minor: enforce lint rule clippy::needless_pass_by_value to datafusion-functions (#18768)

## Which issue does this PR close?

<!--
We generally require a GitHub issue to be filed for all bug fixes and
enhancements and this helps us generate change logs for our releases.
You can link an issue to this PR using the GitHub syntax. For example
`Closes #123` indicates that this PR will close issue #123.
-->

- Closes #18758.

## Rationale for this change

<!--
Why are you proposing this change? If this is already explained clearly
in the issue then this section is not needed.
Explaining clearly why changes are proposed helps reviewers understand
your changes and offer better suggestions for fixes.
-->

- enforce lint rule `clippy::needless_pass_by_value` to
`datafusion-functions`.

## What changes are included in this PR?

<!--
There is no need to duplicate the description in the issue here but it
is sometimes worth providing a summary of the individual changes in this
PR.
-->

## Are these changes tested?

<!--
We typically require tests for all PRs in order to:
1. Prevent the code from being accidentally broken by subsequent changes
2. Serve as another way to document the expected behavior of the code

If tests are not included in your PR, please explain why (for example,
are they covered by existing tests)?
-->

## Are there any user-facing changes?

<!--
If there are user-facing changes then we may require documentation to be
updated before approving the PR.
-->

<!--
If there are any breaking changes to public APIs, please add the `api
change` label.
-->

---------

Signed-off-by: StandingMan <jmtangcs@gmail.com>

Author: Standing-Man

datafusion/functions/src/core/getfield.rs

@@ -197,10 +197,10 @@ impl ScalarUDFImpl for GetFieldFunc {
         };
 
         fn process_map_array(
-            array: Arc<dyn Array>,
+            array: &dyn Array,
             key_array: Arc<dyn Array>,
         ) -> Result<ColumnarValue> {
-            let map_array = as_map_array(array.as_ref())?;
+            let map_array = as_map_array(array)?;
             let keys = if key_array.data_type().is_nested() {
                 let comparator = make_comparator(
                     map_array.keys().as_ref(),
@@ -246,14 +246,14 @@ impl ScalarUDFImpl for GetFieldFunc {
         }
 
         fn process_map_with_nested_key(
-            array: Arc<dyn Array>,
-            key_array: Arc<dyn Array>,
+            array: &dyn Array,
+            key_array: &dyn Array,
         ) -> Result<ColumnarValue> {
-            let map_array = as_map_array(array.as_ref())?;
+            let map_array = as_map_array(array)?;
 
             let comparator = make_comparator(
                 map_array.keys().as_ref(),
-                key_array.as_ref(),
+                key_array,
                 SortOptions::default(),
             )?;
 
@@ -288,17 +288,17 @@ impl ScalarUDFImpl for GetFieldFunc {
         match (array.data_type(), name) {
             (DataType::Map(_, _), ScalarValue::List(arr)) => {
                 let key_array: Arc<dyn Array> = arr;
-                process_map_array(array, key_array)
+                process_map_array(&array, key_array)
             }
             (DataType::Map(_, _), ScalarValue::Struct(arr)) => {
-                process_map_array(array, arr as Arc<dyn Array>)
+                process_map_array(&array, arr as Arc<dyn Array>)
             }
             (DataType::Map(_, _), other) => {
                 let data_type = other.data_type();
                 if data_type.is_nested() {
-                    process_map_with_nested_key(array, other.to_array()?)
+                    process_map_with_nested_key(&array, &other.to_array()?)
                 } else {
-                    process_map_array(array, other.to_array()?)
+                    process_map_array(&array, other.to_array()?)
                 }
             }
             (DataType::Struct(_), ScalarValue::Utf8(Some(k))) => {

datafusion/functions/src/core/greatest_least_utils.rs

@@ -38,11 +38,11 @@ pub(super) trait GreatestLeastOperator {
 }
 
 fn keep_array<Op: GreatestLeastOperator>(
-    lhs: ArrayRef,
-    rhs: ArrayRef,
+    lhs: &dyn Array,
+    rhs: &dyn Array,
 ) -> Result<ArrayRef> {
     // True for values that we should keep from the left array
-    let keep_lhs = Op::get_indexes_to_keep(lhs.as_ref(), rhs.as_ref())?;
+    let keep_lhs = Op::get_indexes_to_keep(lhs, rhs)?;
 
     let result = zip(&keep_lhs, &lhs, &rhs)?;
 
