文章摘要
这篇文章介绍了几个C++函数，用于在UTF-8、Unicode和ASCII编码之间进行转换。这些函数包括： 1. **Utf82Unicode**：将UTF-8编码的字符串转换为Unicode wide string。2. **WideByte2AcsI**：将Unicode字符串转换为ASCII字符串。3. **UTF_82ASCII**：通过先将UTF-8编码转换为Unicode，再将其转换为ASCII字符串。4. **AcsI2WideByte**：将ASCII字符串转换为Unicode。5. **Unicode2Utf8**：将Unicode字符串转换为UTF-8编码的字符串。6. **ASCII2Utf8**：通过先将ASCII字符串转换为Unicode，再将其转换为UTF-8编码的字符串。 这些函数的核心内容是字符编码之间的转换过程，特别关注了不同编码格式之间的转换机制和实现细节。文章通过具体的代码示例展示了如何在C++中实现这些字符编码的转换，提供了对字符编码转换的深入理解。
//UTF-8转Unicode
std::wstring Utf82Unicode(const std::string& utf8string)
{
int widesize=::MultiByteToWideChar(CP_UTF8, 0, utf8string.c_str(), -1, NULL, 0);
if (widesize==ERROR_NO_UNICODE_TRANSLATION)
{
throw std::exception(“Invalid UTF-8 sequence.”);
}
if (widesize==0)
{
throw std::exception(“Error in conversion.”);
}
std::vector
int convresult=::MultiByteToWideChar(CP_UTF8, 0, utf8string.c_str(), -1, &resultstring[0], widesize);
if (convresult !=widesize)
{
throw std::exception(“La falla!”);
}
return std::wstring(&resultstring[0]);
}
//unicode 转为 ascii
string WideByte2Acsi(wstring& wstrcode)
{
int asciisize=::WideCharToMultiByte(CP_OEMCP, 0, wstrcode.c_str(), -1, NULL, 0, NULL, NULL);
if (asciisize==ERROR_NO_UNICODE_TRANSLATION)
{
throw std::exception(“Invalid UTF-8 sequence.”);
}
if (asciisize==0)
{
throw std::exception(“Error in conversion.”);
}
std::vector
int convresult=::WideCharToMultiByte(CP_OEMCP, 0, wstrcode.c_str(), -1, &resultstring[0], asciisize, NULL, NULL);
if (convresult !=asciisize)
{
throw std::exception(“La falla!”);
}
return std::string(&resultstring[0]);
}
//utf-8 转 ascii
string UTF_82ASCII(string& strUtf8Code)
{
string strRet(“”);
//先把 utf8 转为 unicode
wstring wstr=Utf82Unicode(strUtf8Code);
//最后把 unicode 转为 ascii
strRet=WideByte2Acsi(wstr);
return strRet;
}
///////////////////////////////////////////////////////////////////////
//ascii 转 Unicode
wstring Acsi2WideByte(string& strascii)
{
int widesize=MultiByteToWideChar (CP_ACP, 0, (char*)strascii.c_str(), -1, NULL, 0);
if (widesize==ERROR_NO_UNICODE_TRANSLATION)
{
throw std::exception(“Invalid UTF-8 sequence.”);
}
if (widesize==0)
{
throw std::exception(“Error in conversion.”);
}
std::vector
int convresult=MultiByteToWideChar (CP_ACP, 0, (char*)strascii.c_str(), -1, &resultstring[0], widesize);
if (convresult !=widesize)
{
throw std::exception(“La falla!”);
}
return std::wstring(&resultstring[0]);
}
//Unicode 转 Utf8
std::string Unicode2Utf8(const std::wstring& widestring)
{
int utf8size=::WideCharToMultiByte(CP_UTF8, 0, widestring.c_str(), -1, NULL, 0, NULL, NULL);
if (utf8size==0)
{
throw std::exception(“Error in conversion.”);
}
std::vector
int convresult=::WideCharToMultiByte(CP_UTF8, 0, widestring.c_str(), -1, &resultstring[0], utf8size, NULL, NULL);
if (convresult !=utf8size)
{
throw std::exception(“La falla!”);
}
return std::string(&resultstring[0]);
}
//ascii 转 Utf8
string ASCII2UTF_8(string& strAsciiCode)
{
string strRet(“”);
//先把 ascii 转为 unicode
wstring wstr=Acsi2WideByte(strAsciiCode);
//最后把 unicode 转为 utf8
strRet=Unicode2Utf8(wstr);
return strRet;
}
© 版权声明
文章版权归作者所有，未经允许请勿转载。
