def test_format_index_column(self):
comparable = Compare(order=0)
comparable.header = [{
"column_name": "id",
"column_location": 1,
"column_type": ""
}, {
"column_name": "first_name",
"column_location": 2,
"column_type": "mapped"
}, {
"column_name": "last_name",
"column_location": 3,
"column_type": "duplicate"
}, {
"column_name": "last_name",
"column_location": 4,
"column_type": "duplicate"
}, {
"column_name": "requirement",
"column_location": 5,
"column_type": "mapped"
}, {
"column_name": "alternate_name",
"column_location": 6,
"column_type": ""
}]
comparable.index_column_name = [{
"column_name": "id",
"column_location": 1,
"column_type": ""
}]
header_validator.format_index_column(comparable)
assert comparable.header[0]['column_type'] == "index"
def test_set_map_column_number(self):
comparable = Compare(order=1)
comparable.header = [{
"column_name": "id",
"column_location": 1,
"column_type": ""
}, {
"column_name": "first_name",
"column_location": 2,
"column_type": "mapped"
}, {
"column_name": "last_name",
"column_location": 3,
"column_type": "duplicate"
}, {
"column_name": "last_name",
"column_location": 4,
"column_type": "duplicate"
}, {
"column_name": "requirement",
"column_location": 5,
"column_type": "mapped"
}, {
"column_name": "alternate_name",
"column_location": 6,
"column_type": ""
}]
comparable.index_column_name = [{
"column_name": "id",
"column_location": 1,
"column_type": ""
}]
header_validator.set_map_column_number(comparable)
assert 2 == comparable.number_of_mapped_columns
def test_stringify_index(self, mock_df, mock_index):
comparable = Compare()
comparable.data_frame = mock_df
comparable.index_column_name = mock_index
index_validator.stringify_index(comparable)
for val in comparable.data_frame['id']:
assert isinstance(val, str)
def test_extract_not_checked_column(self):
comparable = Compare()
comparable.header = [
{"column_name": "id", "column_location": 1, "column_type": ""},
{"column_name": "first_name", "column_location": 2, "column_type": ""},
{"column_name": "last_name", "column_location": 3, "column_type": "not_checked"},
{"column_name": "middle_name", "column_location": 3, "column_type": "not_checked"},
{"column_name": "requirement", "column_location": 5, "column_type": "mapped"},
{"column_name": "alternate_name", "column_location": 6, "column_type": ""}]
comparable.index_column_name = [
{"column_name": "id", "column_location": 1}]
data = {
'id': [1, 2, 3],
'first_name': ['f1', 'f2', 'f3'],
'last_name': ['l1', 'l2', 'l3'],
'middle_name': ['m1', 'm2', 'm3'],
'requirement': ['r1', 'r2', 'r3'],
'alternate_name': ['a1', 'a2', 'a3']
}
expected = pd.DataFrame({'last_name': ['l1', 'l2', 'l3'],
'middle_name': ['m1', 'm2', 'm3']})
comparable.data_frame = pd.DataFrame(data)
data_importer.extract_not_checked_column(comparable)
assert expected.equals(comparable.not_checked_column)
def test_validate_index_identity(self):
comparable_a = Compare()
comparable_b = Compare()
comparable_a.header = TestIndexValidator.mock_header
comparable_a.index_column_name = TestIndexValidator.mock_index
comparable_b.header = TestIndexValidator.mock_header
comparable_b.index_column_name = TestIndexValidator.mock_index
data = TestIndexValidator.mock_data_a
comparable_a.data_frame = pd.DataFrame(data)
comparable_b.data_frame = pd.DataFrame(data)
assert cell_comparator.validate_index_identity(comparable_a, comparable_b) is None
def test_sort_index(self, mock_index):
comparable = Compare()
comparable.index_column_name = mock_index
d = {'id': ['1', '2', 'str', 'abc', 'abc']}
comparable.data_frame = pd.DataFrame(data=d, dtype="object")
index_validator.sort_index(comparable)
expected = ['1', '2', 'abc', 'abc', 'str']
assert expected == list(comparable.data_frame['id'])
