Skip to content

Apache DataFusion SQL Query Engine

deny on allow_attributes lint in physical-plan (#18983)

YuraLitvinov5519b6145717
diff --git a/datafusion/physical-expr/src/aggregate.rs b/datafusion/physical-expr/src/aggregate.rs
index f16895b44b..dfd2e93030 100644
--- a/datafusion/physical-expr/src/aggregate.rs
+++ b/datafusion/physical-expr/src/aggregate.rs
@@ -16,7 +16,7 @@
// under the License.
pub(crate) mod groups_accumulator {
- #[allow(unused_imports)]
+ #[expect(unused_imports)]
pub(crate) mod accumulate {
pub use datafusion_functions_aggregate_common::aggregate::groups_accumulator::accumulate::NullState;
}
diff --git a/datafusion/physical-expr/src/intervals/cp_solver.rs b/datafusion/physical-expr/src/intervals/cp_solver.rs
index b1fe75a223..cb2391fd1d 100644
--- a/datafusion/physical-expr/src/intervals/cp_solver.rs
+++ b/datafusion/physical-expr/src/intervals/cp_solver.rs
@@ -780,7 +780,7 @@ mod tests {
use rand::{Rng, SeedableRng};
use rstest::*;
- #[allow(clippy::too_many_arguments)]
+ #[expect(clippy::too_many_arguments)]
fn experiment(
expr: Arc<dyn PhysicalExpr>,
exprs_with_interval: (Arc<dyn PhysicalExpr>, Arc<dyn PhysicalExpr>),
diff --git a/datafusion/physical-expr/src/intervals/test_utils.rs b/datafusion/physical-expr/src/intervals/test_utils.rs
index c3d38a974a..9a59227970 100644
--- a/datafusion/physical-expr/src/intervals/test_utils.rs
+++ b/datafusion/physical-expr/src/intervals/test_utils.rs
@@ -25,7 +25,7 @@ use arrow::datatypes::Schema;
use datafusion_common::{DataFusionError, ScalarValue};
use datafusion_expr::Operator;
-#[allow(clippy::too_many_arguments)]
+#[expect(clippy::too_many_arguments)]
/// This test function generates a conjunctive statement with two numeric
/// terms with the following form:
/// left_col (op_1) a >/>= right_col (op_2) b AND left_col (op_3) c </<= right_col (op_4) d
@@ -61,7 +61,7 @@ pub fn gen_conjunctive_numerical_expr(
Arc::new(BinaryExpr::new(left_expr, Operator::And, right_expr))
}
-#[allow(clippy::too_many_arguments)]
+#[expect(clippy::too_many_arguments)]
/// This test function generates a conjunctive statement with
/// two scalar values with the following form:
/// left_col (op_1) a > right_col (op_2) b AND left_col (op_3) c < right_col (op_4) d
diff --git a/datafusion/physical-expr/src/lib.rs b/datafusion/physical-expr/src/lib.rs
index 7feda2360c..871cebe602 100644
--- a/datafusion/physical-expr/src/lib.rs
+++ b/datafusion/physical-expr/src/lib.rs
@@ -24,6 +24,8 @@
// https://github.com/apache/datafusion/issues/11143
#![deny(clippy::clone_on_ref_ptr)]
#![cfg_attr(test, allow(clippy::needless_pass_by_value))]
+// https://github.com/apache/datafusion/issues/18881
+#![deny(clippy::allow_attributes)]
// Backward compatibility
pub mod aggregate;
diff --git a/datafusion/physical-expr/src/window/standard_window_function_expr.rs b/datafusion/physical-expr/src/window/standard_window_function_expr.rs
index 9b1213450c..a6ea5e44a4 100644
--- a/datafusion/physical-expr/src/window/standard_window_function_expr.rs
+++ b/datafusion/physical-expr/src/window/standard_window_function_expr.rs
@@ -28,14 +28,13 @@ use std::any::Any;
use std::sync::Arc;
/// Evaluates a window function by instantiating a
-/// `[PartitionEvaluator]` for calculating the function's output in
+/// [`PartitionEvaluator`] for calculating the function's output in
/// that partition.
///
/// Note that unlike aggregation based window functions, some window
/// functions such as `rank` ignore the values in the window frame,
/// but others such as `first_value`, `last_value`, and
/// `nth_value` need the value.
