c_cpp/lib/htslib/test/test-vcf-sweep.c

   1 /*  test/test-vcf-sweep.c -- VCF test harness.
   2
   3     Copyright (C) 2013 Genome Research Ltd.
   4
   5     Author: Petr Danecek <pd3@sanger.ac.uk>
   6
   7 Permission is hereby granted, free of charge, to any person obtaining a copy
   8 of this software and associated documentation files (the "Software"), to deal
   9 in the Software without restriction, including without limitation the rights
  10 to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
  11 copies of the Software, and to permit persons to whom the Software is
  12 furnished to do so, subject to the following conditions:
  13
  14 The above copyright notice and this permission notice shall be included in
  15 all copies or substantial portions of the Software.
  16
  17 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  18 IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  19 FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
  20 THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  21 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
  22 FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
  23 DEALINGS IN THE SOFTWARE.  */
  24
  25 #include <config.h>
  26
  27 #include <stdio.h>
  28 #include <htslib/vcf_sweep.h>
  29
  30 int main(int argc, char **argv)
  31 {
  32     if ( argc!=2 )
  33     {
  34         fprintf(stderr,"Usage: test-vcf-sweep <file.bcf|file.vcf>\n");
  35         return 1;
  36     }
  37
  38     // Init variables. The checksum is just for this test program to output
  39     // something and verify that all sites are read in both passes - fwd and
  40     // bwd.
  41     bcf_sweep_t *sw = bcf_sweep_init(argv[1]);
  42     bcf_hdr_t *hdr  = bcf_sweep_hdr(sw);
  43     int chksum = 0;
  44
  45     // First we must sweep forward and read the whole file to build an index.
  46     // If this is undesirable, we can require the presence of a .gzi index
  47     // which can be created with `bgzip -r` from the samtools/htslib package
  48     bcf1_t *rec;
  49     while ( (rec = bcf_sweep_fwd(sw)) ) chksum += rec->pos+1;
  50     printf("fwd position chksum: %d\n", chksum);
  51
  52     // Now sweep backward.
  53     chksum = 0;
  54     while ( (rec = bcf_sweep_bwd(sw)) ) chksum += rec->pos+1;
  55     printf("bwd position chksum: %d\n", chksum);
  56
  57     // And forward and backward again, this time summing the PL vectors
  58     int i,j, mPLs = 0, nPLs;
  59     int32_t *PLs = NULL;
  60     chksum = 0;
  61     while ( (rec = bcf_sweep_fwd(sw)) )
  62     {
  63         // get copy of the PL vectors
  64         nPLs = bcf_get_format_int32(hdr, rec, "PL", &PLs, &mPLs);
  65         if ( !nPLs ) continue;  // PL not present
  66
  67         // how many values are there per sample
  68         int nvals = nPLs / bcf_hdr_nsamples(hdr);
  69
  70         int32_t *ptr = PLs;
  71         for (i=0; i<bcf_hdr_nsamples(hdr); i++)
  72         {
  73             for (j=0; j<nvals; j++)
  74             {
  75                 // check for shorter vectors (haploid genotypes amongst diploids)
  76                 if ( ptr[j]==bcf_int32_vector_end ) break;
  77
  78                 // skip missing values
  79                 if ( ptr[j]==bcf_int32_missing ) continue;
  80
  81                 chksum += ptr[j];
  82             }
  83             ptr += nvals;
  84         }
  85     }
  86     printf("fwd PL chksum: %d\n", chksum);
  87
  88     // And the same backwards..
  89     chksum = 0;
  90     while ( (rec = bcf_sweep_bwd(sw)) )
  91     {
  92         nPLs = bcf_get_format_int32(hdr, rec, "PL", &PLs, &mPLs);
  93         if ( !nPLs ) continue;
  94         int nvals = nPLs / bcf_hdr_nsamples(hdr);
  95         int32_t *ptr = PLs;
  96         for (i=0; i<bcf_hdr_nsamples(hdr); i++)
  97         {
  98             for (j=0; j<nvals; j++)
  99             {
 100                 if ( ptr[j]==bcf_int32_vector_end ) break;
 101                 if ( ptr[j]==bcf_int32_missing ) continue;
 102                 chksum += ptr[j];
 103             }
 104             ptr += nvals;
 105         }
 106     }
 107     printf("bwd PL chksum: %d\n", chksum);
 108
 109     // Clean up
 110     bcf_sweep_destroy(sw);
 111     return 0;
 112 }
 113
 114