docu

Author: smehringer

include/bio/map_io/all.hpp

@@ -0,0 +1,28 @@
+// -----------------------------------------------------------------------------------------------------
+// Copyright (c) 2006-2020, Knut Reinert & Freie Universität Berlin
+// Copyright (c) 2016-2020, Knut Reinert & MPI für molekulare Genetik
+// Copyright (c) 2020-2021, deCODE Genetics
+// 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/seqan/b.i.o./blob/master/LICENSE
+// -----------------------------------------------------------------------------------------------------
+
+/*!\file
+ * \brief Meta-include that includes the whole Variant I/O module.
+ * \author Svenja Mehringer <svenja.mehringer AT fu-berlin.de>
+ */
+
+#pragma once
+
+/*!\defgroup map_io Map I/O
+ * \ingroup bio
+ * \brief Reader and writer for SAM and BAM files.
+ *
+ * This module provides high-level APIs to read and write SAM and BAM files.
+ *
+ * To read files, have a look at bio::map_io::reader and to write files have a look at bio::map_io::writer.
+ *
+ */
+
+/*!\namespace bio::map_io
+ * \brief Namespace for the Map I/O module.
+ */

include/bio/map_io/header.hpp

@@ -40,7 +40,15 @@ namespace bio::map_io
  * \ingroup map_io
  * \details
  *
- * TODO
+ * Each header line begins with the character `@` followed by one of the two-letter header record type codes
+ * defined in this section. In the header, each line is tab-delimited and, apart from `@CO` lines, each data field
+ * follows a format `TAG:VALUE` where TAG is a two-character string that defines the format and content of
+ * VALUE. Thus header lines match `/^@(HD|SQ|RG|PG)(\t[A-Za-z][A-Za-z0-9]:[ -~]+)+$/` or are comment lines staring
+ * with `@CO` followed by a tab and any character sequence.
+ * Within each (non-`@CO`) header line, no field tag may appear more than once and the order in which the fields
+ * appear is not significant.
+ *
+ * \sa https://samtools.github.io/hts-specs/SAMv1.pdf
  */
 class header
 {
@@ -57,7 +65,6 @@ class header
     header & operator=(header &&) = default;        //!< Defaulted.
 
     /*!\brief Construct from a range of reference ids.
-     * \param[in] The plain text header.
      * \param[in] ref_ids The range over reference ids to redirect the pointer at.
      */
     template <typename ref_ids_type> // todo: restrict value type to be std::string_view constructible
@@ -95,6 +102,7 @@ class header
     //!\brief The reference sequence names.
     std::vector<std::string_view> reference_names;
 
+    //!\brief Additional information to the reference sequence (same ordering as `reference_names`).
     std::vector<std::tuple<int32_t, std::string>> reference_names_info{};
 
     //!\brief The mapping of reference name to position in the reference_names range and the rnames_info() range.
@@ -103,6 +111,7 @@ class header
     //!\brief Whether reference sequence names were given to the header on construction.
     bool reference_names_given_on_construction{false};
 
+    //!\brief Print a B.I.O warning message with current line number in diagnostic.
     /* [[noreturn]] compiler says this returns something...? */ void warning(auto const &... messages) const
     {
         // if (print_warnings)
@@ -114,22 +123,22 @@ class header
         // }
     }
 public:
-    /*!\name [@HD] File-level meta data
+    /*!\name [HD] File-level meta data
      * \brief You can directly edit these member variables.
      * \{
      */
-    std::string format_version{}; //!< [@HD VN] The file format version. Note: this is overwritten by our formats on output.
-    std::string sorting{};        //!< [@HD SO] The sorting of the file. SAM: [unknown, unsorted, queryname, coordinate].
-    std::string grouping{};       //!< [@HD GO] The grouping of the file. SAM: [none, query, reference].
-    std::string subsorting{};     //!< [@HD SS] The sub-sorting of the file. SAM: [unknown, unsorted, queryname, coordinate](:[A-Za-z0-9_-]+)+.
+    std::string format_version{}; //!< [HD VN] The file format version. Note: this is overwritten by our formats on output.
+    std::string sorting{};        //!< [HD SO] The sorting of the file. SAM: [unknown, unsorted, queryname, coordinate].
+    std::string grouping{};       //!< [HD GO] The grouping of the file. SAM: [none, query, reference].
+    std::string subsorting{};     //!< [HD SS] The sub-sorting of the file. SAM: [unknown, unsorted, queryname, coordinate]`(:[A-Za-z0-9_-]+)+`.
     //!\}
 
