26#include <seqan3/io/detail/record.hpp>
60template <detail::fields_specialisation selected_field_ids_ =
74 detail::type_list_of_sam_file_output_formats valid_formats_ = type_list<format_sam, format_bam>,
75 typename ref_ids_type = ref_info_not_given>
106 static_assert([] ()
constexpr
108 for (
field f : selected_field_ids::as_array)
109 if (!field_ids::contains(f))
113 "You selected a field that is not valid for alignment files, "
114 "please refer to the documentation of "
115 "seqan3::sam_file_output::field_ids for the accepted values.");
133 using iterator = detail::out_file_iterator<sam_file_output>;
185 primary_stream->rdbuf()->pubsetbuf(stream_buffer.data(), stream_buffer.size());
187 std::ios_base::out | std::ios::binary);
190 if (!primary_stream->good())
191 throw file_open_error{
"Could not open file " + filename.
string() +
" for writing."};
194 secondary_stream = detail::make_secondary_ostream(*primary_stream, filename);
197 detail::set_format(format, filename);
216 template <output_stream stream_type, sam_file_output_format file_format>
218 requires std::same_as<typename std::remove_reference_t<stream_type>::char_type,
stream_char_type>
221 file_format
const & SEQAN3_DOXYGEN_ONLY(format_tag),
223 primary_stream{&stream, stream_deleter_noop},
224 secondary_stream{&stream, stream_deleter_noop},
225 format{detail::sam_file_output_format_exposer<file_format>{}}
227 static_assert(list_traits::contains<file_format, valid_formats>,
228 "You selected a format that is not in the valid_formats of this file.");
232 template <output_stream stream_type, sam_file_output_format file_format>
234 requires std::same_as<typename std::remove_reference_t<stream_type>::char_type,
stream_char_type>
237 file_format
const & SEQAN3_DOXYGEN_ONLY(format_tag),
239 primary_stream{
new stream_type{std::move(stream)}, stream_deleter_default},
240 secondary_stream{&*primary_stream, stream_deleter_noop},
241 format{detail::sam_file_output_format_exposer<file_format>{}}
243 static_assert(list_traits::contains<file_format, valid_formats>,
244 "You selected a format that is not in the valid_formats of this file.");
277 template <
typename ref_
ids_type_, std::ranges::forward_range ref_lengths_type>
279 requires std::same_as<std::remove_reference_t<ref_ids_type_>, ref_ids_type>
282 ref_ids_type_ && ref_ids,
283 ref_lengths_type && ref_lengths,
288 initialise_header_information(ref_ids, ref_lengths);
312 template <output_stream stream_type,
314 typename ref_ids_type_,
315 std::ranges::forward_range ref_lengths_type>
317 requires std::same_as<std::remove_reference_t<ref_ids_type_>, ref_ids_type>
320 ref_ids_type_ && ref_ids,
321 ref_lengths_type && ref_lengths,
322 file_format
const & SEQAN3_DOXYGEN_ONLY(format_tag),
326 initialise_header_information(ref_ids, ref_lengths);
393 template <
typename record_t>
396 requires detail::record_like<record_t>
402 write_record(detail::get_or<field::header_ptr>(r,
nullptr),
406 detail::get_or<field::offset>(r, 0u),
408 detail::get_or<field::ref_id>(r, std::ignore),
410 detail::get_or<field::alignment>(r, default_align_t{}),
413 detail::get_or<field::mapq>(r, 0u),
414 detail::get_or<field::mate>(r, default_mate_t{}),
416 detail::get_or<field::evalue>(r, 0u),
417 detail::get_or<field::bit_score>(r, 0u));
441 template <
typename tuple_t>
451 write_record(detail::get_or<selected_field_ids::index_of(
field::header_ptr)>(t,
nullptr),
455 detail::get_or<selected_field_ids::index_of(
field::offset)>(t, 0u),
457 detail::get_or<selected_field_ids::index_of(
field::ref_id)>(t, std::ignore),
459 detail::get_or<selected_field_ids::index_of(
field::alignment)>(t, default_align_t{}),
462 detail::get_or<selected_field_ids::index_of(
field::mapq)>(t, 0u),
463 detail::get_or<selected_field_ids::index_of(
field::mate)>(t, default_mate_t{}),
465 detail::get_or<selected_field_ids::index_of(
