Merge branch 'main' into refactor_limit

datafusion/common/src/scalar/mod.rs

@@ -6603,7 +6603,7 @@ mod tests {
         let not_nulls = not_nulls.finish();
         let not_nulls = Some(NullBuffer::new(not_nulls));
 
-        let ar = unsafe { StructArray::new_unchecked(fields, arrays, not_nulls) };
+        let ar = StructArray::new(fields, arrays, not_nulls);
         let s = ScalarValue::Struct(Arc::new(ar));
 
         assert_eq!(s.to_string(), "{a:1,b:2}");

datafusion/core/tests/fuzz_cases/window_fuzz.rs

@@ -45,8 +45,7 @@ use datafusion_physical_expr::{PhysicalExpr, PhysicalSortExpr};
 use test_utils::add_empty_batches;
 
 use datafusion::functions_window::row_number::row_number_udwf;
-use datafusion_functions_window::dense_rank::dense_rank_udwf;
-use datafusion_functions_window::rank::rank_udwf;
+use datafusion_functions_window::rank::{dense_rank_udwf, rank_udwf};
 use hashbrown::HashMap;
 use rand::distributions::Alphanumeric;
 use rand::rngs::StdRng;

datafusion/expr-common/src/columnar_value.rs

@@ -17,8 +17,7 @@
 
 //! [`ColumnarValue`] represents the result of evaluating an expression.
 
-use arrow::array::ArrayRef;
-use arrow::array::NullArray;
+use arrow::array::{Array, ArrayRef, NullArray};
 use arrow::compute::{kernels, CastOptions};
 use arrow::datatypes::{DataType, TimeUnit};
 use datafusion_common::format::DEFAULT_CAST_OPTIONS;
@@ -218,6 +217,17 @@ impl ColumnarValue {
             }
         }
     }
+
+    /// Converts an [`ArrayRef`] to a [`ColumnarValue`] based on the supplied arguments.
+    /// This is useful for scalar UDF implementations to fulfil their contract:
+    /// if all arguments are scalar values, the result should also be a scalar value.
+    pub fn from_args_and_result(args: &[Self], result: ArrayRef) -> Result<Self> {
+        if result.len() == 1 && args.iter().all(|arg| matches!(arg, Self::Scalar(_))) {
+            Ok(Self::Scalar(ScalarValue::try_from_array(&result, 0)?))
+        } else {
+            Ok(Self::Array(result))
+        }
+    }
 }
 
 #[cfg(test)]

datafusion/functions-window/src/lib.rs

@@ -31,16 +31,12 @@ use datafusion_expr::WindowUDF;
 
 #[macro_use]
 pub mod macros;
-pub mod dense_rank;
-pub mod percent_rank;
 pub mod rank;
 pub mod row_number;
 
 /// Fluent-style API for creating `Expr`s
 pub mod expr_fn {
-    pub use super::dense_rank::dense_rank;
-    pub use super::percent_rank::percent_rank;
-    pub use super::rank::rank;
+    pub use super::rank::{dense_rank, percent_rank, rank};
     pub use super::row_number::row_number;
 }
 
@@ -49,8 +45,8 @@ pub fn all_default_window_functions() -> Vec<Arc<WindowUDF>> {
     vec![
         row_number::row_number_udwf(),
         rank::rank_udwf(),
-        dense_rank::dense_rank_udwf(),
-        percent_rank::percent_rank_udwf(),
+        rank::dense_rank_udwf(),
+        rank::percent_rank_udwf(),
     ]
 }
 /// Registers all enabled packages with a [`FunctionRegistry`]

datafusion/functions-window/src/macros.rs

@@ -303,7 +303,7 @@ macro_rules! create_udwf_expr {
     ($UDWF:ident, $OUT_FN_NAME:ident, $DOC:expr) => {
         paste::paste! {
             #[doc = " Create a [`WindowFunction`](datafusion_expr::Expr::WindowFunction) expression for"]
-            #[doc = concat!(" [`", stringify!($UDWF), "`] user-defined window function.")]
+            #[doc = concat!(" `", stringify!($UDWF), "` user-defined window function.")]
             #[doc = ""]
             #[doc = concat!(" ", $DOC)]
             pub fn $OUT_FN_NAME() -> datafusion_expr::Expr {
@@ -316,7 +316,7 @@ macro_rules! create_udwf_expr {
     ($UDWF:ident, $OUT_FN_NAME:ident, [$($PARAM:ident),+], $DOC:expr) => {
         paste::paste! {
             #[doc = " Create a [`WindowFunction`](datafusion_expr::Expr::WindowFunction) expression for"]
-            #[doc = concat!(" [`", stringify!($UDWF), "`] user-defined window function.")]
+            #[doc = concat!(" `", stringify!($UDWF), "` user-defined window function.")]
             #[doc = ""]
             #[doc = concat!(" ", $DOC)]
             pub fn $OUT_FN_NAME(