def test_check_fk_constraint_valid_1(self):
A = pd.read_csv(path_a)
B = pd.read_csv(path_b)
C = pd.read_csv(path_c)
status = ch.check_fk_constraint(C, 'ltable_ID', A, 'ID')
self.assertEqual(status, True)
status = ch.check_fk_constraint(C, 'rtable_ID', B, 'ID')
self.assertEqual(status, True)
def _add_output_attributes(candset,
fk_ltable,
fk_rtable,
ltable=None,
rtable=None,
l_key=None,
r_key=None,
l_output_attrs=None,
r_output_attrs=None,
l_output_prefix='ltable_',
r_output_prefix='rtable_',
validate=True):
if not isinstance(candset, pd.DataFrame):
logger.error('Input object is not of type pandas data frame')
raise AssertionError('Input object is not of type pandas data frame')
if not isinstance(fk_ltable, six.string_types):
logger.error('fk_ltable is not of type string')
raise AssertionError('fk_ltable is not of type string')
if not isinstance(fk_rtable, six.string_types):
logger.error('fk_rtable is not of type string')
raise AssertionError('fk_rtable is not of type string')
if l_output_attrs is not None:
if ltable is None:
logger.error('ltable is not given to pull l_output_attrs')
raise AssertionError('ltable is not given to pull l_output_attrs')
if l_key is None:
logger.error('ltable key cannot be None')
raise AssertionError('ltable key cannot be None')
if validate:
check_fk_constraint(candset, fk_ltable, ltable, l_key)
col_names = [l_output_prefix + c for c in l_output_attrs]
l_df = create_proj_dataframe(ltable, l_key, candset[fk_ltable],
l_output_attrs, col_names)
if r_output_attrs is not None:
if rtable is None:
logger.error('rtable is not given to pull r_output_attrs')
raise AssertionError('rtable is not given to pull r_output_attrs')
if r_key is None:
logger.error('rtable key cannot be None')
raise AssertionError('rtable key cannot be None')
if validate:
check_fk_constraint(candset, fk_rtable, rtable, r_key)
col_names = [r_output_prefix + c for c in r_output_attrs]
r_df = create_proj_dataframe(rtable, r_key, candset[fk_rtable],
r_output_attrs, col_names)
if l_output_attrs is not None:
candset = pd.concat([candset, l_df], axis=1)
if r_output_attrs is not None:
candset = pd.concat([candset, r_df], axis=1)
return candset
def validate_metadata_for_candset(candset, key, fk_ltable, fk_rtable, ltable,
rtable, l_key, r_key, lgr, verbose):
if not isinstance(candset, pd.DataFrame):
logger.error('Input cand.set is not of type pandas data frame')
raise AssertionError('Input cand.set is not of type pandas data frame')
if not key in candset.columns:
logger.error('Input key ( %s ) not in the dataframe' % key)
raise KeyError('Input key ( %s ) not in the dataframe' % key)
if not fk_ltable in candset.columns:
logger.error('Input fk_ltable ( %s ) not in the dataframe' % fk_ltable)
raise KeyError('Input fk_ltable ( %s ) not in the dataframe' %
fk_ltable)
if not fk_rtable in candset.columns:
logger.error('Input fk_rtable ( %s ) not in the dataframe' % fk_rtable)
raise KeyError('Input fk_rtable ( %s ) not in the dataframe' %
fk_rtable)
if not isinstance(ltable, pd.DataFrame):
logger.error('Input ltable is not of type pandas data frame')
raise AssertionError('Input ltable is not of type pandas data frame')
if not isinstance(rtable, pd.DataFrame):
logger.error('Input rtable is not of type pandas data frame')
raise AssertionError('Input rtable is not of type pandas data frame')
if not l_key in ltable:
logger.error('ltable key ( %s ) not in ltable' % l_key)
raise KeyError('ltable key ( %s ) not in ltable' % l_key)
if not r_key in rtable:
logger.error('rtable key ( %s ) not in rtable' % r_key)
raise KeyError('rtable key ( %s ) not in rtable' % r_key)
validate_metadata_for_table(candset, key, 'cand.set', lgr, verbose)
ch.log_info(lgr, 'Validating foreign key constraint for left table',
verbose)
assert ch.check_fk_constraint(candset, fk_ltable, ltable,
l_key) == True, 'Cand.set does not satisfy foreign key ' \
'constraint with the left table'
ch.log_info(lgr, '..... Done', verbose)
ch.log_info(lgr, 'Validating foreign key constraint for right table',
verbose)
assert ch.check_fk_constraint(candset, fk_rtable, rtable,
r_key) == True, 'Cand.set does not satisfy foreign key ' \
'constraint with the right table'
ch.log_info(lgr, '..... Done', verbose)
return True
def validate_metadata_for_candset(candset, key, fk_ltable, fk_rtable, ltable, rtable,
l_key, r_key,
lgr, verbose):
if not isinstance(candset, pd.DataFrame):
logger.error('Input cand.set is not of type pandas data frame')
raise AssertionError('Input cand.set is not of type pandas data frame')
if not key in candset.columns:
logger.error('Input key ( %s ) not in the dataframe' % key)
raise KeyError('Input key ( %s ) not in the dataframe' % key)
if not fk_ltable in candset.columns:
logger.error('Input fk_ltable ( %s ) not in the dataframe' % fk_ltable)
raise KeyError('Input fk_ltable ( %s ) not in the dataframe' % fk_ltable)
if not fk_rtable in candset.columns:
logger.error('Input fk_rtable ( %s ) not in the dataframe' % fk_rtable)
raise KeyError('Input fk_rtable ( %s ) not in the dataframe' % fk_rtable)
if not isinstance(ltable, pd.DataFrame):
logger.error('Input ltable is not of type pandas data frame')
raise AssertionError('Input ltable is not of type pandas data frame')
if not isinstance(rtable, pd.DataFrame):
logger.error('Input rtable is not of type pandas data frame')
raise AssertionError('Input rtable is not of type pandas data frame')
if not l_key in ltable:
logger.error('ltable key ( %s ) not in ltable' % l_key)
raise KeyError('ltable key ( %s ) not in ltable' % l_key)
if not r_key in rtable:
logger.error('rtable key ( %s ) not in rtable' % r_key)
raise KeyError('rtable key ( %s ) not in rtable' % r_key)
validate_metadata_for_table(candset, key, 'cand.set', lgr, verbose)
ch.log_info(lgr, 'Validating foreign key constraint for left table', verbose)
assert ch.check_fk_constraint(candset, fk_ltable, ltable,
l_key) == True, 'Cand.set does not satisfy foreign key ' \
'constraint with the left table'
ch.log_info(lgr, '..... Done', verbose)
ch.log_info(lgr, 'Validating foreign key constraint for right table', verbose)
assert ch.check_fk_constraint(candset, fk_rtable, rtable,
r_key) == True, 'Cand.set does not satisfy foreign key ' \
'constraint with the right table'
ch.log_info(lgr, '..... Done', verbose)
return True
def _add_output_attributes(candset, fk_ltable, fk_rtable, ltable=None, rtable=None,
l_key=None, r_key=None,
l_output_attrs=None, r_output_attrs=None,
l_output_prefix='ltable_', r_output_prefix='rtable_',
validate=True):
if not isinstance(candset, pd.DataFrame):
logger.error('Input object is not of type pandas data frame')
raise AssertionError('Input object is not of type pandas data frame')
if not isinstance(fk_ltable, six.string_types):
logger.error('fk_ltable is not of type string')
raise AssertionError('fk_ltable is not of type string')
if not isinstance(fk_rtable, six.string_types):
logger.error('fk_rtable is not of type string')
raise AssertionError('fk_rtable is not of type string')
if l_output_attrs is not None:
if ltable is None:
logger.error('ltable is not given to pull l_output_attrs')
raise AssertionError('ltable is not given to pull l_output_attrs')
if l_key is None:
logger.error('ltable key cannot be None')
raise AssertionError('ltable key cannot be None')
if validate:
check_fk_constraint(candset, fk_ltable, ltable, l_key)
col_names = [l_output_prefix+c for c in l_output_attrs]
l_df = create_proj_dataframe(ltable, l_key, candset[fk_ltable], l_output_attrs, col_names)
if r_output_attrs is not None:
if rtable is None:
logger.error('rtable is not given to pull r_output_attrs')
raise AssertionError('rtable is not given to pull r_output_attrs')
if r_key is None:
logger.error('rtable key cannot be None')
raise AssertionError('rtable key cannot be None')
if validate:
check_fk_constraint(candset, fk_rtable, rtable, r_key)
col_names = [r_output_prefix+c for c in r_output_attrs]
r_df = create_proj_dataframe(rtable, r_key, candset[fk_rtable], r_output_attrs, col_names)
if l_output_attrs is not None:
candset = pd.concat([candset, l_df], axis=1)
if r_output_attrs is not None:
candset = pd.concat([candset, r_df], axis=1)
return candset
def test_check_fk_constraint_invalid_attr_mval(self):
A = pd.read_csv(path_a)
B = pd.read_csv(path_b)
C = pd.read_csv(path_c)
C.ix[0, 'ltable_ID'] = pd.np.NaN
status = ch.check_fk_constraint(C, 'ltable_ID', A, 'ID')
self.assertEqual(status, False)
def validate_and_set_fk_rtable(df_foreign, fk_rtable, rtable, r_key):
# validations are done inside the check_fk_constraint fn.
status = ch.check_fk_constraint(df_foreign, fk_rtable, rtable, r_key)
if status == True:
return set_property(df_foreign, 'fk_rtable', fk_rtable)
else:
logger.warning(
'FK constraint for rtable and fk_rtable is not satisfied; Not setting the fk_rtable and rtable')
return False
def validate_and_set_fk_rtable(df_foreign, fk_rtable, rtable, r_key):
# validations are done inside the check_fk_constraint fn.
status = ch.check_fk_constraint(df_foreign, fk_rtable, rtable, r_key)
if status == True:
return set_property(df_foreign, 'fk_rtable', fk_rtable)
else:
logger.warning(
'FK constraint for rtable and fk_rtable is not satisfied; Not setting the fk_rtable and rtable'
)
return False
def test_check_fk_constraint_invalid_attr_notin(self):
A = pd.read_csv(path_a)
B = pd.read_csv(path_b)
C = pd.read_csv(path_c)
status = ch.check_fk_constraint(C, 'ltable_ID', A, 'ID1')
self.assertEqual(status, False)
def test_check_fk_constraint_invalid_foreign_attr(self):
ch.check_fk_constraint(pd.DataFrame(), None, pd.DataFrame(), 'ID')
def test_check_fk_constraint_invalid_base_attr(self):
ch.check_fk_constraint(pd.DataFrame(), 'rtable_ID', pd.DataFrame(), None)
def test_check_fk_constraint_invalid_foreign_df(self):
ch.check_fk_constraint(None, 'rtable_ID', pd.DataFrame(), 'ID')