转自:http://blog.youkuaiyun.com/henren555/article/details/9295907
1. utf8转std::string
转换过程:先将utf8转双字节Unicode编码,再通过WideCharToMultiByte将宽字符转换为多字节。
//-----------------------------------------------------------------------
std::string UTF8_To_string(const std::string & str)
{
int nwLen = MultiByteToWideChar(CP_UTF8, 0, str.c_str(), -1, NULL, 0);
wchar_t * pwBuf = new wchar_t[nwLen + 1];//一定要加1,不然会出现尾巴
memset(pwBuf, 0, nwLen * 2 + 2);
MultiByteToWideChar(CP_UTF8, 0, str.c_str(), str.length(), pwBuf, nwLen);
int nLen = WideCharToMultiByte(CP_ACP, 0, pwBuf, -1, NULL, NULL, NULL, NULL);
char * pBuf = new char[nLen + 1];
memset(pBuf, 0, nLen + 1);
WideCharToMultiByte(CP_ACP, 0, pwBuf, nwLen, pBuf, nLen, NULL, NULL);
std::string retStr = pBuf;
delete []pBuf;
delete []pwBuf;
pBuf = NULL;
pwBuf = NULL;
return retStr;
}
//////////////////////////////////////////////////////////////////////////
//////////////////////////////////////////////////////////////////////////
// [8/19/2009 Leezhm]
// translate ascii characters to utf-8 characters
2.std::string转utf8字符串
转换过程:与1过程相反
//------------------------------------------------------------------------
std::string string_To_UTF8(const std::string & str)
{
int nwLen = ::MultiByteToWideChar(CP_ACP, 0, str.c_str(), -1, NULL, 0);
wchar_t * pwBuf = new wchar_t[nwLen + 1];//一定要加1,不然会出现尾巴
ZeroMemory(pwBuf, nwLen * 2 + 2);
::MultiByteToWideChar(CP_ACP, 0, str.c_str(), str.length(), pwBuf, nwLen);
int nLen = ::WideCharToMultiByte(CP_UTF8, 0, pwBuf, -1, NULL, NULL, NULL, NULL);
char * pBuf = new char[nLen + 1];
ZeroMemory(pBuf, nLen + 1);
::WideCharToMultiByte(CP_UTF8, 0, pwBuf, nwLen, pBuf, nLen, NULL, NULL);
std::string retStr(pBuf);
delete []pwBuf;
delete []pBuf;
pwBuf = NULL;
pBuf = NULL;
return retStr;
}
本文介绍如何在UTF-8编码与标准C++字符串之间进行转换。具体包括从UTF-8转换到标准字符串的过程,及反之亦然的方法。转换过程中涉及到使用Windows API函数MultiByteToWideChar和WideCharToMultiByte。
5468

被折叠的 条评论
为什么被折叠?