-    /*!\name [@SQ] Reference sequence dictionary
+    /*!\name [SQ] Reference sequence dictionary
      * \brief You **CANNOT** directly edit these member variables. Please use the respective modifiers.
      * \{
      */
 
-    /*!\brief [@SQ SN] Reference sequence names
+    /*!\brief [SQ SN] Reference sequence names
      *
      * \details
      *
@@ -139,11 +148,11 @@ class header
      * 1) Reference id information is provided on construction. In this case, no copy is made but this function
      *    gives you a reference to the provided range. When reading the header or the records, their reference
      *    information will be checked against the given input.
-     * 2) No reference information is provided on construction but the \@SQ tags are present in the header.
+     * 2) No reference information is provided on construction but the `@SQ` tags are present in the header.
      *    In this case, the reference id information is extracted from the header and this member function provides
      *    access to them. When reading the records, their reference id information will be checked against the header
      *    information.
-     * 3) No reference information is provided on construction an no \@SQ tags are present in the header.
+     * 3) No reference information is provided on construction an no `@SQ` tags are present in the header.
      *    In this case, the reference information is parsed from the records field::ref_id and stored in the header.
      *    This member function then provides access to the unique list of reference names encountered in the records.
      */
@@ -152,11 +161,11 @@ class header
         return reference_names;
     }
 
-    /*!\brief [@SQ LN,AH,AN,AS,M5,SP,UR] Reference sequence auxiliary information
+    /*!\brief [SQ LN,AH,AN,AS,M5,SP,UR] Reference sequence auxiliary information
      *
      * \details
      *
-     * The reference information store the length (\@LN tag) and
+     * The reference information store the length (`@LN` tag) and
      * additional information of each reference sequence in the file. The record
      * must then store only the index of the reference.
      * The name and length information are required if the header is provided
@@ -166,17 +175,17 @@ class header
      *
      * The additional information (2nd tuple entry) must model
      * the following formatting rules: The information is given in a tab separated
-     * TAG:VALUE format, where TAG must be one of [AH, AN, AS, m5, SP, UR].
+     * `TAG:VALUE` format, where TAG must be one of [AH, AN, AS, m5, SP, UR].
      * The following information and rules apply for each tag (taken from the SAM specs):
      *
      * * **AH:** Indicates that this sequence is an alternate locus. The value is the locus in the primary assembly for
-     *           which this sequence is an alternative, in the format 'chr:start-end', 'chr' (if known), or '*' (if
-     *           unknown), where 'chr' is a sequence in the primary assembly. Must not be present on sequences in the
+     *           which this sequence is an alternative, in the format `chr:start-end`, `chr` (if known), or `*` (if
+     *           unknown), where `chr` is a sequence in the primary assembly. Must not be present on sequences in the
      *           primary assembly.
      * * **AN:** Alternative reference sequence names. A comma-separated list of alternative names that tools may use
      *           when referring to this reference sequence. These alternative names are not used elsewhere within the
      *           SAM file; in  particular, they must not appear in alignment records’ RNAME or RNEXT fields. regular
-     *           expression : name (, name )* where name is [0-9A-Za-z][0-9A-Za-z*+.@ \|-]*
+     *           expression : `name (, name )*` where name is `[0-9A-Za-z][0-9A-Za-z*+.@ \|-]*`.
      * * **AS:** Genome assembly identifier.
      * * **M5:** MD5 checksum of the sequence.  See Section 1.3.1
      * * **SP:** Species.
@@ -204,7 +213,7 @@ class header
     }
     //!\}
 
