chore: Fix clippy and CI (#21287)

## 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 #.

## 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.
-->

## 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.
-->

Author: comphead

datafusion-cli/tests/cli_integration.rs

@@ -414,14 +414,12 @@ fn test_backtrace_output(#[case] query: &str) {
     let output = cmd.output().expect("Failed to execute command");
     let stdout = String::from_utf8_lossy(&output.stdout);
     let stderr = String::from_utf8_lossy(&output.stderr);
-    let combined_output = format!("{}{}", stdout, stderr);
+    let combined_output = format!("{stdout}{stderr}");
 
     // Assert that the output includes literal 'backtrace'
     assert!(
         combined_output.to_lowercase().contains("backtrace"),
-        "Expected output to contain 'backtrace', but got stdout: '{}' stderr: '{}'",
-        stdout,
-        stderr
+        "Expected output to contain 'backtrace', but got stdout: '{stdout}' stderr: '{stderr}'"
     );
 }
 

datafusion/common/src/error.rs

@@ -1274,7 +1274,6 @@ mod test {
     // To pass the test the environment variable RUST_BACKTRACE should be set to 1 to enforce backtrace
     #[cfg(feature = "backtrace")]
     #[test]
-    #[expect(clippy::unnecessary_literal_unwrap)]
     fn test_enabled_backtrace() {
         match std::env::var("RUST_BACKTRACE") {
             Ok(val) if val == "1" => {}

datafusion/common/src/hash_utils.rs

@@ -19,12 +19,15 @@
 
 use arrow::array::types::{IntervalDayTime, IntervalMonthDayNano};
 use arrow::array::*;
+#[cfg(not(feature = "force_hash_collisions"))]
 use arrow::compute::take;
 use arrow::datatypes::*;
 #[cfg(not(feature = "force_hash_collisions"))]
 use arrow::{downcast_dictionary_array, downcast_primitive_array};
 use foldhash::fast::FixedState;
+#[cfg(not(feature = "force_hash_collisions"))]
 use itertools::Itertools;
+#[cfg(not(feature = "force_hash_collisions"))]
 use std::collections::HashMap;
 use std::hash::{BuildHasher, Hash, Hasher};
 
@@ -198,6 +201,7 @@ hash_float_value!((half::f16, u16), (f32, u32), (f64, u64));
 /// Create a `SeedableRandomState` whose per-hasher seed incorporates `seed`.
 /// This folds the previous hash into the hasher's initial state so only the
 /// new value needs to pass through the hash function — same cost as `hash_one`.
+#[cfg(not(feature = "force_hash_collisions"))]
 #[inline]
 fn seeded_state(seed: u64) -> foldhash::fast::SeedableRandomState {
     foldhash::fast::SeedableRandomState::with_seed(
@@ -303,6 +307,7 @@ fn hash_array<T>(
 /// HAS_NULLS: do we have to check null in the inner loop
 /// HAS_BUFFERS: if true, array has external buffers; if false, all strings are inlined/ less then 12 bytes
 /// REHASH: if true, combining with existing hash, otherwise initializing
+#[cfg(not(feature = "force_hash_collisions"))]
 #[inline(never)]
 fn hash_string_view_array_inner<
     T: ByteViewType,
@@ -429,6 +434,7 @@ fn hash_generic_byte_view_array<T: ByteViewType>(
 /// - `HAS_NULL_KEYS`: Whether to check for null dictionary keys
 /// - `HAS_NULL_VALUES`: Whether to check for null dictionary values
 /// - `MULTI_COL`: Whether to combine with existing hash (true) or initialize (false)
+#[cfg(not(feature = "force_hash_collisions"))]
 #[inline(never)]
 fn hash_dictionary_inner<
     K: ArrowDictionaryKeyType,

datafusion/common/src/pruning.rs

@@ -121,6 +121,7 @@ pub trait PruningStatistics {
     /// container, return `None` (the default).
     ///
     /// Note: the returned array must contain [`Self::num_containers`] rows
+    #[allow(clippy::allow_attributes, clippy::mutable_key_type)] // ScalarValue has interior mutability but is intentionally used as hash key
     fn contained(
         &self,
         column: &Column,
@@ -526,6 +527,7 @@ impl PruningStatistics for CompositePruningStatistics {
 