-#[allow(rustdoc::private_intra_doc_links)]
pub trait StandardWindowFunctionExpr: Send + Sync + std::fmt::Debug {
/// Returns the aggregate expression as [`Any`] so that it can be
/// downcast to a specific implementation.
diff --git a/datafusion/physical-expr/src/window/window_expr.rs b/datafusion/physical-expr/src/window/window_expr.rs
index ace0c31d63..8f6f61a2da 100644
--- a/datafusion/physical-expr/src/window/window_expr.rs
+++ b/datafusion/physical-expr/src/window/window_expr.rs
@@ -281,7 +281,7 @@ pub trait AggregateWindowExpr: WindowExpr {
/// * `window_frame_ctx`: Details about the window frame (see [`WindowFrameContext`]).
/// * `idx`: The index of the current row in the record batch.
/// * `not_end`: is the current row not the end of the partition (see [`PartitionBatchState`]).
- #[allow(clippy::too_many_arguments)]
+ #[expect(clippy::too_many_arguments)]
fn get_result_column(
&self,
accumulator: &mut Box<dyn Accumulator>,
diff --git a/datafusion/physical-plan/src/aggregates/mod.rs b/datafusion/physical-plan/src/aggregates/mod.rs
index a87abc2aa5..f2dd785794 100644
--- a/datafusion/physical-plan/src/aggregates/mod.rs
+++ b/datafusion/physical-plan/src/aggregates/mod.rs
@@ -377,7 +377,7 @@ impl PartialEq for PhysicalGroupBy {
}
}
-#[allow(clippy::large_enum_variant)]
+#[expect(clippy::large_enum_variant)]
enum StreamType {
AggregateStream(AggregateStream),
GroupedHash(GroupedHashAggregateStream),
@@ -575,7 +575,6 @@ impl AggregateExec {
/// a rule may re-write aggregate expressions (e.g. reverse them) during
/// initialization, field names may change inadvertently if one re-creates
/// the schema in such cases.
- #[allow(clippy::too_many_arguments)]
fn try_new_with_schema(
mode: AggregateMode,
group_by: PhysicalGroupBy,
diff --git a/datafusion/physical-plan/src/execution_plan.rs b/datafusion/physical-plan/src/execution_plan.rs
index c37a8ade07..d3043ee93c 100644
--- a/datafusion/physical-plan/src/execution_plan.rs
+++ b/datafusion/physical-plan/src/execution_plan.rs
@@ -1534,7 +1534,7 @@ mod tests {
/// A compilation test to ensure that the `ExecutionPlan::name()` method can
/// be called from a trait object.
/// Related ticket: https://github.com/apache/datafusion/pull/11047
- #[allow(dead_code)]
+ #[expect(unused)]
fn use_execution_plan_as_trait_object(plan: &dyn ExecutionPlan) {
let _ = plan.name();
}
diff --git a/datafusion/physical-plan/src/joins/cross_join.rs b/datafusion/physical-plan/src/joins/cross_join.rs
index 0488cd35a8..b90243fdb6 100644
--- a/datafusion/physical-plan/src/joins/cross_join.rs
+++ b/datafusion/physical-plan/src/joins/cross_join.rs
@@ -61,7 +61,7 @@ struct JoinLeftData {
_reservation: MemoryReservation,
}
-#[allow(rustdoc::private_intra_doc_links)]
+#[expect(rustdoc::private_intra_doc_links)]
/// Cross Join Execution Plan
///
/// This operator is used when there are no predicates between two tables and
diff --git a/datafusion/physical-plan/src/joins/hash_join/exec.rs b/datafusion/physical-plan/src/joins/hash_join/exec.rs
index 97ee8ecbdb..2936c64abf 100644
--- a/datafusion/physical-plan/src/joins/hash_join/exec.rs
+++ b/datafusion/physical-plan/src/joins/hash_join/exec.rs
@@ -142,7 +142,7 @@ impl JoinLeftData {
}
}
-#[allow(rustdoc::private_intra_doc_links)]
+#[expect(rustdoc::private_intra_doc_links)]
/// Join execution plan: Evaluates equijoin predicates in parallel on multiple
/// partitions using a hash table and an optional filter list to apply post
/// join.
