Merge branch 'main' into implement_groups_accumulator_count_distinct_primitive_types

Author: coderfender

.github/workflows/audit.yml

@@ -48,4 +48,4 @@ jobs:
       - name: Run audit check
         # Note: you can ignore specific RUSTSEC issues using the `--ignore` flag ,for example:
         # run: cargo audit --ignore RUSTSEC-2026-0001
-        run: cargo audit --ignore RUSTSEC-2024-0014
+        run: cargo audit

Cargo.lock

@@ -677,7 +677,7 @@ run_tpch() {
     echo "Running tpch benchmark..."
 
     FORMAT=$2
-    debug_run $CARGO_COMMAND --bin dfbench -- tpch --iterations 5 --path "${TPCH_DIR}" --prefer_hash_join "${PREFER_HASH_JOIN}" --format ${FORMAT} -o "${RESULTS_FILE}" ${QUERY_ARG} ${LATENCY_ARG}
+    debug_run $CARGO_COMMAND --bin dfbench -- tpch --iterations 5 --path "${TPCH_DIR}" --scale-factor "${SCALE_FACTOR}" --prefer_hash_join "${PREFER_HASH_JOIN}" --format ${FORMAT} -o "${RESULTS_FILE}" ${QUERY_ARG} ${LATENCY_ARG}
 }
 
 # Runs the tpch in memory (needs tpch parquet data)
@@ -693,7 +693,7 @@ run_tpch_mem() {
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running tpch_mem benchmark..."
     # -m means in memory
-    debug_run $CARGO_COMMAND --bin dfbench -- tpch --iterations 5 --path "${TPCH_DIR}" --prefer_hash_join "${PREFER_HASH_JOIN}" -m --format parquet -o "${RESULTS_FILE}" ${QUERY_ARG} ${LATENCY_ARG}
+    debug_run $CARGO_COMMAND --bin dfbench -- tpch --iterations 5 --path "${TPCH_DIR}" --scale-factor "${SCALE_FACTOR}" --prefer_hash_join "${PREFER_HASH_JOIN}" -m --format parquet -o "${RESULTS_FILE}" ${QUERY_ARG} ${LATENCY_ARG}
 }
 
 # Runs the tpcds benchmark
@@ -900,7 +900,7 @@ data_imdb() {
                 if [ "${DOWNLOADED_SIZE}" != "${expected_size}" ]; then
                     echo "Error: Download size mismatch"
                     echo "Expected: ${expected_size}"
-                    echo "Got: ${DOWNLADED_SIZE}"
+                    echo "Got: ${DOWNLOADED_SIZE}"
                     echo "Please re-initiate the download"
                     return 1
                 fi

benchmarks/bench.sh

@@ -164,12 +164,12 @@ def lineformat(
 ) -> None:
     baseline = BenchmarkRun.load_from_file(baseline)
     context = baseline.context
-    benchamrk_str = f"benchmark,name={context.name},version={context.benchmark_version},datafusion_version={context.datafusion_version},num_cpus={context.num_cpus}"
+    benchmark_str = f"benchmark,name={context.name},version={context.benchmark_version},datafusion_version={context.datafusion_version},num_cpus={context.num_cpus}"
     for query in baseline.queries:
         query_str = f"query=\"{query.query}\""
         timestamp = f"{query.start_time*10**9}"
         for iter_num, result in enumerate(query.iterations):
-            print(f"{benchamrk_str} {query_str},iteration={iter_num},row_count={result.row_count},elapsed_ms={result.elapsed*1000:.0f} {timestamp}\n")
+            print(f"{benchmark_str} {query_str},iteration={iter_num},row_count={result.row_count},elapsed_ms={result.elapsed*1000:.0f} {timestamp}\n")
 
 def main() -> None:
     parser = ArgumentParser()

benchmarks/lineprotocol.py

@@ -109,4 +109,11 @@ SELECT
     id3,
     v2,
     sum(v2) OVER (PARTITION BY id2 ORDER BY v2 RANGE BETWEEN 3 PRECEDING AND CURRENT ROW) AS my_range_between_by_id2
-FROM large;
+FROM large;
+
+-- Window Top-N (ROW_NUMBER top-2 per partition)
+SELECT id2, largest2_v2 FROM (
+    SELECT id2, v2 AS largest2_v2,
+           ROW_NUMBER() OVER (PARTITION BY id2 ORDER BY v2 DESC) AS order_v2
+    FROM large WHERE v2 IS NOT NULL
+) sub_query WHERE order_v2 <= 2;

benchmarks/queries/h2o/window.sql

@@ -16,7 +16,7 @@ where
         c_custkey = o_custkey
   and l_orderkey = o_orderkey
   and o_orderdate >= date '1993-10-01'
-  and o_orderdate < date '1994-01-01'
+  and o_orderdate < date '1993-10-01' + interval '3' month
   and l_returnflag = 'R'
   and c_nationkey = n_nationkey
 group by

benchmarks/queries/q10.sql

@@ -13,7 +13,7 @@ group by
     ps_partkey having
     sum(ps_supplycost * ps_availqty) > (
     select
-    sum(ps_supplycost * ps_availqty) * 0.0001
+    sum(ps_supplycost * ps_availqty) * 0.0001 /* __TPCH_Q11_FRACTION__ */
     from
     partsupp,
     supplier,
@@ -24,4 +24,4 @@ group by
                   and n_name = 'GERMANY'
     )
 order by
-    value desc;
+    value desc;

benchmarks/queries/q11.sql

@@ -23,8 +23,8 @@ where
   and l_commitdate < l_receiptdate
   and l_shipdate < l_commitdate
   and l_receiptdate >= date '1994-01-01'
-  and l_receiptdate < date '1995-01-01'
+  and l_receiptdate < date '1994-01-01' + interval '1' year
 group by
     l_shipmode
 order by
-    l_shipmode;
+    l_shipmode;

benchmarks/queries/q12.sql

@@ -10,4 +10,4 @@ from
 where
         l_partkey = p_partkey
   and l_shipdate >= date '1995-09-01'
-  and l_shipdate < date '1995-10-01';
+  and l_shipdate < date '1995-09-01' + interval '1' month;

benchmarks/queries/q14.sql

@@ -17,8 +17,8 @@ where
   and n_regionkey = r_regionkey
   and r_name = 'ASIA'
   and o_orderdate >= date '1994-01-01'
-  and o_orderdate < date '1995-01-01'
+  and o_orderdate < date '1994-01-01' + interval '1' year
 group by
     n_name
 order by
-    revenue desc;
+    revenue desc;