34#include <seqan3/io/detail/record.hpp>
131 requires std::same_as<typename t::ref_sequences, ref_info_not_given> ||
requires ()
138 (!std::same_as<typename t::ref_sequences, ref_info_not_given> ||
140 requires std::ranges::forward_range<std::ranges::range_reference_t<typename t::ref_ids>>;
141 requires std::ranges::forward_range<typename t::ref_ids>;
182template <
typename ref_sequences_t = ref_info_not_given,
typename ref_
ids_t = std::deque<std::
string>>
197 template <
typename _sequence_alphabet>
201 template <
typename _
id_alphabet>
208 template <
typename _quality_alphabet>
273 using dummy_ref_type =
decltype(
views::repeat_n(
typename traits_type::sequence_alphabet{},
size_t{}) |
277 using ref_sequence_unsliced_type =
278 detail::lazy_conditional_t<std::ranges::range<typename traits_type::ref_sequences const>,
279 detail::lazy<std::ranges::range_reference_t,
280 typename traits_type::ref_sequences
const>,
284 using ref_sequence_sliced_type =
decltype(std::declval<ref_sequence_unsliced_type>() |
views::slice(0, 0));
293 typename traits_type::sequence_alphabet>;
295 using id_type =
typename traits_type::template id_container<char>;
306 ref_sequence_sliced_type>;
326 typename traits_type::quality_alphabet>;
341 decltype(std::declval<sequence_type &>() |
views::slice(0, 0))>,
399 static_assert([] ()
constexpr
401 for (
field f : selected_field_ids::as_array)
402 if (!field_ids::contains(f))
406 "You selected a field that is not valid for alignment files, please refer to the documentation "
407 "of sam_file_input::field_ids for the accepted values.");
429 using iterator = detail::in_file_iterator<sam_file_input>;
473 init_by_filename(std::move(filename));
495 template <input_stream stream_t, sam_file_input_format file_format>
497 requires std::same_as<typename std::remove_reference_t<stream_t>::char_type,
stream_char_type>
500 file_format
const & SEQAN3_DOXYGEN_ONLY(format_tag),
502 primary_stream{&stream, stream_deleter_noop}
504 init_by_format<file_format>();
508 template <input_stream stream_t, sam_file_input_format file_format>
510 requires std::same_as<typename std::remove_reference_t<stream_t>::char_type,
stream_char_type>
513 file_format
const & SEQAN3_DOXYGEN_ONLY(format_tag),
515 primary_stream{
new stream_t{std::move(stream)}, stream_deleter_default}
517 init_by_format<file_format>();
544 typename traits_type::ref_ids & ref_ids,
545 typename traits_type::ref_sequences & ref_sequences,
550 set_references(ref_ids, ref_sequences);
552 init_by_filename(std::move(filename));
580 template <input_stream stream_t, sam_file_input_format file_format>
582 typename traits_type::ref_ids & ref_ids,
583 typename traits_type::ref_sequences & ref_sequences,
584 file_format
const & SEQAN3_DOXYGEN_ONLY(format_tag),
586 primary_stream{&stream, stream_deleter_noop}
589 set_references(ref_ids, ref_sequences);
591 init_by_format<file_format>();
595 template <input_stream stream_t, sam_file_input_format file_format>
597 typename traits_type::ref_ids & ref_ids,
598 typename traits_type::ref_sequences & ref_sequences,
599 file_format
const & SEQAN3_DOXYGEN_ONLY(format_tag),
601 primary_stream{
new stream_t{std::move(stream)}, stream_deleter_default}
604 set_references(ref_ids, ref_sequences);
606 init_by_format<file_format>();
612 typename traits_type::ref_ids &&,
613 typename traits_type::ref_sequences &&,
616 template <input_stream stream_t, sam_file_input_format file_format>
618 typename traits_type::ref_ids &&,
619 typename traits_type::ref_sequences &&,
648 if (!first_record_was_read)
651 first_record_was_read =
true;
722 if (!first_record_was_read)
725 first_record_was_read =
true;
737 primary_stream->rdbuf()->pubsetbuf(stream_buffer.data(), stream_buffer.size());
739 std::ios_base::in | std::ios::binary);
741 if (!primary_stream->good())
744 secondary_stream = detail::make_secondary_istream(*primary_stream, filename);
745 detail::set_format(format, filename);
749 template <
typename format_type>
750 void init_by_format()
752 static_assert(list_traits::contains<format_type, valid_formats>,
