Support non-equijoin predicate for EliminateCrossJoin

benchmarks/expected-plans/q11.txt

@@ -1,20 +1,19 @@
 Sort: value DESC NULLS FIRST
   Projection: partsupp.ps_partkey, SUM(partsupp.ps_supplycost * partsupp.ps_availqty) AS value
-    Filter: CAST(SUM(partsupp.ps_supplycost * partsupp.ps_availqty) AS Decimal128(38, 15)) > CAST(__scalar_sq_1.__value AS Decimal128(38, 15))
-      CrossJoin:
-        Aggregate: groupBy=[[partsupp.ps_partkey]], aggr=[[SUM(CAST(partsupp.ps_supplycost AS Decimal128(26, 2)) * CAST(partsupp.ps_availqty AS Decimal128(26, 2)))]]
-          Inner Join: supplier.s_nationkey = nation.n_nationkey
-            Inner Join: partsupp.ps_suppkey = supplier.s_suppkey
-              TableScan: partsupp projection=[ps_partkey, ps_suppkey, ps_availqty, ps_supplycost]
-              TableScan: supplier projection=[s_suppkey, s_nationkey]
-            Filter: nation.n_name = Utf8("GERMANY")
-              TableScan: nation projection=[n_nationkey, n_name]
-        SubqueryAlias: __scalar_sq_1
-          Projection: CAST(SUM(partsupp.ps_supplycost * partsupp.ps_availqty) AS Float64) * Float64(0.0001) AS __value
-            Aggregate: groupBy=[[]], aggr=[[SUM(CAST(partsupp.ps_supplycost AS Decimal128(26, 2)) * CAST(partsupp.ps_availqty AS Decimal128(26, 2)))]]
-              Inner Join: supplier.s_nationkey = nation.n_nationkey
-                Inner Join: partsupp.ps_suppkey = supplier.s_suppkey
-                  TableScan: partsupp projection=[ps_suppkey, ps_availqty, ps_supplycost]
-                  TableScan: supplier projection=[s_suppkey, s_nationkey]
-                Filter: nation.n_name = Utf8("GERMANY")
-                  TableScan: nation projection=[n_nationkey, n_name]
+    Inner Join:  Filter: CAST(SUM(partsupp.ps_supplycost * partsupp.ps_availqty) AS Decimal128(38, 15)) > CAST(__scalar_sq_1.__value AS Decimal128(38, 15))
+      Aggregate: groupBy=[[partsupp.ps_partkey]], aggr=[[SUM(CAST(partsupp.ps_supplycost AS Decimal128(26, 2)) * CAST(partsupp.ps_availqty AS Decimal128(26, 2)))]]
+        Inner Join: supplier.s_nationkey = nation.n_nationkey
+          Inner Join: partsupp.ps_suppkey = supplier.s_suppkey
+            TableScan: partsupp projection=[ps_partkey, ps_suppkey, ps_availqty, ps_supplycost]
+            TableScan: supplier projection=[s_suppkey, s_nationkey]
+          Filter: nation.n_name = Utf8("GERMANY")
+            TableScan: nation projection=[n_nationkey, n_name]
+      SubqueryAlias: __scalar_sq_1
+        Projection: CAST(SUM(partsupp.ps_supplycost * partsupp.ps_availqty) AS Float64) * Float64(0.0001) AS __value
+          Aggregate: groupBy=[[]], aggr=[[SUM(CAST(partsupp.ps_supplycost AS Decimal128(26, 2)) * CAST(partsupp.ps_availqty AS Decimal128(26, 2)))]]
+            Inner Join: supplier.s_nationkey = nation.n_nationkey
+              Inner Join: partsupp.ps_suppkey = supplier.s_suppkey
+                TableScan: partsupp projection=[ps_suppkey, ps_availqty, ps_supplycost]
+                TableScan: supplier projection=[s_suppkey, s_nationkey]
+              Filter: nation.n_name = Utf8("GERMANY")
+                TableScan: nation projection=[n_nationkey, n_name]

