c_cpp/lib/htslib/bcf_sr_sort.h

   1 /*
   2     Copyright (C) 2017 Genome Research Ltd.
   3
   4     Author: Petr Danecek <pd3@sanger.ac.uk>
   5
   6     Permission is hereby granted, free of charge, to any person obtaining a copy
   7     of this software and associated documentation files (the "Software"), to deal
   8     in the Software without restriction, including without limitation the rights
   9     to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
  10     copies of the Software, and to permit persons to whom the Software is
  11     furnished to do so, subject to the following conditions:
  12
  13     The above copyright notice and this permission notice shall be included in
  14     all copies or substantial portions of the Software.
  15
  16     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  17     IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  18     FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
  19     AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  20     LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
  21     OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  22     THE SOFTWARE.
  23 */
  24
  25 /*
  26     Reorder duplicate lines so that compatible variant types are
  27     returned together by bcf_sr_next_line()
  28
  29     - readers grouped by variants. Even with many readers there will be
  30       typically only several groups
  31
  32 */
  33
  34 #ifndef __BCF_SR_SORT_H__
  35 #define __BCF_SR_SORT_H__
  36
  37 #include "htslib/synced_bcf_reader.h"
  38 #include "htslib/kbitset.h"
  39
  40 typedef struct
  41 {
  42     int nrec, mrec;
  43     bcf1_t **rec;
  44 }
  45 vcf_buf_t;
  46
  47 typedef struct
  48 {
  49     char *str;      // "A>C" for biallelic records or "A>C,A>CC" for multiallelic records
  50     int type;       // VCF_SNP, VCF_REF, etc.
  51     int nalt;       // number of alternate alleles in this record
  52     int nvcf, mvcf, *vcf;   // the list of readers with the same variants
  53     bcf1_t **rec;           // list of VCF records in the readers
  54     kbitset_t *mask;        // which groups contain the variant
  55 }
  56 var_t;
  57
  58 typedef struct
  59 {
  60     char *key;              // only for debugging
  61     int nvar, mvar, *var;   // the variants and their type
  62     int nvcf;               // number of readers with the same variants
  63 }
  64 grp_t;
  65
  66 typedef struct
  67 {
  68     int nvar, mvar, *var;   // list of compatible variants that can be output together
  69     int cnt;                // number of readers in this group
  70     kbitset_t *mask;        // which groups are populated in this set (replace with expandable bitmask)
  71 }
  72 varset_t;
  73
  74 typedef struct
  75 {
  76     uint8_t score[256];
  77     int nvar, mvar;
  78     var_t *var;             // list of all variants from all readers
  79     int nvset, mvset;
  80     int mpmat, *pmat;       // pairing matrix, i-th vset and j-th group accessible as i*ngrp+j
  81     int ngrp, mgrp;
  82     int mcnt, *cnt;         // number of VCF covered by a varset
  83     grp_t *grp;             // list of VCF representatives, each with a unique combination of duplicate lines
  84     varset_t *vset;         // list of variant sets - combinations of compatible variants across multiple groups ready for output
  85     vcf_buf_t *vcf_buf;     // records sorted in output order, for each VCF
  86     bcf_srs_t *sr;
  87     void *grp_str2int;
  88     void *var_str2int;
  89     kstring_t str;
  90     int moff, noff, *off, mcharp;
  91     char **charp;
  92     const char *chr;
  93     int pos, nsr, msr;
  94     int pair;
  95 }
  96 sr_sort_t;
  97
  98 sr_sort_t *bcf_sr_sort_init(sr_sort_t *srt);
  99 int bcf_sr_sort_next(bcf_srs_t *readers, sr_sort_t *srt, const char *chr, int pos);
 100 void bcf_sr_sort_destroy(sr_sort_t *srt);
 101 void bcf_sr_sort_remove_reader(bcf_srs_t *readers, sr_sort_t *srt, int i);
 102
 103 #endif