vignette/apps/api/app/test_pii_masking_eval.py

70 lines
2.3 KiB
Python

import json
import subprocess
import sys
import unittest
from pathlib import Path
from unittest.mock import patch
from app.services import guardrail
from app.services.pii_masking_eval import evaluate_fixture, load_cases
REPO_ROOT = Path(__file__).resolve().parents[3]
FIXTURE_PATH = REPO_ROOT / "data" / "privacy" / "pii-masking-ko-fixtures.json"
SCRIPT_PATH = REPO_ROOT / "scripts" / "evaluate-pii-masking.py"
class PiiMaskingEvalTests(unittest.TestCase):
def setUp(self) -> None:
self.presidio_patch = patch.object(
guardrail,
"_try_load_presidio",
return_value=(None, None),
)
self.presidio_patch.start()
self.addCleanup(self.presidio_patch.stop)
def test_fixture_cases_are_valid_json_list(self) -> None:
cases = load_cases(FIXTURE_PATH)
self.assertGreaterEqual(len(cases), 5)
self.assertTrue(all(case.get("id") for case in cases))
self.assertTrue(all(case.get("text") for case in cases))
def test_ko_name_org_fixture_passes_without_raw_identifier_leak(self) -> None:
report = evaluate_fixture(FIXTURE_PATH)
self.assertTrue(report["passed"], report)
self.assertEqual(report["cases_failed"], 0)
self.assertEqual(report["expected_entity_recall"], 1.0)
self.assertEqual(report["forbidden_substring_removal"], 1.0)
self.assertEqual(report["unexpected_entity_violations"], 0)
blob = json.dumps(report, ensure_ascii=False)
for raw in ("김서연", "박민수", "한신대학교", "상담심리학과", "마음봄상담센터"):
self.assertNotIn(raw, blob)
def test_cli_reports_json_and_nonzero_gate_shape(self) -> None:
completed = subprocess.run(
[
sys.executable,
"-X",
"utf8",
str(SCRIPT_PATH),
"--fixtures",
str(FIXTURE_PATH),
"--json",
],
cwd=str(REPO_ROOT),
check=True,
capture_output=True,
text=True,
encoding="utf-8",
)
report = json.loads(completed.stdout)
self.assertTrue(report["passed"])
self.assertEqual(report["cases_total"], 5)
if __name__ == "__main__":
unittest.main()