utf8_to_utf16

17down voteaccepted

Here's some code. Only lightly tested and there's probably a few improvements. Call this function to convert a UTF-8 string to a UTF-16 wstring. If it thinks the input string is not UTF-8 then it will throw an exception, otherwise it returns the equivalent UTF-16 wstring.

std::wstring utf8_to_utf16(const std::string& utf8)
{
    std::vector<unsigned long> unicode;
    size_t i = 0;
    while (i < utf8.size())
    {
        unsigned long uni;
        size_t todo;
        bool error = false;
        unsigned char ch = utf8[i++];
        if (ch <= 0x7F)
        {
            uni = ch;
            todo = 0;
        }
        else if (ch <= 0xBF)
        {
            throw std::logic_error("not a UTF-8 string");
        }
        else if (ch <= 0xDF)
        {
            uni = ch&0x1F;
            todo = 1;
        }
        else if (ch <= 0xEF)
        {
            uni = ch&0x0F;
            todo = 2;
        }
        else if (ch <= 0xF7)
        {
            uni = ch&0x07;
            todo = 3;
        }
        else
        {
            throw std::logic_error("not a UTF-8 string");
        }
        for (size_t j = 0; j < todo; ++j)
        {
            if (i == utf8.size())
                throw std::logic_error