Apache DataFusion SQL Query Engine
remove repartition exec from coalesce batches optimizer (#19239)
jizezhang89af694117d3
diff --git a/datafusion/core/tests/dataframe/mod.rs b/datafusion/core/tests/dataframe/mod.rsindex e543ae0701..6eb9d9743d 100644--- a/datafusion/core/tests/dataframe/mod.rs+++ b/datafusion/core/tests/dataframe/mod.rs@@ -2906,10 +2906,9 @@ async fn test_count_wildcard_on_sort() -> Result<()> {| | SortExec: expr=[count(*)@1 ASC NULLS LAST], preserve_partitioning=[true] || | ProjectionExec: expr=[b@0 as b, count(Int64(1))@1 as count(*), count(Int64(1))@1 as count(Int64(1))] || | AggregateExec: mode=FinalPartitioned, gby=[b@0 as b], aggr=[count(Int64(1))] |- | | CoalesceBatchesExec: target_batch_size=8192 |- | | RepartitionExec: partitioning=Hash([b@0], 4), input_partitions=1 |- | | AggregateExec: mode=Partial, gby=[b@0 as b], aggr=[count(Int64(1))] |- | | DataSourceExec: partitions=1, partition_sizes=[1] |+ | | RepartitionExec: partitioning=Hash([b@0], 4), input_partitions=1 |+ | | AggregateExec: mode=Partial, gby=[b@0 as b], aggr=[count(Int64(1))] |+ | | DataSourceExec: partitions=1, partition_sizes=[1] || | |+---------------+------------------------------------------------------------------------------------------------------------+"@@ -2927,10 +2926,9 @@ async fn test_count_wildcard_on_sort() -> Result<()> {| physical_plan | SortPreservingMergeExec: [count(*)@1 ASC NULLS LAST] || | SortExec: expr=[count(*)@1 ASC NULLS LAST], preserve_partitioning=[true] || | AggregateExec: mode=FinalPartitioned, gby=[b@0 as b], aggr=[count(*)] |- | | CoalesceBatchesExec: target_batch_size=8192 |- | | RepartitionExec: partitioning=Hash([b@0], 4), input_partitions=1 |- | | AggregateExec: mode=Partial, gby=[b@0 as b], aggr=[count(*)] |- | | DataSourceExec: partitions=1, partition_sizes=[1] |+ | | RepartitionExec: partitioning=Hash([b@0], 4), input_partitions=1 |+ | | AggregateExec: mode=Partial, gby=[b@0 as b], aggr=[count(*)] |+ | | DataSourceExec: partitions=1, partition_sizes=[1] || | |+---------------+----------------------------------------------------------------------------+"@@ -3342,10 +3340,9 @@ async fn test_count_wildcard_on_where_scalar_subquery() -> Result<()> {| | CoalescePartitionsExec || | ProjectionExec: expr=[count(Int64(1))@1 as count(*), a@0 as a, true as __always_true] || | AggregateExec: mode=FinalPartitioned, gby=[a@0 as a], aggr=[count(Int64(1))] |- | | CoalesceBatchesExec: target_batch_size=8192 |- | | RepartitionExec: partitioning=Hash([a@0], 4), input_partitions=1 |- | | AggregateExec: mode=Partial, gby=[a@0 as a], aggr=[count(Int64(1))] |- | | DataSourceExec: partitions=1, partition_sizes=[1] |+ | | RepartitionExec: partitioning=Hash([a@0], 4), input_partitions=1 |+ | | AggregateExec: mode=Partial, gby=[a@0 as a], aggr=[count(Int64(1))] |+ | | DataSourceExec: partitions=1, partition_sizes=[1] || | DataSourceExec: partitions=1, partition_sizes=[1] || | |+---------------+----------------------------------------------------------------------------------------------------------------------------+@@ -3399,10 +3396,9 @@ async fn test_count_wildcard_on_where_scalar_subquery() -> Result<()> {| | CoalescePartitionsExec || | ProjectionExec: expr=[count(*)@1 as count(*), a@0 as a, true as __always_true] || | AggregateExec: mode=FinalPartitioned, gby=[a@0 as a], aggr=[count(*)] |- | | CoalesceBatchesExec: target_batch_size=8192 |- | | RepartitionExec: partitioning=Hash([a@0], 4), input_partitions=1 |- | | AggregateExec: mode=Partial, gby=[a@0 as a], aggr=[count(*)] |- | | DataSourceExec: partitions=1, partition_sizes=[1] |+ | | RepartitionExec: partitioning=Hash([a@0], 4), input_partitions=1 |+ | | AggregateExec: mode=Partial, gby=[a@0 as a], aggr=[count(*)] |+ | | DataSourceExec: partitions=1, partition_sizes=[1] || | DataSourceExec: partitions=1, partition_sizes=[1] || | |+---------------+----------------------------------------------------------------------------------------------------------------------------+diff --git a/datafusion/core/tests/sql/explain_analyze.rs b/datafusion/core/tests/sql/explain_analyze.rsindex eb93dc40c0..b0a8aa08f2 100644--- a/datafusion/core/tests/sql/explain_analyze.rs+++ b/datafusion/core/tests/sql/explain_analyze.rs@@ -103,14 +103,6 @@ async fn explain_analyze_baseline_metrics() {"output_bytes=",expected_batch_count_after_repartition);-- assert_metrics!(- &formatted,- "CoalesceBatchesExec: target_batch_size=4096",- "metrics=[output_rows=5, elapsed_compute",- "output_bytes=",- expected_batch_count_after_repartition- );}assert_metrics!(@@ -771,12 +763,11 @@ async fn test_physical_plan_display_indent() {SortExec: TopK(fetch=10), expr=[the_min@2 DESC], preserve_partitioning=[true]ProjectionExec: expr=[c1@0 as c1, max(aggregate_test_100.c12)@1 as max(aggregate_test_100.c12), min(aggregate_test_100.c12)@2 as the_min]AggregateExec: mode=FinalPartitioned, gby=[c1@0 as c1], aggr=[max(aggregate_test_100.c12), min(aggregate_test_100.c12)]- CoalesceBatchesExec: target_batch_size=4096- RepartitionExec: partitioning=Hash([c1@0], 9000), input_partitions=9000- AggregateExec: mode=Partial, gby=[c1@0 as c1], aggr=[max(aggregate_test_100.c12), min(aggregate_test_100.c12)]- FilterExec: c12@1 < 10- RepartitionExec: partitioning=RoundRobinBatch(9000), input_partitions=1- DataSourceExec: file_groups={1 group: [[ARROW_TEST_DATA/csv/aggregate_test_100.csv]]}, projection=[c1, c12], file_type=csv, has_header=true+ RepartitionExec: partitioning=Hash([c1@0], 9000), input_partitions=9000+ AggregateExec: mode=Partial, gby=[c1@0 as c1], aggr=[max(aggregate_test_100.c12), min(aggregate_test_100.c12)]+ FilterExec: c12@1 < 10+ RepartitionExec: partitioning=RoundRobinBatch(9000), input_partitions=1+ DataSourceExec: file_groups={1 group: [[ARROW_TEST_DATA/csv/aggregate_test_100.csv]]}, projection=[c1, c12], file_type=csv, has_header=true");}@@ -813,12 +804,10 @@ async fn test_physical_plan_display_indent_multi_children() {actual,@r"HashJoinExec: mode=Partitioned, join_type=Inner, on=[(c1@0, c2@0)], projection=[c1@0]- CoalesceBatchesExec: target_batch_size=4096- RepartitionExec: partitioning=Hash([c1@0], 9000), input_partitions=1- DataSourceExec: file_groups={1 group: [[ARROW_TEST_DATA/csv/aggregate_test_100.csv]]}, projection=[c1], file_type=csv, has_header=true- CoalesceBatchesExec: target_batch_size=4096- RepartitionExec: partitioning=Hash([c2@0], 9000), input_partitions=1- DataSourceExec: file_groups={1 group: [[ARROW_TEST_DATA/csv/aggregate_test_100.csv]]}, projection=[c1@0 as c2], file_type=csv, has_header=true+ RepartitionExec: partitioning=Hash([c1@0], 9000), input_partitions=1+ DataSourceExec: file_groups={1 group: [[ARROW_TEST_DATA/csv/aggregate_test_100.csv]]}, projection=[c1], file_type=csv, has_header=true+ RepartitionExec: partitioning=Hash([c2@0], 9000), input_partitions=1+ DataSourceExec: file_groups={1 group: [[ARROW_TEST_DATA/csv/aggregate_test_100.csv]]}, projection=[c1@0 as c2], file_type=csv, has_header=true");}diff --git a/datafusion/core/tests/sql/joins.rs b/datafusion/core/tests/sql/joins.rsindex 9b8d1ae75a..5ce3865d65 100644--- a/datafusion/core/tests/sql/joins.rs+++ b/datafusion/core/tests/sql/joins.rs@@ -72,12 +72,10 @@ async fn join_change_in_planner() -> Result<()> {actual,@r"SymmetricHashJoinExec: mode=Partitioned, join_type=Full, on=[(a2@1, a2@1)], filter=CAST(a1@0 AS Int64) > CAST(a1@1 AS Int64) + 3 AND CAST(a1@0 AS Int64) < CAST(a1@1 AS Int64) + 10- CoalesceBatchesExec: target_batch_size=8192- RepartitionExec: partitioning=Hash([a2@1], 8), input_partitions=1, maintains_sort_order=true- StreamingTableExec: partition_sizes=1, projection=[a1, a2], infinite_source=true, output_ordering=[a1@0 ASC NULLS LAST]- CoalesceBatchesExec: target_batch_size=8192- RepartitionExec: partitioning=Hash([a2@1], 8), input_partitions=1, maintains_sort_order=true- StreamingTableExec: partition_sizes=1, projection=[a1, a2], infinite_source=true, output_ordering=[a1@0 ASC NULLS LAST]+ RepartitionExec: partitioning=Hash([a2@1], 8), input_partitions=1, maintains_sort_order=true+ StreamingTableExec: partition_sizes=1, projection=[a1, a2], infinite_source=true, output_ordering=[a1@0 ASC NULLS LAST]+ RepartitionExec: partitioning=Hash([a2@1], 8), input_partitions=1, maintains_sort_order=true+ StreamingTableExec: partition_sizes=1, projection=[a1, a2], infinite_source=true, output_ordering=[a1@0 ASC NULLS LAST]");Ok(())@@ -131,12 +129,10 @@ async fn join_no_order_on_filter() -> Result<()> {actual,@r"SymmetricHashJoinExec: mode=Partitioned, join_type=Full, on=[(a2@1, a2@1)], filter=CAST(a3@0 AS Int64) > CAST(a3@1 AS Int64) + 3 AND CAST(a3@0 AS Int64) < CAST(a3@1 AS Int64) + 10- CoalesceBatchesExec: target_batch_size=8192- RepartitionExec: partitioning=Hash([a2@1], 8), input_partitions=1, maintains_sort_order=true- StreamingTableExec: partition_sizes=1, projection=[a1, a2, a3], infinite_source=true, output_ordering=[a1@0 ASC NULLS LAST]- CoalesceBatchesExec: target_batch_size=8192- RepartitionExec: partitioning=Hash([a2@1], 8), input_partitions=1, maintains_sort_order=true- StreamingTableExec: partition_sizes=1, projection=[a1, a2, a3], infinite_source=true, output_ordering=[a1@0 ASC NULLS LAST]+ RepartitionExec: partitioning=Hash([a2@1], 8), input_partitions=1, maintains_sort_order=true+ StreamingTableExec: partition_sizes=1, projection=[a1, a2, a3], infinite_source=true, output_ordering=[a1@0 ASC NULLS LAST]+ RepartitionExec: partitioning=Hash([a2@1], 8), input_partitions=1, maintains_sort_order=true+ StreamingTableExec: partition_sizes=1, projection=[a1, a2, a3], infinite_source=true, output_ordering=[a1@0 ASC NULLS LAST]");Ok(())@@ -172,12 +168,10 @@ async fn join_change_in_planner_without_sort() -> Result<()> {actual,@r"SymmetricHashJoinExec: mode=Partitioned, join_type=Full, on=[(a2@1, a2@1)], filter=CAST(a1@0 AS Int64) > CAST(a1@1 AS Int64) + 3 AND CAST(a1@0 AS Int64) < CAST(a1@1 AS Int64) + 10- CoalesceBatchesExec: target_batch_size=8192- RepartitionExec: partitioning=Hash([a2@1], 8), input_partitions=1- StreamingTableExec: partition_sizes=1, projection=[a1, a2], infinite_source=true- CoalesceBatchesExec: target_batch_size=8192- RepartitionExec: partitioning=Hash([a2@1], 8), input_partitions=1- StreamingTableExec: partition_sizes=1, projection=[a1, a2], infinite_source=true+ RepartitionExec: partitioning=Hash([a2@1], 8), input_partitions=1+ StreamingTableExec: partition_sizes=1, projection=[a1, a2], infinite_source=true+ RepartitionExec: partitioning=Hash([a2@1], 8), input_partitions=1+ StreamingTableExec: partition_sizes=1, projection=[a1, a2], infinite_source=true");Ok(())diff --git a/datafusion/physical-optimizer/src/coalesce_batches.rs b/datafusion/physical-optimizer/src/coalesce_batches.rsindex 24efcc437a..bedb7f6be0 100644--- a/datafusion/physical-optimizer/src/coalesce_batches.rs+++ b/datafusion/physical-optimizer/src/coalesce_batches.rs@@ -25,10 +25,8 @@ use std::sync::Arc;use datafusion_common::assert_eq_or_internal_err;use datafusion_common::config::ConfigOptions;use datafusion_common::error::Result;-use datafusion_physical_expr::Partitioning;use datafusion_physical_plan::{ExecutionPlan, async_func::AsyncFuncExec, coalesce_batches::CoalesceBatchesExec,- repartition::RepartitionExec,};use datafusion_common::tree_node::{Transformed, TransformedResult, TreeNode};@@ -57,23 +55,7 @@ impl PhysicalOptimizerRule for CoalesceBatches {let target_batch_size = config.execution.batch_size;plan.transform_up(|plan| {let plan_any = plan.as_any();- let wrap_in_coalesce = plan_any- // Don't need to add CoalesceBatchesExec after a round robin RepartitionExec- .downcast_ref::<RepartitionExec>()- .map(|repart_exec| {- !matches!(- repart_exec.partitioning().clone(),- Partitioning::RoundRobinBatch(_)- )- })- .unwrap_or(false);-- if wrap_in_coalesce {- Ok(Transformed::yes(Arc::new(CoalesceBatchesExec::new(- plan,- target_batch_size,- ))))- } else if let Some(async_exec) = plan_any.downcast_ref::<AsyncFuncExec>() {+ if let Some(async_exec) = plan_any.downcast_ref::<AsyncFuncExec>() {// Coalesce inputs to async functions to reduce number of async function invocationslet children = async_exec.children();assert_eq_or_internal_err!(diff --git a/datafusion/sqllogictest/test_files/agg_func_substitute.slt b/datafusion/sqllogictest/test_files/agg_func_substitute.sltindex 088c61047e..2b33452184 100644--- a/datafusion/sqllogictest/test_files/agg_func_substitute.slt+++ b/datafusion/sqllogictest/test_files/agg_func_substitute.slt@@ -46,11 +46,10 @@ physical_plan01)ProjectionExec: expr=[a@0 as a, nth_value(multiple_ordered_table.c,Int64(1)) ORDER BY [multiple_ordered_table.c ASC NULLS LAST]@1 as result]02)--AggregateExec: mode=FinalPartitioned, gby=[a@0 as a], aggr=[nth_value(multiple_ordered_table.c,Int64(1)) ORDER BY [multiple_ordered_table.c ASC NULLS LAST]], ordering_mode=Sorted03)----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=4-06)----------AggregateExec: mode=Partial, gby=[a@0 as a], aggr=[nth_value(multiple_ordered_table.c,Int64(1)) ORDER BY [multiple_ordered_table.c ASC NULLS LAST]], ordering_mode=Sorted-07)------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1, maintains_sort_order=true-08)--------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a, c], output_orderings=[[a@0 ASC NULLS LAST], [c@1 ASC NULLS LAST]], file_type=csv, has_header=true+04)------RepartitionExec: partitioning=Hash([a@0], 4), input_partitions=4+05)--------AggregateExec: mode=Partial, gby=[a@0 as a], aggr=[nth_value(multiple_ordered_table.c,Int64(1)) ORDER BY [multiple_ordered_table.c ASC NULLS LAST]], ordering_mode=Sorted+06)----------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1, maintains_sort_order=true+07)------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a, c], output_orderings=[[a@0 ASC NULLS LAST], [c@1 ASC NULLS LAST]], file_type=csv, has_header=truequery TT@@ -66,11 +65,10 @@ physical_plan01)ProjectionExec: expr=[a@0 as a, nth_value(multiple_ordered_table.c,Int64(1)) ORDER BY [multiple_ordered_table.c ASC NULLS LAST]@1 as result]02)--AggregateExec: mode=FinalPartitioned, gby=[a@0 as a], aggr=[nth_value(multiple_ordered_table.c,Int64(1)) ORDER BY [multiple_ordered_table.c ASC NULLS LAST]], ordering_mode=Sorted03)----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=4-06)----------AggregateExec: mode=Partial, gby=[a@0 as a], aggr=[nth_value(multiple_ordered_table.c,Int64(1)) ORDER BY [multiple_ordered_table.c ASC NULLS LAST]], ordering_mode=Sorted-07)------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1, maintains_sort_order=true-08)--------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a, c], output_orderings=[[a@0 ASC NULLS LAST], [c@1 ASC NULLS LAST]], file_type=csv, has_header=true+04)------RepartitionExec: partitioning=Hash([a@0], 4), input_partitions=4+05)--------AggregateExec: mode=Partial, gby=[a@0 as a], aggr=[nth_value(multiple_ordered_table.c,Int64(1)) ORDER BY [multiple_ordered_table.c ASC NULLS LAST]], ordering_mode=Sorted+06)----------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1, maintains_sort_order=true+07)------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a, c], output_orderings=[[a@0 ASC NULLS LAST], [c@1 ASC NULLS LAST]], file_type=csv, has_header=truequery TTEXPLAIN SELECT a, ARRAY_AGG(c ORDER BY c)[1 + 100] as result@@ -85,11 +83,10 @@ physical_plan01)ProjectionExec: expr=[a@0 as a, nth_value(multiple_ordered_table.c,Int64(1) + Int64(100)) ORDER BY [multiple_ordered_table.c ASC NULLS LAST]@1 as result]02)--AggregateExec: mode=FinalPartitioned, gby=[a@0 as a], aggr=[nth_value(multiple_ordered_table.c,Int64(1) + Int64(100)) ORDER BY [multiple_ordered_table.c ASC NULLS LAST]], ordering_mode=Sorted03)----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=4-06)----------AggregateExec: mode=Partial, gby=[a@0 as a], aggr=[nth_value(multiple_ordered_table.c,Int64(1) + Int64(100)) ORDER BY [multiple_ordered_table.c ASC NULLS LAST]], ordering_mode=Sorted-07)------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1, maintains_sort_order=true-08)--------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a, c], output_orderings=[[a@0 ASC NULLS LAST], [c@1 ASC NULLS LAST]], file_type=csv, has_header=true+04)------RepartitionExec: partitioning=Hash([a@0], 4), input_partitions=4+05)--------AggregateExec: mode=Partial, gby=[a@0 as a], aggr=[nth_value(multiple_ordered_table.c,Int64(1) + Int64(100)) ORDER BY [multiple_ordered_table.c ASC NULLS LAST]], ordering_mode=Sorted+06)----------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1, maintains_sort_order=true+07)------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a, c], output_orderings=[[a@0 ASC NULLS LAST], [c@1 ASC NULLS LAST]], file_type=csv, has_header=truequery IISELECT a, ARRAY_AGG(c ORDER BY c)[1] as resultdiff --git a/datafusion/sqllogictest/test_files/aggregate.slt b/datafusion/sqllogictest/test_files/aggregate.sltindex f5bc705044..4172d400fa 100644--- a/datafusion/sqllogictest/test_files/aggregate.slt+++ b/datafusion/sqllogictest/test_files/aggregate.slt@@ -434,20 +434,19 @@ logical_planphysical_plan01)ProjectionExec: expr=[array_length(array_agg(DISTINCT a.foo)@1) as array_length(array_agg(DISTINCT a.foo)), sum(DISTINCT Int64(1))@2 as sum(DISTINCT Int64(1))]02)--AggregateExec: mode=FinalPartitioned, gby=[id@0 as id], aggr=[array_agg(DISTINCT a.foo), sum(DISTINCT Int64(1))], ordering_mode=Sorted-03)----CoalesceBatchesExec: target_batch_size=8192-04)------RepartitionExec: partitioning=Hash([id@0], 4), input_partitions=5-05)--------AggregateExec: mode=Partial, gby=[id@0 as id], aggr=[array_agg(DISTINCT a.foo), sum(DISTINCT Int64(1))], ordering_mode=Sorted-06)----------UnionExec-07)------------ProjectionExec: expr=[1 as id, 2 as foo]-08)--------------PlaceholderRowExec-09)------------ProjectionExec: expr=[1 as id, NULL as foo]-10)--------------PlaceholderRowExec-11)------------ProjectionExec: expr=[1 as id, NULL as foo]-12)--------------PlaceholderRowExec-13)------------ProjectionExec: expr=[1 as id, 3 as foo]-14)--------------PlaceholderRowExec-15)------------ProjectionExec: expr=[1 as id, 2 as foo]-16)--------------PlaceholderRowExec+03)----RepartitionExec: partitioning=Hash([id@0], 4), input_partitions=5+04)------AggregateExec: mode=Partial, gby=[id@0 as id], aggr=[array_agg(DISTINCT a.foo), sum(DISTINCT Int64(1))], ordering_mode=Sorted+05)--------UnionExec+06)----------ProjectionExec: expr=[1 as id, 2 as foo]+07)------------PlaceholderRowExec+08)----------ProjectionExec: expr=[1 as id, NULL as foo]+09)------------PlaceholderRowExec+10)----------ProjectionExec: expr=[1 as id, NULL as foo]+11)------------PlaceholderRowExec+12)----------ProjectionExec: expr=[1 as id, 3 as foo]+13)------------PlaceholderRowExec+14)----------ProjectionExec: expr=[1 as id, 2 as foo]+15)------------PlaceholderRowExec# FIX: custom absolute values@@ -1359,10 +1358,9 @@ physical_plan03)----CoalescePartitionsExec04)------AggregateExec: mode=Partial, gby=[], aggr=[median(alias1)]05)--------AggregateExec: mode=FinalPartitioned, gby=[alias1@0 as alias1], aggr=[]-06)----------CoalesceBatchesExec: target_batch_size=8192-07)------------RepartitionExec: partitioning=Hash([alias1@0], 4), input_partitions=1-08)--------------AggregateExec: mode=Partial, gby=[c@0 as alias1], aggr=[]-09)----------------DataSourceExec: partitions=1, partition_sizes=[1]+06)----------RepartitionExec: partitioning=Hash([alias1@0], 4), input_partitions=1+07)------------AggregateExec: mode=Partial, gby=[c@0 as alias1], aggr=[]+08)--------------DataSourceExec: partitions=1, partition_sizes=[1]statement okdrop table t;@@ -6196,15 +6194,13 @@ logical_planphysical_plan01)CoalescePartitionsExec: fetch=502)--AggregateExec: mode=FinalPartitioned, gby=[c3@0 as c3, min(aggregate_test_100.c1)@1 as min(aggregate_test_100.c1)], aggr=[], lim=[5]-03)----CoalesceBatchesExec: target_batch_size=8192-04)------RepartitionExec: partitioning=Hash([c3@0, min(aggregate_test_100.c1)@1], 4), input_partitions=4-05)--------AggregateExec: mode=Partial, gby=[c3@0 as c3, min(aggregate_test_100.c1)@1 as min(aggregate_test_100.c1)], aggr=[], lim=[5]-06)----------AggregateExec: mode=FinalPartitioned, gby=[c3@0 as c3], aggr=[min(aggregate_test_100.c1)]-07)------------CoalesceBatchesExec: target_batch_size=8192-08)--------------RepartitionExec: partitioning=Hash([c3@0], 4), input_partitions=4-09)----------------AggregateExec: mode=Partial, gby=[c3@1 as c3], aggr=[min(aggregate_test_100.c1)]-10)------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-11)--------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100_with_dates.csv]]}, projection=[c1, c3], file_type=csv, has_header=true+03)----RepartitionExec: partitioning=Hash([c3@0, min(aggregate_test_100.c1)@1], 4), input_partitions=4+04)------AggregateExec: mode=Partial, gby=[c3@0 as c3, min(aggregate_test_100.c1)@1 as min(aggregate_test_100.c1)], aggr=[], lim=[5]+05)--------AggregateExec: mode=FinalPartitioned, gby=[c3@0 as c3], aggr=[min(aggregate_test_100.c1)]+06)----------RepartitionExec: partitioning=Hash([c3@0], 4), input_partitions=4+07)------------AggregateExec: mode=Partial, gby=[c3@1 as c3], aggr=[min(aggregate_test_100.c1)]+08)--------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+09)----------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100_with_dates.csv]]}, projection=[c1, c3], file_type=csv, has_header=true#@@ -7434,10 +7430,9 @@ logical_planphysical_plan01)FilterExec: max(having_test.v1)@2 = 3, projection=[v1@0, v2@1]02)--AggregateExec: mode=FinalPartitioned, gby=[v1@0 as v1, v2@1 as v2], aggr=[max(having_test.v1)]-03)----CoalesceBatchesExec: target_batch_size=8192-04)------RepartitionExec: partitioning=Hash([v1@0, v2@1], 4), input_partitions=1-05)--------AggregateExec: mode=Partial, gby=[v1@0 as v1, v2@1 as v2], aggr=[max(having_test.v1)]-06)----------DataSourceExec: partitions=1, partition_sizes=[1]+03)----RepartitionExec: partitioning=Hash([v1@0, v2@1], 4), input_partitions=1+04)------AggregateExec: mode=Partial, gby=[v1@0 as v1, v2@1 as v2], aggr=[max(having_test.v1)]+05)--------DataSourceExec: partitions=1, partition_sizes=[1]query error@@ -7582,20 +7577,19 @@ logical_planphysical_plan01)ProjectionExec: expr=[last_value(a.foo) ORDER BY [a.foo ASC NULLS LAST]@1 as last_value(a.foo) ORDER BY [a.foo ASC NULLS LAST], sum(DISTINCT Int64(1))@2 as sum(DISTINCT Int64(1))]02)--AggregateExec: mode=FinalPartitioned, gby=[id@0 as id], aggr=[last_value(a.foo) ORDER BY [a.foo ASC NULLS LAST], sum(DISTINCT Int64(1))], ordering_mode=Sorted-03)----CoalesceBatchesExec: target_batch_size=8192-04)------RepartitionExec: partitioning=Hash([id@0], 4), input_partitions=5-05)--------AggregateExec: mode=Partial, gby=[id@0 as id], aggr=[last_value(a.foo) ORDER BY [a.foo ASC NULLS LAST], sum(DISTINCT Int64(1))], ordering_mode=Sorted-06)----------UnionExec-07)------------ProjectionExec: expr=[1 as id, 2 as foo]-08)--------------PlaceholderRowExec-09)------------ProjectionExec: expr=[1 as id, 4 as foo]-10)--------------PlaceholderRowExec-11)------------ProjectionExec: expr=[1 as id, 5 as foo]-12)--------------PlaceholderRowExec-13)------------ProjectionExec: expr=[1 as id, 3 as foo]-14)--------------PlaceholderRowExec-15)------------ProjectionExec: expr=[1 as id, 2 as foo]-16)--------------PlaceholderRowExec+03)----RepartitionExec: partitioning=Hash([id@0], 4), input_partitions=5+04)------AggregateExec: mode=Partial, gby=[id@0 as id], aggr=[last_value(a.foo) ORDER BY [a.foo ASC NULLS LAST], sum(DISTINCT Int64(1))], ordering_mode=Sorted+05)--------UnionExec+06)----------ProjectionExec: expr=[1 as id, 2 as foo]+07)------------PlaceholderRowExec+08)----------ProjectionExec: expr=[1 as id, 4 as foo]+09)------------PlaceholderRowExec+10)----------ProjectionExec: expr=[1 as id, 5 as foo]+11)------------PlaceholderRowExec+12)----------ProjectionExec: expr=[1 as id, 3 as foo]+13)------------PlaceholderRowExec+14)----------ProjectionExec: expr=[1 as id, 2 as foo]+15)------------PlaceholderRowExec# SortExec is removed if it is coming after one-row producing AggregateExec's having an empty group by expressionquery TTdiff --git a/datafusion/sqllogictest/test_files/aggregate_repartition.slt b/datafusion/sqllogictest/test_files/aggregate_repartition.sltindex 5db26f00a7..eeece78623 100644--- a/datafusion/sqllogictest/test_files/aggregate_repartition.slt+++ b/datafusion/sqllogictest/test_files/aggregate_repartition.slt@@ -77,11 +77,10 @@ logical_planphysical_plan01)ProjectionExec: expr=[env@0 as env, count(Int64(1))@1 as count(*)]02)--AggregateExec: mode=FinalPartitioned, gby=[env@0 as env], aggr=[count(Int64(1))]-03)----CoalesceBatchesExec: target_batch_size=8192-04)------RepartitionExec: partitioning=Hash([env@0], 4), input_partitions=4-05)--------AggregateExec: mode=Partial, gby=[env@0 as env], aggr=[count(Int64(1))]-06)----------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-07)------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/aggregate_repartition/dim.csv]]}, projection=[env], file_type=csv, has_header=true+03)----RepartitionExec: partitioning=Hash([env@0], 4), input_partitions=4+04)------AggregateExec: mode=Partial, gby=[env@0 as env], aggr=[count(Int64(1))]+05)--------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+06)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/aggregate_repartition/dim.csv]]}, projection=[env], file_type=csv, has_header=true# Test 2: EXPLAIN query for Parquet table with GROUP BY@@ -95,10 +94,9 @@ logical_planphysical_plan01)ProjectionExec: expr=[env@0 as env, count(Int64(1))@1 as count(*)]02)--AggregateExec: mode=FinalPartitioned, gby=[env@0 as env], aggr=[count(Int64(1))]-03)----CoalesceBatchesExec: target_batch_size=8192-04)------RepartitionExec: partitioning=Hash([env@0], 4), input_partitions=1-05)--------AggregateExec: mode=Partial, gby=[env@0 as env], aggr=[count(Int64(1))]-06)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/aggregate_repartition/dim.parquet]]}, projection=[env], file_type=parquet+03)----RepartitionExec: partitioning=Hash([env@0], 4), input_partitions=1+04)------AggregateExec: mode=Partial, gby=[env@0 as env], aggr=[count(Int64(1))]+05)--------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/aggregate_repartition/dim.parquet]]}, projection=[env], file_type=parquet# Verify the queries actually work and return the same resultsquery TI rowsortdiff --git a/datafusion/sqllogictest/test_files/aggregates_topk.slt b/datafusion/sqllogictest/test_files/aggregates_topk.sltindex 76f8eb954c..58abecfacf 100644--- a/datafusion/sqllogictest/test_files/aggregates_topk.slt+++ b/datafusion/sqllogictest/test_files/aggregates_topk.slt@@ -46,10 +46,9 @@ physical_plan01)SortPreservingMergeExec: [max(traces.timestamp)@1 DESC], fetch=402)--SortExec: TopK(fetch=4), expr=[max(traces.timestamp)@1 DESC], preserve_partitioning=[true]03)----AggregateExec: mode=FinalPartitioned, gby=[trace_id@0 as trace_id], aggr=[max(traces.timestamp)]-04)------CoalesceBatchesExec: target_batch_size=8192-05)--------RepartitionExec: partitioning=Hash([trace_id@0], 4), input_partitions=1-06)----------AggregateExec: mode=Partial, gby=[trace_id@0 as trace_id], aggr=[max(traces.timestamp)]-07)------------DataSourceExec: partitions=1, partition_sizes=[1]+04)------RepartitionExec: partitioning=Hash([trace_id@0], 4), input_partitions=1+05)--------AggregateExec: mode=Partial, gby=[trace_id@0 as trace_id], aggr=[max(traces.timestamp)]+06)----------DataSourceExec: partitions=1, partition_sizes=[1]query TIselect * from (select trace_id, MAX(timestamp) max_ts from traces t group by trace_id) where trace_id != 'b' order by max_ts desc limit 3;@@ -109,10 +108,9 @@ physical_plan01)SortPreservingMergeExec: [max(traces.timestamp)@1 DESC], fetch=402)--SortExec: TopK(fetch=4), expr=[max(traces.timestamp)@1 DESC], preserve_partitioning=[true]03)----AggregateExec: mode=FinalPartitioned, gby=[trace_id@0 as trace_id], aggr=[max(traces.timestamp)], lim=[4]-04)------CoalesceBatchesExec: target_batch_size=8192-05)--------RepartitionExec: partitioning=Hash([trace_id@0], 4), input_partitions=1-06)----------AggregateExec: mode=Partial, gby=[trace_id@0 as trace_id], aggr=[max(traces.timestamp)], lim=[4]-07)------------DataSourceExec: partitions=1, partition_sizes=[1]+04)------RepartitionExec: partitioning=Hash([trace_id@0], 4), input_partitions=1+05)--------AggregateExec: mode=Partial, gby=[trace_id@0 as trace_id], aggr=[max(traces.timestamp)], lim=[4]+06)----------DataSourceExec: partitions=1, partition_sizes=[1]query TTexplain select trace_id, MIN(timestamp) from traces group by trace_id order by MIN(timestamp) desc limit 4;@@ -125,10 +123,9 @@ physical_plan01)SortPreservingMergeExec: [min(traces.timestamp)@1 DESC], fetch=402)--SortExec: TopK(fetch=4), expr=[min(traces.timestamp)@1 DESC], preserve_partitioning=[true]03)----AggregateExec: mode=FinalPartitioned, gby=[trace_id@0 as trace_id], aggr=[min(traces.timestamp)]-04)------CoalesceBatchesExec: target_batch_size=8192-05)--------RepartitionExec: partitioning=Hash([trace_id@0], 4), input_partitions=1-06)----------AggregateExec: mode=Partial, gby=[trace_id@0 as trace_id], aggr=[min(traces.timestamp)]-07)------------DataSourceExec: partitions=1, partition_sizes=[1]+04)------RepartitionExec: partitioning=Hash([trace_id@0], 4), input_partitions=1+05)--------AggregateExec: mode=Partial, gby=[trace_id@0 as trace_id], aggr=[min(traces.timestamp)]+06)----------DataSourceExec: partitions=1, partition_sizes=[1]query TTexplain select trace_id, MAX(timestamp) from traces group by trace_id order by MAX(timestamp) asc limit 4;@@ -141,10 +138,9 @@ physical_plan01)SortPreservingMergeExec: [max(traces.timestamp)@1 ASC NULLS LAST], fetch=402)--SortExec: TopK(fetch=4), expr=[max(traces.timestamp)@1 ASC NULLS LAST], preserve_partitioning=[true]03)----AggregateExec: mode=FinalPartitioned, gby=[trace_id@0 as trace_id], aggr=[max(traces.timestamp)]-04)------CoalesceBatchesExec: target_batch_size=8192-05)--------RepartitionExec: partitioning=Hash([trace_id@0], 4), input_partitions=1-06)----------AggregateExec: mode=Partial, gby=[trace_id@0 as trace_id], aggr=[max(traces.timestamp)]-07)------------DataSourceExec: partitions=1, partition_sizes=[1]+04)------RepartitionExec: partitioning=Hash([trace_id@0], 4), input_partitions=1+05)--------AggregateExec: mode=Partial, gby=[trace_id@0 as trace_id], aggr=[max(traces.timestamp)]+06)----------DataSourceExec: partitions=1, partition_sizes=[1]query TTexplain select trace_id, MAX(timestamp) from traces group by trace_id order by trace_id asc limit 4;@@ -157,10 +153,9 @@ physical_plan01)SortPreservingMergeExec: [trace_id@0 ASC NULLS LAST], fetch=402)--SortExec: TopK(fetch=4), expr=[trace_id@0 ASC NULLS LAST], preserve_partitioning=[true]03)----AggregateExec: mode=FinalPartitioned, gby=[trace_id@0 as trace_id], aggr=[max(traces.timestamp)]-04)------CoalesceBatchesExec: target_batch_size=8192-05)--------RepartitionExec: partitioning=Hash([trace_id@0], 4), input_partitions=1-06)----------AggregateExec: mode=Partial, gby=[trace_id@0 as trace_id], aggr=[max(traces.timestamp)]-07)------------DataSourceExec: partitions=1, partition_sizes=[1]+04)------RepartitionExec: partitioning=Hash([trace_id@0], 4), input_partitions=1+05)--------AggregateExec: mode=Partial, gby=[trace_id@0 as trace_id], aggr=[max(traces.timestamp)]+06)----------DataSourceExec: partitions=1, partition_sizes=[1]query TIselect trace_id, max(timestamp) from traces group by trace_id order by MAX(timestamp) desc limit 4;@@ -230,10 +225,9 @@ physical_plan01)SortPreservingMergeExec: [max(traces_utf8view.timestamp)@1 DESC], fetch=402)--SortExec: TopK(fetch=4), expr=[max(traces_utf8view.timestamp)@1 DESC], preserve_partitioning=[true]03)----AggregateExec: mode=FinalPartitioned, gby=[trace_id@0 as trace_id], aggr=[max(traces_utf8view.timestamp)], lim=[4]-04)------CoalesceBatchesExec: target_batch_size=8192-05)--------RepartitionExec: partitioning=Hash([trace_id@0], 4), input_partitions=1-06)----------AggregateExec: mode=Partial, gby=[trace_id@0 as trace_id], aggr=[max(traces_utf8view.timestamp)], lim=[4]-07)------------DataSourceExec: partitions=1, partition_sizes=[1]+04)------RepartitionExec: partitioning=Hash([trace_id@0], 4), input_partitions=1+05)--------AggregateExec: mode=Partial, gby=[trace_id@0 as trace_id], aggr=[max(traces_utf8view.timestamp)], lim=[4]+06)----------DataSourceExec: partitions=1, partition_sizes=[1]# Also add LargeUtf8 to test PR https://github.com/apache/datafusion/pull/15152@@ -257,10 +251,9 @@ physical_plan01)SortPreservingMergeExec: [max(traces_largeutf8.timestamp)@1 DESC], fetch=402)--SortExec: TopK(fetch=4), expr=[max(traces_largeutf8.timestamp)@1 DESC], preserve_partitioning=[true]03)----AggregateExec: mode=FinalPartitioned, gby=[trace_id@0 as trace_id], aggr=[max(traces_largeutf8.timestamp)], lim=[4]-04)------CoalesceBatchesExec: target_batch_size=8192-05)--------RepartitionExec: partitioning=Hash([trace_id@0], 4), input_partitions=1-06)----------AggregateExec: mode=Partial, gby=[trace_id@0 as trace_id], aggr=[max(traces_largeutf8.timestamp)], lim=[4]-07)------------DataSourceExec: partitions=1, partition_sizes=[1]+04)------RepartitionExec: partitioning=Hash([trace_id@0], 4), input_partitions=1+05)--------AggregateExec: mode=Partial, gby=[trace_id@0 as trace_id], aggr=[max(traces_largeutf8.timestamp)], lim=[4]+06)----------DataSourceExec: partitions=1, partition_sizes=[1]statement okdiff --git a/datafusion/sqllogictest/test_files/async_udf.slt b/datafusion/sqllogictest/test_files/async_udf.sltindex 9bca72a2fd..31ca87c435 100644--- a/datafusion/sqllogictest/test_files/async_udf.slt+++ b/datafusion/sqllogictest/test_files/async_udf.slt@@ -58,14 +58,13 @@ logical_planphysical_plan01)ProjectionExec: expr=[min(async_abs(data.x))@1 as min(async_abs(data.x))]02)--AggregateExec: mode=FinalPartitioned, gby=[async_abs(data.x)@0 as async_abs(data.x)], aggr=[min(async_abs(data.x))]-03)----CoalesceBatchesExec: target_batch_size=8192-04)------RepartitionExec: partitioning=Hash([async_abs(data.x)@0], 4), input_partitions=4-05)--------AggregateExec: mode=Partial, gby=[__common_expr_1@0 as async_abs(data.x)], aggr=[min(async_abs(data.x))]-06)----------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-07)------------ProjectionExec: expr=[__async_fn_0@1 as __common_expr_1]-08)--------------AsyncFuncExec: async_expr=[async_expr(name=__async_fn_0, expr=async_abs(x@0))]-09)----------------CoalesceBatchesExec: target_batch_size=8192-10)------------------DataSourceExec: partitions=1, partition_sizes=[1]+03)----RepartitionExec: partitioning=Hash([async_abs(data.x)@0], 4), input_partitions=4+04)------AggregateExec: mode=Partial, gby=[__common_expr_1@0 as async_abs(data.x)], aggr=[min(async_abs(data.x))]+05)--------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+06)----------ProjectionExec: expr=[__async_fn_0@1 as __common_expr_1]+07)------------AsyncFuncExec: async_expr=[async_expr(name=__async_fn_0, expr=async_abs(x@0))]+08)--------------CoalesceBatchesExec: target_batch_size=8192+09)----------------DataSourceExec: partitions=1, partition_sizes=[1]# Async udf can be used in filterquery Idiff --git a/datafusion/sqllogictest/test_files/count_star_rule.slt b/datafusion/sqllogictest/test_files/count_star_rule.sltindex 38676baddd..a1c0e6303a 100644--- a/datafusion/sqllogictest/test_files/count_star_rule.slt+++ b/datafusion/sqllogictest/test_files/count_star_rule.slt@@ -49,10 +49,9 @@ logical_planphysical_plan01)ProjectionExec: expr=[a@0 as a, count(Int64(1))@1 as count()]02)--AggregateExec: mode=FinalPartitioned, gby=[a@0 as a], aggr=[count(Int64(1))]-03)----CoalesceBatchesExec: target_batch_size=8192-04)------RepartitionExec: partitioning=Hash([a@0], 4), input_partitions=1-05)--------AggregateExec: mode=Partial, gby=[a@0 as a], aggr=[count(Int64(1))]-06)----------DataSourceExec: partitions=1, partition_sizes=[1]+03)----RepartitionExec: partitioning=Hash([a@0], 4), input_partitions=1+04)------AggregateExec: mode=Partial, gby=[a@0 as a], aggr=[count(Int64(1))]+05)--------DataSourceExec: partitions=1, partition_sizes=[1]query TTEXPLAIN SELECT t1.a, COUNT() AS cnt FROM t1 GROUP BY t1.a HAVING COUNT() > 0;@@ -66,10 +65,9 @@ physical_plan01)ProjectionExec: expr=[a@0 as a, count(Int64(1))@1 as cnt]02)--FilterExec: count(Int64(1))@1 > 003)----AggregateExec: mode=FinalPartitioned, gby=[a@0 as a], aggr=[count(Int64(1))]-04)------CoalesceBatchesExec: target_batch_size=8192-05)--------RepartitionExec: partitioning=Hash([a@0], 4), input_partitions=1-06)----------AggregateExec: mode=Partial, gby=[a@0 as a], aggr=[count(Int64(1))]-07)------------DataSourceExec: partitions=1, partition_sizes=[1]+04)------RepartitionExec: partitioning=Hash([a@0], 4), input_partitions=1+05)--------AggregateExec: mode=Partial, gby=[a@0 as a], aggr=[count(Int64(1))]+06)----------DataSourceExec: partitions=1, partition_sizes=[1]query IISELECT t1.a, COUNT() AS cnt FROM t1 GROUP BY t1.a HAVING COUNT() > 1;diff --git a/datafusion/sqllogictest/test_files/cte.slt b/datafusion/sqllogictest/test_files/cte.sltindex d6ef2dc4aa..853dbd2e24 100644--- a/datafusion/sqllogictest/test_files/cte.slt+++ b/datafusion/sqllogictest/test_files/cte.slt@@ -1099,12 +1099,10 @@ physical_plan02)--DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/recursive_cte/closure.csv]]}, projection=[start, end], file_type=csv, has_header=true03)--CoalescePartitionsExec04)----HashJoinExec: mode=Partitioned, join_type=Inner, on=[(end@1, start@0)], projection=[start@0, end@3]-05)------CoalesceBatchesExec: target_batch_size=8182-06)--------RepartitionExec: partitioning=Hash([end@1], 4), input_partitions=1-07)----------WorkTableExec: name=trans-08)------CoalesceBatchesExec: target_batch_size=8182-09)--------RepartitionExec: partitioning=Hash([start@0], 4), input_partitions=1-10)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/recursive_cte/closure.csv]]}, projection=[start, end], file_type=csv, has_header=true+05)------RepartitionExec: partitioning=Hash([end@1], 4), input_partitions=1+06)--------WorkTableExec: name=trans+07)------RepartitionExec: partitioning=Hash([start@0], 4), input_partitions=1+08)--------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/recursive_cte/closure.csv]]}, projection=[start, end], file_type=csv, has_header=truestatement count 0set datafusion.execution.enable_recursive_ctes = false;diff --git a/datafusion/sqllogictest/test_files/distinct_on.slt b/datafusion/sqllogictest/test_files/distinct_on.sltindex b4a491619e..23a269b525 100644--- a/datafusion/sqllogictest/test_files/distinct_on.slt+++ b/datafusion/sqllogictest/test_files/distinct_on.slt@@ -98,11 +98,10 @@ physical_plan02)--SortPreservingMergeExec: [c1@0 ASC NULLS LAST]03)----SortExec: expr=[c1@0 ASC NULLS LAST], preserve_partitioning=[true]04)------AggregateExec: mode=FinalPartitioned, gby=[c1@0 as c1], aggr=[first_value(aggregate_test_100.c3) ORDER BY [aggregate_test_100.c1 ASC NULLS LAST, aggregate_test_100.c3 ASC NULLS LAST], first_value(aggregate_test_100.c2) ORDER BY [aggregate_test_100.c1 ASC NULLS LAST, aggregate_test_100.c3 ASC NULLS LAST]]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([c1@0], 4), input_partitions=4-07)------------AggregateExec: mode=Partial, gby=[c1@0 as c1], aggr=[first_value(aggregate_test_100.c3) ORDER BY [aggregate_test_100.c1 ASC NULLS LAST, aggregate_test_100.c3 ASC NULLS LAST], first_value(aggregate_test_100.c2) ORDER BY [aggregate_test_100.c1 ASC NULLS LAST, aggregate_test_100.c3 ASC NULLS LAST]]-08)--------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-09)----------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c2, c3], file_type=csv, has_header=true+05)--------RepartitionExec: partitioning=Hash([c1@0], 4), input_partitions=4+06)----------AggregateExec: mode=Partial, gby=[c1@0 as c1], aggr=[first_value(aggregate_test_100.c3) ORDER BY [aggregate_test_100.c1 ASC NULLS LAST, aggregate_test_100.c3 ASC NULLS LAST], first_value(aggregate_test_100.c2) ORDER BY [aggregate_test_100.c1 ASC NULLS LAST, aggregate_test_100.c3 ASC NULLS LAST]]+07)------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+08)--------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c2, c3], file_type=csv, has_header=true# ON expressions are not a sub-set of the ORDER BY expressionsquery error SELECT DISTINCT ON expressions must match initial ORDER BY expressionsdiff --git a/datafusion/sqllogictest/test_files/explain_tree.slt b/datafusion/sqllogictest/test_files/explain_tree.sltindex bf1b337514..9215ce87e3 100644--- a/datafusion/sqllogictest/test_files/explain_tree.slt+++ b/datafusion/sqllogictest/test_files/explain_tree.slt@@ -204,44 +204,38 @@ physical_plan10)│ FinalPartitioned │11)└─────────────┬─────────────┘12)┌─────────────┴─────────────┐-13)│ CoalesceBatchesExec │+13)│ RepartitionExec │14)│ -------------------- │-15)│ target_batch_size: │-16)│ 8192 │-17)└─────────────┬─────────────┘-18)┌─────────────┴─────────────┐-19)│ RepartitionExec │-20)│ -------------------- │-21)│ partition_count(in->out): │-22)│ 4 -> 4 │-23)│ │-24)│ partitioning_scheme: │-25)│ Hash([string_col@0], 4) │-26)└─────────────┬─────────────┘-27)┌─────────────┴─────────────┐-28)│ AggregateExec │-29)│ -------------------- │-30)│ aggr: │-31)│ sum(table1.bigint_col) │-32)│ │-33)│ group_by: string_col │-34)│ mode: Partial │-35)└─────────────┬─────────────┘-36)┌─────────────┴─────────────┐-37)│ RepartitionExec │-38)│ -------------------- │-39)│ partition_count(in->out): │-40)│ 1 -> 4 │-41)│ │-42)│ partitioning_scheme: │-43)│ RoundRobinBatch(4) │-44)└─────────────┬─────────────┘-45)┌─────────────┴─────────────┐-46)│ DataSourceExec │-47)│ -------------------- │-48)│ files: 1 │-49)│ format: csv │-50)└───────────────────────────┘+15)│ partition_count(in->out): │+16)│ 4 -> 4 │+17)│ │+18)│ partitioning_scheme: │+19)│ Hash([string_col@0], 4) │+20)└─────────────┬─────────────┘+21)┌─────────────┴─────────────┐+22)│ AggregateExec │+23)│ -------------------- │+24)│ aggr: │+25)│ sum(table1.bigint_col) │+26)│ │+27)│ group_by: string_col │+28)│ mode: Partial │+29)└─────────────┬─────────────┘+30)┌─────────────┴─────────────┐+31)│ RepartitionExec │+32)│ -------------------- │+33)│ partition_count(in->out): │+34)│ 1 -> 4 │+35)│ │+36)│ partitioning_scheme: │+37)│ RoundRobinBatch(4) │+38)└─────────────┬─────────────┘+39)┌─────────────┴─────────────┐+40)│ DataSourceExec │+41)│ -------------------- │+42)│ files: 1 │+43)│ format: csv │+44)└───────────────────────────┘# Limit@@ -1294,33 +1288,27 @@ physical_plan25)│ FinalPartitioned ││ FinalPartitioned │26)└─────────────┬─────────────┘└─────────────┬─────────────┘27)┌─────────────┴─────────────┐┌─────────────┴─────────────┐-28)│ CoalesceBatchesExec ││ CoalesceBatchesExec │+28)│ RepartitionExec ││ RepartitionExec │29)│ -------------------- ││ -------------------- │-30)│ target_batch_size: ││ target_batch_size: │-31)│ 8192 ││ 8192 │-32)└─────────────┬─────────────┘└─────────────┬─────────────┘-33)┌─────────────┴─────────────┐┌─────────────┴─────────────┐-34)│ RepartitionExec ││ RepartitionExec │-35)│ -------------------- ││ -------------------- │-36)│ partition_count(in->out): ││ partition_count(in->out): │-37)│ 1 -> 4 ││ 1 -> 4 │-38)│ ││ │-39)│ partitioning_scheme: ││ partitioning_scheme: │-40)│ Hash([name@0], 4) ││ Hash([name@0], 4) │+30)│ partition_count(in->out): ││ partition_count(in->out): │+31)│ 1 -> 4 ││ 1 -> 4 │+32)│ ││ │+33)│ partitioning_scheme: ││ partitioning_scheme: │+34)│ Hash([name@0], 4) ││ Hash([name@0], 4) │+35)└─────────────┬─────────────┘└─────────────┬─────────────┘+36)┌─────────────┴─────────────┐┌─────────────┴─────────────┐+37)│ AggregateExec ││ AggregateExec │+38)│ -------------------- ││ -------------------- │+39)│ group_by: name ││ group_by: name │+40)│ mode: Partial ││ mode: Partial │41)└─────────────┬─────────────┘└─────────────┬─────────────┘42)┌─────────────┴─────────────┐┌─────────────┴─────────────┐-43)│ AggregateExec ││ AggregateExec │+43)│ DataSourceExec ││ DataSourceExec │44)│ -------------------- ││ -------------------- │-45)│ group_by: name ││ group_by: name │-46)│ mode: Partial ││ mode: Partial │-47)└─────────────┬─────────────┘└─────────────┬─────────────┘-48)┌─────────────┴─────────────┐┌─────────────┴─────────────┐-49)│ DataSourceExec ││ DataSourceExec │-50)│ -------------------- ││ -------------------- │-51)│ bytes: 296 ││ bytes: 288 │-52)│ format: memory ││ format: memory │-53)│ rows: 1 ││ rows: 1 │-54)└───────────────────────────┘└───────────────────────────┘+45)│ bytes: 296 ││ bytes: 288 │+46)│ format: memory ││ format: memory │+47)│ rows: 1 ││ rows: 1 │+48)└───────────────────────────┘└───────────────────────────┘# Test explain tree for UnionExecquery TTdiff --git a/datafusion/sqllogictest/test_files/group_by.slt b/datafusion/sqllogictest/test_files/group_by.sltindex 308e9ef498..cd1ed2bc0c 100644--- a/datafusion/sqllogictest/test_files/group_by.slt+++ b/datafusion/sqllogictest/test_files/group_by.slt@@ -2017,14 +2017,13 @@ physical_plan02)--SortExec: expr=[col0@0 ASC NULLS LAST], preserve_partitioning=[true]03)----ProjectionExec: expr=[col0@0 as col0, last_value(r.col1) ORDER BY [r.col0 ASC NULLS LAST]@3 as last_col1]04)------AggregateExec: mode=FinalPartitioned, gby=[col0@0 as col0, col1@1 as col1, col2@2 as col2], aggr=[last_value(r.col1) ORDER BY [r.col0 ASC NULLS LAST]]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([col0@0, col1@1, col2@2], 4), input_partitions=4-07)------------AggregateExec: mode=Partial, gby=[col0@0 as col0, col1@1 as col1, col2@2 as col2], aggr=[last_value(r.col1) ORDER BY [r.col0 ASC NULLS LAST]]-08)--------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-09)----------------ProjectionExec: expr=[col0@2 as col0, col1@3 as col1, col2@4 as col2, col0@0 as col0, col1@1 as col1]-10)------------------HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(col0@0, col0@0)]-11)--------------------DataSourceExec: partitions=1, partition_sizes=[3]-12)--------------------DataSourceExec: partitions=1, partition_sizes=[3]+05)--------RepartitionExec: partitioning=Hash([col0@0, col1@1, col2@2], 4), input_partitions=4+06)----------AggregateExec: mode=Partial, gby=[col0@0 as col0, col1@1 as col1, col2@2 as col2], aggr=[last_value(r.col1) ORDER BY [r.col0 ASC NULLS LAST]]+07)------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+08)--------------ProjectionExec: expr=[col0@2 as col0, col1@3 as col1, col2@4 as col2, col0@0 as col0, col1@1 as col1]+09)----------------HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(col0@0, col0@0)]+10)------------------DataSourceExec: partitions=1, partition_sizes=[3]+11)------------------DataSourceExec: partitions=1, partition_sizes=[3]# Columns in the table are a,b,c,d. Source is DataSourceExec which is ordered by# a,b,c column. Column a has cardinality 2, column b has cardinality 4.@@ -2986,10 +2985,9 @@ physical_plan02)--SortExec: expr=[country@0 ASC NULLS LAST], preserve_partitioning=[true]03)----ProjectionExec: expr=[country@0 as country, first_value(sales_global.amount) ORDER BY [sales_global.ts ASC NULLS LAST]@1 as fv1, last_value(sales_global.amount) ORDER BY [sales_global.ts ASC NULLS LAST]@2 as fv2]04)------AggregateExec: mode=FinalPartitioned, gby=[country@0 as country], aggr=[first_value(sales_global.amount) ORDER BY [sales_global.ts ASC NULLS LAST], last_value(sales_global.amount) ORDER BY [sales_global.ts ASC NULLS LAST]]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([country@0], 8), input_partitions=1-07)------------AggregateExec: mode=Partial, gby=[country@0 as country], aggr=[first_value(sales_global.amount) ORDER BY [sales_global.ts ASC NULLS LAST], last_value(sales_global.amount) ORDER BY [sales_global.ts ASC NULLS LAST]]-08)--------------DataSourceExec: partitions=1, partition_sizes=[1]+05)--------RepartitionExec: partitioning=Hash([country@0], 8), input_partitions=1+06)----------AggregateExec: mode=Partial, gby=[country@0 as country], aggr=[first_value(sales_global.amount) ORDER BY [sales_global.ts ASC NULLS LAST], last_value(sales_global.amount) ORDER BY [sales_global.ts ASC NULLS LAST]]+07)------------DataSourceExec: partitions=1, partition_sizes=[1]query TRRSELECT country, FIRST_VALUE(amount ORDER BY ts ASC) AS fv1,@@ -3021,10 +3019,9 @@ physical_plan02)--SortExec: expr=[country@0 ASC NULLS LAST], preserve_partitioning=[true]03)----ProjectionExec: expr=[country@0 as country, first_value(sales_global.amount) ORDER BY [sales_global.ts ASC NULLS LAST]@1 as fv1, last_value(sales_global.amount) ORDER BY [sales_global.ts DESC NULLS FIRST]@2 as fv2]04)------AggregateExec: mode=FinalPartitioned, gby=[country@0 as country], aggr=[first_value(sales_global.amount) ORDER BY [sales_global.ts ASC NULLS LAST], last_value(sales_global.amount) ORDER BY [sales_global.ts DESC NULLS FIRST]]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([country@0], 8), input_partitions=1-07)------------AggregateExec: mode=Partial, gby=[country@0 as country], aggr=[first_value(sales_global.amount) ORDER BY [sales_global.ts ASC NULLS LAST], last_value(sales_global.amount) ORDER BY [sales_global.ts DESC NULLS FIRST]]-08)--------------DataSourceExec: partitions=1, partition_sizes=[1]+05)--------RepartitionExec: partitioning=Hash([country@0], 8), input_partitions=1+06)----------AggregateExec: mode=Partial, gby=[country@0 as country], aggr=[first_value(sales_global.amount) ORDER BY [sales_global.ts ASC NULLS LAST], last_value(sales_global.amount) ORDER BY [sales_global.ts DESC NULLS FIRST]]+07)------------DataSourceExec: partitions=1, partition_sizes=[1]query TRR@@ -3184,12 +3181,11 @@ physical_plan02)--SortExec: expr=[country@0 ASC NULLS LAST], preserve_partitioning=[true]03)----ProjectionExec: expr=[country@0 as country, array_agg(sales_global.amount) ORDER BY [sales_global.amount ASC NULLS LAST]@1 as array_agg1]04)------AggregateExec: mode=FinalPartitioned, gby=[country@0 as country], aggr=[array_agg(sales_global.amount) ORDER BY [sales_global.amount ASC NULLS LAST]]-05)--------CoalesceBatchesExec: target_batch_size=4-06)----------RepartitionExec: partitioning=Hash([country@0], 8), input_partitions=8-07)------------AggregateExec: mode=Partial, gby=[country@0 as country], aggr=[array_agg(sales_global.amount) ORDER BY [sales_global.amount ASC NULLS LAST]]-08)--------------SortExec: expr=[amount@1 ASC NULLS LAST], preserve_partitioning=[true]-09)----------------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=1-10)------------------DataSourceExec: partitions=1, partition_sizes=[1]+05)--------RepartitionExec: partitioning=Hash([country@0], 8), input_partitions=8+06)----------AggregateExec: mode=Partial, gby=[country@0 as country], aggr=[array_agg(sales_global.amount) ORDER BY [sales_global.amount ASC NULLS LAST]]+07)------------SortExec: expr=[amount@1 ASC NULLS LAST], preserve_partitioning=[true]+08)--------------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=1+09)----------------DataSourceExec: partitions=1, partition_sizes=[1]query T?SELECT country, ARRAY_AGG(amount ORDER BY amount ASC) AS array_agg1@@ -3220,12 +3216,11 @@ physical_plan02)--SortExec: expr=[country@0 ASC NULLS LAST], preserve_partitioning=[true]03)----ProjectionExec: expr=[country@0 as country, array_agg(sales_global.amount) ORDER BY [sales_global.amount DESC NULLS FIRST]@1 as amounts, first_value(sales_global.amount) ORDER BY [sales_global.amount ASC NULLS LAST]@2 as fv1, last_value(sales_global.amount) ORDER BY [sales_global.amount DESC NULLS FIRST]@3 as fv2]04)------AggregateExec: mode=FinalPartitioned, gby=[country@0 as country], aggr=[array_agg(sales_global.amount) ORDER BY [sales_global.amount DESC NULLS FIRST], first_value(sales_global.amount) ORDER BY [sales_global.amount ASC NULLS LAST], last_value(sales_global.amount) ORDER BY [sales_global.amount DESC NULLS FIRST]]-05)--------CoalesceBatchesExec: target_batch_size=4-06)----------RepartitionExec: partitioning=Hash([country@0], 8), input_partitions=8-07)------------AggregateExec: mode=Partial, gby=[country@0 as country], aggr=[array_agg(sales_global.amount) ORDER BY [sales_global.amount DESC NULLS FIRST], last_value(sales_global.amount) ORDER BY [sales_global.amount DESC NULLS FIRST], last_value(sales_global.amount) ORDER BY [sales_global.amount DESC NULLS FIRST]]-08)--------------SortExec: expr=[amount@1 DESC], preserve_partitioning=[true]-09)----------------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=1-10)------------------DataSourceExec: partitions=1, partition_sizes=[1]+05)--------RepartitionExec: partitioning=Hash([country@0], 8), input_partitions=8+06)----------AggregateExec: mode=Partial, gby=[country@0 as country], aggr=[array_agg(sales_global.amount) ORDER BY [sales_global.amount DESC NULLS FIRST], last_value(sales_global.amount) ORDER BY [sales_global.amount DESC NULLS FIRST], last_value(sales_global.amount) ORDER BY [sales_global.amount DESC NULLS FIRST]]+07)------------SortExec: expr=[amount@1 DESC], preserve_partitioning=[true]+08)--------------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=1+09)----------------DataSourceExec: partitions=1, partition_sizes=[1]query T?RRSELECT country, ARRAY_AGG(amount ORDER BY amount DESC) AS amounts,@@ -3421,11 +3416,10 @@ physical_plan02)--SortExec: expr=[sn@0 ASC NULLS LAST], preserve_partitioning=[true]03)----ProjectionExec: expr=[sn@0 as sn, amount@1 as amount, 2 * CAST(sn@0 AS Int64) as Int64(2) * s.sn]04)------AggregateExec: mode=FinalPartitioned, gby=[sn@0 as sn, amount@1 as amount], aggr=[]-05)--------CoalesceBatchesExec: target_batch_size=4-06)----------RepartitionExec: partitioning=Hash([sn@0, amount@1], 8), input_partitions=8-07)------------AggregateExec: mode=Partial, gby=[sn@0 as sn, amount@1 as amount], aggr=[]-08)--------------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=1-09)----------------DataSourceExec: partitions=1, partition_sizes=[2]+05)--------RepartitionExec: partitioning=Hash([sn@0, amount@1], 8), input_partitions=8+06)----------AggregateExec: mode=Partial, gby=[sn@0 as sn, amount@1 as amount], aggr=[]+07)------------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=1+08)--------------DataSourceExec: partitions=1, partition_sizes=[2]query IRISELECT s.sn, s.amount, 2*s.sn@@ -3490,13 +3484,12 @@ physical_plan02)--SortExec: expr=[sn@0 ASC NULLS LAST], preserve_partitioning=[true]03)----ProjectionExec: expr=[sn@0 as sn, sum(l.amount)@2 as sum(l.amount), amount@1 as amount]04)------AggregateExec: mode=FinalPartitioned, gby=[sn@0 as sn, amount@1 as amount], aggr=[sum(l.amount)]-05)--------CoalesceBatchesExec: target_batch_size=4-06)----------RepartitionExec: partitioning=Hash([sn@0, amount@1], 8), input_partitions=8-07)------------AggregateExec: mode=Partial, gby=[sn@1 as sn, amount@2 as amount], aggr=[sum(l.amount)]-08)--------------NestedLoopJoinExec: join_type=Inner, filter=sn@0 >= sn@1, projection=[amount@1, sn@2, amount@3]-09)----------------DataSourceExec: partitions=1, partition_sizes=[2]-10)----------------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=1-11)------------------DataSourceExec: partitions=1, partition_sizes=[2]+05)--------RepartitionExec: partitioning=Hash([sn@0, amount@1], 8), input_partitions=8+06)----------AggregateExec: mode=Partial, gby=[sn@1 as sn, amount@2 as amount], aggr=[sum(l.amount)]+07)------------NestedLoopJoinExec: join_type=Inner, filter=sn@0 >= sn@1, projection=[amount@1, sn@2, amount@3]+08)--------------DataSourceExec: partitions=1, partition_sizes=[2]+09)--------------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=1+10)----------------DataSourceExec: partitions=1, partition_sizes=[2]query IRRSELECT r.sn, SUM(l.amount), r.amount@@ -3637,13 +3630,12 @@ physical_plan02)--SortExec: expr=[sn@2 ASC NULLS LAST], preserve_partitioning=[true]03)----ProjectionExec: expr=[zip_code@1 as zip_code, country@2 as country, sn@0 as sn, ts@3 as ts, currency@4 as currency, amount@5 as amount, sum_amount@6 as sum_amount]04)------AggregateExec: mode=FinalPartitioned, gby=[sn@0 as sn, zip_code@1 as zip_code, country@2 as country, ts@3 as ts, currency@4 as currency, amount@5 as amount, sum_amount@6 as sum_amount], aggr=[]-05)--------CoalesceBatchesExec: target_batch_size=4-06)----------RepartitionExec: partitioning=Hash([sn@0, zip_code@1, country@2, ts@3, currency@4, amount@5, sum_amount@6], 8), input_partitions=8-07)------------AggregateExec: mode=Partial, gby=[sn@2 as sn, zip_code@0 as zip_code, country@1 as country, ts@3 as ts, currency@4 as currency, amount@5 as amount, sum_amount@6 as sum_amount], aggr=[]-08)--------------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=1-09)----------------ProjectionExec: expr=[zip_code@0 as zip_code, country@1 as country, sn@2 as sn, ts@3 as ts, currency@4 as currency, amount@5 as amount, sum(l.amount) ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING@6 as sum_amount]-10)------------------BoundedWindowAggExec: wdw=[sum(l.amount) ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING: Field { "sum(l.amount) ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING": nullable Float64 }, frame: ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING], mode=[Sorted]-11)--------------------DataSourceExec: partitions=1, partition_sizes=[2]+05)--------RepartitionExec: partitioning=Hash([sn@0, zip_code@1, country@2, ts@3, currency@4, amount@5, sum_amount@6], 8), input_partitions=8+06)----------AggregateExec: mode=Partial, gby=[sn@2 as sn, zip_code@0 as zip_code, country@1 as country, ts@3 as ts, currency@4 as currency, amount@5 as amount, sum_amount@6 as sum_amount], aggr=[]+07)------------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=1+08)--------------ProjectionExec: expr=[zip_code@0 as zip_code, country@1 as country, sn@2 as sn, ts@3 as ts, currency@4 as currency, amount@5 as amount, sum(l.amount) ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING@6 as sum_amount]+09)----------------BoundedWindowAggExec: wdw=[sum(l.amount) ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING: Field { "sum(l.amount) ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING": nullable Float64 }, frame: ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING], mode=[Sorted]+10)------------------DataSourceExec: partitions=1, partition_sizes=[2]query ITIPTRR@@ -3865,11 +3857,10 @@ logical_planphysical_plan01)ProjectionExec: expr=[first_value(multiple_ordered_table.a) ORDER BY [multiple_ordered_table.a ASC NULLS LAST]@1 as first_a, last_value(multiple_ordered_table.c) ORDER BY [multiple_ordered_table.c DESC NULLS FIRST]@2 as last_c]02)--AggregateExec: mode=FinalPartitioned, gby=[d@0 as d], aggr=[first_value(multiple_ordered_table.a) ORDER BY [multiple_ordered_table.a ASC NULLS LAST], last_value(multiple_ordered_table.c) ORDER BY [multiple_ordered_table.c DESC NULLS FIRST]]-03)----CoalesceBatchesExec: target_batch_size=2-04)------RepartitionExec: partitioning=Hash([d@0], 8), input_partitions=8-05)--------AggregateExec: mode=Partial, gby=[d@2 as d], aggr=[first_value(multiple_ordered_table.a) ORDER BY [multiple_ordered_table.a ASC NULLS LAST], first_value(multiple_ordered_table.c) ORDER BY [multiple_ordered_table.c ASC NULLS LAST]]-06)----------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=1, maintains_sort_order=true-07)------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a, c, d], output_orderings=[[a@0 ASC NULLS LAST], [c@1 ASC NULLS LAST]], file_type=csv, has_header=true+03)----RepartitionExec: partitioning=Hash([d@0], 8), input_partitions=8+04)------AggregateExec: mode=Partial, gby=[d@2 as d], aggr=[first_value(multiple_ordered_table.a) ORDER BY [multiple_ordered_table.a ASC NULLS LAST], first_value(multiple_ordered_table.c) ORDER BY [multiple_ordered_table.c ASC NULLS LAST]]+05)--------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=1, maintains_sort_order=true+06)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a, c, d], output_orderings=[[a@0 ASC NULLS LAST], [c@1 ASC NULLS LAST]], file_type=csv, has_header=truequery II rowsortSELECT FIRST_VALUE(a ORDER BY a ASC) as first_a,@@ -3976,11 +3967,10 @@ logical_planphysical_plan01)AggregateExec: mode=FinalPartitioned, gby=[c@0 as c, b@1 as b], aggr=[sum(multiple_ordered_table_with_pk.d)], ordering_mode=PartiallySorted([0])02)--SortExec: expr=[c@0 ASC NULLS LAST], preserve_partitioning=[true]-03)----CoalesceBatchesExec: target_batch_size=2-04)------RepartitionExec: partitioning=Hash([c@0, b@1], 8), input_partitions=8-05)--------AggregateExec: mode=Partial, gby=[c@1 as c, b@0 as b], aggr=[sum(multiple_ordered_table_with_pk.d)], ordering_mode=PartiallySorted([0])-06)----------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=1, maintains_sort_order=true-07)------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[b, c, d], output_ordering=[c@1 ASC NULLS LAST], constraints=[PrimaryKey([3])], file_type=csv, has_header=true+03)----RepartitionExec: partitioning=Hash([c@0, b@1], 8), input_partitions=8+04)------AggregateExec: mode=Partial, gby=[c@1 as c, b@0 as b], aggr=[sum(multiple_ordered_table_with_pk.d)], ordering_mode=PartiallySorted([0])+05)--------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=1, maintains_sort_order=true+06)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[b, c, d], output_ordering=[c@1 ASC NULLS LAST], constraints=[PrimaryKey([3])], file_type=csv, has_header=true# drop table multiple_ordered_table_with_pkstatement ok@@ -4017,11 +4007,10 @@ logical_planphysical_plan01)AggregateExec: mode=FinalPartitioned, gby=[c@0 as c, b@1 as b], aggr=[sum(multiple_ordered_table_with_pk.d)], ordering_mode=PartiallySorted([0])02)--SortExec: expr=[c@0 ASC NULLS LAST], preserve_partitioning=[true]-03)----CoalesceBatchesExec: target_batch_size=2-04)------RepartitionExec: partitioning=Hash([c@0, b@1], 8), input_partitions=8-05)--------AggregateExec: mode=Partial, gby=[c@1 as c, b@0 as b], aggr=[sum(multiple_ordered_table_with_pk.d)], ordering_mode=PartiallySorted([0])-06)----------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=1, maintains_sort_order=true-07)------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[b, c, d], output_ordering=[c@1 ASC NULLS LAST], constraints=[PrimaryKey([3])], file_type=csv, has_header=true+03)----RepartitionExec: partitioning=Hash([c@0, b@1], 8), input_partitions=8+04)------AggregateExec: mode=Partial, gby=[c@1 as c, b@0 as b], aggr=[sum(multiple_ordered_table_with_pk.d)], ordering_mode=PartiallySorted([0])+05)--------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=1, maintains_sort_order=true+06)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[b, c, d], output_ordering=[c@1 ASC NULLS LAST], constraints=[PrimaryKey([3])], file_type=csv, has_header=truestatement okset datafusion.execution.target_partitions = 1;@@ -4238,10 +4227,9 @@ logical_planphysical_plan01)ProjectionExec: expr=[sum(DISTINCT t1.x)@1 as sum(DISTINCT t1.x), max(DISTINCT t1.x)@2 as max(DISTINCT t1.x)]02)--AggregateExec: mode=FinalPartitioned, gby=[y@0 as y], aggr=[sum(DISTINCT t1.x), max(DISTINCT t1.x)]-03)----CoalesceBatchesExec: target_batch_size=2-04)------RepartitionExec: partitioning=Hash([y@0], 8), input_partitions=1-05)--------AggregateExec: mode=Partial, gby=[y@1 as y], aggr=[sum(DISTINCT t1.x), max(DISTINCT t1.x)]-06)----------DataSourceExec: partitions=1, partition_sizes=[1]+03)----RepartitionExec: partitioning=Hash([y@0], 8), input_partitions=1+04)------AggregateExec: mode=Partial, gby=[y@1 as y], aggr=[sum(DISTINCT t1.x), max(DISTINCT t1.x)]+05)--------DataSourceExec: partitions=1, partition_sizes=[1]query TTEXPLAIN SELECT SUM(DISTINCT CAST(x AS DOUBLE)), MAX(DISTINCT CAST(x AS DOUBLE)) FROM t1 GROUP BY y;@@ -4254,14 +4242,12 @@ logical_planphysical_plan01)ProjectionExec: expr=[sum(alias1)@1 as sum(DISTINCT t1.x), max(alias1)@2 as max(DISTINCT t1.x)]02)--AggregateExec: mode=FinalPartitioned, gby=[y@0 as y], aggr=[sum(alias1), max(alias1)]-03)----CoalesceBatchesExec: target_batch_size=2-04)------RepartitionExec: partitioning=Hash([y@0], 8), input_partitions=8-05)--------AggregateExec: mode=Partial, gby=[y@0 as y], aggr=[sum(alias1), max(alias1)]-06)----------AggregateExec: mode=FinalPartitioned, gby=[y@0 as y, alias1@1 as alias1], aggr=[]-07)------------CoalesceBatchesExec: target_batch_size=2-08)--------------RepartitionExec: partitioning=Hash([y@0, alias1@1], 8), input_partitions=1-09)----------------AggregateExec: mode=Partial, gby=[y@1 as y, CAST(x@0 AS Float64) as alias1], aggr=[]-10)------------------DataSourceExec: partitions=1, partition_sizes=[1]+03)----RepartitionExec: partitioning=Hash([y@0], 8), input_partitions=8+04)------AggregateExec: mode=Partial, gby=[y@0 as y], aggr=[sum(alias1), max(alias1)]+05)--------AggregateExec: mode=FinalPartitioned, gby=[y@0 as y, alias1@1 as alias1], aggr=[]+06)----------RepartitionExec: partitioning=Hash([y@0, alias1@1], 8), input_partitions=1+07)------------AggregateExec: mode=Partial, gby=[y@1 as y, CAST(x@0 AS Float64) as alias1], aggr=[]+08)--------------DataSourceExec: partitions=1, partition_sizes=[1]# create an unbounded table that contains ordered timestamp.statement ok@@ -4290,11 +4276,10 @@ physical_plan01)SortPreservingMergeExec: [time_chunks@0 DESC], fetch=502)--ProjectionExec: expr=[date_bin(Utf8("15 minutes"),unbounded_csv_with_timestamps.ts)@0 as time_chunks]03)----AggregateExec: mode=FinalPartitioned, gby=[date_bin(Utf8("15 minutes"),unbounded_csv_with_timestamps.ts)@0 as date_bin(Utf8("15 minutes"),unbounded_csv_with_timestamps.ts)], aggr=[], ordering_mode=Sorted-04)------CoalesceBatchesExec: target_batch_size=2-05)--------RepartitionExec: partitioning=Hash([date_bin(Utf8("15 minutes"),unbounded_csv_with_timestamps.ts)@0], 8), input_partitions=8, preserve_order=true, sort_exprs=date_bin(Utf8("15 minutes"),unbounded_csv_with_timestamps.ts)@0 DESC-06)----------AggregateExec: mode=Partial, gby=[date_bin(IntervalMonthDayNano { months: 0, days: 0, nanoseconds: 900000000000 }, ts@0) as date_bin(Utf8("15 minutes"),unbounded_csv_with_timestamps.ts)], aggr=[], ordering_mode=Sorted-07)------------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=1, maintains_sort_order=true-08)--------------StreamingTableExec: partition_sizes=1, projection=[ts], infinite_source=true, output_ordering=[ts@0 DESC]+04)------RepartitionExec: partitioning=Hash([date_bin(Utf8("15 minutes"),unbounded_csv_with_timestamps.ts)@0], 8), input_partitions=8, preserve_order=true, sort_exprs=date_bin(Utf8("15 minutes"),unbounded_csv_with_timestamps.ts)@0 DESC+05)--------AggregateExec: mode=Partial, gby=[date_bin(IntervalMonthDayNano { months: 0, days: 0, nanoseconds: 900000000000 }, ts@0) as date_bin(Utf8("15 minutes"),unbounded_csv_with_timestamps.ts)], aggr=[], ordering_mode=Sorted+06)----------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=1, maintains_sort_order=true+07)------------StreamingTableExec: partition_sizes=1, projection=[ts], infinite_source=true, output_ordering=[ts@0 DESC]query PSELECT date_bin('15 minutes', ts) as time_chunks@@ -4345,11 +4330,10 @@ physical_plan02)--SortExec: TopK(fetch=5), expr=[months@0 DESC], preserve_partitioning=[true]03)----ProjectionExec: expr=[date_part(Utf8("MONTH"),csv_with_timestamps.ts)@0 as months]04)------AggregateExec: mode=FinalPartitioned, gby=[date_part(Utf8("MONTH"),csv_with_timestamps.ts)@0 as date_part(Utf8("MONTH"),csv_with_timestamps.ts)], aggr=[]-05)--------CoalesceBatchesExec: target_batch_size=2-06)----------RepartitionExec: partitioning=Hash([date_part(Utf8("MONTH"),csv_with_timestamps.ts)@0], 8), input_partitions=8-07)------------AggregateExec: mode=Partial, gby=[date_part(MONTH, ts@0) as date_part(Utf8("MONTH"),csv_with_timestamps.ts)], aggr=[]-08)--------------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=1, maintains_sort_order=true-09)----------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/timestamps.csv]]}, projection=[ts], output_ordering=[ts@0 DESC], file_type=csv, has_header=false+05)--------RepartitionExec: partitioning=Hash([date_part(Utf8("MONTH"),csv_with_timestamps.ts)@0], 8), input_partitions=8+06)----------AggregateExec: mode=Partial, gby=[date_part(MONTH, ts@0) as date_part(Utf8("MONTH"),csv_with_timestamps.ts)], aggr=[]+07)------------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=1, maintains_sort_order=true+08)--------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/timestamps.csv]]}, projection=[ts], output_ordering=[ts@0 DESC], file_type=csv, has_header=falsequery ISELECT extract(month from ts) as months@@ -4457,15 +4441,13 @@ physical_plan02)--SortExec: expr=[c1@0 ASC NULLS LAST], preserve_partitioning=[true]03)----ProjectionExec: expr=[c1@0 as c1, count(alias1)@1 as count(DISTINCT aggregate_test_100.c2), min(alias1)@2 as min(DISTINCT aggregate_test_100.c2), sum(alias2)@3 as sum(aggregate_test_100.c3), max(alias3)@4 as max(aggregate_test_100.c4)]04)------AggregateExec: mode=FinalPartitioned, gby=[c1@0 as c1], aggr=[count(alias1), min(alias1), sum(alias2), max(alias3)]-05)--------CoalesceBatchesExec: target_batch_size=2-06)----------RepartitionExec: partitioning=Hash([c1@0], 8), input_partitions=8-07)------------AggregateExec: mode=Partial, gby=[c1@0 as c1], aggr=[count(alias1), min(alias1), sum(alias2), max(alias3)]-08)--------------AggregateExec: mode=FinalPartitioned, gby=[c1@0 as c1, alias1@1 as alias1], aggr=[alias2, alias3]-09)----------------CoalesceBatchesExec: target_batch_size=2-10)------------------RepartitionExec: partitioning=Hash([c1@0, alias1@1], 8), input_partitions=8-11)--------------------AggregateExec: mode=Partial, gby=[c1@0 as c1, c2@1 as alias1], aggr=[alias2, alias3]-12)----------------------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=1-13)------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c2, c3, c4], file_type=csv, has_header=true+05)--------RepartitionExec: partitioning=Hash([c1@0], 8), input_partitions=8+06)----------AggregateExec: mode=Partial, gby=[c1@0 as c1], aggr=[count(alias1), min(alias1), sum(alias2), max(alias3)]+07)------------AggregateExec: mode=FinalPartitioned, gby=[c1@0 as c1, alias1@1 as alias1], aggr=[alias2, alias3]+08)--------------RepartitionExec: partitioning=Hash([c1@0, alias1@1], 8), input_partitions=8+09)----------------AggregateExec: mode=Partial, gby=[c1@0 as c1, c2@1 as alias1], aggr=[alias2, alias3]+10)------------------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=1+11)--------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c2, c3, c4], file_type=csv, has_header=truequery IISELECT c2, count(distinct c3) FILTER (WHERE c1 != 'a') FROM aggregate_test_100 GROUP BY c2 ORDER BY c2;@@ -4627,11 +4609,10 @@ physical_plan01)SortPreservingMergeExec: [max(timestamp_table.t1)@1 DESC], fetch=402)--SortExec: TopK(fetch=4), expr=[max(timestamp_table.t1)@1 DESC], preserve_partitioning=[true]03)----AggregateExec: mode=FinalPartitioned, gby=[c2@0 as c2], aggr=[max(timestamp_table.t1)], lim=[4]-04)------CoalesceBatchesExec: target_batch_size=2-05)--------RepartitionExec: partitioning=Hash([c2@0], 8), input_partitions=8-06)----------AggregateExec: mode=Partial, gby=[c2@1 as c2], aggr=[max(timestamp_table.t1)], lim=[4]-07)------------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=4-08)--------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/group_by/timestamp_table/0.csv], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/group_by/timestamp_table/1.csv], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/group_by/timestamp_table/2.csv], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/group_by/timestamp_table/3.csv]]}, projection=[t1, c2], file_type=csv, has_header=true+04)------RepartitionExec: partitioning=Hash([c2@0], 8), input_partitions=8+05)--------AggregateExec: mode=Partial, gby=[c2@1 as c2], aggr=[max(timestamp_table.t1)], lim=[4]+06)----------RepartitionExec: partitioning=RoundRobinBatch(8), input_partitions=4+07)------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/group_by/timestamp_table/0.csv], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/group_by/timestamp_table/1.csv], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/group_by/timestamp_table/2.csv], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/group_by/timestamp_table/3.csv]]}, projection=[t1, c2], file_type=csv, has_header=true# Clean upstatement okdiff --git a/datafusion/sqllogictest/test_files/insert.slt b/datafusion/sqllogictest/test_files/insert.sltindex 4551b6cb49..8ef2596f18 100644--- a/datafusion/sqllogictest/test_files/insert.slt+++ b/datafusion/sqllogictest/test_files/insert.slt@@ -70,9 +70,8 @@ physical_plan04)------ProjectionExec: expr=[sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING@3 as sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING, count(Int64(1)) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING@4 as count(*) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING, c1@0 as c1]05)--------BoundedWindowAggExec: wdw=[sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING: Field { "sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING": nullable Int64 }, frame: ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING, count(Int64(1)) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING: Field { "count(Int64(1)) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING": Int64 }, frame: ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING], mode=[Sorted]06)----------SortExec: expr=[c1@0 ASC NULLS LAST, c9@2 ASC NULLS LAST], preserve_partitioning=[true]-07)------------CoalesceBatchesExec: target_batch_size=8192-08)--------------RepartitionExec: partitioning=Hash([c1@0], 8), input_partitions=1-09)----------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c4, c9], file_type=csv, has_header=true+07)------------RepartitionExec: partitioning=Hash([c1@0], 8), input_partitions=1+08)--------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c4, c9], file_type=csv, has_header=truequery IINSERT INTO table_without_values SELECT@@ -129,9 +128,8 @@ physical_plan03)----ProjectionExec: expr=[sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING@3 as field1, count(Int64(1)) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING@4 as field2]04)------BoundedWindowAggExec: wdw=[sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING: Field { "sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING": nullable Int64 }, frame: ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING, count(Int64(1)) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING: Field { "count(Int64(1)) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING": Int64 }, frame: ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING], mode=[Sorted]05)--------SortExec: expr=[c1@0 ASC NULLS LAST, c9@2 ASC NULLS LAST], preserve_partitioning=[true]-06)----------CoalesceBatchesExec: target_batch_size=8192-07)------------RepartitionExec: partitioning=Hash([c1@0], 8), input_partitions=1-08)--------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c4, c9], file_type=csv, has_header=true+06)----------RepartitionExec: partitioning=Hash([c1@0], 8), input_partitions=1+07)------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c4, c9], file_type=csv, has_header=true@@ -179,9 +177,8 @@ physical_plan04)------ProjectionExec: expr=[sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING@3 as a1, count(Int64(1)) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING@4 as a2, c1@0 as c1]05)--------BoundedWindowAggExec: wdw=[sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING: Field { "sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING": nullable Int64 }, frame: ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING, count(Int64(1)) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING: Field { "count(Int64(1)) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING": Int64 }, frame: ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING], mode=[Sorted]06)----------SortExec: expr=[c1@0 ASC NULLS LAST, c9@2 ASC NULLS LAST], preserve_partitioning=[true]-07)------------CoalesceBatchesExec: target_batch_size=8192-08)--------------RepartitionExec: partitioning=Hash([c1@0], 8), input_partitions=1-09)----------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c4, c9], file_type=csv, has_header=true+07)------------RepartitionExec: partitioning=Hash([c1@0], 8), input_partitions=1+08)--------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c4, c9], file_type=csv, has_header=truequery Idiff --git a/datafusion/sqllogictest/test_files/insert_to_external.slt b/datafusion/sqllogictest/test_files/insert_to_external.sltindex 2642b2780f..4702b0b9ca 100644--- a/datafusion/sqllogictest/test_files/insert_to_external.slt+++ b/datafusion/sqllogictest/test_files/insert_to_external.slt@@ -424,9 +424,8 @@ physical_plan04)------ProjectionExec: expr=[sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING@3 as sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING, count(Int64(1)) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING@4 as count(*) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING, c1@0 as c1]05)--------BoundedWindowAggExec: wdw=[sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING: Field { "sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING": nullable Int64 }, frame: ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING, count(Int64(1)) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING: Field { "count(Int64(1)) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING": Int64 }, frame: ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING], mode=[Sorted]06)----------SortExec: expr=[c1@0 ASC NULLS LAST, c9@2 ASC NULLS LAST], preserve_partitioning=[true]-07)------------CoalesceBatchesExec: target_batch_size=8192-08)--------------RepartitionExec: partitioning=Hash([c1@0], 8), input_partitions=1-09)----------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c4, c9], file_type=csv, has_header=true+07)------------RepartitionExec: partitioning=Hash([c1@0], 8), input_partitions=1+08)--------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c4, c9], file_type=csv, has_header=truequery IINSERT INTO table_without_values SELECT@@ -484,9 +483,8 @@ physical_plan03)----ProjectionExec: expr=[sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING@3 as field1, count(Int64(1)) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING@4 as field2]04)------BoundedWindowAggExec: wdw=[sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING: Field { "sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING": nullable Int64 }, frame: ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING, count(Int64(1)) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING: Field { "count(Int64(1)) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING": Int64 }, frame: ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING], mode=[Sorted]05)--------SortExec: expr=[c1@0 ASC NULLS LAST, c9@2 ASC NULLS LAST], preserve_partitioning=[true]-06)----------CoalesceBatchesExec: target_batch_size=8192-07)------------RepartitionExec: partitioning=Hash([c1@0], 8), input_partitions=1-08)--------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c4, c9], file_type=csv, has_header=true+06)----------RepartitionExec: partitioning=Hash([c1@0], 8), input_partitions=1+07)------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c4, c9], file_type=csv, has_header=truediff --git a/datafusion/sqllogictest/test_files/join.slt.part b/datafusion/sqllogictest/test_files/join.slt.partindex 29d8f952fb..5d111374ac 100644--- a/datafusion/sqllogictest/test_files/join.slt.part+++ b/datafusion/sqllogictest/test_files/join.slt.part@@ -1426,11 +1426,10 @@ physical_plan03)----CoalescePartitionsExec04)------ProjectionExec: expr=[sum(t1.v1)@1 as sum(t1.v1), v0@0 as v0]05)--------AggregateExec: mode=FinalPartitioned, gby=[v0@0 as v0], aggr=[sum(t1.v1)]-06)----------CoalesceBatchesExec: target_batch_size=8192-07)------------RepartitionExec: partitioning=Hash([v0@0], 4), input_partitions=1-08)--------------AggregateExec: mode=Partial, gby=[v0@0 as v0], aggr=[sum(t1.v1)]-09)----------------DataSourceExec: partitions=1, partition_sizes=[1]-10)----DataSourceExec: partitions=1, partition_sizes=[1]+06)----------RepartitionExec: partitioning=Hash([v0@0], 4), input_partitions=1+07)------------AggregateExec: mode=Partial, gby=[v0@0 as v0], aggr=[sum(t1.v1)]+08)--------------DataSourceExec: partitions=1, partition_sizes=[1]+09)----DataSourceExec: partitions=1, partition_sizes=[1]query IIISELECT *diff --git a/datafusion/sqllogictest/test_files/joins.slt b/datafusion/sqllogictest/test_files/joins.sltindex 02761b5d3d..3259ef9cd8 100644--- a/datafusion/sqllogictest/test_files/joins.slt+++ b/datafusion/sqllogictest/test_files/joins.slt@@ -1339,13 +1339,12 @@ logical_plan05)------TableScan: join_t2 projection=[t2_id]physical_plan01)AggregateExec: mode=FinalPartitioned, gby=[t1_id@0 as t1_id], aggr=[]-02)--CoalesceBatchesExec: target_batch_size=2-03)----RepartitionExec: partitioning=Hash([t1_id@0], 2), input_partitions=2-04)------AggregateExec: mode=Partial, gby=[t1_id@0 as t1_id], aggr=[]-05)--------HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(t1_id@0, t2_id@0)], projection=[t1_id@0]-06)----------DataSourceExec: