Derive UDF equality from PartialEq, Hash

Reduce boilerplate in cases where implementation of
`{ScalarUDFImpl,AggregateUDFImpl,WindowUDFImpl}::{equals,hash_code}` can
be derived using standard `PartialEq` and `Hash` traits.

This is code complexity reduction.

This also prepares for more automatic derivation of UDF equals/hash
and/or removal of default implementations (which currently are
error-prone).

Author: findepi

datafusion/core/tests/user_defined/user_defined_scalar_functions.rs

@@ -43,9 +43,9 @@ use datafusion_common::{
 use datafusion_expr::expr::FieldMetadata;
 use datafusion_expr::simplify::{ExprSimplifyResult, SimplifyInfo};
 use datafusion_expr::{
-    lit_with_metadata, Accumulator, ColumnarValue, CreateFunction, CreateFunctionBody,
-    LogicalPlanBuilder, OperateFunctionArg, ReturnFieldArgs, ScalarFunctionArgs,
-    ScalarUDF, ScalarUDFImpl, Signature, Volatility,
+    lit_with_metadata, udf_equals_hash, Accumulator, ColumnarValue, CreateFunction,
+    CreateFunctionBody, LogicalPlanBuilder, OperateFunctionArg, ReturnFieldArgs,
+    ScalarFunctionArgs, ScalarUDF, ScalarUDFImpl, Signature, Volatility,
 };
 use datafusion_functions_nested::range::range_udf;
 use parking_lot::Mutex;
@@ -517,7 +517,7 @@ async fn test_user_defined_functions_with_alias() -> Result<()> {
 }
 
 /// Volatile UDF that should append a different value to each row
-#[derive(Debug)]
+#[derive(Debug, PartialEq, Hash)]
 struct AddIndexToStringVolatileScalarUDF {
     name: String,
     signature: Signature,
@@ -586,33 +586,7 @@ impl ScalarUDFImpl for AddIndexToStringVolatileScalarUDF {
         Ok(ColumnarValue::Array(Arc::new(StringArray::from(answer))))
     }
 
-    fn equals(&self, other: &dyn ScalarUDFImpl) -> bool {
-        let Some(other) = other.as_any().downcast_ref::<Self>() else {
-            return false;
-        };
-        let Self {
-            name,
-            signature,
-            return_type,
-        } = self;
-        name == &other.name
-            && signature == &other.signature
-            && return_type == &other.return_type
-    }
-
-    fn hash_value(&self) -> u64 {
-        let Self {
-            name,
-            signature,
-            return_type,
-        } = self;
-        let mut hasher = DefaultHasher::new();
-        std::any::type_name::<Self>().hash(&mut hasher);
-        name.hash(&mut hasher);
-        signature.hash(&mut hasher);
-        return_type.hash(&mut hasher);
-        hasher.finish()
-    }
+    udf_equals_hash!(ScalarUDFImpl);
 }
 
 #[tokio::test]

datafusion/expr/src/utils.rs

@@ -1260,6 +1260,24 @@ pub fn collect_subquery_cols(
     })
 }
 
+#[macro_export]
+macro_rules! udf_equals_hash {
+    ($udf_type:tt) => {
+        fn equals(&self, other: &dyn $udf_type) -> bool {
+            let Some(other) = other.as_any().downcast_ref::<Self>() else {
+                return false;
+            };
+            self == other
+        }
+
+        fn hash_value(&self) -> u64 {
+            let hasher = &mut DefaultHasher::new();
+            self.hash(hasher);
+            hasher.finish()
+        }
+    };
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;