def test_strip_index(self, mock_df, mock_index):
comparable = Compare()
comparable.data_frame = mock_df
comparable.index_column_name = mock_index
index_validator.strip_index(comparable)
expected = [1, 2, 'str', 'abc', 'abc']
assert expected == list(comparable.data_frame["id"])
def test_check_for_duplicate_index(self, mock_index):
comparable = Compare()
comparable.index_column_name = mock_index
d = {'id': ['dup1', '1', '2', 'dup1', '3', '4']}
comparable.data_frame = pd.DataFrame(data=d, dtype="object")
index_validator.check_for_duplicate_index(comparable)
actual = list(comparable.duplicate_index['id'].values)
expected = ['dup1', 'dup1']
assert expected == actual
def test_check_for_empty_index(self, mock_index):
comparable = Compare()
comparable.index_column_name = mock_index
d = {'id': ['', '', 'str', 'abc', 'abc', '', None, np.nan]}
comparable.data_frame = pd.DataFrame(data=d, dtype="object")
index_validator.check_for_empty_index(comparable)
expected = [0, 1, 5, 6, 7]
actual = comparable.empty_index
assert expected == actual
def test_check_for_disjunctive_index(self, mock_index):
comparable_1 = Compare()
comparable_2 = Compare()
comparable_1.index_column_name = mock_index
comparable_2.index_column_name = mock_index
data1 = {
'id': ['a', 'b', '1', '2', 'c'],
"fname": ['p1', 'q1', 'r1', 's1', 'j1']
}
data2 = {
'id': ['a', 'b', '3', '4', 'c'],
"fname": ['p2', 'q2', 'r2', 's2', 'j2']
}
comparable_1.data_frame = pd.DataFrame(data=data1, dtype="object")
comparable_2.data_frame = pd.DataFrame(data=data2, dtype="object")
index_validator.check_for_disjunctive_index(comparable_1, comparable_2)
expected = ['1', '2']
actual = list(comparable_1.disjunctive_index['id'].values)
assert expected == actual
def test_drop_empty_index(self, mock_index):
comparable = Compare()
comparable.index_column_name = mock_index
d = {'id': ['', '', 'str', 'abc', 'abc', '', None]}
comparable.data_frame = pd.DataFrame(data=d, dtype="object")
comparable.empty_index = [0, 1, 5, 6]
index_validator.drop_empty_index(comparable)
expected = ['str', 'abc', 'abc']
actual = list(comparable.data_frame["id"])
assert expected == actual
def test_drop_duplicate_index(self, mock_index):
comparable = Compare()
comparable.index_column_name = mock_index
d = {'id': ['dup1', 'dup1', 'dup1', 'AAA', 'BBB']}
dup = {'id': ['dup1', 'dup1', 'dup1']}
comparable.data_frame = pd.DataFrame(data=d, dtype="object")
comparable.duplicate_index = pd.DataFrame(data=dup, dtype="object")
index_validator.drop_duplicate_index(comparable)
expected = ['AAA', 'BBB']
actual = list(comparable.data_frame['id'].values)
assert expected == actual
def test_set_index_column_location_when_multiple_index_exist(self):
comparable = Compare()
comparable.index_column_name = [{"column_name": "id"}]
comparable.header = [{
"column_name": "id",
"column_location": 1
}, {
"column_name": "id",
"column_location": 2
}]
with pytest.raises(AppErrorHandler):
header_validator.set_index_column_location(comparable)
def test_drop_disjunctive_index(self, mock_index):
comparable = Compare()
comparable.index_column_name = mock_index
data1 = {
'id': ['1', '2', 'a', 'b', 'c'],
"fname": ['p1', 'q1', 'r1', 's1', 'j1']
}
comparable.data_frame = pd.DataFrame(data=data1, dtype="object")
disjunctive = {'id': ['1', '2']}
comparable.disjunctive_index = pd.DataFrame(data=disjunctive,
dtype="object")
index_validator.drop_disjunctive_index(comparable)
expected = ['a', 'b', 'c']
actual = list(comparable.data_frame['id'].values)
assert expected == actual
def test_remove_white_space_char(self):
comparable = Compare()
comparable.header = TestIndexValidator.mock_header
comparable.index_column_name = TestIndexValidator.mock_index
