"""testing each function in a consecutive way like each one is
executed in in a pipeline
"""

from lang_main.analysis import preprocessing as ppc
from lang_main.analysis import shared


def test_load_data(raw_data_path, raw_data_date_cols):
    (data,) = ppc.load_raw_data(raw_data_path, raw_data_date_cols)
    assert len(data) == 1000


def test_remove_simple_duplicates(raw_data_path, raw_data_date_cols):
    (data,) = ppc.load_raw_data(raw_data_path, raw_data_date_cols)
    (data,) = ppc.remove_duplicates(data)
    assert len(data) == 999


def test_remove_na(raw_data_path, raw_data_date_cols):
    (data,) = ppc.load_raw_data(raw_data_path, raw_data_date_cols)
    (data,) = ppc.remove_duplicates(data)
    target_features: tuple[str] = ('VorgangsBeschreibung',)
    (data,) = ppc.remove_NA(data, target_features)
    assert len(data) == 998


# def test_string_cleansing():
#     string = 'Ölleckage   durch\nundichten \t Ölsumpf,, aber Dichtung intakt??!!!'
#     cleaned_string = shared.clean_string_slim(string)
#     target_string = 'Ölleckage durch undichten Ölsumpf, aber Dichtung intakt!'
#     assert cleaned_string == target_string


def test_entry_wise_cleansing(raw_data_path, raw_data_date_cols):
    (data,) = ppc.load_raw_data(raw_data_path, raw_data_date_cols)
    (data,) = ppc.remove_duplicates(data)
    target_features: tuple[str] = ('VorgangsBeschreibung',)
    (data,) = ppc.remove_NA(data, target_features)
    starting_string = 'Ölleckage   durch\nundichten \t Ölsumpf,, aber Dichtung intakt??!!!'
    cleaned_string = shared.clean_string_slim(starting_string)
    target_string = 'Ölleckage durch undichten Ölsumpf, aber Dichtung intakt!'
    assert cleaned_string == target_string
    starting_string = 'Ölleckage   durch\nundichten    Ölsumpf,, aber Dichtung intakt??!!!'
    assert data.at[0, 'VorgangsBeschreibung'] == starting_string
    (data,) = shared.entry_wise_cleansing(
        data,
        target_features=target_features,
        cleansing_func=shared.clean_string_slim,
    )
    assert data.at[0, 'VorgangsBeschreibung'] == target_string


def test_analyse_feature(raw_data_path, raw_data_date_cols):
    (data,) = ppc.load_raw_data(raw_data_path, raw_data_date_cols)
    (data,) = ppc.remove_duplicates(data)
    target_features: tuple[str] = ('VorgangsBeschreibung',)
    (data,) = ppc.remove_NA(data, target_features)
    starting_string = 'Ölleckage   durch\nundichten \t Ölsumpf,, aber Dichtung intakt??!!!'
    cleaned_string = shared.clean_string_slim(starting_string)
    target_string = 'Ölleckage durch undichten Ölsumpf, aber Dichtung intakt!'
    assert cleaned_string == target_string
    starting_string = 'Ölleckage   durch\nundichten    Ölsumpf,, aber Dichtung intakt??!!!'
    assert data.at[0, 'VorgangsBeschreibung'] == starting_string
    (data,) = shared.entry_wise_cleansing(
        data,
        target_features=target_features,
        cleansing_func=shared.clean_string_slim,
    )
    assert data.at[0, 'VorgangsBeschreibung'] == target_string

    (data,) = ppc.analyse_feature(data, target_feature=target_features[0])
    assert len(data) == 139