gsoap中文介绍见:
http://blog.youkuaiyun.com/darkone/archive/2006/12/14/1442525.aspx
http://dev.youkuaiyun.com/article/83869.shtm
最近用gSoap作了个项目,测试时发现对英字符串处理正常,但不能正常处理中文字符串,感到纳闷。如果gSoap有问题,早就有人提出来并且改正了,所以应该是我的程序的问题。在网上搜了下,也没找到合理的解释,所以就自己读了它的代码,终于找到了解决方法,现在写出来,给那些有此疑问的朋友一点帮助,也方便自己将来查询。
中文乱码与locale有关,这里给出两种解决方法:
一、设置locale
1、setlocale(LC_ALL, "");//设置程序locale为系统默认(我的系统是zh_CN.utf8),gsoap内部进行编码转换依赖于locale,所以必须设置为中文环境。
2、gSoap初始化 gSoap生成的代理类名字为:CSmsProxy
CSmsProxy soapRequest(SOAP_C_MBSTRING);
下面同一般编程。gSoap会自动把字符串转换为正确的编码。
二、不设置locale,使用默认的"C" locale,程序中传给gSoap、从gSoap接收的字符串都使用utf8编码
代理类初始化: CSmsProxy soapRequest(SOAP_C_UTFSTRING);
下面同一般编程。gSoap会把字符串当成utf8编码处理。
下面附带gb2312与utf8编码之间的转换函数:
//gb2312转utf8
void Gb2312ToUtf8(char* pstrOut, u32 dwOutLen, const char* pstrIn, u32 dwInLen)
{
#ifdef WIN32
int i = MultiByteToWideChar(CP_ACP, 0, pstrIn, -1, NULL, 0);
wchar_t * strSrc = new wchar_t[i+1];
MultiByteToWideChar(CP_ACP, 0, pstrIn, -1, strSrc, i);
i = WideCharToMultiByte(CP_UTF8, 0, strSrc, -1, NULL, 0, NULL, NULL);
if (i >= dwOutLen)
{
i = dwOutLen - 1;
}
WideCharToMultiByte(CP_UTF8, 0, strSrc, -1, pstrOut, i, NULL, NULL);
delete strSrc;
#else
iconv_t iConv = iconv_open("utf-8", "gb2312");
iconv(iConv, (char **)&pstrIn, (size_t *)&dwInLen, (char **)&pstrOut, (size_t *)&dwOutLen);
iconv_close(iConv);
#endif
}
//utf8转gb2312
void Utf8ToGb2312(char* pstrOut, u32 dwOutLen, const char* pstrIn, u32 dwInLen)
{
if (NULL == pstrOut)
{
return ;
}
#ifdef WIN32
int i = MultiByteToWideChar(CP_UTF8, 0, pstrIn, -1, NULL, 0);
wchar_t * strSrc = new wchar_t[i+1];
MultiByteToWideChar(CP_UTF8, 0, pstrIn, -1, strSrc, i);
i = WideCharToMultiByte(CP_ACP, 0, strSrc, -1, NULL, 0, NULL, NULL);
if (i >= dwOutLen)
{
i = dwOutLen - 1;
}
WideCharToMultiByte(CP_ACP, 0, strSrc, -1, pstrOut, i, NULL, NULL);
delete strSrc;
#else
iconv_t iConv = iconv_open("gb2312", "utf-8");
iconv(iConv, (char **)&pstrIn, (size_t *)&dwInLen, (char **)&pstrOut, (size_t *)&dwOutLen);
iconv_close(iConv);
#endif
}
//gb2312转Unicode
void Gb2312ToUnicode(wchar_t* pstrOut, u32 dwOutLen, const char* pstrIn, u32 dwInLen)
{
if (NULL == pstrOut)
{
return ;
}
#ifdef WIN32
u32 i = MultiByteToWideChar(CP_ACP, 0, pstrIn, -1, NULL, 0);
if (i >= dwOutLen)
{
i = dwOutLen - 1;
}
MultiByteToWideChar(CP_ACP, 0, pstrIn, -1, pstrOut, i);
#else
iconv_t iConv = iconv_open("unicode", "gb2312");
iconv(iConv, (char**)pstrIn, &dwInLen, (char**)pstrOut, &dwOutLen);
iconv_close(iConv);
#endif
}
//Unicode转Gb2312
void UnicodeToGb2312(char* pstrOut, u32 dwOutLen, const wchar_t* pstrIn, u32 dwInLen)
{
if (NULL == pstrOut)
{
return ;
}
#ifdef WIN32
u32 i = WideCharToMultiByte(CP_ACP, 0, pstrIn, -1, NULL, 0, NULL, NULL);
if (i >= dwOutLen)
{
i = dwOutLen - 1;
}
WideCharToMultiByte(CP_ACP, 0, pstrIn, -1, pstrOut, i, 0, 0);
#else
iconv_t iConv = iconv_open("gb2312", "unicode");
iconv(iConv, (char**)pstrIn, &dwInLen, (char**)pstrOut, &dwOutLen);
iconv_close(iConv);
#endif
}
//utf8转Unicode
void Utf8ToUnicode(wchar_t* pstrOut, u32 dwOutLen, const char* pstrIn, u32 dwInLen)
{
if (NULL == pstrOut)
{
return ;
}
#ifdef WIN32
u32 i = MultiByteToWideChar(CP_UTF8, 0, pstrIn, -1, NULL, 0);
if (i >= dwOutLen)
{
i = dwOutLen - 1;
}
MultiByteToWideChar(CP_UTF8, 0, pstrIn, -1, pstrOut, i);
#else
iconv_t iConv = iconv_open("unicode", "utf-8");
iconv(iConv, (char**)pstrIn, &dwInLen, (char**)pstrOut, &dwOutLen);
iconv_close(iConv);
#endif
}