Merge pull request #160 from hammerlab/fix-issue-158

Fix load_vcf_fast for sample names containing a space character
openvax · Jul 15, 2016 · 78f789e · 78f789e
2 parents 4bb441f + b965d71
commit 78f789e
Show file tree

Hide file tree

Showing 4 changed files with 40 additions and 5 deletions.
diff --git a/test/data/multiallelic.vcf b/test/data/multiallelic.vcf
@@ -12,5 +12,5 @@
 ##contig=<ID=chr15,length=102531392>
 ##contig=<ID=chr16,length=90354753>
 ##contig=<ID=chr17,length=81195210>
-#CHROM  POS ID  REF ALT QUAL	FILTER  INFO	FORMAT  metastasis
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	metastasis
 chr1	1431105	rs199599542	A	C,G	593.69	PASS	DP=17;GE=Wuzzle	GT	0/1
diff --git a/test/data/somatic_hg19_14muts.space_in_sample_name.vcf b/test/data/somatic_hg19_14muts.space_in_sample_name.vcf
@@ -0,0 +1,29 @@
+##fileformat=VCFv4.1
+##reference=file:///projects/ngs/resources/gatk/2.3/ucsc.hg19.fasta
+##INFO=<ID=GE,Number=.,Type=String,Description="HGNC Gene Symbol (could be more than one)">
+##INFO=<ID=EG,Number=.,Type=String,Description="Entrez Gene ID (could be more than one)">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##contig=<ID=chrM,length=16571>
+##contig=<ID=chr1,length=249250621>
+##contig=<ID=chr10,length=135534747>
+##contig=<ID=chr11,length=135006516>
+##contig=<ID=chr12,length=133851895>
+##contig=<ID=chr14,length=107349540>
+##contig=<ID=chr15,length=102531392>
+##contig=<ID=chr16,length=90354753>
+##contig=<ID=chr17,length=81195210>
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	metastasis foo
+chr1	53513530	.	A	C	.	.	GE=SCP2;EG=6342	GT	0/1
+chr1	228295398	.	G	T	.	.	GE=MRPL55;EG=128308	GT	0/1
+chr10	49658590	.	T	C	.	.	GE=ARHGAP22;EG=58504	GT	0/1
+chr10	51585166	.	G	T	.	.	GE=NCOA4;EG=8031	GT	0/1
+chr10	96709040	.	A	C	.	.	GE=CYP2C9;EG=1559	GT	0/1
+chr10	119134281	.	G	T	.	.	GE=PDZD8;EG=118987	GT	0/1
+chr11	118244286	.	G	G	.	.	GE=UBE4A;EG=9354	GT	0/1
+chr12	14794076	.	C	A	.	.	GE=GUCY2C;EG=2984	GT	0/1
+chr12	25398284	.	C	G	.	.	GE=KRAS;EG=3845	GT	0/1
+chr12	42778752	.	T	A	.	.	GE=PPHLN1;EG=51535	GT	0/1
+chr14	31144202	.	A	C	.	.	GE=SCFD1;EG=23256	GT	0/1
+chr16	25704209	.	G	A	.	.	GE=HS3ST4;EG=9951	GT	0/1
+chr17	7577548	.	C	CA	.	.	GE=TP53;EG=7157	GT	0/1
+chr17	36731197	.	C	AAT	.	.	GE=SRCIN1;EG=80725	GT	0/1
diff --git a/test/test_vcf.py b/test/test_vcf.py
@@ -73,6 +73,7 @@ def test_vcf_reference_name():
 def test_pandas_and_pyvcf_implementations_equivalent():
     paths = [
         {'path': data_path("somatic_hg19_14muts.vcf")},
+        {'path': data_path("somatic_hg19_14muts.space_in_sample_name.vcf")},
         {'path': "/" + data_path("somatic_hg19_14muts.vcf")},
         {'path': data_path("somatic_hg19_14muts.vcf.gz")},
         {'path': data_path("multiallelic.vcf")},

diff --git a/varcode/vcf.py b/varcode/vcf.py
@@ -151,8 +151,8 @@ def load_vcf_fast(
 
     genome : {pyensembl.Genome, reference name, Ensembl version int}, optional
         Optionally pass in a PyEnsembl Genome object, name of reference, or
-        PyEnsembl release version to specify the reference associated with a VCF
-        (otherwise infer reference from VCF using reference_vcf_key)
+        PyEnsembl release version to specify the reference associated with a
+        VCF (otherwise infer reference from VCF using reference_vcf_key)
 
     reference_vcf_key : str, optional
         Name of metadata field which contains path to reference FASTA
@@ -469,7 +469,9 @@ def __init__(self, path):
             self.path = path
             parsed_path = parse_url_or_path(path)
             if not parsed_path.scheme or parsed_path.scheme.lower() == 'file':
-                self.vcf_reader = pyvcf.Reader(filename=parsed_path.path)
+                self.vcf_reader = pyvcf.Reader(
+                    filename=parsed_path.path,
+                    strict_whitespace=True)
             elif parsed_path.scheme.lower() in ("http", "https", "ftp"):
                 self._to_close = response = requests.get(path, stream=True)
                 response.raise_for_status()  # raise error on 404, etc.
@@ -478,7 +480,10 @@ def __init__(self, path):
                         response.iter_content())
                 else:
                     lines = response.iter_lines(decode_unicode=True)
-                self.vcf_reader = pyvcf.Reader(fsock=lines, compressed=False)
+                self.vcf_reader = pyvcf.Reader(
+                    fsock=lines,
+                    compressed=False,
+                    strict_whitespace=True)
             else:
                 raise ValueError("Unsupported scheme: %s" % parsed_path.scheme)