def test_interval_metadata_to_gff3(self):
with io.StringIO() as fh:
_interval_metadata_to_gff3(self.imd1, fh, seq_id='Chromosome')
# only compare the uncommented lines because the comments are not
# stored in IntervalMetadata
obs = [i for i in fh.getvalue().splitlines()
if not i.startswith('#')]
with open(self.single_fp) as f:
exp = [i.rstrip() for i in f.readlines() if not i.startswith('#')]
self.assertEqual(obs, exp)
def test_interval_metadata_to_gff3(self):
with io.StringIO() as fh:
_interval_metadata_to_gff3(self.imd1, fh, seq_id='Chromosome')
# only compare the uncommented lines because the comments are not
# stored in IntervalMetadata
obs = [
i for i in fh.getvalue().splitlines() if not i.startswith('#')
]
with open(self.single_fp) as f:
exp = [i.rstrip() for i in f.readlines() if not i.startswith('#')]
self.assertEqual(obs, exp)
def test_interval_metadata_to_gff3_missing_field(self):
exp = 'ctg123\t.\tgene\t1\t9\t.\t.\t.\tID=gene00001;Name=EDEN'
imd = IntervalMetadata(9)
imd.add([(0, 9)], metadata={
'type': 'gene', 'ID': 'gene00001', 'Name': 'EDEN'})
with io.StringIO() as fh:
_interval_metadata_to_gff3(imd, fh, seq_id='ctg123')
# only compare the uncommented lines because the comments are not
# stored in IntervalMetadata
obs = [i for i in fh.getvalue().splitlines()
if not i.startswith('#')]
self.assertEqual([exp], obs)
def test_interval_metadata_to_gff3_escape(self):
# test escape of reserved char in GFF3
exp = 'ctg123\t.\tgene\t1\t9\t.\t.\t.\tID=a%3B%3D%26%2Cb'
imd = IntervalMetadata(9)
imd.add([(0, 9)], metadata={'type': 'gene', 'ID': 'a;=&,b'})
with io.StringIO() as fh:
_interval_metadata_to_gff3(imd, fh, seq_id='ctg123')
# only compare the uncommented lines because the comments are not
# stored in IntervalMetadata
obs = [
i for i in fh.getvalue().splitlines() if not i.startswith('#')
]
self.assertEqual([exp], obs)
def test_interval_metadata_to_gff3_multiple_values(self):
# test multiple values of db_xref are correctly serialized
exp = 'ctg123\t.\tgene\t1\t9\t.\t.\t.\tDbxref=GO:000152,GO:001234'
imd = IntervalMetadata(9)
imd.add([(0, 9)], metadata={
'type': 'gene', 'db_xref': ['GO:000152', 'GO:001234']})
with io.StringIO() as fh:
_interval_metadata_to_gff3(imd, fh, seq_id='ctg123')
# only compare the uncommented lines because the comments are not
# stored in IntervalMetadata
obs = [i for i in fh.getvalue().splitlines()
if not i.startswith('#')]
self.assertEqual([exp], obs)
def test_interval_metadata_to_gff3_escape(self):
# test escape of reserved char in GFF3
exp = 'ctg123\t.\tgene\t1\t9\t.\t.\t.\tID=a%3B%3D%26%2Cb'
imd = IntervalMetadata(9)
imd.add([(0, 9)], metadata={
'type': 'gene', 'ID': 'a;=&,b'})
with io.StringIO() as fh:
_interval_metadata_to_gff3(imd, fh, seq_id='ctg123')
# only compare the uncommented lines because the comments are not
# stored in IntervalMetadata
obs = [i for i in fh.getvalue().splitlines()
if not i.startswith('#')]
self.assertEqual([exp], obs)
def test_roundtrip_interval_metadata(self):
''''''
with io.StringIO() as fh:
_interval_metadata_to_gff3(_gff3_to_interval_metadata(
self.single_fp, seq_id='Chromosome'),
fh,
seq_id='Chromosome')
obs = [
i for i in fh.getvalue().splitlines() if not i.startswith('#')
]
with open(self.single_fp) as f:
exp = [i.rstrip() for i in f.readlines() if not i.startswith('#')]
self.assertEqual(obs, exp)
def test_roundtrip_interval_metadata(self):
''''''
with io.StringIO() as fh:
_interval_metadata_to_gff3(
_gff3_to_interval_metadata(
self.single_fp,
seq_id='Chromosome'),
fh,
seq_id='Chromosome')
obs = [i for i in fh.getvalue().splitlines()
if not i.startswith('#')]
with open(self.single_fp) as f:
exp = [i.rstrip() for i in f.readlines() if not i.startswith('#')]
self.assertEqual(obs, exp)
def test_interval_metadata_to_gff3_multiple_values(self):
# test multiple values of db_xref are correctly serialized
exp = 'ctg123\t.\tgene\t1\t9\t.\t.\t.\tDbxref=GO:000152,GO:001234'
imd = IntervalMetadata(9)
imd.add([(0, 9)],
metadata={
'type': 'gene',
'db_xref': ['GO:000152', 'GO:001234']
})
with io.StringIO() as fh:
_interval_metadata_to_gff3(imd, fh, seq_id='ctg123')
# only compare the uncommented lines because the comments are not
# stored in IntervalMetadata
obs = [
i for i in fh.getvalue().splitlines() if not i.startswith('#')
]
self.assertEqual([exp], obs)
def test_interval_metadata_to_gff3_missing_field(self):
exp = 'ctg123\t.\tgene\t1\t9\t.\t.\t.\tID=gene00001;Name=EDEN'
imd = IntervalMetadata(9)
imd.add([(0, 9)],
metadata={
'type': 'gene',
'ID': 'gene00001',
'Name': 'EDEN'
})
with io.StringIO() as fh:
_interval_metadata_to_gff3(imd, fh, seq_id='ctg123')
# only compare the uncommented lines because the comments are not
# stored in IntervalMetadata
obs = [
i for i in fh.getvalue().splitlines() if not i.startswith('#')
]
self.assertEqual([exp], obs)
def test_interval_metadata_to_gff3_empty(self):
imd = IntervalMetadata(None)
with io.StringIO() as fh:
_interval_metadata_to_gff3(imd, fh, seq_id='foo')
obs = fh.getvalue()
self.assertEqual(obs, '##gff-version 3\n')
def test_interval_metadata_to_gff3_empty(self):
imd = IntervalMetadata(None)
with io.StringIO() as fh:
_interval_metadata_to_gff3(imd, fh, seq_id='foo')
obs = fh.getvalue()
self.assertEqual(obs, '##gff-version 3\n')
