def test_parse(self):
file = StringIO("""
#=GENOME_DIFF 1.0
#=AUTHOR test
SNP 1 23423 NC_000913 223 A gene_name=mhpE
RA 2 NC_000913 223 0 G A frequency=0.1366
""".strip())
p = GenomeDiffParser(fsock=file)
self.assertEqual([
Metadata('GENOME_DIFF', '1.0'),
Metadata('AUTHOR', 'test'),
Record('SNP',
1,
parent_ids=[23423],
new_seq='A',
seq_id='NC_000913',
position=223,
gene_name='mhpE'),
Record('RA',
2,
new_base='A',
frequency=0.1366,
position=223,
seq_id='NC_000913',
insert_position=0,
ref_base='G')
], list(p))
def test_document(self):
file = StringIO("""
#=GENOME_DIFF 1.0
#=AUTHOR test
SNP 1 23423 NC_000913 223 A
RA 2 NC_000913 223 0 G A
""".strip())
document = GenomeDiff.read(file)
self.assertEqual({
'AUTHOR': 'test',
'GENOME_DIFF': '1.0'
}, document.metadata)
snp_record = Record('SNP',
1,
document, [23423],
seq_id='NC_000913',
new_seq='A',
position=223)
ra_record = Record('RA',
2,
document,
None,
position=223,
seq_id='NC_000913',
insert_position=0,
new_base='A',
ref_base='G')
self.assertEqual([snp_record], document.mutations)
self.assertEqual([ra_record], document.evidence)
self.assertEqual(snp_record, document[1])
self.assertEqual(ra_record, document[2])
def test_simple(self):
snp_record = Record('SNP', 1, parent_ids=[23423], seq_id='NC_000913', new_seq='A', position=223, test='more')
self.assertEqual('SNP', snp_record.type)
self.assertEqual(1, snp_record.id)
self.assertEqual('A', snp_record.new_seq)
self.assertEqual('more', snp_record.test)
def __iter__(self):
metadata_pattern = re.compile(r'^#=(\w+)\s+(.*)$')
mutation_pattern = re.compile(r'^(?P<type>[A-Z]{2,4})'
'\t(?P<id>\d+)'
'\t((?P<parent_ids>\d+(,\s*\d+)*)|\.?)'
'\t(?P<extra>.+)?$')
for i, line in enumerate(self._fsock):
if not line:
continue
elif line.startswith('#'):
match = metadata_pattern.match(line)
if match:
yield Metadata(*match.group(1, 2))
else:
match = mutation_pattern.match(line)
if match:
type = match.group('type')
id = int(match.group('id'))
parent_ids = match.group('parent_ids')
if parent_ids:
parent_ids = [int(id) for id in parent_ids.split(',')]
extra = match.group('extra').split('\t')
extra_dct = OrderedDict()
for name in TYPE_SPECIFIC_FIELDS[type]:
value = extra.pop(0)
extra_dct[name] = self._convert_value(value)
for k, v in (e.split('=', 1) for e in extra):
extra_dct[k] = self._convert_value(v)
yield Record(type, id, self._document, parent_ids,
**extra_dct)
else:
raise Exception('Could not parse line #{}: {}'.format(
i, line))