@@ -102,8 +102,8 @@ pub(super) fn execute_conditional<Op: GreatestLeastOperator>(
 
         // Start with the result value
         result = keep_array::<Op>(
-            Arc::clone(first_array),
-            result_scalar.to_array_of_size(first_array.len())?,
+            first_array,
+            &result_scalar.to_array_of_size(first_array.len())?,
         )?;
     } else {
         // If we only have arrays, start with the first array
@@ -112,7 +112,7 @@ pub(super) fn execute_conditional<Op: GreatestLeastOperator>(
     }
 
     for array in arrays_iter {
-        result = keep_array::<Op>(Arc::clone(array), result)?;
+        result = keep_array::<Op>(array, &result)?;
     }
 
     Ok(ColumnarValue::Array(result))

datafusion/functions/src/core/mod.rs

@@ -110,11 +110,13 @@ pub mod expr_fn {
     ));
 
     #[doc = "Returns the value of the field with the given name from the struct"]
+    #[expect(clippy::needless_pass_by_value)]
     pub fn get_field(arg1: Expr, arg2: impl Literal) -> Expr {
         super::get_field().call(vec![arg1, arg2.lit()])
     }
 
     #[doc = "Returns the value of the field with the given name from the union when it's selected, or NULL otherwise"]
+    #[expect(clippy::needless_pass_by_value)]
     pub fn union_extract(arg1: Expr, arg2: impl Literal) -> Expr {
         super::union_extract().call(vec![arg1, arg2.lit()])
     }

datafusion/functions/src/crypto/basic.rs

@@ -259,11 +259,11 @@ impl DigestAlgorithm {
         let array = match value.data_type() {
             DataType::Binary | DataType::LargeBinary => {
                 let v = value.as_binary::<T>();
-                self.digest_binary_array_impl::<&GenericBinaryArray<T>>(v)
+                self.digest_binary_array_impl::<&GenericBinaryArray<T>>(&v)
             }
             DataType::BinaryView => {
                 let v = value.as_binary_view();
-                self.digest_binary_array_impl::<&BinaryViewArray>(v)
+                self.digest_binary_array_impl::<&BinaryViewArray>(&v)
             }
             other => {
                 return exec_err!("unsupported type for digest_utf_array: {other:?}")
@@ -280,11 +280,11 @@ impl DigestAlgorithm {
         let array = match value.data_type() {
             DataType::Utf8 | DataType::LargeUtf8 => {
                 let v = value.as_string::<T>();
-                self.digest_utf8_array_impl::<&GenericStringArray<T>>(v)
+                self.digest_utf8_array_impl::<&GenericStringArray<T>>(&v)
             }
             DataType::Utf8View => {
                 let v = value.as_string_view();
-                self.digest_utf8_array_impl::<&StringViewArray>(v)
+                self.digest_utf8_array_impl::<&StringViewArray>(&v)
             }
             other => {
                 return exec_err!("unsupported type for digest_utf_array: {other:?}")
@@ -295,7 +295,7 @@ impl DigestAlgorithm {
 
     pub fn digest_utf8_array_impl<'a, StringArrType>(
         self,
-        input_value: StringArrType,
+        input_value: &StringArrType,
     ) -> ArrayRef
     where
         StringArrType: StringArrayType<'a>,
@@ -326,7 +326,7 @@ impl DigestAlgorithm {
 
     pub fn digest_binary_array_impl<'a, BinaryArrType>(
         self,
-        input_value: BinaryArrType,
+        input_value: &BinaryArrType,
     ) -> ArrayRef
     where
         BinaryArrType: BinaryArrayType<'a>,