field::evalue)>(t, 0u),
492 template <
typename arg_t,
typename ...arg_types>
522 template <
typename rng_t>
528 for (
auto &&
record : range)
561 template <
typename rng_t>
572 template <
typename rng_t>
591 return *secondary_stream;
607 if constexpr (std::same_as<ref_ids_type, ref_info_not_given>)
608 throw std::logic_error{
"Please construct your file with reference id and length information in order "
609 "to properly initialise the header before accessing it."};
631 stream_ptr_t primary_stream{
nullptr, stream_deleter_noop};
633 stream_ptr_t secondary_stream{
nullptr, stream_deleter_noop};
636 using format_type =
typename detail::variant_from_tags<
valid_formats,
637 detail::sam_file_output_format_exposer>::type;
644 using header_type = sam_file_header<std::conditional_t<std::same_as<ref_ids_type, ref_info_not_given>,
652 template <
typename ref_
ids_type_,
typename ref_lengths_type>
653 void initialise_header_information(ref_ids_type_ && ref_ids, ref_lengths_type && ref_lengths)
657 header_ptr = std::make_unique<sam_file_header<ref_ids_type>>(std::forward<ref_ids_type_>(ref_ids));
659 for (int32_t idx = 0; idx < std::ranges::distance(ref_ids); ++idx)
661 header_ptr->ref_id_info.emplace_back(ref_lengths[idx],
"");
663 if constexpr (std::ranges::contiguous_range<std::ranges::range_reference_t<ref_ids_type_>> &&
664 std::ranges::sized_range<std::ranges::range_reference_t<ref_ids_type_>> &&
665 std::ranges::borrowed_range<std::ranges::range_reference_t<ref_ids_type_>>)
678 template <
typename record_header_ptr_t,
typename ...pack_type>
679 void write_record(record_header_ptr_t && record_header_ptr, pack_type && ...remainder)
681 static_assert((
sizeof...(pack_type) == 15),
"Wrong parameter list passed to write_record.");
683 assert(!
format.valueless_by_exception());
688 if constexpr (!std::same_as<record_header_ptr_t, std::nullptr_t>)
690 f.write_alignment_record(*secondary_stream,
693 std::forward<pack_type>(remainder)...);
695 else if constexpr (std::same_as<ref_ids_type, ref_info_not_given>)
697 f.write_alignment_record(*secondary_stream,
700 std::forward<pack_type>(remainder)...);
704 f.write_alignment_record(*secondary_stream,
707 std::forward<pack_type>(remainder)...);
724template <detail::fields_specialisation selected_field_
ids>
731template <output_stream stream_type,
740template <output_stream stream_type,
749template <output_stream stream_type,
757template <output_stream stream_type,
764 std::ranges::forward_range ref_ids_type,
765 std::ranges::forward_range ref_lengths_type>
772template <std::ranges::forward_range ref_ids_type,
773 std::ranges::forward_range ref_lengths_type>
780template <output_stream stream_type,
781 std::ranges::forward_range ref_ids_type,
782 std::ranges::forward_range ref_lengths_type,
789template <output_stream stream_type,
790 std::ranges::forward_range ref_ids_type,
791 std::ranges::forward_range ref_lengths_type,
798template <output_stream stream_type,
799 std::ranges::forward_range ref_ids_type,
800 std::ranges::forward_range ref_lengths_type,
802sam_file_output(stream_type &&, ref_ids_type &&, ref_lengths_type &&, file_format
const &)
808template <output_stream stream_type,
809 std::ranges::forward_range ref_ids_type,
810 std::ranges::forward_range ref_lengths_type,
812sam_file_output(stream_type &, ref_ids_type &&, ref_lengths_type &&, file_format
const &)
A class for writing alignment files, e.g. SAM, BAL, BLAST, ...
Definition: output.hpp:77
sam_file_output(stream_type &, ref_ids_type &&, ref_lengths_type &&, file_format const &) -> sam_file_output< typename sam_file_output<>::selected_field_ids, type_list< file_format >, std::remove_reference_t< ref_ids_type > >
Deduces the valid format, and the ref_ids_type from input. selected_field_ids set to the default.
void const_reference
The const reference type (void).
