bench(hj): Add missing Q16–Q23 to benchmarks

benchmarks/sql_benchmarks/hj/benchmarks/q16.benchmark

@@ -0,0 +1,21 @@
+name Q16
+group hj
+
+init sql_benchmarks/hj/init/set_config.sql
+
+load sql_benchmarks/hj/init/load.sql
+
+assert I
+SELECT count(*) > 0 FROM customer
+----
+true
+
+expect_plan HashJoinExec
+
+run
+-- Q16: RightSemi, Small build (25 rows), 100% Hit rate
+-- Build Side: nation (25 rows) | Probe Side: customer (1.5M rows)
+SELECT c.k
+FROM (SELECT CAST(n_nationkey AS INT) as k FROM nation) n
+RIGHT SEMI JOIN (SELECT CAST(c_nationkey AS INT) as k FROM customer) c
+ON n.k = c.k;

benchmarks/sql_benchmarks/hj/benchmarks/q17.benchmark

@@ -0,0 +1,21 @@
+name Q17
+group hj
+
+init sql_benchmarks/hj/init/set_config.sql
+
+load sql_benchmarks/hj/init/load.sql
+
+assert I
+SELECT count(*) > 0 FROM lineitem
+----
+true
+
+expect_plan HashJoinExec
+
+run
+-- Q17: RightSemi, Medium build (100K rows), 100% Hit rate
+-- Build Side: supplier (100K rows) | Probe Side: lineitem (60M rows)
+SELECT l.k
+FROM (SELECT CAST(s_suppkey AS INT) as k FROM supplier) s
+RIGHT SEMI JOIN (SELECT CAST(l_suppkey AS INT) as k FROM lineitem) l
+ON s.k = l.k;

benchmarks/sql_benchmarks/hj/benchmarks/q18.benchmark

@@ -0,0 +1,24 @@
+name Q18
+group hj
+
+init sql_benchmarks/hj/init/set_config.sql
+
+load sql_benchmarks/hj/init/load.sql
+
+assert I
+SELECT count(*) > 0 FROM lineitem
+----
+true
+
+expect_plan HashJoinExec
+
+run
+-- Q18: RightSemi, Medium build (100K rows), 10% Hit rate
+-- Build Side: supplier (100K rows) | Probe Side: lineitem (60M rows)
+SELECT l.k
+FROM (SELECT CAST(s_suppkey AS INT) as k FROM supplier) s
+RIGHT SEMI JOIN (
+  SELECT CAST(CASE WHEN l_suppkey % 10 = 0 THEN l_suppkey ELSE l_suppkey + 1000000 END AS INT) as k
+  FROM lineitem
+) l
+ON s.k = l.k;

benchmarks/sql_benchmarks/hj/benchmarks/q19.benchmark

@@ -0,0 +1,21 @@
+name Q19
+group hj
+
+init sql_benchmarks/hj/init/set_config.sql
+
+load sql_benchmarks/hj/init/load.sql
+
+assert I
+SELECT count(*) > 0 FROM customer
+----
+true
+
+expect_plan HashJoinExec
+
+run
+-- Q19: RightAnti, Small build (25 rows), 100% Hit rate (no output)
+-- Build Side: nation (25 rows) | Probe Side: customer (1.5M rows)
+SELECT c.k
+FROM (SELECT CAST(n_nationkey AS INT) as k FROM nation) n
+RIGHT ANTI JOIN (SELECT CAST(c_nationkey AS INT) as k FROM customer) c
+ON n.k = c.k;

benchmarks/sql_benchmarks/hj/benchmarks/q20.benchmark

@@ -0,0 +1,21 @@
+name Q20
+group hj
+
+init sql_benchmarks/hj/init/set_config.sql
+
+load sql_benchmarks/hj/init/load.sql
+
+assert I
+SELECT count(*) > 0 FROM lineitem
+----
+true
+
+expect_plan HashJoinExec
+
+run
+-- Q20: RightAnti, Medium build (100K rows), 100% Hit rate (no output)
+-- Build Side: supplier (100K rows) | Probe Side: lineitem (60M rows)
+SELECT l.k
+FROM (SELECT CAST(s_suppkey AS INT) as k FROM supplier) s
+RIGHT ANTI JOIN (SELECT CAST(l_suppkey AS INT) as k FROM lineitem) l
+ON s.k = l.k;

