def test_given_several_results_then_we_filter_them_and_get_correct_mocked_result(
):
analyzer_results = [
RecognizerResult(start=48, end=57, score=0.55, entity_type="SSN"),
RecognizerResult(start=24, end=32, score=0.6, entity_type="FULL_NAME"),
RecognizerResult(start=24, end=28, score=0.9,
entity_type="FIRST_NAME"),
RecognizerResult(start=29, end=32, score=0.6, entity_type="LAST_NAME"),
RecognizerResult(start=24, end=30, score=0.8, entity_type="NAME"),
RecognizerResult(start=18, end=32, score=0.8, entity_type="BLA"),
RecognizerResult(start=23, end=35, score=0.8, entity_type="BLA"),
RecognizerResult(start=28, end=36, score=0.8, entity_type="BLA"),
RecognizerResult(start=48,
end=57,
score=0.95,
entity_type="PHONE_NUMBER")
]
operator_config = OperatorConfig("replace", {})
operator_config.operator_name = ""
engine = AnonymizerEngine()
engine._operate = _operate
result = engine.anonymize(
"hello world, my name is Jane Doe. My number is: 034453334",
analyzer_results, {"DEFAULT": operator_config})
assert result.text == "Number: I am your new text!"
assert len(result.items) == 1
assert result.items[0].operator == "hash"
assert result.items[0].entity_type == "type"
assert result.items[0].start == 0
assert result.items[0].end == 35
assert result.items[0].text == "text"
def test_given_specific_anonymizer_then_we_use_it():
engine = AnonymizerEngine()
text = "please REPLACE ME."
analyzer_result = RecognizerResult("SSN", 7, 17, 0.8)
anonymizer_config = OperatorConfig("replace",
{"new_value": "and thank you"})
ssn_anonymizer_config = OperatorConfig("redact", {})
result = engine.anonymize(
text,
[analyzer_result],
{
"DEFAULT": anonymizer_config,
"SSN": ssn_anonymizer_config
},
).text
assert result == "please ."
def anonymize_reverse_lambda(analyzer_results, text_to_anonymize):
anonymized_results = anonymizer.anonymize(
text=text_to_anonymize,
analyzer_results=analyzer_results,
operators={"EMAIL_ADDRESS": OperatorConfig("custom", {"lambda": lambda x: x[::-1]})}
)
return anonymized_results
def anonymize_faker_lambda(analyzer_results, text_to_anonymize):
anonymized_results = anonymizer.anonymize(
text=text_to_anonymize,
analyzer_results=analyzer_results,
operators={"EMAIL_ADDRESS": OperatorConfig("custom", {"lambda": lambda x: fake.safe_email()})}
)
return anonymized_results
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], {})
@pytest.mark.parametrize(
# fmt: off
"anonymizers, result_text",
[
({
"number": OperatorConfig("fake")
}, "Invalid operator class 'fake'."),
],
# fmt: on
)
def test_given_invalid_json_for_anonymizers_then_we_fail(
anonymizers, result_text):
with pytest.raises(InvalidParamException, match=result_text):
AnonymizerEngine().anonymize("this is my text",
[RecognizerResult("number", 0, 4, 0)],
anonymizers)
def test_given_several_results_then_we_filter_them_and_get_correct_mocked_result(
):
analyzer_results = [