Definition: output.hpp:127
sam_file_output(stream_type &&stream, ref_ids_type_ &&ref_ids, ref_lengths_type &&ref_lengths, file_format const &format_tag, selected_field_ids const &fields_tag=selected_field_ids{})
Construct from an existing stream and with specified format.
Definition: output.hpp:319
sam_file_output(stream_type &, ref_ids_type &&, ref_lengths_type &&, file_format const &, selected_field_ids const &) -> sam_file_output< selected_field_ids, type_list< file_format >, std::remove_reference_t< ref_ids_type > >
Deduces selected_field_ids, the valid format, and the ref_ids_type from input.
sam_file_output(std::filesystem::path const &, ref_ids_type &&, ref_lengths_type &&) -> sam_file_output< typename sam_file_output<>::selected_field_ids, typename sam_file_output<>::valid_formats, std::remove_reference_t< ref_ids_type > >
Deduces ref_ids_type from input. Valid formats, and selected_field_ids are set to the default.
void size_type
The size type (void).
Definition: output.hpp:129
friend sam_file_output & operator|(rng_t &&range, sam_file_output &f)
Write a range of records (or tuples) to the file.
Definition: output.hpp:562
sam_file_output(stream_type &&stream, file_format const &format_tag, selected_field_ids const &fields_tag=selected_field_ids{})
This is an overloaded member function, provided for convenience. It differs from the above function o...
Definition: output.hpp:236
sam_file_output(sam_file_output const &)=delete
Copy construction is explicitly deleted, because you can't have multiple access to the same file.
sam_file_output()=delete
Default constructor is explicitly deleted, you need to give a stream or file name.
sam_file_output & operator=(rng_t &&range)
Write a range of records (or tuples) to the file.
Definition: output.hpp:523
detail::out_file_iterator< sam_file_output > iterator
The iterator type of this view (an output iterator).
Definition: output.hpp:133
std::default_sentinel_t sentinel
The type returned by end().
Definition: output.hpp:137
char stream_char_type
Character type of the stream(s).
Definition: output.hpp:88
sam_file_output(stream_type &stream, file_format const &format_tag, selected_field_ids const &fields_tag=selected_field_ids{})
Construct from an existing stream and with specified format.
Definition: output.hpp:220
iterator begin() noexcept
Returns an iterator to current position in the file.
Definition: output.hpp:351
sentinel end() noexcept
Returns a sentinel for comparison with iterator.
Definition: output.hpp:370
sam_file_output(std::filesystem::path, selected_field_ids const &) -> sam_file_output< selected_field_ids, typename sam_file_output<>::valid_formats, ref_info_not_given >
Deduces selected_field_ids from input and sets sam_file_output::ref_ids_type to seqan3::detail::ref_i...
sam_file_output(stream_type &&, ref_ids_type &&, ref_lengths_type &&, file_format const &) -> sam_file_output< typename sam_file_output<>::selected_field_ids, type_list< file_format >, std::remove_reference_t< ref_ids_type > >
Deduces the valid format, and the ref_ids_type from input. selected_field_ids set to the default.
void emplace_back(arg_t &&arg, arg_types &&... args)
Write a record to the file by passing individual fields.
Definition: output.hpp:496
void push_back(record_t &&r)
Write a seqan3::record to the file.
Definition: output.hpp:394
sam_file_output & operator=(sam_file_output &&)=default
Move assignment is defaulted.
selected_field_ids_ selected_field_ids
A seqan3::fields list with the fields selected for the record.
Definition: output.hpp:84
valid_formats_ valid_formats
A seqan3::type_list with the possible formats.
Definition: output.hpp:86
sam_file_output & operator=(sam_file_output const &)=delete
Copy assignment is explicitly deleted, because you can't have multiple access to the same file.
sam_file_output(stream_type &&, ref_ids_type &&, ref_lengths_type &&, file_format const &, selected_field_ids const &) -> sam_file_output< selected_field_ids, type_list< file_format >, std::remove_reference_t< ref_ids_type > >
Deduces selected_field_ids, the valid format, and the ref_ids_type from input.
void reference
The reference type (void).
