feat: Add type error for pathological non-Column members in Schema (#159)

Co-authored-by: Andreas Albert <[email protected]>
Co-authored-by: Juraj Mičko <[email protected]>

Author: 3 people

dataframely/_base_schema.py

@@ -137,6 +137,29 @@ def __new__(
                         f"which are not in the schema: {missing_list}."
                     )
 
+        # 3) Check that all members are non-pathological (i.e., user errors).
+        for attr, value in namespace.items():
+            if attr.startswith("__"):
+                continue
+            # Check for tuple of column (commonly caused by trailing comma)
+            if (
+                isinstance(value, tuple)
+                and len(value) > 0
+                and isinstance(value[0], Column)
+            ):
+                raise TypeError(
+                    f"Column '{attr}' is defined as a tuple of dy.Column. "
+                    f"Did you accidentally add a trailing comma?"
+                )
+
+            # Check for column type instead of instance (e.g., dy.Float64 instead of dy.Float64())
+            if isinstance(value, type) and issubclass(value, Column):
+                raise TypeError(
+                    f"Column '{attr}' is a type, not an instance. "
+                    f"Schema members must be of type Column not type[Column]. "
+                    f"Did you forget to add parentheses?"
+                )
+
         return super().__new__(mcs, name, bases, namespace, *args, **kwargs)
 
     def __getattribute__(cls, name: str) -> Any:

tests/schema/test_base.py

@@ -95,3 +95,34 @@ def test_dunder_name() -> None:
 
 def test_dunder_name_with_rule() -> None:
     assert MySchemaWithRule.__name__ == "MySchemaWithRule"
+
+
+def test_non_column_member_is_allowed() -> None:
+    class MySchemaWithNonColumnMembers(dy.Schema):
+        a = dy.Int32(nullable=False)
+        version: int = 1
+        useful_tuple: tuple[int, int] = (1, 2)
+
+    columns = MySchemaWithNonColumnMembers.columns()
+    assert "a" in columns
+    assert "version" not in columns
+    assert "useful_tuple" not in columns
+    assert MySchemaWithNonColumnMembers.version == 1
+    assert MySchemaWithNonColumnMembers.useful_tuple == (1, 2)
+
+
+def test_user_error_tuple_column() -> None:
+    with pytest.raises(TypeError, match="tuple"):
+
+        class MySchemaWithTupleOfColumn(dy.Schema):
+            a = dy.Int32(nullable=False)
+            b = (dy.Int32(nullable=False),)  # User error: Trailing comma = tuple
+            c = dy.Int32(nullable=False)
+
+
+def test_user_error_column_type_not_instance() -> None:
+    with pytest.raises(TypeError, match="type, not an instance"):
+
+        class MySchemaWithColumnTypeNotInstance(dy.Schema):
+            a = dy.Int32(nullable=False, primary_key=True)
+            b = dy.Float64  # User error: Forgot parentheses!