id	summary	reporter	owner	description	type	status	milestone	component	version	severity	resolution	keywords	cc
7743	utf_traits::decode does not check for correct UTF-8 trailing bytes	peter.klotz@…	Artyom Beilis	"This program shows the erroneous behavior. An exception should be thrown since 0xdf is the start byte of a 2-byte sequence. However it is followed by a 1-byte character.

Boost.Locale does not throw an exception.


#include <iostream>
#include <stdexcept>
#include <boost/locale/utf.hpp>

template<typename T>
std::basic_string<T> checkUtf(const std::basic_string<T>& p_str)
{
    const std::string encodingType = sizeof(T) == 1 ? ""UTF-8"" : (sizeof(T) == 2 ? ""UTF-16"" : ""UTF-32"");
    typename std::basic_string<T>::const_iterator it = p_str.begin();
    while (it != p_str.end()) {
        const boost::locale::utf::code_point cp = boost::locale::utf::utf_traits<T>::decode(it, p_str.end());
        if (cp == boost::locale::utf::illegal)
            throw std::runtime_error(""Source string contains illegal "" + encodingType + "" byte sequences"");
        else if (cp == boost::locale::utf::incomplete)
            throw std::runtime_error(""Source string contains imcomplete "" + encodingType + "" byte sequences"");
    }
    return p_str;
}

int main(void)
{
    try
    {
        checkUtf(""A""+std::string(1,0xdf)+""A"");
        return 0;
    }
    catch (const std::exception& e) {
        std::cout << e.what() << std::endl;
    }
    return 1;
}
"	Bugs	closed	To Be Determined	locale	Boost 1.52.0	Showstopper	fixed