add test for #20

header.go

@@ -19,7 +19,7 @@ var contigRegexp = regexp.MustCompile(`contig=<.*((\w+)=([^,>]+))`)
 var sampleRegexp = regexp.MustCompile(`SAMPLE=<ID=([^,>]+)`)
 var pedRegexp = regexp.MustCompile(`PEDIGREE=<=([^,>]+)`)
 
-//var headerIdRegexp = regexp.MustCompile(`##([^=]+)=<ID=([^,]+)`)
+// var headerIdRegexp = regexp.MustCompile(`##([^=]+)=<ID=([^,]+)`)
 var fileVersionRegexp = regexp.MustCompile(`##fileformat=VCFv(.+)`)
 
 // Info holds the Info and Format fields
@@ -226,7 +226,7 @@ func parseHeaderExtraKV(kv string) ([]string, error) {
 	kvpair := strings.SplitN(kv, "=", 2)
 
 	if len(kvpair) != 2 {
-        kvpair = append(kvpair, "")
+		kvpair = append(kvpair, "")
 		return kvpair, fmt.Errorf("header error in extra field: %s", kv)
 	}
 	return kvpair, nil

reader.go

@@ -1,24 +1,25 @@
 // Package vcfgo implements a Reader and Writer for variant call format.
 // It eases reading, filtering modifying VCF's even if they are not to spec.
 // Example:
-//  f, _ := os.Open("examples/test.auto_dom.no_parents.vcf")
-//  rdr, err := vcfgo.NewReader(f)
-//  if err != nil {
-//  	panic(err)
-//  }
-//  for {
-//  	variant := rdr.Read()
-//  	if variant == nil {
-//  		break
-//  	}
-//  	fmt.Printf("%s\t%d\t%s\t%s\n", variant.Chromosome, variant.Pos, variant.Ref, variant.Alt)
-//  	fmt.Printf("%s", variant.Info["DP"].(int) > 10)
-//  	sample := variant.Samples[0]
-//  	// we can get the PL field as a list (-1 is default in case of missing value)
-//  	fmt.Println("%s", variant.GetGenotypeField(sample, "PL", -1))
-//  	_ = sample.DP
-//  }
-//  fmt.Fprintln(os.Stderr, rdr.Error())
+//
+//	f, _ := os.Open("examples/test.auto_dom.no_parents.vcf")
+//	rdr, err := vcfgo.NewReader(f)
+//	if err != nil {
+//		panic(err)
+//	}
+//	for {
+//		variant := rdr.Read()
+//		if variant == nil {
+//			break
+//		}
+//		fmt.Printf("%s\t%d\t%s\t%s\n", variant.Chromosome, variant.Pos, variant.Ref, variant.Alt)
+//		fmt.Printf("%s", variant.Info["DP"].(int) > 10)
+//		sample := variant.Samples[0]
+//		// we can get the PL field as a list (-1 is default in case of missing value)
+//		fmt.Println("%s", variant.GetGenotypeField(sample, "PL", -1))
+//		_ = sample.DP
+//	}
+//	fmt.Fprintln(os.Stderr, rdr.Error())
 package vcfgo
 
 import (

variant.go

@@ -223,6 +223,11 @@ type SampleGenotype struct {
 	Fields map[string]string
 }
 
+// String returns the string representation of the sample field.
+func (s *SampleGenotype) String() string {
+	return fmt.Sprintf("GT: %v, DP: %d, GL: %v, GQ: %d, MQ: %d, Fields: %v", s.GT, s.DP, s.GL, s.GQ, s.MQ, s.Fields)
+}
+
 // RefDepth returns the depths of the alternates for this sample
 func (s *SampleGenotype) RefDepth() (int, error) {
 	if ad, ok := s.Fields["AD"]; ok {
@@ -257,8 +262,8 @@ func (s *SampleGenotype) AltDepths() ([]int, error) {
 	return vals, nil
 }
 
-// String returns the string representation of the sample field.
-func (sg *SampleGenotype) String(fields []string) string {
+// ToString returns the string representation of the sample field.
+func (sg *SampleGenotype) ToString(fields []string) string {
 	if len(fields) == 0 {
 		return "."
 	}
@@ -291,7 +296,7 @@ func (v *Variant) String() string {
 	if len(v.Samples) > 0 {
 		samps := make([]string, len(v.Samples))
 		for i, s := range v.Samples {
-			samps[i] = s.String(v.Format)
+			samps[i] = s.ToString(v.Format)
 		}
 		s += fmt.Sprintf("\t%s\t%s", strings.Join(v.Format, ":"), strings.Join(samps, "\t"))
 	} else if v.sampleString != "" {

vcf_test.go

@@ -1,6 +1,7 @@
 package vcfgo
 
 import (
+	"fmt"
 	"os"
 	"testing"
 
@@ -180,3 +181,25 @@ func (s *VCFSuite) TestWriterWithSamples(c *C) {
 	c.Assert(strings.HasPrefix(lines[len(lines)-1], "#CHROM"), Equals, true)
 
 }
+func (s *VCFSuite) TestIssue20SampleGenotypes(c *C) {
+	fname := "test-issue-20.vcf"
+	rdr, err := os.Open(fname)
+	c.Assert(err, IsNil)
+	defer rdr.Close()
+
+	vcf, err := NewReader(rdr, false)
+	c.Assert(err, IsNil)
+
+	variant := vcf.Read()
+	c.Assert(variant, NotNil)
+
+	samples := variant.Samples
+	c.Assert(len(samples), Equals, 3)
+	// print samples
+	fmt.Printf("%+v\n", samples)
+
+	// Check genotypes for each sample
+	c.Assert(samples[0].GT, DeepEquals, []int{1, 1})
+	c.Assert(samples[1].GT, DeepEquals, []int{0, 1})
+	c.Assert(samples[2].GT, DeepEquals, []int{-1, -1})
+}