def test_write_headers(self):
header = _get_vcf_header_from_lines(self.lines)
with temp_dir.TempDir() as tempdir:
tempfile = tempdir.create_temp_file(suffix='.vcf')
header_fn = WriteVcfHeaderFn(tempfile)
header_fn.process(header)
self._assert_file_contents_equal(tempfile, self.lines)
def test_write_contig(self):
self.lines = [
'##contig=<ID=M,length=16,assembly=B37,md5=c6,species="Homosapiens">\n',
self.lines[-1],
]
header = _get_vcf_header_from_lines(self.lines)
header_fn = WriteVcfHeaderFn('')
actual = header_fn._to_vcf_header_line('contig', header.contigs.values()[0])
expected = '##contig=<ID=M,length=16>\n'
self.assertEqual(actual, expected)
def test_info_source_and_version(self):
self.lines = [
'##INFO=<ID=DP,Number=1,Type=Integer,Description="Total Depth",'
'Source="source",Version="version">\n', self.lines[-1]
]
header = _get_vcf_header_from_lines(self.lines)
header_fn = WriteVcfHeaderFn('')
actual = header_fn._to_vcf_header_line('INFO',
header.infos.values()[0])
expected = self.lines[0]
self.assertEqual(actual, expected)
def test_to_vcf_header_line(self):
header_fn = WriteVcfHeaderFn('')
header = collections.OrderedDict([
('id', 'NS'),
('num', 1),
('type', 'Integer'),
('desc', 'Number samples'),
])
expected = ('##INFO=<ID=NS,Number=1,Type=Integer,'
'Description="Number samples">\n')
self.assertEqual(header_fn._to_vcf_header_line('INFO', header),
expected)
def test_write_info_number_types(self):
self.lines = [
'##INFO=<ID=NS,Number=1,Type=Integer,Description="Number samples">\n',
'##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency">\n',
'##INFO=<ID=HG,Number=G,Type=Integer,Description="IntInfo_G">\n',
'##INFO=<ID=HR,Number=R,Type=String,Description="ChrInfo_R">\n',
self.lines[-1],
]
header = _get_vcf_header_from_lines(self.lines)
header_fn = WriteVcfHeaderFn('')
actual = []
for info in list(header.infos.values()):
actual.append(header_fn._to_vcf_header_line('INFO', info))
expected = self.lines[:-1]
self.assertCountEqual(actual, expected)
def test_write_headers_with_vcf_version_line(self):
header = _get_vcf_header_from_lines(self.lines)
vcf_version_line = '##fileformat=VCFv4.3\n'
expected_results = [
vcf_version_line.encode('utf-8'),
b'##INFO=<ID=NS,Number=1,Type=Integer,Description="Number samples">\n',
b'##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency">\n',
b'##INFO=<ID=HG,Number=G,Type=Integer,Description="IntInfo_G">\n',
b'##INFO=<ID=HR,Number=R,Type=String,Description="ChrInfo_R">\n',
b'##FILTER=<ID=MPCBT,Description="Mate pair count below 10">\n',
b'##ALT=<ID=INS:ME:MER,Description="Insertion of MER element">\n',
b'##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">\n',
b'##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="GQ">\n',
b'#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT\n'
]
with temp_dir.TempDir() as tempdir:
tempfile = tempdir.create_temp_file(suffix='.vcf')
header_fn = WriteVcfHeaderFn(tempfile)
header_fn.process(header, vcf_version_line)
with open(tempfile, 'rb') as f:
actual = f.readlines()
self.assertCountEqual(actual, expected_results)
def test_raises_error_for_invalid_num(self):
header_fn = WriteVcfHeaderFn('')
header = collections.OrderedDict([('num', -4)])
with self.assertRaises(ValueError):
header_fn._format_header_key_value('num', header['num'])