Spaces:
Sleeping
Sleeping
File size: 2,358 Bytes
68f0a4a 48ed660 68f0a4a 48ed660 68f0a4a 48ed660 68f0a4a 48ed660 68f0a4a | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 | from candidate_scanner import scan_unmasked_candidates
from test_cases.legal_regression_cases import (
CANDIDATE_SCANNER_TEXT,
EXPECTED_CANDIDATES,
EXPECTED_CANDIDATE_TYPES,
NEGATIVE_VALUES,
)
def test_candidate_scanner_finds_expected_reference_like_values():
rows = scan_unmasked_candidates(CANDIDATE_SCANNER_TEXT, analyzer_results=[])
found = {row["text"] for row in rows}
missing = EXPECTED_CANDIDATES - found
assert not missing, f"Expected candidates were not found: {sorted(missing)}"
def test_candidate_scanner_assigns_expected_reference_categories():
rows = scan_unmasked_candidates(CANDIDATE_SCANNER_TEXT, analyzer_results=[])
by_text = {row["text"]: row["entity_type"] for row in rows}
mismatches = {
value: {"expected": expected_type, "actual": by_text.get(value)}
for value, expected_type in EXPECTED_CANDIDATE_TYPES.items()
if by_text.get(value) != expected_type
}
assert not mismatches, f"Candidate type mismatches: {mismatches}"
def test_candidate_scanner_does_not_suggest_known_false_positives():
rows = scan_unmasked_candidates(CANDIDATE_SCANNER_TEXT, analyzer_results=[])
found = {row["text"] for row in rows}
unexpected = NEGATIVE_VALUES & found
assert not unexpected, f"False-positive values were suggested: {sorted(unexpected)}"
def test_candidate_scanner_preserves_context_by_returning_value_only():
rows = scan_unmasked_candidates(CANDIDATE_SCANNER_TEXT, analyzer_results=[])
found = {row["text"] for row in rows}
assert "reparatienummer REP-2026-4410" not in found
assert "intern incidentnummer INC-2026-0912" not in found
assert "kenteken XX123X" not in found
assert "KvK-nummer vennootschap: 76543210" not in found
assert "REP-2026-4410" in found
assert "INC-2026-0912" in found
assert "XX123X" in found
assert "76543210" in found
def test_candidate_scanner_respects_existing_analyzer_spans():
start = CANDIDATE_SCANNER_TEXT.index("REP-2026-4410")
end = start + len("REP-2026-4410")
class ExistingResult:
pass
existing = ExistingResult()
existing.start = start
existing.end = end
rows = scan_unmasked_candidates(CANDIDATE_SCANNER_TEXT, analyzer_results=[existing])
found = {row["text"] for row in rows}
assert "REP-2026-4410" not in found
|