Added vcf and testcases to demonstrate issue214

vcf/test/issue-214.vcf

@@ -0,0 +1,32 @@
+##fileformat=VCFv4.1
+##ALT=<ID=NON_REF,Description="Represents any possible alternative allele at this location">
+##FILTER=<ID=LowQual,Description="Low quality">
+##FORMAT=<ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=MIN_DP,Number=1,Type=Integer,Description="Minimum DP observed within the GVCF block">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
+##FORMAT=<ID=RGQ,Number=1,Type=Integer,Description="Unconditional reference genotype confidence, encoded as a phred quality -10*log10 p(genotype call is wrong)">
+##FORMAT=<ID=SB,Number=4,Type=Integer,Description="Per-sample component statistics which comprise the Fisher's Exact Test to detect strand bias.">
+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=BaseQRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt Vs. Ref base qualities">
+##INFO=<ID=ClippingRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref number of hard clipped bases">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">
+##INFO=<ID=DS,Number=0,Type=Flag,Description="Were any of the samples downsampled?">
+##INFO=<ID=END,Number=1,Type=Integer,Description="Stop position of the interval">
+##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher's exact test to detect strand bias">
+##INFO=<ID=HaplotypeScore,Number=1,Type=Float,Description="Consistency of the site with at most two segregating haplotypes">
+##INFO=<ID=InbreedingCoeff,Number=1,Type=Float,Description="Inbreeding coefficient as estimated from the genotype likelihoods per-sample when compared against the Hardy-Weinberg expectation">
+##INFO=<ID=MLEAC,Number=A,Type=Integer,Description="Maximum likelihood expectation (MLE) for the allele counts (not necessarily the same as the AC), for each ALT allele, in the same order as listed">
+##INFO=<ID=MLEAF,Number=A,Type=Float,Description="Maximum likelihood expectation (MLE) for the allele frequency (not necessarily the same as the AF), for each ALT allele, in the same order as listed">
+##INFO=<ID=MQ,Number=1,Type=Float,Description="RMS Mapping Quality">
+##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities">
+##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">
+##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">
+##INFO=<ID=SOR,Number=1,Type=Float,Description="Symmetric Odds Ratio of 2x2 contingency table to detect strand bias">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	Sample1	Sample2
+1	456904	.	T	C,*	6162.77	.	AC=1,1;AF=8.333e-03,8.333e-03;AN=120;DP=7693;FS=0.000;MLEAC=1,1;MLEAF=8.333e-03,8.333e-03;MQ=60.00;QD=31.36;SOR=0.976	GT:AD:DP:GQ:PL	0:106,0,0:106:99:0,1800,1800	0:110,0,0:110:99:0,1800,1800
+1	456940	.	*	C,T	6162.77	.	AC=1,1;AF=8.333e-03,8.333e-03;AN=120;DP=7693;FS=0.000;MLEAC=1,1;MLEAF=8.333e-03,8.333e-03;MQ=60.00;QD=31.36;SOR=0.976	GT:AD:DP:GQ:PL	0:106,0,0:106:99:0,1800,1800	0:110,0,0:110:99:0,1800,1800

vcf/test/test_vcf.py

@@ -229,7 +229,35 @@ def testParse(self):
             for s in r.samples:
                 s.phased
 
-
+class TestIssue214(unittest.TestCase):
+    """ See https://github.com/jamescasbon/PyVCF/issues/214 """
+
+    def test_issue_214_is_snp(self):
+        reader=vcf.Reader(fh('issue-214.vcf'))
+        r=reader.next()
+        self.assertTrue(r.is_snp)
+
+    def test_issue_214_var_type(self):
+        reader=vcf.Reader(fh('issue-214.vcf'))
+        r=reader.next()
+        self.assertEqual(r.var_type,'snp')
+
+    # Can the ref even be a spanning deletion?
+    # Note, this does not trigger issue 214, but I've added it here for completeness
+    def test_issue_214_ref_is_del_is_snp(self):
+        reader=vcf.Reader(fh('issue-214.vcf'))
+        reader.next()
+        r=reader.next()
+        self.assertTrue(r.is_snp)
+
+    # Can the ref even be a spanning deletion?
+    # Note, this does not trigger issue 214, but I've added it here for completeness
+    def test_issue_214_ref_is_del_var_type(self):
+        reader=vcf.Reader(fh('issue-214.vcf'))
+        reader.next()
+        r=reader.next()
+        self.assertEqual(r.var_type,'snp')
+
 class Test1kg(unittest.TestCase):
 
     def testParse(self):
@@ -1532,6 +1560,7 @@ def test_write_uncalled(self):
 suite.addTests(unittest.TestLoader().loadTestsFromTestCase(TestFreebayesOutput))
 suite.addTests(unittest.TestLoader().loadTestsFromTestCase(TestSamtoolsOutput))
 suite.addTests(unittest.TestLoader().loadTestsFromTestCase(TestBcfToolsOutput))
+suite.addTests(unittest.TestLoader().loadTestsFromTestCase(TestIssue214))
 suite.addTests(unittest.TestLoader().loadTestsFromTestCase(Test1kg))
 suite.addTests(unittest.TestLoader().loadTestsFromTestCase(Test1kgSites))
 suite.addTests(unittest.TestLoader().loadTestsFromTestCase(TestGoNL))