def test_find_terminator_exception(body, sep, quoting, quotechar, lineterminator):
with pytest.raises(LineTerminatorNotFound):
assert Pandas._find_terminator(body=body,
sep=sep,
quoting=quoting,
quotechar=quotechar,
lineterminator=lineterminator)
def test_normalize_columns_names_athena():
dataframe = pd.DataFrame({
"CamelCase": [1, 2, 3],
"With Spaces": [4, 5, 6],
"With-Dash": [7, 8, 9],
"Ãccént": [10, 11, 12],
"with.dot": [10, 11, 12],
"Camel_Case2": [13, 14, 15],
"Camel___Case3": [16, 17, 18]
})
Pandas.normalize_columns_names_athena(dataframe=dataframe, inplace=True)
assert dataframe.columns[0] == "camel_case"
assert dataframe.columns[1] == "with_spaces"
assert dataframe.columns[2] == "with_dash"
assert dataframe.columns[3] == "accent"
assert dataframe.columns[4] == "with_dot"
assert dataframe.columns[5] == "camel_case2"
assert dataframe.columns[6] == "camel_case3"
def test_drop_duplicated_columns():
dataframe = pd.DataFrame({
"a": [1, 2, 3],
"b": [4, 5, 6],
"c": [7, 8, 9],
})
dataframe.columns = ["a", "a", "c"]
dataframe = Pandas.drop_duplicated_columns(dataframe=dataframe)
assert dataframe.columns[0] == "a"
assert dataframe.columns[1] == "c"
def test_extract_terminator_profile(body, sep, quotechar, lineterminator, last_index, last_terminator_suspect_index,
first_non_special_byte_index, sep_counter, quote_counter):
profile = Pandas._extract_terminator_profile(body=body,
sep=sep,
quotechar=quotechar,
lineterminator=lineterminator,
last_index=last_index)
assert profile["last_terminator_suspect_index"] == last_terminator_suspect_index
assert profile["first_non_special_byte_index"] == first_non_special_byte_index
assert profile["sep_counter"] == sep_counter
assert profile["quote_counter"] == quote_counter
def test_find_terminator(body, sep, quoting, quotechar, lineterminator, ret):
assert Pandas._find_terminator(body=body,
sep=sep,
quoting=quoting,
quotechar=quotechar,
lineterminator=lineterminator) == ret