Merge branch 'main' into row_group_limit_pruning

Author: xudong963

.github/dependabot.yml

@@ -23,6 +23,7 @@ updates:
       interval: weekly
     target-branch: main
     labels: [auto-dependencies]
+    open-pull-requests-limit: 15
     ignore:
       # major version bumps of arrow* and parquet are handled manually
       - dependency-name: "arrow*"

.github/workflows/audit.yml

@@ -42,7 +42,7 @@ jobs:
     steps:
       - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8  # v6.0.1
       - name: Install cargo-audit
-        uses: taiki-e/install-action@0e76c5c569f13f7eb21e8e5b26fe710062b57b62  # v2.65.13
+        uses: taiki-e/install-action@3522286d40783523f9c7880e33f785905b4c20d0  # v2.66.1
         with:
           tool: cargo-audit
       - name: Run audit check

.github/workflows/rust.yml

@@ -421,7 +421,7 @@ jobs:
           sudo apt-get update -qq
           sudo apt-get install -y -qq clang
       - name: Setup wasm-pack
-        uses: taiki-e/install-action@0e76c5c569f13f7eb21e8e5b26fe710062b57b62  # v2.65.13
+        uses: taiki-e/install-action@3522286d40783523f9c7880e33f785905b4c20d0  # v2.66.1
         with:
           tool: wasm-pack
       - name: Run tests with headless mode
@@ -741,7 +741,7 @@ jobs:
       - name: Setup Rust toolchain
         uses: ./.github/actions/setup-builder
       - name: Install cargo-msrv
-        uses: taiki-e/install-action@0e76c5c569f13f7eb21e8e5b26fe710062b57b62  # v2.65.13
+        uses: taiki-e/install-action@3522286d40783523f9c7880e33f785905b4c20d0  # v2.66.1
         with:
           tool: cargo-msrv
 

Cargo.lock

@@ -158,7 +158,7 @@ glob = "0.3.0"
 half = { version = "2.7.0", default-features = false }
 hashbrown = { version = "0.16.1" }
 hex = { version = "0.4.3" }
-indexmap = "2.12.1"
+indexmap = "2.13.0"
 insta = { version = "1.46.0", features = ["glob", "filters"] }
 itertools = "0.14"
 liblzma = { version = "0.4.4", features = ["static"] }

Cargo.toml

@@ -322,8 +322,7 @@ main() {
                     echo "NLJ benchmark does not require data generation"
                     ;;
                 hj)
-                    # hj uses range() function, no data generation needed
-                    echo "HJ benchmark does not require data generation"
+                    data_tpch "10" "parquet"
                     ;;
                 smj)
                     # smj uses range() function, no data generation needed
@@ -1228,10 +1227,11 @@ run_nlj() {
 
 # Runs the hj benchmark
 run_hj() {
+    TPCH_DIR="${DATA_DIR}/tpch_sf10"
     RESULTS_FILE="${RESULTS_DIR}/hj.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running hj benchmark..."
-    debug_run $CARGO_COMMAND --bin dfbench -- hj --iterations 5 -o "${RESULTS_FILE}" ${QUERY_ARG}
+    debug_run $CARGO_COMMAND --bin dfbench -- hj --iterations 5 --path "${TPCH_DIR}" -o "${RESULTS_FILE}" ${QUERY_ARG}
 }
 
 # Runs the smj benchmark

benchmarks/bench.sh

@@ -154,17 +154,17 @@ def compare(
     baseline = BenchmarkRun.load_from_file(baseline_path)
     comparison = BenchmarkRun.load_from_file(comparison_path)
 
-    console = Console()
+    console = Console(width=200)
 
     # use basename as the column names
-    baseline_header = baseline_path.parent.stem
-    comparison_header = comparison_path.parent.stem
+    baseline_header = baseline_path.parent.name
+    comparison_header = comparison_path.parent.name
 
     table = Table(show_header=True, header_style="bold magenta")
-    table.add_column("Query", style="dim", width=12)
-    table.add_column(baseline_header, justify="right", style="dim")
-    table.add_column(comparison_header, justify="right", style="dim")
-    table.add_column("Change", justify="right", style="dim")
+    table.add_column("Query", style="dim", no_wrap=True)
+    table.add_column(baseline_header, justify="right", style="dim", no_wrap=True)
+    table.add_column(comparison_header, justify="right", style="dim", no_wrap=True)
+    table.add_column("Change", justify="right", style="dim", no_wrap=True)
 
     faster_count = 0
     slower_count = 0
@@ -175,12 +175,12 @@ def compare(
 
     for baseline_result, comparison_result in zip(baseline.queries, comparison.queries):
         assert baseline_result.query == comparison_result.query
-        
+
         base_failed = not baseline_result.success
-        comp_failed = not comparison_result.success 
+        comp_failed = not comparison_result.success
         # If a query fails, its execution time is excluded from the performance comparison
         if base_failed or comp_failed:
-            change_text = "incomparable" 
+            change_text = "incomparable"
             failure_count += 1
             table.add_row(
                 f"Q{baseline_result.query}",