More

datafusion/sqllogictest/test_files/sort_merge_join.slt

@@ -0,0 +1,48 @@
+# related to: https://github.com/apache/arrow-datafusion/issues/8374
+statement ok
+CREATE TABLE t1(a text, b int) AS VALUES ('Alice', 50), ('Alice', 100);
+
+statement ok
+CREATE TABLE t2(a text, b int) AS VALUES ('Alice', 2), ('Alice', 1);
+
+# Reset the configs to old values
+statement ok
+set datafusion.execution.target_partitions = 4;
+
+statement ok
+set datafusion.optimizer.repartition_joins = true;
+
+# equijoin_and_other_condition (sort merge join)
+statement ok
+set datafusion.optimizer.prefer_hash_join = false;
+
+query TT
+EXPLAIN SELECT t1.a, t1.b, t2.a, t2.b FROM t1 JOIN t2 ON t1.a = t2.a AND t2.b + 1 > t1.b
+----
+logical_plan
+Inner Join: t1.a = t2.a Filter: CAST(t2.b AS Int64) + Int64(1) > CAST(t1.b AS Int64)
+--TableScan: t1 projection=[a, b]
+--TableScan: t2 projection=[a, b]
+physical_plan
+SortMergeJoin: join_type=Inner, on=[(a@0, a@0)], filter=CAST(b@1 AS Int64) + 1 > CAST(b@0 AS Int64)
+--SortExec: expr=[a@0 ASC]
+----CoalesceBatchesExec: target_batch_size=8192
+------RepartitionExec: partitioning=Hash([a@0], 4), input_partitions=1
+--------MemoryExec: partitions=1, partition_sizes=[1]
+--SortExec: expr=[a@0 ASC]
+----CoalesceBatchesExec: target_batch_size=8192
+------RepartitionExec: partitioning=Hash([a@0], 4), input_partitions=1
+--------MemoryExec: partitions=1, partition_sizes=[1]
+
+query TITI
+SELECT t1.a, t1.b, t2.a, t2.b FROM t1 JOIN t2 ON t1.a = t2.a AND t2.b > t1.b
+----
+
+statement ok
+set datafusion.optimizer.prefer_hash_join = true;
+
+statement ok
+DROP TABLE t1;
+
+statement ok
+DROP TABLE t2;