//string类型的utf-8字符串转为CString类型的unicode字符串
CString ConvertUTF8ToCString( std::string utf8str )
{
/* 预转换,得到所需空间的大小 */
int nLen = ::MultiByteToWideChar( CP_UTF8, NULL,
utf8str.data(), utf8str.size(), NULL, 0 );
/* 转换为Unicode */
std::wstring wbuffer;
wbuffer.resize( nLen );
::MultiByteToWideChar( CP_UTF8, NULL, utf8str.data(), utf8str.size(),
(LPWSTR) (wbuffer.data() ), wbuffer.length() );
#ifdef UNICODE
return(CString( wbuffer.data(), wbuffer.length() ) );
#else
/*
* 转换为ANSI
* 得到转换后长度
*/
nLen = WideCharToMultiByte( CP_ACP, 0,
wbuffer.data(), wbuffer.length(), NULL, 0, NULL, NULL );
std::string ansistr;
ansistr.resize( nLen );
/* 把unicode转成ansi */
WideCharToMultiByte( CP_ACP, 0, (LPWSTR) (wbuffer.data() ), wbuffer.length(),
(LPSTR) (ansistr.data() ), ansistr.size(), NULL, NULL );
return(CString( ansistr.data(), ansistr.length() ) );
#endif
}
//CString类型的unicode字符串转为string类型的utf-8字符串
string _UnicodeToUtf8(CString Unicodestr)
{
wchar_t* unicode = Unicodestr.AllocSysString();
int len;
len = WideCharToMultiByte(CP_UTF8, 0, unicode, -1, NULL, 0, NULL, NULL);
char *szUtf8 = (char*)malloc(len + 1);
memset(szUtf8, 0, len + 1);
WideCharToMultiByte(CP_UTF8, 0, unicode, -1, szUtf8, len, NULL, NULL);
string result = szUtf8;
free(szUtf8);
return result;
}
//string转const char*
string str = "abc";
const char* result= str.c_str();
//CString转char*
CString str;
USES_CONVERSION;
char * result= T2A(str);
//判断字符是否为UTF-8编码方式,是就返回true,否则返回false
bool _is_str_utf8(string src)
{
const char* str= src.c_str();
unsigned int nBytes = 0;//UFT8可用1-6个字节编码,ASCII用一个字节
unsigned char chr = *str;
bool bAllAscii = true;
for (unsigned int i = 0; str[i] != '\0'; ++i){
chr = *(str + i);
//判断是否ASCII编码,如果不是,说明有可能是UTF8,ASCII用7位编码,最高位标记为0,0xxxxxxx
if (nBytes == 0 && (chr & 0x80) != 0){
bAllAscii = false;
}
if (nBytes == 0) {
//如果不是ASCII码,应该是多字节符,计算字节数
if (chr >= 0x80) {
if (chr >= 0xFC && chr <= 0xFD){
nBytes = 6;
}
else if (chr >= 0xF8){
nBytes = 5;
}
else if (chr >= 0xF0){
nBytes = 4;
}
else if (chr >= 0xE0){
nBytes = 3;
}
else if (chr >= 0xC0){
nBytes = 2;
}
else{
return false;
}
nBytes--;
}
}
else{
//多字节符的非首字节,应为 10xxxxxx
if ((chr & 0xC0) != 0x80){
return false;
}
//减到为零为止
nBytes--;
}
}
//违反UTF8编码规则
if (nBytes != 0) {
return false;
}
if (bAllAscii){ //如果全部都是ASCII, 也是UTF8
return true;
}
return true;
}
//string转CString
string str = "1234";
CString result = CString(str.c_str());
|