Definition: output.hpp:125
sam_file_output(stream_type &&, file_format const &) -> sam_file_output< typename sam_file_output<>::selected_field_ids, type_list< file_format >, ref_info_not_given >
Deduces the valid format from input and sets sam_file_output::ref_ids_type to seqan3::detail::ref_inf...
sam_file_output(std::filesystem::path filename, selected_field_ids const &fields_tag=selected_field_ids{})
Construct from filename.
Definition: output.hpp:181
void push_back(tuple_t &&t)
Write a record in form of a std::tuple to the file.
Definition: output.hpp:442
void value_type
The value type (void).
Definition: output.hpp:123
~sam_file_output()=default
Destructor is defaulted.
sam_file_output_options options
The options are public and its members can be set directly.
Definition: output.hpp:584
sam_file_output(sam_file_output &&)=default
Move construction is defaulted.
sam_file_output(stream_type &, file_format const &, selected_field_ids const &) -> sam_file_output< selected_field_ids, type_list< file_format >, ref_info_not_given >
Deduces selected_field_ids, and the valid format from input and sets sam_file_output::ref_ids_type to...
sam_file_output(stream_type &&, file_format const &, selected_field_ids const &) -> sam_file_output< selected_field_ids, type_list< file_format >, ref_info_not_given >
Deduces selected_field_ids, and the valid format from input and sets sam_file_output::ref_ids_type to...
sam_file_output(std::filesystem::path const &filename, ref_ids_type_ &&ref_ids, ref_lengths_type &&ref_lengths, selected_field_ids const &fields_tag=selected_field_ids{})
Construct from filename.
Definition: output.hpp:281
auto & header()
Access the file's header.
Definition: output.hpp:605
friend sam_file_output operator|(rng_t &&range, sam_file_output &&f)
This is an overloaded member function, provided for convenience. It differs from the above function o...
Definition: output.hpp:573
sam_file_output(std::filesystem::path const &, ref_ids_type &&, ref_lengths_type &&, selected_field_ids const &) -> sam_file_output< selected_field_ids, typename sam_file_output<>::valid_formats, std::remove_reference_t< ref_ids_type > >
Deduces selected_field_ids and ref_ids_type from input. valid_formats is set to the default.
void const_iterator
The const iterator type is void, because files are not const-iterable.
Definition: output.hpp:135
sam_file_output(stream_type &, file_format const &) -> sam_file_output< typename sam_file_output<>::selected_field_ids, type_list< file_format >, ref_info_not_given >
Deduces the valid format from input and sets sam_file_output::ref_ids_type to seqan3::detail::ref_inf...
The SAM tag dictionary class that stores all optional SAM fields.
Definition: sam_tag_dictionary.hpp:337
The <filesystem> header from C++17's standard library.
@ none
None of the flags below are set.
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.
@ ref_seq
The (reference) "sequence" information, usually a range of nucleotides or amino acids.
@ 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.
@ bit_score
The bit score (statistical significance indicator), unsigned value.
@ 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.
@ evalue
The e-value (length normalized bit score), double value.
@ 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 size_t size
The size of a type pack.
Definition: traits.hpp:151
Whether a type behaves like a tuple.
Provides exceptions used in the I/O module.
Provides various utility functions required only for output.
The main SeqAn3 namespace.
Definition: cigar_operation_table.hpp:2
Provides the seqan3::detail::out_file_iterator class template.
The <ranges> header from C++20's standard library.
Provides the seqan3::record template and the seqan3::field enum.
Provides seqan3::detail::record_like.
Provides seqan3::sam_file_output_options.
Provides helper data structures for the seqan3::sam_file_output.
A class template that holds a choice of seqan3::field.
Definition: record.hpp:128
The class template that file records are based on; behaves like a std::tuple.
Definition: record.hpp:191
Type tag which indicates that no reference information has been passed to the alignment file on const...
Definition: sam_flag.hpp:24
The options type defines various option members that influence the behavior of all or some formats.
Definition: output_options.hpp:26
Type that contains multiple types.
Definition: type_list.hpp:29
Provides traits for seqan3::type_list.
Provides seqan3::tuple_like.