Merge pull request #269 from VictoriaAdjeiQC/predicates_validation

Further validation for non-scalar values inside `check_predicates`

Author: fjetter

CHANGES.rst

@@ -2,6 +2,12 @@
 Changelog
 =========
 
+Plateau 4.6.2 (2025-08-XX)
+==========================
+
+* Add further validation for predicates to raise errors if operators are misused with non-scalar values
+
+
 Plateau 4.6.1 (2025-08-13)
 ==========================
 

plateau/serialization/_generic.py

@@ -203,9 +203,19 @@ def check_predicates(predicates: PredicatesType) -> None:
             ):
                 raise ValueError(
                     f"Invalid predicates: Clause {clause_idx} in conjunction {conjunction_idx} "
-                    f"with null value and operator {op}. Only operators supporting null values "
+                    f"with null value and operator '{op}'. Only operators supporting null values "
                     "are '==', '!=', 'in' and 'is distinct from'."
                 )
+            if op == "in" and pd.api.types.is_scalar(val):
+                raise ValueError(
+                    f"Invalid predicates in clause {clause_idx} in conjunction {conjunction_idx} "
+                    f"with operator '{op}' must be used with a tuple or list, got {type(val)} instead."
+                )
+            if op != "in" and is_list_like(val):
+                raise ValueError(
+                    f"Invalid predicates in clause {clause_idx} in conjunction {conjunction_idx} "
+                    f"with operator '{op}' must be used with a scalar type, got {type(val)} instead."
+                )
 
 
 def filter_predicates_by_column(

tests/io_components/test_read.py

@@ -25,7 +25,19 @@ def test_dispatch_metapartitions(dataset, store_session):
 
 @pytest.mark.parametrize(
     "predicates,error_msg",
-    [([], "Empty predicates"), ([[]], "Invalid predicates: Conjunction 0 is empty")],
+    [
+        ([], "Empty predicates"),
+        ([[]], "Invalid predicates: Conjunction 0 is empty"),
+        (
+            [[("mycol", "in", None)]],
+            "Invalid predicates: Clause 0 in conjunction 0 with null value and operator 'in'.",
+        ),
+        (
+            [[("mycol", "in", "scalar")]],
+            "operator 'in' must be used with a tuple or list",
+        ),
+        ([[("mycol", "<", [17, 12])]], "operator '<' must be used with a scalar type"),
+    ],
 )
 def test_dispatch_metapartition_undefined_behaviour(
     dataset, store_session, predicates, error_msg