def t_gff2_iteration(self):
"""Test iterated features with GFF2 files, breaking without parents.
"""
gff_iterator = GFFAddingIterator()
break_dicts = []
for rec_dict in gff_iterator.get_features(self._wormbase_file,
target_lines=15):
break_dicts.append(rec_dict)
assert len(break_dicts) == 3
def t_solid_iterator(self):
"""Iterated parsing in a flat file without nested features.
"""
gff_iterator = GFFAddingIterator()
feature_sizes = []
for rec_dict in gff_iterator.get_features(self._test_gff_file,
target_lines=5):
feature_sizes.append([len(r.features) for r in rec_dict.values()])
assert max([sum(s) for s in feature_sizes]) == 5
assert len(feature_sizes) == 26, len(feature_sizes)
def t_gff3_iterator(self):
"""Iterated parsing in GFF3 files with nested features.
"""
gff_iterator = GFFAddingIterator()
feature_sizes = []
for rec_dict in gff_iterator.get_features(self._test_gff_file,
target_lines=70):
feature_sizes.append([len(r.features) for r in rec_dict.values()])
# should be one big set because we don't have a good place to split
assert len(feature_sizes) == 1
assert feature_sizes[0][0] == 59
def t_gff3_iterator_limit(self):
"""Iterated interface using a limit query on GFF3 files.
"""
gff_iterator = GFFAddingIterator()
cds_limit_info = dict(
gff_source_type = [('Coding_transcript', 'gene'),
('Coding_transcript', 'mRNA'),
('Coding_transcript', 'CDS')],
gff_id = ['I']
)
it_recs = []
for rec_dict in gff_iterator.get_features(self._test_gff_file,
limit_info=cds_limit_info):
it_recs.append(rec_dict)
assert len(it_recs) == 1
tfeature = it_recs[0]["I"].features[0].sub_features[0]
for sub_test in tfeature.sub_features:
assert sub_test.type == "CDS", sub_test
