Fix PySpark struct() to accept a list of columns (#17189)

The struct() function now unwraps a single list or set argument,
matching the PySpark API behavior and the existing array() function
in this codebase.

Author: Carson Jones

duckdb/experimental/spark/sql/functions.py

@@ -122,7 +122,9 @@ def _inner_expr_or_val(val: Union[Column, str]) -> Union[Column, str]:
     return val.expr if isinstance(val, Column) else val
 
 
-def struct(*cols: Column) -> Column:  # noqa: D103
+def struct(*cols: Union["ColumnOrName", list["ColumnOrName"], tuple["ColumnOrName", ...]]) -> Column:  # noqa: D103
+    if len(cols) == 1 and isinstance(cols[0], (list, set)):
+        cols = cols[0]
     return Column(FunctionExpression("struct_pack", *[_inner_expr_or_val(x) for x in cols]))
 
 

tests/fast/spark/test_spark_column.py

@@ -35,6 +35,14 @@ def test_struct_column(self, spark):
         ):
             df = df.withColumn("struct", "yes")
 
+    def test_struct_column_with_list(self, spark):
+        df = spark.createDataFrame([("Alice", 2), ("Bob", 5)], ("name", "age"))
+        res = df.select(struct([df.age, df.name]).alias("struct")).collect()
+        assert res == [
+            Row(struct=Row(age=2, name="Alice")),
+            Row(struct=Row(age=5, name="Bob")),
+        ]
+
     def test_array_column(self, spark):
         df = spark.createDataFrame([Row(a=1, b=2, c=3, d=4)], ["a", "b", "c", "d"])