partitions=1, partition_sizes=[1]-07)----------RepartitionExec: partitioning=RoundRobinBatch(2), input_partitions=1-08)------------DataSourceExec: partitions=1, partition_sizes=[1]+02)--RepartitionExec: partitioning=Hash([t1_id@0], 2), input_partitions=2+03)----AggregateExec: mode=Partial, gby=[t1_id@0 as t1_id], aggr=[]+04)------HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(t1_id@0, t2_id@0)], projection=[t1_id@0]+05)--------DataSourceExec: partitions=1, partition_sizes=[1]+06)--------RepartitionExec: partitioning=RoundRobinBatch(2), input_partitions=1+07)----------DataSourceExec: partitions=1, partition_sizes=[1]# Join on structquery TT@@ -1395,13 +1394,12 @@ logical_planphysical_plan01)ProjectionExec: expr=[count(Int64(1))@1 as count(*)]02)--AggregateExec: mode=FinalPartitioned, gby=[t1_id@0 as t1_id], aggr=[count(Int64(1))]-03)----CoalesceBatchesExec: target_batch_size=2-04)------RepartitionExec: partitioning=Hash([t1_id@0], 2), input_partitions=2-05)--------AggregateExec: mode=Partial, gby=[t1_id@0 as t1_id], aggr=[count(Int64(1))]-06)----------HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(t1_id@0, t2_id@0)], projection=[t1_id@0]-07)------------DataSourceExec: partitions=1, partition_sizes=[1]-08)------------RepartitionExec: partitioning=RoundRobinBatch(2), input_partitions=1-09)--------------DataSourceExec: partitions=1, partition_sizes=[1]+03)----RepartitionExec: partitioning=Hash([t1_id@0], 2), input_partitions=2+04)------AggregateExec: mode=Partial, gby=[t1_id@0 as t1_id], aggr=[count(Int64(1))]+05)--------HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(t1_id@0, t2_id@0)], projection=[t1_id@0]+06)----------DataSourceExec: partitions=1, partition_sizes=[1]+07)----------RepartitionExec: partitioning=RoundRobinBatch(2), input_partitions=1+08)------------DataSourceExec: partitions=1, partition_sizes=[1]query TTEXPLAIN@@ -1423,13 +1421,12 @@ physical_plan03)----CoalescePartitionsExec04)------AggregateExec: mode=Partial, gby=[], aggr=[count(alias1)]05)--------AggregateExec: mode=FinalPartitioned, gby=[alias1@0 as alias1], aggr=[]-06)----------CoalesceBatchesExec: target_batch_size=2-07)------------RepartitionExec: partitioning=Hash([alias1@0], 2), input_partitions=2-08)--------------AggregateExec: mode=Partial, gby=[t1_id@0 as alias1], aggr=[]-09)----------------HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(t1_id@0, t2_id@0)], projection=[t1_id@0]-10)------------------DataSourceExec: partitions=1, partition_sizes=[1]-11)------------------RepartitionExec: partitioning=RoundRobinBatch(2), input_partitions=1-12)--------------------DataSourceExec: partitions=1, partition_sizes=[1]+06)----------RepartitionExec: partitioning=Hash([alias1@0], 2), input_partitions=2+07)------------AggregateExec: mode=Partial, gby=[t1_id@0 as alias1], aggr=[]+08)--------------HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(t1_id@0, t2_id@0)], projection=[t1_id@0]+09)----------------DataSourceExec: partitions=1, partition_sizes=[1]+10)----------------RepartitionExec: partitioning=RoundRobinBatch(2), input_partitions=1+11)------------------DataSourceExec: partitions=1, partition_sizes=[1]statement okset datafusion.explain.logical_plan_only = true;@@ -2726,13 +2723,11 @@ logical_planphysical_plan01)SortMergeJoin: join_type=Inner, on=[(c1@0, c1@0)]02)--SortExec: expr=[c1@0 ASC], preserve_partitioning=[true]-03)----CoalesceBatchesExec: target_batch_size=2-04)------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=1-05)--------DataSourceExec: partitions=1, partition_sizes=[1]-06)--SortExec: expr=[c1@0 ASC], preserve_partitioning=[true]-07)----CoalesceBatchesExec: target_batch_size=2-08)------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=1-09)--------DataSourceExec: partitions=1, partition_sizes=[1]+03)----RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=1+04)------DataSourceExec: partitions=1, partition_sizes=[1]+05)--SortExec: expr=[c1@0 ASC], preserve_partitioning=[true]+06)----RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=1+07)------DataSourceExec: partitions=1, partition_sizes=[1]# sort_merge_join_on_date32 inner sort merge join on data type (Date32)query DDRTDDRT rowsort@@ -2755,15 +2750,13 @@ physical_plan01)ProjectionExec: expr=[c1@0 as c1, c2@1 as c2, c3@2 as c3, c4@3 as c4, c1@5 as c1, c2@6 as c2, c3@7 as c3, c4@8 as c4]02)--SortMergeJoin: join_type=Right, on=[(CAST(t1.c3 AS Decimal128(10, 2))@4, c3@2)]03)----SortExec: expr=[CAST(t1.c3 AS Decimal128(10, 2))@4 ASC], preserve_partitioning=[true]-04)------CoalesceBatchesExec: target_batch_size=2-05)--------RepartitionExec: partitioning=Hash([CAST(t1.c3 AS Decimal128(10, 2))@4], 2), input_partitions=2-06)----------ProjectionExec: expr=[c1@0 as c1, c2@1 as c2, c3@2 as c3, c4@3 as c4, CAST(c3@2 AS Decimal128(10, 2)) as CAST(t1.c3 AS Decimal128(10, 2))]-07)------------RepartitionExec: partitioning=RoundRobinBatch(2), input_partitions=1-08)--------------DataSourceExec: partitions=1, partition_sizes=[1]-09)----SortExec: expr=[c3@2 ASC], preserve_partitioning=[true]-10)------CoalesceBatchesExec: target_batch_size=2-11)--------RepartitionExec: partitioning=Hash([c3@2], 2), input_partitions=1-12)----------DataSourceExec: partitions=1, partition_sizes=[1]+04)------RepartitionExec: partitioning=Hash([CAST(t1.c3 AS Decimal128(10, 2))@4], 2), input_partitions=2+05)--------ProjectionExec: expr=[c1@0 as c1, c2@1 as c2, c3@2 as c3, c4@3 as c4, CAST(c3@2 AS Decimal128(10, 2)) as CAST(t1.c3 AS Decimal128(10, 2))]+06)----------RepartitionExec: partitioning=RoundRobinBatch(2), input_partitions=1+07)------------DataSourceExec: partitions=1, partition_sizes=[1]+08)----SortExec: expr=[c3@2 ASC], preserve_partitioning=[true]+09)------RepartitionExec: partitioning=Hash([c3@2], 2), input_partitions=1+10)--------DataSourceExec: partitions=1, partition_sizes=[1]# sort_merge_join_on_decimal right join on data type (Decimal)query DDRTDDRT rowsort@@ -3165,14 +3158,12 @@ logical_planphysical_plan01)SortPreservingMergeExec: [rn1@5 ASC NULLS LAST]02)--SortMergeJoin: join_type=Inner, on=[(a@1, a@1)]-03)----CoalesceBatchesExec: target_batch_size=2-04)------RepartitionExec: partitioning=Hash([a@1], 2), input_partitions=1, maintains_sort_order=true-05)--------ProjectionExec: expr=[a0@0 as a0, a@1 as a, b@2 as b, c@3 as c, d@4 as d, row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING@5 as rn1]-06)----------BoundedWindowAggExec: wdw=[row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING: Field { "row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING": UInt64 }, frame: ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING], mode=[Sorted]-07)------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a0, a, b, c, d], output_ordering=[a@1 ASC, b@2 ASC NULLS LAST, c@3 ASC NULLS LAST], file_type=csv, has_header=true-08)----CoalesceBatchesExec: target_batch_size=2-09)------RepartitionExec: partitioning=Hash([a@1], 2), input_partitions=1, maintains_sort_order=true-10)--------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a0, a, b, c, d], output_ordering=[a@1 ASC, b@2 ASC NULLS LAST, c@3 ASC NULLS LAST], file_type=csv, has_header=true+03)----RepartitionExec: partitioning=Hash([a@1], 2), input_partitions=1, maintains_sort_order=true+04)------ProjectionExec: expr=[a0@0 as a0, a@1 as a, b@2 as b, c@3 as c, d@4 as d, row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING@5 as rn1]+05)--------BoundedWindowAggExec: wdw=[row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING: Field { "row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING": UInt64 }, frame: ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING], mode=[Sorted]+06)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a0, a, b, c, d], output_ordering=[a@1 ASC, b@2 ASC NULLS LAST, c@3 ASC NULLS LAST], file_type=csv, has_header=true+07)----RepartitionExec: partitioning=Hash([a@1], 2), input_partitions=1, maintains_sort_order=true+08)------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a0, a, b, c, d], output_ordering=[a@1 ASC, b@2 ASC NULLS LAST, c@3 ASC NULLS LAST], file_type=csv, has_header=true# sort merge join should propagate ordering equivalence of the right side# for right join. Hence final requirement rn1 ASC is already satisfied at@@ -3197,14 +3188,12 @@ logical_planphysical_plan01)SortPreservingMergeExec: [rn1@10 ASC NULLS LAST]02)--SortMergeJoin: join_type=Right, on=[(a@1, a@1)]-03)----CoalesceBatchesExec: target_batch_size=2-04)------RepartitionExec: partitioning=Hash([a@1], 2), input_partitions=1, maintains_sort_order=true-05)--------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a0, a, b, c, d], output_ordering=[a@1 ASC, b@2 ASC NULLS LAST, c@3 ASC NULLS LAST], file_type=csv, has_header=true-06)----CoalesceBatchesExec: target_batch_size=2-07)------RepartitionExec: partitioning=Hash([a@1], 2), input_partitions=1, maintains_sort_order=true-08)--------ProjectionExec: expr=[a0@0 as a0, a@1 as a, b@2 as b, c@3 as c, d@4 as d, row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING@5 as rn1]-09)----------BoundedWindowAggExec: wdw=[row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING: Field { "row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING": UInt64 }, frame: ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING], mode=[Sorted]-10)------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a0, a, b, c, d], output_ordering=[a@1 ASC, b@2 ASC NULLS LAST, c@3 ASC NULLS LAST], file_type=csv, has_header=true+03)----RepartitionExec: partitioning=Hash([a@1], 2), input_partitions=1, maintains_sort_order=true+04)------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a0, a, b, c, d], output_ordering=[a@1 ASC, b@2 ASC NULLS LAST, c@3 ASC NULLS LAST], file_type=csv, has_header=true+05)----RepartitionExec: partitioning=Hash([a@1], 2), input_partitions=1, maintains_sort_order=true+06)------ProjectionExec: expr=[a0@0 as a0, a@1 as a, b@2 as b, c@3 as c, d@4 as d, row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING@5 as rn1]+07)--------BoundedWindowAggExec: wdw=[row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING: Field { "row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING": UInt64 }, frame: ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING], mode=[Sorted]+08)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a0, a, b, c, d], output_ordering=[a@1 ASC, b@2 ASC NULLS LAST, c@3 ASC NULLS LAST], file_type=csv, has_header=truestatement okset datafusion.optimizer.prefer_existing_sort = false;@@ -3236,16 +3225,14 @@ logical_planphysical_plan01)SortPreservingMergeExec: [a@1 ASC, b@2 ASC NULLS LAST, c@3 ASC NULLS LAST, rn1@11 ASC NULLS LAST]02)--SortMergeJoin: join_type=Inner, on=[(a@1, a@1)]-03)----CoalesceBatchesExec: target_batch_size=2-04)------RepartitionExec: partitioning=Hash([a@1], 2), input_partitions=1, maintains_sort_order=true-05)--------ProjectionExec: expr=[a0@0 as a0, a@1 as a, b@2 as b, c@3 as c, d@4 as d, row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING@5 as rn1]-06)----------BoundedWindowAggExec: wdw=[row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING: Field { "row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING": UInt64 }, frame: ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING], mode=[Sorted]-07)------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a0, a, b, c, d], output_ordering=[a@1 ASC, b@2 ASC NULLS LAST, c@3 ASC NULLS LAST], file_type=csv, has_header=true-08)----CoalesceBatchesExec: target_batch_size=2-09)------RepartitionExec: partitioning=Hash([a@1], 2), input_partitions=1, maintains_sort_order=true-10)--------ProjectionExec: expr=[a0@0 as a0, a@1 as a, b@2 as b, c@3 as c, d@4 as d, row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING@5 as rn1]-11)----------BoundedWindowAggExec: wdw=[row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING: Field { "row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING": UInt64 }, frame: ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING], mode=[Sorted]-12)------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a0, a, b, c, d], output_ordering=[a@1 ASC, b@2 ASC NULLS LAST, c@3 ASC NULLS LAST], file_type=csv, has_header=true+03)----RepartitionExec: partitioning=Hash([a@1], 2), input_partitions=1, maintains_sort_order=true+04)------ProjectionExec: expr=[a0@0 as a0, a@1 as a, b@2 as b, c@3 as c, d@4 as d, row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING@5 as rn1]+05)--------BoundedWindowAggExec: wdw=[row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING: Field { "row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING": UInt64 }, frame: ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING], mode=[Sorted]+06)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a0, a, b, c, d], output_ordering=[a@1 ASC, b@2 ASC NULLS LAST, c@3 ASC NULLS LAST], file_type=csv, has_header=true+07)----RepartitionExec: partitioning=Hash([a@1], 2), input_partitions=1, maintains_sort_order=true+08)------ProjectionExec: expr=[a0@0 as a0, a@1 as a, b@2 as b, c@3 as c, d@4 as d, row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING@5 as rn1]+09)--------BoundedWindowAggExec: wdw=[row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING: Field { "row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING": UInt64 }, frame: ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING], mode=[Sorted]+10)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a0, a, b, c, d], output_ordering=[a@1 ASC, b@2 ASC NULLS LAST, c@3 ASC NULLS LAST], file_type=csv, has_header=truestatement okset datafusion.optimizer.prefer_hash_join = true;@@ -3429,16 +3416,13 @@ physical_plan01)SortPreservingMergeExec: [a@0 ASC]02)--ProjectionExec: expr=[a@0 as a, last_value(r.b) ORDER BY [r.a ASC NULLS FIRST]@3 as last_col1]03)----AggregateExec: mode=FinalPartitioned, gby=[a@0 as a, b@1 as b, c@2 as c], aggr=[last_value(r.b) ORDER BY [r.a ASC NULLS FIRST]], ordering_mode=PartiallySorted([0])-04)------CoalesceBatchesExec: target_batch_size=2-05)--------RepartitionExec: partitioning=Hash([a@0, b@1, c@2], 2), input_partitions=2, preserve_order=true, sort_exprs=a@0 ASC-06)----------AggregateExec: mode=Partial, gby=[a@0 as a, b@1 as b, c@2 as c], aggr=[last_value(r.b) ORDER BY [r.a ASC NULLS FIRST]], ordering_mode=PartiallySorted([0])-07)------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(a@0, a@0)]-08)--------------CoalesceBatchesExec: target_batch_size=2-09)----------------RepartitionExec: partitioning=Hash([a@0], 2), input_partitions=1, maintains_sort_order=true-10)------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a, b, c], output_ordering=[a@0 ASC, b@1 ASC NULLS LAST, c@2 ASC NULLS LAST], file_type=csv, has_header=true-11)--------------CoalesceBatchesExec: target_batch_size=2-12)----------------RepartitionExec: partitioning=Hash([a@0], 2), input_partitions=1, maintains_sort_order=true-13)------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a, b], output_ordering=[a@0 ASC, b@1 ASC NULLS LAST], file_type=csv, has_header=true+04)------RepartitionExec: partitioning=Hash([a@0, b@1, c@2], 2), input_partitions=2, preserve_order=true, sort_exprs=a@0 ASC+05)--------AggregateExec: mode=Partial, gby=[a@0 as a, b@1 as b, c@2 as c], aggr=[last_value(r.b) ORDER BY [r.a ASC NULLS FIRST]], ordering_mode=PartiallySorted([0])+06)----------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(a@0, a@0)]+07)------------RepartitionExec: partitioning=Hash([a@0], 2), input_partitions=1, maintains_sort_order=true+08)--------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a, b, c], output_ordering=[a@0 ASC, b@1 ASC NULLS LAST, c@2 ASC NULLS LAST], file_type=csv, has_header=true+09)------------RepartitionExec: partitioning=Hash([a@0], 2), input_partitions=1, maintains_sort_order=true+10)--------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a, b], output_ordering=[a@0 ASC, b@1 ASC NULLS LAST], file_type=csv, has_header=truequery TTEXPLAIN SELECT *diff --git a/datafusion/sqllogictest/test_files/limit.slt b/datafusion/sqllogictest/test_files/limit.sltindex a2b6eae7d9..524304546d 100644--- a/datafusion/sqllogictest/test_files/limit.slt+++ b/datafusion/sqllogictest/test_files/limit.slt@@ -404,10 +404,9 @@ logical_plan02)--TableScan: t1000 projection=[i]physical_plan01)AggregateExec: mode=FinalPartitioned, gby=[i@0 as i], aggr=[]-02)--CoalesceBatchesExec: target_batch_size=8192-03)----RepartitionExec: partitioning=Hash([i@0], 4), input_partitions=1-04)------AggregateExec: mode=Partial, gby=[i@0 as i], aggr=[]-05)--------DataSourceExec: partitions=1+02)--RepartitionExec: partitioning=Hash([i@0], 4), input_partitions=1+03)----AggregateExec: mode=Partial, gby=[i@0 as i], aggr=[]+04)------DataSourceExec: partitions=1statement okset datafusion.explain.show_sizes = true;@@ -635,11 +634,10 @@ physical_plan02)--SortPreservingMergeExec: [b@0 DESC], fetch=303)----SortExec: TopK(fetch=3), expr=[b@0 DESC], preserve_partitioning=[true]04)------AggregateExec: mode=FinalPartitioned, gby=[b@0 as b], aggr=[sum(ordered_table.a)]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([b@0], 4), input_partitions=4-07)------------AggregateExec: mode=Partial, gby=[b@1 as b], aggr=[sum(ordered_table.a)]-08)--------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-09)----------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a, b], file_type=csv, has_header=true+05)--------RepartitionExec: partitioning=Hash([b@0], 4), input_partitions=4+06)----------AggregateExec: mode=Partial, gby=[b@1 as b], aggr=[sum(ordered_table.a)]+07)------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+08)--------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/data/window_2.csv]]}, projection=[a, b], file_type=csv, has_header=true# Applying offset & limit when multiple streams from union# the plan must still have a global limit to apply the offsetdiff --git a/datafusion/sqllogictest/test_files/order.slt b/datafusion/sqllogictest/test_files/order.sltindex 86650386a4..62579ea1cd 100644--- a/datafusion/sqllogictest/test_files/order.slt+++ b/datafusion/sqllogictest/test_files/order.slt@@ -918,18 +918,16 @@ physical_plan03)----InterleaveExec04)------ProjectionExec: expr=[0 as m, t@0 as t]05)--------AggregateExec: mode=FinalPartitioned, gby=[t@0 as t], aggr=[]-06)----------CoalesceBatchesExec: target_batch_size=8192-07)------------RepartitionExec: partitioning=Hash([t@0], 2), input_partitions=1-08)--------------AggregateExec: mode=Partial, gby=[t@0 as t], aggr=[]-09)----------------ProjectionExec: expr=[column1@0 as t]-10)------------------DataSourceExec: partitions=1, partition_sizes=[1]-11)------ProjectionExec: expr=[1 as m, t@0 as t]-12)--------AggregateExec: mode=FinalPartitioned, gby=[t@0 as t], aggr=[]-13)----------CoalesceBatchesExec: target_batch_size=8192-14)------------RepartitionExec: partitioning=Hash([t@0], 2), input_partitions=1-15)--------------AggregateExec: mode=Partial, gby=[t@0 as t], aggr=[]-16)----------------ProjectionExec: expr=[column1@0 as t]-17)------------------DataSourceExec: partitions=1, partition_sizes=[1]+06)----------RepartitionExec: partitioning=Hash([t@0], 2), input_partitions=1+07)------------AggregateExec: mode=Partial, gby=[t@0 as t], aggr=[]+08)--------------ProjectionExec: expr=[column1@0 as t]+09)----------------DataSourceExec: partitions=1, partition_sizes=[1]+10)------ProjectionExec: expr=[1 as m, t@0 as t]+11)--------AggregateExec: mode=FinalPartitioned, gby=[t@0 as t], aggr=[]+12)----------RepartitionExec: partitioning=Hash([t@0], 2), input_partitions=1+13)------------AggregateExec: mode=Partial, gby=[t@0 as t], aggr=[]+14)--------------ProjectionExec: expr=[column1@0 as t]+15)----------------DataSourceExec: partitions=1, partition_sizes=[1]###### Multi column sorting with listsdiff --git a/datafusion/sqllogictest/test_files/predicates.slt b/datafusion/sqllogictest/test_files/predicates.sltindex 90c683947c..7d33814b8b 100644--- a/datafusion/sqllogictest/test_files/predicates.slt+++ b/datafusion/sqllogictest/test_files/predicates.slt@@ -669,16 +669,14 @@ logical_plan06)------TableScan: part projection=[p_partkey, p_brand, p_size], partial_filters=[part.p_size >= Int32(1), part.p_brand = Utf8View("Brand#12") AND part.p_size <= Int32(5) OR part.p_brand = Utf8View("Brand#23") AND part.p_size <= Int32(10) OR part.p_brand = Utf8View("Brand#34") AND part.p_size <= Int32(15)]physical_plan01)HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_partkey@0, p_partkey@0)], filter=p_brand@1 = Brand#12 AND l_quantity@0 >= Some(100),15,2 AND l_quantity@0 <= Some(1100),15,2 AND p_size@2 <= 5 OR p_brand@1 = Brand#23 AND l_quantity@0 >= Some(1000),15,2 AND l_quantity@0 <= Some(2000),15,2 AND p_size@2 <= 10 OR p_brand@1 = Brand#34 AND l_quantity@0 >= Some(2000),15,2 AND l_quantity@0 <= Some(3000),15,2 AND p_size@2 <= 15, projection=[l_partkey@0]-02)--CoalesceBatchesExec: target_batch_size=8192-03)----RepartitionExec: partitioning=Hash([l_partkey@0], 4), input_partitions=4-04)------FilterExec: l_quantity@1 >= Some(100),15,2 AND l_quantity@1 <= Some(1100),15,2 OR l_quantity@1 >= Some(1000),15,2 AND l_quantity@1 <= Some(2000),15,2 OR l_quantity@1 >= Some(2000),15,2 AND l_quantity@1 <= Some(3000),15,2-05)--------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-06)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/tpch-csv/lineitem.csv]]}, projection=[l_partkey, l_quantity], file_type=csv, has_header=true-07)--CoalesceBatchesExec: target_batch_size=8192-08)----RepartitionExec: partitioning=Hash([p_partkey@0], 4), input_partitions=4-09)------FilterExec: (p_brand@1 = Brand#12 AND p_size@2 <= 5 OR p_brand@1 = Brand#23 AND p_size@2 <= 10 OR p_brand@1 = Brand#34 AND p_size@2 <= 15) AND p_size@2 >= 1-10)--------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-11)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/tpch-csv/part.csv]]}, projection=[p_partkey, p_brand, p_size], file_type=csv, has_header=true+02)--RepartitionExec: partitioning=Hash([l_partkey@0], 4), input_partitions=4+03)----FilterExec: l_quantity@1 >= Some(100),15,2 AND l_quantity@1 <= Some(1100),15,2 OR l_quantity@1 >= Some(1000),15,2 AND l_quantity@1 <= Some(2000),15,2 OR l_quantity@1 >= Some(2000),15,2 AND l_quantity@1 <= Some(3000),15,2+04)------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+05)--------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/tpch-csv/lineitem.csv]]}, projection=[l_partkey, l_quantity], file_type=csv, has_header=true+06)--RepartitionExec: partitioning=Hash([p_partkey@0], 4), input_partitions=4+07)----FilterExec: (p_brand@1 = Brand#12 AND p_size@2 <= 5 OR p_brand@1 = Brand#23 AND p_size@2 <= 10 OR p_brand@1 = Brand#34 AND p_size@2 <= 15) AND p_size@2 >= 1+08)------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+09)--------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/tpch-csv/part.csv]]}, projection=[p_partkey, p_brand, p_size], file_type=csv, has_header=true######### TPCH Q19 - Pull predicates to inner join (simplified)@@ -761,14 +759,12 @@ physical_plan03)----HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(ps_partkey@0, p_partkey@2)], projection=[ps_suppkey@1, l_extendedprice@2, l_discount@3, p_partkey@4]04)------DataSourceExec: partitions=1, partition_sizes=[1]05)------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_partkey@0, p_partkey@0)], projection=[l_extendedprice@1, l_discount@2, p_partkey@3]-06)--------CoalesceBatchesExec: target_batch_size=8192-07)----------RepartitionExec: partitioning=Hash([l_partkey@0], 4), input_partitions=1-08)------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/tpch-csv/lineitem.csv]]}, projection=[l_partkey, l_extendedprice, l_discount], file_type=csv, has_header=true-09)--------CoalesceBatchesExec: target_batch_size=8192-10)----------RepartitionExec: partitioning=Hash([p_partkey@0], 4), input_partitions=4-11)------------FilterExec: p_brand@1 = Brand#12 OR p_brand@1 = Brand#23, projection=[p_partkey@0]-12)--------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-13)----------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/tpch-csv/part.csv]]}, projection=[p_partkey, p_brand], file_type=csv, has_header=true+06)--------RepartitionExec: partitioning=Hash([l_partkey@0], 4), input_partitions=1+07)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/tpch-csv/lineitem.csv]]}, projection=[l_partkey, l_extendedprice, l_discount], file_type=csv, has_header=true+08)--------RepartitionExec: partitioning=Hash([p_partkey@0], 4), input_partitions=4+09)----------FilterExec: p_brand@1 = Brand#12 OR p_brand@1 = Brand#23, projection=[p_partkey@0]+10)------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+11)--------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/core/tests/tpch-csv/part.csv]]}, projection=[p_partkey, p_brand], file_type=csv, has_header=true# Simplification of a binary operator with a NULL valuediff --git a/datafusion/sqllogictest/test_files/preserve_file_partitioning.slt b/datafusion/sqllogictest/test_files/preserve_file_partitioning.sltindex c92fccc459..34c5fd97b5 100644--- a/datafusion/sqllogictest/test_files/preserve_file_partitioning.slt+++ b/datafusion/sqllogictest/test_files/preserve_file_partitioning.slt@@ -198,10 +198,9 @@ logical_planphysical_plan01)ProjectionExec: expr=[f_dkey@0 as f_dkey, count(Int64(1))@1 as count(*), sum(fact_table.value)@2 as sum(fact_table.value)]02)--AggregateExec: mode=FinalPartitioned, gby=[f_dkey@0 as f_dkey], aggr=[count(Int64(1)), sum(fact_table.value)]-03)----CoalesceBatchesExec: target_batch_size=8192-04)------RepartitionExec: partitioning=Hash([f_dkey@0], 3), input_partitions=3-05)--------AggregateExec: mode=Partial, gby=[f_dkey@1 as f_dkey], aggr=[count(Int64(1)), sum(fact_table.value)]-06)----------DataSourceExec: file_groups={3 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=A/data.parquet], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=B/data.parquet], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=C/data.parquet]]}, projection=[value, f_dkey], file_type=parquet+03)----RepartitionExec: partitioning=Hash([f_dkey@0], 3), input_partitions=3+04)------AggregateExec: mode=Partial, gby=[f_dkey@1 as f_dkey], aggr=[count(Int64(1)), sum(fact_table.value)]+05)--------DataSourceExec: file_groups={3 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=A/data.parquet], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=B/data.parquet], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=C/data.parquet]]}, projection=[value, f_dkey], file_type=parquet# Verify results without optimizationquery TIR rowsort@@ -260,10 +259,9 @@ physical_plan02)--ProjectionExec: expr=[f_dkey@0 as f_dkey, count(Int64(1))@1 as count(*), avg(fact_table_ordered.value)@2 as avg(fact_table_ordered.value)]03)----AggregateExec: mode=FinalPartitioned, gby=[f_dkey@0 as f_dkey], aggr=[count(Int64(1)), avg(fact_table_ordered.value)], ordering_mode=Sorted04)------SortExec: expr=[f_dkey@0 ASC NULLS LAST], preserve_partitioning=[true]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([f_dkey@0], 3), input_partitions=3-07)------------AggregateExec: mode=Partial, gby=[f_dkey@1 as f_dkey], aggr=[count(Int64(1)), avg(fact_table_ordered.value)], ordering_mode=Sorted-08)--------------DataSourceExec: file_groups={3 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=A/data.parquet], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=B/data.parquet], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=C/data.parquet]]}, projection=[value, f_dkey], output_ordering=[f_dkey@1 ASC NULLS LAST], file_type=parquet+05)--------RepartitionExec: partitioning=Hash([f_dkey@0], 3), input_partitions=3+06)----------AggregateExec: mode=Partial, gby=[f_dkey@1 as f_dkey], aggr=[count(Int64(1)), avg(fact_table_ordered.value)], ordering_mode=Sorted+07)------------DataSourceExec: file_groups={3 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=A/data.parquet], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=B/data.parquet], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=C/data.parquet]]}, projection=[value, f_dkey], output_ordering=[f_dkey@1 ASC NULLS LAST], file_type=parquet# Verify results without optimizationquery TIR@@ -334,16 +332,15 @@ physical_plan02)--ProjectionExec: expr=[f_dkey@0 as f_dkey, max(d.env)@1 as max(d.env), max(d.service)@2 as max(d.service), count(Int64(1))@3 as count(*), sum(f.value)@4 as sum(f.value)]03)----AggregateExec: mode=FinalPartitioned, gby=[f_dkey@0 as f_dkey], aggr=[max(d.env), max(d.service), count(Int64(1)), sum(f.value)], ordering_mode=Sorted04)------SortExec: expr=[f_dkey@0 ASC NULLS LAST], preserve_partitioning=[true]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([f_dkey@0], 3), input_partitions=3-07)------------AggregateExec: mode=Partial, gby=[f_dkey@1 as f_dkey], aggr=[max(d.env), max(d.service), count(Int64(1)), sum(f.value)], ordering_mode=Sorted-08)--------------ProjectionExec: expr=[value@2 as value, f_dkey@3 as f_dkey, env@0 as env, service@1 as service]-09)----------------HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(d_dkey@0, f_dkey@1)], projection=[env@1, service@2, value@3, f_dkey@4]-10)------------------CoalescePartitionsExec-11)--------------------FilterExec: service@2 = log-12)----------------------RepartitionExec: partitioning=RoundRobinBatch(3), input_partitions=1-13)------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/dimension/data.parquet]]}, projection=[d_dkey, env, service], file_type=parquet, predicate=service@2 = log, pruning_predicate=service_null_count@2 != row_count@3 AND service_min@0 <= log AND log <= service_max@1, required_guarantees=[service in (log)]-14)------------------DataSourceExec: file_groups={3 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=A/data.parquet], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=B/data.parquet], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=C/data.parquet]]}, projection=[value, f_dkey], output_ordering=[f_dkey@1 ASC NULLS LAST], file_type=parquet, predicate=DynamicFilter [ empty ]+05)--------RepartitionExec: partitioning=Hash([f_dkey@0], 3), input_partitions=3+06)----------AggregateExec: mode=Partial, gby=[f_dkey@1 as f_dkey], aggr=[max(d.env), max(d.service), count(Int64(1)), sum(f.value)], ordering_mode=Sorted+07)------------ProjectionExec: expr=[value@2 as value, f_dkey@3 as f_dkey, env@0 as env, service@1 as service]+08)--------------HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(d_dkey@0, f_dkey@1)], projection=[env@1, service@2, value@3, f_dkey@4]+09)----------------CoalescePartitionsExec+10)------------------FilterExec: service@2 = log+11)--------------------RepartitionExec: partitioning=RoundRobinBatch(3), input_partitions=1+12)----------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/dimension/data.parquet]]}, projection=[d_dkey, env, service], file_type=parquet, predicate=service@2 = log, pruning_predicate=service_null_count@2 != row_count@3 AND service_min@0 <= log AND log <= service_max@1, required_guarantees=[service in (log)]+13)----------------DataSourceExec: file_groups={3 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=A/data.parquet], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=B/data.parquet], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=C/data.parquet]]}, projection=[value, f_dkey], output_ordering=[f_dkey@1 ASC NULLS LAST], file_type=parquet, predicate=DynamicFilter [ empty ]# Verify results without optimizationquery TTTIR rowsort@@ -430,9 +427,8 @@ physical_plan01)ProjectionExec: expr=[f_dkey@2 as f_dkey, timestamp@0 as timestamp, value@1 as value, row_number() PARTITION BY [fact_table_ordered.f_dkey] ORDER BY [fact_table_ordered.timestamp ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW@3 as rn]02)--BoundedWindowAggExec: wdw=[row_number() PARTITION BY [fact_table_ordered.f_dkey] ORDER BY [fact_table_ordered.timestamp ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "row_number() PARTITION BY [fact_table_ordered.f_dkey] ORDER BY [fact_table_ordered.timestamp ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": UInt64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[Sorted]03)----SortExec: expr=[f_dkey@2 ASC NULLS LAST, timestamp@0 ASC NULLS LAST], preserve_partitioning=[true]-04)------CoalesceBatchesExec: target_batch_size=8192-05)--------RepartitionExec: partitioning=Hash([f_dkey@2], 3), input_partitions=3-06)----------DataSourceExec: file_groups={3 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=A/data.parquet], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=B/data.parquet], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=C/data.parquet]]}, projection=[timestamp, value, f_dkey], output_ordering=[f_dkey@2 ASC NULLS LAST, timestamp@0 ASC NULLS LAST], file_type=parquet+04)------RepartitionExec: partitioning=Hash([f_dkey@2], 3), input_partitions=3+05)--------DataSourceExec: file_groups={3 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=A/data.parquet], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=B/data.parquet], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/fact/f_dkey=C/data.parquet]]}, projection=[timestamp, value, f_dkey], output_ordering=[f_dkey@2 ASC NULLS LAST, timestamp@0 ASC NULLS LAST], file_type=parquet# Verify results without optimization (limited for readability)query TPRI rowsort@@ -568,10 +564,9 @@ logical_planphysical_plan01)ProjectionExec: expr=[f_dkey@0 as f_dkey, count(Int64(1))@1 as count(*), sum(high_cardinality_table.value)@2 as sum(high_cardinality_table.value)]02)--AggregateExec: mode=FinalPartitioned, gby=[f_dkey@0 as f_dkey], aggr=[count(Int64(1)), sum(high_cardinality_table.value)]-03)----CoalesceBatchesExec: target_batch_size=8192-04)------RepartitionExec: partitioning=Hash([f_dkey@0], 3), input_partitions=3-05)--------AggregateExec: mode=Partial, gby=[f_dkey@1 as f_dkey], aggr=[count(Int64(1)), sum(high_cardinality_table.value)]-06)----------DataSourceExec: file_groups={3 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/high_cardinality/f_dkey=A/data.parquet, WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/high_cardinality/f_dkey=B/data.parquet], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/high_cardinality/f_dkey=C/data.parquet, WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/high_cardinality/f_dkey=D/data.parquet], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/high_cardinality/f_dkey=E/data.parquet]]}, projection=[value, f_dkey], file_type=parquet+03)----RepartitionExec: partitioning=Hash([f_dkey@0], 3), input_partitions=3+04)------AggregateExec: mode=Partial, gby=[f_dkey@1 as f_dkey], aggr=[count(Int64(1)), sum(high_cardinality_table.value)]+05)--------DataSourceExec: file_groups={3 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/high_cardinality/f_dkey=A/data.parquet, WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/high_cardinality/f_dkey=B/data.parquet], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/high_cardinality/f_dkey=C/data.parquet, WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/high_cardinality/f_dkey=D/data.parquet], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/preserve_file_partitioning/high_cardinality/f_dkey=E/data.parquet]]}, projection=[value, f_dkey], file_type=parquetquery TIR rowsortSELECT f_dkey, count(*), sum(value)diff --git a/datafusion/sqllogictest/test_files/push_down_filter.slt b/datafusion/sqllogictest/test_files/push_down_filter.sltindex 8dc31d5f63..4353f805c8 100644--- a/datafusion/sqllogictest/test_files/push_down_filter.slt+++ b/datafusion/sqllogictest/test_files/push_down_filter.slt@@ -482,10 +482,9 @@ group by grouping sets ((), (id))physical_plan01)ProjectionExec: expr=[max(agg_dyn_test.id)@2 as max(agg_dyn_test.id)]02)--AggregateExec: mode=FinalPartitioned, gby=[id@0 as id, __grouping_id@1 as __grouping_id], aggr=[max(agg_dyn_test.id)]-03)----CoalesceBatchesExec: target_batch_size=8192-04)------RepartitionExec: partitioning=Hash([id@0, __grouping_id@1], 2), input_partitions=2-05)--------AggregateExec: mode=Partial, gby=[(NULL as id), (id@0 as id)], aggr=[max(agg_dyn_test.id)]-06)----------DataSourceExec: file_groups={2 groups: [[WORKSPACE_ROOT/datafusion/core/tests/data/test_statistics_per_partition/date=2025-03-01/j5fUeSDQo22oPyPU.parquet, WORKSPACE_ROOT/datafusion/core/tests/data/test_statistics_per_partition/date=2025-03-02/j5fUeSDQo22oPyPU.parquet], [WORKSPACE_ROOT/datafusion/core/tests/data/test_statistics_per_partition/date=2025-03-03/j5fUeSDQo22oPyPU.parquet, WORKSPACE_ROOT/datafusion/core/tests/data/test_statistics_per_partition/date=2025-03-04/j5fUeSDQo22oPyPU.parquet]]}, projection=[id], file_type=parquet, predicate=id@0 < 10, pruning_predicate=id_null_count@1 != row_count@2 AND id_min@0 < 10, required_guarantees=[]+03)----RepartitionExec: partitioning=Hash([id@0, __grouping_id@1], 2), input_partitions=2+04)------AggregateExec: mode=Partial, gby=[(NULL as id), (id@0 as id)], aggr=[max(agg_dyn_test.id)]+05)--------DataSourceExec: file_groups={2 groups: [[WORKSPACE_ROOT/datafusion/core/tests/data/test_statistics_per_partition/date=2025-03-01/j5fUeSDQo22oPyPU.parquet, WORKSPACE_ROOT/datafusion/core/tests/data/test_statistics_per_partition/date=2025-03-02/j5fUeSDQo22oPyPU.parquet], [WORKSPACE_ROOT/datafusion/core/tests/data/test_statistics_per_partition/date=2025-03-03/j5fUeSDQo22oPyPU.parquet, WORKSPACE_ROOT/datafusion/core/tests/data/test_statistics_per_partition/date=2025-03-04/j5fUeSDQo22oPyPU.parquet]]}, projection=[id], file_type=parquet, predicate=id@0 < 10, pruning_predicate=id_null_count@1 != row_count@2 AND id_min@0 < 10, required_guarantees=[]statement okdrop table agg_dyn_test;diff --git a/datafusion/sqllogictest/test_files/qualify.slt b/datafusion/sqllogictest/test_files/qualify.sltindex 8ced344e0f..ce58e3998c 100644--- a/datafusion/sqllogictest/test_files/qualify.slt+++ b/datafusion/sqllogictest/test_files/qualify.slt@@ -320,16 +320,14 @@ physical_plan03)----ProjectionExec: expr=[dept@0 as dept, avg(users.salary) PARTITION BY [users.dept] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING@2 as avg(users.salary) PARTITION BY [users.dept] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING]04)------WindowAggExec: wdw=[avg(users.salary) PARTITION BY [users.dept] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING: Ok(Field { name: "avg(users.salary) PARTITION BY [users.dept] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING", data_type: Decimal128(14, 6), nullable: true }), frame: WindowFrame { units: Rows, start_bound: Preceding(UInt64(NULL)), end_bound: Following(UInt64(NULL)), is_causal: false }]05)--------SortExec: expr=[dept@0 ASC NULLS LAST], preserve_partitioning=[true]-06)----------CoalesceBatchesExec: target_batch_size=8192-07)------------RepartitionExec: partitioning=Hash([dept@0], 4), input_partitions=4-08)--------------FilterExec: sum(users.salary)@2 > Some(2000000),20,2, projection=[dept@0, salary@1]-09)----------------AggregateExec: mode=FinalPartitioned, gby=[dept@0 as dept, salary@1 as salary], aggr=[sum(users.salary)]-10)------------------CoalesceBatchesExec: target_batch_size=8192-11)--------------------RepartitionExec: partitioning=Hash([dept@0, salary@1], 4), input_partitions=4-12)----------------------AggregateExec: mode=Partial, gby=[dept@1 as dept, salary@0 as salary], aggr=[sum(users.salary)]-13)------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-14)--------------------------FilterExec: salary@0 > Some(500000),10,2-15)----------------------------DataSourceExec: partitions=1, partition_sizes=[1]+06)----------RepartitionExec: partitioning=Hash([dept@0], 4), input_partitions=4+07)------------FilterExec: sum(users.salary)@2 > Some(2000000),20,2, projection=[dept@0, salary@1]+08)--------------AggregateExec: mode=FinalPartitioned, gby=[dept@0 as dept, salary@1 as salary], aggr=[sum(users.salary)]+09)----------------RepartitionExec: partitioning=Hash([dept@0, salary@1], 4), input_partitions=4+10)------------------AggregateExec: mode=Partial, gby=[dept@1 as dept, salary@0 as salary], aggr=[sum(users.salary)]+11)--------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+12)----------------------FilterExec: salary@0 > Some(500000),10,2+13)------------------------DataSourceExec: partitions=1, partition_sizes=[1]# plan with aggregate functionquery TT@@ -356,10 +354,9 @@ physical_plan07)------------SortPreservingMergeExec: [sum(users.salary)@1 DESC]08)--------------SortExec: expr=[sum(users.salary)@1 DESC], preserve_partitioning=[true]09)----------------AggregateExec: mode=FinalPartitioned, gby=[dept@0 as dept], aggr=[sum(users.salary)]-10)------------------CoalesceBatchesExec: target_batch_size=8192-11)--------------------RepartitionExec: partitioning=Hash([dept@0], 4), input_partitions=1-12)----------------------AggregateExec: mode=Partial, gby=[dept@1 as dept], aggr=[sum(users.salary)]-13)------------------------DataSourceExec: partitions=1, partition_sizes=[1]+10)------------------RepartitionExec: partitioning=Hash([dept@0], 4), input_partitions=1+11)--------------------AggregateExec: mode=Partial, gby=[dept@1 as dept], aggr=[sum(users.salary)]+12)----------------------DataSourceExec: partitions=1, partition_sizes=[1]# Clean upstatement okdiff --git a/datafusion/sqllogictest/test_files/repartition.slt b/datafusion/sqllogictest/test_files/repartition.sltindex f6061b61a2..54e445f212 100644--- a/datafusion/sqllogictest/test_files/repartition.slt+++ b/datafusion/sqllogictest/test_files/repartition.slt@@ -44,10 +44,9 @@ logical_plan02)--TableScan: parquet_table projection=[column1, column2]physical_plan01)AggregateExec: mode=FinalPartitioned, gby=[column1@0 as column1], aggr=[sum(parquet_table.column2)]-02)--CoalesceBatchesExec: target_batch_size=8192-03)----RepartitionExec: partitioning=Hash([column1@0], 4), input_partitions=1-04)------AggregateExec: mode=Partial, gby=[column1@0 as column1], aggr=[sum(parquet_table.column2)]-05)--------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition/parquet_table/2.parquet]]}, projection=[column1, column2], file_type=parquet+02)--RepartitionExec: partitioning=Hash([column1@0], 4), input_partitions=1+03)----AggregateExec: mode=Partial, gby=[column1@0 as column1], aggr=[sum(parquet_table.column2)]+04)------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition/parquet_table/2.parquet]]}, projection=[column1, column2], file_type=parquet# disable round robin repartitioningstatement ok@@ -61,10 +60,9 @@ logical_plan02)--TableScan: parquet_table projection=[column1, column2]physical_plan01)AggregateExec: mode=FinalPartitioned, gby=[column1@0 as column1], aggr=[sum(parquet_table.column2)]-02)--CoalesceBatchesExec: target_batch_size=8192-03)----RepartitionExec: partitioning=Hash([column1@0], 4), input_partitions=1-04)------AggregateExec: mode=Partial, gby=[column1@0 as column1], aggr=[sum(parquet_table.column2)]-05)--------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition/parquet_table/2.parquet]]}, projection=[column1, column2], file_type=parquet+02)--RepartitionExec: partitioning=Hash([column1@0], 4), input_partitions=1+03)----AggregateExec: mode=Partial, gby=[column1@0 as column1], aggr=[sum(parquet_table.column2)]+04)------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/repartition/parquet_table/2.parquet]]}, projection=[column1, column2], file_type=parquet# Cleanupdiff --git a/datafusion/sqllogictest/test_files/select.slt b/datafusion/sqllogictest/test_files/select.sltindex ab0859fa4a..490df4b72d 100644--- a/datafusion/sqllogictest/test_files/select.slt+++ b/datafusion/sqllogictest/test_files/select.slt@@ -1543,13 +1543,12 @@ logical_planphysical_plan01)ProjectionExec: expr=[c2@0 as c2, count(Int64(1))@1 as count(*)]02)--AggregateExec: mode=FinalPartitioned, gby=[c2@0 as c2], aggr=[count(Int64(1))]-03)----CoalesceBatchesExec: target_batch_size=8192-04)------RepartitionExec: partitioning=Hash([c2@0], 2), input_partitions=2-05)--------AggregateExec: mode=Partial, gby=[c2@0 as c2], aggr=[count(Int64(1))]-06)----------RepartitionExec: partitioning=RoundRobinBatch(2), input_partitions=1-07)------------ProjectionExec: expr=[c2@0 as c2]-08)--------------SortExec: TopK(fetch=4), expr=[c1@1 ASC NULLS LAST, c2@0 ASC NULLS LAST], preserve_partitioning=[false]-09)----------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c2, c1], file_type=csv, has_header=true+03)----RepartitionExec: partitioning=Hash([c2@0], 2), input_partitions=2+04)------AggregateExec: mode=Partial, gby=[c2@0 as c2], aggr=[count(Int64(1))]+05)--------RepartitionExec: partitioning=RoundRobinBatch(2), input_partitions=1+06)----------ProjectionExec: expr=[c2@0 as c2]+07)------------SortExec: TopK(fetch=4), expr=[c1@1 ASC NULLS LAST, c2@0 ASC NULLS LAST], preserve_partitioning=[false]+08)--------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c2, c1], file_type=csv, has_header=true# FilterExec can track equality of non-column expressions.