SeqAn3 3.2.0
The Modern C++ library for sequence analysis.
sam_tag_dictionary.hpp
Go to the documentation of this file.
1// -----------------------------------------------------------------------------------------------------
2// Copyright (c) 2006-2022, Knut Reinert & Freie Universität Berlin
3// Copyright (c) 2016-2022, Knut Reinert & MPI für molekulare Genetik
4// This file may be used, modified and/or redistributed under the terms of the 3-clause BSD-License
5// shipped with this file and also available at: https://github.com/seqan/seqan3/blob/master/LICENSE.md
6// -----------------------------------------------------------------------------------------------------
7
13#pragma once
14
15#include <concepts>
16#include <map>
17#include <variant>
18
19#include <seqan3/core/detail/template_inspection.hpp>
20#include <seqan3/utility/char_operations/predicate.hpp>
21#include <seqan3/utility/container/small_string.hpp>
22
23namespace seqan3::detail
24{
27using sam_tag_variant = std::variant<char,
28 int32_t,
29 float,
30 std::string,
31 std::vector<std::byte>,
32 std::vector<int8_t>,
33 std::vector<uint8_t>,
34 std::vector<int16_t>,
35 std::vector<uint16_t>,
36 std::vector<int32_t>,
37 std::vector<uint32_t>,
38 std::vector<float>>;
39
42constexpr char sam_tag_type_char[12] = {'A', 'i', 'f', 'Z', 'H', 'B', 'B', 'B', 'B', 'B', 'B', 'B'};
45constexpr char sam_tag_type_char_extra[12] = {'\0', '\0', '\0', '\0', '\0', 'c', 'C', 's', 'S', 'i', 'I', 'f'};
46} // namespace seqan3::detail
47
48namespace seqan3
49{
50
51inline namespace literals
52{
53
74#ifdef __cpp_nontype_template_parameter_class
75template <small_string<2> str> // TODO: better handling if too large string is provided?
76constexpr uint16_t operator""_tag()
77{
78#else // GCC/Clang extension
79# pragma GCC diagnostic push
80# pragma GCC diagnostic ignored "-Wpedantic"
81template <typename char_t, char_t... s>
82constexpr uint16_t operator""_tag()
83{
84 static_assert(std::same_as<char_t, char>, "Illegal SAM tag: Type must be char.");
85 constexpr small_string<sizeof...(s)> str{std::array<char, sizeof...(s)>{s...}};
86# pragma GCC diagnostic pop
87#endif
88
89 static_assert(str.size() == 2, "Illegal SAM tag: Exactly two characters must be given.");
90
91 constexpr char char0 = str[0];
92 constexpr char char1 = str[1];
93
94 static_assert((is_alpha(char0) && is_alnum(char1)), "Illegal SAM tag: a SAM tag must match /[A-Za-z][A-Za-z0-9]/.");
95
96 return static_cast<uint16_t>(char0) * 256 + static_cast<uint16_t>(char1);
97}
99
100} // namespace literals
101
179template <uint16_t tag_value>
180struct sam_tag_type
181{
183 using type = detail::sam_tag_variant;
184};
185
188template <uint16_t tag_value>
189using sam_tag_type_t = typename sam_tag_type<tag_value>::type;
190
191// clang-format off
193template <> struct sam_tag_type<"AM"_tag> { using type = int32_t; };
194template <> struct sam_tag_type<"AS"_tag> { using type = int32_t; };
195template <> struct sam_tag_type<"BC"_tag> { using type = std::string; };
196template <> struct sam_tag_type<"BQ"_tag> { using type = std::string; };
197template <> struct sam_tag_type<"BZ"_tag> { using type = std::string; };
198template <> struct sam_tag_type<"CB"_tag> { using type = std::string; };
199template <> struct sam_tag_type<"CC"_tag> { using type = std::string; };
200template <> struct sam_tag_type<"CG"_tag> { using type = std::vector<int32_t>; };
201template <> struct sam_tag_type<"CM"_tag> { using type = int32_t; };
202template <> struct sam_tag_type<"CO"_tag> { using type = std::string; };
203template <> struct sam_tag_type<"CP"_tag> { using type = int32_t; };
204template <> struct sam_tag_type<"CQ"_tag> { using type = std::string; };
205template <> struct sam_tag_type<"CR"_tag> { using type = std::string; };
206template <> struct sam_tag_type<"CS"_tag> { using type = std::string; };
207template <> struct sam_tag_type<"CT"_tag> { using type = std::string; };
208template <> struct sam_tag_type<"CY"_tag> { using type = std::string; };
209template <> struct sam_tag_type<"E2"_tag> { using type = std::string; };
210template <> struct sam_tag_type<"FI"_tag> { using type = int32_t; };
211template <> struct sam_tag_type<"FS"_tag> { using type = std::string; };
212template <> struct sam_tag_type<"FZ"_tag> { using type = std::vector<uint16_t>; };
213
214// template <> struct sam_tag_type<"GC"_tag> {};
215// template <> struct sam_tag_type<"GQ"_tag> {};
216// template <> struct sam_tag_type<"GS"_tag> {};
217
218template <> struct sam_tag_type<"H0"_tag> { using type = int32_t; };
219template <> struct sam_tag_type<"H1"_tag> { using type = int32_t; };
220template <> struct sam_tag_type<"H2"_tag> { using type = int32_t; };
221template <> struct sam_tag_type<"HI"_tag> { using type = int32_t; };
222template <> struct sam_tag_type<"IH"_tag> { using type = int32_t; };
223template <> struct sam_tag_type<"LB"_tag> { using type = std::string; };
224template <> struct sam_tag_type<"MC"_tag> { using type = std::string; };
225template <> struct sam_tag_type<"MD"_tag> { using type = std::string; };