benchmarks/sql_benchmarks/hj/benchmarks/q21.benchmark

@@ -0,0 +1,24 @@
+name Q21
+group hj
+
+init sql_benchmarks/hj/init/set_config.sql
+
+load sql_benchmarks/hj/init/load.sql
+
+assert I
+SELECT count(*) > 0 FROM lineitem
+----
+true
+
+expect_plan HashJoinExec
+
+run
+-- Q21: RightAnti, Medium build (100K rows), 10% Hit rate (90% output)
+-- Build Side: supplier (100K rows) | Probe Side: lineitem (60M rows)
+SELECT l.k
+FROM (SELECT CAST(s_suppkey AS INT) as k FROM supplier) s
+RIGHT ANTI JOIN (
+  SELECT CAST(CASE WHEN l_suppkey % 10 = 0 THEN l_suppkey ELSE l_suppkey + 1000000 END AS INT) as k
+  FROM lineitem
+) l
+ON s.k = l.k;

benchmarks/sql_benchmarks/hj/benchmarks/q22.benchmark

@@ -0,0 +1,28 @@
+name Q22
+group hj
+
+init sql_benchmarks/hj/init/set_config.sql
+
+load sql_benchmarks/hj/init/load.sql
+
+assert I
+SELECT count(*) > 0 FROM lineitem
+----
+true
+
+expect_plan HashJoinExec
+
+run
+-- Q22: RightSemi, Medium build (100K rows), ~1% Hit rate, fanout ~100
+-- Build Side: supplier (100K rows) collapsed onto 1K distinct keys
+-- Probe Side: lineitem (60M rows)
+SELECT l.k
+FROM (
+  SELECT CAST(((s_suppkey - 1) % 1000) + 1 AS INT) as k
+  FROM supplier
+) s
+RIGHT SEMI JOIN (
+  SELECT CAST(l_suppkey AS INT) as k
+  FROM lineitem
+) l
+ON s.k = l.k;

benchmarks/sql_benchmarks/hj/benchmarks/q23.benchmark

@@ -0,0 +1,31 @@
+name Q23
+group hj
+
+init sql_benchmarks/hj/init/set_config_no_stats.sql
+
+load sql_benchmarks/hj/init/load.sql
+
+assert I
+SELECT count(*) > 0 FROM lineitem
+----
+true
+
+expect_plan HashJoinExec
+
+run
+-- Q23: high-fanout string-key inner join.
+-- Build ~32K rows / ~415 distinct keys (fanout ~78), probe ~2.3M rows
+-- (all carrying the dominant key), output ~176M pairs. Long keys (~28 chars)
+-- make per-pair key comparison expensive; count(*) isolates the match path.
+-- Thresholds zeroed to force Partitioned mode (simulates absent row-count stats).
+SELECT count(*)
+FROM (
+  SELECT 'high_fanout_string_join_key_' || CAST((s_suppkey % 415) + 1 AS VARCHAR) as k
+  FROM supplier
+  WHERE s_suppkey <= 32340
+) s
+JOIN (
+  SELECT 'high_fanout_string_join_key_1' as k
+  FROM lineitem
+  WHERE l_orderkey % 265 = 0
+) l ON s.k = l.k;

benchmarks/sql_benchmarks/hj/init/set_config.sql

@@ -0,0 +1 @@
+set datafusion.optimizer.join_reordering = false;

benchmarks/sql_benchmarks/hj/init/set_config_no_stats.sql

@@ -0,0 +1,3 @@
+set datafusion.optimizer.join_reordering = false;
+set datafusion.optimizer.hash_join_single_partition_threshold = 0;
+set datafusion.optimizer.hash_join_single_partition_threshold_rows = 0;