comparable.data_frame = pd.DataFrame(TestIndexValidator.mock_data_white_space_char)
cell_comparator.remove_non_printable_char(comparable)
expected = pd.DataFrame({
'id': [1, 2, 3],
'first_name': ['f1', 'f 2', 'f3'],
'last_name': ['l1', 'l2', 'l3'],
'middle_name': ['m1', 'm2', 'm3'],
'requirement': ['r1', 'r 2', 'r 3'],
'alternate_name': ['a 1', 'a 2', 'a 3']
})
cell_comparator.remove_white_space_char(comparable)
assert expected.equals(comparable.data_frame)
def test_strip_index_2(self, mock_index):
comparable = Compare()
data1 = pd.DataFrame({
'id': [
' 1 ', '2 ', ' a \n\n',
'\t\t\t b \n', ' c '
],
"fname": ['p1', 'q1', 'r1', 's1', 'j1']
})
expected = pd.DataFrame({
'id': ['1', '2', 'a', 'b', 'c'],
"fname": ['p1', 'q1', 'r1', 's1', 'j1']
})
comparable.index_column_name = mock_index
comparable.data_frame = data1
index_validator.strip_index(comparable)
assert expected.equals(data1)
def test_get_index_name(self, mock_index):
comparable = Compare()
comparable.index_column_name = mock_index
assert index_validator.get_index_name(comparable) == 'id'
def test_create_the_entire_excel_file(self):
comparable_1 = Compare()
comparable_2 = Compare()
comparable_1.order = 0
comparable_1.start_column = 1
comparable_1.end_column = 12
comparable_1.index_column_start = 1
comparable_1.index_column_end = 1
comparable_1.checked_column_start = 2
comparable_1.checked_column_end = 3
comparable_1.not_checked_column_start = 4
comparable_1.not_checked_column_end = 5
comparable_1.disjunctive_column_start = 6
comparable_1.disjunctive_column_end = 7
comparable_1.duplicate_column_start = 8
comparable_1.duplicate_column_end = 9
comparable_1.unnamed_column_start = 10
comparable_1.unnamed_column_end = 11
comparable_1.file_name = "/path/to.my/file/my_first_file___1.csv"
comparable_1.header = [
{
"column_name": "id",
"column_location": 1,
"column_type": "index"
},
{
"column_name": "first_name",
"column_location": 2,
"column_type": "not_checked"
},
{
"column_name": "last_name(@duplicate)",
"column_location": 3,
"column_type": "duplicate"
},
{
"column_name": "last_name(@duplicate)",
"column_location": 4,
"column_type": "duplicate"
},
{
"column_name": "requirement1",
"column_location": 5,
"column_type": "mapped"
},
{
"column_name": "requirement2",
"column_location": 6,
"column_type": "mapped"
},
{
"column_name": "alternate_name",
"column_location": 7,
"column_type": "not_checked"
},
{
"column_name": "@unnamed",
"column_location": 8,
"column_type": "unnamed"
},
{
"column_name": "@unnamed",
"column_location": 9,
"column_type": "unnamed"
},
{
"column_name": "some_name(@NotFound)",
"column_location": 10,
"column_type": "disjunctive"
},
{
"column_name": "some_name(@NotFound)",
"column_location": 11,
"column_type": "disjunctive"
},
]
comparable_1.index_column_name = [{
"column_name": "id",
"column_location": 1,
"column_type": ""
}]
comparable_2.header = [
{
"column_name": "id",
"column_location": 1,
"column_type": "index"
},
{
"column_name": "first_name",
"column_location": 2,
"column_type": "not_checked"
},
{
"column_name": "last_name(@duplicate.4)",
"column_location": 4,
"column_type": "duplicate"
},
{
"column_name": "last_name(@duplicate.3)",
"column_location": 3,
"column_type": "duplicate"
},
{
"column_name": "requirement1",
"column_location": 5,
"column_type": "mapped"
},
{
"column_name": "requirement2",
"column_location": 6,
"column_type": "mapped"
},
{
"column_name": "alternate_name",
"column_location": 7,
"column_type": "not_checked"
},
{
"column_name": "@unnamed.8",
"column_location": 8,
"column_type": "unnamed"
},
{
"column_name": "@unnamed.9",
"column_location": 9,
"column_type": "unnamed"
},
{
"column_name": "some_name(@NotFound.10)",
"column_location": 10,
