def test_report_conflicted_and_inferred_headers(self):
header_definitions = merge_header_definitions.VcfHeaderDefinitions()
header_definitions._infos = {'NS': {Definition(1, 'Float'): ['file1'],
Definition(1, 'Integer'): ['file2']}}
infos = OrderedDict([
('NS', Info('NS', 1, 'Float', 'Number samples', None, None))])
formats = OrderedDict([
('DP', Format('DP', 2, 'Float', 'Total Depth'))])
resolved_headers = VcfHeader(infos=infos, formats=formats)
inferred_headers = VcfHeader(formats=formats)
expected = [
preprocess_reporter._InconsistencyType.HEADER_CONFLICTS + '\n',
preprocess_reporter._HeaderLine.CONFLICTS_HEADER + '\n',
(preprocess_reporter._DELIMITER).join([
'NS', 'INFO', 'num=1 type=Float', 'file1', 'num=1 type=Float\n']),
(preprocess_reporter._DELIMITER).join([
' ', ' ', 'num=1 type=Integer', 'file2', ' \n']),
'\n',
preprocess_reporter._InconsistencyType.UNDEFINED_HEADERS + '\n',
preprocess_reporter._HeaderLine.UNDEFINED_FIELD_HEADER + '\n',
(preprocess_reporter._DELIMITER).join([
'DP', 'FORMAT', 'num=2 type=Float\n']),
'\n'
]
self._generate_report_and_assert_contents_equal(expected,
header_definitions,
resolved_headers,
inferred_headers)
def test_report_multiple_files(self):
header_definitions = merge_header_definitions.VcfHeaderDefinitions()
header_definitions._infos = {
'NS': {Definition(1, 'Float'): ['file1', 'file2'],
Definition(1, 'Integer'): ['file3']}
}
infos = OrderedDict([
('NS', Info('NS', 1, 'Float', 'Number samples', None, None))])
resolved_headers = VcfHeader(infos=infos)
expected = [
preprocess_reporter._InconsistencyType.HEADER_CONFLICTS + '\n',
preprocess_reporter._HeaderLine.CONFLICTS_HEADER + '\n',
(preprocess_reporter._DELIMITER).join([
'NS', 'INFO', 'num=1 type=Float', 'file1', 'num=1 type=Float\n']),
(preprocess_reporter._DELIMITER).join([
' ', ' ', ' ', 'file2', ' \n']),
(preprocess_reporter._DELIMITER).join([
' ', ' ', 'num=1 type=Integer', 'file3', ' \n']),
'\n'
]
self._generate_report_and_assert_contents_equal(expected,
header_definitions,
resolved_headers)
def _get_header_from_reader(vcf_reader, file_name=None):
return VcfHeader(infos=vcf_reader.infos,
filters=vcf_reader.filters,
alts=vcf_reader.alts,
formats=vcf_reader.formats,
contigs=vcf_reader.contigs,
file_name=file_name)
def _get_header_from_reader(vcf_reader, file_path=None):
return VcfHeader(infos=vcf_reader.infos,
filters=vcf_reader.filters,
alts=vcf_reader.alts,
formats=vcf_reader.formats,
contigs=vcf_reader.contigs,
samples=vcf_reader.samples,
file_path=file_path)
def test_report_no_inconsistencies(self):
header_definitions = merge_header_definitions.VcfHeaderDefinitions()
inferred_headers = VcfHeader()
expected = [
'No Header Conflicts Found.\n', '\n',
'No Undefined Headers Found.\n', '\n',
'No Malformed Records Found.\n', '\n'
]
self._generate_report_and_assert_contents_equal(
expected,
header_definitions,
inferred_headers=inferred_headers,
malformed_records=[])
def test_report_no_conflicts(self):
header_definitions = merge_header_definitions.VcfHeaderDefinitions()
header_definitions._infos = {'NS': {Definition(1, 'Float'): ['file1']}}
header_definitions._formats = {'NS': {Definition(1, 'Float'): ['file2']}}
infos = OrderedDict([
('NS', Info('NS', 1, 'Integer', 'Number samples', None, None))])
formats = OrderedDict([('NS', Format('NS', 1, 'Float', 'Number samples'))])
resolved_headers = VcfHeader(infos=infos, formats=formats)
expected = ['No Header Conflicts Found.\n', '\n']
self._generate_report_and_assert_contents_equal(expected,
header_definitions,
resolved_headers)
def test_report_inferred_headers_only(self):
header_definitions = merge_header_definitions.VcfHeaderDefinitions()
formats = OrderedDict([('DP', Format('DP', 2, 'Float',
'Total Depth'))])
inferred_headers = VcfHeader(formats=formats)
expected = [
'No Header Conflicts Found.\n', '\n',
preprocess_reporter._InconsistencyType.UNDEFINED_HEADERS + '\n',
preprocess_reporter._HeaderLine.UNDEFINED_FIELD_HEADER + '\n',
(preprocess_reporter._DELIMITER).join(
['DP', 'FORMAT', 'num=2 type=Float\n']), '\n'
]
self._generate_report_and_assert_contents_equal(
expected, header_definitions, inferred_headers=inferred_headers)
def _get_vcf_header_from_lines(lines, file_name=None):
header = libcbcf.VariantHeader()
sample_line = LAST_HEADER_LINE_PREFIX
header.add_line('##fileformat=VCFv4.0')
for line in lines:
if line.startswith('#'):
if line.startswith(LAST_HEADER_LINE_PREFIX):
sample_line = line.strip()
break
header.add_line(line.strip())
else:
break
return VcfHeader(infos=header.info,
filters=header.filters,
alts=header.alts,
formats=header.formats,
contigs=header.contigs,
samples=sample_line,
file_path=file_name)
def test_report_malformed_records(self):
header_definitions = merge_header_definitions.VcfHeaderDefinitions()
inferred_headers = VcfHeader()
records = [vcfio.MalformedVcfRecord('file1',
'rs6054257 G A 29 PASS',
'Invalid literal')]
expected = [
'No Header Conflicts Found.\n',
'\n',
'No Undefined Headers Found.\n',
'\n',
preprocess_reporter._InconsistencyType.MALFORMED_RECORDS + '\n',
preprocess_reporter._HeaderLine.MALFORMED_RECORDS_HEADER + '\n',
(preprocess_reporter._DELIMITER).join([
'file1', 'rs6054257 G A 29 PASS', 'Invalid literal\n']),
'\n'
]
self._generate_report_and_assert_contents_equal(
expected, header_definitions, inferred_headers=inferred_headers,
malformed_records=records)