benchmarks/expected-plans/q17.txt

@@ -1,7 +1,7 @@
 Projection: CAST(SUM(lineitem.l_extendedprice) AS Float64) / Float64(7) AS avg_yearly
   Aggregate: groupBy=[[]], aggr=[[SUM(lineitem.l_extendedprice)]]
-    Filter: CAST(lineitem.l_quantity AS Decimal128(30, 15)) < CAST(__scalar_sq_1.__value AS Decimal128(30, 15))
-      Inner Join: part.p_partkey = __scalar_sq_1.l_partkey, lineitem.l_partkey = __scalar_sq_1.l_partkey
+    Projection: lineitem.l_extendedprice
+      Inner Join: part.p_partkey = __scalar_sq_1.l_partkey Filter: CAST(lineitem.l_quantity AS Decimal128(30, 15)) < CAST(__scalar_sq_1.__value AS Decimal128(30, 15))
         Inner Join: lineitem.l_partkey = part.p_partkey
           TableScan: lineitem projection=[l_partkey, l_quantity, l_extendedprice]
           Filter: part.p_brand = Utf8("Brand#23") AND part.p_container = Utf8("MED BOX")

benchmarks/expected-plans/q19.txt

@@ -1,8 +1,7 @@
 Projection: SUM(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount) AS revenue
   Aggregate: groupBy=[[]], aggr=[[SUM(CAST(lineitem.l_extendedprice AS Decimal128(38, 4)) * CAST(Decimal128(Some(100),23,2) - CAST(lineitem.l_discount AS Decimal128(23, 2)) AS Decimal128(38, 4))) AS SUM(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)]]
-    Filter: part.p_brand = Utf8("Brand#12") AND part.p_container IN ([Utf8("SM CASE"), Utf8("SM BOX"), Utf8("SM PACK"), Utf8("SM PKG")]) AND lineitem.l_quantity >= Decimal128(Some(100),15,2) AND lineitem.l_quantity <= Decimal128(Some(1100),15,2) AND part.p_size <= Int32(5) OR part.p_brand = Utf8("Brand#23") AND part.p_container IN ([Utf8("MED BAG"), Utf8("MED BOX"), Utf8("MED PKG"), Utf8("MED PACK")]) AND lineitem.l_quantity >= Decimal128(Some(1000),15,2) AND lineitem.l_quantity <= Decimal128(Some(2000),15,2) AND part.p_size <= Int32(10) OR part.p_brand = Utf8("Brand#34") AND part.p_container IN ([Utf8("LG CASE"), Utf8("LG BOX"), Utf8("LG PACK"), Utf8("LG PKG")]) AND lineitem.l_quantity >= Decimal128(Some(2000),15,2) AND lineitem.l_quantity <= Decimal128(Some(3000),15,2) AND part.p_size <= Int32(15)
-      Inner Join: lineitem.l_partkey = part.p_partkey
-        Filter: (lineitem.l_quantity >= Decimal128(Some(100),15,2) AND lineitem.l_quantity <= Decimal128(Some(1100),15,2) OR lineitem.l_quantity >= Decimal128(Some(1000),15,2) AND lineitem.l_quantity <= Decimal128(Some(2000),15,2) OR lineitem.l_quantity >= Decimal128(Some(2000),15,2) AND lineitem.l_quantity <= Decimal128(Some(3000),15,2)) AND (lineitem.l_shipmode = Utf8("AIR REG") OR lineitem.l_shipmode = Utf8("AIR")) AND lineitem.l_shipinstruct = Utf8("DELIVER IN PERSON")
-          TableScan: lineitem projection=[l_partkey, l_quantity, l_extendedprice, l_discount, l_shipinstruct, l_shipmode]
