def test__get_primary_keys_raise_value_error_field_not_id(self):
"""Test a ValueError is raised when generator is None and field type not id."""
# Setup
sampler = Mock(spec=Sampler)
sampler.metadata = Mock(spec=Metadata)
sampler.metadata.get_primary_key.return_value = 'pk_field'
sampler.metadata.get_fields.return_value = {
'pk_field': {
'type': 'not id'
}
}
sampler.primary_key = {'test': None}
# Run
with pytest.raises(ValueError):
Sampler._get_primary_keys(sampler, 'test', 5)
def test__get_primary_keys_raises_not_implemented_error_datetime(self):
"""Test a NotImplementedError is raised when pk field is datetime."""
# Setup
sampler = Mock(spec=Sampler)
sampler.metadata = Mock(spec=Metadata)
sampler.metadata.get_primary_key.return_value = 'pk_field'
sampler.metadata.get_fields.return_value = {
'pk_field': {
'type': 'id',
'subtype': 'datetime'
}
}
sampler.primary_key = {'test': None}
# Run
with pytest.raises(NotImplementedError):
Sampler._get_primary_keys(sampler, 'test', 5)
def test__get_primary_keys_raise_value_error_field_not_supported(self):
"""Test a ValueError is raised when a field subtype is not supported."""
# Setup
sampler = Mock(spec=Sampler)
sampler.metadata = Mock(spec=Metadata)
sampler.metadata.get_primary_key.return_value = 'pk_field'
sampler.metadata.get_fields.return_value = {
'pk_field': {
'type': 'id',
'subtype': 'X'
}
}
sampler.primary_key = {'test': None}
# Run
with pytest.raises(ValueError):
Sampler._get_primary_keys(sampler, 'test', 5)
def test__get_primary_keys_raises_value_error_remaining(self):
"""Test a ValueError is raised when there are not enough uniques values"""
# Setup
sampler = Mock(spec=Sampler)
sampler.metadata = Mock(spec=Metadata)
sampler.metadata.get_primary_key.return_value = 'pk_field'
sampler.metadata.get_fields.return_value = {
'pk_field': {
'type': 'id',
'subtype': 'datetime'
}
}
sampler.primary_key = {'test': 'generator'}
sampler.remaining_primary_key = {'test': 4}
# Run
with pytest.raises(ValueError):
Sampler._get_primary_keys(sampler, 'test', 5)
def test__get_primary_keys_none(self):
"""Test returns a tuple of none when a table doesn't have a primary key"""
# Setup
sampler = Mock(spec=Sampler)
sampler.metadata = Mock(spec=Metadata)
sampler.metadata.get_primary_key.return_value = None
# Run
result = Sampler._get_primary_keys(sampler, 'test', 5)
# Asserts
assert result == (None, None)
def test__get_primary_keys_raises_error(self):
"""_get_primary_keys raises an exception if there aren't enough values."""
# Setup
data_navigator = MagicMock(spec=DataNavigator)
data_navigator.get_meta_data.return_value = {
'primary_key': 'table_pk',
'fields': {
'table_pk': {
'regex': 'regex for table_pk',
'type': 'number',
'subtype': 'integer'
},
}
}
modeler = MagicMock(spec=Modeler)
sampler = Sampler(data_navigator=data_navigator, modeler=modeler)
sampler.primary_key['table'] = 'a generator'
sampler.remaining_primary_key['table'] = 0
# Run / Check
with self.assertRaises(ValueError):
sampler._get_primary_keys('table', 5)
def test__get_primary_keys_no_pk(self):
"""If no primary key, _get_primary_keys return a duple of None """
# Setup
data_navigator = MagicMock(spec=DataNavigator)
data_navigator.get_meta_data.return_value = {}
modeler = MagicMock(spec=Modeler)
sampler = Sampler(data_navigator=data_navigator, modeler=modeler)
# Run
result = sampler._get_primary_keys('table', 5)
# Check
primary_key, primary_key_values = result
assert primary_key is None
assert primary_key_values is None
def test__get_primary_keys_create_generator(self, exrex_gen_mock,
exrex_count_mock):
"""If there's a primary key, but no generator, a new one is created and used."""
# Setup
data_navigator = MagicMock(spec=DataNavigator)
data_navigator.get_meta_data.return_value = {
'primary_key': 'table_pk',
'fields': {
'table_pk': {
'regex': 'regex for table_pk',
'type': 'number',
'subtype': 'integer'
},
}
}
modeler = MagicMock(spec=Modeler)
sampler = Sampler(data_navigator=data_navigator, modeler=modeler)
exrex_gen_mock.return_value = (str(x) for x in range(10))
exrex_count_mock.return_value = 10
expected_primary_key = 'table_pk'
expected_primary_key_values = pd.Series(range(5))
# Run
result = sampler._get_primary_keys('table', 5)
# Check
primary_key, primary_key_values = result
assert primary_key == expected_primary_key
primary_key_values.equals(expected_primary_key_values)
assert sampler.primary_key['table'] == exrex_gen_mock.return_value
assert sampler.remaining_primary_key['table'] == 5
data_navigator.get_meta_data.assert_called_once_with('table')
exrex_count_mock.assert_called_once_with('regex for table_pk')
exrex_gen_mock.assert_called_once_with('regex for table_pk')
