ci: enforce needless_pass_by_value for datafusion-optimzer (apache#18533)

## 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 apache#123` indicates that this PR will close issue apache#123.
-->

- Closes apache#18505.

## 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 clippy `needless_pass_by_value`.

## 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)?
-->
Yes

## 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.
-->

No

Author: jizezhang

datafusion/optimizer/src/analyzer/resolve_grouping_function.rs

@@ -28,7 +28,7 @@ use arrow::datatypes::DataType;
 use datafusion_common::config::ConfigOptions;
 use datafusion_common::tree_node::{Transformed, TransformedResult, TreeNode};
 use datafusion_common::{
-    internal_datafusion_err, plan_err, Column, DFSchemaRef, Result, ScalarValue,
+    internal_datafusion_err, plan_err, Column, DFSchema, Result, ScalarValue,
 };
 use datafusion_expr::expr::{AggregateFunction, Alias};
 use datafusion_expr::logical_plan::LogicalPlan;
@@ -74,7 +74,7 @@ fn group_expr_to_bitmap_index(group_expr: &[Expr]) -> Result<HashMap<&Expr, usiz
 
 fn replace_grouping_exprs(
     input: Arc<LogicalPlan>,
-    schema: DFSchemaRef,
+    schema: &DFSchema,
     group_expr: Vec<Expr>,
     aggr_expr: Vec<Expr>,
 ) -> Result<LogicalPlan> {
@@ -139,7 +139,7 @@ fn analyze_internal(plan: LogicalPlan) -> Result<Transformed<LogicalPlan>> {
             schema,
             ..
         }) if contains_grouping_function(&aggr_expr) => Ok(Transformed::yes(
-            replace_grouping_exprs(input, schema, group_expr, aggr_expr)?,
+            replace_grouping_exprs(input, schema.as_ref(), group_expr, aggr_expr)?,
         )),
         _ => Ok(Transformed::no(plan)),
     })?;

datafusion/optimizer/src/decorrelate_predicate_subquery.rs

@@ -136,7 +136,7 @@ fn rewrite_inner_subqueries(
         Expr::Exists(Exists {
             subquery: Subquery { subquery, .. },
             negated,
-        }) => match mark_join(&cur_input, Arc::clone(&subquery), None, negated, alias)? {
+        }) => match mark_join(&cur_input, &subquery, None, negated, alias)? {
             Some((plan, exists_expr)) => {
                 cur_input = plan;
                 Ok(Transformed::yes(exists_expr))
@@ -154,13 +154,7 @@ fn rewrite_inner_subqueries(
                 .map_or(plan_err!("single expression required."), |output_expr| {
                     Ok(Expr::eq(*expr.clone(), output_expr))
                 })?;
-            match mark_join(
-                &cur_input,
-                Arc::clone(&subquery),
-                Some(in_predicate),
-                negated,
-                alias,
-            )? {
+            match mark_join(&cur_input, &subquery, Some(&in_predicate), negated, alias)? {
                 Some((plan, exists_expr)) => {
                     cur_input = plan;
                     Ok(Transformed::yes(exists_expr))
@@ -275,7 +269,13 @@ fn build_join_top(
     };
     let subquery = query_info.query.subquery.as_ref();
     let subquery_alias = alias.next("__correlated_sq");
-    build_join(left, subquery, in_predicate_opt, join_type, subquery_alias)
+    build_join(
+        left,
+        subquery,
+        in_predicate_opt.as_ref(),
+        join_type,
+        subquery_alias,
+    )
 }
 
 /// This is used to handle the case when the subquery is embedded in a more complex boolean
@@ -295,8 +295,8 @@ fn build_join_top(
 ///           TableScan: t2
 fn mark_join(
     left: &LogicalPlan,
-    subquery: Arc<LogicalPlan>,
-    in_predicate_opt: Option<Expr>,
+    subquery: &LogicalPlan,
+    in_predicate_opt: Option<&Expr>,
     negated: bool,
     alias_generator: &Arc<AliasGenerator>,
 ) -> Result<Option<(LogicalPlan, Expr)>> {
@@ -306,20 +306,20 @@ fn mark_join(
     let exists_expr = if negated { !exists_col } else { exists_col };
 
     Ok(
-        build_join(left, &subquery, in_predicate_opt, JoinType::LeftMark, alias)?
+        build_join(left, subquery, in_predicate_opt, JoinType::LeftMark, alias)?
             .map(|plan| (plan, exists_expr)),
     )
 }
 
 fn build_join(
     left: &LogicalPlan,
     subquery: &LogicalPlan,
-    in_predicate_opt: Option<Expr>,
+    in_predicate_opt: Option<&Expr>,
     join_type: JoinType,
     alias: String,
 ) -> Result<Option<LogicalPlan>> {
     let mut pull_up = PullUpCorrelatedExpr::new()
-        .with_in_predicate_opt(in_predicate_opt.clone())
+        .with_in_predicate_opt(in_predicate_opt.cloned())
         .with_exists_sub_query(in_predicate_opt.is_none());
 
     let new_plan = subquery.clone().rewrite(&mut pull_up).data()?;
@@ -342,7 +342,7 @@ fn build_join(
             replace_qualified_name(filter, &all_correlated_cols, &alias).map(Some)
         })?;
 
-    let join_filter = match (join_filter_opt, in_predicate_opt.clone()) {
+    let join_filter = match (join_filter_opt, in_predicate_opt.cloned()) {
         (
             Some(join_filter),
             Some(Expr::BinaryExpr(BinaryExpr {
@@ -378,7 +378,7 @@ fn build_join(
         // Gather all columns needed for the join filter + predicates
         let mut needed = std::collections::HashSet::new();
         expr_to_columns(&join_filter, &mut needed)?;
-        if let Some(ref in_pred) = in_predicate_opt {
+        if let Some(in_pred) = in_predicate_opt {
             expr_to_columns(in_pred, &mut needed)?;
         }
 

datafusion/optimizer/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))]
 
 //! # DataFusion Optimizer
 //!

datafusion/optimizer/src/simplify_expressions/expr_simplifier.rs

@@ -1659,7 +1659,7 @@ impl<S: SimplifyInfo> TreeNodeRewriter for Simplifier<'_, S> {
                                     .to_string();
                                 Transformed::yes(Expr::Like(Like {
                                     pattern: Box::new(to_string_scalar(
-                                        data_type,
+                                        &data_type,
                                         Some(simplified_pattern),
                                     )),
                                     ..like
@@ -1971,7 +1971,7 @@ fn as_string_scalar(expr: &Expr) -> Option<(DataType, &Option<String>)> {
     }
 }
 
-fn to_string_scalar(data_type: DataType, value: Option<String>) -> Expr {
+fn to_string_scalar(data_type: &DataType, value: Option<String>) -> Expr {
     match data_type {
         DataType::Utf8 => Expr::Literal(ScalarValue::Utf8(value), None),
         DataType::LargeUtf8 => Expr::Literal(ScalarValue::LargeUtf8(value), None),