Merge branch 'main' into aa/string_builder_char

Author: ajita-asthana

benchmarks/README.md

@@ -510,6 +510,15 @@ See [`sort_tpch.rs`](src/sort_tpch.rs) for more details.
 ./bench.sh run sort_tpch
 ```
 
+### TopK TPCH
+
+In addition, topk_tpch is available from the bench.sh script:
+
+```bash
+./bench.sh run topk_tpch
+```
+
+
 ## IMDB
 
 Run Join Order Benchmark (JOB) on IMDB dataset.

benchmarks/bench.sh

@@ -236,6 +236,10 @@ main() {
                     # same data as for tpch
                     data_tpch "1"
                     ;;
+                topk_tpch)
+                    # same data as for tpch
+                    data_tpch "1"
+                    ;;
                 *)
                     echo "Error: unknown benchmark '$BENCHMARK' for data generation"
                     usage
@@ -361,6 +365,9 @@ main() {
                 sort_tpch)
                     run_sort_tpch
                     ;;
+                topk_tpch)
+                    run_topk_tpch
+                    ;;
                 *)
                     echo "Error: unknown benchmark '$BENCHMARK' for run"
                     usage
@@ -981,6 +988,16 @@ run_sort_tpch() {
     debug_run $CARGO_COMMAND --bin dfbench -- sort-tpch --iterations 5 --path "${TPCH_DIR}" -o "${RESULTS_FILE}"
 }
 
+# Runs the sort tpch integration benchmark with limit 100 (topk)
+run_topk_tpch() {
+    TPCH_DIR="${DATA_DIR}/tpch_sf1"
+    RESULTS_FILE="${RESULTS_DIR}/run_topk_tpch.json"
+    echo "RESULTS_FILE: ${RESULTS_FILE}"
+    echo "Running topk tpch benchmark..."
+
+    $CARGO_COMMAND --bin dfbench -- sort-tpch --iterations 5 --path "${TPCH_DIR}" -o "${RESULTS_FILE}" --limit 100
+}
+
 
 compare_benchmarks() {
     BASE_RESULTS_DIR="${SCRIPT_DIR}/results"

datafusion/expr/src/logical_plan/tree_node.rs

@@ -436,11 +436,11 @@ impl LogicalPlan {
                 filters.apply_elements(f)
             }
             LogicalPlan::Unnest(unnest) => {
-                let columns = unnest.exec_columns.clone();
-
-                let exprs = columns
+                let exprs = unnest
+                    .exec_columns
                     .iter()
-                    .map(|c| Expr::Column(c.clone()))
+                    .cloned()
+                    .map(Expr::Column)
                     .collect::<Vec<_>>();
                 exprs.apply_elements(f)
             }

datafusion/optimizer/src/simplify_expressions/inlist_simplifier.rs

@@ -39,10 +39,10 @@ impl TreeNodeRewriter for ShortenInListSimplifier {
         // if expr is a single column reference:
         // expr IN (A, B, ...) --> (expr = A) OR (expr = B) OR (expr = C)
         if let Expr::InList(InList {
-            expr,
-            list,
+            ref expr,
+            ref list,
             negated,
-        }) = expr.clone()
+        }) = expr
         {
             if !list.is_empty()
                 && (
@@ -57,7 +57,7 @@ impl TreeNodeRewriter for ShortenInListSimplifier {
             {
                 let first_val = list[0].clone();
                 if negated {
-                    return Ok(Transformed::yes(list.into_iter().skip(1).fold(
+                    return Ok(Transformed::yes(list.iter().skip(1).cloned().fold(
                         (*expr.clone()).not_eq(first_val),
                         |acc, y| {
                             // Note that `A and B and C and D` is a left-deep tree structure
@@ -81,7 +81,7 @@ impl TreeNodeRewriter for ShortenInListSimplifier {
                         },
                     )));
                 } else {
-                    return Ok(Transformed::yes(list.into_iter().skip(1).fold(
+                    return Ok(Transformed::yes(list.iter().skip(1).cloned().fold(
                         (*expr.clone()).eq(first_val),
                         |acc, y| {
                             // Same reasoning as above