A string tokenizer in C++ that allows multiple separators

Question

Is there a way to tokenize a string in C++ with multiple separators? In C# I would have done:

string[] tokens = \"adsl, dkks; dk\".Split(new [] { \",\", \" \", \         


        

Answer 1

Here is my version (not heavily tested (yet)):

std::vector split(std::string const& s,
    std::vector const& delims)
{
    std::vector parts;

    std::vector> poss;
    poss.reserve(delims.size());

    std::string::size_type beg = 0;

    for(;;)
    {
        poss.clear();

        std::string::size_type idx = 0;
        for(auto const& delim: delims)
        {
            if(auto end = s.find(delim, beg) + 1)
                poss.emplace_back(end - 1, idx);
            ++idx;
        }

        if(poss.empty())
            break;

        std::sort(std::begin(poss), std::end(poss));

        auto old_beg = beg;

        for(auto pos: poss)
        {
            parts.emplace_back(std::begin(s) + beg,
                std::begin(s) + old_beg + pos.first);
            beg = pos.first + delims[pos.second].size();
        }
    }

    if(beg < s.size())
        parts.emplace_back(std::begin(s) + beg, std::end(s));

    return parts;
}