# plan below shouldn't have a SortExec because given column 'a' is ordered.diff --git a/datafusion/sqllogictest/test_files/spark/math/hex.slt b/datafusion/sqllogictest/test_files/spark/math/hex.sltindex 00f03c2a58..05c9fb3f31 100644--- a/datafusion/sqllogictest/test_files/spark/math/hex.slt+++ b/datafusion/sqllogictest/test_files/spark/math/hex.slt@@ -62,4 +62,4 @@ SELECT hex(1, 2);query TSELECT hex(arrow_cast('test', 'LargeBinary')) as lar_b;-----74657374\ No newline at end of file+74657374diff --git a/datafusion/sqllogictest/test_files/subquery.slt b/datafusion/sqllogictest/test_files/subquery.sltindex b7c5a2bcbf..da0bfc89d5 100644--- a/datafusion/sqllogictest/test_files/subquery.slt+++ b/datafusion/sqllogictest/test_files/subquery.slt@@ -205,13 +205,12 @@ physical_plan03)----CoalescePartitionsExec04)------ProjectionExec: expr=[sum(t2.t2_int)@1 as sum(t2.t2_int), t2_id@0 as t2_id]05)--------AggregateExec: mode=FinalPartitioned, gby=[t2_id@0 as t2_id], aggr=[sum(t2.t2_int)]-06)----------CoalesceBatchesExec: target_batch_size=2-07)------------RepartitionExec: partitioning=Hash([t2_id@0], 4), input_partitions=4-08)--------------AggregateExec: mode=Partial, gby=[t2_id@0 as t2_id], aggr=[sum(t2.t2_int)]-09)----------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-10)------------------DataSourceExec: partitions=1, partition_sizes=[2]-11)----RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-12)------DataSourceExec: partitions=1, partition_sizes=[2]+06)----------RepartitionExec: partitioning=Hash([t2_id@0], 4), input_partitions=4+07)------------AggregateExec: mode=Partial, gby=[t2_id@0 as t2_id], aggr=[sum(t2.t2_int)]+08)--------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+09)----------------DataSourceExec: partitions=1, partition_sizes=[2]+10)----RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+11)------DataSourceExec: partitions=1, partition_sizes=[2]query II rowsortSELECT t1_id, (SELECT sum(t2_int) FROM t2 WHERE t2.t2_id = t1.t1_id) as t2_sum from t1@@ -239,13 +238,12 @@ physical_plan03)----CoalescePartitionsExec04)------ProjectionExec: expr=[sum(t2.t2_int * Float64(1))@1 + 1 as sum(t2.t2_int * Float64(1)) + Int64(1), t2_id@0 as t2_id]05)--------AggregateExec: mode=FinalPartitioned, gby=[t2_id@0 as t2_id], aggr=[sum(t2.t2_int * Float64(1))]-06)----------CoalesceBatchesExec: target_batch_size=2-07)------------RepartitionExec: partitioning=Hash([t2_id@0], 4), input_partitions=4-08)--------------AggregateExec: mode=Partial, gby=[t2_id@0 as t2_id], aggr=[sum(t2.t2_int * Float64(1))]-09)----------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-10)------------------DataSourceExec: partitions=1, partition_sizes=[2]-11)----RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-12)------DataSourceExec: partitions=1, partition_sizes=[2]+06)----------RepartitionExec: partitioning=Hash([t2_id@0], 4), input_partitions=4+07)------------AggregateExec: mode=Partial, gby=[t2_id@0 as t2_id], aggr=[sum(t2.t2_int * Float64(1))]+08)--------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+09)----------------DataSourceExec: partitions=1, partition_sizes=[2]+10)----RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+11)------DataSourceExec: partitions=1, partition_sizes=[2]query IR rowsortSELECT t1_id, (SELECT sum(t2_int * 1.0) + 1 FROM t2 WHERE t2.t2_id = t1.t1_id) as t2_sum from t1@@ -273,13 +271,12 @@ physical_plan03)----CoalescePartitionsExec04)------ProjectionExec: expr=[sum(t2.t2_int)@1 as sum(t2.t2_int), t2_id@0 as t2_id]05)--------AggregateExec: mode=FinalPartitioned, gby=[t2_id@0 as t2_id], aggr=[sum(t2.t2_int)]-06)----------CoalesceBatchesExec: target_batch_size=2-07)------------RepartitionExec: partitioning=Hash([t2_id@0], 4), input_partitions=4-08)--------------AggregateExec: mode=Partial, gby=[t2_id@0 as t2_id], aggr=[sum(t2.t2_int)]-09)----------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-10)------------------DataSourceExec: partitions=1, partition_sizes=[2]-11)----RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-12)------DataSourceExec: partitions=1, partition_sizes=[2]+06)----------RepartitionExec: partitioning=Hash([t2_id@0], 4), input_partitions=4+07)------------AggregateExec: mode=Partial, gby=[t2_id@0 as t2_id], aggr=[sum(t2.t2_int)]+08)--------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+09)----------------DataSourceExec: partitions=1, partition_sizes=[2]+10)----RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+11)------DataSourceExec: partitions=1, partition_sizes=[2]query II rowsortSELECT t1_id, (SELECT sum(t2_int) FROM t2 WHERE t2.t2_id = t1.t1_id group by t2_id, 'a') as t2_sum from t1@@ -309,13 +306,12 @@ physical_plan04)------ProjectionExec: expr=[sum(t2.t2_int)@1 as sum(t2.t2_int), t2_id@0 as t2_id]05)--------FilterExec: sum(t2.t2_int)@1 < 306)----------AggregateExec: mode=FinalPartitioned, gby=[t2_id@0 as t2_id], aggr=[sum(t2.t2_int)]-07)------------CoalesceBatchesExec: target_batch_size=2-08)--------------RepartitionExec: partitioning=Hash([t2_id@0], 4), input_partitions=4-09)----------------AggregateExec: mode=Partial, gby=[t2_id@0 as t2_id], aggr=[sum(t2.t2_int)]-10)------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-11)--------------------DataSourceExec: partitions=1, partition_sizes=[2]-12)----RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-13)------DataSourceExec: partitions=1, partition_sizes=[2]+07)------------RepartitionExec: partitioning=Hash([t2_id@0], 4), input_partitions=4+08)--------------AggregateExec: mode=Partial, gby=[t2_id@0 as t2_id], aggr=[sum(t2.t2_int)]+09)----------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+10)------------------DataSourceExec: partitions=1, partition_sizes=[2]+11)----RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+12)------DataSourceExec: partitions=1, partition_sizes=[2]query II rowsortSELECT t1_id, (SELECT sum(t2_int) FROM t2 WHERE t2.t2_id = t1.t1_id having sum(t2_int) < 3) as t2_sum from t1diff --git a/datafusion/sqllogictest/test_files/subquery_sort.slt b/datafusion/sqllogictest/test_files/subquery_sort.sltindex ea7addd8e3..dd474f3fa1 100644--- a/datafusion/sqllogictest/test_files/subquery_sort.slt+++ b/datafusion/sqllogictest/test_files/subquery_sort.slt@@ -150,11 +150,10 @@ physical_plan03)----SortExec: expr=[c1@0 ASC NULLS LAST, c3@2 DESC, c9@3 ASC NULLS LAST], preserve_partitioning=[true]04)------ProjectionExec: expr=[first_value(sink_table.c1) ORDER BY [sink_table.c1 ASC NULLS LAST, sink_table.c3 DESC NULLS FIRST, sink_table.c9 ASC NULLS LAST]@1 as c1, first_value(sink_table.c2) ORDER BY [sink_table.c1 ASC NULLS LAST, sink_table.c3 DESC NULLS FIRST, sink_table.c9 ASC NULLS LAST]@2 as c2, first_value(sink_table.c3) ORDER BY [sink_table.c1 ASC NULLS LAST, sink_table.c3 DESC NULLS FIRST, sink_table.c9 ASC NULLS LAST]@3 as c3, first_value(sink_table.c9) ORDER BY [sink_table.c1 ASC NULLS LAST, sink_table.c3 DESC NULLS FIRST, sink_table.c9 ASC NULLS LAST]@4 as c9]05)--------AggregateExec: mode=FinalPartitioned, gby=[c1@0 as c1], aggr=[first_value(sink_table.c1) ORDER BY [sink_table.c1 ASC NULLS LAST, sink_table.c3 DESC NULLS FIRST, sink_table.c9 ASC NULLS LAST], first_value(sink_table.c2) ORDER BY [sink_table.c1 ASC NULLS LAST, sink_table.c3 DESC NULLS FIRST, sink_table.c9 ASC NULLS LAST], first_value(sink_table.c3) ORDER BY [sink_table.c1 ASC NULLS LAST, sink_table.c3 DESC NULLS FIRST, sink_table.c9 ASC NULLS LAST], first_value(sink_table.c9) ORDER BY [sink_table.c1 ASC NULLS LAST, sink_table.c3 DESC NULLS FIRST, sink_table.c9 ASC NULLS LAST]]-06)----------CoalesceBatchesExec: target_batch_size=8192-07)------------RepartitionExec: partitioning=Hash([c1@0], 4), input_partitions=4-08)--------------AggregateExec: mode=Partial, gby=[c1@0 as c1], aggr=[first_value(sink_table.c1) ORDER BY [sink_table.c1 ASC NULLS LAST, sink_table.c3 DESC NULLS FIRST, sink_table.c9 ASC NULLS LAST], first_value(sink_table.c2) ORDER BY [sink_table.c1 ASC NULLS LAST, sink_table.c3 DESC NULLS FIRST, sink_table.c9 ASC NULLS LAST], first_value(sink_table.c3) ORDER BY [sink_table.c1 ASC NULLS LAST, sink_table.c3 DESC NULLS FIRST, sink_table.c9 ASC NULLS LAST], first_value(sink_table.c9) ORDER BY [sink_table.c1 ASC NULLS LAST, sink_table.c3 DESC NULLS FIRST, sink_table.c9 ASC NULLS LAST]]-09)----------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-10)------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c2, c3, c9], file_type=csv, has_header=true+06)----------RepartitionExec: partitioning=Hash([c1@0], 4), input_partitions=4+07)------------AggregateExec: mode=Partial, gby=[c1@0 as c1], aggr=[first_value(sink_table.c1) ORDER BY [sink_table.c1 ASC NULLS LAST, sink_table.c3 DESC NULLS FIRST, sink_table.c9 ASC NULLS LAST], first_value(sink_table.c2) ORDER BY [sink_table.c1 ASC NULLS LAST, sink_table.c3 DESC NULLS FIRST, sink_table.c9 ASC NULLS LAST], first_value(sink_table.c3) ORDER BY [sink_table.c1 ASC NULLS LAST, sink_table.c3 DESC NULLS FIRST, sink_table.c9 ASC NULLS LAST], first_value(sink_table.c9) ORDER BY [sink_table.c1 ASC NULLS LAST, sink_table.c3 DESC NULLS FIRST, sink_table.c9 ASC NULLS LAST]]+08)--------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+09)----------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c2, c3, c9], file_type=csv, has_header=truequery TIdiff --git a/datafusion/sqllogictest/test_files/timestamps.slt b/datafusion/sqllogictest/test_files/timestamps.sltindex 6ad6c799f2..05d379c110 100644--- a/datafusion/sqllogictest/test_files/timestamps.slt+++ b/datafusion/sqllogictest/test_files/timestamps.slt@@ -3168,7 +3168,7 @@ NULLstatement okinsert into table_strings values ('33', '12', '23');-query error DataFusion error: Execution error: Hour value '33' is out of range+query error DataFusion error: Execution error: Hour value '33' is out of rangeselect make_time(t.hour, t.minute, t.second) from table_strings t;statement ok@@ -3180,13 +3180,13 @@ select make_time(22);query error Function 'make_time' expects 3 arguments but received 2select make_time(22, 22);-query error DataFusion error: Execution error: Hour value '26' is out of range+query error DataFusion error: Execution error: Hour value '26' is out of rangeselect make_time(26, 13, 23);query error DataFusion error: Execution error: Second value '62' is out of rangeselect make_time(22, 01, 62);-query error DataFusion error: Execution error: Minute value '64' is out of range+query error DataFusion error: Execution error: Minute value '64' is out of rangeselect make_time(22, 64, 23);query error DataFusion error: Execution error: Hour value '-1' is out of rangediff --git a/datafusion/sqllogictest/test_files/tpch/plans/q1.slt.part b/datafusion/sqllogictest/test_files/tpch/plans/q1.slt.partindex 6d76be67c2..84237e4393 100644--- a/datafusion/sqllogictest/test_files/tpch/plans/q1.slt.part+++ b/datafusion/sqllogictest/test_files/tpch/plans/q1.slt.part@@ -51,9 +51,8 @@ physical_plan02)--SortExec: expr=[l_returnflag@0 ASC NULLS LAST, l_linestatus@1 ASC NULLS LAST], preserve_partitioning=[true]03)----ProjectionExec: expr=[l_returnflag@0 as l_returnflag, l_linestatus@1 as l_linestatus, sum(lineitem.l_quantity)@2 as sum_qty, sum(lineitem.l_extendedprice)@3 as sum_base_price, sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)@4 as sum_disc_price, sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount * Int64(1) + lineitem.l_tax)@5 as sum_charge, avg(lineitem.l_quantity)@6 as avg_qty, avg(lineitem.l_extendedprice)@7 as avg_price, avg(lineitem.l_discount)@8 as avg_disc, count(Int64(1))@9 as count_order]04)------AggregateExec: mode=FinalPartitioned, gby=[l_returnflag@0 as l_returnflag, l_linestatus@1 as l_linestatus], aggr=[sum(lineitem.l_quantity), sum(lineitem.l_extendedprice), sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount), sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount * Int64(1) + lineitem.l_tax), avg(lineitem.l_quantity), avg(lineitem.l_extendedprice), avg(lineitem.l_discount), count(Int64(1))]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([l_returnflag@0, l_linestatus@1], 4), input_partitions=4-07)------------AggregateExec: mode=Partial, gby=[l_returnflag@5 as l_returnflag, l_linestatus@6 as l_linestatus], aggr=[sum(lineitem.l_quantity), sum(lineitem.l_extendedprice), sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount), sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount * Int64(1) + lineitem.l_tax), avg(lineitem.l_quantity), avg(lineitem.l_extendedprice), avg(lineitem.l_discount), count(Int64(1))]-08)--------------ProjectionExec: expr=[l_extendedprice@1 * (Some(1),20,0 - l_discount@2) as __common_expr_1, l_quantity@0 as l_quantity, l_extendedprice@1 as l_extendedprice, l_discount@2 as l_discount, l_tax@3 as l_tax, l_returnflag@4 as l_returnflag, l_linestatus@5 as l_linestatus]-09)----------------FilterExec: l_shipdate@6 <= 1998-09-02, projection=[l_quantity@0, l_extendedprice@1, l_discount@2, l_tax@3, l_returnflag@4, l_linestatus@5]-10)------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_quantity, l_extendedprice, l_discount, l_tax, l_returnflag, l_linestatus, l_shipdate], file_type=csv, has_header=false+05)--------RepartitionExec: partitioning=Hash([l_returnflag@0, l_linestatus@1], 4), input_partitions=4+06)----------AggregateExec: mode=Partial, gby=[l_returnflag@5 as l_returnflag, l_linestatus@6 as l_linestatus], aggr=[sum(lineitem.l_quantity), sum(lineitem.l_extendedprice), sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount), sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount * Int64(1) + lineitem.l_tax), avg(lineitem.l_quantity), avg(lineitem.l_extendedprice), avg(lineitem.l_discount), count(Int64(1))]+07)------------ProjectionExec: expr=[l_extendedprice@1 * (Some(1),20,0 - l_discount@2) as __common_expr_1, l_quantity@0 as l_quantity, l_extendedprice@1 as l_extendedprice, l_discount@2 as l_discount, l_tax@3 as l_tax, l_returnflag@4 as l_returnflag, l_linestatus@5 as l_linestatus]+08)--------------FilterExec: l_shipdate@6 <= 1998-09-02, projection=[l_quantity@0, l_extendedprice@1, l_discount@2, l_tax@3, l_returnflag@4, l_linestatus@5]+09)----------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_quantity, l_extendedprice, l_discount, l_tax, l_returnflag, l_linestatus, l_shipdate], file_type=csv, has_header=falsediff --git a/datafusion/sqllogictest/test_files/tpch/plans/q10.slt.part b/datafusion/sqllogictest/test_files/tpch/plans/q10.slt.partindex 7e087da5af..62649148bf 100644--- a/datafusion/sqllogictest/test_files/tpch/plans/q10.slt.part+++ b/datafusion/sqllogictest/test_files/tpch/plans/q10.slt.part@@ -73,27 +73,20 @@ physical_plan02)--SortExec: TopK(fetch=10), expr=[revenue@2 DESC], preserve_partitioning=[true]03)----ProjectionExec: expr=[c_custkey@0 as c_custkey, c_name@1 as c_name, sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)@7 as revenue, c_acctbal@2 as c_acctbal, n_name@4 as n_name, c_address@5 as c_address, c_phone@3 as c_phone, c_comment@6 as c_comment]04)------AggregateExec: mode=FinalPartitioned, gby=[c_custkey@0 as c_custkey, c_name@1 as c_name, c_acctbal@2 as c_acctbal, c_phone@3 as c_phone, n_name@4 as n_name, c_address@5 as c_address, c_comment@6 as c_comment], aggr=[sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([c_custkey@0, c_name@1, c_acctbal@2, c_phone@3, n_name@4, c_address@5, c_comment@6], 4), input_partitions=4-07)------------AggregateExec: mode=Partial, gby=[c_custkey@0 as c_custkey, c_name@1 as c_name, c_acctbal@4 as c_acctbal, c_phone@3 as c_phone, n_name@8 as n_name, c_address@2 as c_address, c_comment@5 as c_comment], aggr=[sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)]-08)--------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(c_nationkey@3, n_nationkey@0)], projection=[c_custkey@0, c_name@1, c_address@2, c_phone@4, c_acctbal@5, c_comment@6, l_extendedprice@7, l_discount@8, n_name@10]-09)----------------CoalesceBatchesExec: target_batch_size=8192-10)------------------RepartitionExec: partitioning=Hash([c_nationkey@3], 4), input_partitions=4-11)--------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(o_orderkey@7, l_orderkey@0)], projection=[c_custkey@0, c_name@1, c_address@2, c_nationkey@3, c_phone@4, c_acctbal@5, c_comment@6, l_extendedprice@9, l_discount@10]-12)----------------------CoalesceBatchesExec: target_batch_size=8192-13)------------------------RepartitionExec: partitioning=Hash([o_orderkey@7], 4), input_partitions=4-14)--------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(c_custkey@0, o_custkey@1)], projection=[c_custkey@0, c_name@1, c_address@2, c_nationkey@3, c_phone@4, c_acctbal@5, c_comment@6, o_orderkey@7]-15)----------------------------CoalesceBatchesExec: target_batch_size=8192-16)------------------------------RepartitionExec: partitioning=Hash([c_custkey@0], 4), input_partitions=1-17)--------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/customer.tbl]]}, projection=[c_custkey, c_name, c_address, c_nationkey, c_phone, c_acctbal, c_comment], file_type=csv, has_header=false-18)----------------------------CoalesceBatchesExec: target_batch_size=8192-19)------------------------------RepartitionExec: partitioning=Hash([o_custkey@1], 4), input_partitions=4-20)--------------------------------FilterExec: o_orderdate@2 >= 1993-10-01 AND o_orderdate@2 < 1994-01-01, projection=[o_orderkey@0, o_custkey@1]-21)----------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_orderkey, o_custkey, o_orderdate], file_type=csv, has_header=false-22)----------------------CoalesceBatchesExec: target_batch_size=8192-23)------------------------RepartitionExec: partitioning=Hash([l_orderkey@0], 4), input_partitions=4-24)--------------------------FilterExec: l_returnflag@3 = R, projection=[l_orderkey@0, l_extendedprice@1, l_discount@2]-25)----------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_extendedprice, l_discount, l_returnflag], file_type=csv, has_header=false-26)----------------CoalesceBatchesExec: target_batch_size=8192-27)------------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=1-28)--------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_name], file_type=csv, has_header=false+05)--------RepartitionExec: partitioning=Hash([c_custkey@0, c_name@1, c_acctbal@2, c_phone@3, n_name@4, c_address@5, c_comment@6], 4), input_partitions=4+06)----------AggregateExec: mode=Partial, gby=[c_custkey@0 as c_custkey, c_name@1 as c_name, c_acctbal@4 as c_acctbal, c_phone@3 as c_phone, n_name@8 as n_name, c_address@2 as c_address, c_comment@5 as c_comment], aggr=[sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)]+07)------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(c_nationkey@3, n_nationkey@0)], projection=[c_custkey@0, c_name@1, c_address@2, c_phone@4, c_acctbal@5, c_comment@6, l_extendedprice@7, l_discount@8, n_name@10]+08)--------------RepartitionExec: partitioning=Hash([c_nationkey@3], 4), input_partitions=4+09)----------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(o_orderkey@7, l_orderkey@0)], projection=[c_custkey@0, c_name@1, c_address@2, c_nationkey@3, c_phone@4, c_acctbal@5, c_comment@6, l_extendedprice@9, l_discount@10]+10)------------------RepartitionExec: partitioning=Hash([o_orderkey@7], 4), input_partitions=4+11)--------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(c_custkey@0, o_custkey@1)], projection=[c_custkey@0, c_name@1, c_address@2, c_nationkey@3, c_phone@4, c_acctbal@5, c_comment@6, o_orderkey@7]+12)----------------------RepartitionExec: partitioning=Hash([c_custkey@0], 4), input_partitions=1+13)------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/customer.tbl]]}, projection=[c_custkey, c_name, c_address, c_nationkey, c_phone, c_acctbal, c_comment], file_type=csv, has_header=false+14)----------------------RepartitionExec: partitioning=Hash([o_custkey@1], 4), input_partitions=4+15)------------------------FilterExec: o_orderdate@2 >= 1993-10-01 AND o_orderdate@2 < 1994-01-01, projection=[o_orderkey@0, o_custkey@1]+16)--------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_orderkey, o_custkey, o_orderdate], file_type=csv, has_header=false+17)------------------RepartitionExec: partitioning=Hash([l_orderkey@0], 4), input_partitions=4+18)--------------------FilterExec: l_returnflag@3 = R, projection=[l_orderkey@0, l_extendedprice@1, l_discount@2]+19)----------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_extendedprice, l_discount, l_returnflag], file_type=csv, has_header=false+20)--------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=1+21)----------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_name], file_type=csv, has_header=falsediff --git a/datafusion/sqllogictest/test_files/tpch/plans/q11.slt.part b/datafusion/sqllogictest/test_files/tpch/plans/q11.slt.partindex cb2271ca65..a31579eb1e 100644--- a/datafusion/sqllogictest/test_files/tpch/plans/q11.slt.part+++ b/datafusion/sqllogictest/test_files/tpch/plans/q11.slt.part@@ -79,40 +79,31 @@ physical_plan04)------ProjectionExec: expr=[ps_partkey@0 as ps_partkey, sum(partsupp.ps_supplycost * partsupp.ps_availqty)@1 as sum(partsupp.ps_supplycost * partsupp.ps_availqty), CAST(sum(partsupp.ps_supplycost * partsupp.ps_availqty)@1 AS Decimal128(38, 15)) as join_proj_push_down_1]05)--------CoalescePartitionsExec06)----------AggregateExec: mode=FinalPartitioned, gby=[ps_partkey@0 as ps_partkey], aggr=[sum(partsupp.ps_supplycost * partsupp.ps_availqty)]-07)------------CoalesceBatchesExec: target_batch_size=8192-08)--------------RepartitionExec: partitioning=Hash([ps_partkey@0], 4), input_partitions=4-09)----------------AggregateExec: mode=Partial, gby=[ps_partkey@0 as ps_partkey], aggr=[sum(partsupp.ps_supplycost * partsupp.ps_availqty)]-10)------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_nationkey@3, n_nationkey@0)], projection=[ps_partkey@0, ps_availqty@1, ps_supplycost@2]-11)--------------------CoalesceBatchesExec: target_batch_size=8192-12)----------------------RepartitionExec: partitioning=Hash([s_nationkey@3], 4), input_partitions=4-13)------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(ps_suppkey@1, s_suppkey@0)], projection=[ps_partkey@0, ps_availqty@2, ps_supplycost@3, s_nationkey@5]-14)--------------------------CoalesceBatchesExec: target_batch_size=8192-15)----------------------------RepartitionExec: partitioning=Hash([ps_suppkey@1], 4), input_partitions=4-16)------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:0..2932049], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:2932049..5864098], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:5864098..8796147], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:8796147..11728193]]}, projection=[ps_partkey, ps_suppkey, ps_availqty, ps_supplycost], file_type=csv, has_header=false-17)--------------------------CoalesceBatchesExec: target_batch_size=8192-18)----------------------------RepartitionExec: partitioning=Hash([s_suppkey@0], 4), input_partitions=1-19)------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_nationkey], file_type=csv, has_header=false-20)--------------------CoalesceBatchesExec: target_batch_size=8192-21)----------------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=4-22)------------------------FilterExec: n_name@1 = GERMANY, projection=[n_nationkey@0]-23)--------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-24)----------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_name], file_type=csv, has_header=false-25)------ProjectionExec: expr=[CAST(CAST(sum(partsupp.ps_supplycost * partsupp.ps_availqty)@0 AS Float64) * 0.0001 AS Decimal128(38, 15)) as sum(partsupp.ps_supplycost * partsupp.ps_availqty) * Float64(0.0001)]-26)--------AggregateExec: mode=Final, gby=[], aggr=[sum(partsupp.ps_supplycost * partsupp.ps_availqty)]-27)----------CoalescePartitionsExec-28)------------AggregateExec: mode=Partial, gby=[], aggr=[sum(partsupp.ps_supplycost * partsupp.ps_availqty)]-29)--------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_nationkey@2, n_nationkey@0)], projection=[ps_availqty@0, ps_supplycost@1]-30)----------------CoalesceBatchesExec: target_batch_size=8192-31)------------------RepartitionExec: partitioning=Hash([s_nationkey@2], 4), input_partitions=4-32)--------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(ps_suppkey@0, s_suppkey@0)], projection=[ps_availqty@1, ps_supplycost@2, s_nationkey@4]-33)----------------------CoalesceBatchesExec: target_batch_size=8192-34)------------------------RepartitionExec: partitioning=Hash([ps_suppkey@0], 4), input_partitions=4-35)--------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:0..2932049], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:2932049..5864098], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:5864098..8796147], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:8796147..11728193]]}, projection=[ps_suppkey, ps_availqty, ps_supplycost], file_type=csv, has_header=false-36)----------------------CoalesceBatchesExec: target_batch_size=8192-37)------------------------RepartitionExec: partitioning=Hash([s_suppkey@0], 4), input_partitions=1-38)--------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_nationkey], file_type=csv, has_header=false-39)----------------CoalesceBatchesExec: target_batch_size=8192-40)------------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=4-41)--------------------FilterExec: n_name@1 = GERMANY, projection=[n_nationkey@0]-42)----------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-43)------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_name], file_type=csv, has_header=false+07)------------RepartitionExec: partitioning=Hash([ps_partkey@0], 4), input_partitions=4+08)--------------AggregateExec: mode=Partial, gby=[ps_partkey@0 as ps_partkey], aggr=[sum(partsupp.ps_supplycost * partsupp.ps_availqty)]+09)----------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_nationkey@3, n_nationkey@0)], projection=[ps_partkey@0, ps_availqty@1, ps_supplycost@2]+10)------------------RepartitionExec: partitioning=Hash([s_nationkey@3], 4), input_partitions=4+11)--------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(ps_suppkey@1, s_suppkey@0)], projection=[ps_partkey@0, ps_availqty@2, ps_supplycost@3, s_nationkey@5]+12)----------------------RepartitionExec: partitioning=Hash([ps_suppkey@1], 4), input_partitions=4+13)------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:0..2932049], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:2932049..5864098], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:5864098..8796147], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:8796147..11728193]]}, projection=[ps_partkey, ps_suppkey, ps_availqty, ps_supplycost], file_type=csv, has_header=false+14)----------------------RepartitionExec: partitioning=Hash([s_suppkey@0], 4), input_partitions=1+15)------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_nationkey], file_type=csv, has_header=false+16)------------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=4+17)--------------------FilterExec: n_name@1 = GERMANY, projection=[n_nationkey@0]+18)----------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+19)------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_name], file_type=csv, has_header=false+20)------ProjectionExec: expr=[CAST(CAST(sum(partsupp.ps_supplycost * partsupp.ps_availqty)@0 AS Float64) * 0.0001 AS Decimal128(38, 15)) as sum(partsupp.ps_supplycost * partsupp.ps_availqty) * Float64(0.0001)]+21)--------AggregateExec: mode=Final, gby=[], aggr=[sum(partsupp.ps_supplycost * partsupp.ps_availqty)]+22)----------CoalescePartitionsExec+23)------------AggregateExec: mode=Partial, gby=[], aggr=[sum(partsupp.ps_supplycost * partsupp.ps_availqty)]+24)--------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_nationkey@2, n_nationkey@0)], projection=[ps_availqty@0, ps_supplycost@1]+25)----------------RepartitionExec: partitioning=Hash([s_nationkey@2], 4), input_partitions=4+26)------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(ps_suppkey@0, s_suppkey@0)], projection=[ps_availqty@1, ps_supplycost@2, s_nationkey@4]+27)--------------------RepartitionExec: partitioning=Hash([ps_suppkey@0], 4), input_partitions=4+28)----------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:0..2932049], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:2932049..5864098], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:5864098..8796147], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:8796147..11728193]]}, projection=[ps_suppkey, ps_availqty, ps_supplycost], file_type=csv, has_header=false+29)--------------------RepartitionExec: partitioning=Hash([s_suppkey@0], 4), input_partitions=1+30)----------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_nationkey], file_type=csv, has_header=false+31)----------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=4+32)------------------FilterExec: n_name@1 = GERMANY, projection=[n_nationkey@0]+33)--------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+34)----------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_name], file_type=csv, has_header=falsediff --git a/datafusion/sqllogictest/test_files/tpch/plans/q12.slt.part b/datafusion/sqllogictest/test_files/tpch/plans/q12.slt.partindex f1008fead1..b152fde02f 100644--- a/datafusion/sqllogictest/test_files/tpch/plans/q12.slt.part+++ b/datafusion/sqllogictest/test_files/tpch/plans/q12.slt.part@@ -63,14 +63,11 @@ physical_plan02)--SortExec: expr=[l_shipmode@0 ASC NULLS LAST], preserve_partitioning=[true]03)----ProjectionExec: expr=[l_shipmode@0 as l_shipmode, sum(CASE WHEN orders.o_orderpriority = Utf8("1-URGENT") OR orders.o_orderpriority = Utf8("2-HIGH") THEN Int64(1) ELSE Int64(0) END)@1 as high_line_count, sum(CASE WHEN orders.o_orderpriority != Utf8("1-URGENT") AND orders.o_orderpriority != Utf8("2-HIGH") THEN Int64(1) ELSE Int64(0) END)@2 as low_line_count]04)------AggregateExec: mode=FinalPartitioned, gby=[l_shipmode@0 as l_shipmode], aggr=[sum(CASE WHEN orders.o_orderpriority = Utf8("1-URGENT") OR orders.o_orderpriority = Utf8("2-HIGH") THEN Int64(1) ELSE Int64(0) END), sum(CASE WHEN orders.o_orderpriority != Utf8("1-URGENT") AND orders.o_orderpriority != Utf8("2-HIGH") THEN Int64(1) ELSE Int64(0) END)]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([l_shipmode@0], 4), input_partitions=4-07)------------AggregateExec: mode=Partial, gby=[l_shipmode@0 as l_shipmode], aggr=[sum(CASE WHEN orders.o_orderpriority = Utf8("1-URGENT") OR orders.o_orderpriority = Utf8("2-HIGH") THEN Int64(1) ELSE Int64(0) END), sum(CASE WHEN orders.o_orderpriority != Utf8("1-URGENT") AND orders.o_orderpriority != Utf8("2-HIGH") THEN Int64(1) ELSE Int64(0) END)]-08)--------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_orderkey@0, o_orderkey@0)], projection=[l_shipmode@1, o_orderpriority@3]-09)----------------CoalesceBatchesExec: target_batch_size=8192-10)------------------RepartitionExec: partitioning=Hash([l_orderkey@0], 4), input_partitions=4-11)--------------------FilterExec: (l_shipmode@4 = MAIL OR l_shipmode@4 = SHIP) AND l_receiptdate@3 > l_commitdate@2 AND l_shipdate@1 < l_commitdate@2 AND l_receiptdate@3 >= 1994-01-01 AND l_receiptdate@3 < 1995-01-01, projection=[l_orderkey@0, l_shipmode@4]-12)----------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_shipdate, l_commitdate, l_receiptdate, l_shipmode], file_type=csv, has_header=false-13)----------------CoalesceBatchesExec: target_batch_size=8192-14)------------------RepartitionExec: partitioning=Hash([o_orderkey@0], 4), input_partitions=4-15)--------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_orderkey, o_orderpriority], file_type=csv, has_header=false+05)--------RepartitionExec: partitioning=Hash([l_shipmode@0], 4), input_partitions=4+06)----------AggregateExec: mode=Partial, gby=[l_shipmode@0 as l_shipmode], aggr=[sum(CASE WHEN orders.o_orderpriority = Utf8("1-URGENT") OR orders.o_orderpriority = Utf8("2-HIGH") THEN Int64(1) ELSE Int64(0) END), sum(CASE WHEN orders.o_orderpriority != Utf8("1-URGENT") AND orders.o_orderpriority != Utf8("2-HIGH") THEN Int64(1) ELSE Int64(0) END)]+07)------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_orderkey@0, o_orderkey@0)], projection=[l_shipmode@1, o_orderpriority@3]+08)--------------RepartitionExec: partitioning=Hash([l_orderkey@0], 4), input_partitions=4+09)----------------FilterExec: (l_shipmode@4 = MAIL OR l_shipmode@4 = SHIP) AND l_receiptdate@3 > l_commitdate@2 AND l_shipdate@1 < l_commitdate@2 AND l_receiptdate@3 >= 1994-01-01 AND l_receiptdate@3 < 1995-01-01, projection=[l_orderkey@0, l_shipmode@4]+10)------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_shipdate, l_commitdate, l_receiptdate, l_shipmode], file_type=csv, has_header=false+11)--------------RepartitionExec: partitioning=Hash([o_orderkey@0], 4), input_partitions=4+12)----------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_orderkey, o_orderpriority], file_type=csv, has_header=falsediff --git a/datafusion/sqllogictest/test_files/tpch/plans/q13.slt.part b/datafusion/sqllogictest/test_files/tpch/plans/q13.slt.partindex f05bb6648a..94e0848bfc 100644--- a/datafusion/sqllogictest/test_files/tpch/plans/q13.slt.part+++ b/datafusion/sqllogictest/test_files/tpch/plans/q13.slt.part@@ -57,16 +57,13 @@ physical_plan02)--SortExec: TopK(fetch=10), expr=[custdist@1 DESC, c_count@0 DESC], preserve_partitioning=[true]03)----ProjectionExec: expr=[c_count@0 as c_count, count(Int64(1))@1 as custdist]04)------AggregateExec: mode=FinalPartitioned, gby=[c_count@0 as c_count], aggr=[count(Int64(1))]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([c_count@0], 4), input_partitions=4-07)------------AggregateExec: mode=Partial, gby=[c_count@0 as c_count], aggr=[count(Int64(1))]-08)--------------ProjectionExec: expr=[count(orders.o_orderkey)@1 as c_count]-09)----------------AggregateExec: mode=SinglePartitioned, gby=[c_custkey@0 as c_custkey], aggr=[count(orders.o_orderkey)]-10)------------------HashJoinExec: mode=Partitioned, join_type=Left, on=[(c_custkey@0, o_custkey@1)], projection=[c_custkey@0, o_orderkey@1]-11)--------------------CoalesceBatchesExec: target_batch_size=8192-12)----------------------RepartitionExec: partitioning=Hash([c_custkey@0], 4), input_partitions=1-13)------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/customer.tbl]]}, projection=[c_custkey], file_type=csv, has_header=false-14)--------------------CoalesceBatchesExec: target_batch_size=8192-15)----------------------RepartitionExec: partitioning=Hash([o_custkey@1], 4), input_partitions=4-16)------------------------FilterExec: o_comment@2 NOT LIKE %special%requests%, projection=[o_orderkey@0, o_custkey@1]-17)--------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_orderkey, o_custkey, o_comment], file_type=csv, has_header=false+05)--------RepartitionExec: partitioning=Hash([c_count@0], 4), input_partitions=4+06)----------AggregateExec: mode=Partial, gby=[c_count@0 as c_count], aggr=[count(Int64(1))]+07)------------ProjectionExec: expr=[count(orders.o_orderkey)@1 as c_count]+08)--------------AggregateExec: mode=SinglePartitioned, gby=[c_custkey@0 as c_custkey], aggr=[count(orders.o_orderkey)]+09)----------------HashJoinExec: mode=Partitioned, join_type=Left, on=[(c_custkey@0, o_custkey@1)], projection=[c_custkey@0, o_orderkey@1]+10)------------------RepartitionExec: partitioning=Hash([c_custkey@0], 4), input_partitions=1+11)--------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/customer.tbl]]}, projection=[c_custkey], file_type=csv, has_header=false+12)------------------RepartitionExec: partitioning=Hash([o_custkey@1], 4), input_partitions=4+13)--------------------FilterExec: o_comment@2 NOT LIKE %special%requests%, projection=[o_orderkey@0, o_custkey@1]+14)----------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_orderkey, o_custkey, o_comment], file_type=csv, has_header=falsediff --git a/datafusion/sqllogictest/test_files/tpch/plans/q14.slt.part b/datafusion/sqllogictest/test_files/tpch/plans/q14.slt.partindex b51c142406..a9ac517f28 100644--- a/datafusion/sqllogictest/test_files/tpch/plans/q14.slt.part+++ b/datafusion/sqllogictest/test_files/tpch/plans/q14.slt.part@@ -47,10 +47,8 @@ physical_plan04)------AggregateExec: mode=Partial, gby=[], aggr=[sum(CASE WHEN part.p_type LIKE Utf8("PROMO%") THEN lineitem.l_extendedprice * Int64(1) - lineitem.l_discount ELSE Int64(0) END), sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)]05)--------ProjectionExec: expr=[l_extendedprice@0 * (Some(1),20,0 - l_discount@1) as __common_expr_1, p_type@2 as p_type]06)----------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_partkey@0, p_partkey@0)], projection=[l_extendedprice@1, l_discount@2, p_type@4]-07)------------CoalesceBatchesExec: target_batch_size=8192-08)--------------RepartitionExec: partitioning=Hash([l_partkey@0], 4), input_partitions=4-09)----------------FilterExec: l_shipdate@3 >= 1995-09-01 AND l_shipdate@3 < 1995-10-01, projection=[l_partkey@0, l_extendedprice@1, l_discount@2]-10)------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_partkey, l_extendedprice, l_discount, l_shipdate], file_type=csv, has_header=false-11)------------CoalesceBatchesExec: target_batch_size=8192-12)--------------RepartitionExec: partitioning=Hash([p_partkey@0], 4), input_partitions=1-13)----------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/part.tbl]]}, projection=[p_partkey, p_type], file_type=csv, has_header=false+07)------------RepartitionExec: partitioning=Hash([l_partkey@0], 4), input_partitions=4+08)--------------FilterExec: l_shipdate@3 >= 1995-09-01 AND l_shipdate@3 < 1995-10-01, projection=[l_partkey@0, l_extendedprice@1, l_discount@2]+09)----------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_partkey, l_extendedprice, l_discount, l_shipdate], file_type=csv, has_header=false+10)------------RepartitionExec: partitioning=Hash([p_partkey@0], 4), input_partitions=1+11)--------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/part.tbl]]}, projection=[p_partkey, p_type], file_type=csv, has_header=falsediff --git a/datafusion/sqllogictest/test_files/tpch/plans/q15.slt.part b/datafusion/sqllogictest/test_files/tpch/plans/q15.slt.partindex 9f1534aa1b..ae0c0a93a3 100644--- a/datafusion/sqllogictest/test_files/tpch/plans/q15.slt.part+++ b/datafusion/sqllogictest/test_files/tpch/plans/q15.slt.part@@ -79,19 +79,16 @@ physical_plan06)----------AggregateExec: mode=Partial, gby=[], aggr=[max(revenue0.total_revenue)]07)------------ProjectionExec: expr=[sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)@1 as total_revenue]08)--------------AggregateExec: mode=FinalPartitioned, gby=[l_suppkey@0 as l_suppkey], aggr=[sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)]-09)----------------CoalesceBatchesExec: target_batch_size=8192-10)------------------RepartitionExec: partitioning=Hash([l_suppkey@0], 4), input_partitions=4-11)--------------------AggregateExec: mode=Partial, gby=[l_suppkey@0 as l_suppkey], aggr=[sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)]-12)----------------------FilterExec: l_shipdate@3 >= 1996-01-01 AND l_shipdate@3 < 1996-04-01, projection=[l_suppkey@0, l_extendedprice@1, l_discount@2]-13)------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_suppkey, l_extendedprice, l_discount, l_shipdate], file_type=csv, has_header=false-14)------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_suppkey@0, supplier_no@0)], projection=[s_suppkey@0, s_name@1, s_address@2, s_phone@3, total_revenue@5]-15)--------CoalesceBatchesExec: target_batch_size=8192-16)----------RepartitionExec: partitioning=Hash([s_suppkey@0], 4), input_partitions=1-17)------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_name, s_address, s_phone], file_type=csv, has_header=false-18)--------ProjectionExec: expr=[l_suppkey@0 as supplier_no, sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)@1 as total_revenue]-19)----------AggregateExec: mode=FinalPartitioned, gby=[l_suppkey@0 as l_suppkey], aggr=[sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)]-20)------------CoalesceBatchesExec: target_batch_size=8192-21)--------------RepartitionExec: partitioning=Hash([l_suppkey@0], 4), input_partitions=4-22)----------------AggregateExec: mode=Partial, gby=[l_suppkey@0 as l_suppkey], aggr=[sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)]-23)------------------FilterExec: l_shipdate@3 >= 1996-01-01 AND l_shipdate@3 < 1996-04-01, projection=[l_suppkey@0, l_extendedprice@1, l_discount@2]-24)--------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_suppkey, l_extendedprice, l_discount, l_shipdate], file_type=csv, has_header=false+09)----------------RepartitionExec: partitioning=Hash([l_suppkey@0], 4), input_partitions=4+10)------------------AggregateExec: mode=Partial, gby=[l_suppkey@0 as l_suppkey], aggr=[sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)]+11)--------------------FilterExec: l_shipdate@3 >= 1996-01-01 AND l_shipdate@3 < 1996-04-01, projection=[l_suppkey@0, l_extendedprice@1, l_discount@2]+12)----------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_suppkey, l_extendedprice, l_discount, l_shipdate], file_type=csv, has_header=false+13)------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_suppkey@0, supplier_no@0)], projection=[s_suppkey@0, s_name@1, s_address@2, s_phone@3, total_revenue@5]+14)--------RepartitionExec: partitioning=Hash([s_suppkey@0], 4), input_partitions=1+15)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_name, s_address, s_phone], file_type=csv, has_header=false+16)--------ProjectionExec: expr=[l_suppkey@0 as supplier_no, sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)@1 as total_revenue]+17)----------AggregateExec: mode=FinalPartitioned, gby=[l_suppkey@0 as l_suppkey], aggr=[sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)]+18)------------RepartitionExec: partitioning=Hash([l_suppkey@0], 4), input_partitions=4+19)--------------AggregateExec: mode=Partial, gby=[l_suppkey@0 as l_suppkey], aggr=[sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)]+20)----------------FilterExec: l_shipdate@3 >= 1996-01-01 AND l_shipdate@3 < 1996-04-01, projection=[l_suppkey@0, l_extendedprice@1, l_discount@2]+21)------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_suppkey, l_extendedprice, l_discount, l_shipdate], file_type=csv, has_header=falsediff --git a/datafusion/sqllogictest/test_files/tpch/plans/q16.slt.part b/datafusion/sqllogictest/test_files/tpch/plans/q16.slt.partindex 0537f7e5f3..d697d8e34c 100644--- a/datafusion/sqllogictest/test_files/tpch/plans/q16.slt.part+++ b/datafusion/sqllogictest/test_files/tpch/plans/q16.slt.part@@ -69,27 +69,21 @@ physical_plan02)--SortExec: TopK(fetch=10), expr=[supplier_cnt@3 DESC, p_brand@0 ASC NULLS LAST, p_type@1 ASC NULLS LAST, p_size@2 ASC NULLS LAST], preserve_partitioning=[true]03)----ProjectionExec: expr=[p_brand@0 as p_brand, p_type@1 as p_type, p_size@2 as p_size, count(alias1)@3 as supplier_cnt]04)------AggregateExec: mode=FinalPartitioned, gby=[p_brand@0 as p_brand, p_type@1 as p_type, p_size@2 as p_size], aggr=[count(alias1)]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([p_brand@0, p_type@1, p_size@2], 4), input_partitions=4-07)------------AggregateExec: mode=Partial, gby=[p_brand@0 as p_brand, p_type@1 as p_type, p_size@2 as p_size], aggr=[count(alias1)]-08)--------------AggregateExec: mode=FinalPartitioned, gby=[p_brand@0 as p_brand, p_type@1 as p_type, p_size@2 as p_size, alias1@3 as alias1], aggr=[]-09)----------------CoalesceBatchesExec: target_batch_size=8192-10)------------------RepartitionExec: partitioning=Hash([p_brand@0, p_type@1, p_size@2, alias1@3], 4), input_partitions=4-11)--------------------AggregateExec: mode=Partial, gby=[p_brand@1 as p_brand, p_type@2 as p_type, p_size@3 as p_size, ps_suppkey@0 as alias1], aggr=[]-12)----------------------HashJoinExec: mode=Partitioned, join_type=LeftAnti, on=[(ps_suppkey@0, s_suppkey@0)]-13)------------------------CoalesceBatchesExec: target_batch_size=8192-14)--------------------------RepartitionExec: partitioning=Hash([ps_suppkey@0], 4), input_partitions=4-15)----------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(ps_partkey@0, p_partkey@0)], projection=[ps_suppkey@1, p_brand@3, p_type@4, p_size@5]-16)------------------------------CoalesceBatchesExec: target_batch_size=8192-17)--------------------------------RepartitionExec: partitioning=Hash([ps_partkey@0], 4), input_partitions=4-18)----------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:0..2932049], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:2932049..5864098], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:5864098..8796147], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:8796147..11728193]]}, projection=[ps_partkey, ps_suppkey], file_type=csv, has_header=false-19)------------------------------CoalesceBatchesExec: target_batch_size=8192-20)--------------------------------RepartitionExec: partitioning=Hash([p_partkey@0], 4), input_partitions=4-21)----------------------------------FilterExec: p_brand@1 != Brand#45 AND p_type@2 NOT LIKE MEDIUM POLISHED% AND p_size@3 IN (SET) ([49, 14, 23, 45, 19, 3, 36, 9])-22)------------------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-23)--------------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/part.tbl]]}, projection=[p_partkey, p_brand, p_type, p_size], file_type=csv, has_header=false-24)------------------------CoalesceBatchesExec: target_batch_size=8192-25)--------------------------RepartitionExec: partitioning=Hash([s_suppkey@0], 4), input_partitions=4-26)----------------------------FilterExec: s_comment@1 LIKE %Customer%Complaints%, projection=[s_suppkey@0]-27)------------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-28)--------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_comment], file_type=csv, has_header=false+05)--------RepartitionExec: partitioning=Hash([p_brand@0, p_type@1, p_size@2], 4), input_partitions=4+06)----------AggregateExec: mode=Partial, gby=[p_brand@0 as p_brand, p_type@1 as p_type, p_size@2 as p_size], aggr=[count(alias1)]+07)------------AggregateExec: mode=FinalPartitioned, gby=[p_brand@0 as p_brand, p_type@1 as p_type, p_size@2 as p_size, alias1@3 as alias1], aggr=[]+08)--------------RepartitionExec: partitioning=Hash([p_brand@0, p_type@1, p_size@2, alias1@3], 4), input_partitions=4+09)----------------AggregateExec: mode=Partial, gby=[p_brand@1 as p_brand, p_type@2 as p_type, p_size@3 as p_size, ps_suppkey@0 as alias1], aggr=[]+10)------------------HashJoinExec: mode=Partitioned, join_type=LeftAnti, on=[(ps_suppkey@0, s_suppkey@0)]+11)--------------------RepartitionExec: partitioning=Hash([ps_suppkey@0], 4), input_partitions=4+12)----------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(ps_partkey@0, p_partkey@0)], projection=[ps_suppkey@1, p_brand@3, p_type@4, p_size@5]+13)------------------------RepartitionExec: partitioning=Hash([ps_partkey@0], 4), input_partitions=4+14)--------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:0..2932049], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:2932049..5864098], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:5864098..8796147], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:8796147..11728193]]}, projection=[ps_partkey, ps_suppkey], file_type=csv, has_header=false+15)------------------------RepartitionExec: partitioning=Hash([p_partkey@0], 4), input_partitions=4+16)--------------------------FilterExec: p_brand@1 != Brand#45 AND p_type@2 NOT LIKE MEDIUM POLISHED% AND p_size@3 IN (SET) ([49, 14, 23, 45, 19, 3, 36, 9])+17)----------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+18)------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/part.tbl]]}, projection=[p_partkey, p_brand, p_type, p_size], file_type=csv, has_header=false+19)--------------------RepartitionExec: partitioning=Hash([s_suppkey@0], 4), input_partitions=4+20)----------------------FilterExec: s_comment@1 LIKE %Customer%Complaints%, projection=[s_suppkey@0]+21)------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+22)--------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_comment], file_type=csv, has_header=falsediff --git a/datafusion/sqllogictest/test_files/tpch/plans/q17.slt.part b/datafusion/sqllogictest/test_files/tpch/plans/q17.slt.partindex 433082c554..83294d61a1 100644--- a/datafusion/sqllogictest/test_files/tpch/plans/q17.slt.part+++ b/datafusion/sqllogictest/test_files/tpch/plans/q17.slt.part@@ -57,17 +57,14 @@ physical_plan04)------AggregateExec: mode=Partial, gby=[], aggr=[sum(lineitem.l_extendedprice)]05)--------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(p_partkey@2, l_partkey@1)], filter=CAST(l_quantity@0 AS Decimal128(30, 15)) < Float64(0.2) * avg(lineitem.l_quantity)@1, projection=[l_extendedprice@1]06)----------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_partkey@0, p_partkey@0)], projection=[l_quantity@1, l_extendedprice@2, p_partkey@3]-07)------------CoalesceBatchesExec: target_batch_size=8192-08)--------------RepartitionExec: partitioning=Hash([l_partkey@0], 4), input_partitions=4-09)----------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_partkey, l_quantity, l_extendedprice], file_type=csv, has_header=false-10)------------CoalesceBatchesExec: target_batch_size=8192-11)--------------RepartitionExec: partitioning=Hash([p_partkey@0], 4), input_partitions=4-12)----------------FilterExec: p_brand@1 = Brand#23 AND p_container@2 = MED BOX, projection=[p_partkey@0]-13)------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-14)--------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/part.tbl]]}, projection=[p_partkey, p_brand, p_container], file_type=csv, has_header=false-15)----------ProjectionExec: expr=[CAST(0.2 * CAST(avg(lineitem.l_quantity)@1 AS Float64) AS Decimal128(30, 15)) as Float64(0.2) * avg(lineitem.l_quantity), l_partkey@0 as l_partkey]-16)------------AggregateExec: mode=FinalPartitioned, gby=[l_partkey@0 as l_partkey], aggr=[avg(lineitem.l_quantity)]-17)--------------CoalesceBatchesExec: target_batch_size=8192-18)----------------RepartitionExec: partitioning=Hash([l_partkey@0], 4), input_partitions=4-19)------------------AggregateExec: mode=Partial, gby=[l_partkey@0 as l_partkey], aggr=[avg(lineitem.l_quantity)]-20)--------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_partkey, l_quantity], file_type=csv, has_header=false+07)------------RepartitionExec: partitioning=Hash([l_partkey@0], 4), input_partitions=4+08)--------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_partkey, l_quantity, l_extendedprice], file_type=csv, has_header=false+09)------------RepartitionExec: partitioning=Hash([p_partkey@0], 4), input_partitions=4+10)--------------FilterExec: p_brand@1 = Brand#23 AND p_container@2 = MED BOX, projection=[p_partkey@0]+11)----------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+12)------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/part.tbl]]}, projection=[p_partkey, p_brand, p_container], file_type=csv, has_header=false+13)----------ProjectionExec: expr=[CAST(0.2 * CAST(avg(lineitem.l_quantity)@1 AS Float64) AS Decimal128(30, 15)) as Float64(0.2) * avg(lineitem.l_quantity), l_partkey@0 as l_partkey]+14)------------AggregateExec: mode=FinalPartitioned, gby=[l_partkey@0 as l_partkey], aggr=[avg(lineitem.l_quantity)]+15)--------------RepartitionExec: partitioning=Hash([l_partkey@0], 4), input_partitions=4+16)----------------AggregateExec: mode=Partial, gby=[l_partkey@0 as l_partkey], aggr=[avg(lineitem.l_quantity)]+17)------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_partkey, l_quantity], file_type=csv, has_header=falsediff --git a/datafusion/sqllogictest/test_files/tpch/plans/q18.slt.part b/datafusion/sqllogictest/test_files/tpch/plans/q18.slt.partindex 39f06a8f45..358a97462e 100644--- a/datafusion/sqllogictest/test_files/tpch/plans/q18.slt.part+++ b/datafusion/sqllogictest/test_files/tpch/plans/q18.slt.part@@ -70,26 +70,20 @@ physical_plan01)SortPreservingMergeExec: [o_totalprice@4 DESC, o_orderdate@3 ASC NULLS LAST]02)--SortExec: expr=[o_totalprice@4 DESC, o_orderdate@3 ASC NULLS LAST], preserve_partitioning=[true]03)----AggregateExec: mode=FinalPartitioned, gby=[c_name@0 as c_name, c_custkey@1 as c_custkey, o_orderkey@2 as o_orderkey, o_orderdate@3 as o_orderdate, o_totalprice@4 as o_totalprice], aggr=[sum(lineitem.l_quantity)]-04)------CoalesceBatchesExec: target_batch_size=8192-05)--------RepartitionExec: partitioning=Hash([c_name@0, c_custkey@1, o_orderkey@2, o_orderdate@3, o_totalprice@4], 4), input_partitions=4-06)----------AggregateExec: mode=Partial, gby=[c_name@1 as c_name, c_custkey@0 as c_custkey, o_orderkey@2 as o_orderkey, o_orderdate@4 as o_orderdate, o_totalprice@3 as o_totalprice], aggr=[sum(lineitem.l_quantity)]-07)------------HashJoinExec: mode=Partitioned, join_type=LeftSemi, on=[(o_orderkey@2, l_orderkey@0)]-08)--------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(o_orderkey@2, l_orderkey@0)], projection=[c_custkey@0, c_name@1, o_orderkey@2, o_totalprice@3, o_orderdate@4, l_quantity@6]-09)----------------CoalesceBatchesExec: target_batch_size=8192-10)------------------RepartitionExec: partitioning=Hash([o_orderkey@2], 4), input_partitions=4-11)--------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(c_custkey@0, o_custkey@1)], projection=[c_custkey@0, c_name@1, o_orderkey@2, o_totalprice@4, o_orderdate@5]-12)----------------------CoalesceBatchesExec: target_batch_size=8192-13)------------------------RepartitionExec: partitioning=Hash([c_custkey@0], 4), input_partitions=1-14)--------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/customer.tbl]]}, projection=[c_custkey, c_name], file_type=csv, has_header=false-15)----------------------CoalesceBatchesExec: target_batch_size=8192-16)------------------------RepartitionExec: partitioning=Hash([o_custkey@1], 4), input_partitions=4-17)--------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_orderkey, o_custkey, o_totalprice, o_orderdate], file_type=csv, has_header=false-18)----------------CoalesceBatchesExec: target_batch_size=8192-19)------------------RepartitionExec: partitioning=Hash([l_orderkey@0], 4), input_partitions=4+04)------RepartitionExec: partitioning=Hash([c_name@0, c_custkey@1, o_orderkey@2, o_orderdate@3, o_totalprice@4], 4), input_partitions=4+05)--------AggregateExec: mode=Partial, gby=[c_name@1 as c_name, c_custkey@0 as c_custkey, o_orderkey@2 as o_orderkey, o_orderdate@4 as o_orderdate, o_totalprice@3 as o_totalprice], aggr=[sum(lineitem.l_quantity)]+06)----------HashJoinExec: mode=Partitioned, join_type=LeftSemi, on=[(o_orderkey@2, l_orderkey@0)]+07)------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(o_orderkey@2, l_orderkey@0)], projection=[c_custkey@0, c_name@1, o_orderkey@2, o_totalprice@3, o_orderdate@4, l_quantity@6]+08)--------------RepartitionExec: partitioning=Hash([o_orderkey@2], 4), input_partitions=4+09)----------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(c_custkey@0, o_custkey@1)], projection=[c_custkey@0, c_name@1, o_orderkey@2, o_totalprice@4, o_orderdate@5]+10)------------------RepartitionExec: partitioning=Hash([c_custkey@0], 4), input_partitions=1+11)--------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/customer.tbl]]}, projection=[c_custkey, c_name], file_type=csv, has_header=false+12)------------------RepartitionExec: partitioning=Hash([o_custkey@1], 4), input_partitions=4+13)--------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_orderkey, o_custkey, o_totalprice, o_orderdate], file_type=csv, has_header=false+14)--------------RepartitionExec: partitioning=Hash([l_orderkey@0], 4), input_partitions=4+15)----------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_quantity], file_type=csv, has_header=false+16)------------FilterExec: sum(lineitem.l_quantity)@1 > Some(30000),25,2, projection=[l_orderkey@0]+17)--------------AggregateExec: mode=FinalPartitioned, gby=[l_orderkey@0 as l_orderkey], aggr=[sum(lineitem.l_quantity)]+18)----------------RepartitionExec: partitioning=Hash([l_orderkey@0], 4), input_partitions=4+19)------------------AggregateExec: mode=Partial, gby=[l_orderkey@0 as l_orderkey], aggr=[sum(lineitem.l_quantity)]20)--------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_quantity], file_type=csv, has_header=false-21)--------------FilterExec: sum(lineitem.l_quantity)@1 > Some(30000),25,2, projection=[l_orderkey@0]-22)----------------AggregateExec: mode=FinalPartitioned, gby=[l_orderkey@0 as l_orderkey], aggr=[sum(lineitem.l_quantity)]-23)------------------CoalesceBatchesExec: target_batch_size=8192-24)--------------------RepartitionExec: partitioning=Hash([l_orderkey@0], 4), input_partitions=4-25)----------------------AggregateExec: mode=Partial, gby=[l_orderkey@0 as l_orderkey], aggr=[sum(lineitem.l_quantity)]-26)------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_quantity], file_type=csv, has_header=falsediff --git a/datafusion/sqllogictest/test_files/tpch/plans/q19.slt.part b/datafusion/sqllogictest/test_files/tpch/plans/q19.slt.partindex 93b9294245..72c21e060f 100644--- a/datafusion/sqllogictest/test_files/tpch/plans/q19.slt.part+++ b/datafusion/sqllogictest/test_files/tpch/plans/q19.slt.part@@ -69,12 +69,10 @@ physical_plan03)----CoalescePartitionsExec04)------AggregateExec: mode=Partial, gby=[], aggr=[sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)]05)--------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_partkey@0, p_partkey@0)], filter=p_brand@1 = Brand#12 AND p_container@3 IN (SET) ([SM CASE, SM BOX, SM PACK, SM PKG]) AND l_quantity@0 >= Some(100),15,2 AND l_quantity@0 <= Some(1100),15,2 AND p_size@2 <= 5 OR p_brand@1 = Brand#23 AND p_container@3 IN (SET) ([MED BAG, MED BOX, MED PKG, MED PACK]) AND l_quantity@0 >= Some(1000),15,2 AND l_quantity@0 <= Some(2000),15,2 AND p_size@2 <= 10 OR p_brand@1 = Brand#34 AND p_container@3 IN (SET) ([LG CASE, LG BOX, LG PACK, LG PKG]) AND l_quantity@0 >= Some(2000),15,2 AND l_quantity@0 <= Some(3000),15,2 AND p_size@2 <= 15, projection=[l_extendedprice@2, l_discount@3]-06)----------CoalesceBatchesExec: target_batch_size=8192-07)------------RepartitionExec: partitioning=Hash([l_partkey@0], 4), input_partitions=4-08)--------------FilterExec: (l_quantity@1 >= Some(100),15,2 AND l_quantity@1 <= Some(1100),15,2 OR l_quantity@1 >= Some(1000),15,2 AND l_quantity@1 <= Some(2000),15,2 OR l_quantity@1 >= Some(2000),15,2 AND l_quantity@1 <= Some(3000),15,2) AND (l_shipmode@5 = AIR OR l_shipmode@5 = AIR REG) AND l_shipinstruct@4 = DELIVER IN PERSON, projection=[l_partkey@0, l_quantity@1, l_extendedprice@2, l_discount@3]-09)----------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_partkey, l_quantity, l_extendedprice, l_discount, l_shipinstruct, l_shipmode], file_type=csv, has_header=false-10)----------CoalesceBatchesExec: target_batch_size=8192-11)------------RepartitionExec: partitioning=Hash([p_partkey@0], 4), input_partitions=4-12)--------------FilterExec: (p_brand@1 = Brand#12 AND p_container@3 IN (SET) ([SM CASE, SM BOX, SM PACK, SM PKG]) AND p_size@2 <= 5 OR p_brand@1 = Brand#23 AND p_container@3 IN (SET) ([MED BAG, MED BOX, MED PKG, MED PACK]) AND p_size@2 <= 10 OR p_brand@1 = Brand#34 AND p_container@3 IN (SET) ([LG CASE, LG BOX, LG PACK, LG PKG]) AND p_size@2 <= 15) AND p_size@2 >= 1-13)----------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-14)------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/part.tbl]]}, projection=[p_partkey, p_brand, p_size, p_container], file_type=csv, has_header=false+06)----------RepartitionExec: partitioning=Hash([l_partkey@0], 4), input_partitions=4+07)------------FilterExec: (l_quantity@1 >= Some(100),15,2 AND l_quantity@1 <= Some(1100),15,2 OR l_quantity@1 >= Some(1000),15,2 AND l_quantity@1 <= Some(2000),15,2 OR l_quantity@1 >= Some(2000),15,2 AND l_quantity@1 <= Some(3000),15,2) AND (l_shipmode@5 = AIR OR l_shipmode@5 = AIR REG) AND l_shipinstruct@4 = DELIVER IN PERSON, projection=[l_partkey@0, l_quantity@1, l_extendedprice@2, l_discount@3]+08)--------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_partkey, l_quantity, l_extendedprice, l_discount, l_shipinstruct, l_shipmode], file_type=csv, has_header=false+09)----------RepartitionExec: partitioning=Hash([p_partkey@0], 4), input_partitions=4+10)------------FilterExec: (p_brand@1 = Brand#12 AND p_container@3 IN (SET) ([SM CASE, SM BOX, SM PACK, SM PKG]) AND p_size@2 <= 5 OR p_brand@1 = Brand#23 AND p_container@3 IN (SET) ([MED BAG, MED BOX, MED PKG, MED PACK]) AND p_size@2 <= 10 OR p_brand@1 = Brand#34 AND p_container@3 IN (SET) ([LG CASE, LG BOX, LG PACK, LG PKG]) AND p_size@2 <= 15) AND p_size@2 >= 1+11)--------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+12)----------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/part.tbl]]}, projection=[p_partkey, p_brand, p_size, p_container], file_type=csv, has_header=falsediff --git a/datafusion/sqllogictest/test_files/tpch/plans/q2.slt.part b/datafusion/sqllogictest/test_files/tpch/plans/q2.slt.partindex 552837f890..d5ff672440 100644--- a/datafusion/sqllogictest/test_files/tpch/plans/q2.slt.part+++ b/datafusion/sqllogictest/test_files/tpch/plans/q2.slt.part@@ -103,63 +103,46 @@ physical_plan02)--SortExec: TopK(fetch=10), expr=[s_acctbal@0 DESC, n_name@2 ASC NULLS LAST, s_name@1 ASC NULLS LAST, p_partkey@3 ASC NULLS LAST], preserve_partitioning=[true]03)----ProjectionExec: expr=[s_acctbal@5 as s_acctbal, s_name@2 as s_name, n_name@7 as n_name, p_partkey@0 as p_partkey, p_mfgr@1 as p_mfgr, s_address@3 as s_address, s_phone@4 as s_phone, s_comment@6 as s_comment]04)------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(p_partkey@0, ps_partkey@1), (ps_supplycost@7, min(partsupp.ps_supplycost)@0)], projection=[p_partkey@0, p_mfgr@1, s_name@2, s_address@3, s_phone@4, s_acctbal@5, s_comment@6, n_name@8]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([p_partkey@0, ps_supplycost@7], 4), input_partitions=4-07)------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(n_regionkey@9, r_regionkey@0)], projection=[p_partkey@0, p_mfgr@1, s_name@2, s_address@3, s_phone@4, s_acctbal@5, s_comment@6, ps_supplycost@7, n_name@8]-08)--------------CoalesceBatchesExec: target_batch_size=8192-09)----------------RepartitionExec: partitioning=Hash([n_regionkey@9], 4), input_partitions=4-10)------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_nationkey@4, n_nationkey@0)], projection=[p_partkey@0, p_mfgr@1, s_name@2, s_address@3, s_phone@5, s_acctbal@6, s_comment@7, ps_supplycost@8, n_name@10, n_regionkey@11]-11)--------------------CoalesceBatchesExec: target_batch_size=8192-12)----------------------RepartitionExec: partitioning=Hash([s_nationkey@4], 4), input_partitions=4-13)------------------------ProjectionExec: expr=[p_partkey@0 as p_partkey, p_mfgr@1 as p_mfgr, s_name@3 as s_name, s_address@4 as s_address, s_nationkey@5 as s_nationkey, s_phone@6 as s_phone, s_acctbal@7 as s_acctbal, s_comment@8 as s_comment, ps_supplycost@2 as ps_supplycost]-14)--------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(ps_suppkey@2, s_suppkey@0)], projection=[p_partkey@0, p_mfgr@1, ps_supplycost@3, s_name@5, s_address@6, s_nationkey@7, s_phone@8, s_acctbal@9, s_comment@10]-15)----------------------------CoalesceBatchesExec: target_batch_size=8192-16)------------------------------RepartitionExec: partitioning=Hash([ps_suppkey@2], 4), input_partitions=4-17)--------------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(p_partkey@0, ps_partkey@0)], projection=[p_partkey@0, p_mfgr@1, ps_suppkey@3, ps_supplycost@4]-18)----------------------------------CoalesceBatchesExec: target_batch_size=8192-19)------------------------------------RepartitionExec: partitioning=Hash([p_partkey@0], 4), input_partitions=4-20)--------------------------------------FilterExec: p_size@3 = 15 AND p_type@2 LIKE %BRASS, projection=[p_partkey@0, p_mfgr@1]-21)----------------------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-22)------------------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/part.tbl]]}, projection=[p_partkey, p_mfgr, p_type, p_size], file_type=csv, has_header=false-23)----------------------------------CoalesceBatchesExec: target_batch_size=8192-24)------------------------------------RepartitionExec: partitioning=Hash([ps_partkey@0], 4), input_partitions=4-25)--------------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:0..2932049], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:2932049..5864098], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:5864098..8796147], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:8796147..11728193]]}, projection=[ps_partkey, ps_suppkey, ps_supplycost], file_type=csv, has_header=false-26)----------------------------CoalesceBatchesExec: target_batch_size=8192-27)------------------------------RepartitionExec: partitioning=Hash([s_suppkey@0], 4), input_partitions=1-28)--------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_name, s_address, s_nationkey, s_phone, s_acctbal, s_comment], file_type=csv, has_header=false-29)--------------------CoalesceBatchesExec: target_batch_size=8192-30)----------------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=1-31)------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_name, n_regionkey], file_type=csv, has_header=false-32)--------------CoalesceBatchesExec: target_batch_size=8192-33)----------------RepartitionExec: partitioning=Hash([r_regionkey@0], 4), input_partitions=4-34)------------------FilterExec: r_name@1 = EUROPE, projection=[r_regionkey@0]-35)--------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-36)----------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/region.tbl]]}, projection=[r_regionkey, r_name], file_type=csv, has_header=false-37)--------CoalesceBatchesExec: target_batch_size=8192-38)----------RepartitionExec: partitioning=Hash([ps_partkey@1, min(partsupp.ps_supplycost)@0], 4), input_partitions=4-39)------------ProjectionExec: expr=[min(partsupp.ps_supplycost)@1 as min(partsupp.ps_supplycost), ps_partkey@0 as ps_partkey]-40)--------------AggregateExec: mode=FinalPartitioned, gby=[ps_partkey@0 as ps_partkey], aggr=[min(partsupp.ps_supplycost)]-41)----------------CoalesceBatchesExec: target_batch_size=8192-42)------------------RepartitionExec: partitioning=Hash([ps_partkey@0], 4), input_partitions=4-43)--------------------AggregateExec: mode=Partial, gby=[ps_partkey@0 as ps_partkey], aggr=[min(partsupp.ps_supplycost)]-44)----------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(n_regionkey@2, r_regionkey@0)], projection=[ps_partkey@0, ps_supplycost@1]-45)------------------------CoalesceBatchesExec: target_batch_size=8192-46)--------------------------RepartitionExec: partitioning=Hash([n_regionkey@2], 4), input_partitions=4-47)----------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_nationkey@2, n_nationkey@0)], projection=[ps_partkey@0, ps_supplycost@1, n_regionkey@4]-48)------------------------------CoalesceBatchesExec: target_batch_size=8192-49)--------------------------------RepartitionExec: partitioning=Hash([s_nationkey@2], 4), input_partitions=4-50)----------------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(ps_suppkey@1, s_suppkey@0)], projection=[ps_partkey@0, ps_supplycost@2, s_nationkey@4]-51)------------------------------------CoalesceBatchesExec: target_batch_size=8192-52)--------------------------------------RepartitionExec: partitioning=Hash([ps_suppkey@1], 4), input_partitions=4-53)----------------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:0..2932049], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:2932049..5864098], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:5864098..8796147], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:8796147..11728193]]}, projection=[ps_partkey, ps_suppkey, ps_supplycost], file_type=csv, has_header=false-54)------------------------------------CoalesceBatchesExec: target_batch_size=8192-55)--------------------------------------RepartitionExec: partitioning=Hash([s_suppkey@0], 4), input_partitions=1-56)----------------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_nationkey], file_type=csv, has_header=false-57)------------------------------CoalesceBatchesExec: target_batch_size=8192-58)--------------------------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=1-59)----------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_regionkey], file_type=csv, has_header=false-60)------------------------CoalesceBatchesExec: target_batch_size=8192-61)--------------------------RepartitionExec: partitioning=Hash([r_regionkey@0], 4), input_partitions=4-62)----------------------------FilterExec: r_name@1 = EUROPE, projection=[r_regionkey@0]-63)------------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-64)--------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/region.tbl]]}, projection=[r_regionkey, r_name], file_type=csv, has_header=false+05)--------RepartitionExec: partitioning=Hash([p_partkey@0, ps_supplycost@7], 4), input_partitions=4+06)----------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(n_regionkey@9, r_regionkey@0)], projection=[p_partkey@0, p_mfgr@1, s_name@2, s_address@3, s_phone@4, s_acctbal@5, s_comment@6, ps_supplycost@7, n_name@8]+07)------------RepartitionExec: partitioning=Hash([n_regionkey@9], 4), input_partitions=4+08)--------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_nationkey@4, n_nationkey@0)], projection=[p_partkey@0, p_mfgr@1, s_name@2, s_address@3, s_phone@5, s_acctbal@6, s_comment@7, ps_supplycost@8, n_name@10, n_regionkey@11]+09)----------------RepartitionExec: partitioning=Hash([s_nationkey@4], 4), input_partitions=4+10)------------------ProjectionExec: expr=[p_partkey@0 as p_partkey, p_mfgr@1 as p_mfgr, s_name@3 as s_name, s_address@4 as s_address, s_nationkey@5 as s_nationkey, s_phone@6 as s_phone, s_acctbal@7 as s_acctbal, s_comment@8 as s_comment, ps_supplycost@2 as ps_supplycost]+11)--------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(ps_suppkey@2, s_suppkey@0)], projection=[p_partkey@0, p_mfgr@1, ps_supplycost@3, s_name@5, s_address@6, s_nationkey@7, s_phone@8, s_acctbal@9, s_comment@10]+12)----------------------RepartitionExec: partitioning=Hash([ps_suppkey@2], 4), input_partitions=4+13)------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(p_partkey@0, ps_partkey@0)], projection=[p_partkey@0, p_mfgr@1, ps_suppkey@3, ps_supplycost@4]+14)--------------------------RepartitionExec: partitioning=Hash([p_partkey@0], 4), input_partitions=4+15)----------------------------FilterExec: p_size@3 = 15 AND p_type@2 LIKE %BRASS, projection=[p_partkey@0, p_mfgr@1]+16)------------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+17)--------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/part.tbl]]}, projection=[p_partkey, p_mfgr, p_type, p_size], file_type=csv, has_header=false+18)--------------------------RepartitionExec: partitioning=Hash([ps_partkey@0], 4), input_partitions=4+19)----------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:0..2932049], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:2932049..5864098], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:5864098..8796147], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:8796147..11728193]]}, projection=[ps_partkey, ps_suppkey, ps_supplycost], file_type=csv, has_header=false+20)----------------------RepartitionExec: partitioning=Hash([s_suppkey@0], 4), input_partitions=1+21)------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_name, s_address, s_nationkey, s_phone, s_acctbal, s_comment], file_type=csv, has_header=false+22)----------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=1+23)------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_name, n_regionkey], file_type=csv, has_header=false+24)------------RepartitionExec: partitioning=Hash([r_regionkey@0], 4), input_partitions=4+25)--------------FilterExec: r_name@1 = EUROPE, projection=[r_regionkey@0]+26)----------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+27)------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/region.tbl]]}, projection=[r_regionkey, r_name], file_type=csv, has_header=false+28)--------RepartitionExec: partitioning=Hash([ps_partkey@1, min(partsupp.ps_supplycost)@0], 4), input_partitions=4+29)----------ProjectionExec: expr=[min(partsupp.ps_supplycost)@1 as min(partsupp.ps_supplycost), ps_partkey@0 as ps_partkey]+30)------------AggregateExec: mode=FinalPartitioned, gby=[ps_partkey@0 as ps_partkey], aggr=[min(partsupp.ps_supplycost)]+31)--------------RepartitionExec: partitioning=Hash([ps_partkey@0], 4), input_partitions=4+32)----------------AggregateExec: mode=Partial, gby=[ps_partkey@0 as ps_partkey], aggr=[min(partsupp.ps_supplycost)]+33)------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(n_regionkey@2, r_regionkey@0)], projection=[ps_partkey@0, ps_supplycost@1]+34)--------------------RepartitionExec: partitioning=Hash([n_regionkey@2], 4), input_partitions=4+35)----------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_nationkey@2, n_nationkey@0)], projection=[ps_partkey@0, ps_supplycost@1, n_regionkey@4]+36)------------------------RepartitionExec: partitioning=Hash([s_nationkey@2], 4), input_partitions=4+37)--------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(ps_suppkey@1, s_suppkey@0)], projection=[ps_partkey@0, ps_supplycost@2, s_nationkey@4]+38)----------------------------RepartitionExec: partitioning=Hash([ps_suppkey@1], 4), input_partitions=4+39)------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:0..2932049], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:2932049..5864098], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:5864098..8796147], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:8796147..11728193]]}, projection=[ps_partkey, ps_suppkey, ps_supplycost], file_type=csv, has_header=false+40)----------------------------RepartitionExec: partitioning=Hash([s_suppkey@0], 4), input_partitions=1+41)------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_nationkey], file_type=csv, has_header=false+42)------------------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=1+43)--------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_regionkey], file_type=csv, has_header=false+44)--------------------RepartitionExec: partitioning=Hash([r_regionkey@0], 4), input_partitions=4+45)----------------------FilterExec: r_name@1 = EUROPE, projection=[r_regionkey@0]+46)------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+47)--------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/region.tbl]]}, projection=[r_regionkey, r_name], file_type=csv, has_header=falsediff --git a/datafusion/sqllogictest/test_files/tpch/plans/q20.slt.part b/datafusion/sqllogictest/test_files/tpch/plans/q20.slt.partindex 68ea776173..426a1cbaa4 100644--- a/datafusion/sqllogictest/test_files/tpch/plans/q20.slt.part+++ b/datafusion/sqllogictest/test_files/tpch/plans/q20.slt.part@@ -84,35 +84,27 @@ physical_plan01)SortPreservingMergeExec: [s_name@0 ASC NULLS LAST]02)--SortExec: expr=[s_name@0 ASC NULLS LAST], preserve_partitioning=[true]03)----HashJoinExec: mode=Partitioned, join_type=LeftSemi, on=[(s_suppkey@0, ps_suppkey@0)], projection=[s_name@1, s_address@2]-04)------CoalesceBatchesExec: target_batch_size=8192-05)--------RepartitionExec: partitioning=Hash([s_suppkey@0], 4), input_partitions=4-06)----------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_nationkey@3, n_nationkey@0)], projection=[s_suppkey@0, s_name@1, s_address@2]-07)------------CoalesceBatchesExec: target_batch_size=8192-08)--------------RepartitionExec: partitioning=Hash([s_nationkey@3], 4), input_partitions=1-09)----------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_name, s_address, s_nationkey], file_type=csv, has_header=false-10)------------CoalesceBatchesExec: target_batch_size=8192-11)--------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=4-12)----------------FilterExec: n_name@1 = CANADA, projection=[n_nationkey@0]-13)------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-14)--------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_name], file_type=csv, has_header=false-15)------CoalesceBatchesExec: target_batch_size=8192-16)--------RepartitionExec: partitioning=Hash([ps_suppkey@0], 4), input_partitions=4-17)----------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(ps_partkey@0, l_partkey@1), (ps_suppkey@1, l_suppkey@2)], filter=CAST(ps_availqty@0 AS Float64) > Float64(0.5) * sum(lineitem.l_quantity)@1, projection=[ps_suppkey@1]-18)------------CoalesceBatchesExec: target_batch_size=8192-19)--------------RepartitionExec: partitioning=Hash([ps_partkey@0, ps_suppkey@1], 4), input_partitions=4-20)----------------HashJoinExec: mode=Partitioned, join_type=LeftSemi, on=[(ps_partkey@0, p_partkey@0)]-21)------------------CoalesceBatchesExec: target_batch_size=8192-22)--------------------RepartitionExec: partitioning=Hash([ps_partkey@0], 4), input_partitions=4-23)----------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:0..2932049], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:2932049..5864098], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:5864098..8796147], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:8796147..11728193]]}, projection=[ps_partkey, ps_suppkey, ps_availqty], file_type=csv, has_header=false-24)------------------CoalesceBatchesExec: target_batch_size=8192-25)--------------------RepartitionExec: partitioning=Hash([p_partkey@0], 4), input_partitions=4-26)----------------------FilterExec: p_name@1 LIKE forest%, projection=[p_partkey@0]-27)------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-28)--------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/part.tbl]]}, projection=[p_partkey, p_name], file_type=csv, has_header=false-29)------------ProjectionExec: expr=[0.5 * CAST(sum(lineitem.l_quantity)@2 AS Float64) as Float64(0.5) * sum(lineitem.l_quantity), l_partkey@0 as l_partkey, l_suppkey@1 as l_suppkey]-30)--------------AggregateExec: mode=FinalPartitioned, gby=[l_partkey@0 as l_partkey, l_suppkey@1 as l_suppkey], aggr=[sum(lineitem.l_quantity)]-31)----------------CoalesceBatchesExec: target_batch_size=8192-32)------------------RepartitionExec: partitioning=Hash([l_partkey@0, l_suppkey@1], 4), input_partitions=4-33)--------------------AggregateExec: mode=Partial, gby=[l_partkey@0 as l_partkey, l_suppkey@1 as l_suppkey], aggr=[sum(lineitem.l_quantity)]-34)----------------------FilterExec: l_shipdate@3 >= 1994-01-01 AND l_shipdate@3 < 1995-01-01, projection=[l_partkey@0, l_suppkey@1, l_quantity@2]-35)------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_partkey, l_suppkey, l_quantity, l_shipdate], file_type=csv, has_header=false+04)------RepartitionExec: partitioning=Hash([s_suppkey@0], 4), input_partitions=4+05)--------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_nationkey@3, n_nationkey@0)], projection=[s_suppkey@0, s_name@1, s_address@2]+06)----------RepartitionExec: partitioning=Hash([s_nationkey@3], 4), input_partitions=1+07)------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_name, s_address, s_nationkey], file_type=csv, has_header=false+08)----------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=4+09)------------FilterExec: n_name@1 = CANADA, projection=[n_nationkey@0]+10)--------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+11)----------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_name], file_type=csv, has_header=false+12)------RepartitionExec: partitioning=Hash([ps_suppkey@0], 4), input_partitions=4+13)--------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(ps_partkey@0, l_partkey@1), (ps_suppkey@1, l_suppkey@2)], filter=CAST(ps_availqty@0 AS Float64) > Float64(0.5) * sum(lineitem.l_quantity)@1, projection=[ps_suppkey@1]+14)----------RepartitionExec: partitioning=Hash([ps_partkey@0, ps_suppkey@1], 4), input_partitions=4+15)------------HashJoinExec: mode=Partitioned, join_type=LeftSemi, on=[(ps_partkey@0, p_partkey@0)]+16)--------------RepartitionExec: partitioning=Hash([ps_partkey@0], 4), input_partitions=4+17)----------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:0..2932049], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:2932049..5864098], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:5864098..8796147], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:8796147..11728193]]}, projection=[ps_partkey, ps_suppkey, ps_availqty], file_type=csv, has_header=false+18)--------------RepartitionExec: partitioning=Hash([p_partkey@0], 4), input_partitions=4+19)----------------FilterExec: p_name@1 LIKE forest%, projection=[p_partkey@0]+20)------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+21)--------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/part.tbl]]}, projection=[p_partkey, p_name], file_type=csv, has_header=false+22)----------ProjectionExec: expr=[0.5 * CAST(sum(lineitem.l_quantity)@2 AS Float64) as Float64(0.5) * sum(lineitem.l_quantity), l_partkey@0 as l_partkey, l_suppkey@1 as l_suppkey]+23)------------AggregateExec: mode=FinalPartitioned, gby=[l_partkey@0 as l_partkey, l_suppkey@1 as l_suppkey], aggr=[sum(lineitem.l_quantity)]+24)--------------RepartitionExec: partitioning=Hash([l_partkey@0, l_suppkey@1], 4), input_partitions=4+25)----------------AggregateExec: mode=Partial, gby=[l_partkey@0 as l_partkey, l_suppkey@1 as l_suppkey], aggr=[sum(lineitem.l_quantity)]+26)------------------FilterExec: l_shipdate@3 >= 1994-01-01 AND l_shipdate@3 < 1995-01-01, projection=[l_partkey@0, l_suppkey@1, l_quantity@2]+27)--------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_partkey, l_suppkey, l_quantity, l_shipdate], file_type=csv, has_header=falsediff --git a/datafusion/sqllogictest/test_files/tpch/plans/q21.slt.part b/datafusion/sqllogictest/test_files/tpch/plans/q21.slt.partindex 254fbc7991..5e9192d677 100644--- a/datafusion/sqllogictest/test_files/tpch/plans/q21.slt.part+++ b/datafusion/sqllogictest/test_files/tpch/plans/q21.slt.part@@ -94,40 +94,30 @@ physical_plan02)--SortExec: expr=[numwait@1 DESC, s_name@0 ASC NULLS LAST], preserve_partitioning=[true]03)----ProjectionExec: expr=[s_name@0 as s_name, count(Int64(1))@1 as numwait]04)------AggregateExec: mode=FinalPartitioned, gby=[s_name@0 as s_name], aggr=[count(Int64(1))]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([s_name@0], 4), input_partitions=4-07)------------AggregateExec: mode=Partial, gby=[s_name@0 as s_name], aggr=[count(Int64(1))]-08)--------------HashJoinExec: mode=Partitioned, join_type=LeftAnti, on=[(l_orderkey@1, l_orderkey@0)], filter=l_suppkey@1 != l_suppkey@0, projection=[s_name@0]-09)----------------HashJoinExec: mode=Partitioned, join_type=LeftSemi, on=[(l_orderkey@1, l_orderkey@0)], filter=l_suppkey@1 != l_suppkey@0-10)------------------CoalesceBatchesExec: target_batch_size=8192-11)--------------------RepartitionExec: partitioning=Hash([l_orderkey@1], 4), input_partitions=4-12)----------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_nationkey@1, n_nationkey@0)], projection=[s_name@0, l_orderkey@2, l_suppkey@3]-13)------------------------CoalesceBatchesExec: target_batch_size=8192-14)--------------------------RepartitionExec: partitioning=Hash([s_nationkey@1], 4), input_partitions=4-15)----------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_orderkey@2, o_orderkey@0)], projection=[s_name@0, s_nationkey@1, l_orderkey@2, l_suppkey@3]-16)------------------------------CoalesceBatchesExec: target_batch_size=8192-17)--------------------------------RepartitionExec: partitioning=Hash([l_orderkey@2], 4), input_partitions=4-18)----------------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_suppkey@0, l_suppkey@1)], projection=[s_name@1, s_nationkey@2, l_orderkey@3, l_suppkey@4]-19)------------------------------------CoalesceBatchesExec: target_batch_size=8192-20)--------------------------------------RepartitionExec: partitioning=Hash([s_suppkey@0], 4), input_partitions=1-21)----------------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_name, s_nationkey], file_type=csv, has_header=false-22)------------------------------------CoalesceBatchesExec: target_batch_size=8192-23)--------------------------------------RepartitionExec: partitioning=Hash([l_suppkey@1], 4), input_partitions=4-24)----------------------------------------FilterExec: l_receiptdate@3 > l_commitdate@2, projection=[l_orderkey@0, l_suppkey@1]-25)------------------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_suppkey, l_commitdate, l_receiptdate], file_type=csv, has_header=false-26)------------------------------CoalesceBatchesExec: target_batch_size=8192-27)--------------------------------RepartitionExec: partitioning=Hash([o_orderkey@0], 4), input_partitions=4-28)----------------------------------FilterExec: o_orderstatus@1 = F, projection=[o_orderkey@0]-29)------------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_orderkey, o_orderstatus], file_type=csv, has_header=false-30)------------------------CoalesceBatchesExec: target_batch_size=8192-31)--------------------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=4-32)----------------------------FilterExec: n_name@1 = SAUDI ARABIA, projection=[n_nationkey@0]-33)------------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-34)--------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_name], file_type=csv, has_header=false-35)------------------CoalesceBatchesExec: target_batch_size=8192-36)--------------------RepartitionExec: partitioning=Hash([l_orderkey@0], 4), input_partitions=4-37)----------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_suppkey], file_type=csv, has_header=false-38)----------------CoalesceBatchesExec: target_batch_size=8192-39)------------------RepartitionExec: partitioning=Hash([l_orderkey@0], 4), input_partitions=4-40)--------------------FilterExec: l_receiptdate@3 > l_commitdate@2, projection=[l_orderkey@0, l_suppkey@1]-41)----------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_suppkey, l_commitdate, l_receiptdate], file_type=csv, has_header=false+05)--------RepartitionExec: partitioning=Hash([s_name@0], 4), input_partitions=4+06)----------AggregateExec: mode=Partial, gby=[s_name@0 as s_name], aggr=[count(Int64(1))]+07)------------HashJoinExec: mode=Partitioned, join_type=LeftAnti, on=[(l_orderkey@1, l_orderkey@0)], filter=l_suppkey@1 != l_suppkey@0, projection=[s_name@0]+08)--------------HashJoinExec: mode=Partitioned, join_type=LeftSemi, on=[(l_orderkey@1, l_orderkey@0)], filter=l_suppkey@1 != l_suppkey@0+09)----------------RepartitionExec: partitioning=Hash([l_orderkey@1], 4), input_partitions=4+10)------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_nationkey@1, n_nationkey@0)], projection=[s_name@0, l_orderkey@2, l_suppkey@3]+11)--------------------RepartitionExec: partitioning=Hash([s_nationkey@1], 4), input_partitions=4+12)----------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_orderkey@2, o_orderkey@0)], projection=[s_name@0, s_nationkey@1, l_orderkey@2, l_suppkey@3]+13)------------------------RepartitionExec: partitioning=Hash([l_orderkey@2], 4), input_partitions=4+14)--------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_suppkey@0, l_suppkey@1)], projection=[s_name@1, s_nationkey@2, l_orderkey@3, l_suppkey@4]+15)----------------------------RepartitionExec: partitioning=Hash([s_suppkey@0], 4), input_partitions=1+16)------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_name, s_nationkey], file_type=csv, has_header=false+17)----------------------------RepartitionExec: partitioning=Hash([l_suppkey@1], 4), input_partitions=4+18)------------------------------FilterExec: l_receiptdate@3 > l_commitdate@2, projection=[l_orderkey@0, l_suppkey@1]+19)--------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_suppkey, l_commitdate, l_receiptdate], file_type=csv, has_header=false+20)------------------------RepartitionExec: partitioning=Hash([o_orderkey@0], 4), input_partitions=4+21)--------------------------FilterExec: o_orderstatus@1 = F, projection=[o_orderkey@0]+22)----------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_orderkey, o_orderstatus], file_type=csv, has_header=false+23)--------------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=4+24)----------------------FilterExec: n_name@1 = SAUDI ARABIA, projection=[n_nationkey@0]+25)------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+26)--------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_name], file_type=csv, has_header=false+27)----------------RepartitionExec: partitioning=Hash([l_orderkey@0], 4), input_partitions=4+28)------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_suppkey], file_type=csv, has_header=false+29)--------------RepartitionExec: partitioning=Hash([l_orderkey@0], 4), input_partitions=4+30)----------------FilterExec: l_receiptdate@3 > l_commitdate@2, projection=[l_orderkey@0, l_suppkey@1]+31)------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_suppkey, l_commitdate, l_receiptdate], file_type=csv, has_header=falsediff --git a/datafusion/sqllogictest/test_files/tpch/plans/q22.slt.part b/datafusion/sqllogictest/test_files/tpch/plans/q22.slt.partindex ef227430f3..add578c3b0 100644--- a/datafusion/sqllogictest/test_files/tpch/plans/q22.slt.part+++ b/datafusion/sqllogictest/test_files/tpch/plans/q22.slt.part@@ -78,26 +78,23 @@ physical_plan02)--SortExec: expr=[cntrycode@0 ASC NULLS LAST], preserve_partitioning=[true]03)----ProjectionExec: expr=[cntrycode@0 as cntrycode, count(Int64(1))@1 as numcust, sum(custsale.c_acctbal)@2 as totacctbal]04)------AggregateExec: mode=FinalPartitioned, gby=[cntrycode@0 as cntrycode], aggr=[count(Int64(1)), sum(custsale.c_acctbal)]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([cntrycode@0], 4), input_partitions=4-07)------------AggregateExec: mode=Partial, gby=[cntrycode@0 as cntrycode], aggr=[count(Int64(1)), sum(custsale.c_acctbal)]-08)--------------ProjectionExec: expr=[substr(c_phone@0, 1, 2) as cntrycode, c_acctbal@1 as c_acctbal]-09)----------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-10)------------------NestedLoopJoinExec: join_type=Inner, filter=join_proj_push_down_1@1 > avg(customer.c_acctbal)@0, projection=[c_phone@0, c_acctbal@1, avg(customer.c_acctbal)@3]-11)--------------------ProjectionExec: expr=[c_phone@0 as c_phone, c_acctbal@1 as c_acctbal, CAST(c_acctbal@1 AS Decimal128(19, 6)) as join_proj_push_down_1]-12)----------------------CoalescePartitionsExec-13)------------------------HashJoinExec: mode=Partitioned, join_type=LeftAnti, on=[(c_custkey@0, o_custkey@0)], projection=[c_phone@1, c_acctbal@2]-14)--------------------------CoalesceBatchesExec: target_batch_size=8192-15)----------------------------RepartitionExec: partitioning=Hash([c_custkey@0], 4), input_partitions=4-16)------------------------------FilterExec: substr(c_phone@1, 1, 2) IN (SET) ([13, 31, 23, 29, 30, 18, 17])-17)--------------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-18)----------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/customer.tbl]]}, projection=[c_custkey, c_phone, c_acctbal], file_type=csv, has_header=false-19)--------------------------CoalesceBatchesExec: target_batch_size=8192-20)----------------------------RepartitionExec: partitioning=Hash([o_custkey@0], 4), input_partitions=4-21)------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_custkey], file_type=csv, has_header=false-22)--------------------AggregateExec: mode=Final, gby=[], aggr=[avg(customer.c_acctbal)]-23)----------------------CoalescePartitionsExec-24)------------------------AggregateExec: mode=Partial, gby=[], aggr=[avg(customer.c_acctbal)]-25)--------------------------FilterExec: c_acctbal@1 > Some(0),15,2 AND substr(c_phone@0, 1, 2) IN (SET) ([13, 31, 23, 29, 30, 18, 17]), projection=[c_acctbal@1]-26)----------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-27)------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/customer.tbl]]}, projection=[c_phone, c_acctbal], file_type=csv, has_header=false+05)--------RepartitionExec: partitioning=Hash([cntrycode@0], 4), input_partitions=4+06)----------AggregateExec: mode=Partial, gby=[cntrycode@0 as cntrycode], aggr=[count(Int64(1)), sum(custsale.c_acctbal)]+07)------------ProjectionExec: expr=[substr(c_phone@0, 1, 2) as cntrycode, c_acctbal@1 as c_acctbal]+08)--------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+09)----------------NestedLoopJoinExec: join_type=Inner, filter=join_proj_push_down_1@1 > avg(customer.c_acctbal)@0, projection=[c_phone@0, c_acctbal@1, avg(customer.c_acctbal)@3]+10)------------------ProjectionExec: expr=[c_phone@0 as c_phone, c_acctbal@1 as c_acctbal, CAST(c_acctbal@1 AS Decimal128(19, 6)) as join_proj_push_down_1]+11)--------------------CoalescePartitionsExec+12)----------------------HashJoinExec: mode=Partitioned, join_type=LeftAnti, on=[(c_custkey@0, o_custkey@0)], projection=[c_phone@1, c_acctbal@2]+13)------------------------RepartitionExec: partitioning=Hash([c_custkey@0], 4), input_partitions=4+14)--------------------------FilterExec: substr(c_phone@1, 1, 2) IN (SET) ([13, 31, 23, 29, 30, 18, 17])+15)----------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+16)------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/customer.tbl]]}, projection=[c_custkey, c_phone, c_acctbal], file_type=csv, has_header=false+17)------------------------RepartitionExec: partitioning=Hash([o_custkey@0], 4), input_partitions=4+18)--------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_custkey], file_type=csv, has_header=false+19)------------------AggregateExec: mode=Final, gby=[], aggr=[avg(customer.c_acctbal)]+20)--------------------CoalescePartitionsExec+21)----------------------AggregateExec: mode=Partial, gby=[], aggr=[avg(customer.c_acctbal)]+22)------------------------FilterExec: c_acctbal@1 > Some(0),15,2 AND substr(c_phone@0, 1, 2) IN (SET) ([13, 31, 23, 29, 30, 18, 17]), projection=[c_acctbal@1]+23)--------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+24)----------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/customer.tbl]]}, projection=[c_phone, c_acctbal], file_type=csv, has_header=falsediff --git a/datafusion/sqllogictest/test_files/tpch/plans/q3.slt.part b/datafusion/sqllogictest/test_files/tpch/plans/q3.slt.partindex 225a18daff..093e1c34bc 100644--- a/datafusion/sqllogictest/test_files/tpch/plans/q3.slt.part+++ b/datafusion/sqllogictest/test_files/tpch/plans/q3.slt.part@@ -62,23 +62,18 @@ physical_plan02)--SortExec: TopK(fetch=10), expr=[revenue@1 DESC, o_orderdate@2 ASC NULLS LAST], preserve_partitioning=[true]03)----ProjectionExec: expr=[l_orderkey@0 as l_orderkey, sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)@3 as revenue, o_orderdate@1 as o_orderdate, o_shippriority@2 as o_shippriority]04)------AggregateExec: mode=FinalPartitioned, gby=[l_orderkey@0 as l_orderkey, o_orderdate@1 as o_orderdate, o_shippriority@2 as o_shippriority], aggr=[sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([l_orderkey@0, o_orderdate@1, o_shippriority@2], 4), input_partitions=4-07)------------AggregateExec: mode=Partial, gby=[l_orderkey@2 as l_orderkey, o_orderdate@0 as o_orderdate, o_shippriority@1 as o_shippriority], aggr=[sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)]-08)--------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(o_orderkey@0, l_orderkey@0)], projection=[o_orderdate@1, o_shippriority@2, l_orderkey@3, l_extendedprice@4, l_discount@5]-09)----------------CoalesceBatchesExec: target_batch_size=8192-10)------------------RepartitionExec: partitioning=Hash([o_orderkey@0], 4), input_partitions=4-11)--------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(c_custkey@0, o_custkey@1)], projection=[o_orderkey@1, o_orderdate@3, o_shippriority@4]-12)----------------------CoalesceBatchesExec: target_batch_size=8192-13)------------------------RepartitionExec: partitioning=Hash([c_custkey@0], 4), input_partitions=4-14)--------------------------FilterExec: c_mktsegment@1 = BUILDING, projection=[c_custkey@0]-15)----------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-16)------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/customer.tbl]]}, projection=[c_custkey, c_mktsegment], file_type=csv, has_header=false-17)----------------------CoalesceBatchesExec: target_batch_size=8192-18)------------------------RepartitionExec: partitioning=Hash([o_custkey@1], 4), input_partitions=4-19)--------------------------FilterExec: o_orderdate@2 < 1995-03-15-20)----------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_orderkey, o_custkey, o_orderdate, o_shippriority], file_type=csv, has_header=false-21)----------------CoalesceBatchesExec: target_batch_size=8192-22)------------------RepartitionExec: partitioning=Hash([l_orderkey@0], 4), input_partitions=4-23)--------------------FilterExec: l_shipdate@3 > 1995-03-15, projection=[l_orderkey@0, l_extendedprice@1, l_discount@2]-24)----------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_extendedprice, l_discount, l_shipdate], file_type=csv, has_header=false+05)--------RepartitionExec: partitioning=Hash([l_orderkey@0, o_orderdate@1, o_shippriority@2], 4), input_partitions=4+06)----------AggregateExec: mode=Partial, gby=[l_orderkey@2 as l_orderkey, o_orderdate@0 as o_orderdate, o_shippriority@1 as o_shippriority], aggr=[sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)]+07)------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(o_orderkey@0, l_orderkey@0)], projection=[o_orderdate@1, o_shippriority@2, l_orderkey@3, l_extendedprice@4, l_discount@5]+08)--------------RepartitionExec: partitioning=Hash([o_orderkey@0], 4), input_partitions=4+09)----------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(c_custkey@0, o_custkey@1)], projection=[o_orderkey@1, o_orderdate@3, o_shippriority@4]+10)------------------RepartitionExec: partitioning=Hash([c_custkey@0], 4), input_partitions=4+11)--------------------FilterExec: c_mktsegment@1 = BUILDING, projection=[c_custkey@0]+12)----------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+13)------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/customer.tbl]]}, projection=[c_custkey, c_mktsegment], file_type=csv, has_header=false+14)------------------RepartitionExec: partitioning=Hash([o_custkey@1], 4), input_partitions=4+15)--------------------FilterExec: o_orderdate@2 < 1995-03-15+16)----------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_orderkey, o_custkey, o_orderdate, o_shippriority], file_type=csv, has_header=false+17)--------------RepartitionExec: partitioning=Hash([l_orderkey@0], 4), input_partitions=4+18)----------------FilterExec: l_shipdate@3 > 1995-03-15, projection=[l_orderkey@0, l_extendedprice@1, l_discount@2]+19)------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_extendedprice, l_discount, l_shipdate], file_type=csv, has_header=falsediff --git a/datafusion/sqllogictest/test_files/tpch/plans/q4.slt.part b/datafusion/sqllogictest/test_files/tpch/plans/q4.slt.partindex 1adc37a91f..0007666f15 100644--- a/datafusion/sqllogictest/test_files/tpch/plans/q4.slt.part+++ b/datafusion/sqllogictest/test_files/tpch/plans/q4.slt.part@@ -57,15 +57,12 @@ physical_plan02)--SortExec: expr=[o_orderpriority@0 ASC NULLS LAST], preserve_partitioning=[true]03)----ProjectionExec: expr=[o_orderpriority@0 as o_orderpriority, count(Int64(1))@1 as order_count]04)------AggregateExec: mode=FinalPartitioned, gby=[o_orderpriority@0 as o_orderpriority], aggr=[count(Int64(1))]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([o_orderpriority@0], 4), input_partitions=4-07)------------AggregateExec: mode=Partial, gby=[o_orderpriority@0 as o_orderpriority], aggr=[count(Int64(1))]-08)--------------HashJoinExec: mode=Partitioned, join_type=LeftSemi, on=[(o_orderkey@0, l_orderkey@0)], projection=[o_orderpriority@1]-09)----------------CoalesceBatchesExec: target_batch_size=8192-10)------------------RepartitionExec: partitioning=Hash([o_orderkey@0], 4), input_partitions=4-11)--------------------FilterExec: o_orderdate@1 >= 1993-07-01 AND o_orderdate@1 < 1993-10-01, projection=[o_orderkey@0, o_orderpriority@2]-12)----------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_orderkey, o_orderdate, o_orderpriority], file_type=csv, has_header=false-13)----------------CoalesceBatchesExec: target_batch_size=8192-14)------------------RepartitionExec: partitioning=Hash([l_orderkey@0], 4), input_partitions=4-15)--------------------FilterExec: l_receiptdate@2 > l_commitdate@1, projection=[l_orderkey@0]-16)----------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_commitdate, l_receiptdate], file_type=csv, has_header=false+05)--------RepartitionExec: partitioning=Hash([o_orderpriority@0], 4), input_partitions=4+06)----------AggregateExec: mode=Partial, gby=[o_orderpriority@0 as o_orderpriority], aggr=[count(Int64(1))]+07)------------HashJoinExec: mode=Partitioned, join_type=LeftSemi, on=[(o_orderkey@0, l_orderkey@0)], projection=[o_orderpriority@1]+08)--------------RepartitionExec: partitioning=Hash([o_orderkey@0], 4), input_partitions=4+09)----------------FilterExec: o_orderdate@1 >= 1993-07-01 AND o_orderdate@1 < 1993-10-01, projection=[o_orderkey@0, o_orderpriority@2]+10)------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_orderkey, o_orderdate, o_orderpriority], file_type=csv, has_header=false+11)--------------RepartitionExec: partitioning=Hash([l_orderkey@0], 4), input_partitions=4+12)----------------FilterExec: l_receiptdate@2 > l_commitdate@1, projection=[l_orderkey@0]+13)------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_commitdate, l_receiptdate], file_type=csv, has_header=falsediff --git a/datafusion/sqllogictest/test_files/tpch/plans/q5.slt.part b/datafusion/sqllogictest/test_files/tpch/plans/q5.slt.partindex fdac01f51f..d854001f3c 100644--- a/datafusion/sqllogictest/test_files/tpch/plans/q5.slt.part+++ b/datafusion/sqllogictest/test_files/tpch/plans/q5.slt.part@@ -71,40 +71,29 @@ physical_plan02)--SortExec: expr=[revenue@1 DESC], preserve_partitioning=[true]03)----ProjectionExec: expr=[n_name@0 as n_name, sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)@1 as revenue]04)------AggregateExec: mode=FinalPartitioned, gby=[n_name@0 as n_name], aggr=[sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([n_name@0], 4), input_partitions=4-07)------------AggregateExec: mode=Partial, gby=[n_name@2 as n_name], aggr=[sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)]-08)--------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(n_regionkey@3, r_regionkey@0)], projection=[l_extendedprice@0, l_discount@1, n_name@2]-09)----------------CoalesceBatchesExec: target_batch_size=8192-10)------------------RepartitionExec: partitioning=Hash([n_regionkey@3], 4), input_partitions=4-11)--------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_nationkey@2, n_nationkey@0)], projection=[l_extendedprice@0, l_discount@1, n_name@4, n_regionkey@5]-12)----------------------CoalesceBatchesExec: target_batch_size=8192-13)------------------------RepartitionExec: partitioning=Hash([s_nationkey@2], 4), input_partitions=4-14)--------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_suppkey@1, s_suppkey@0), (c_nationkey@0, s_nationkey@1)], projection=[l_extendedprice@2, l_discount@3, s_nationkey@5]-15)----------------------------CoalesceBatchesExec: target_batch_size=8192-16)------------------------------RepartitionExec: partitioning=Hash([l_suppkey@1, c_nationkey@0], 4), input_partitions=4-17)--------------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(o_orderkey@1, l_orderkey@0)], projection=[c_nationkey@0, l_suppkey@3, l_extendedprice@4, l_discount@5]-18)----------------------------------CoalesceBatchesExec: target_batch_size=8192-19)------------------------------------RepartitionExec: partitioning=Hash([o_orderkey@1], 4), input_partitions=4-20)--------------------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(c_custkey@0, o_custkey@1)], projection=[c_nationkey@1, o_orderkey@2]-21)----------------------------------------CoalesceBatchesExec: target_batch_size=8192-22)------------------------------------------RepartitionExec: partitioning=Hash([c_custkey@0], 4), input_partitions=1-23)--------------------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/customer.tbl]]}, projection=[c_custkey, c_nationkey], file_type=csv, has_header=false-24)----------------------------------------CoalesceBatchesExec: target_batch_size=8192-25)------------------------------------------RepartitionExec: partitioning=Hash([o_custkey@1], 4), input_partitions=4-26)--------------------------------------------FilterExec: o_orderdate@2 >= 1994-01-01 AND o_orderdate@2 < 1995-01-01, projection=[o_orderkey@0, o_custkey@1]-27)----------------------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_orderkey, o_custkey, o_orderdate], file_type=csv, has_header=false-28)----------------------------------CoalesceBatchesExec: target_batch_size=8192-29)------------------------------------RepartitionExec: partitioning=Hash([l_orderkey@0], 4), input_partitions=4-30)--------------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_suppkey, l_extendedprice, l_discount], file_type=csv, has_header=false-31)----------------------------CoalesceBatchesExec: target_batch_size=8192-32)------------------------------RepartitionExec: partitioning=Hash([s_suppkey@0, s_nationkey@1], 4), input_partitions=1-33)--------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_nationkey], file_type=csv, has_header=false-34)----------------------CoalesceBatchesExec: target_batch_size=8192-35)------------------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=1-36)--------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_name, n_regionkey], file_type=csv, has_header=false-37)----------------CoalesceBatchesExec: target_batch_size=8192-38)------------------RepartitionExec: partitioning=Hash([r_regionkey@0], 4), input_partitions=4-39)--------------------FilterExec: r_name@1 = ASIA, projection=[r_regionkey@0]-40)----------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-41)------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/region.tbl]]}, projection=[r_regionkey, r_name], file_type=csv, has_header=false+05)--------RepartitionExec: partitioning=Hash([n_name@0], 4), input_partitions=4+06)----------AggregateExec: mode=Partial, gby=[n_name@2 as n_name], aggr=[sum(lineitem.l_extendedprice * Int64(1) - lineitem.l_discount)]+07)------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(n_regionkey@3, r_regionkey@0)], projection=[l_extendedprice@0, l_discount@1, n_name@2]+08)--------------RepartitionExec: partitioning=Hash([n_regionkey@3], 4), input_partitions=4+09)----------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_nationkey@2, n_nationkey@0)], projection=[l_extendedprice@0, l_discount@1, n_name@4, n_regionkey@5]+10)------------------RepartitionExec: partitioning=Hash([s_nationkey@2], 4), input_partitions=4+11)--------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_suppkey@1, s_suppkey@0), (c_nationkey@0, s_nationkey@1)], projection=[l_extendedprice@2, l_discount@3, s_nationkey@5]+12)----------------------RepartitionExec: partitioning=Hash([l_suppkey@1, c_nationkey@0], 4), input_partitions=4+13)------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(o_orderkey@1, l_orderkey@0)], projection=[c_nationkey@0, l_suppkey@3, l_extendedprice@4, l_discount@5]+14)--------------------------RepartitionExec: partitioning=Hash([o_orderkey@1], 4), input_partitions=4+15)----------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(c_custkey@0, o_custkey@1)], projection=[c_nationkey@1, o_orderkey@2]+16)------------------------------RepartitionExec: partitioning=Hash([c_custkey@0], 4), input_partitions=1+17)--------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/customer.tbl]]}, projection=[c_custkey, c_nationkey], file_type=csv, has_header=false+18)------------------------------RepartitionExec: partitioning=Hash([o_custkey@1], 4), input_partitions=4+19)--------------------------------FilterExec: o_orderdate@2 >= 1994-01-01 AND o_orderdate@2 < 1995-01-01, projection=[o_orderkey@0, o_custkey@1]+20)----------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_orderkey, o_custkey, o_orderdate], file_type=csv, has_header=false+21)--------------------------RepartitionExec: partitioning=Hash([l_orderkey@0], 4), input_partitions=4+22)----------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_suppkey, l_extendedprice, l_discount], file_type=csv, has_header=false+23)----------------------RepartitionExec: partitioning=Hash([s_suppkey@0, s_nationkey@1], 4), input_partitions=1+24)------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_nationkey], file_type=csv, has_header=false+25)------------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=1+26)--------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_name, n_regionkey], file_type=csv, has_header=false+27)--------------RepartitionExec: partitioning=Hash([r_regionkey@0], 4), input_partitions=4+28)----------------FilterExec: r_name@1 = ASIA, projection=[r_regionkey@0]+29)------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+30)--------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/region.tbl]]}, projection=[r_regionkey, r_name], file_type=csv, has_header=falsediff --git a/datafusion/sqllogictest/test_files/tpch/plans/q7.slt.part b/datafusion/sqllogictest/test_files/tpch/plans/q7.slt.partindex 5abbe1ad5a..b4e7099339 100644--- a/datafusion/sqllogictest/test_files/tpch/plans/q7.slt.part+++ b/datafusion/sqllogictest/test_files/tpch/plans/q7.slt.part@@ -88,43 +88,32 @@ physical_plan02)--SortExec: expr=[supp_nation@0 ASC NULLS LAST, cust_nation@1 ASC NULLS LAST, l_year@2 ASC NULLS LAST], preserve_partitioning=[true]03)----ProjectionExec: expr=[supp_nation@0 as supp_nation, cust_nation@1 as cust_nation, l_year@2 as l_year, sum(shipping.volume)@3 as revenue]04)------AggregateExec: mode=FinalPartitioned, gby=[supp_nation@0 as supp_nation, cust_nation@1 as cust_nation, l_year@2 as l_year], aggr=[sum(shipping.volume)]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([supp_nation@0, cust_nation@1, l_year@2], 4), input_partitions=4-07)------------AggregateExec: mode=Partial, gby=[supp_nation@0 as supp_nation, cust_nation@1 as cust_nation, l_year@2 as l_year], aggr=[sum(shipping.volume)]-08)--------------ProjectionExec: expr=[n_name@3 as supp_nation, n_name@4 as cust_nation, date_part(YEAR, l_shipdate@2) as l_year, l_extendedprice@0 * (Some(1),20,0 - l_discount@1) as volume]-09)----------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(c_nationkey@3, n_nationkey@0)], filter=n_name@0 = FRANCE AND n_name@1 = GERMANY OR n_name@0 = GERMANY AND n_name@1 = FRANCE, projection=[l_extendedprice@0, l_discount@1, l_shipdate@2, n_name@4, n_name@6]-10)------------------CoalesceBatchesExec: target_batch_size=8192-11)--------------------RepartitionExec: partitioning=Hash([c_nationkey@3], 4), input_partitions=4-12)----------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_nationkey@0, n_nationkey@0)], projection=[l_extendedprice@1, l_discount@2, l_shipdate@3, c_nationkey@4, n_name@6]-13)------------------------CoalesceBatchesExec: target_batch_size=8192-14)--------------------------RepartitionExec: partitioning=Hash([s_nationkey@0], 4), input_partitions=4-15)----------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(o_custkey@4, c_custkey@0)], projection=[s_nationkey@0, l_extendedprice@1, l_discount@2, l_shipdate@3, c_nationkey@6]-16)------------------------------CoalesceBatchesExec: target_batch_size=8192-17)--------------------------------RepartitionExec: partitioning=Hash([o_custkey@4], 4), input_partitions=4-18)----------------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_orderkey@1, o_orderkey@0)], projection=[s_nationkey@0, l_extendedprice@2, l_discount@3, l_shipdate@4, o_custkey@6]-19)------------------------------------CoalesceBatchesExec: target_batch_size=8192-20)--------------------------------------RepartitionExec: partitioning=Hash([l_orderkey@1], 4), input_partitions=4-21)----------------------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_suppkey@0, l_suppkey@1)], projection=[s_nationkey@1, l_orderkey@2, l_extendedprice@4, l_discount@5, l_shipdate@6]-22)------------------------------------------CoalesceBatchesExec: target_batch_size=8192-23)--------------------------------------------RepartitionExec: partitioning=Hash([s_suppkey@0], 4), input_partitions=1-24)----------------------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_nationkey], file_type=csv, has_header=false-25)------------------------------------------CoalesceBatchesExec: target_batch_size=8192-26)--------------------------------------------RepartitionExec: partitioning=Hash([l_suppkey@1], 4), input_partitions=4-27)----------------------------------------------FilterExec: l_shipdate@4 >= 1995-01-01 AND l_shipdate@4 <= 1996-12-31-28)------------------------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_suppkey, l_extendedprice, l_discount, l_shipdate], file_type=csv, has_header=false-29)------------------------------------CoalesceBatchesExec: target_batch_size=8192-30)--------------------------------------RepartitionExec: partitioning=Hash([o_orderkey@0], 4), input_partitions=4-31)----------------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_orderkey, o_custkey], file_type=csv, has_header=false-32)------------------------------CoalesceBatchesExec: target_batch_size=8192-33)--------------------------------RepartitionExec: partitioning=Hash([c_custkey@0], 4), input_partitions=1-34)----------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/customer.tbl]]}, projection=[c_custkey, c_nationkey], file_type=csv, has_header=false-35)------------------------CoalesceBatchesExec: target_batch_size=8192-36)--------------------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=4-37)----------------------------FilterExec: n_name@1 = FRANCE OR n_name@1 = GERMANY-38)------------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-39)--------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_name], file_type=csv, has_header=false-40)------------------CoalesceBatchesExec: target_batch_size=8192-41)--------------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=4-42)----------------------FilterExec: n_name@1 = GERMANY OR n_name@1 = FRANCE-43)------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-44)--------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_name], file_type=csv, has_header=false+05)--------RepartitionExec: partitioning=Hash([supp_nation@0, cust_nation@1, l_year@2], 4), input_partitions=4+06)----------AggregateExec: mode=Partial, gby=[supp_nation@0 as supp_nation, cust_nation@1 as cust_nation, l_year@2 as l_year], aggr=[sum(shipping.volume)]+07)------------ProjectionExec: expr=[n_name@3 as supp_nation, n_name@4 as cust_nation, date_part(YEAR, l_shipdate@2) as l_year, l_extendedprice@0 * (Some(1),20,0 - l_discount@1) as volume]+08)--------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(c_nationkey@3, n_nationkey@0)], filter=n_name@0 = FRANCE AND n_name@1 = GERMANY OR n_name@0 = GERMANY AND n_name@1 = FRANCE, projection=[l_extendedprice@0, l_discount@1, l_shipdate@2, n_name@4, n_name@6]+09)----------------RepartitionExec: partitioning=Hash([c_nationkey@3], 4), input_partitions=4+10)------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_nationkey@0, n_nationkey@0)], projection=[l_extendedprice@1, l_discount@2, l_shipdate@3, c_nationkey@4, n_name@6]+11)--------------------RepartitionExec: partitioning=Hash([s_nationkey@0], 4), input_partitions=4+12)----------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(o_custkey@4, c_custkey@0)], projection=[s_nationkey@0, l_extendedprice@1, l_discount@2, l_shipdate@3, c_nationkey@6]+13)------------------------RepartitionExec: partitioning=Hash([o_custkey@4], 4), input_partitions=4+14)--------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_orderkey@1, o_orderkey@0)], projection=[s_nationkey@0, l_extendedprice@2, l_discount@3, l_shipdate@4, o_custkey@6]+15)----------------------------RepartitionExec: partitioning=Hash([l_orderkey@1], 4), input_partitions=4+16)------------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_suppkey@0, l_suppkey@1)], projection=[s_nationkey@1, l_orderkey@2, l_extendedprice@4, l_discount@5, l_shipdate@6]+17)--------------------------------RepartitionExec: partitioning=Hash([s_suppkey@0], 4), input_partitions=1+18)----------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_nationkey], file_type=csv, has_header=false+19)--------------------------------RepartitionExec: partitioning=Hash([l_suppkey@1], 4), input_partitions=4+20)----------------------------------FilterExec: l_shipdate@4 >= 1995-01-01 AND l_shipdate@4 <= 1996-12-31+21)------------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_suppkey, l_extendedprice, l_discount, l_shipdate], file_type=csv, has_header=false+22)----------------------------RepartitionExec: partitioning=Hash([o_orderkey@0], 4), input_partitions=4+23)------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_orderkey, o_custkey], file_type=csv, has_header=false+24)------------------------RepartitionExec: partitioning=Hash([c_custkey@0], 4), input_partitions=1+25)--------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/customer.tbl]]}, projection=[c_custkey, c_nationkey], file_type=csv, has_header=false+26)--------------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=4+27)----------------------FilterExec: n_name@1 = FRANCE OR n_name@1 = GERMANY+28)------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+29)--------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_name], file_type=csv, has_header=false+30)----------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=4+31)------------------FilterExec: n_name@1 = GERMANY OR n_name@1 = FRANCE+32)--------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+33)----------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_name], file_type=csv, has_header=falsediff --git a/datafusion/sqllogictest/test_files/tpch/plans/q8.slt.part b/datafusion/sqllogictest/test_files/tpch/plans/q8.slt.partindex 6281c2013e..12f19d43d4 100644--- a/datafusion/sqllogictest/test_files/tpch/plans/q8.slt.part+++ b/datafusion/sqllogictest/test_files/tpch/plans/q8.slt.part@@ -94,55 +94,40 @@ physical_plan02)--SortExec: expr=[o_year@0 ASC NULLS LAST], preserve_partitioning=[true]03)----ProjectionExec: expr=[o_year@0 as o_year, CAST(CAST(sum(CASE WHEN all_nations.nation = Utf8("BRAZIL") THEN all_nations.volume ELSE Int64(0) END)@1 AS Decimal128(12, 2)) / CAST(sum(all_nations.volume)@2 AS Decimal128(12, 2)) AS Decimal128(15, 2)) as mkt_share]04)------AggregateExec: mode=FinalPartitioned, gby=[o_year@0 as o_year], aggr=[sum(CASE WHEN all_nations.nation = Utf8("BRAZIL") THEN all_nations.volume ELSE Int64(0) END), sum(all_nations.volume)]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([o_year@0], 4), input_partitions=4-07)------------AggregateExec: mode=Partial, gby=[o_year@0 as o_year], aggr=[sum(CASE WHEN all_nations.nation = Utf8("BRAZIL") THEN all_nations.volume ELSE Int64(0) END), sum(all_nations.volume)]-08)--------------ProjectionExec: expr=[date_part(YEAR, o_orderdate@2) as o_year, l_extendedprice@0 * (Some(1),20,0 - l_discount@1) as volume, n_name@3 as nation]-09)----------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(n_regionkey@3, r_regionkey@0)], projection=[l_extendedprice@0, l_discount@1, o_orderdate@2, n_name@4]-10)------------------CoalesceBatchesExec: target_batch_size=8192-11)--------------------RepartitionExec: partitioning=Hash([n_regionkey@3], 4), input_partitions=4-12)----------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_nationkey@2, n_nationkey@0)], projection=[l_extendedprice@0, l_discount@1, o_orderdate@3, n_regionkey@4, n_name@6]-13)------------------------CoalesceBatchesExec: target_batch_size=8192-14)--------------------------RepartitionExec: partitioning=Hash([s_nationkey@2], 4), input_partitions=4-15)----------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(c_nationkey@4, n_nationkey@0)], projection=[l_extendedprice@0, l_discount@1, s_nationkey@2, o_orderdate@3, n_regionkey@6]-16)------------------------------CoalesceBatchesExec: target_batch_size=8192-17)--------------------------------RepartitionExec: partitioning=Hash([c_nationkey@4], 4), input_partitions=4-18)----------------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(o_custkey@3, c_custkey@0)], projection=[l_extendedprice@0, l_discount@1, s_nationkey@2, o_orderdate@4, c_nationkey@6]-19)------------------------------------CoalesceBatchesExec: target_batch_size=8192-20)--------------------------------------RepartitionExec: partitioning=Hash([o_custkey@3], 4), input_partitions=4-21)----------------------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_orderkey@0, o_orderkey@0)], projection=[l_extendedprice@1, l_discount@2, s_nationkey@3, o_custkey@5, o_orderdate@6]-22)------------------------------------------CoalesceBatchesExec: target_batch_size=8192-23)--------------------------------------------RepartitionExec: partitioning=Hash([l_orderkey@0], 4), input_partitions=4-24)----------------------------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_suppkey@1, s_suppkey@0)], projection=[l_orderkey@0, l_extendedprice@2, l_discount@3, s_nationkey@5]-25)------------------------------------------------CoalesceBatchesExec: target_batch_size=8192-26)--------------------------------------------------RepartitionExec: partitioning=Hash([l_suppkey@1], 4), input_partitions=4-27)----------------------------------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(p_partkey@0, l_partkey@1)], projection=[l_orderkey@1, l_suppkey@3, l_extendedprice@4, l_discount@5]-28)------------------------------------------------------CoalesceBatchesExec: target_batch_size=8192-29)--------------------------------------------------------RepartitionExec: partitioning=Hash([p_partkey@0], 4), input_partitions=4-30)----------------------------------------------------------FilterExec: p_type@1 = ECONOMY ANODIZED STEEL, projection=[p_partkey@0]-31)------------------------------------------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-32)--------------------------------------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/part.tbl]]}, projection=[p_partkey, p_type], file_type=csv, has_header=false-33)------------------------------------------------------CoalesceBatchesExec: target_batch_size=8192-34)--------------------------------------------------------RepartitionExec: partitioning=Hash([l_partkey@1], 4), input_partitions=4-35)----------------------------------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_partkey, l_suppkey, l_extendedprice, l_discount], file_type=csv, has_header=false-36)------------------------------------------------CoalesceBatchesExec: target_batch_size=8192-37)--------------------------------------------------RepartitionExec: partitioning=Hash([s_suppkey@0], 4), input_partitions=1-38)----------------------------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_nationkey], file_type=csv, has_header=false-39)------------------------------------------CoalesceBatchesExec: target_batch_size=8192-40)--------------------------------------------RepartitionExec: partitioning=Hash([o_orderkey@0], 4), input_partitions=4-41)----------------------------------------------FilterExec: o_orderdate@2 >= 1995-01-01 AND o_orderdate@2 <= 1996-12-31-42)------------------------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_orderkey, o_custkey, o_orderdate], file_type=csv, has_header=false-43)------------------------------------CoalesceBatchesExec: target_batch_size=8192-44)--------------------------------------RepartitionExec: partitioning=Hash([c_custkey@0], 4), input_partitions=1-45)----------------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/customer.tbl]]}, projection=[c_custkey, c_nationkey], file_type=csv, has_header=false-46)------------------------------CoalesceBatchesExec: target_batch_size=8192-47)--------------------------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=1-48)----------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_regionkey], file_type=csv, has_header=false-49)------------------------CoalesceBatchesExec: target_batch_size=8192-50)--------------------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=1-51)----------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_name], file_type=csv, has_header=false-52)------------------CoalesceBatchesExec: target_batch_size=8192-53)--------------------RepartitionExec: partitioning=Hash([r_regionkey@0], 4), input_partitions=4-54)----------------------FilterExec: r_name@1 = AMERICA, projection=[r_regionkey@0]-55)------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-56)--------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/region.tbl]]}, projection=[r_regionkey, r_name], file_type=csv, has_header=false+05)--------RepartitionExec: partitioning=Hash([o_year@0], 4), input_partitions=4+06)----------AggregateExec: mode=Partial, gby=[o_year@0 as o_year], aggr=[sum(CASE WHEN all_nations.nation = Utf8("BRAZIL") THEN all_nations.volume ELSE Int64(0) END), sum(all_nations.volume)]+07)------------ProjectionExec: expr=[date_part(YEAR, o_orderdate@2) as o_year, l_extendedprice@0 * (Some(1),20,0 - l_discount@1) as volume, n_name@3 as nation]+08)--------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(n_regionkey@3, r_regionkey@0)], projection=[l_extendedprice@0, l_discount@1, o_orderdate@2, n_name@4]+09)----------------RepartitionExec: partitioning=Hash([n_regionkey@3], 4), input_partitions=4+10)------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_nationkey@2, n_nationkey@0)], projection=[l_extendedprice@0, l_discount@1, o_orderdate@3, n_regionkey@4, n_name@6]+11)--------------------RepartitionExec: partitioning=Hash([s_nationkey@2], 4), input_partitions=4+12)----------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(c_nationkey@4, n_nationkey@0)], projection=[l_extendedprice@0, l_discount@1, s_nationkey@2, o_orderdate@3, n_regionkey@6]+13)------------------------RepartitionExec: partitioning=Hash([c_nationkey@4], 4), input_partitions=4+14)--------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(o_custkey@3, c_custkey@0)], projection=[l_extendedprice@0, l_discount@1, s_nationkey@2, o_orderdate@4, c_nationkey@6]+15)----------------------------RepartitionExec: partitioning=Hash([o_custkey@3], 4), input_partitions=4+16)------------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_orderkey@0, o_orderkey@0)], projection=[l_extendedprice@1, l_discount@2, s_nationkey@3, o_custkey@5, o_orderdate@6]+17)--------------------------------RepartitionExec: partitioning=Hash([l_orderkey@0], 4), input_partitions=4+18)----------------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_suppkey@1, s_suppkey@0)], projection=[l_orderkey@0, l_extendedprice@2, l_discount@3, s_nationkey@5]+19)------------------------------------RepartitionExec: partitioning=Hash([l_suppkey@1], 4), input_partitions=4+20)--------------------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(p_partkey@0, l_partkey@1)], projection=[l_orderkey@1, l_suppkey@3, l_extendedprice@4, l_discount@5]+21)----------------------------------------RepartitionExec: partitioning=Hash([p_partkey@0], 4), input_partitions=4+22)------------------------------------------FilterExec: p_type@1 = ECONOMY ANODIZED STEEL, projection=[p_partkey@0]+23)--------------------------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+24)----------------------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/part.tbl]]}, projection=[p_partkey, p_type], file_type=csv, has_header=false+25)----------------------------------------RepartitionExec: partitioning=Hash([l_partkey@1], 4), input_partitions=4+26)------------------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_partkey, l_suppkey, l_extendedprice, l_discount], file_type=csv, has_header=false+27)------------------------------------RepartitionExec: partitioning=Hash([s_suppkey@0], 4), input_partitions=1+28)--------------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_nationkey], file_type=csv, has_header=false+29)--------------------------------RepartitionExec: partitioning=Hash([o_orderkey@0], 4), input_partitions=4+30)----------------------------------FilterExec: o_orderdate@2 >= 1995-01-01 AND o_orderdate@2 <= 1996-12-31+31)------------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_orderkey, o_custkey, o_orderdate], file_type=csv, has_header=false+32)----------------------------RepartitionExec: partitioning=Hash([c_custkey@0], 4), input_partitions=1+33)------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/customer.tbl]]}, projection=[c_custkey, c_nationkey], file_type=csv, has_header=false+34)------------------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=1+35)--------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_regionkey], file_type=csv, has_header=false+36)--------------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=1+37)----------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_name], file_type=csv, has_header=false+38)----------------RepartitionExec: partitioning=Hash([r_regionkey@0], 4), input_partitions=4+39)------------------FilterExec: r_name@1 = AMERICA, projection=[r_regionkey@0]+40)--------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+41)----------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/region.tbl]]}, projection=[r_regionkey, r_name], file_type=csv, has_header=falsediff --git a/datafusion/sqllogictest/test_files/tpch/plans/q9.slt.part b/datafusion/sqllogictest/test_files/tpch/plans/q9.slt.partindex 88d52612e0..4ec434c903 100644--- a/datafusion/sqllogictest/test_files/tpch/plans/q9.slt.part+++ b/datafusion/sqllogictest/test_files/tpch/plans/q9.slt.part@@ -79,40 +79,29 @@ physical_plan02)--SortExec: TopK(fetch=10), expr=[nation@0 ASC NULLS LAST, o_year@1 DESC], preserve_partitioning=[true]03)----ProjectionExec: expr=[nation@0 as nation, o_year@1 as o_year, sum(profit.amount)@2 as sum_profit]04)------AggregateExec: mode=FinalPartitioned, gby=[nation@0 as nation, o_year@1 as o_year], aggr=[sum(profit.amount)]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([nation@0, o_year@1], 4), input_partitions=4-07)------------AggregateExec: mode=Partial, gby=[nation@0 as nation, o_year@1 as o_year], aggr=[sum(profit.amount)]-08)--------------ProjectionExec: expr=[n_name@5 as nation, date_part(YEAR, o_orderdate@4) as o_year, l_extendedprice@1 * (Some(1),20,0 - l_discount@2) - ps_supplycost@3 * l_quantity@0 as amount]-09)----------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_nationkey@3, n_nationkey@0)], projection=[l_quantity@0, l_extendedprice@1, l_discount@2, ps_supplycost@4, o_orderdate@5, n_name@7]-10)------------------CoalesceBatchesExec: target_batch_size=8192-11)--------------------RepartitionExec: partitioning=Hash([s_nationkey@3], 4), input_partitions=4-12)----------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_orderkey@0, o_orderkey@0)], projection=[l_quantity@1, l_extendedprice@2, l_discount@3, s_nationkey@4, ps_supplycost@5, o_orderdate@7]-13)------------------------CoalesceBatchesExec: target_batch_size=8192-14)--------------------------RepartitionExec: partitioning=Hash([l_orderkey@0], 4), input_partitions=4-15)----------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_suppkey@2, ps_suppkey@1), (l_partkey@1, ps_partkey@0)], projection=[l_orderkey@0, l_quantity@3, l_extendedprice@4, l_discount@5, s_nationkey@6, ps_supplycost@9]-16)------------------------------CoalesceBatchesExec: target_batch_size=8192-17)--------------------------------RepartitionExec: partitioning=Hash([l_suppkey@2, l_partkey@1], 4), input_partitions=4-18)----------------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_suppkey@2, s_suppkey@0)], projection=[l_orderkey@0, l_partkey@1, l_suppkey@2, l_quantity@3, l_extendedprice@4, l_discount@5, s_nationkey@7]-19)------------------------------------CoalesceBatchesExec: target_batch_size=8192-20)--------------------------------------RepartitionExec: partitioning=Hash([l_suppkey@2], 4), input_partitions=4-21)----------------------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(p_partkey@0, l_partkey@1)], projection=[l_orderkey@1, l_partkey@2, l_suppkey@3, l_quantity@4, l_extendedprice@5, l_discount@6]-22)------------------------------------------CoalesceBatchesExec: target_batch_size=8192-23)--------------------------------------------RepartitionExec: partitioning=Hash([p_partkey@0], 4), input_partitions=4-24)----------------------------------------------FilterExec: p_name@1 LIKE %green%, projection=[p_partkey@0]-25)------------------------------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-26)--------------------------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/part.tbl]]}, projection=[p_partkey, p_name], file_type=csv, has_header=false-27)------------------------------------------CoalesceBatchesExec: target_batch_size=8192-28)--------------------------------------------RepartitionExec: partitioning=Hash([l_partkey@1], 4), input_partitions=4-29)----------------------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_partkey, l_suppkey, l_quantity, l_extendedprice, l_discount], file_type=csv, has_header=false-30)------------------------------------CoalesceBatchesExec: target_batch_size=8192-31)--------------------------------------RepartitionExec: partitioning=Hash([s_suppkey@0], 4), input_partitions=1-32)----------------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_nationkey], file_type=csv, has_header=false-33)------------------------------CoalesceBatchesExec: target_batch_size=8192-34)--------------------------------RepartitionExec: partitioning=Hash([ps_suppkey@1, ps_partkey@0], 4), input_partitions=4-35)----------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:0..2932049], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:2932049..5864098], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:5864098..8796147], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:8796147..11728193]]}, projection=[ps_partkey, ps_suppkey, ps_supplycost], file_type=csv, has_header=false-36)------------------------CoalesceBatchesExec: target_batch_size=8192-37)--------------------------RepartitionExec: partitioning=Hash([o_orderkey@0], 4), input_partitions=4-38)----------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_orderkey, o_orderdate], file_type=csv, has_header=false-39)------------------CoalesceBatchesExec: target_batch_size=8192-40)--------------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=1-41)----------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_name], file_type=csv, has_header=false+05)--------RepartitionExec: partitioning=Hash([nation@0, o_year@1], 4), input_partitions=4+06)----------AggregateExec: mode=Partial, gby=[nation@0 as nation, o_year@1 as o_year], aggr=[sum(profit.amount)]+07)------------ProjectionExec: expr=[n_name@5 as nation, date_part(YEAR, o_orderdate@4) as o_year, l_extendedprice@1 * (Some(1),20,0 - l_discount@2) - ps_supplycost@3 * l_quantity@0 as amount]+08)--------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(s_nationkey@3, n_nationkey@0)], projection=[l_quantity@0, l_extendedprice@1, l_discount@2, ps_supplycost@4, o_orderdate@5, n_name@7]+09)----------------RepartitionExec: partitioning=Hash([s_nationkey@3], 4), input_partitions=4+10)------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_orderkey@0, o_orderkey@0)], projection=[l_quantity@1, l_extendedprice@2, l_discount@3, s_nationkey@4, ps_supplycost@5, o_orderdate@7]+11)--------------------RepartitionExec: partitioning=Hash([l_orderkey@0], 4), input_partitions=4+12)----------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_suppkey@2, ps_suppkey@1), (l_partkey@1, ps_partkey@0)], projection=[l_orderkey@0, l_quantity@3, l_extendedprice@4, l_discount@5, s_nationkey@6, ps_supplycost@9]+13)------------------------RepartitionExec: partitioning=Hash([l_suppkey@2, l_partkey@1], 4), input_partitions=4+14)--------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(l_suppkey@2, s_suppkey@0)], projection=[l_orderkey@0, l_partkey@1, l_suppkey@2, l_quantity@3, l_extendedprice@4, l_discount@5, s_nationkey@7]+15)----------------------------RepartitionExec: partitioning=Hash([l_suppkey@2], 4), input_partitions=4+16)------------------------------HashJoinExec: mode=Partitioned, join_type=Inner, on=[(p_partkey@0, l_partkey@1)], projection=[l_orderkey@1, l_partkey@2, l_suppkey@3, l_quantity@4, l_extendedprice@5, l_discount@6]+17)--------------------------------RepartitionExec: partitioning=Hash([p_partkey@0], 4), input_partitions=4+18)----------------------------------FilterExec: p_name@1 LIKE %green%, projection=[p_partkey@0]+19)------------------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+20)--------------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/part.tbl]]}, projection=[p_partkey, p_name], file_type=csv, has_header=false+21)--------------------------------RepartitionExec: partitioning=Hash([l_partkey@1], 4), input_partitions=4+22)----------------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:0..18561749], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:18561749..37123498], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:37123498..55685247], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/lineitem.tbl:55685247..74246996]]}, projection=[l_orderkey, l_partkey, l_suppkey, l_quantity, l_extendedprice, l_discount], file_type=csv, has_header=false+23)----------------------------RepartitionExec: partitioning=Hash([s_suppkey@0], 4), input_partitions=1+24)------------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/supplier.tbl]]}, projection=[s_suppkey, s_nationkey], file_type=csv, has_header=false+25)------------------------RepartitionExec: partitioning=Hash([ps_suppkey@1, ps_partkey@0], 4), input_partitions=4+26)--------------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:0..2932049], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:2932049..5864098], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:5864098..8796147], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/partsupp.tbl:8796147..11728193]]}, projection=[ps_partkey, ps_suppkey, ps_supplycost], file_type=csv, has_header=false+27)--------------------RepartitionExec: partitioning=Hash([o_orderkey@0], 4), input_partitions=4+28)----------------------DataSourceExec: file_groups={4 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:0..4223281], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:4223281..8446562], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:8446562..12669843], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/orders.tbl:12669843..16893122]]}, projection=[o_orderkey, o_orderdate], file_type=csv, has_header=false+29)----------------RepartitionExec: partitioning=Hash([n_nationkey@0], 4), input_partitions=1+30)------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/tpch/data/nation.tbl]]}, projection=[n_nationkey, n_name], file_type=csv, has_header=falsediff --git a/datafusion/sqllogictest/test_files/union.slt b/datafusion/sqllogictest/test_files/union.sltindex d62360ae8c..b79b6d2fe5 100644--- a/datafusion/sqllogictest/test_files/union.slt+++ b/datafusion/sqllogictest/test_files/union.slt@@ -234,14 +234,13 @@ logical_plan06)------TableScan: t2 projection=[name]physical_plan01)AggregateExec: mode=FinalPartitioned, gby=[name@0 as name], aggr=[]-02)--CoalesceBatchesExec: target_batch_size=8192-03)----RepartitionExec: partitioning=Hash([name@0], 4), input_partitions=3-04)------AggregateExec: mode=Partial, gby=[name@0 as name], aggr=[]-05)--------UnionExec-06)----------DataSourceExec: partitions=1, partition_sizes=[1]-07)----------DataSourceExec: partitions=1, partition_sizes=[1]-08)----------ProjectionExec: expr=[name@0 || _new as name]-09)------------DataSourceExec: partitions=1, partition_sizes=[1]+02)--RepartitionExec: partitioning=Hash([name@0], 4), input_partitions=3+03)----AggregateExec: mode=Partial, gby=[name@0 as name], aggr=[]+04)------UnionExec+05)--------DataSourceExec: partitions=1, partition_sizes=[1]+06)--------DataSourceExec: partitions=1, partition_sizes=[1]+07)--------ProjectionExec: expr=[name@0 || _new as name]+08)----------DataSourceExec: partitions=1, partition_sizes=[1]# nested_union_allquery T rowsort@@ -312,23 +311,21 @@ physical_plan05)--------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=106)----------DataSourceExec: partitions=1, partition_sizes=[1]07)----AggregateExec: mode=FinalPartitioned, gby=[id@0 as id, name@1 as name], aggr=[]-08)------CoalesceBatchesExec: target_batch_size=2-09)--------RepartitionExec: partitioning=Hash([id@0, name@1], 4), input_partitions=4-10)----------AggregateExec: mode=Partial, gby=[id@0 as id, name@1 as name], aggr=[]-11)------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-12)--------------DataSourceExec: partitions=1, partition_sizes=[1]-13)--ProjectionExec: expr=[CAST(id@0 AS Int32) as id, name@1 as name]-14)----HashJoinExec: mode=CollectLeft, join_type=LeftAnti, on=[(CAST(t2.id AS Int32)@2, id@0), (name@1, name@1)], projection=[id@0, name@1], NullsEqual: true-15)------CoalescePartitionsExec-16)--------ProjectionExec: expr=[id@0 as id, name@1 as name, CAST(id@0 AS Int32) as CAST(t2.id AS Int32)]-17)----------AggregateExec: mode=FinalPartitioned, gby=[id@0 as id, name@1 as name], aggr=[]-18)------------CoalesceBatchesExec: target_batch_size=2-19)--------------RepartitionExec: partitioning=Hash([id@0, name@1], 4), input_partitions=4-20)----------------AggregateExec: mode=Partial, gby=[id@0 as id, name@1 as name], aggr=[]-21)------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-22)--------------------DataSourceExec: partitions=1, partition_sizes=[1]-23)------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-24)--------DataSourceExec: partitions=1, partition_sizes=[1]+08)------RepartitionExec: partitioning=Hash([id@0, name@1], 4), input_partitions=4+09)--------AggregateExec: mode=Partial, gby=[id@0 as id, name@1 as name], aggr=[]+10)----------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+11)------------DataSourceExec: partitions=1, partition_sizes=[1]+12)--ProjectionExec: expr=[CAST(id@0 AS Int32) as id, name@1 as name]+13)----HashJoinExec: mode=CollectLeft, join_type=LeftAnti, on=[(CAST(t2.id AS Int32)@2, id@0), (name@1, name@1)], projection=[id@0, name@1], NullsEqual: true+14)------CoalescePartitionsExec+15)--------ProjectionExec: expr=[id@0 as id, name@1 as name, CAST(id@0 AS Int32) as CAST(t2.id AS Int32)]+16)----------AggregateExec: mode=FinalPartitioned, gby=[id@0 as id, name@1 as name], aggr=[]+17)------------RepartitionExec: partitioning=Hash([id@0, name@1], 4), input_partitions=4+18)--------------AggregateExec: mode=Partial, gby=[id@0 as id, name@1 as name], aggr=[]+19)----------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+20)------------------DataSourceExec: partitions=1, partition_sizes=[1]+21)------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+22)--------DataSourceExec: partitions=1, partition_sizes=[1]query IT rowsort@@ -377,23 +374,21 @@ physical_plan02)--HashJoinExec: mode=CollectLeft, join_type=LeftAnti, on=[(name@0, name@0)], NullsEqual: true03)----CoalescePartitionsExec04)------AggregateExec: mode=FinalPartitioned, gby=[name@0 as name], aggr=[]-05)--------CoalesceBatchesExec: target_batch_size=2-06)----------RepartitionExec: partitioning=Hash([name@0], 4), input_partitions=4-07)------------AggregateExec: mode=Partial, gby=[name@0 as name], aggr=[]-08)--------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-09)----------------DataSourceExec: partitions=1, partition_sizes=[1]-10)----RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-11)------DataSourceExec: partitions=1, partition_sizes=[1]-12)--HashJoinExec: mode=CollectLeft, join_type=LeftAnti, on=[(name@0, name@0)], NullsEqual: true-13)----CoalescePartitionsExec-14)------AggregateExec: mode=FinalPartitioned, gby=[name@0 as name], aggr=[]-15)--------CoalesceBatchesExec: target_batch_size=2-16)----------RepartitionExec: partitioning=Hash([name@0], 4), input_partitions=4-17)------------AggregateExec: mode=Partial, gby=[name@0 as name], aggr=[]-18)--------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-19)----------------DataSourceExec: partitions=1, partition_sizes=[1]-20)----RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-21)------DataSourceExec: partitions=1, partition_sizes=[1]+05)--------RepartitionExec: partitioning=Hash([name@0], 4), input_partitions=4+06)----------AggregateExec: mode=Partial, gby=[name@0 as name], aggr=[]+07)------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+08)--------------DataSourceExec: partitions=1, partition_sizes=[1]+09)----RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+10)------DataSourceExec: partitions=1, partition_sizes=[1]+11)--HashJoinExec: mode=CollectLeft, join_type=LeftAnti, on=[(name@0, name@0)], NullsEqual: true+12)----CoalescePartitionsExec+13)------AggregateExec: mode=FinalPartitioned, gby=[name@0 as name], aggr=[]+14)--------RepartitionExec: partitioning=Hash([name@0], 4), input_partitions=4+15)----------AggregateExec: mode=Partial, gby=[name@0 as name], aggr=[]+16)------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+17)--------------DataSourceExec: partitions=1, partition_sizes=[1]+18)----RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+19)------DataSourceExec: partitions=1, partition_sizes=[1]# union_upcast_typesquery TT@@ -448,17 +443,15 @@ physical_plan02)--AggregateExec: mode=SinglePartitioned, gby=[name@0 as name], aggr=[count(Int64(1))]03)----InterleaveExec04)------AggregateExec: mode=FinalPartitioned, gby=[name@0 as name], aggr=[]-05)--------CoalesceBatchesExec: target_batch_size=2-06)----------RepartitionExec: partitioning=Hash([name@0], 4), input_partitions=4-07)------------AggregateExec: mode=Partial, gby=[name@0 as name], aggr=[]-08)--------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-09)----------------DataSourceExec: partitions=1, partition_sizes=[1]-10)------AggregateExec: mode=FinalPartitioned, gby=[name@0 as name], aggr=[]-11)--------CoalesceBatchesExec: target_batch_size=2-12)----------RepartitionExec: partitioning=Hash([name@0], 4), input_partitions=4-13)------------AggregateExec: mode=Partial, gby=[name@0 as name], aggr=[]-14)--------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-15)----------------DataSourceExec: partitions=1, partition_sizes=[1]+05)--------RepartitionExec: partitioning=Hash([name@0], 4), input_partitions=4+06)----------AggregateExec: mode=Partial, gby=[name@0 as name], aggr=[]+07)------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+08)--------------DataSourceExec: partitions=1, partition_sizes=[1]+09)------AggregateExec: mode=FinalPartitioned, gby=[name@0 as name], aggr=[]+10)--------RepartitionExec: partitioning=Hash([name@0], 4), input_partitions=4+11)----------AggregateExec: mode=Partial, gby=[name@0 as name], aggr=[]+12)------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+13)--------------DataSourceExec: partitions=1, partition_sizes=[1]# Union with limit push down 3 children test casequery TT@@ -506,18 +499,17 @@ physical_plan06)----------AggregateExec: mode=Partial, gby=[], aggr=[count(Int64(1))]07)------------ProjectionExec: expr=[]08)--------------AggregateExec: mode=FinalPartitioned, gby=[c1@0 as c1], aggr=[]-09)----------------CoalesceBatchesExec: target_batch_size=2-10)------------------RepartitionExec: partitioning=Hash([c1@0], 4), input_partitions=4-11)--------------------AggregateExec: mode=Partial, gby=[c1@0 as c1], aggr=[]-12)----------------------FilterExec: c13@1 != C2GT5KVyOPZpgKVl110TyZO0NcJ434, projection=[c1@0]-13)------------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1-14)--------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c13], file_type=csv, has_header=true-15)----ProjectionExec: expr=[1 as cnt]-16)------PlaceholderRowExec-17)----ProjectionExec: expr=[lead(b.c1,Int64(1)) ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING@1 as cnt]-18)------BoundedWindowAggExec: wdw=[lead(b.c1,Int64(1)) ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING: Field { "lead(b.c1,Int64(1)) ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING": nullable Int64 }, frame: ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING], mode=[Sorted]-19)--------ProjectionExec: expr=[1 as c1]-20)----------PlaceholderRowExec+09)----------------RepartitionExec: partitioning=Hash([c1@0], 4), input_partitions=4+10)------------------AggregateExec: mode=Partial, gby=[c1@0 as c1], aggr=[]+11)--------------------FilterExec: c13@1 != C2GT5KVyOPZpgKVl110TyZO0NcJ434, projection=[c1@0]+12)----------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1+13)------------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c13], file_type=csv, has_header=true+14)----ProjectionExec: expr=[1 as cnt]+15)------PlaceholderRowExec+16)----ProjectionExec: expr=[lead(b.c1,Int64(1)) ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING@1 as cnt]+17)------BoundedWindowAggExec: wdw=[lead(b.c1,Int64(1)) ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING: Field { "lead(b.c1,Int64(1)) ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING": nullable Int64 }, frame: ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING], mode=[Sorted]+18)--------ProjectionExec: expr=[1 as c1]+19)----------PlaceholderRowExec########diff --git a/datafusion/sqllogictest/test_files/unnest.slt b/datafusion/sqllogictest/test_files/unnest.sltindex 537b334ecb..352056adbf 100644--- a/datafusion/sqllogictest/test_files/unnest.slt+++ b/datafusion/sqllogictest/test_files/unnest.slt@@ -962,15 +962,14 @@ physical_plan01)ProjectionExec: expr=[array_agg(unnested.ar)@1 as array_agg(unnested.ar)]02)--AggregateExec: mode=FinalPartitioned, gby=[generated_id@0 as generated_id], aggr=[array_agg(unnested.ar)], ordering_mode=Sorted03)----SortExec: expr=[generated_id@0 ASC NULLS LAST], preserve_partitioning=[true]-04)------CoalesceBatchesExec: target_batch_size=8192-05)--------RepartitionExec: partitioning=Hash([generated_id@0], 4), input_partitions=4-06)----------AggregateExec: mode=Partial, gby=[generated_id@0 as generated_id], aggr=[array_agg(unnested.ar)], ordering_mode=Sorted-07)------------ProjectionExec: expr=[generated_id@0 as generated_id, __unnest_placeholder(make_array(range().value),depth=1)@1 as ar]-08)--------------UnnestExec-09)----------------ProjectionExec: expr=[row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING@1 as generated_id, make_array(value@0) as __unnest_placeholder(make_array(range().value))]-10)------------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1, maintains_sort_order=true-11)--------------------BoundedWindowAggExec: wdw=[row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING: Field { "row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING": UInt64 }, frame: ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING], mode=[Sorted]-12)----------------------LazyMemoryExec: partitions=1, batch_generators=[range: start=1, end=5, batch_size=8192]+04)------RepartitionExec: partitioning=Hash([generated_id@0], 4), input_partitions=4+05)--------AggregateExec: mode=Partial, gby=[generated_id@0 as generated_id], aggr=[array_agg(unnested.ar)], ordering_mode=Sorted+06)----------ProjectionExec: expr=[generated_id@0 as generated_id, __unnest_placeholder(make_array(range().value),depth=1)@1 as ar]+07)------------UnnestExec+08)--------------ProjectionExec: expr=[row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING@1 as generated_id, make_array(value@0) as __unnest_placeholder(make_array(range().value))]+09)----------------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1, maintains_sort_order=true+10)------------------BoundedWindowAggExec: wdw=[row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING: Field { "row_number() ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING": UInt64 }, frame: ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING], mode=[Sorted]+11)--------------------LazyMemoryExec: partitions=1, batch_generators=[range: start=1, end=5, batch_size=8192]# Unnest array where data is already ordered by column2 (100, 200, 300, 400)statement okdiff --git a/datafusion/sqllogictest/test_files/window.slt b/datafusion/sqllogictest/test_files/window.sltindex 818c861695..8ac8724683 100644--- a/datafusion/sqllogictest/test_files/window.slt+++ b/datafusion/sqllogictest/test_files/window.slt@@ -275,18 +275,17 @@ physical_plan02)--SortExec: expr=[b@0 ASC NULLS LAST], preserve_partitioning=[true]03)----ProjectionExec: expr=[b@0 as b, max(d.a)@1 as max_a]04)------AggregateExec: mode=FinalPartitioned, gby=[b@0 as b], aggr=[max(d.a)]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([b@0], 4), input_partitions=4-07)------------AggregateExec: mode=Partial, gby=[b@1 as b], aggr=[max(d.a)], ordering_mode=Sorted-08)--------------UnionExec-09)----------------ProjectionExec: expr=[1 as a, aa as b]-10)------------------PlaceholderRowExec-11)----------------ProjectionExec: expr=[3 as a, aa as b]-12)------------------PlaceholderRowExec-13)----------------ProjectionExec: expr=[5 as a, bb as b]-14)------------------PlaceholderRowExec-15)----------------ProjectionExec: expr=[7 as a, bb as b]-16)------------------PlaceholderRowExec+05)--------RepartitionExec: partitioning=Hash([b@0], 4), input_partitions=4+06)----------AggregateExec: mode=Partial, gby=[b@1 as b], aggr=[max(d.a)], ordering_mode=Sorted+07)------------UnionExec+08)--------------ProjectionExec: expr=[1 as a, aa as b]+09)----------------PlaceholderRowExec+10)--------------ProjectionExec: expr=[3 as a, aa as b]+11)----------------PlaceholderRowExec+12)--------------ProjectionExec: expr=[5 as a, bb as b]+13)----------------PlaceholderRowExec+14)--------------ProjectionExec: expr=[7 as a, bb as b]+15)----------------PlaceholderRowExec# Check actual result:query TI@@ -362,17 +361,16 @@ physical_plan04)------ProjectionExec: expr=[row_number() PARTITION BY [s.b] ORDER BY [s.a ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW@2 as seq, a@0 as a, b@1 as b]05)--------BoundedWindowAggExec: wdw=[row_number() PARTITION BY [s.b] ORDER BY [s.a ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "row_number() PARTITION BY [s.b] ORDER BY [s.a ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": UInt64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[Sorted]06)----------SortExec: expr=[b@1 ASC NULLS LAST, a@0 ASC NULLS LAST], preserve_partitioning=[true]-07)------------CoalesceBatchesExec: target_batch_size=8192-08)--------------RepartitionExec: partitioning=Hash([b@1], 4), input_partitions=4-09)----------------UnionExec-10)------------------ProjectionExec: expr=[1 as a, aa as b]-11)--------------------PlaceholderRowExec-12)------------------ProjectionExec: expr=[3 as a, aa as b]-13)--------------------PlaceholderRowExec-14)------------------ProjectionExec: expr=[5 as a, bb as b]-15)--------------------PlaceholderRowExec-16)------------------ProjectionExec: expr=[7 as a, bb as b]-17)--------------------PlaceholderRowExec+07)------------RepartitionExec: partitioning=Hash([b@1], 4), input_partitions=4+08)--------------UnionExec+09)----------------ProjectionExec: expr=[1 as a, aa as b]+10)------------------PlaceholderRowExec+11)----------------ProjectionExec: expr=[3 as a, aa as b]+12)------------------PlaceholderRowExec+13)----------------ProjectionExec: expr=[5 as a, bb as b]+14)------------------PlaceholderRowExec+15)----------------ProjectionExec: expr=[7 as a, bb as b]+16)------------------PlaceholderRowExec# check actual result@@ -1313,14 +1311,12 @@ physical_plan01)ProjectionExec: expr=[sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1, aggregate_test_100.c2] ORDER BY [aggregate_test_100.c2 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING@2 as sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1, aggregate_test_100.c2] ORDER BY [aggregate_test_100.c2 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING, count(Int64(1)) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c2 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING@3 as count(*) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c2 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING]02)--BoundedWindowAggExec: wdw=[count(Int64(1)) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c2 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING: Field { "count(Int64(1)) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c2 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING": Int64 }, frame: ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING], mode=[Sorted]03)----SortExec: expr=[c1@0 ASC NULLS LAST, c2@1 ASC NULLS LAST], preserve_partitioning=[true]-04)------CoalesceBatchesExec: target_batch_size=4096-05)--------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=2-06)----------ProjectionExec: expr=[c1@0 as c1, c2@1 as c2, sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1, aggregate_test_100.c2] ORDER BY [aggregate_test_100.c2 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING@3 as sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1, aggregate_test_100.c2] ORDER BY [aggregate_test_100.c2 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING]-07)------------BoundedWindowAggExec: wdw=[sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1, aggregate_test_100.c2] ORDER BY [aggregate_test_100.c2 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING: Field { "sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1, aggregate_test_100.c2] ORDER BY [aggregate_test_100.c2 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING": nullable Int64 }, frame: ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING], mode=[Sorted]-08)--------------SortExec: expr=[c1@0 ASC NULLS LAST, c2@1 ASC NULLS LAST], preserve_partitioning=[true]-09)----------------CoalesceBatchesExec: target_batch_size=4096-10)------------------RepartitionExec: partitioning=Hash([c1@0, c2@1], 2), input_partitions=1-11)--------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c2, c4], file_type=csv, has_header=true+04)------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=2+05)--------ProjectionExec: expr=[c1@0 as c1, c2@1 as c2, sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1, aggregate_test_100.c2] ORDER BY [aggregate_test_100.c2 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING@3 as sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1, aggregate_test_100.c2] ORDER BY [aggregate_test_100.c2 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING]+06)----------BoundedWindowAggExec: wdw=[sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1, aggregate_test_100.c2] ORDER BY [aggregate_test_100.c2 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING: Field { "sum(aggregate_test_100.c4) PARTITION BY [aggregate_test_100.c1, aggregate_test_100.c2] ORDER BY [aggregate_test_100.c2 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING": nullable Int64 }, frame: ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING], mode=[Sorted]+07)------------SortExec: expr=[c1@0 ASC NULLS LAST, c2@1 ASC NULLS LAST], preserve_partitioning=[true]+08)--------------RepartitionExec: partitioning=Hash([c1@0, c2@1], 2), input_partitions=1+09)----------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c2, c4], file_type=csv, has_header=true# test_window_agg_sort_reversed_plan@@ -1882,12 +1878,11 @@ physical_plan04)------AggregateExec: mode=Partial, gby=[], aggr=[count(Int64(1))]05)--------ProjectionExec: expr=[]06)----------AggregateExec: mode=FinalPartitioned, gby=[c1@0 as c1], aggr=[]-07)------------CoalesceBatchesExec: target_batch_size=4096-08)--------------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=2-09)----------------AggregateExec: mode=Partial, gby=[c1@0 as c1], aggr=[]-10)------------------FilterExec: c13@1 != C2GT5KVyOPZpgKVl110TyZO0NcJ434, projection=[c1@0]-11)--------------------RepartitionExec: partitioning=RoundRobinBatch(2), input_partitions=1-12)----------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c13], file_type=csv, has_header=true+07)------------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=2+08)--------------AggregateExec: mode=Partial, gby=[c1@0 as c1], aggr=[]+09)----------------FilterExec: c13@1 != C2GT5KVyOPZpgKVl110TyZO0NcJ434, projection=[c1@0]+10)------------------RepartitionExec: partitioning=RoundRobinBatch(2), input_partitions=1+11)--------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c13], file_type=csv, has_header=truequery I@@ -1926,12 +1921,11 @@ physical_plan02)--SortExec: TopK(fetch=5), expr=[c3@0 ASC NULLS LAST], preserve_partitioning=[true]03)----ProjectionExec: expr=[c3@0 as c3, sum(aggregate_test_100.c9) ORDER BY [aggregate_test_100.c3 DESC NULLS FIRST, aggregate_test_100.c9 DESC NULLS FIRST, aggregate_test_100.