feat(core): _category_of dérivé (anti-dérive) + filtre audit Tier 1 (P1-2/F-1)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 09:54:32 +02:00
parent c93dc34a70
commit b15d0da141
2 changed files with 141 additions and 1 deletions
--- a/tests/unit/test_core_category_gating.py
+++ b/tests/unit/test_core_category_gating.py
@@ -0,0 +1,47 @@
+import anonymizer_core_refactored_onnx as core
+
+
+def test_category_of_each_source():
+    assert core._category_of("NOM_FORCE") == "NOM"          # explicite/regex
+    assert core._category_of("NIR") == "NIR"                # placeholder-self
+    assert core._category_of("NIR_GLOBAL") == "NIR"         # suffixe _GLOBAL
+    assert core._category_of("ADHERENT_GLOBAL") == "ADHERENT"
+    assert core._category_of("VLM_NOM") == "NOM"            # dérivé VLM
+    assert core._category_of("VLM_ETAB") == "ETAB"
+    assert core._category_of("EDS_SECU") == "NIR"           # dérivé EDS (SECU→NIR)
+    assert core._category_of("EDS_HOPITAL") == "ETAB"
+    assert core._category_of("VLM_CP") == "ADRESSE"          # CP suit « Adresses » (Dom 2026-06-26)
+    assert core._category_of("EDS_ZIP") == "ADRESSE"
+
+
+def test_category_of_default_deny():
+    # Non toggleables → None (restent TOUJOURS masqués). Sécurité.
+    # NB : VILLE reste masquée ; seul CODE_POSTAL (VLM_CP/EDS_ZIP) a été basculé vers ADRESSE.
+    for k in ("EMAIL", "IBAN", "IPP", "VILLE", "FAX",
+              "VLM_VILLE", "EMAIL_GLOBAL", "INCONNU_XYZ"):
+        assert core._category_of(k) is None, k
+    # Garde de terminaison de la récursion (_GLOBAL strip) : entrées vides.
+    assert core._category_of(None) is None
+    assert core._category_of("") is None
+
+
+def test_no_toggleable_vlm_or_eds_kind_is_uncategorised():
+    # ANTI-DÉRIVE : tout kind VLM/EDS dont le placeholder est une des 7 catégories
+    # DOIT être catégorisé (sinon toggle faussé sur ce chemin).
+    import vlm_manager, eds_pseudo_manager
+    seven = {"NOM", "DATE_NAISSANCE", "ETAB", "ADRESSE", "NIR", "TEL", "ADHERENT"}
+    for _label, (kind, placeholder) in vlm_manager.VLM_CATEGORY_MAP.items():
+        if core._placeholder_to_category(placeholder) in seven:
+            assert core._category_of(kind) is not None, f"VLM {kind} non catégorisé"
+    for label, placeholder in eds_pseudo_manager.EDS_LABEL_MAP.items():
+        if core._placeholder_to_category(placeholder) in seven:
+            assert core._category_of(f"EDS_{label}") is not None, f"EDS_{label} non catégorisé"
+
+
+def test_filter_audit_drops_only_disabled():
+    PiiHit = core.PiiHit
+    audit = [PiiHit(1, "NOM", "Dupont", "[NOM]"), PiiHit(1, "NIR", "1850574", "[NIR]"),
+             PiiHit(1, "EMAIL", "x@y.fr", "[EMAIL]"), PiiHit(1, "NIR_GLOBAL", "1850574", "[NIR]")]
+    kinds = {h.kind for h in core._filter_audit_by_disabled(audit, {"NIR"})}
+    assert "NIR" not in kinds and "NIR_GLOBAL" not in kinds  # NIR + propagation retirés
+    assert "NOM" in kinds and "EMAIL" in kinds               # autres conservés