bool StringICompare(const std::basic_string<CharT> &lhs, const std::basic_string<CharT> &rhs)
{
if (lhs.length() == rhs.length()) {
return std::equal(lhs.cbegin(), lhs.cend(), rhs.cbegin(), ICompare);
} else {
return false;
}
}
basic_str_wrap( std::basic_string<Char_T> const& str )
:fst( &*str.cbegin() )
,lst( &*str.cend() )
,cstr( str.c_str() )
{}
bool UTF8string::utf8_is_valid_() const noexcept
{
const std::basic_string<unsigned char> U8STRING = toUstring( _utf8string );
auto it = U8STRING.begin();
const auto ITEND = U8STRING.cend();
while ( it < ITEND )
{
if ( ( 0xF8 & *it ) == 0xF0 && *it <= 0xF4 )
{
// The UTF-8 codepoint begin with 0b11110xxx -> 4-byte codepoint
// If the iterator reach the end of the string before the
// end of the 4-byte codepoint -> invalid string
if ( ( it + 1 ) == ITEND || ( it + 2 ) == ITEND || ( it + 3 ) == ITEND )
return false;
// Each of the following bytes is a value
// between 0x80 and 0xBF
if ( ( ( 0xC0 & *( it + 1 ) ) != 0x80 ) || ( ( 0xC0 & *( it + 2 ) ) != 0x80 )
|| ( ( 0xC0 & *( it + 3 ) ) != 0x80 ) )
{
return false;
}
// If the first byte of the sequence is 0xF0
// then the first continuation byte must be between 0x90 and 0xBF
// otherwise, if the byte is 0xF4
// then the first continuation byte must be between 0x80 and 0x8F
if ( *it == 0xF0 )
{
if ( *( it + 1 ) < 0x90 || *( it + 1 ) > 0xBF )
return false;
}
else if ( *it == 0xF4 )
{
if ( *( it + 1 ) < 0x80 || *( it + 1 ) > 0x8F )
return false;
}
it += 4; // Jump to the next codepoint
}
else if ( ( 0xF0 & *it ) == 0xE0 )
{
// The UTF-8 codepoint begin with 0b1110xxxx -> 3-byte codepoint
if ( ( it + 1 ) == ITEND || ( it + 2 ) == ITEND )
return false;
// Each of the following bytes starts with
// 0b10xxxxxx in a valid string
if ( ( ( 0xC0 & *( it + 1 ) ) != 0x80 ) || ( ( 0xC0 & *( it + 2 ) ) != 0x80 ) )
return false;
// If the first byte of the sequence is 0xE0
// then the first continuation byte must be between 0xA0 and 0xBF
// otherwise, if the byte is 0xF4
// then the first continuation byte must be between 0x80 and 0x9F
if ( *it == 0xE0 )
{
if ( *( it + 1 ) < 0xA0 || *( it + 1 ) > 0xBF )
return false;
}
else if ( *it == 0xED )
{
if ( *( it + 1 ) > 0x9F )
return false;
}
it += 3;
}
else if ( ( 0xE0 & *it ) == 0xC0 )
{
// The UTF-8 codepoint begin with 0b110xxxxx -> 2-byte codepoint
if ( ( it + 1 ) == ITEND )
return false;
// The following byte starts with 0b10xxxxxx in a valid string
if ( ( 0xC0 & *( it + 1 ) ) != 0x80 )
return false;
it += 2;
}
else if ( ( 0x80 & *it ) == 0x00 )
{
// The UTF-8 codepoint begin with 0b0xxxxxxx -> 1-byte codepoint
it += 1;
}
else
{
// Invalid codepoint
return false;
}
}
return true;
}
