Require Debug for PhysicalOptimizerRule (#12624)

AnthonyZhOon · web-flow · commit 91c8a47f2001 · 2024-09-25T14:11:02.000-04:00
* Require Debug for PhysicalOptimizerRule * Add reference to meet &JoinType type required * Revert "Add reference to meet &JoinType type required" as clippy lint informs this is unnecessary This reverts commit f69d73c.
diff --git a/datafusion/core/src/physical_optimizer/coalesce_batches.rs b/datafusion/core/src/physical_optimizer/coalesce_batches.rs
@@ -34,7 +34,7 @@ use datafusion_physical_optimizer::PhysicalOptimizerRule;
 
 /// Optimizer rule that introduces CoalesceBatchesExec to avoid overhead with small batches that
 /// are produced by highly selective filters
-#[derive(Default)]
+#[derive(Default, Debug)]
 pub struct CoalesceBatches {}
 
 impl CoalesceBatches {
diff --git a/datafusion/core/src/physical_optimizer/enforce_distribution.rs b/datafusion/core/src/physical_optimizer/enforce_distribution.rs
@@ -176,7 +176,7 @@ use itertools::izip;
 ///
 /// This rule only chooses the exact match and satisfies the Distribution(a, b, c)
 /// by a HashPartition(a, b, c).
-#[derive(Default)]
+#[derive(Default, Debug)]
 pub struct EnforceDistribution {}
 
 impl EnforceDistribution {
diff --git a/datafusion/core/src/physical_optimizer/enforce_sorting.rs b/datafusion/core/src/physical_optimizer/enforce_sorting.rs
@@ -72,7 +72,7 @@ use itertools::izip;
 
 /// This rule inspects [`SortExec`]'s in the given physical plan and removes the
 /// ones it can prove unnecessary.
-#[derive(Default)]
+#[derive(Default, Debug)]
 pub struct EnforceSorting {}
 
 impl EnforceSorting {
diff --git a/datafusion/core/src/physical_optimizer/join_selection.rs b/datafusion/core/src/physical_optimizer/join_selection.rs
@@ -46,7 +46,7 @@ use datafusion_physical_optimizer::PhysicalOptimizerRule;
 /// The [`JoinSelection`] rule tries to modify a given plan so that it can
 /// accommodate infinite sources and optimize joins in the plan according to
 /// available statistical information, if there is any.
-#[derive(Default)]
+#[derive(Default, Debug)]
 pub struct JoinSelection {}
 
 impl JoinSelection {
diff --git a/datafusion/core/src/physical_optimizer/optimizer.rs b/datafusion/core/src/physical_optimizer/optimizer.rs
@@ -35,7 +35,7 @@ use crate::physical_optimizer::sanity_checker::SanityCheckPlan;
 use crate::physical_optimizer::topk_aggregation::TopKAggregation;
 
 /// A rule-based physical optimizer.
-#[derive(Clone)]
+#[derive(Clone, Debug)]
 pub struct PhysicalOptimizer {
     /// All rules to apply
     pub rules: Vec<Arc<dyn PhysicalOptimizerRule + Send + Sync>>,
diff --git a/datafusion/core/src/physical_optimizer/projection_pushdown.rs b/datafusion/core/src/physical_optimizer/projection_pushdown.rs
@@ -60,7 +60,7 @@ use itertools::Itertools;
 
 /// This rule inspects [`ProjectionExec`]'s in the given physical plan and tries to
 /// remove or swap with its child.
-#[derive(Default)]
+#[derive(Default, Debug)]
 pub struct ProjectionPushdown {}
 
 impl ProjectionPushdown {
diff --git a/datafusion/core/src/physical_optimizer/sanity_checker.rs b/datafusion/core/src/physical_optimizer/sanity_checker.rs
@@ -41,7 +41,7 @@ use itertools::izip;
 ///    are not satisfied by their children.
 /// 2. Plans that use pipeline-breaking operators on infinite input(s),
 ///    it is impossible to execute such queries (they will never generate output nor finish)
-#[derive(Default)]
+#[derive(Default, Debug)]
 pub struct SanityCheckPlan {}
 