-    /*!\name [@RG] Read groups
+    /*!\name [RG] Read groups
      * \brief You can directly edit these member variables.
      * \{
      */
@@ -215,7 +224,7 @@ class header
      * The read group list stores the group id and
      * additional information of each read group in the file. The record
      * may store a RG tag information referencing one of the stored id's.
-     * The id information is required if the @RG header line is provided.
+     * The id information is required if the \@RG header line is provided.
      *
      * The additional information (2nd tuple entry) for the SAM format must follow
      * the following formatting rules: The information is given in a tab separated
@@ -225,13 +234,13 @@ class header
      * * **BC:** Barcode sequence identifying the sample or library. This value is the expected barcode bases as read by
      *           the sequencing machine in the absence of errors. If there are several barcodes for the sample/library
      *           (e.g., one on each end of the template), the recommended implementation concatenates all the barcodes
-     *           separating them with hyphens ('-').
+     *           separating them with hyphens (`-`).
      * * **CN:** Name of sequencing center producing the read.
      * * **DS:** Description.  UTF-8 encoding may be used.
      * * **DT:** Date the run was produced (ISO8601 date or date/time).
      * * **FO:** Flow order. The array of nucleotide bases that correspond to the nucleotides used for each flow of each
      *           read. Multi-base flows are encoded in IUPAC format, and non-nucleotide flows by various other
-     *           characters. Format : /\*\|[ACMGRSVTWYHKDBN]+/
+     *           characters. Format : `/\*\|[ACMGRSVTWYHKDBN]+/`
      * * **KS:** The array of nucleotide bases that correspond to the key sequence of each read.
      * * **LB:** Library.
      * * **PG:** Programs used for processing the read group.
@@ -245,7 +254,7 @@ class header
     std::vector<std::pair<std::string, std::string>> read_groups{};
     //!\}
 
-    /*!\name [@PG] Programm information
+    /*!\name [PG] Programm information
      * \brief You can directly edit these member variables.
      * \{
      */
@@ -263,7 +272,7 @@ class header
     std::vector<program_info_t> program_infos{}; //!< The list of program information.
     //!\}
 
-    /*!\name [@CO] Comments
+    /*!\name [CO] Comments
      * \brief You can directly edit these member variables.
      * \{
      */
@@ -272,17 +281,16 @@ class header
 };
 
 /*!\brief Reads the SAM header.
- * \tparam stream_view_type     The type of the stream as a view.
- * \param[in, out] stream_view  The stream view to iterate over.
+ * \param[in] header_string  The full header as a std::string_view.
  *
- * \throws seqan3::format_error if any unexpected character or format is encountered.
+ * \throws bio::map_io::format_error if any unexpected character or format is encountered.
  *
  * \details
  *
  * Reading the header format is done according to the official
  * [SAM format specifications](https://samtools.github.io/hts-specs/SAMv1.pdf).
  *
- * The function throws a seqan3::format_error if any unknown tag was encountered. It will also fail if the format is
+ * The function throws a bio::map_io::format_error if any unknown tag was encountered. It will also fail if the format is
  * not in a correct state (e.g. required fields are not given), but throwing might occur downstream of the actual
  * error.
  */

