boost::property_tree::json_parser and two-byte wide characters

Question

Introduction

std::string text = \"á\";

\"á\" is two-byte character (assuming a UTF-8 encoding).
So following line prints 2.

Answer 1

Support above Basic Multilingual Plane:

    template
std::basic_string create_escapes(const std::basic_string &s)
{
    std::basic_string result;
    typename std::basic_string::const_iterator b = s.begin();
    typename std::basic_string::const_iterator e = s.end();
    while (b != e)
    {
        if (*b == 0x20 || *b == 0x21 || (*b >= 0x23 && *b <= 0x2E) ||
            (*b >= 0x30 && *b <= 0x5B) || (*b >= 0x5D && *b <= 0x80))
            result += *b;
        else if (*b == Ch('\b')) result += Ch('\\'), result += Ch('b');
        else if (*b == Ch('\f')) result += Ch('\\'), result += Ch('f');
        else if (*b == Ch('\n')) result += Ch('\\'), result += Ch('n');
        else if (*b == Ch('\r')) result += Ch('\\'), result += Ch('r');
        else if (*b == Ch('/')) result += Ch('\\'), result += Ch('/');
        else if (*b == Ch('"'))  result += Ch('\\'), result += Ch('"');
        else if (*b == Ch('\\')) result += Ch('\\'), result += Ch('\\');
        else
        {
            const char * hexdigits = "0123456789ABCDEF";

            typedef typename make_unsigned::type UCh;
            unsigned long u = static_cast(static_cast(*b));

            if (u <= 0xFFFF)
            {            
                int d1 = u / 4096; u -= d1 * 4096;
                int d2 = u / 256; u -= d2 * 256;
                int d3 = u / 16; u -= d3 * 16;
                int d4 = u;

                result += Ch('\\'); result += Ch('u');
                result += Ch(hexdigits[d1]); result += Ch(hexdigits[d2]);
                result += Ch(hexdigits[d3]); result += Ch(hexdigits[d4]);
            }
            else
            {
                u = (((static_cast(static_cast(*b)) - 0x10000) >> 10) & 0x3ff) + 0xd800;

                int d1 = u / 4096; u -= d1 * 4096;
                int d2 = u / 256; u -= d2 * 256;
                int d3 = u / 16; u -= d3 * 16;
                int d4 = u;

                result += Ch('\\'); result += Ch('u');
                result += Ch(hexdigits[d1]); result += Ch(hexdigits[d2]);
                result += Ch(hexdigits[d3]); result += Ch(hexdigits[d4]);

                u = ((static_cast(static_cast(*b)) - 0x10000) & 0x3ff) + 0xdc00;

                d1 = u / 4096; u -= d1 * 4096;
                d2 = u / 256; u -= d2 * 256;
                d3 = u / 16; u -= d3 * 16;
                d4 = u;

                result += Ch('\\'); result += Ch('u');
                result += Ch(hexdigits[d1]); result += Ch(hexdigits[d2]);
                result += Ch(hexdigits[d3]); result += Ch(hexdigits[d4]);
            }
        }
        ++b;
    }
    return result;
}