def test_sars2_legacy():
result = konstel.generate('sars-cov-2-s-legacy.protein',
f'{data_dir}/spike.prot.fa')
assert result['id'] == 'S:papoheme'
result = konstel.generate('sars-cov-2-s-legacy.genome',
f'{data_dir}/spike.genome.fa')
assert result['id'] == 'S:papoheme'
def generate(scheme: str,
file: str,
format: typing.Union[str, None] = None,
output: str = 'json',
length: int = 0,
hide_prefix: bool = False):
'''
Generate identifier(s) for input file path or stdin according to the specified scheme
Returns dict, and prints format specified in OUTPUT
:arg scheme: Scheme name; use {scheme}.{directive} if scheme specifies multiple directives
:arg file: Input path or - for stdin
:arg format: Input format; mandatory if scheme specifies multiple formats
:arg output: Output format (json, tsv, table)
:arg length: Encoding length; overrides scheme
:arg hide_prefix: Hide encoding prefix; overrides scheme
'''
outputs = konstel.generate(scheme, file, format, output, length, hide_prefix)
print(konstel.format_encodings(outputs, output))
def test_sars2_generate_stdin():
with open(f'{data_dir}/spike.genome.fa') as sys.stdin:
result = konstel.generate('sars-cov-2-s.genome', file='-')
print(result)
assert result['id'] == 'S:sapapag'
def test_sars2_generate_prot():
result = konstel.generate('sars-cov-2-s.protein',
f'{data_dir}/spike.prot.fa')
print(result)
assert result['id'] == 'S:sapapag'
def test_sars2_generate_nucl():
result = konstel.generate('sars-cov-2-s.genome',
f'{data_dir}/spike.genome.fa')
print(result)
assert result['id'] == 'S:sapapag'
def test_sars2_generate_length():
result = konstel.generate('sars-cov-2-s.protein',
f'{data_dir}/spike.prot.fa',
length=21)
assert result['id'] == 'S:huhijig-akihifu-tofikip'
def test_validation_alphabet():
sys.stdin = io.StringIO('ACGTX')
with pytest.raises(RuntimeError):
konstel.generate('generic.nucl', file='-')
def test_sars2_generate_nucl():
result = konstel.generate('sars-cov-2-s.genome',
f'{data_dir}/spike.genome.fa')
assert result['id'] == 'S:huhijig-akih'
def test_sars2_generate_prot():
result = konstel.generate('sars-cov-2-s.protein',
f'{data_dir}/spike.prot.fa')
assert result['id'] == 'S:huhijig-akih'
def test_bio_normalisation():
result1 = konstel.generate('bio.nuc', '-', sequence='ACGT')
result2 = konstel.generate('bio.nuc', '-', sequence='A-\nC G\tT')
assert result1['id'] == 'bituzu-gupahu-zolodu-lumaki-suripi-rozitu-guhabi'
assert result1['id'] == result2['id']
def test_direct_string_input():
result = konstel.generate('string', '-', sequence='ACGT')
assert result['id'] == 'bituzu-gupahu-zolodu-lumaki-suripi-rozitu-guhabi'
def test_stdin_string():
sys.stdin = io.StringIO('ACGT')
result = konstel.generate('string', file='-')
assert result['id'] == 'bituzu-gupahu-zolodu-lumaki-suripi-rozitu-guhabi'