include/bio/map_io/sam_flag.hpp

@@ -35,37 +35,35 @@ namespace bio::map_io
  * Adapted from the [SAM specifications](https://samtools.github.io/hts-specs/SAMv1.pdf) are the following additional
  * information to some flag values:
  * * For each read/contig in a SAM file, it is required that one and only one line associated with the read
- *   has neither the seqan3::sam_flag::secondary_alignment nor the seqan3::sam_flag::supplementary_alignment flag value
- *   set (satisfies `FLAG & 0x900 == 0 `). This line is called the **primary alignment** of the read.
- * * seqan3::sam_flag::secondary_alignment (bit `0x100`) marks the alignment not to be used in certain analyses when
- *   the tools in use are aware of this bit. It is typically used to flag alternative mappings when multiple mappings
+ *   has neither the bio::map_io::sam_flag::secondary_alignment nor the bio::map_io::sam_flag::supplementary_alignment
+ *   flag value set (satisfies `FLAG & 0x900 == 0 `). This line is called the **primary alignment** of the read.
+ * * bio::map_io::sam_flag::secondary_alignment (bit `0x100`) marks the alignment not to be used in certain analyses
+ *   when the tools in use are aware of this bit. It is typically used to flag alternative mappings when multiple mappings
  *   are presented in a SAM.
- * * seqan3::sam_flag::supplementary_alignment (bit `0x800`) indicates that the corresponding alignment line is part
+ * * bio::map_io::sam_flag::supplementary_alignment (bit `0x800`) indicates that the corresponding alignment line is part
  *   of a chimeric alignment. If the SAM/BAM file corresponds to long reads (nanopore/pacbio) this happens when
  *   reads are split before being aligned and the best matching part is marked as primary, while all other aligned
  *   parts are marked supplementary.
- * * seqan3::sam_flag::unmapped (bit `0x4`) is the only reliable place to tell whether the read is unmapped.
- *   If seqan3::sam_flag::unmapped is set, no assumptions can be made about RNAME, POS, CIGAR, MAPQ, and
- *   seqan3::sam_flag::proper_pair, seqan3::sam_flag::secondary_alignment, and seqan3::sam_flag::supplementary_alignment
+ * * bio::map_io::sam_flag::unmapped (bit `0x4`) is the only reliable place to tell whether the read is unmapped.
+ *   If bio::map_io::sam_flag::unmapped is set, no assumptions can be made about RNAME, POS, CIGAR, MAPQ, and
+ *   bio::map_io::sam_flag::proper_pair, bio::map_io::sam_flag::secondary_alignment, and bio::map_io::sam_flag::supplementary_alignment
  *   (bits `0x2`, `0x100`, and `0x800`).
- * * seqan3::sam_flag::on_reverse_strand (bit `0x10`) indicates  whether the read sequence has been reverse complemented
- *   and the quality string is reversed.  When bit seqan3::sam_flag::unmapped (`0x4`) is unset, this
- *   corresponds to the strand to which the segment has been mapped: seqan3::sam_flag::on_reverse_strand (bit `0x10`)
- *   unset indicates the forward strand, while set indicates the reverse strand. When seqan3::sam_flag::unmapped (`0x4`)
+ * * bio::map_io::sam_flag::on_reverse_strand (bit `0x10`) indicates  whether the read sequence has been reverse complemented
+ *   and the quality string is reversed.  When bit bio::map_io::sam_flag::unmapped (`0x4`) is unset, this
+ *   corresponds to the strand to which the segment has been mapped: bio::map_io::sam_flag::on_reverse_strand (bit `0x10`)
+ *   unset indicates the forward strand, while set indicates the reverse strand. When bio::map_io::sam_flag::unmapped (`0x4`)
  *   is set, this indicates whether the unmapped read is stored in its original orientation as it came off the
  *   sequencing machine.
- * * seqan3::sam_flag::first_in_pair and seqan3::sam_flag::second_in_pair (bits `0x40` and `0x80`) reflect the read
- *   ordering within each template inherent in the sequencing technology used. If seqan3::sam_flag::first_in_pair and
