Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add support for VCFv4.4 / VCFv4.5 Number= fields #1874

Draft
wants to merge 1 commit into
base: develop
Choose a base branch
from
+24 −8
Draft

Add support for VCFv4.4 / VCFv4.5 Number= fields #1874

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 15 additions & 5 deletions htslib/vcf.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,11 +65,21 @@ extern "C" {
#define BCF_HT_STR 3
#define BCF_HT_LONG (BCF_HT_INT | 0x100) // BCF_HT_INT, but for int64_t values; VCF only!

#define BCF_VL_FIXED 0 // variable length
#define BCF_VL_VAR 1
#define BCF_VL_A 2
#define BCF_VL_G 3
#define BCF_VL_R 4
// Values for INFO / FORMAT "Number=" fields
#define BCF_VL_FIXED 0 ///< Integer defining a fixed number of items
#define BCF_VL_VAR 1 ///< Generic variable length ("Number=.")
#define BCF_VL_A 2 ///< One value per alternate allele
#define BCF_VL_G 3 ///< One value for each possible genotype
#define BCF_VL_R 4 ///< One value for each allele, including the reference

// The following was introduced in VCFv4.4 and is only valid for FORMAT header lines
#define BCF_VL_P 5 ///< One value for each allele value defined in GT

// The following were introduced in VCFv4.5 and are only valid for FORMAT header lines
#define BCF_VL_LA 6 ///< As BCF_VL_A, but only alt alleles listed in LAA are considered present
#define BCF_VL_LG 7 ///< As BCF_VL_G, but only alt alleles listed in LAA are considered present
#define BCF_VL_LR 8 ///< As BCF_VL_R, but only alt alleles listed in LAA are considered present
#define BCF_VL_M 9 ///< One value for each possible base modification for the corresponding ChEBI ID

/* === Dictionary ===

Expand Down
12 changes: 9 additions & 3 deletions vcf.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -846,14 +846,20 @@ static int bcf_hdr_register_hrec(bcf_hdr_t *hdr, bcf_hrec_t *hrec)
}
else if ( !strcmp(hrec->keys[i], "Number") )
{
int is_fmt = hrec->type == BCF_HL_FMT;
if ( !strcmp(hrec->vals[i],"A") ) var = BCF_VL_A;
else if ( !strcmp(hrec->vals[i],"R") ) var = BCF_VL_R;
else if ( !strcmp(hrec->vals[i],"G") ) var = BCF_VL_G;
else if ( !strcmp(hrec->vals[i],".") ) var = BCF_VL_VAR;
else if ( is_fmt && !strcmp(hrec->vals[i],"P") ) var = BCF_VL_P;
else if ( is_fmt && !strcmp(hrec->vals[i],"LA") ) var = BCF_VL_LA;
else if ( is_fmt && !strcmp(hrec->vals[i],"LR") ) var = BCF_VL_LR;
else if ( is_fmt && !strcmp(hrec->vals[i],"LG") ) var = BCF_VL_LG;
else if ( is_fmt && !strcmp(hrec->vals[i],"M") ) var = BCF_VL_M;
else
{
sscanf(hrec->vals[i],"%d",&num);
var = BCF_VL_FIXED;
if (sscanf(hrec->vals[i],"%d",&num) == 1)
var = BCF_VL_FIXED;
}
if (var != BCF_VL_FIXED) num = 0xfffff;
}
Expand All @@ -864,7 +870,7 @@ static int bcf_hdr_register_hrec(bcf_hdr_t *hdr, bcf_hrec_t *hrec)
*hrec->key == 'I' ? "An" : "A", hrec->key);
type = BCF_HT_STR;
}
if (var == -1) {
if (var == UINT32_MAX) {
hts_log_warning("%s %s field has no Number defined. Assuming '.'",
*hrec->key == 'I' ? "An" : "A", hrec->key);
var = BCF_VL_VAR;
Expand Down