Create unit_validator.py

validators/unit_validator.py

@@ -0,0 +1,33 @@
+import math
+import json
+
+def _in_range(val, min_v, max_v):
+    return (val is None) or (min_v <= val <= max_v)
+
+def assert_valid(data: dict, global_policy_path: str):
+    with open(global_policy_path, "r", encoding="utf-8") as f:
+        policy = json.load(f)
+
+    ranges = policy["numeric_ranges"]
+    # Very lightweight checks; the output must contain numeric deltas in the text strings.
+    # Here, we simply ensure required numeric fields in cost/capacity are non-negative,
+    # and clinical sections contain unit tokens.
+    cost = data.get("cost", {})
+    for k in ["startup_per_client", "ongoing_per_client", "total_per_client", "total_for_n"]:
+        v = cost.get(k)
+        if v is None or v < 0:
+            raise ValueError(f"UnitValidator: cost.{k} must be >= 0")
+
+    cap = data.get("capacity", {})
+    if cap.get("total_clients", 0) < 0:
+        raise ValueError("UnitValidator: capacity.total_clients must be >= 0")
+
+    # Check presence of unit tokens in clinical text
+    clin = data.get("clinical_benefits", {})
+    di = (clin.get("diabetes_group") or "").lower()
+    ndi = (clin.get("non_diabetes_group") or "").lower()
+    must_tokens = ["%", "mmhg", "kg/m²"]
+    if not any(tok in di for tok in must_tokens):
+        raise ValueError("UnitValidator: diabetes_group must include units (%, mmHg, kg/m² where applicable).")
+    if not any(tok in ndi for tok in must_tokens):
+        raise ValueError("UnitValidator: non_diabetes_group must include units (%, mmHg, kg/m² where applicable).")