-        Filter: (part.p_brand = Utf8("Brand#12") AND part.p_container IN ([Utf8("SM CASE"), Utf8("SM BOX"), Utf8("SM PACK"), Utf8("SM PKG")]) AND part.p_size <= Int32(5) OR part.p_brand = Utf8("Brand#23") AND part.p_container IN ([Utf8("MED BAG"), Utf8("MED BOX"), Utf8("MED PKG"), Utf8("MED PACK")]) AND part.p_size <= Int32(10) OR part.p_brand = Utf8("Brand#34") AND part.p_container IN ([Utf8("LG CASE"), Utf8("LG BOX"), Utf8("LG PACK"), Utf8("LG PKG")]) AND part.p_size <= Int32(15)) AND part.p_size >= Int32(1)
-          TableScan: part projection=[p_partkey, p_brand, p_size, p_container]
+    Inner Join: lineitem.l_partkey = part.p_partkey Filter: part.p_brand = Utf8("Brand#12") AND part.p_container IN ([Utf8("SM CASE"), Utf8("SM BOX"), Utf8("SM PACK"), Utf8("SM PKG")]) AND lineitem.l_quantity >= Decimal128(Some(100),15,2) AND lineitem.l_quantity <= Decimal128(Some(1100),15,2) AND part.p_size <= Int32(5) OR part.p_brand = Utf8("Brand#23") AND part.p_container IN ([Utf8("MED BAG"), Utf8("MED BOX"), Utf8("MED PKG"), Utf8("MED PACK")]) AND lineitem.l_quantity >= Decimal128(Some(1000),15,2) AND lineitem.l_quantity <= Decimal128(Some(2000),15,2) AND part.p_size <= Int32(10) OR part.p_brand = Utf8("Brand#34") AND part.p_container IN ([Utf8("LG CASE"), Utf8("LG BOX"), Utf8("LG PACK"), Utf8("LG PKG")]) AND lineitem.l_quantity >= Decimal128(Some(2000),15,2) AND lineitem.l_quantity <= Decimal128(Some(3000),15,2) AND part.p_size <= Int32(15)
+      Filter: (lineitem.l_quantity >= Decimal128(Some(100),15,2) AND lineitem.l_quantity <= Decimal128(Some(1100),15,2) OR lineitem.l_quantity >= Decimal128(Some(1000),15,2) AND lineitem.l_quantity <= Decimal128(Some(2000),15,2) OR lineitem.l_quantity >= Decimal128(Some(2000),15,2) AND lineitem.l_quantity <= Decimal128(Some(3000),15,2)) AND (lineitem.l_shipmode = Utf8("AIR REG") OR lineitem.l_shipmode = Utf8("AIR")) AND lineitem.l_shipinstruct = Utf8("DELIVER IN PERSON")
+        TableScan: lineitem projection=[l_partkey, l_quantity, l_extendedprice, l_discount, l_shipinstruct, l_shipmode]
+      Filter: (part.p_brand = Utf8("Brand#12") AND part.p_container IN ([Utf8("SM CASE"), Utf8("SM BOX"), Utf8("SM PACK"), Utf8("SM PKG")]) AND part.p_size <= Int32(5) OR part.p_brand = Utf8("Brand#23") AND part.p_container IN ([Utf8("MED BAG"), Utf8("MED BOX"), Utf8("MED PKG"), Utf8("MED PACK")]) AND part.p_size <= Int32(10) OR part.p_brand = Utf8("Brand#34") AND part.p_container IN ([Utf8("LG CASE"), Utf8("LG BOX"), Utf8("LG PACK"), Utf8("LG PKG")]) AND part.p_size <= Int32(15)) AND part.p_size >= Int32(1)
+        TableScan: part projection=[p_partkey, p_brand, p_size, p_container]

