編碼轉換的方法(UNICODE/ASCII/UTF-8)

參考了網上一些方法：所謂的短字符,就是用8bit來表示的字符,典型的應用是ASCII碼.  而寬字符,顧名思義,就是用16bit表示的字符,典型的有UNICODE.
   常用的代碼頁有CP_ACP和CP_UTF8兩個。
   使用CP_ACP代碼頁就實現了ANSI與Unicode之間的轉換。
   使用CP_UTF8代碼頁就實現了UTF-8與Unicode之間的轉換。

 

1.  ASCII  to  Unicode(CP_ACP)

std::wstring string2wstring_CP_ACP(std::string str)
{
  std::wstring result = L"";
  int len = MultiByteToWideChar(CP_ACP, 0, str.c_str(), str.size(), NULL, 0);
  TCHAR* buffer = new TCHAR[len + 1];//保存到Unicode串
  MultiByteToWideChar(CP_ACP, 0, str.c_str(), str.size(), buffer, len);
  buffer[len] = '\0';
  result.append(buffer);
  delete[] buffer;
  return result;
}

2. Unicode to ASCII(CP_ACP)

std::string wstring2string_CP_ACP(std::wstring wstr)
{
  std::string result = "";
  int len = WideCharToMultiByte(CP_ACP, 0, wstr.c_str(), wstr.size(), NULL, 0, NULL, NULL);
  char* buffer = new char [len + 1]; //保存ANSI串
  WideCharToMultiByte(CP_ACP, 0, wstr.c_str(), wstr.size(), buffer, len,
                      NULL, NULL);
  buffer[len] = '\0';
  result.append(buffer);
  delete[] buffer;
  return result;
}

3. UTF-8 to Unicode(CP_UTF8)

std::wstring string2wstring_CP_UTF8(std::string str)
{
  std::wstring result = L"";
  int len = MultiByteToWideChar(CP_UTF8, 0, str.c_str(), str.size(), NULL, 0);
  TCHAR* buffer = new TCHAR[len + 1];//保存到Unicode串
  MultiByteToWideChar(CP_UTF8, 0, str.c_str(), str.size(), buffer, len);
  buffer[len] = '\0';
  result.append(buffer);
  delete[] buffer;
  return result;
}

4.  Unicode to UTF-8(CP_UTF8)

std::string wstring2string_CP_UTF8(std::wstring wstr)
{
  std::string result = "";
  int len = WideCharToMultiByte(CP_UTF8, 0, wstr.c_str(), wstr.size(), NULL, 0, NULL, NULL);
  char* buffer = new char [len + 1]; 
  WideCharToMultiByte(CP_UTF8, 0, wstr.c_str(), wstr.size(), buffer, len,
                      NULL, NULL);
  buffer[len] = '\0';
  result.append(buffer);
  delete[] buffer;
  return result;
}