datafusion/functions/src/datetime/common.rs

@@ -190,19 +190,19 @@ where
         ColumnarValue::Array(a) => match a.data_type() {
             DataType::Utf8View => Ok(ColumnarValue::Array(Arc::new(
                 unary_string_to_primitive_function::<&StringViewArray, O, _>(
-                    a.as_ref().as_string_view(),
+                    &a.as_string_view(),
                     op,
                 )?,
             ))),
             DataType::LargeUtf8 => Ok(ColumnarValue::Array(Arc::new(
                 unary_string_to_primitive_function::<&GenericStringArray<i64>, O, _>(
-                    a.as_ref().as_string::<i64>(),
+                    &a.as_string::<i64>(),
                     op,
                 )?,
             ))),
             DataType::Utf8 => Ok(ColumnarValue::Array(Arc::new(
                 unary_string_to_primitive_function::<&GenericStringArray<i32>, O, _>(
-                    a.as_ref().as_string::<i32>(),
+                    &a.as_string::<i32>(),
                     op,
                 )?,
             ))),
@@ -431,7 +431,7 @@ where
 /// * the number of arguments is not 1 or
 /// * the function `op` errors
 fn unary_string_to_primitive_function<'a, StringArrType, O, F>(
-    array: StringArrType,
+    array: &StringArrType,
     op: F,
 ) -> Result<PrimitiveArray<O>>
 where

datafusion/functions/src/datetime/to_char.rs

@@ -144,13 +144,11 @@ impl ScalarUDFImpl for ToCharFunc {
 
         match format {
             ColumnarValue::Scalar(ScalarValue::Utf8(None))
-            | ColumnarValue::Scalar(ScalarValue::Null) => {
-                to_char_scalar(date_time.clone(), None)
-            }
+            | ColumnarValue::Scalar(ScalarValue::Null) => to_char_scalar(date_time, None),
             // constant format
             ColumnarValue::Scalar(ScalarValue::Utf8(Some(format))) => {
                 // invoke to_char_scalar with the known string, without converting to array
-                to_char_scalar(date_time.clone(), Some(format))
+                to_char_scalar(date_time, Some(format))
             }
             ColumnarValue::Array(_) => to_char_array(&args),
             _ => {
@@ -206,7 +204,7 @@ fn build_format_options<'a>(
 
 /// Special version when arg\[1] is a scalar
 fn to_char_scalar(
-    expression: ColumnarValue,
+    expression: &ColumnarValue,
     format: Option<&str>,
 ) -> Result<ColumnarValue> {
     // it's possible that the expression is a scalar however because
@@ -253,7 +251,7 @@ fn to_char_scalar(
         // if the data type was a Date32, formatting could have failed because the format string
         // contained datetime specifiers, so we'll retry by casting the date array as a timestamp array
         if data_type == &Date32 {
-            return to_char_scalar(expression.clone().cast_to(&Date64, None)?, format);
+            return to_char_scalar(&expression.cast_to(&Date64, None)?, format);
         }
 
         exec_err!("{}", formatted.unwrap_err())
@@ -292,7 +290,7 @@ fn to_char_array(args: &[ColumnarValue]) -> Result<ColumnarValue> {
                 if data_type == &Date32 {
                     let failed_date_value = arrays[0].slice(idx, 1);
 
-                    match retry_date_as_timestamp(failed_date_value, &format_options) {
+                    match retry_date_as_timestamp(&failed_date_value, &format_options) {
                         Ok(value) => {
                             results.push(Some(value));
                             continue;
@@ -322,7 +320,7 @@ fn to_char_array(args: &[ColumnarValue]) -> Result<ColumnarValue> {
 }
 
 fn retry_date_as_timestamp(
-    array_ref: ArrayRef,
+    array_ref: &ArrayRef,
     format_options: &FormatOptions,
 ) -> Result<String> {
     let target_data_type = Date64;

datafusion/functions/src/lib.rs

@@ -23,6 +23,9 @@
 // Make sure fast / cheap clones on Arc are explicit:
 // https://github.com/apache/datafusion/issues/11143
 #![deny(clippy::clone_on_ref_ptr)]
+// https://github.com/apache/datafusion/issues/18503
+#![deny(clippy::needless_pass_by_value)]
+#![cfg_attr(test, allow(clippy::needless_pass_by_value))]
 
 //! Function packages for [DataFusion].
 //!

