Method generate

programs/obfuscator/Obfuscator.cpp:865–933

    size_t generate(char * data, size_t desired_size, size_t buffer_size,
        UInt64 seed, const char * determinator_data, size_t determinator_size)
    {
        code_points.resize(params.order);

        char * pos = data;
        char * end = data + buffer_size;

        while (pos < end)
        {
            Table::LookupResult it = {};

            size_t context_size = params.order;
            while (true)
            {
                it = table.find(hashContext(code_points.data() + code_points.size() - context_size, code_points.data() + code_points.size()));
                if (it && it->getMapped().total + it->getMapped().count_end != 0)
                    break;

                if (context_size == 0)
                    break;
                --context_size;
            }

            if (!it)
                throw Exception(ErrorCodes::LOGICAL_ERROR, "Logical error in markov model");

            size_t offset_from_begin_of_string = pos - data;
            size_t determinator_sliding_window_size = std::min(params.determinator_sliding_window_size, determinator_size);

            size_t determinator_sliding_window_overflow = offset_from_begin_of_string + determinator_sliding_window_size > determinator_size
                ? offset_from_begin_of_string + determinator_sliding_window_size - determinator_size : 0;

            const char * determinator_sliding_window_begin = determinator_data + offset_from_begin_of_string - determinator_sliding_window_overflow;

            SipHash hash;
            hash.update(seed);
            hash.update(determinator_sliding_window_begin, determinator_sliding_window_size);
            hash.update(determinator_sliding_window_overflow);
            UInt64 determinator = hash.get64();

            /// If string is greater than desired_size, increase probability of end.
            double end_probability_multiplier = 0;
            Int64 num_bytes_after_desired_size = (pos - data) - desired_size;

            if (num_bytes_after_desired_size > 0)
                end_probability_multiplier = std::pow(1.25, num_bytes_after_desired_size);

            CodePoint code = it->getMapped().sample(determinator, end_probability_multiplier);

            if (code == END)
                break;

            if (num_bytes_after_desired_size > 0)
            {
                /// Heuristic: break at ASCII non-alnum code point.
                /// This allows to be close to desired_size but not break natural looking words.
                if (code < 128 && !isAlphaNumericASCII(static_cast<char>(code)))