- *   seqan3::sam_flag::second_in_pair (`0x40` and `0x80`) are both set, the read is part of a linear template, but it
+ * * bio::map_io::sam_flag::first_in_pair and bio::map_io::sam_flag::second_in_pair (bits `0x40` and `0x80`) reflect the read
+ *   ordering within each template inherent in the sequencing technology used. If bio::map_io::sam_flag::first_in_pair and
+ *   bio::map_io::sam_flag::second_in_pair (`0x40` and `0x80`) are both set, the read is part of a linear template, but it
  *   is neither the first nor the last read. If both are unset, the index of the read in the template is unknown.
  *   This may happen for a non-linear template or when this information is lost during data processing.
- * * If seqan3::sam_flag::paired (bit `0x1`) is unset, no assumptions can be made about seqan3::sam_flag::proper_pair,
- *   seqan3::sam_flag::mate_unmapped, seqan3::sam_flag::mate_on_reverse_strand, seqan3::sam_flag::first_in_pair and
- *   seqan3::sam_flag::second_in_pair (bits `0x2`, `0x8`, `0x20`, `0x40` and `0x80`).
+ * * If bio::map_io::sam_flag::paired (bit `0x1`) is unset, no assumptions can be made about bio::map_io::sam_flag::proper_pair,
+ *   bio::map_io::sam_flag::mate_unmapped, bio::map_io::sam_flag::mate_on_reverse_strand, bio::map_io::sam_flag::first_in_pair and
+ *   bio::map_io::sam_flag::second_in_pair (bits `0x2`, `0x8`, `0x20`, `0x40` and `0x80`).
  *
  * \sa https://broadinstitute.github.io/picard/explain-flags.html
- *
- * \remark For a complete overview, take a look at \ref io_sam_file
  */
 enum class sam_flag : uint16_t
 {
@@ -76,27 +74,27 @@ enum class sam_flag : uint16_t
    mate_unmapped           = 0x8,   //!< The mate of this read is not mapped to a reference (unaligned).
    on_reverse_strand       = 0x10,  //!< The read sequence has been reverse complemented before being mapped (aligned).
    mate_on_reverse_strand  = 0x20,  //!< The mate sequence has been reverse complemented before being mapped (aligned).
-   first_in_pair           = 0x40,  //!< Indicates the ordering (see details in the seqan3::sam_flag description).
-   second_in_pair          = 0x80,  //!< Indicates the ordering (see details in the seqan3::sam_flag description).
+   first_in_pair           = 0x40,  //!< Indicates the ordering (see details in the bio::map_io::sam_flag description).
+   second_in_pair          = 0x80,  //!< Indicates the ordering (see details in the bio::map_io::sam_flag description).
    secondary_alignment     = 0x100, //!< This read alignment is an alternative (possibly suboptimal) to the primary.
    failed_filter           = 0x200, //!< The read alignment failed a filter, e.g. quality controls.
    duplicate               = 0x400, //!< The read is marked as a PCR duplicate or optical duplicate.
    supplementary_alignment = 0x800  //!< This sequence is part of a split alignment and is not the primary alignment.
 };
 
 //!\cond DEV
-//!\brief Enables bitwise operations for seqan3::sam_flags.
-//!\ingroup io_sam_file
-//!\sa seqan3::enum_bitwise_operators enables combining enum values.
+/*!\brief Enables bitwise operations for bio::map_io::sam_flags.
+ * \ingroup io_sam_file
+ * \sa seqan3::enum_bitwise_operators enables combining enum values.
+ */
 template <>
 constexpr bool add_enum_bitwise_operators<sam_flag> = true;
 //!\endcond
 
-/*!\brief Overload for the seqan3::sam_flags.
+/*!\brief seqan3::debug_stream overload for the bio::map_io::::sam_flags.
  * \tparam char_t Type char type of the debug_stream.
  * \param stream The seqan3::debug_stream.
  * \param flag The flag to print.
- * \relates seqan3::debug_stream_type
  */
 template <typename char_t>
 inline seqan3::debug_stream_type<char_t> & operator<<(seqan3::debug_stream_type<char_t> & stream, sam_flag const flag)