"column_type": "disjunctive"
},
{
"column_name": "some_name(@NotFound.11)",
"column_location": 11,
"column_type": "disjunctive"
},
]
comparable_2.index_column_name = [{
"column_name": "id",
"column_location": 1,
"column_type": ""
}]
comparable_2.order = 1
comparable_2.start_column = 12
comparable_2.end_column = 22
comparable_2.index_column_start = 12
comparable_2.index_column_end = 12
comparable_2.checked_column_start = 13
comparable_2.checked_column_end = 14
comparable_2.not_checked_column_start = 15
comparable_2.not_checked_column_end = 16
comparable_2.disjunctive_column_start = 17
comparable_2.disjunctive_column_end = 18
comparable_2.duplicate_column_start = 19
comparable_2.duplicate_column_end = 20
comparable_2.unnamed_column_start = 21
comparable_2.unnamed_column_end = 22
comparable_2.hide_duplicate_columns = True
comparable_2.hide_unnamed_columns = True
comparable_2.hide_disjunctive_columns = True
comparable_2.file_name = "/path/to.my/file/my_second_file__2.csv"
Compare.output_path = "./"
Compare.worksheet_name = "Master"
data_exporter.create_name_for_output_file(comparable_1, comparable_2)
data_exporter.create_excel_workbook()
data_exporter.create_excel_worksheet()
data_exporter.add_local_excel_format([comparable_1, comparable_2])
data_exporter.apply_column_general_format([comparable_1, comparable_2])
data_exporter.write_file_name_label()
data_exporter.write_file_name_title([comparable_1, comparable_2])
data_exporter.write_column_type_label()
data_exporter.write_index_column_type_title(
[comparable_1, comparable_2])
data_exporter.write_checked_column_type_title(
[comparable_1, comparable_2])
data_exporter.write_not_checked_column_type_title(
[comparable_1, comparable_2])
data_exporter.write_disjunctive_column_type_title(
[comparable_1, comparable_2])
data_exporter.write_duplicate_column_type_title(
[comparable_1, comparable_2])
data_exporter.write_unnamed_column_type_title(
[comparable_1, comparable_2])
data_exporter.apply_checked_column_hide_condition(
[comparable_1, comparable_2])
data_exporter.apply_not_checked_column_hide_condition(
[comparable_1, comparable_2])
data_exporter.apply_disjunctive_column_hide_condition(
[comparable_1, comparable_2])
data_exporter.apply_duplicate_column_hide_condition(
[comparable_1, comparable_2])
data_exporter.apply_unnamed_column_hide_condition(
[comparable_1, comparable_2])
data_exporter.write_column_name_label()
data_exporter.write_index_column_name([comparable_1, comparable_2])
data_exporter.write_checked_column_name([comparable_1, comparable_2])
data_exporter.write_not_checked_column_name(
[comparable_1, comparable_2])
data_exporter.write_disjunctive_column_name(
[comparable_1, comparable_2])
data_exporter.write_duplicate_column_name([comparable_1, comparable_2])
data_exporter.write_unnamed_column_name([comparable_1, comparable_2])
data_exporter.close_excel_workbook()
def test_set_index_column_location(self):
comparable = Compare()
comparable.index_column_name = [{"column_name": "id"}]
comparable.header = [{"column_name": "id", "column_location": 1}]
assert header_validator.set_index_column_location(comparable) is None
def test_check_for_index_name_existence_when_index_does_not_exist(self):
comparable = Compare()
comparable.index_column_name = [{"column_name": "id"}]
comparable.header = [{"column_name": "id1", "column_location": 1}]
with pytest.raises(AppErrorHandler):
header_validator.check_for_index_name_existence(comparable)
def test_check_for_index_name_existence(self):
comparable = Compare()
comparable.index_column_name = [{"column_name": "id"}]
comparable.header = [{"column_name": "id", "column_location": 1}]
assert header_validator.check_for_index_name_existence(
comparable) is None
