def test_valid_line_count():
p = iterators._FileIterator(example_filename('ncbi_gff3.txt'))
assert len(list(p)) == 17
p = iterators._FileIterator(example_filename('hybrid1.gff3'))
assert len(list(p)) == 6
p = iterators._FileIterator(example_filename('FBgn0031208.gff'))
assert len(list(p)) == 27
def test_valid_line_count():
p = iterators._FileIterator(example_filename('ncbi_gff3.txt'))
assert len(list(p)) == 17
p = iterators._FileIterator(example_filename('hybrid1.gff3'))
assert len(list(p)) == 6
p = iterators._FileIterator(example_filename('FBgn0031208.gff'))
assert len(list(p)) == 27
def parser_smoke_test():
"""
Just confirm we can iterate completely through the test files....
"""
# Don't show the warnings for tests
import logging
parser.logger.setLevel(logging.CRITICAL)
for filename in TEST_FILENAMES:
p = iterators._FileIterator(filename)
for i in p:
continue
def parser_smoke_test():
"""
Just confirm we can iterate completely through the test files....
"""
# Don't show the warnings for tests
import logging
parser.logger.setLevel(logging.CRITICAL)
for filename in TEST_FILENAMES:
p = iterators._FileIterator(filename)
for i in p:
continue
def test_parser_from_string():
"""
make sure from string and from file return identical results
"""
line = b"chr2L FlyBase exon 7529 8116 . + . Name=CG11023:1;Parent=FBtr0300689,FBtr0300690"
tmp = tempfile.NamedTemporaryFile()
tmp.write(line)
tmp.seek(0)
p1 = iterators._StringIterator(
"chr2L FlyBase exon 7529 8116 . + . Name=CG11023:1;Parent=FBtr0300689,FBtr0300690"
)
p2 = iterators._FileIterator(tmp.name)
lines = list(zip(p1, p2))
assert len(lines) == 1
assert p1.current_item_number == p2.current_item_number == 0
assert lines[0][0] == lines[0][1]
def test_parser_from_string():
"""
make sure from string and from file return identical results
"""
line = b"chr2L FlyBase exon 7529 8116 . + . Name=CG11023:1;Parent=FBtr0300689,FBtr0300690"
tmp = tempfile.NamedTemporaryFile()
tmp.write(line)
tmp.seek(0)
p1 = iterators._StringIterator(
"chr2L FlyBase exon 7529 8116 . + . Name=CG11023:1;Parent=FBtr0300689,FBtr0300690"
)
p2 = iterators._FileIterator(tmp.name)
lines = list(zip(p1, p2))
assert len(lines) == 1
assert p1.current_item_number == p2.current_item_number == 0
assert lines[0][0] == lines[0][1]
def test_inspect():
file_results = inspect.inspect(gffutils.example_filename('FBgn0031208.gff'), verbose=False)
db_results = inspect.inspect(
gffutils.create_db(
gffutils.example_filename('FBgn0031208.gff'),
':memory:'),
verbose=False
)
expected = {
'featuretype': {
'intron': 3,
'five_prime_UTR': 1,
'exon': 6,
'mRNA': 4,
'CDS': 5,
'pcr_product': 1,
'three_prime_UTR': 2,
'protein': 2,
'gene': 3,
},
'feature_count': 27,
'chrom': {
'chr2L': 27,
},
'attribute_keys': {
u'': 3,
'Dbxref': 6,
'Name': 19,
'Parent': 20,
' Parent': 1,
'score_text': 2,
'gbunit': 1,
'derived_computed_cyto': 1,
'Derives_from': 2,
'derived_molecular_weight': 2,
'score': 2,
'ID': 25,
'derived_isoelectric_point': 2,
'Ontology_term': 1,
}
}
assert file_results == db_results == expected
# file and db work because db is created from
kwargs = dict(
look_for=['chrom', 'strand', 'attribute_keys', 'featuretype'],
verbose=False,
limit=10,
)
file_results = inspect.inspect(
gffutils.example_filename('FBgn0031208.gff'),
**kwargs
)
iter_results = inspect.inspect(
iter(iterators._FileIterator(gffutils.example_filename('FBgn0031208.gff'))),
**kwargs
)
db_results = inspect.inspect(
gffutils.create_db(
gffutils.example_filename('FBgn0031208.gff'),
':memory:'),
**kwargs
)
expected = {
'attribute_keys': {
u'Name': 9,
u'Parent': 9,
u'score_text': 2,
u'gbunit': 1,
u'derived_computed_cyto': 1,
u'score': 2,
u'Dbxref': 3,
u'ID': 8,
u'Ontology_term': 1,
},
'feature_count': 10,
'chrom': {u'chr2L': 10},
'strand': {u'+': 10},
'featuretype': {
u'five_prime_UTR': 1,
u'exon': 3,
u'mRNA': 2,
u'CDS': 1,
'intron': 2,
u'gene': 1}
}
assert file_results == db_results == iter_results == expected
def test_inspect():
file_results = inspect.inspect(
gffutils.example_filename('FBgn0031208.gff'), verbose=False)
db_results = inspect.inspect(gffutils.create_db(
gffutils.example_filename('FBgn0031208.gff'), ':memory:'),
verbose=False)
expected = {
'featuretype': {
'intron': 3,
'five_prime_UTR': 1,
'exon': 6,
'mRNA': 4,
'CDS': 5,
'pcr_product': 1,
'three_prime_UTR': 2,
'protein': 2,
'gene': 3,
},
'feature_count': 27,
'chrom': {
'chr2L': 27,
},
'attribute_keys': {
u'': 3,
'Dbxref': 6,
'Name': 19,
'Parent': 20,
' Parent': 1,
'score_text': 2,
'gbunit': 1,
'derived_computed_cyto': 1,
'Derives_from': 2,
'derived_molecular_weight': 2,
'score': 2,
'ID': 25,
'derived_isoelectric_point': 2,
'Ontology_term': 1,
}
}
assert file_results == db_results == expected
# file and db work because db is created from
kwargs = dict(
look_for=['chrom', 'strand', 'attribute_keys', 'featuretype'],
verbose=False,
limit=10,
)
file_results = inspect.inspect(
gffutils.example_filename('FBgn0031208.gff'), **kwargs)
iter_results = inspect.inspect(
iter(
iterators._FileIterator(
gffutils.example_filename('FBgn0031208.gff'))), **kwargs)
db_results = inspect.inspect(
gffutils.create_db(gffutils.example_filename('FBgn0031208.gff'),
':memory:'), **kwargs)
expected = {
'attribute_keys': {
u'Name': 9,
u'Parent': 9,
u'score_text': 2,
u'gbunit': 1,
u'derived_computed_cyto': 1,
u'score': 2,
u'Dbxref': 3,
u'ID': 8,
u'Ontology_term': 1,
},
'feature_count': 10,
'chrom': {
u'chr2L': 10
},
'strand': {
u'+': 10
},
'featuretype': {
u'five_prime_UTR': 1,
u'exon': 3,
u'mRNA': 2,
u'CDS': 1,
'intron': 2,
u'gene': 1
}
}
assert file_results == db_results == iter_results == expected