mirror of
https://github.com/open-metadata/OpenMetadata.git
synced 2025-10-31 02:29:03 +00:00
a7e2f33adc
* Add PII Tag and Sensitivity Level enums. * Add feature-extraction for PII classification tasks * Add faker as test dependency * Add unit tests for presidio tag extractor * Add PIISensitivityTags enum and update sensitivity mapping logic * Add Presidio utility functions for PII analysis * Extend column name regexs for PII * Add colum name split * Move pii algorithms to dedicated package * Add tests for PAN, NIF, SSN entities * Fix linting * Add comment on why we need to set specific lanaguage to Presidio recognizers, as per PR suggestion. * Fix version of faker to prevent flaky tests. Fix failing tests. * Fix wrong import --------- Co-authored-by: Pere Menal <pere.menal@getcollate.io>
43 lines
1.5 KiB
Python
43 lines
1.5 KiB
Python
# Copyright 2025 Collate
|
|
# Licensed under the Collate Community License, Version 1.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
# https://github.com/open-metadata/OpenMetadata/blob/main/ingestion/LICENSE
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
import pytest
|
|
|
|
from metadata.pii.algorithms.preprocessing import convert_to_str, preprocess_values
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"input_value,expected",
|
|
[
|
|
("hello", "hello"),
|
|
(123, "123"),
|
|
(123.45, "123.45"),
|
|
(b"hello", "hello"),
|
|
(None, None),
|
|
({"key": "value"}, '{"key": "value"}'),
|
|
({1, 2, 3}, None), # Sets cannot be converted to JSON
|
|
],
|
|
)
|
|
def test_converts_various_types_to_string(input_value, expected):
|
|
assert convert_to_str(input_value) == expected
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"input_values,expected",
|
|
[
|
|
(["hello", 123, None, b"world", "", " "], ["hello", "123", "world"]),
|
|
([], []),
|
|
([None, "", " "], []),
|
|
([{"key": "value"}, [1, 2, 3]], ['{"key": "value"}', "[1, 2, 3]"]),
|
|
],
|
|
)
|
|
def test_preprocesses_sequences_correctly(input_values, expected):
|
|
assert preprocess_values(input_values) == expected
|