def test_address_check_returns_empty_list_if_no_addresses_found():
df = pd.DataFrame({
"nonPrivateColumn1": ["a", "b", "c"],
"nonPrivateColumn2": ["a", "b", "c"]
})
actual_private_columns = pp.check_addresses(df)
expected_private_columns = []
assert actual_private_columns == expected_private_columns
def test_does_not_identify_non_whitelisted_street_types_as_addresses(address):
df = pd.DataFrame({
"privateColumn": ["a", address, "c"],
"nonPrivateColumn": ["a", "b", "c"]
})
actual_private_columns = pp.check_addresses(df)
expected_private_columns = []
assert actual_private_columns == expected_private_columns
def test_can_identify_column_containing_simple_street_names(address):
df = pd.DataFrame({
"privateColumn": ["a", address, "c"],
"nonPrivateColumn": ["a", "b", "c"]
})
actual_private_columns = pp.check_addresses(df)
expected_private_columns = ["privateColumn"]
assert actual_private_columns == expected_private_columns
def test_can_identify_column_containing_UK_postcode(postcode):
df = pd.DataFrame({
"privateColumn": ["a", postcode, "c"],
"nonPrivateColumn": ["a", "b", "c"]
})
actual_private_columns = pp.check_addresses(df)
expected_private_columns = ["privateColumn"]
assert actual_private_columns == expected_private_columns
def test_does_not_identify_non_whitelisted_suffixes_as_emails(email):
df = pd.DataFrame({
"privateColumn": ["a", email, "c"],
"nonPrivateColumn": ["a", "b", "c"]
})
actual_private_columns = pp.check_addresses(df)
expected_private_columns = []
assert actual_private_columns == expected_private_columns
def test_check_addresses_can_handle_mixed_dtype_columns():
df = pd.DataFrame({
"privateColumn": [True, "AB1 1AB", "c"],
"privateColumn2": [1, "b", "10 Downing Street"],
"nonPrivateColumn": [0, True, "test"],
})
actual_private_columns = pp.check_addresses(df)
expected_private_columns = ["privateColumn", "privateColumn2"]
assert actual_private_columns == expected_private_columns