datafusion/functions/src/regex/regexpcount.rs

@@ -201,57 +201,57 @@ pub fn regexp_count(
 
     match (values.data_type(), regex_array.data_type(), flags_array) {
         (Utf8, Utf8, None) => regexp_count_inner(
-            values.as_string::<i32>(),
-            regex_array.as_string::<i32>(),
+            &values.as_string::<i32>(),
+            &regex_array.as_string::<i32>(),
             is_regex_scalar,
             start_array.map(|start| start.as_primitive::<Int64Type>()),
             is_start_scalar,
             None,
             is_flags_scalar,
         ),
         (Utf8, Utf8, Some(flags_array)) if *flags_array.data_type() == Utf8 => regexp_count_inner(
-            values.as_string::<i32>(),
-            regex_array.as_string::<i32>(),
+            &values.as_string::<i32>(),
+            &regex_array.as_string::<i32>(),
             is_regex_scalar,
             start_array.map(|start| start.as_primitive::<Int64Type>()),
             is_start_scalar,
-            Some(flags_array.as_string::<i32>()),
+            Some(&flags_array.as_string::<i32>()),
             is_flags_scalar,
         ),
         (LargeUtf8, LargeUtf8, None) => regexp_count_inner(
-            values.as_string::<i64>(),
-            regex_array.as_string::<i64>(),
+            &values.as_string::<i64>(),
+            &regex_array.as_string::<i64>(),
             is_regex_scalar,
             start_array.map(|start| start.as_primitive::<Int64Type>()),
             is_start_scalar,
             None,
             is_flags_scalar,
         ),
         (LargeUtf8, LargeUtf8, Some(flags_array)) if *flags_array.data_type() == LargeUtf8 => regexp_count_inner(
-            values.as_string::<i64>(),
-            regex_array.as_string::<i64>(),
+            &values.as_string::<i64>(),
+            &regex_array.as_string::<i64>(),
             is_regex_scalar,
             start_array.map(|start| start.as_primitive::<Int64Type>()),
             is_start_scalar,
-            Some(flags_array.as_string::<i64>()),
+            Some(&flags_array.as_string::<i64>()),
             is_flags_scalar,
         ),
         (Utf8View, Utf8View, None) => regexp_count_inner(
-            values.as_string_view(),
-            regex_array.as_string_view(),
+            &values.as_string_view(),
+            &regex_array.as_string_view(),
             is_regex_scalar,
             start_array.map(|start| start.as_primitive::<Int64Type>()),
             is_start_scalar,
             None,
             is_flags_scalar,
         ),
         (Utf8View, Utf8View, Some(flags_array)) if *flags_array.data_type() == Utf8View => regexp_count_inner(
-            values.as_string_view(),
-            regex_array.as_string_view(),
+            &values.as_string_view(),
+            &regex_array.as_string_view(),
             is_regex_scalar,
             start_array.map(|start| start.as_primitive::<Int64Type>()),
             is_start_scalar,
-            Some(flags_array.as_string_view()),
+            Some(&flags_array.as_string_view()),
             is_flags_scalar,
         ),
         _ => Err(ArrowError::ComputeError(
@@ -260,13 +260,13 @@ pub fn regexp_count(
     }
 }
 
-pub fn regexp_count_inner<'a, S>(
-    values: S,
-    regex_array: S,
+fn regexp_count_inner<'a, S>(
+    values: &S,
+    regex_array: &S,
     is_regex_scalar: bool,
     start_array: Option<&Int64Array>,
     is_start_scalar: bool,
-    flags_array: Option<S>,
+    flags_array: Option<&S>,
     is_flags_scalar: bool,
 ) -> Result<ArrayRef, ArrowError>
 where

datafusion/functions/src/regex/regexpinstr.rs

@@ -287,6 +287,7 @@ pub fn regexp_instr(
 }
 
 #[allow(clippy::too_many_arguments)]
+#[expect(clippy::needless_pass_by_value)]
 pub fn regexp_instr_inner<'a, S>(
     values: S,
     regex_array: S,

datafusion/functions/src/regex/regexpreplace.rs

@@ -382,6 +382,7 @@ where
     }
 }
 
+#[expect(clippy::needless_pass_by_value)]
 fn _regexp_replace_early_abort<T: ArrayAccessor>(
     input_array: T,
     sz: usize,