8;
delete[] wszUtf8;
}

void ConvertUtf8ToGBK(std::string&amp, std::string strUtf8)
{
int len=MultiByteToWideChar(CP_UTF8, 0, (LPCSTR)strUtf8.c_str(), -1, NULL,0);
unsigned short * wszGBK = new unsigned short[len+1];
memset(wszGBK, 0, len * 2 + 2);
MultiByteToWideChar(CP_UTF8, 0, (LPCSTR)strUtf8.c_str(), -1, (LPWSTR)wszGBK, len);
len = WideCharToMultiByte(CP_ACP, 0, (LPCWSTR)wszGBK, -1, NULL, 0, NULL, NULL);
char *szGBK=new char[len + 1];
memset(szGBK, 0, len + 1);
WideCharToMultiByte (CP_ACP, 0, (LPCWSTR)wszGBK, -1, szGBK, len, NULL,NULL);
//strUtf8 = szGBK;
amp=szGBK;
delete[] szGBK;
delete[] wszGBK;
}

int main(int argc, char *argv)
{
std::string amp;
std::string strGBK = "china 中国人民！！";
ConvertGBKToUtf8(amp, strGBK);

std::wcout << "/////////////////////////////////// " << std::endl;

std::string temp;
ConvertUtf8ToGBK(temp, amp);
std::cout << "Utf8ToGBK : " << temp << std::endl;
system("PAUSE");
}