def test_given_anonymize_with_encrypt_then_text_returned_with_encrypted_content():
unencrypted_text = "My name is "
expected_encrypted_text = "Chloë"
text = unencrypted_text + expected_encrypted_text
start_index = 11
end_index = 16
key = "WmZq4t7w!z%C&F)J"
analyzer_results = [RecognizerResult("PERSON", start_index, end_index, 0.8)]
anonymizers_config = {"PERSON": OperatorConfig("encrypt", {"key": key})}
actual_anonymize_result = (
AnonymizerEngine().anonymize(text, analyzer_results, anonymizers_config)
)
assert len(actual_anonymize_result.items) == 1
anonymized_entities = [
AnonymizerResult.from_operator_result(actual_anonymize_result.items[0])
]
engine = DeanonymizeEngine()
decryption = engine.deanonymize(
actual_anonymize_result.text, anonymized_entities,
{"PERSON": OperatorConfig(Decrypt.NAME, {"key": key})}
)
assert decryption.text == "My name is Chloë"
assert len(decryption.items) == 1
assert decryption.items[0].text == "Chloë"
assert decryption.items[0].end == 16
assert decryption.items[0].start == 11
assert decryption.items[0].entity_type == "PERSON"
def test_given_empty_text_to_engine_then_we_fail():
engine = AnonymizerEngine()
analyzer_result = RecognizerResult("SSN", 0, 1, 0.5)
with pytest.raises(
InvalidParamException, match="Invalid input, text can not be empty"
):
engine.anonymize("", [analyzer_result], {})
def test_given_default_anonymizer_then_we_use_it():
engine = AnonymizerEngine()
text = "please REPLACE ME."
analyzer_result = RecognizerResult("SSN", 7, 17, 0.8)
anonymizer_config = AnonymizerConfig("replace", {"new_value": "and thank you"})
result = engine.anonymize(
text, [analyzer_result], {"DEFAULT": anonymizer_config}
).text
assert result == "please and thank you."
def test_given_analyzer_result_with_an_incorrect_text_positions_then_we_fail(
original_text, start, end
):
engine = AnonymizerEngine()
analyzer_result = RecognizerResult("type", start, end, 0.5)
err_msg = (
f"Invalid analyzer result, start: {start} and end: "
f"{end}, while text length is only 11."
)
with pytest.raises(InvalidParamException, match=err_msg):
engine.anonymize(original_text, [analyzer_result], {})
def test_given_several_anonymizers_then_we_use_the_correct_one():
analyzer_result = RecognizerResult.from_json(
{"score": 0.5, "entity_type": "PHONE_NUMBER", "start": 8, "end": 18}
)
anonymizer_config = AnonymizerConfig("replace", {})
anonymizer_config.anonymizer_class = MockAnonymizer
text = (
AnonymizerEngine()
.anonymize(
"Number: 0554555556", [analyzer_result], {"PHONE_NUMBER": anonymizer_config}
)
.text
)
assert text == "Number: I am your new text!"
def handle_analyzer_results_json(cls, data: Dict) -> AnalyzerResults:
"""
Go over analyzer results, validate them and convert to List[AnalyzeResult].
:param data: contains the anonymizers and analyzer_results_json
"""
analyzer_results = AnalyzerResults()
analyzer_results_json = data.get("analyzer_results")
if analyzer_results_json is None:
cls.logger.debug(
"invalid input, json missing field: analyzer_results_json")
raise InvalidParamException(
"Invalid input, "
"request must contain analyzer results")
for analyzer_result in analyzer_results_json:
analyzer_result = RecognizerResult.from_json(analyzer_result)
analyzer_results.append(analyzer_result)
return analyzer_results
def test_given_anonymize_with_encrypt_then_text_returned_with_encrypted_content(
):
unencrypted_text = "My name is "
expected_encrypted_text = "Chloë"
text = unencrypted_text + expected_encrypted_text
start_index = 11
end_index = 16
key = "WmZq4t7w!z%C&F)J"
analyzer_results = [
RecognizerResult("PERSON", start_index, end_index, 0.8)
]
anonymizers_config = {"PERSON": AnonymizerConfig("encrypt", {"key": key})}
actual_anonymize_result = (AnonymizerEngine().anonymize(
text, analyzer_results, anonymizers_config).text)
assert actual_anonymize_result[:start_index] == unencrypted_text
actual_encrypted_text = actual_anonymize_result[start_index:]
assert actual_encrypted_text != expected_encrypted_text
actual_decrypted_text = AESCipher.decrypt(key.encode(),
actual_encrypted_text)
assert actual_decrypted_text == expected_encrypted_text
def test_given_none_as_anonymziers_list_then_we_fall_to_default():
engine = AnonymizerEngine()
text = "please REPLACE ME."
analyzer_result = RecognizerResult("SSN", 7, 17, 0.8)
result = engine.anonymize(text, [analyzer_result]).text
assert result == "please <SSN>."
def create_recognizer_result(entity_type: str, score: float, start: int, end: int):
data = {"entity_type": entity_type, "score": score, "start": start, "end": end}
return RecognizerResult.from_json(data)
def test_given_json_for_creating_recognizer_result_without_text_then_creation_fails(
request_json, result_text
):
with pytest.raises(InvalidParamException) as e:
RecognizerResult.from_json(request_json)
assert result_text == e.value.err_msg