@@ -387,7 +387,7 @@ impl HashJoinExec {
///
/// # Error
/// This function errors when it is not possible to join the left and right sides on keys `on`.
- #[allow(clippy::too_many_arguments)]
+ #[expect(clippy::too_many_arguments)]
pub fn try_new(
left: Arc<dyn ExecutionPlan>,
right: Arc<dyn ExecutionPlan>,
@@ -1336,7 +1336,7 @@ impl BuildSideState {
/// # Returns
/// `JoinLeftData` containing the hash map, consolidated batch, join key values,
/// visited indices bitmap, and computed bounds (if requested).
-#[allow(clippy::too_many_arguments)]
+#[expect(clippy::too_many_arguments)]
async fn collect_left_input(
random_state: RandomState,
left_stream: SendableRecordBatchStream,
diff --git a/datafusion/physical-plan/src/joins/hash_join/stream.rs b/datafusion/physical-plan/src/joins/hash_join/stream.rs
index a50a6551db..ed7da409ce 100644
--- a/datafusion/physical-plan/src/joins/hash_join/stream.rs
+++ b/datafusion/physical-plan/src/joins/hash_join/stream.rs
@@ -272,7 +272,6 @@ impl RecordBatchStream for HashJoinStream {
/// Build indices: 4, 5, 6, 6
/// Probe indices: 3, 3, 4, 5
/// ```
-#[allow(clippy::too_many_arguments)]
pub(super) fn lookup_join_hashmap(
build_hashmap: &dyn JoinHashMapType,
build_side_values: &[ArrayRef],
@@ -329,7 +328,7 @@ fn count_distinct_sorted_indices(indices: &UInt32Array) -> usize {
}
impl HashJoinStream {
- #[allow(clippy::too_many_arguments)]
+ #[expect(clippy::too_many_arguments)]
pub(super) fn new(
partition: usize,
schema: Arc<Schema>,
diff --git a/datafusion/physical-plan/src/joins/nested_loop_join.rs b/datafusion/physical-plan/src/joins/nested_loop_join.rs
index c82961e0e7..e61e457247 100644
--- a/datafusion/physical-plan/src/joins/nested_loop_join.rs
+++ b/datafusion/physical-plan/src/joins/nested_loop_join.rs
@@ -75,7 +75,7 @@ use futures::{Stream, StreamExt, TryStreamExt};
use log::debug;
use parking_lot::Mutex;
-#[allow(rustdoc::private_intra_doc_links)]
+#[expect(rustdoc::private_intra_doc_links)]
/// NestedLoopJoinExec is a build-probe join operator designed for joins that
/// do not have equijoin keys in their `ON` clause.
///
@@ -785,7 +785,7 @@ pub(crate) struct NestedLoopJoinStream {
left_exhausted: bool,
/// If we can buffer all left data in one pass
/// TODO(now): this is for the (unimplemented) memory-limited execution
- #[allow(dead_code)]
+ #[expect(dead_code)]
left_buffered_in_one_pass: bool,
// Probe(right) side
@@ -1013,7 +1013,7 @@ impl RecordBatchStream for NestedLoopJoinStream {
}
impl NestedLoopJoinStream {
- #[allow(clippy::too_many_arguments)]
+ #[expect(clippy::too_many_arguments)]
pub(crate) fn new(
schema: Arc<Schema>,
filter: Option<JoinFilter>,
diff --git a/datafusion/physical-plan/src/joins/piecewise_merge_join/classic_join.rs b/datafusion/physical-plan/src/joins/piecewise_merge_join/classic_join.rs
index 695e73f109..c74f4d984e 100644
--- a/datafusion/physical-plan/src/joins/piecewise_merge_join/classic_join.rs
+++ b/datafusion/physical-plan/src/joins/piecewise_merge_join/classic_join.rs
@@ -70,7 +70,6 @@ pub(super) struct SortedStreamBatch {
}
impl SortedStreamBatch {
- #[allow(dead_code)]
fn new(batch: RecordBatch, compare_key_values: Vec<ArrayRef>) -> Self {
Self {
batch,
@@ -132,7 +131,7 @@ impl RecordBatchStream for ClassicPWMJStream {
// `Completed` however for Full and Right we will need to process the unmatched buffered rows.
