Function readCSVStringInto

src/IO/ReadHelpers.cpp:725–819

template <typename Vector>
void readCSVStringInto(Vector & s, ReadBuffer & buf, const FormatSettings::CSV & settings)
{
    if (buf.eof())
        throwReadAfterEOF();

    const char delimiter = settings.delimiter;
    const char maybe_quote = *buf.position();

    /// Emptiness and not even in quotation marks.
    if (maybe_quote == delimiter)
        return;

    if ((settings.allow_single_quotes && maybe_quote == '\'') || (settings.allow_double_quotes && maybe_quote == '"'))
    {
        ++buf.position();

        /// The quoted case. We are looking for the next quotation mark.
        while (!buf.eof())
        {
            char * next_pos = reinterpret_cast<char *>(memchr(buf.position(), maybe_quote, buf.buffer().end() - buf.position()));

            if (nullptr == next_pos)
                next_pos = buf.buffer().end();

            appendToStringOrVector(s, buf, next_pos);
            buf.position() = next_pos;

            if (!buf.hasPendingData())
                continue;

            /// Now there is a quotation mark under the cursor. Is there any following?
            ++buf.position();
            if (buf.eof())
                return;

            if (*buf.position() == maybe_quote)
            {
                s.push_back(maybe_quote);
                ++buf.position();
                continue;
            }

            return;
        }
    }
    else
    {
        /// Unquoted case. Look for delimiter or \r or \n.
        while (!buf.eof())
        {
            char * next_pos = buf.position();

            [&]()
            {
#ifdef __SSE2__
                auto rc = _mm_set1_epi8('\r');
                auto nc = _mm_set1_epi8('\n');
                auto dc = _mm_set1_epi8(delimiter);