dna5.hpp

Go to the documentation of this file.

// -----------------------------------------------------------------------------------------------------
// Copyright (c) 2022 deCODE Genetics
// Copyright (c) 2006-2020, Knut Reinert & Freie Universität Berlin
// Copyright (c) 2016-2020, Knut Reinert & MPI für molekulare Genetik
// This file may be used, modified and/or redistributed under the terms of the 3-clause BSD-License
// shipped with this file and also available at: https://github.com/biocpp/biocpp-core/blob/main/LICENSE.md
// -----------------------------------------------------------------------------------------------------
 
#pragma once
 
#include <vector>
 
#include <bio/alphabet/detail/to_lower.hpp>
#include <bio/alphabet/nucleotide/nucleotide_base.hpp>
 
// ------------------------------------------------------------------
// dna5
// ------------------------------------------------------------------
 
namespace bio::alphabet
{
 
class rna5;
 
class dna5 : public nucleotide_base<dna5, 5>
{
private:
    using base_t = nucleotide_base<dna5, 5>;
 
    friend base_t;
    friend base_t::base_t;
    friend rna5;
 
public:
    constexpr dna5() noexcept                         = default; 
    constexpr dna5(dna5 const &) noexcept             = default; 
    constexpr dna5(dna5 &&) noexcept                  = default; 
    constexpr dna5 & operator=(dna5 const &) noexcept = default; 
    constexpr dna5 & operator=(dna5 &&) noexcept      = default; 
    ~dna5() noexcept                                  = default; 
 
    using base_t::base_t;
 
    template <std::same_as<rna5> t> // Accept incomplete type
    constexpr dna5(t const & r) noexcept
    {
        assign_rank(r.to_rank());
    }
 
protected:
 
    static constexpr std::array<char_type, alphabet_size> rank_to_char{'A', 'C', 'G', 'N', 'T'};
 
    static constexpr std::array<rank_type, 256> char_to_rank = []() constexpr
    {
        std::array<rank_type, 256> ret{};
 
        // initialize with UNKNOWN
        ret.fill(3); // == 'N'
 
        // reverse mapping for characters and their lowercase
        for (size_t rnk = 0u; rnk < alphabet_size; ++rnk)
        {
            ret[rank_to_char[rnk]]                   = rnk;
            ret[detail::to_lower(rank_to_char[rnk])] = rnk;
        }
 
        // set U equal to T
        ret['U'] = ret['T'];
        ret['u'] = ret['t'];
 
        // iupac characters are implicitly "UNKNOWN"
        return ret;
    }();
 
    static const std::array<dna5, alphabet_size> complement_table;
};
 
} // namespace bio::alphabet
 
// ------------------------------------------------------------------
// literals
// ------------------------------------------------------------------
 
namespace bio::alphabet
{
 
inline namespace literals
{
 
consteval dna5 operator""_dna5(char const c)
{
    if (!char_is_valid_for<dna5>(c))
        throw std::invalid_argument{"Illegal character in character literal."};
 
    return dna5{}.assign_char(c);
}
 
template <meta::detail::literal_buffer_string str>
constexpr std::vector<dna5> operator""_dna5()
{
    return detail::string_literal<str, dna5>();
}
 
} // namespace literals
 
} // namespace bio::alphabet
 
// ------------------------------------------------------------------
// dna5 (deferred definition)
// ------------------------------------------------------------------
 
namespace bio::alphabet
{
 
constexpr std::array<dna5, dna5::alphabet_size> dna5::complement_table{
  'T'_dna5, // complement of 'A'_dna5
  'G'_dna5, // complement of 'C'_dna5
  'C'_dna5, // complement of 'G'_dna5
  'N'_dna5, // complement of 'N'_dna5
  'A'_dna5  // complement of 'T'_dna5
};
 
} // namespace bio::alphabet