为了支持Unicode编码,需要多字节与宽字节之间的相互转换。这两个系统函数在使用时需要指定代码页,在实际应用过程中遇到乱码问题,然后重新阅读《Windows核心编程》,总结出正确的用法。
WideCharToMultiByte的代码页用来标记与新转换的字符串相关的代码页。
MultiByteToWideChar的代码页用来标记与一个多字节字符串相关的代码页。
常用的代码页由CP_ACP和CP_UTF8两个。
使用CP_ACP代码页就实现了ANSI与Unicode之间的转换。
使用CP_UTF8代码页就实现了UTF-8与Unicode之间的转换。
下面是代码实现:
1. ANSI to Unicode
wstring ANSIToUnicode( const string& str ) { int len = 0; len = str.length(); int unicodeLen = ::MultiByteToWideChar( CP_ACP, 0, str.c_str(), -1, NULL,0 ); wchar_t * pUnicode; pUnicode = new wchar_t[unicodeLen+1]; memset(pUnicode,0,(unicodeLen+1)*sizeof(wchar_t)); ::MultiByteToWideChar( CP_ACP, 0, str.c_str(), -1, (LPWSTR)pUnicode, unicodeLen ); wstring rt; rt = ( wchar_t* )pUnicode; delete pUnicode; return rt; }
2. Unicode to ANSI
string UnicodeToANSI( const wstring& str ) { char* pElementText; int iTextLen; // wide char to multi char iTextLen = WideCharToMultiByte( CP_ACP, 0,str.c_str(), -1, NULL, 0,NULL, NULL ); pElementText = new char[iTextLen + 1]; memset( ( void* )pElementText, 0, sizeof( char ) * ( iTextLen + 1 ) ); ::WideCharToMultiByte( CP_ACP, 0, str.c_str(), -1, pElementText, iTextLen, NULL, NULL ); string strText; strText = pElementText; delete[] pElementText; return strText; }
3. UTF-8 to Unicode
wstring UTF8ToUnicode( const string& str ) { int len = 0; len = str.length(); int unicodeLen = ::MultiByteToWideChar( CP_UTF8, 0, str.c_str(),-1, NULL, 0 ); wchar_t * pUnicode; pUnicode = new wchar_t[unicodeLen+1]; memset(pUnicode,0,(unicodeLen+1)*sizeof(wchar_t)); ::MultiByteToWideChar( CP_UTF8, 0, str.c_str(), -1, (LPWSTR)pUnicode, unicodeLen ); wstring rt; rt = ( wchar_t* )pUnicode; delete pUnicode; return rt; }
4. Unicode to UTF-8
string UnicodeToUTF8( const wstring& str ) { char* pElementText; int iTextLen; // wide char to multi char iTextLen = WideCharToMultiByte( CP_UTF8, 0,str.c_str(), -1,NULL, 0, NULL, NULL ); pElementText = new char[iTextLen + 1]; memset( ( void* )pElementText, 0, sizeof( char ) * ( iTextLen + 1 ) ); ::WideCharToMultiByte( CP_UTF8, 0, str.c_str(), -1, pElementText,iTextLen, NULL, NULL ); string strText; strText = pElementText; delete[] pElementText; return strText; }
不用ansi C
char m_szFile[260]; int len = WideCharToMultiByte(CP_ACP, 0, m_strFilePath, m_strFilePath.GetLength(), NULL, 0, NULL, NULL); char * pFileName = new char[len + 1]; WideCharToMultiByte(CP_ACP, 0, m_strFilePath, m_strFilePath.GetLength() + 1, pFileName, len + 1, NULL, NULL); pFileName[len] = '\0'; delete[] pFileName;
改写的
LPCSTR UnicodeToANSI(CString &str) { char* pElementText; int iTextLen; iTextLen = WideCharToMultiByte(CP_ACP, 0, str, -1, NULL, 0, NULL, NULL); pElementText = new char[iTextLen + 1]; memset((void*)pElementText, 0, sizeof(char)* (iTextLen + 1)); ::WideCharToMultiByte(CP_ACP, 0, str, -1, pElementText, iTextLen, NULL, NULL); LPCSTR strText; strText = pElementText; delete[] pElementText; return strText; } CString ANSIToUnicode(const LPCSTR& str) { int len = 0; len = strlen( str); int unicodeLen = ::MultiByteToWideChar(CP_ACP, 0, str, -1, NULL, 0); wchar_t * pUnicode; pUnicode = new wchar_t[unicodeLen + 1]; memset(pUnicode, 0, (unicodeLen + 1)*sizeof(wchar_t)); ::MultiByteToWideChar(CP_ACP, 0, str, -1, (LPWSTR)pUnicode, unicodeLen); CString rt; rt = (wchar_t*)pUnicode; delete pUnicode; return rt; }