mirror of
https://github.com/data-privacy-stack/presidio.git
synced 2026-07-23 11:20:55 -05:00
f0dbdce29e
* feat(analyzer): add nine South African predefined recognizers Extend ZA coverage beyond ZA_ID_NUMBER with passport, tax, VAT, CIPC registration, eNaTIS driver's licence and traffic register numbers, licence plates, and mobile/telephone numbers split by line type. All recognizers are disabled by default in default_recognizers.yaml. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(analyzer): update year validation logic in South African recognizers Refactor the year validation logic in the ZaCompanyRegistrationRecognizer and ZaDriverLicenseRecognizer to ensure the current year is accurately checked without allowing for the next year. Remove unnecessary dependency on ZaIdNumberRecognizer in ZaDriverLicenseRecognizer to streamline the code. Update the validate_result method in ZaLicensePlateRecognizer to return a boolean type for consistency. * fix(analyzer): address Copilot review feedback for ZA recognizers Correct 08x NSN fallback classification, tighten driver licence validation, and replace the unstable passport docstring reference. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(analyzer): align ZA driver licence docs and address Copilot round 3 Update driver licence length documentation to 10-14 characters to match validation constraints, and use PhoneNumberMatcher.number directly instead of re-parsing matched substrings. Co-authored-by: Cursor <cursoragent@cursor.com> * Update CHANGELOG.md * Update CHANGELOG.md --------- Co-authored-by: Cursor <cursoragent@cursor.com> Co-authored-by: Sharon Hart <sharonh.dev@gmail.com>
79 lines
2.4 KiB
Python
79 lines
2.4 KiB
Python
"""Tests for South African telephone number (ZA_TELEPHONE_NUMBER) recognizer."""
|
|
|
|
import pytest
|
|
|
|
from presidio_analyzer.predefined_recognizers import ZaTelephoneNumberRecognizer
|
|
|
|
from tests import assert_result_within_score_range
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def recognizer():
|
|
"""Create a ZaTelephoneNumberRecognizer instance for testing."""
|
|
return ZaTelephoneNumberRecognizer()
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def entities():
|
|
"""Return the ZA_TELEPHONE_NUMBER entity type for testing."""
|
|
return ["ZA_TELEPHONE_NUMBER"]
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text, expected_len, expected_positions, expected_score_ranges",
|
|
[
|
|
("011 262 5500", 1, ((0, 12),), ((0.4, 1.0),)),
|
|
("021 447 1234", 1, ((0, 12),), ((0.4, 1.0),)),
|
|
("010 222 0057", 1, ((0, 12),), ((0.4, 1.0),)),
|
|
("(011) 390-9872", 1, ((0, 14),), ((0.4, 1.0),)),
|
|
("0800 123 456", 1, ((0, 12),), ((0.4, 1.0),)),
|
|
("0860 123 456", 1, ((0, 12),), ((0.4, 1.0),)),
|
|
("H(011)3909872", 1, ((1, 13),), ((0.4, 1.0),)),
|
|
(
|
|
"Landline (011) 262-5500 on file.",
|
|
1,
|
|
((9, 23),),
|
|
((0.4, 1.0),),
|
|
),
|
|
(
|
|
"H(011)3909872 B(011)4517333",
|
|
2,
|
|
((1, 13), (15, 27)),
|
|
((0.4, 1.0), (0.4, 1.0)),
|
|
),
|
|
("082 560 9352", 0, (), ()),
|
|
("+27632118258", 0, (), ()),
|
|
("+14155550132", 0, (), ()),
|
|
("1234567890", 0, (), ()),
|
|
("hello world", 0, (), ()),
|
|
],
|
|
)
|
|
def test_when_telephone_in_text_then_all_telephone_numbers_found(
|
|
text,
|
|
expected_len,
|
|
expected_positions,
|
|
expected_score_ranges,
|
|
recognizer,
|
|
entities,
|
|
):
|
|
"""Test that ZA telephone recognizer identifies landline and service numbers."""
|
|
results = recognizer.analyze(text, entities)
|
|
assert len(results) == expected_len
|
|
|
|
for res, (st_pos, fn_pos), (st_score, fn_score) in zip(
|
|
results, expected_positions, expected_score_ranges
|
|
):
|
|
assert_result_within_score_range(
|
|
res, entities[0], st_pos, fn_pos, st_score, fn_score
|
|
)
|
|
|
|
|
|
def test_supported_entity(recognizer):
|
|
"""Test that supported entity is correctly set."""
|
|
assert recognizer.supported_entities == ["ZA_TELEPHONE_NUMBER"]
|
|
|
|
|
|
def test_supported_language(recognizer):
|
|
"""Test that supported language is correctly set."""
|
|
assert recognizer.supported_language == "en"
|