UCS2String UTF8toUCS2String(const UTF8String& s)
{
UCS2String result;
UCS4 c;
int len = 0;
// Compute the encoded length by simply counting all non-continuation bytes.
// In case of malformed sequences we might get the number wrong, but this is just an estimate
// used to pre-allocate memory.
for (UTF8String::const_iterator i = s.begin(); i != s.end(); ++i)
if (((*i) & 0xC0) != 0x80)
++len;
result.reserve(len);
for(UTF8String::const_iterator i = s.begin(); i != s.end(); )
{
c = DecodeUTF8Character(i);
if ((c > 0xFFFFu) || (c == 0x0000u))
// Not valid in UCS2, or we can't deal with it; substitute with a replacement character.
c = 0xFFFDu;
result.push_back(c);
}
return result;
}
UTF8String Filename::getExtension(bool includeDot) const
{
const UTF8String fname = getFilename();
UTF8String::const_reverse_iterator it = std::find(fname.rbegin(), fname.rend(), '.');
if (it!=fname.rend())
return UTF8String(it.base() - ((includeDot) ? 1 : 0), fname.end());
else
return UTF8String("");
}