226
227// template <> struct sam_tag_type<"MF"_tag> {};
228
229template <> struct sam_tag_type<"MI"_tag> { using type = std::string; };
230template <> struct sam_tag_type<"MQ"_tag> { using type = int32_t; };
231template <> struct sam_tag_type<"NH"_tag> { using type = int32_t; };
232template <> struct sam_tag_type<"NM"_tag> { using type = int32_t; };
233template <> struct sam_tag_type<"OC"_tag> { using type = std::string; };
234template <> struct sam_tag_type<"OP"_tag> { using type = int32_t; };
235template <> struct sam_tag_type<"OQ"_tag> { using type = std::string; };
236template <> struct sam_tag_type<"OX"_tag> { using type = std::string; };
237template <> struct sam_tag_type<"PG"_tag> { using type = std::string; };
238template <> struct sam_tag_type<"PQ"_tag> { using type = int32_t; };
239template <> struct sam_tag_type<"PT"_tag> { using type = std::string; };
240template <> struct sam_tag_type<"PU"_tag> { using type = std::string; };
241template <> struct sam_tag_type<"Q2"_tag> { using type = std::string; };
242template <> struct sam_tag_type<"QT"_tag> { using type = std::string; };
243template <> struct sam_tag_type<"QX"_tag> { using type = std::string; };
244template <> struct sam_tag_type<"R2"_tag> { using type = std::string; };
245template <> struct sam_tag_type<"RG"_tag> { using type = std::string; };
246template <> struct sam_tag_type<"RT"_tag> { using type = std::string; };
247template <> struct sam_tag_type<"RX"_tag> { using type = std::string; };
248
249// template <> struct sam_tag_type<"S2"_tag> {};
250
251template <> struct sam_tag_type<"SA"_tag> { using type = std::string; };
252template <> struct sam_tag_type<"SM"_tag> { using type = int32_t; };
253
254// template <> struct sam_tag_type<"SQ"_tag> {};
255
256template <> struct sam_tag_type<"TC"_tag> { using type = int32_t; };
257template <> struct sam_tag_type<"U2"_tag> { using type = std::string; };
258template <> struct sam_tag_type<"UQ"_tag> { using type = int32_t; };
260// clang-format on
261
342class sam_tag_dictionary : public std::map<uint16_t, detail::sam_tag_variant>
343{
344private:
346 using base_type = std::map<uint16_t, detail::sam_tag_variant>;
347
348public:
350 using variant_type = detail::sam_tag_variant;
351
368 template <uint16_t tag>
369 requires (!std::same_as<sam_tag_type_t<tag>, variant_type>)
370 auto & get() &
371 {
372 if ((*this).count(tag) == 0)
373 (*this)[tag] = sam_tag_type_t<tag>{}; // set correct type if tag is not set yet on
374
375 return std::get<sam_tag_type_t<tag>>((*this)[tag]);
376 }
377
379 template <uint16_t tag>
380 requires (!std::same_as<sam_tag_type_t<tag>, variant_type>)
381 auto && get() &&
382 {
383 if ((*this).count(tag) == 0)
384 (*this)[tag] = sam_tag_type_t<tag>{}; // set correct type if tag is not set yet on
385
386 return std::get<sam_tag_type_t<tag>>(std::move((*this)[tag]));
387 }
388
391 template <uint16_t tag>
392 requires (!std::same_as<sam_tag_type_t<tag>, variant_type>)
393 auto const & get() const &
394 {
395 return std::get<sam_tag_type_t<tag>>((*this).at(tag));
396 }
397
400 template <uint16_t tag>
401 requires (!std::same_as<sam_tag_type_t<tag>, variant_type>)
402 auto const && get() const &&
403 {
404 return std::get<sam_tag_type_t<tag>>(std::move((*this).at(tag)));
405 }
407};
408
409} // namespace seqan3
seqan3::sam_tag_dictionary
The SAM tag dictionary class that stores all optional SAM fields.
Definition: sam_tag_dictionary.hpp:343
seqan3::sam_tag_dictionary::get
auto && get() &&
Uses std::map::operator[] for access and default initializes new keys.
Definition: sam_tag_dictionary.hpp:381
seqan3::sam_tag_dictionary::get
auto & get() &
Uses std::map::operator[] for access and default initializes new keys.
Definition: sam_tag_dictionary.hpp:370
seqan3::sam_tag_dictionary::get
auto const && get() const &&
Uses std::map::at() for access and throws when the key is unknown.
Definition: sam_tag_dictionary.hpp:402
seqan3::sam_tag_dictionary::get
auto const & get() const &
Uses std::map::at() for access and throws when the key is unknown.
Definition: sam_tag_dictionary.hpp:393
seqan3::small_string
Implements a small string that can be used for compile time computations.
Definition: small_string.hpp:44
seqan3::is_alnum
constexpr auto is_alnum
Checks whether c is a alphanumeric character.
Definition: predicate.hpp:197
seqan3::is_alpha
constexpr auto is_alpha
Checks whether c is a alphabetical character.
Definition: predicate.hpp:214
seqan3
The main SeqAn3 namespace.
Definition: aligned_sequence_concept.hpp:29
predicate.hpp
Provides character predicates for tokenisation.
small_string.hpp
A constexpr string implementation to manipulate string literals at compile time.
seqan3::sam_tag_type
The generic base class.
Definition: sam_tag_dictionary.hpp:181
seqan3::sam_tag_type::sam_tag_type_t
typename sam_tag_type< tag_value >::type sam_tag_type_t
Short cut helper for seqan3::sam_tag_type::type.
Definition: sam_tag_dictionary.hpp:189
template_inspection.hpp
Provides type traits for working with templates.