impl ClassicPWMJStream {
// Creates a new `PiecewiseMergeJoinStream` instance
- #[allow(clippy::too_many_arguments)]
+ #[expect(clippy::too_many_arguments)]
pub fn try_new(
schema: Arc<Schema>,
on_streamed: PhysicalExprRef,
@@ -248,10 +247,7 @@ impl ClassicPWMJStream {
// Reset BatchProcessState before processing a new stream batch
self.batch_process_state.reset();
self.state = PiecewiseMergeJoinStreamState::ProcessStreamBatch(
- SortedStreamBatch {
- batch: stream_batch,
- compare_key_values: vec![stream_values],
- },
+ SortedStreamBatch::new(stream_batch, vec![stream_values]),
);
}
Some(Err(err)) => return Poll::Ready(Err(err)),
@@ -451,7 +447,6 @@ impl Stream for ClassicPWMJStream {
}
// For Left, Right, Full, and Inner joins, incoming stream batches will already be sorted.
-#[allow(clippy::too_many_arguments)]
fn resolve_classic_join(
buffered_side: &mut BufferedSideReadyState,
stream_batch: &SortedStreamBatch,
diff --git a/datafusion/physical-plan/src/joins/piecewise_merge_join/exec.rs b/datafusion/physical-plan/src/joins/piecewise_merge_join/exec.rs
index a9ea92f2d9..06a1df4386 100644
--- a/datafusion/physical-plan/src/joins/piecewise_merge_join/exec.rs
+++ b/datafusion/physical-plan/src/joins/piecewise_merge_join/exec.rs
@@ -272,7 +272,7 @@ pub struct PiecewiseMergeJoinExec {
left_child_plan_required_order: LexOrdering,
/// The right sort order, descending for `<`, `<=` operations + ascending for `>`, `>=` operations
/// Unsorted for mark joins
- #[allow(unused)]
+ #[expect(dead_code)]
right_batch_required_orders: LexOrdering,
/// This determines the sort order of all join columns used in sorting the stream and buffered execution plans.
diff --git a/datafusion/physical-plan/src/joins/sort_merge_join/metrics.rs b/datafusion/physical-plan/src/joins/sort_merge_join/metrics.rs
index ac476853d5..8457408919 100644
--- a/datafusion/physical-plan/src/joins/sort_merge_join/metrics.rs
+++ b/datafusion/physical-plan/src/joins/sort_merge_join/metrics.rs
@@ -23,7 +23,6 @@ use crate::metrics::{
};
/// Metrics for SortMergeJoinExec
-#[allow(dead_code)]
pub(super) struct SortMergeJoinMetrics {
/// Total time for joining probe-side batches to the build-side batches
join_time: Time,
@@ -41,7 +40,6 @@ pub(super) struct SortMergeJoinMetrics {
}
impl SortMergeJoinMetrics {
- #[allow(dead_code)]
pub fn new(partition: usize, metrics: &ExecutionPlanMetricsSet) -> Self {
let join_time = MetricBuilder::new(metrics).subset_time("join_time", partition);
let input_batches =
diff --git a/datafusion/physical-plan/src/joins/sort_merge_join/stream.rs b/datafusion/physical-plan/src/joins/sort_merge_join/stream.rs
index 9acaba1c89..e1d002a436 100644
--- a/datafusion/physical-plan/src/joins/sort_merge_join/stream.rs
+++ b/datafusion/physical-plan/src/joins/sort_merge_join/stream.rs
@@ -533,7 +533,7 @@ pub(super) fn get_corrected_filter_mask(
// If the left row seen as true its needed to output it once
// To do that we mark all other matches for same row as null to avoid the output
if seen_true {
- #[allow(clippy::needless_range_loop)]
+ #[expect(clippy::needless_range_loop)]
for j in first_row_idx..last_true_idx {
mask[j] = None;
}
@@ -748,7 +748,7 @@ impl Stream for SortMergeJoinStream {
}
impl SortMergeJoinStream {
- #[allow(clippy::too_many_arguments)]
+ #[expect(clippy::too_many_arguments)]
pub fn try_new(
// Configured via `datafusion.execution.spill_compression`.
spill_compression: SpillCompression,
diff --git a/datafusion/physical-plan/src/joins/symmetric_hash_join.rs b/datafusion/physical-plan/src/joins/symmetric_hash_join.rs
index 9c778ad131..2b8d2bd40e 100644
--- a/datafusion/physical-plan/src/joins/symmetric_hash_join.rs
+++ b/datafusion/physical-plan/src/joins/symmetric_hash_join.rs
@@ -207,7 +207,7 @@ impl SymmetricHashJoinExec {
/// - It is not possible to join the left and right sides on keys `on`, or
/// - It fails to construct `SortedFilterExpr`s, or
/// - It fails to create the [ExprIntervalGraph].
