def test_output_sql(input_obj, kwargs):
data = DataSet(input_obj, **kwargs)
assert isinstance(data, DataSet)
assert data.db_uri == kwargs.get('db_uri')
data.to_output()
db = dataset_db.connect(kwargs.get('db_uri'))
rows = list(db.query('select * from test;'))
assert len(rows) == 2
# removing id
assert sorted(list(rows[0].values())[1:]) == sorted(
list(input_obj[0].values()))
if os.path.exists(kwargs.get('db_uri').replace('sqlite:///', '')):
os.remove(kwargs.get('db_uri').replace('sqlite:///', ''))
def test_output(input_obj, output, output_type, kwargs):
data = DataSet(input_obj, output=output, **kwargs)
if output.startswith('file://'):
assert data.output_filename == output.replace('file://', '')
to_output = data.to_output()
assert isinstance(to_output, output_type)
if output_type == list and isinstance(input_obj, list):
assert input_obj == to_output
elif output_type == list:
assert input_obj.tolist() == to_output
elif output_type == pd.DataFrame:
assert to_output.shape == (2, 3)
elif output_type == np.ndarray and not kwargs:
assert np.array_equal(to_output[0, :], [1, 2, 5])
elif output_type == np.ndarray:
assert to_output[0] == {'a': 1, 'b': 2, 'd': 5}
elif output_type == str:
assert os.path.exists(to_output)
def fuzz_from_parser(parser):
""" Fuzz using parser input.
This will generate a `dataset.Dataset` from `parser.input`,
apply any defined strategies and call `dataset.to_output`.
Arguments:
parser (`parsers.StrategyCLIParser` or
`parsers.StrategyYAMLParser`): strategy parser
Returns:
dataset.to_output()
"""
dataset = DataSet(parser.input,
output=parser.output,
db_uri=parser.db_uri,
query=parser.query,
table=parser.table)
for strategy in parser.strategies:
strategy_obj = build_strategy(strategy, dataset)
try:
strategy_obj.run_strategy()
except Exception:
logging.exception('Error running strategy: %s', strategy)
return dataset.to_output()
def test_bad_io(input_obj, output, kwargs):
with pytest.raises(Exception):
if 'data' in input_obj:
input_obj = 'file://{}'.format(input_obj)
data = DataSet(input_obj, output=output, **kwargs)
data.to_output()
def test_output_errors(input_obj, output):
with pytest.raises(NotImplementedError):
data = DataSet(input_obj, output=output)
data.to_output()