benchmarks/expected-plans/q20.txt

@@ -7,16 +7,15 @@ Sort: supplier.s_name ASC NULLS LAST
           TableScan: nation projection=[n_nationkey, n_name]
       SubqueryAlias: __correlated_sq_1
         Projection: partsupp.ps_suppkey AS ps_suppkey
-          Filter: CAST(partsupp.ps_availqty AS Float64) > __scalar_sq_1.__value
-            Inner Join: partsupp.ps_partkey = __scalar_sq_1.l_partkey, partsupp.ps_suppkey = __scalar_sq_1.l_suppkey
-              LeftSemi Join: partsupp.ps_partkey = __correlated_sq_2.p_partkey
-                TableScan: partsupp projection=[ps_partkey, ps_suppkey, ps_availqty]
-                SubqueryAlias: __correlated_sq_2
-                  Projection: part.p_partkey AS p_partkey
-                    Filter: part.p_name LIKE Utf8("forest%")
-                      TableScan: part projection=[p_partkey, p_name]
-              SubqueryAlias: __scalar_sq_1
-                Projection: lineitem.l_partkey, lineitem.l_suppkey, Float64(0.5) * CAST(SUM(lineitem.l_quantity) AS Float64) AS __value
-                  Aggregate: groupBy=[[lineitem.l_partkey, lineitem.l_suppkey]], aggr=[[SUM(lineitem.l_quantity)]]
-                    Filter: lineitem.l_shipdate >= Date32("8766") AND lineitem.l_shipdate < Date32("9131")
-                      TableScan: lineitem projection=[l_partkey, l_suppkey, l_quantity, l_shipdate]
+          Inner Join: partsupp.ps_partkey = __scalar_sq_1.l_partkey, partsupp.ps_suppkey = __scalar_sq_1.l_suppkey Filter: CAST(partsupp.ps_availqty AS Float64) > __scalar_sq_1.__value
+            LeftSemi Join: partsupp.ps_partkey = __correlated_sq_2.p_partkey
+              TableScan: partsupp projection=[ps_partkey, ps_suppkey, ps_availqty]
+              SubqueryAlias: __correlated_sq_2
+                Projection: part.p_partkey AS p_partkey
+                  Filter: part.p_name LIKE Utf8("forest%")
+                    TableScan: part projection=[p_partkey, p_name]
+            SubqueryAlias: __scalar_sq_1
+              Projection: lineitem.l_partkey, lineitem.l_suppkey, Float64(0.5) * CAST(SUM(lineitem.l_quantity) AS Float64) AS __value
+                Aggregate: groupBy=[[lineitem.l_partkey, lineitem.l_suppkey]], aggr=[[SUM(lineitem.l_quantity)]]
+                  Filter: lineitem.l_shipdate >= Date32("8766") AND lineitem.l_shipdate < Date32("9131")
+                    TableScan: lineitem projection=[l_partkey, l_suppkey, l_quantity, l_shipdate]

benchmarks/expected-plans/q22.txt

@@ -3,14 +3,13 @@ Sort: custsale.cntrycode ASC NULLS LAST
     Aggregate: groupBy=[[custsale.cntrycode]], aggr=[[COUNT(UInt8(1)), SUM(custsale.c_acctbal)]]
       SubqueryAlias: custsale
         Projection: substr(customer.c_phone, Int64(1), Int64(2)) AS cntrycode, customer.c_acctbal
-          Filter: CAST(customer.c_acctbal AS Decimal128(19, 6)) > __scalar_sq_1.__value
-            CrossJoin:
-              LeftAnti Join: customer.c_custkey = orders.o_custkey
-                Filter: substr(customer.c_phone, Int64(1), Int64(2)) IN ([Utf8("13"), Utf8("31"), Utf8("23"), Utf8("29"), Utf8("30"), Utf8("18"), Utf8("17")])
-                  TableScan: customer projection=[c_custkey, c_phone, c_acctbal]
-                TableScan: orders projection=[o_custkey]
-              SubqueryAlias: __scalar_sq_1
-                Projection: AVG(customer.c_acctbal) AS __value
-                  Aggregate: groupBy=[[]], aggr=[[AVG(customer.c_acctbal)]]
-                    Filter: customer.c_acctbal > Decimal128(Some(0),15,2) AND substr(customer.c_phone, Int64(1), Int64(2)) IN ([Utf8("13"), Utf8("31"), Utf8("23"), Utf8("29"), Utf8("30"), Utf8("18"), Utf8("17")])
-                      TableScan: customer projection=[c_phone, c_acctbal]
+          Inner Join:  Filter: CAST(customer.c_acctbal AS Decimal128(19, 6)) > __scalar_sq_1.__value
+            LeftAnti Join: customer.c_custkey = orders.o_custkey
+              Filter: substr(customer.c_phone, Int64(1), Int64(2)) IN ([Utf8("13"), Utf8("31"), Utf8("23"), Utf8("29"), Utf8("30"), Utf8("18"), Utf8("17")])
+                TableScan: customer projection=[c_custkey, c_phone, c_acctbal]
+              TableScan: orders projection=[o_custkey]
+            SubqueryAlias: __scalar_sq_1
+              Projection: AVG(customer.c_acctbal) AS __value
+                Aggregate: groupBy=[[]], aggr=[[AVG(customer.c_acctbal)]]
+                  Filter: customer.c_acctbal > Decimal128(Some(0),15,2) AND substr(customer.c_phone, Int64(1), Int64(2)) IN ([Utf8("13"), Utf8("31"), Utf8("23"), Utf8("29"), Utf8("30"), Utf8("18"), Utf8("17")])
+                    TableScan: customer projection=[c_phone, c_acctbal]