- #[allow(clippy::too_many_arguments)]
+ #[expect(clippy::too_many_arguments)]
pub fn try_new(
left: Arc<dyn ExecutionPlan>,
right: Arc<dyn ExecutionPlan>,
@@ -957,7 +957,7 @@ pub(crate) fn build_side_determined_results(
///
/// A [Result] containing an optional record batch if the join type is not one of `LeftAnti`, `RightAnti`, `LeftSemi` or `RightSemi`.
/// If the join type is one of the above four, the function will return [None].
-#[allow(clippy::too_many_arguments)]
+#[expect(clippy::too_many_arguments)]
pub(crate) fn join_with_probe_batch(
build_hash_joiner: &mut OneSideHashJoiner,
probe_hash_joiner: &mut OneSideHashJoiner,
@@ -1055,7 +1055,7 @@ pub(crate) fn join_with_probe_batch(
///
/// A [Result] containing a tuple with two equal length arrays, representing indices of rows from build and probe side,
/// matched by join key columns.
-#[allow(clippy::too_many_arguments)]
+#[expect(clippy::too_many_arguments)]
fn lookup_join_hashmap(
build_hashmap: &PruningJoinHashMap,
build_batch: &RecordBatch,
diff --git a/datafusion/physical-plan/src/joins/utils.rs b/datafusion/physical-plan/src/joins/utils.rs
index 9087ac415f..561c9c022f 100644
--- a/datafusion/physical-plan/src/joins/utils.rs
+++ b/datafusion/physical-plan/src/joins/utils.rs
@@ -1683,7 +1683,7 @@ pub fn swap_join_projection(
/// `fifo_hashmap` sets the order of iteration over `batch` rows while updating hashmap,
/// which allows to keep either first (if set to true) or last (if set to false) row index
/// as a chain head for rows with equal hash values.
-#[allow(clippy::too_many_arguments)]
+#[expect(clippy::too_many_arguments)]
pub fn update_hash(
on: &[PhysicalExprRef],
batch: &RecordBatch,
diff --git a/datafusion/physical-plan/src/lib.rs b/datafusion/physical-plan/src/lib.rs
index 45425aa717..107ace95bb 100644
--- a/datafusion/physical-plan/src/lib.rs
+++ b/datafusion/physical-plan/src/lib.rs
@@ -24,6 +24,8 @@
// https://github.com/apache/datafusion/issues/11143
#![deny(clippy::clone_on_ref_ptr)]
#![cfg_attr(test, allow(clippy::needless_pass_by_value))]
+// https://github.com/apache/datafusion/issues/18881
+#![deny(clippy::allow_attributes)]
//! Traits for physical query plan, supporting parallel execution for partitioned relations.
//!
diff --git a/datafusion/physical-plan/src/projection.rs b/datafusion/physical-plan/src/projection.rs
index 8e8baef3e7..c256bcbcd6 100644
--- a/datafusion/physical-plan/src/projection.rs
+++ b/datafusion/physical-plan/src/projection.rs
@@ -785,10 +785,6 @@ pub fn update_join_on(
hash_join_on: &[(PhysicalExprRef, PhysicalExprRef)],
left_field_size: usize,
) -> Option<Vec<(PhysicalExprRef, PhysicalExprRef)>> {
- // TODO: Clippy wants the "map" call removed, but doing so generates
- // a compilation error. Remove the clippy directive once this
- // issue is fixed.
- #[allow(clippy::map_identity)]
let (left_idx, right_idx): (Vec<_>, Vec<_>) = hash_join_on
.iter()
.map(|(left, right)| (left, right))
diff --git a/datafusion/physical-plan/src/render_tree.rs b/datafusion/physical-plan/src/render_tree.rs
index f86e4c55e7..40e2763698 100644
--- a/datafusion/physical-plan/src/render_tree.rs
+++ b/datafusion/physical-plan/src/render_tree.rs
@@ -31,11 +31,12 @@ use crate::{DisplayFormatType, ExecutionPlan};
// TODO: It's never used.