 #[cfg(test)]
 #[expect(deprecated)]
+#[allow(clippy::allow_attributes, clippy::mutable_key_type)] // ScalarValue has interior mutability but is intentionally used as hash key
 mod tests {
     use crate::{
         ColumnStatistics,

datafusion/common/src/scalar/mod.rs

@@ -4601,6 +4601,7 @@ impl ScalarValue {
     /// Estimates [size](Self::size) of [`HashSet`] in bytes.
     ///
     /// Includes the size of the [`HashSet`] container itself.
+    #[allow(clippy::allow_attributes, clippy::mutable_key_type)] // ScalarValue has interior mutability but is intentionally used as hash key
     pub fn size_of_hashset<S>(set: &HashSet<Self, S>) -> usize {
         size_of_val(set)
             + (size_of::<ScalarValue>() * set.capacity())
@@ -7263,6 +7264,8 @@ mod tests {
             size_of::<Vec<ScalarValue>>() + (9 * size_of::<ScalarValue>()) + sv_size,
         );
 
+        #[allow(clippy::allow_attributes, clippy::mutable_key_type)]
+        // ScalarValue has interior mutability but is intentionally used as hash key
         let mut s = HashSet::with_capacity(0);
         // do NOT clone `sv` here because this may shrink the vector capacity
         s.insert(v.pop().unwrap());

datafusion/core/src/physical_planner.rs

@@ -2093,6 +2093,7 @@ fn get_physical_expr_pair(
 /// A vector of unqualified filter expressions that can be passed to the TableProvider for execution.
 /// Returns an empty vector if no applicable filters are found.
 ///
+#[allow(clippy::allow_attributes, clippy::mutable_key_type)] // Expr contains Arc with interior mutability but is intentionally used as hash key
 fn extract_dml_filters(
     input: &Arc<LogicalPlan>,
     target: &TableReference,

datafusion/datasource/src/file_groups.rs

@@ -488,6 +488,7 @@ impl FileGroup {
     ///
     /// Note: May return fewer groups than `max_target_partitions` when the
     /// number of unique partition values is less than the target.
+    #[allow(clippy::allow_attributes, clippy::mutable_key_type)] // ScalarValue has interior mutability but is intentionally used as hash key
     pub fn group_by_partition_values(
         self,
         max_target_partitions: usize,

datafusion/execution/src/memory_pool/arrow.rs

@@ -59,7 +59,7 @@ impl arrow_buffer::MemoryReservation for MemoryReservation {
 impl arrow_buffer::MemoryPool for ArrowMemoryPool {
     fn reserve(&self, size: usize) -> Box<dyn arrow_buffer::MemoryReservation> {
         let consumer = self.consumer.clone_with_new_id();
-        let mut reservation = consumer.register(&self.inner);
+        let reservation = consumer.register(&self.inner);
         reservation.grow(size);
 
         Box::new(reservation)

datafusion/expr/src/logical_plan/builder.rs

@@ -2132,6 +2132,8 @@ pub fn wrap_projection_for_join_if_necessary(
             .into_iter()
             .map(Expr::Column)
             .collect::<Vec<_>>();
+        #[allow(clippy::allow_attributes, clippy::mutable_key_type)]
+        // Expr contains Arc with interior mutability but is intentionally used as hash key
         let join_key_items = alias_join_keys
             .iter()
             .flat_map(|expr| expr.try_as_col().is_none().then_some(expr))

datafusion/functions-aggregate/src/median.rs

@@ -285,6 +285,7 @@ impl<T: ArrowNumericType> Accumulator for MedianAccumulator<T> {
         size_of_val(self) + self.all_values.capacity() * size_of::<T::Native>()
     }
 
+    #[allow(clippy::allow_attributes, clippy::mutable_key_type)] // ScalarValue has interior mutability but is intentionally used as hash key
     fn retract_batch(&mut self, values: &[ArrayRef]) -> Result<()> {
         let mut to_remove: HashMap<ScalarValue, usize> = HashMap::new();