benchmarks/expected-plans/q7.txt

@@ -3,20 +3,19 @@ Sort: shipping.supp_nation ASC NULLS LAST, shipping.cust_nation ASC NULLS LAST,
     Aggregate: groupBy=[[shipping.supp_nation, shipping.cust_nation, shipping.l_year]], aggr=[[SUM(shipping.volume)]]
       SubqueryAlias: shipping
         Projection: n1.n_name AS supp_nation, n2.n_name AS cust_nation, datepart(Utf8("YEAR"), lineitem.l_shipdate) AS l_year, CAST(lineitem.l_extendedprice AS Decimal128(38, 4)) * CAST(Decimal128(Some(100),23,2) - CAST(lineitem.l_discount AS Decimal128(23, 2)) AS Decimal128(38, 4)) AS volume
-          Filter: n1.n_name = Utf8("FRANCE") AND n2.n_name = Utf8("GERMANY") OR n1.n_name = Utf8("GERMANY") AND n2.n_name = Utf8("FRANCE")
-            Inner Join: customer.c_nationkey = n2.n_nationkey
-              Inner Join: supplier.s_nationkey = n1.n_nationkey
-                Inner Join: orders.o_custkey = customer.c_custkey
-                  Inner Join: lineitem.l_orderkey = orders.o_orderkey
-                    Inner Join: supplier.s_suppkey = lineitem.l_suppkey
-                      TableScan: supplier projection=[s_suppkey, s_nationkey]
-                      Filter: lineitem.l_shipdate >= Date32("9131") AND lineitem.l_shipdate <= Date32("9861")
-                        TableScan: lineitem projection=[l_orderkey, l_suppkey, l_extendedprice, l_discount, l_shipdate]
-                    TableScan: orders projection=[o_orderkey, o_custkey]
-                  TableScan: customer projection=[c_custkey, c_nationkey]
-                SubqueryAlias: n1
-                  Filter: nation.n_name = Utf8("FRANCE") OR nation.n_name = Utf8("GERMANY")
-                    TableScan: nation projection=[n_nationkey, n_name]
-              SubqueryAlias: n2
-                Filter: nation.n_name = Utf8("GERMANY") OR nation.n_name = Utf8("FRANCE")
-                  TableScan: nation projection=[n_nationkey, n_name]
+          Inner Join: customer.c_nationkey = n2.n_nationkey Filter: n1.n_name = Utf8("FRANCE") AND n2.n_name = Utf8("GERMANY") OR n1.n_name = Utf8("GERMANY") AND n2.n_name = Utf8("FRANCE")
+            Inner Join: supplier.s_nationkey = n1.n_nationkey
+              Inner Join: orders.o_custkey = customer.c_custkey
+                Inner Join: lineitem.l_orderkey = orders.o_orderkey
+                  Inner Join: supplier.s_suppkey = lineitem.l_suppkey
+                    TableScan: supplier projection=[s_suppkey, s_nationkey]
+                    Filter: lineitem.l_shipdate >= Date32("9131") AND lineitem.l_shipdate <= Date32("9861")
+                      TableScan: lineitem projection=[l_orderkey, l_suppkey, l_extendedprice, l_discount, l_shipdate]
+                  TableScan: orders projection=[o_orderkey, o_custkey]
+                TableScan: customer projection=[c_custkey, c_nationkey]
+              SubqueryAlias: n1
+                Filter: nation.n_name = Utf8("FRANCE") OR nation.n_name = Utf8("GERMANY")
+                  TableScan: nation projection=[n_nationkey, n_name]
+            SubqueryAlias: n2
+              Filter: nation.n_name = Utf8("GERMANY") OR nation.n_name = Utf8("FRANCE")
+                TableScan: nation projection=[n_nationkey, n_name]