tests: more tests

Author: tshauck

datafusion/sqllogictest/test_files/count_empty_rule.slt

@@ -18,6 +18,12 @@
 statement ok
 CREATE TABLE t1 (a INTEGER, b INTEGER, c INTEGER);
 
+statement ok
+INSERT INTO t1 VALUES
+(1, 2, 3),
+(1, 5, 6),
+(2, 3, 5);
+
 statement ok
 CREATE TABLE t2 (a INTEGER, b INTEGER, c INTEGER);
 
@@ -32,45 +38,65 @@ physical_plan
 01)ProjectionExec: expr=[1 as count()]
 02)--PlaceholderRowExec
 
-
 query TT
-EXPLAIN SELECT t1.a, t1.b, t1.c
-FROM t1
-WHERE t1.a IN (
-    SELECT COUNT()
-    FROM t2
-);
+EXPLAIN SELECT t1.a, COUNT() FROM t1 GROUP BY t1.a;
 ----
 logical_plan
-01)LeftSemi Join: CAST(t1.a AS Int64) = __correlated_sq_1.count()
-02)--TableScan: t1 projection=[a, b, c]
-03)--SubqueryAlias: __correlated_sq_1
-04)----Aggregate: groupBy=[[]], aggr=[[count(Int64(1)) AS count()]]
-05)------TableScan: t2 projection=[]
+01)Aggregate: groupBy=[[t1.a]], aggr=[[count(Int64(1)) AS count()]]
+02)--TableScan: t1 projection=[a]
 physical_plan
-01)CoalesceBatchesExec: target_batch_size=8192
-02)--HashJoinExec: mode=Partitioned, join_type=LeftSemi, on=[(CAST(t1.a AS Int64)@3, count()@0)], projection=[a@0, b@1, c@2]
-03)----CoalesceBatchesExec: target_batch_size=8192
-04)------RepartitionExec: partitioning=Hash([CAST(t1.a AS Int64)@3], 4), input_partitions=1
-05)--------ProjectionExec: expr=[a@0 as a, b@1 as b, c@2 as c, CAST(a@0 AS Int64) as CAST(t1.a AS Int64)]
-06)----------MemoryExec: partitions=1, partition_sizes=[0]
-07)----CoalesceBatchesExec: target_batch_size=8192
-08)------RepartitionExec: partitioning=Hash([count()@0], 4), input_partitions=1
-09)--------ProjectionExec: expr=[0 as count()]
-10)----------PlaceholderRowExec
+01)AggregateExec: mode=FinalPartitioned, gby=[a@0 as a], aggr=[count()]
+02)--CoalesceBatchesExec: target_batch_size=8192
+03)----RepartitionExec: partitioning=Hash([a@0], 4), input_partitions=4
+04)------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1
+05)--------AggregateExec: mode=Partial, gby=[a@0 as a], aggr=[count()]
+06)----------MemoryExec: partitions=1, partition_sizes=[1]
 
 query TT
-EXPLAIN SELECT t1.a, COUNT() FROM t1 GROUP BY t1.a;
+EXPLAIN SELECT t1.a, COUNT() AS cnt FROM t1 GROUP BY t1.a HAVING COUNT() > 0;
 ----
 logical_plan
-01)Aggregate: groupBy=[[t1.a]], aggr=[[count(Int64(1)) AS count()]]
-02)--TableScan: t1 projection=[a]
+01)Projection: t1.a, count() AS cnt
+02)--Filter: count() > Int64(0)
+03)----Aggregate: groupBy=[[t1.a]], aggr=[[count(Int64(1)) AS count()]]
+04)------TableScan: t1 projection=[a]
 physical_plan
-01)AggregateExec: mode=FinalPartitioned, gby=[a@0 as a], aggr=[count()]
+01)ProjectionExec: expr=[a@0 as a, count()@1 as cnt]
 02)--CoalesceBatchesExec: target_batch_size=8192
-03)----RepartitionExec: partitioning=Hash([a@0], 4), input_partitions=1
-04)------AggregateExec: mode=Partial, gby=[a@0 as a], aggr=[count()]
-05)--------MemoryExec: partitions=1, partition_sizes=[0]
+03)----FilterExec: count()@1 > 0
+04)------AggregateExec: mode=FinalPartitioned, gby=[a@0 as a], aggr=[count()]
+05)--------CoalesceBatchesExec: target_batch_size=8192
+06)----------RepartitionExec: partitioning=Hash([a@0], 4), input_partitions=4
+07)------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1
+08)--------------AggregateExec: mode=Partial, gby=[a@0 as a], aggr=[count()]
+09)----------------MemoryExec: partitions=1, partition_sizes=[1]
+
+query II
+SELECT t1.a, COUNT() AS cnt FROM t1 GROUP BY t1.a HAVING COUNT() > 1;
+----
+1 2
+
+query TT
+EXPLAIN SELECT a, COUNT() OVER (PARTITION BY a) AS count_a FROM t1;
+----
+logical_plan
+01)Projection: t1.a, count() PARTITION BY [t1.a] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING AS count_a
+02)--WindowAggr: windowExpr=[[count(Int64(1)) PARTITION BY [t1.a] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING AS count() PARTITION BY [t1.a] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING]]
+03)----TableScan: t1 projection=[a]
+physical_plan
+01)ProjectionExec: expr=[a@0 as a, count() PARTITION BY [t1.a] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING@1 as count_a]
+02)--WindowAggExec: wdw=[count() PARTITION BY [t1.a] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING: Ok(Field { name: "count() PARTITION BY [t1.a] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: {} }), frame: WindowFrame { units: Rows, start_bound: Preceding(UInt64(NULL)), end_bound: Following(UInt64(NULL)), is_causal: false }]
+03)----SortExec: expr=[a@0 ASC NULLS LAST], preserve_partitioning=[true]
+04)------CoalesceBatchesExec: target_batch_size=8192
+05)--------RepartitionExec: partitioning=Hash([a@0], 4), input_partitions=1
+06)----------MemoryExec: partitions=1, partition_sizes=[1]
+
+query II
+SELECT a, COUNT() OVER (PARTITION BY a) AS count_a FROM t1 ORDER BY a;
+----
+1 2
+1 2
+2 1
 
 statement ok
 DROP TABLE t1;