753 "You selected a format that is not in the valid_formats of this file.");
755 format = detail::sam_file_input_format_exposer<format_type>{};
756 secondary_stream = detail::make_secondary_istream(*primary_stream);
783 stream_ptr_t primary_stream{
nullptr, stream_deleter_noop};
785 stream_ptr_t secondary_stream{
nullptr, stream_deleter_noop};
788 bool first_record_was_read{
false};
793 using format_type =
typename detail::variant_from_tags<
valid_formats,
794 detail::sam_file_input_format_exposer>::type;
804 typename traits_type::ref_sequences
const * reference_sequences_ptr{
nullptr};
816 template <std::ranges::forward_range ref_sequences_t>
817 void set_references(
typename traits_type::ref_ids & ref_ids, ref_sequences_t && ref_sequences)
819 assert(std::ranges::distance(ref_ids) == std::ranges::distance(ref_sequences));
822 reference_sequences_ptr = &ref_sequences;
825 for (int32_t idx = 0; idx < std::ranges::distance(ref_ids); ++idx)
827 header_ptr->ref_id_info.emplace_back(std::ranges::distance(ref_sequences[idx]),
"");
829 if constexpr (std::ranges::contiguous_range<std::ranges::range_reference_t<
830 typename traits_type::ref_ids>> &&
831 std::ranges::sized_range<std::ranges::range_reference_t<typename traits_type::ref_ids>> &&
832 std::ranges::borrowed_range<std::ranges::range_reference_t<typename traits_type::ref_ids>>)
834 auto &&
id = header_ptr->ref_ids()[idx];
839 header_ptr->ref_dict[header_ptr->ref_ids()[idx]] = idx;
846 void read_next_record()
849 record_buffer.clear();
850 detail::get_or_ignore<field::header_ptr>(record_buffer) = header_ptr.get();
860 auto call_read_func = [
this] (
auto & ref_seq_info)
864 f.read_alignment_record(*secondary_stream,
868 detail::get_or_ignore<field::seq>(record_buffer),
869 detail::get_or_ignore<field::qual>(record_buffer),
870 detail::get_or_ignore<field::id>(record_buffer),
871 detail::get_or_ignore<field::offset>(record_buffer),
872 detail::get_or_ignore<field::ref_seq>(record_buffer),
873 detail::get_or_ignore<field::ref_id>(record_buffer),
874 detail::get_or_ignore<field::ref_offset>(record_buffer),
875 detail::get_or_ignore<field::alignment>(record_buffer),
876 detail::get_or_ignore<field::cigar>(record_buffer),
877 detail::get_or_ignore<field::flag>(record_buffer),
878 detail::get_or_ignore<field::mapq>(record_buffer),
879 detail::get_or_ignore<field::mate>(record_buffer),
880 detail::get_or_ignore<field::tags>(record_buffer),
881 detail::get_or_ignore<field::evalue>(record_buffer),
882 detail::get_or_ignore<field::bit_score>(record_buffer));
886 assert(!
format.valueless_by_exception());
888 if constexpr (!std::same_as<typename traits_type::ref_sequences, ref_info_not_given>)
889 call_read_func(*reference_sequences_ptr);
891 call_read_func(std::ignore);
903template <input_stream stream_type, sam_file_input_format file_format, detail::fields_specialisation selected_field_
ids>
910template <input_stream stream_type, sam_file_input_format file_format, detail::fields_specialisation selected_field_
ids>
917template <input_stream stream_type, sam_file_input_format file_format>
924template <input_stream stream_type, sam_file_input_format file_format>
931template <std::ranges::forward_range ref_ids_t,
932 std::ranges::forward_range ref_sequences_t,
941template <std::ranges::forward_range ref_ids_t,
942 std::ranges::forward_range ref_sequences_t>
950template <input_stream stream_type,
951 std::ranges::forward_range ref_ids_t,
952 std::ranges::forward_range ref_sequences_t,
962template <input_stream stream_type,
963 std::ranges::forward_range ref_ids_t,
964 std::ranges::forward_range ref_sequences_t,
974template <input_stream stream_type,
975 std::ranges::forward_range ref_ids_t,
976 std::ranges::forward_range ref_sequences_t,
978sam_file_input(stream_type && stream, ref_ids_t &, ref_sequences_t &, file_format
const &)
985template <input_stream stream_type,
986 std::ranges::forward_range ref_ids_t,
987 std::ranges::forward_range ref_sequences_t,
989sam_file_input(stream_type & stream, ref_ids_t &, ref_sequences_t &, file_format
const &)
Provides seqan3::aa27, container aliases and string literals.