/// Represents a 2D coordinate in the rendered tree.
/// Used to track positions of nodes and their connections.
-#[allow(dead_code)]
pub struct Coordinate {
/// Horizontal position in the tree
+ #[expect(dead_code)]
pub x: usize,
/// Vertical position in the tree
+ #[expect(dead_code)]
pub y: usize,
}
diff --git a/datafusion/physical-plan/src/sorts/multi_level_merge.rs b/datafusion/physical-plan/src/sorts/multi_level_merge.rs
index 6e7a5e7a72..784c9f7a60 100644
--- a/datafusion/physical-plan/src/sorts/multi_level_merge.rs
+++ b/datafusion/physical-plan/src/sorts/multi_level_merge.rs
@@ -145,7 +145,7 @@ impl Debug for MultiLevelMergeBuilder {
}
impl MultiLevelMergeBuilder {
- #[allow(clippy::too_many_arguments)]
+ #[expect(clippy::too_many_arguments)]
pub(crate) fn new(
spill_manager: SpillManager,
schema: SchemaRef,
diff --git a/datafusion/physical-plan/src/sorts/sort.rs b/datafusion/physical-plan/src/sorts/sort.rs
index c4c871da74..00cc96dccf 100644
--- a/datafusion/physical-plan/src/sorts/sort.rs
+++ b/datafusion/physical-plan/src/sorts/sort.rs
@@ -266,7 +266,7 @@ struct ExternalSorter {
impl ExternalSorter {
// TODO: make a builder or some other nicer API to avoid the
// clippy warning
- #[allow(clippy::too_many_arguments)]
+ #[expect(clippy::too_many_arguments)]
pub fn new(
partition_id: usize,
schema: SchemaRef,
diff --git a/datafusion/physical-plan/src/windows/bounded_window_agg_exec.rs b/datafusion/physical-plan/src/windows/bounded_window_agg_exec.rs
index ccc154bc10..eb8bb982b8 100644
--- a/datafusion/physical-plan/src/windows/bounded_window_agg_exec.rs
+++ b/datafusion/physical-plan/src/windows/bounded_window_agg_exec.rs
@@ -1474,20 +1474,6 @@ mod tests {
Ok(results)
}
- /// Execute the [ExecutionPlan] and collect the results in memory
- #[allow(dead_code)]
- pub async fn collect_bonafide(
- plan: Arc<dyn ExecutionPlan>,
- context: Arc<TaskContext>,
- ) -> Result<Vec<RecordBatch>> {
- let stream = execute_stream(plan, context)?;
- let mut results = vec![];
-
- collect_stream(stream, &mut results).await?;
-
- Ok(results)
- }
-
fn test_schema() -> SchemaRef {
Arc::new(Schema::new(vec![
Field::new("sn", DataType::UInt64, true),
diff --git a/datafusion/physical-plan/src/windows/mod.rs b/datafusion/physical-plan/src/windows/mod.rs
index cd35325eb3..01926ab156 100644
--- a/datafusion/physical-plan/src/windows/mod.rs
+++ b/datafusion/physical-plan/src/windows/mod.rs
@@ -88,7 +88,7 @@ pub fn schema_add_window_field(
}
/// Create a physical expression for window function
-#[allow(clippy::too_many_arguments)]
+#[expect(clippy::too_many_arguments)]
pub fn create_window_expr(
fun: &WindowFunctionDefinition,
name: String,
diff --git a/datafusion/physical-plan/src/work_table.rs b/datafusion/physical-plan/src/work_table.rs
index e2c6efd508..b0f300dd37 100644
--- a/datafusion/physical-plan/src/work_table.rs
+++ b/datafusion/physical-plan/src/work_table.rs
@@ -40,7 +40,6 @@ use datafusion_physical_expr::{EquivalenceProperties, Partitioning};
#[derive(Debug)]
pub(super) struct ReservedBatches {
batches: Vec<RecordBatch>,
- #[allow(dead_code)]
reservation: MemoryReservation,
}