 impl SanityCheckPlan {
diff --git a/datafusion/core/src/physical_optimizer/update_aggr_exprs.rs b/datafusion/core/src/physical_optimizer/update_aggr_exprs.rs
@@ -48,7 +48,7 @@ use datafusion_physical_plan::{
 /// This rule analyzes aggregate expressions of type `Beneficial` to see whether
 /// their input ordering requirements are satisfied. If this is the case, the
 /// aggregators are modified to run in a more efficient mode.
-#[derive(Default)]
+#[derive(Default, Debug)]
 pub struct OptimizeAggregateOrder {}
 
 impl OptimizeAggregateOrder {
diff --git a/datafusion/physical-optimizer/src/aggregate_statistics.rs b/datafusion/physical-optimizer/src/aggregate_statistics.rs
@@ -33,7 +33,7 @@ use datafusion_physical_plan::placeholder_row::PlaceholderRowExec;
 use datafusion_physical_plan::udaf::AggregateFunctionExpr;
 
 /// Optimizer that uses available statistics for aggregate functions
-#[derive(Default)]
+#[derive(Default, Debug)]
 pub struct AggregateStatistics {}
 
 impl AggregateStatistics {
diff --git a/datafusion/physical-optimizer/src/combine_partial_final_agg.rs b/datafusion/physical-optimizer/src/combine_partial_final_agg.rs
@@ -37,7 +37,7 @@ use datafusion_physical_expr::{physical_exprs_equal, PhysicalExpr};
 ///
 /// This rule should be applied after the EnforceDistribution and EnforceSorting rules
 ///
-#[derive(Default)]
+#[derive(Default, Debug)]
 pub struct CombinePartialFinalAggregate {}
 
 impl CombinePartialFinalAggregate {
diff --git a/datafusion/physical-optimizer/src/limit_pushdown.rs b/datafusion/physical-optimizer/src/limit_pushdown.rs
@@ -33,7 +33,7 @@ use datafusion_physical_plan::{ExecutionPlan, ExecutionPlanProperties};
 
 /// This rule inspects [`ExecutionPlan`]'s and pushes down the fetch limit from
 /// the parent to the child if applicable.
-#[derive(Default)]
+#[derive(Default, Debug)]
 pub struct LimitPushdown {}
 
 /// This is a "data class" we use within the [`LimitPushdown`] rule to push
diff --git a/datafusion/physical-optimizer/src/limited_distinct_aggregation.rs b/datafusion/physical-optimizer/src/limited_distinct_aggregation.rs
@@ -35,6 +35,7 @@ use itertools::Itertools;
 /// rows in the group to be processed for correctness. Example queries fitting this description are:
 /// - `SELECT distinct l_orderkey FROM lineitem LIMIT 10;`
 /// - `SELECT l_orderkey FROM lineitem GROUP BY l_orderkey LIMIT 10;`
+#[derive(Debug)]
 pub struct LimitedDistinctAggregation {}
 
 impl LimitedDistinctAggregation {
diff --git a/datafusion/physical-optimizer/src/optimizer.rs b/datafusion/physical-optimizer/src/optimizer.rs
@@ -20,6 +20,7 @@
 use datafusion_common::config::ConfigOptions;
 use datafusion_common::Result;
 use datafusion_physical_plan::ExecutionPlan;
+use std::fmt::Debug;
 use std::sync::Arc;
 
 /// `PhysicalOptimizerRule` transforms one ['ExecutionPlan'] into another which
@@ -29,7 +30,7 @@ use std::sync::Arc;
 /// `PhysicalOptimizerRule`s.
 ///
 /// [`SessionState::add_physical_optimizer_rule`]: https://docs.rs/datafusion/latest/datafusion/execution/session_state/struct.SessionState.html#method.add_physical_optimizer_rule
-pub trait PhysicalOptimizerRule {
+pub trait PhysicalOptimizerRule: Debug {
     /// Rewrite `plan` to an optimized form
     fn optimize(
         &self,
diff --git a/datafusion/physical-optimizer/src/topk_aggregation.rs b/datafusion/physical-optimizer/src/topk_aggregation.rs
@@ -37,6 +37,7 @@ use crate::PhysicalOptimizerRule;
 use itertools::Itertools;
 
 /// An optimizer rule that passes a `limit` hint to aggregations if the whole result is not needed
+#[derive(Debug)]
 pub struct TopKAggregation {}
 
 impl TopKAggregation {