Provides the seqan3::cigar alphabet.
Provides alphabet adaptations for standard char types.
A combined alphabet that can hold values of either of its alternatives..
Definition: alphabet_variant.hpp:129
The 15 letter DNA alphabet, containing all IUPAC smybols minus the gap..
Definition: dna15.hpp:51
The five letter DNA alphabet of A,C,G,T and the unknown character N..
Definition: dna5.hpp:51
A gap decorator allows the annotation of sequences with gap symbols while leaving the underlying sequ...
Definition: gap_decorator.hpp:83
Quality type for traditional Sanger and modern Illumina Phred scores..
Definition: phred42.hpp:47
The SAM tag dictionary class that stores all optional SAM fields.
Definition: sam_tag_dictionary.hpp:337
The <concepts> header from C++20's standard library.
Provides seqan3::dna15, container aliases and string literals.
Provides seqan3::dna5, container aliases and string literals.
The <filesystem> header from C++17's standard library.
Provides seqan3::gap_decorator.
sam_flag
An enum flag that describes the properties of an aligned read (given as a SAM record).
Definition: sam_flag.hpp:76
field
An enumerator for the fields used in file formats.
Definition: record.hpp:63
@ flag
The alignment flag (bit information), uint16_t value.
@ ref_offset
Sequence (seqan3::field::ref_seq) relative start position (0-based), unsigned value.
@ alignment
The (pairwise) alignment stored in an object that models seqan3::detail::pairwise_alignment.
@ cigar
The cigar vector (std::vector<seqan3::cigar>) representing the alignment in SAM/BAM format.
@ mapq
The mapping quality of the seqan3::field::seq alignment, usually a Phred-scaled score.
@ offset
Sequence (seqan3::field::seq) relative start position (0-based), unsigned value.
@ mate
The mate pair information given as a std::tuple of reference name, offset and template length.
@ header_ptr
A pointer to the seqan3::sam_file_header object storing header information.
@ ref_id
The identifier of the (reference) sequence that seqan3::field::seq was aligned to.
@ id
The identifier, usually a string.
@ tags
The optional tags in the SAM format, stored in a dictionary.
@ seq
The "sequence", usually a range of nucleotides or amino acids.
@ qual
The qualities, usually in Phred score notation.
constexpr bool contains
Whether a type occurs in a type list or not.
Definition: traits.hpp:231
decltype(detail::transform< trait_t >(list_t{})) transform
Apply a transformation trait to every type in the list and return a seqan3::type_list of the results.
Definition: traits.hpp:471
constexpr size_t size
The size of a type pack.
Definition: traits.hpp:151
constexpr auto slice
A view adaptor that returns a half-open interval on the underlying range.
Definition: slice.hpp:183
constexpr auto repeat_n
A view factory that repeats a given value n times.
Definition: repeat_n.hpp:91
Provides the seqan3::detail::in_file_iterator class template.
The generic alphabet concept that covers most data types used in ranges.
Resolves to std::ranges::explicitly_convertible_to<type1, type2>().
A more refined container concept than seqan3::container.
Refines seqan3::alphabet and adds assignability.
A concept that indicates whether a writable alphabet represents quality scores.
Provides exceptions used in the I/O module.
The main SeqAn3 namespace.
Definition: cigar_operation_table.hpp:2
Provides seqan3::phred42 quality scores.
Provides quality alphabet composites.
The <ranges> header from C++20's standard library.
Provides seqan3::views::repeat_n.
Provides seqan3::sam_record.
Provides helper data structures for the seqan3::sam_file_output.
Provides seqan3::views::slice.
A class template that holds a choice of seqan3::field.
Definition: record.hpp:128
Thrown if there is an unspecified filesystem or stream error while opening, e.g. permission problem.
Definition: exception.hpp:39
Type that contains multiple types.
Definition: type_list.hpp:29
Provides traits for seqan3::type_list.
Provides seqan3::tuple_like.