fix: unify ColumnNotFound for duckdb and pyspark

narwhals/_duckdb/expr.py

@@ -28,6 +28,7 @@
 from narwhals._duckdb.utils import narwhals_to_native_dtype
 from narwhals._duckdb.utils import when
 from narwhals._expression_parsing import ExprKind
+from narwhals.exceptions import ColumnNotFoundError
 from narwhals.utils import Implementation
 from narwhals.utils import not_implemented
 from narwhals.utils import requires
@@ -186,7 +187,14 @@ def from_column_names(
         context: _FullContext,
     ) -> Self:
         def func(df: DuckDBLazyFrame) -> list[duckdb.Expression]:
-            return [col(name) for name in evaluate_column_names(df)]
+            col_names = evaluate_column_names(df)
+            missing_columns = [c for c in col_names if c not in df.columns]
+            if missing_columns:
+                raise ColumnNotFoundError.from_missing_and_available_column_names(
+                    missing_columns=missing_columns,
+                    available_columns=df.columns,
+                )
+            return [col(name) for name in col_names]
 
         return cls(
             func,

narwhals/_spark_like/dataframe.py

@@ -15,6 +15,7 @@
 from narwhals._spark_like.utils import import_native_dtypes
 from narwhals._spark_like.utils import import_window
 from narwhals._spark_like.utils import native_to_narwhals_dtype
+from narwhals.exceptions import ColumnNotFoundError
 from narwhals.exceptions import InvalidOperationError
 from narwhals.typing import CompliantLazyFrame
 from narwhals.utils import Implementation
@@ -257,6 +258,13 @@ def collect(
         raise ValueError(msg)  # pragma: no cover
 
     def simple_select(self, *column_names: str) -> Self:
+        df_columns = self.columns
+        missing_columns = [c for c in column_names if c not in df_columns]
+        if missing_columns:
+            raise ColumnNotFoundError.from_missing_and_available_column_names(
+                missing_columns=missing_columns,
+                available_columns=df_columns,
+            )
         return self._with_native(self.native.select(*column_names))
 
     def aggregate(

narwhals/_spark_like/expr.py

@@ -20,6 +20,7 @@
 from narwhals._spark_like.utils import import_window
 from narwhals._spark_like.utils import narwhals_to_native_dtype
 from narwhals.dependencies import get_pyspark
+from narwhals.exceptions import ColumnNotFoundError
 from narwhals.utils import Implementation
 from narwhals.utils import not_implemented
 from narwhals.utils import parse_version
@@ -224,7 +225,14 @@ def from_column_names(
         context: _FullContext,
     ) -> Self:
         def func(df: SparkLikeLazyFrame) -> list[Column]:
-            return [df._F.col(col_name) for col_name in evaluate_column_names(df)]
+            col_names = evaluate_column_names(df)
+            missing_columns = [c for c in col_names if c not in df.columns]
+            if missing_columns:
+                raise ColumnNotFoundError.from_missing_and_available_column_names(
+                    missing_columns=missing_columns,
+                    available_columns=df.columns,
+                )
+            return [df._F.col(col_name) for col_name in col_names]
 
         return cls(
             func,

tests/frame/select_test.py

@@ -83,11 +83,7 @@ def test_comparison_with_list_error_message() -> None:
         nw.from_native(pd.Series([[1, 2, 3]]), series_only=True) == [1, 2, 3]  # noqa: B015
 
 
-def test_missing_columns(
-    constructor: Constructor, request: pytest.FixtureRequest
-) -> None:
-    if ("pyspark" in str(constructor)) or "duckdb" in str(constructor):
-        request.applymarker(pytest.mark.xfail)
+def test_missing_columns(constructor: Constructor) -> None:
     data = {"a": [1, 3, 2], "b": [4, 4, 6], "z": [7.0, 8.0, 9.0]}
     df = nw.from_native(constructor(data))
     selected_columns = ["a", "e", "f"]