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW@2 as sum1, sum(aggregate_test_100.c9) PARTITION BY [aggregate_test_100.c3] ORDER BY [aggregate_test_100.c9 DESC NULLS FIRST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW@3 as sum2]04)------BoundedWindowAggExec: wdw=[sum(aggregate_test_100.c9) PARTITION BY [aggregate_test_100.c3] ORDER BY [aggregate_test_100.c9 DESC NULLS FIRST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "sum(aggregate_test_100.c9) PARTITION BY [aggregate_test_100.c3] ORDER BY [aggregate_test_100.c9 DESC NULLS FIRST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": nullable UInt64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[Sorted]-05)--------CoalesceBatchesExec: target_batch_size=4096-06)----------RepartitionExec: partitioning=Hash([c3@0], 2), input_partitions=1, maintains_sort_order=true-07)------------ProjectionExec: expr=[c3@1 as c3, c9@2 as c9, sum(aggregate_test_100.c9) ORDER BY [aggregate_test_100.c3 DESC NULLS FIRST, aggregate_test_100.c9 DESC NULLS FIRST, aggregate_test_100.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW@3 as sum(aggregate_test_100.c9) ORDER BY [aggregate_test_100.c3 DESC NULLS FIRST, aggregate_test_100.c9 DESC NULLS FIRST, aggregate_test_100.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW]-08)--------------BoundedWindowAggExec: wdw=[sum(aggregate_test_100.c9) ORDER BY [aggregate_test_100.c3 DESC NULLS FIRST, aggregate_test_100.c9 DESC NULLS FIRST, aggregate_test_100.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "sum(aggregate_test_100.c9) ORDER BY [aggregate_test_100.c3 DESC NULLS FIRST, aggregate_test_100.c9 DESC NULLS FIRST, aggregate_test_100.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": nullable UInt64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[Sorted]-09)----------------SortExec: expr=[c3@1 DESC, c9@2 DESC, c2@0 ASC NULLS LAST], preserve_partitioning=[false]-10)------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c2, c3, c9], file_type=csv, has_header=true+05)--------RepartitionExec: partitioning=Hash([c3@0], 2), input_partitions=1, maintains_sort_order=true+06)----------ProjectionExec: expr=[c3@1 as c3, c9@2 as c9, sum(aggregate_test_100.c9) ORDER BY [aggregate_test_100.c3 DESC NULLS FIRST, aggregate_test_100.c9 DESC NULLS FIRST, aggregate_test_100.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW@3 as sum(aggregate_test_100.c9) ORDER BY [aggregate_test_100.c3 DESC NULLS FIRST, aggregate_test_100.c9 DESC NULLS FIRST, aggregate_test_100.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW]+07)------------BoundedWindowAggExec: wdw=[sum(aggregate_test_100.c9) ORDER BY [aggregate_test_100.c3 DESC NULLS FIRST, aggregate_test_100.c9 DESC NULLS FIRST, aggregate_test_100.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "sum(aggregate_test_100.c9) ORDER BY [aggregate_test_100.c3 DESC NULLS FIRST, aggregate_test_100.c9 DESC NULLS FIRST, aggregate_test_100.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": nullable UInt64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[Sorted]+08)--------------SortExec: expr=[c3@1 DESC, c9@2 DESC, c2@0 ASC NULLS LAST], preserve_partitioning=[false]+09)----------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c2, c3, c9], file_type=csv, has_header=true@@ -1967,9 +1961,8 @@ physical_plan02)--ProjectionExec: expr=[c1@0 as c1, row_number() PARTITION BY [aggregate_test_100.c1] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING@1 as rn1]03)----BoundedWindowAggExec: wdw=[row_number() PARTITION BY [aggregate_test_100.c1] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING: Field { "row_number() PARTITION BY [aggregate_test_100.c1] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING": UInt64 }, frame: ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING], mode=[Sorted]04)------SortExec: expr=[c1@0 ASC NULLS LAST], preserve_partitioning=[true]-05)--------CoalesceBatchesExec: target_batch_size=4096-06)----------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=1-07)------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1], file_type=csv, has_header=true+05)--------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=1+06)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1], file_type=csv, has_header=truequery TISELECT c1, ROW_NUMBER() OVER (PARTITION BY c1) as rn1 FROM aggregate_test_100 ORDER BY c1 ASC@@ -2095,9 +2088,8 @@ physical_plan02)--ProjectionExec: expr=[c1@0 as c1, row_number() PARTITION BY [aggregate_test_100.c1] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING@1 as rn1]03)----BoundedWindowAggExec: wdw=[row_number() PARTITION BY [aggregate_test_100.c1] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING: Field { "row_number() PARTITION BY [aggregate_test_100.c1] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING": UInt64 }, frame: ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING], mode=[Sorted]04)------SortExec: expr=[c1@0 ASC NULLS LAST], preserve_partitioning=[true]-05)--------CoalesceBatchesExec: target_batch_size=4096-06)----------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=1-07)------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1], file_type=csv, has_header=true+05)--------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=1+06)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1], file_type=csv, has_header=truestatement okset datafusion.optimizer.repartition_sorts = true;@@ -2123,9 +2115,8 @@ physical_plan05)--------SortExec: expr=[c9@1 ASC NULLS LAST], preserve_partitioning=[true]06)----------BoundedWindowAggExec: wdw=[sum(aggregate_test_100.c9) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 3 FOLLOWING: Field { "sum(aggregate_test_100.c9) PARTITION BY [aggregate_test_100.c1] ORDER BY [aggregate_test_100.c9 ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND 3 FOLLOWING": nullable UInt64 }, frame: ROWS BETWEEN 1 PRECEDING AND 3 FOLLOWING], mode=[Sorted]07)------------SortExec: expr=[c1@0 ASC NULLS LAST, c9@1 ASC NULLS LAST], preserve_partitioning=[true]-08)--------------CoalesceBatchesExec: target_batch_size=4096-09)----------------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=1-10)------------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c9], file_type=csv, has_header=true+08)--------------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=1+09)----------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c9], file_type=csv, has_header=true# test_window_agg_with_global_limitstatement ok@@ -3354,21 +3345,17 @@ logical_planphysical_plan01)ProjectionExec: expr=[sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.a, annotated_data_infinite2.b] ORDER BY [annotated_data_infinite2.c ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW@3 as sum1, sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.b, annotated_data_infinite2.a] ORDER BY [annotated_data_infinite2.c ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW@5 as sum2, sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.a, annotated_data_infinite2.d] ORDER BY [annotated_data_infinite2.b ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW@4 as sum3, sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.d] ORDER BY [annotated_data_infinite2.a ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW@6 as sum4]02)--BoundedWindowAggExec: wdw=[sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.d] ORDER BY [annotated_data_infinite2.a ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.d] ORDER BY [annotated_data_infinite2.a ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": nullable Int64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[Linear]-03)----CoalesceBatchesExec: target_batch_size=4096-04)------RepartitionExec: partitioning=Hash([d@2], 2), input_partitions=2, preserve_order=true, sort_exprs=__common_expr_1@0 ASC NULLS LAST, a@1 ASC NULLS LAST-05)--------ProjectionExec: expr=[__common_expr_1@0 as __common_expr_1, a@1 as a, d@4 as d, sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.a, annotated_data_infinite2.b] ORDER BY [annotated_data_infinite2.c ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW@5 as sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.a, annotated_data_infinite2.b] ORDER BY [annotated_data_infinite2.c ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW, sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.a, annotated_data_infinite2.d] ORDER BY [annotated_data_infinite2.b ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW@6 as sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.a, annotated_data_infinite2.d] ORDER BY [annotated_data_infinite2.b ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW, sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.b, annotated_data_infinite2.a] ORDER BY [annotated_data_infinite2.c ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW@7 as sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.b, annotated_data_infinite2.a] ORDER BY [annotated_data_infinite2.c ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW]-06)----------BoundedWindowAggExec: wdw=[sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.b, annotated_data_infinite2.a] ORDER BY [annotated_data_infinite2.c ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.b, annotated_data_infinite2.a] ORDER BY [annotated_data_infinite2.c ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": nullable Int64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[Sorted]-07)------------CoalesceBatchesExec: target_batch_size=4096-08)--------------RepartitionExec: partitioning=Hash([b@2, a@1], 2), input_partitions=2, preserve_order=true, sort_exprs=a@1 ASC NULLS LAST, b@2 ASC NULLS LAST, c@3 ASC NULLS LAST, __common_expr_1@0 ASC NULLS LAST-09)----------------BoundedWindowAggExec: wdw=[sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.a, annotated_data_infinite2.d] ORDER BY [annotated_data_infinite2.b ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.a, annotated_data_infinite2.d] ORDER BY [annotated_data_infinite2.b ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": nullable Int64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[PartiallySorted([0])]-10)------------------CoalesceBatchesExec: target_batch_size=4096-11)--------------------RepartitionExec: partitioning=Hash([a@1, d@4], 2), input_partitions=2, preserve_order=true, sort_exprs=a@1 ASC NULLS LAST, b@2 ASC NULLS LAST, c@3 ASC NULLS LAST, __common_expr_1@0 ASC NULLS LAST-12)----------------------BoundedWindowAggExec: wdw=[sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.a, annotated_data_infinite2.b] ORDER BY [annotated_data_infinite2.c ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.a, annotated_data_infinite2.b] ORDER BY [annotated_data_infinite2.c ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": nullable Int64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[Sorted]-13)------------------------CoalesceBatchesExec: target_batch_size=4096-14)--------------------------RepartitionExec: partitioning=Hash([a@1, b@2], 2), input_partitions=2, preserve_order=true, sort_exprs=a@1 ASC NULLS LAST, b@2 ASC NULLS LAST, c@3 ASC NULLS LAST, __common_expr_1@0 ASC NULLS LAST-15)----------------------------ProjectionExec: expr=[CAST(a@0 AS Int64) as __common_expr_1, a@0 as a, b@1 as b, c@2 as c, d@3 as d]-16)------------------------------RepartitionExec: partitioning=RoundRobinBatch(2), input_partitions=1, maintains_sort_order=true-17)--------------------------------StreamingTableExec: partition_sizes=1, projection=[a, b, c, d], infinite_source=true, output_ordering=[a@0 ASC NULLS LAST, b@1 ASC NULLS LAST, c@2 ASC NULLS LAST]+03)----RepartitionExec: partitioning=Hash([d@2], 2), input_partitions=2, preserve_order=true, sort_exprs=__common_expr_1@0 ASC NULLS LAST, a@1 ASC NULLS LAST+04)------ProjectionExec: expr=[__common_expr_1@0 as __common_expr_1, a@1 as a, d@4 as d, sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.a, annotated_data_infinite2.b] ORDER BY [annotated_data_infinite2.c ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW@5 as sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.a, annotated_data_infinite2.b] ORDER BY [annotated_data_infinite2.c ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW, sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.a, annotated_data_infinite2.d] ORDER BY [annotated_data_infinite2.b ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW@6 as sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.a, annotated_data_infinite2.d] ORDER BY [annotated_data_infinite2.b ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW, sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.b, annotated_data_infinite2.a] ORDER BY [annotated_data_infinite2.c ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW@7 as sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.b, annotated_data_infinite2.a] ORDER BY [annotated_data_infinite2.c ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW]+05)--------BoundedWindowAggExec: wdw=[sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.b, annotated_data_infinite2.a] ORDER BY [annotated_data_infinite2.c ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.b, annotated_data_infinite2.a] ORDER BY [annotated_data_infinite2.c ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": nullable Int64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[Sorted]+06)----------RepartitionExec: partitioning=Hash([b@2, a@1], 2), input_partitions=2, preserve_order=true, sort_exprs=a@1 ASC NULLS LAST, b@2 ASC NULLS LAST, c@3 ASC NULLS LAST, __common_expr_1@0 ASC NULLS LAST+07)------------BoundedWindowAggExec: wdw=[sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.a, annotated_data_infinite2.d] ORDER BY [annotated_data_infinite2.b ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.a, annotated_data_infinite2.d] ORDER BY [annotated_data_infinite2.b ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": nullable Int64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[PartiallySorted([0])]+08)--------------RepartitionExec: partitioning=Hash([a@1, d@4], 2), input_partitions=2, preserve_order=true, sort_exprs=a@1 ASC NULLS LAST, b@2 ASC NULLS LAST, c@3 ASC NULLS LAST, __common_expr_1@0 ASC NULLS LAST+09)----------------BoundedWindowAggExec: wdw=[sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.a, annotated_data_infinite2.b] ORDER BY [annotated_data_infinite2.c ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "sum(annotated_data_infinite2.a) PARTITION BY [annotated_data_infinite2.a, annotated_data_infinite2.b] ORDER BY [annotated_data_infinite2.c ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": nullable Int64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[Sorted]+10)------------------RepartitionExec: partitioning=Hash([a@1, b@2], 2), input_partitions=2, preserve_order=true, sort_exprs=a@1 ASC NULLS LAST, b@2 ASC NULLS LAST, c@3 ASC NULLS LAST, __common_expr_1@0 ASC NULLS LAST+11)--------------------ProjectionExec: expr=[CAST(a@0 AS Int64) as __common_expr_1, a@0 as a, b@1 as b, c@2 as c, d@3 as d]+12)----------------------RepartitionExec: partitioning=RoundRobinBatch(2), input_partitions=1, maintains_sort_order=true+13)------------------------StreamingTableExec: partition_sizes=1, projection=[a, b, c, d], infinite_source=true, output_ordering=[a@0 ASC NULLS LAST, b@1 ASC NULLS LAST, c@2 ASC NULLS LAST]# reset the partition number 1 againstatement ok@@ -3711,9 +3698,8 @@ physical_plan01)SortPreservingMergeExec: [c@3 ASC NULLS LAST]02)--ProjectionExec: expr=[a0@0 as a0, a@1 as a, b@2 as b, c@3 as c, d@4 as d, avg(multiple_ordered_table_inf.d) PARTITION BY [multiple_ordered_table_inf.d] ORDER BY [multiple_ordered_table_inf.a ASC NULLS LAST] RANGE BETWEEN 10 PRECEDING AND CURRENT ROW@5 as avg_d]03)----BoundedWindowAggExec: wdw=[avg(multiple_ordered_table_inf.d) PARTITION BY [multiple_ordered_table_inf.d] ORDER BY [multiple_ordered_table_inf.a ASC NULLS LAST] RANGE BETWEEN 10 PRECEDING AND CURRENT ROW: Field { "avg(multiple_ordered_table_inf.d) PARTITION BY [multiple_ordered_table_inf.d] ORDER BY [multiple_ordered_table_inf.a ASC NULLS LAST] RANGE BETWEEN 10 PRECEDING AND CURRENT ROW": nullable Float64 }, frame: RANGE BETWEEN 10 PRECEDING AND CURRENT ROW], mode=[Linear]-04)------CoalesceBatchesExec: target_batch_size=4096-05)--------RepartitionExec: partitioning=Hash([d@4], 2), input_partitions=1, maintains_sort_order=true-06)----------StreamingTableExec: partition_sizes=1, projection=[a0, a, b, c, d], infinite_source=true, output_orderings=[[a@1 ASC NULLS LAST, b@2 ASC NULLS LAST], [c@3 ASC NULLS LAST]]+04)------RepartitionExec: partitioning=Hash([d@4], 2), input_partitions=1, maintains_sort_order=true+05)--------StreamingTableExec: partition_sizes=1, projection=[a0, a, b, c, d], infinite_source=true, output_orderings=[[a@1 ASC NULLS LAST, b@2 ASC NULLS LAST], [c@3 ASC NULLS LAST]]# CTAS with NTILE functionstatement ok@@ -4205,10 +4191,9 @@ logical_planphysical_plan01)ProjectionExec: expr=[count(Int64(1)) PARTITION BY [a.a] ORDER BY [a.a ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW@1 as count(*) PARTITION BY [a.a] ORDER BY [a.a ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW]02)--BoundedWindowAggExec: wdw=[count(Int64(1)) PARTITION BY [a.a] ORDER BY [a.a ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "count(Int64(1)) PARTITION BY [a.a] ORDER BY [a.a ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": Int64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[Sorted]-03)----CoalesceBatchesExec: target_batch_size=4096-04)------RepartitionExec: partitioning=Hash([a@0], 2), input_partitions=1-05)--------FilterExec: a@0 = 1-06)----------DataSourceExec: partitions=1, partition_sizes=[1]+03)----RepartitionExec: partitioning=Hash([a@0], 2), input_partitions=1+04)------FilterExec: a@0 = 1+05)--------DataSourceExec: partitions=1, partition_sizes=[1]query Iselect ROW_NUMBER() over (partition by a) from (select * from a where a = 1);@@ -4226,10 +4211,9 @@ logical_planphysical_plan01)ProjectionExec: expr=[row_number() PARTITION BY [a.a] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING@1 as row_number() PARTITION BY [a.a] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING]02)--BoundedWindowAggExec: wdw=[row_number() PARTITION BY [a.a] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING: Field { "row_number() PARTITION BY [a.a] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING": UInt64 }, frame: ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING], mode=[Sorted]-03)----CoalesceBatchesExec: target_batch_size=4096-04)------RepartitionExec: partitioning=Hash([a@0], 2), input_partitions=1-05)--------FilterExec: a@0 = 1-06)----------DataSourceExec: partitions=1, partition_sizes=[1]+03)----RepartitionExec: partitioning=Hash([a@0], 2), input_partitions=1+04)------FilterExec: a@0 = 1+05)--------DataSourceExec: partitions=1, partition_sizes=[1]# LAG window function IGNORE/RESPECT NULLS support with ascending order and default offset 1query TTTTTT@@ -5294,11 +5278,10 @@ physical_plan02)--ProjectionExec: expr=[c1@0 as c1, c2@1 as c2, rank() PARTITION BY [t1.c1] ORDER BY [t1.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW@2 as rank]03)----BoundedWindowAggExec: wdw=[rank() PARTITION BY [t1.c1] ORDER BY [t1.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "rank() PARTITION BY [t1.c1] ORDER BY [t1.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": UInt64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[Sorted]04)------SortExec: expr=[c1@0 ASC NULLS LAST, c2@1 ASC NULLS LAST], preserve_partitioning=[true]-05)--------CoalesceBatchesExec: target_batch_size=1-06)----------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=2-07)------------FilterExec: c1@0 = 2 OR c1@0 = 3-08)--------------RepartitionExec: partitioning=RoundRobinBatch(2), input_partitions=1-09)----------------DataSourceExec: partitions=1, partition_sizes=[1]+05)--------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=2+06)----------FilterExec: c1@0 = 2 OR c1@0 = 3+07)------------RepartitionExec: partitioning=RoundRobinBatch(2), input_partitions=1+08)--------------DataSourceExec: partitions=1, partition_sizes=[1]query IIIselect c1, c2, rank@@ -5336,9 +5319,8 @@ physical_plan03)----FilterExec: c2@1 >= 1004)------BoundedWindowAggExec: wdw=[rank() PARTITION BY [t1.c1] ORDER BY [t1.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "rank() PARTITION BY [t1.c1] ORDER BY [t1.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": UInt64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[Sorted]05)--------SortExec: expr=[c1@0 ASC NULLS LAST, c2@1 ASC NULLS LAST], preserve_partitioning=[true]-06)----------CoalesceBatchesExec: target_batch_size=1-07)------------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=1-08)--------------DataSourceExec: partitions=1, partition_sizes=[1]+06)----------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=1+07)------------DataSourceExec: partitions=1, partition_sizes=[1]query IIIselect c1, c2, rank@@ -5376,11 +5358,10 @@ physical_plan03)----FilterExec: c2@1 = 1004)------BoundedWindowAggExec: wdw=[rank() PARTITION BY [t1.c1] ORDER BY [t1.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "rank() PARTITION BY [t1.c1] ORDER BY [t1.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": UInt64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[Sorted]05)--------SortExec: expr=[c2@1 ASC NULLS LAST], preserve_partitioning=[true]-06)----------CoalesceBatchesExec: target_batch_size=1-07)------------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=2-08)--------------FilterExec: c1@0 = 1-09)----------------RepartitionExec: partitioning=RoundRobinBatch(2), input_partitions=1-10)------------------DataSourceExec: partitions=1, partition_sizes=[1]+06)----------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=2+07)------------FilterExec: c1@0 = 1+08)--------------RepartitionExec: partitioning=RoundRobinBatch(2), input_partitions=1+09)----------------DataSourceExec: partitions=1, partition_sizes=[1]query IIIselect c1, c2, rank@@ -5415,9 +5396,8 @@ physical_plan03)----FilterExec: c1@0 = 1 OR c2@1 = 1004)------BoundedWindowAggExec: wdw=[rank() PARTITION BY [t1.c1] ORDER BY [t1.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "rank() PARTITION BY [t1.c1] ORDER BY [t1.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": UInt64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[Sorted]05)--------SortExec: expr=[c1@0 ASC NULLS LAST, c2@1 ASC NULLS LAST], preserve_partitioning=[true]-06)----------CoalesceBatchesExec: target_batch_size=1-07)------------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=1-08)--------------DataSourceExec: partitions=1, partition_sizes=[1]+06)----------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=1+07)------------DataSourceExec: partitions=1, partition_sizes=[1]query IIIselect c1, c2, rank@@ -5457,15 +5437,13 @@ physical_plan03)----ProjectionExec: expr=[c1@0 as c1, c2@1 as c2, rank() PARTITION BY [t1.c1] ORDER BY [t1.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW@2 as rank1, rank() PARTITION BY [t1.c2, t1.c1] ORDER BY [t1.c1 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW@3 as rank2]04)------BoundedWindowAggExec: wdw=[rank() PARTITION BY [t1.c2, t1.c1] ORDER BY [t1.c1 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "rank() PARTITION BY [t1.c2, t1.c1] ORDER BY [t1.c1 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": UInt64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[Sorted]05)--------SortExec: expr=[c2@1 ASC NULLS LAST, c1@0 ASC NULLS LAST], preserve_partitioning=[true]-06)----------CoalesceBatchesExec: target_batch_size=1-07)------------RepartitionExec: partitioning=Hash([c2@1, c1@0], 2), input_partitions=2-08)--------------BoundedWindowAggExec: wdw=[rank() PARTITION BY [t1.c1] ORDER BY [t1.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "rank() PARTITION BY [t1.c1] ORDER BY [t1.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": UInt64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[Sorted]-09)----------------SortExec: expr=[c1@0 ASC NULLS LAST, c2@1 ASC NULLS LAST], preserve_partitioning=[true]-10)------------------CoalesceBatchesExec: target_batch_size=1-11)--------------------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=2-12)----------------------FilterExec: c1@0 > 1-13)------------------------RepartitionExec: partitioning=RoundRobinBatch(2), input_partitions=1-14)--------------------------DataSourceExec: partitions=1, partition_sizes=[1]+06)----------RepartitionExec: partitioning=Hash([c2@1, c1@0], 2), input_partitions=2+07)------------BoundedWindowAggExec: wdw=[rank() PARTITION BY [t1.c1] ORDER BY [t1.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "rank() PARTITION BY [t1.c1] ORDER BY [t1.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": UInt64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[Sorted]+08)--------------SortExec: expr=[c1@0 ASC NULLS LAST, c2@1 ASC NULLS LAST], preserve_partitioning=[true]+09)----------------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=2+10)------------------FilterExec: c1@0 > 1+11)--------------------RepartitionExec: partitioning=RoundRobinBatch(2), input_partitions=1+12)----------------------DataSourceExec: partitions=1, partition_sizes=[1]query IIIIselect c1, c2, rank1, rank2@@ -5507,14 +5485,12 @@ physical_plan03)----ProjectionExec: expr=[c1@0 as c1, c2@1 as c2, rank() PARTITION BY [t1.c1] ORDER BY [t1.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW@2 as rank1, rank() PARTITION BY [t1.c2, t1.c1] ORDER BY [t1.c1 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW@3 as rank2]04)------BoundedWindowAggExec: wdw=[rank() PARTITION BY [t1.c2, t1.c1] ORDER BY [t1.c1 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "rank() PARTITION BY [t1.c2, t1.c1] ORDER BY [t1.c1 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": UInt64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[Sorted]05)--------SortExec: expr=[c2@1 ASC NULLS LAST, c1@0 ASC NULLS LAST], preserve_partitioning=[true]-06)----------CoalesceBatchesExec: target_batch_size=1-07)------------RepartitionExec: partitioning=Hash([c2@1, c1@0], 2), input_partitions=2-08)--------------FilterExec: c2@1 > 1-09)----------------BoundedWindowAggExec: wdw=[rank() PARTITION BY [t1.c1] ORDER BY [t1.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "rank() PARTITION BY [t1.c1] ORDER BY [t1.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": UInt64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[Sorted]-10)------------------SortExec: expr=[c1@0 ASC NULLS LAST, c2@1 ASC NULLS LAST], preserve_partitioning=[true]-11)--------------------CoalesceBatchesExec: target_batch_size=1-12)----------------------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=1-13)------------------------DataSourceExec: partitions=1, partition_sizes=[1]+06)----------RepartitionExec: partitioning=Hash([c2@1, c1@0], 2), input_partitions=2+07)------------FilterExec: c2@1 > 1+08)--------------BoundedWindowAggExec: wdw=[rank() PARTITION BY [t1.c1] ORDER BY [t1.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW: Field { "rank() PARTITION BY [t1.c1] ORDER BY [t1.c2 ASC NULLS LAST] RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW": UInt64 }, frame: RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], mode=[Sorted]+09)----------------SortExec: expr=[c1@0 ASC NULLS LAST, c2@1 ASC NULLS LAST], preserve_partitioning=[true]+10)------------------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=1+11)--------------------DataSourceExec: partitions=1, partition_sizes=[1]query IIIIselect c1, c2, rank1, rank2@@ -5571,9 +5547,8 @@ physical_plan01)SortPreservingMergeExec: [c1@0 ASC NULLS LAST, sum_c9@1 ASC NULLS LAST]02)--ProjectionExec: expr=[c1@0 as c1, sum(aggregate_test_100_ordered.c9) PARTITION BY [aggregate_test_100_ordered.c1] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING@2 as sum_c9]03)----WindowAggExec: wdw=[sum(aggregate_test_100_ordered.c9) PARTITION BY [aggregate_test_100_ordered.c1] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING: Ok(Field { name: "sum(aggregate_test_100_ordered.c9) PARTITION BY [aggregate_test_100_ordered.c1] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING", data_type: UInt64, nullable: true }), frame: WindowFrame { units: Rows, start_bound: Preceding(UInt64(NULL)), end_bound: Following(UInt64(NULL)), is_causal: false }]-04)------CoalesceBatchesExec: target_batch_size=1-05)--------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=1, maintains_sort_order=true-06)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c9], output_ordering=[c1@0 ASC NULLS LAST], file_type=csv, has_header=true+04)------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=1, maintains_sort_order=true+05)--------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c9], output_ordering=[c1@0 ASC NULLS LAST], file_type=csv, has_header=truequery TTEXPLAIN SELECT SUM(c9) OVER() as sum_c9 FROM aggregate_test_100_ordered ORDER BY sum_c9;@@ -5601,9 +5576,8 @@ physical_plan01)SortPreservingMergeExec: [c1@0 ASC NULLS LAST, min_c5@1 DESC NULLS LAST]02)--ProjectionExec: expr=[c1@0 as c1, min(aggregate_test_100_ordered.c5) PARTITION BY [aggregate_test_100_ordered.c1] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING@2 as min_c5]03)----WindowAggExec: wdw=[min(aggregate_test_100_ordered.c5) PARTITION BY [aggregate_test_100_ordered.c1] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING: Ok(Field { name: "min(aggregate_test_100_ordered.c5) PARTITION BY [aggregate_test_100_ordered.c1] ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING", data_type: Int32, nullable: true }), frame: WindowFrame { units: Rows, start_bound: Preceding(UInt64(NULL)), end_bound: Following(UInt64(NULL)), is_causal: false }]-04)------CoalesceBatchesExec: target_batch_size=1-05)--------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=1, maintains_sort_order=true-06)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c5], output_ordering=[c1@0 ASC NULLS LAST], file_type=csv, has_header=true+04)------RepartitionExec: partitioning=Hash([c1@0], 2), input_partitions=1, maintains_sort_order=true+05)--------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c5], output_ordering=[c1@0 ASC NULLS LAST], file_type=csv, has_header=truequery TTEXPLAIN SELECT MAX(c5) OVER() as max_c5 FROM aggregate_test_100_ordered ORDER BY max_c5;@@ -5800,9 +5774,8 @@ physical_plan02)--ProjectionExec: expr=[k@0 as k, time@2 as time, count(table_test_distinct_count.v) PARTITION BY [table_test_distinct_count.k] ORDER BY [table_test_distinct_count.time ASC NULLS LAST] RANGE BETWEEN 2 minutes PRECEDING AND CURRENT ROW@3 as normal_count, count(DISTINCT table_test_distinct_count.v) PARTITION BY [table_test_distinct_count.k] ORDER BY [table_test_distinct_count.time ASC NULLS LAST] RANGE BETWEEN 2 minutes PRECEDING AND CURRENT ROW@4 as distinct_count]03)----BoundedWindowAggExec: wdw=[count(table_test_distinct_count.v) PARTITION BY [table_test_distinct_count.k] ORDER BY [table_test_distinct_count.time ASC NULLS LAST] RANGE BETWEEN 2 minutes PRECEDING AND CURRENT ROW: Field { "count(table_test_distinct_count.v) PARTITION BY [table_test_distinct_count.k] ORDER BY [table_test_distinct_count.time ASC NULLS LAST] RANGE BETWEEN 2 minutes PRECEDING AND CURRENT ROW": Int64 }, frame: RANGE BETWEEN IntervalMonthDayNano { months: 0, days: 0, nanoseconds: 120000000000 } PRECEDING AND CURRENT ROW, count(DISTINCT table_test_distinct_count.v) PARTITION BY [table_test_distinct_count.k] ORDER BY [table_test_distinct_count.time ASC NULLS LAST] RANGE BETWEEN 2 minutes PRECEDING AND CURRENT ROW: Field { "count(DISTINCT table_test_distinct_count.v) PARTITION BY [table_test_distinct_count.k] ORDER BY [table_test_distinct_count.time ASC NULLS LAST] RANGE BETWEEN 2 minutes PRECEDING AND CURRENT ROW": Int64 }, frame: RANGE BETWEEN IntervalMonthDayNano { months: 0, days: 0, nanoseconds: 120000000000 } PRECEDING AND CURRENT ROW], mode=[Sorted]04)------SortExec: expr=[k@0 ASC NULLS LAST, time@2 ASC NULLS LAST], preserve_partitioning=[true]-05)--------CoalesceBatchesExec: target_batch_size=1-06)----------RepartitionExec: partitioning=Hash([k@0], 2), input_partitions=2-07)------------DataSourceExec: partitions=2, partition_sizes=[5, 4]+05)--------RepartitionExec: partitioning=Hash([k@0], 2), input_partitions=2+06)----------DataSourceExec: partitions=2, partition_sizes=[5, 4]# Add testing for distinct sum@@ -5863,10 +5836,9 @@ physical_plan02)--ProjectionExec: expr=[k@1 as k, time@2 as time, sum(table_test_distinct_count.v) PARTITION BY [table_test_distinct_count.k] ORDER BY [table_test_distinct_count.time ASC NULLS LAST] RANGE BETWEEN 2 minutes PRECEDING AND CURRENT ROW@3 as sum_v, sum(DISTINCT table_test_distinct_count.v) PARTITION BY [table_test_distinct_count.k] ORDER BY [table_test_distinct_count.time ASC NULLS LAST] RANGE BETWEEN 2 minutes PRECEDING AND CURRENT ROW@4 as sum_distinct_v]03)----BoundedWindowAggExec: wdw=[sum(table_test_distinct_count.v) PARTITION BY [table_test_distinct_count.k] ORDER BY [table_test_distinct_count.time ASC NULLS LAST] RANGE BETWEEN 2 minutes PRECEDING AND CURRENT ROW: Field { "sum(table_test_distinct_count.v) PARTITION BY [table_test_distinct_count.k] ORDER BY [table_test_distinct_count.time ASC NULLS LAST] RANGE BETWEEN 2 minutes PRECEDING AND CURRENT ROW": nullable Int64 }, frame: RANGE BETWEEN IntervalMonthDayNano { months: 0, days: 0, nanoseconds: 120000000000 } PRECEDING AND CURRENT ROW, sum(DISTINCT table_test_distinct_count.v) PARTITION BY [table_test_distinct_count.k] ORDER BY [table_test_distinct_count.time ASC NULLS LAST] RANGE BETWEEN 2 minutes PRECEDING AND CURRENT ROW: Field { "sum(DISTINCT table_test_distinct_count.v) PARTITION BY [table_test_distinct_count.k] ORDER BY [table_test_distinct_count.time ASC NULLS LAST] RANGE BETWEEN 2 minutes PRECEDING AND CURRENT ROW": nullable Int64 }, frame: RANGE BETWEEN IntervalMonthDayNano { months: 0, days: 0, nanoseconds: 120000000000 } PRECEDING AND CURRENT ROW], mode=[Sorted]04)------SortExec: expr=[k@1 ASC NULLS LAST, time@2 ASC NULLS LAST], preserve_partitioning=[true]-05)--------CoalesceBatchesExec: target_batch_size=1-06)----------RepartitionExec: partitioning=Hash([k@1], 2), input_partitions=2-07)------------ProjectionExec: expr=[CAST(v@1 AS Int64) as __common_expr_1, k@0 as k, time@2 as time]-08)--------------DataSourceExec: partitions=2, partition_sizes=[5, 4]+05)--------RepartitionExec: partitioning=Hash([k@1], 2), input_partitions=2+06)----------ProjectionExec: expr=[CAST(v@1 AS Int64) as __common_expr_1, k@0 as k, time@2 as time]+07)------------DataSourceExec: partitions=2, partition_sizes=[5, 4]# FILTER clause with window functionsdiff --git a/datafusion/sqllogictest/test_files/window_limits.slt b/datafusion/sqllogictest/test_files/window_limits.sltindex 8729e5ed41..3a10cbb96a 100644--- a/datafusion/sqllogictest/test_files/window_limits.slt+++ b/datafusion/sqllogictest/test_files/window_limits.slt@@ -543,9 +543,8 @@ physical_plan02)--ProjectionExec: expr=[depname@0 as depname, empno@1 as empno, salary@2 as salary, sum(employees.salary) PARTITION BY [employees.depname] ORDER BY [employees.empno ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND CURRENT ROW@3 as running_sum]03)----BoundedWindowAggExec: wdw=[sum(employees.salary) PARTITION BY [employees.depname] ORDER BY [employees.empno ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND CURRENT ROW: Field { "sum(employees.salary) PARTITION BY [employees.depname] ORDER BY [employees.empno ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND CURRENT ROW": nullable UInt64 }, frame: ROWS BETWEEN 1 PRECEDING AND CURRENT ROW], mode=[Sorted]04)------SortExec: expr=[depname@0 ASC NULLS LAST, empno@1 ASC NULLS LAST], preserve_partitioning=[true]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([depname@0], 4), input_partitions=1-07)------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100_with_dates.csv]]}, projection=[depname, empno, salary], file_type=csv, has_header=true+05)--------RepartitionExec: partitioning=Hash([depname@0], 4), input_partitions=1+06)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100_with_dates.csv]]}, projection=[depname, empno, salary], file_type=csv, has_header=true# should handle partition by optimizedstatement ok@@ -588,9 +587,8 @@ physical_plan02)--ProjectionExec: expr=[depname@0 as depname, empno@1 as empno, salary@2 as salary, sum(employees.salary) PARTITION BY [employees.depname] ORDER BY [employees.empno ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND CURRENT ROW@3 as running_sum]03)----BoundedWindowAggExec: wdw=[sum(employees.salary) PARTITION BY [employees.depname] ORDER BY [employees.empno ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND CURRENT ROW: Field { "sum(employees.salary) PARTITION BY [employees.depname] ORDER BY [employees.empno ASC NULLS LAST] ROWS BETWEEN 1 PRECEDING AND CURRENT ROW": nullable UInt64 }, frame: ROWS BETWEEN 1 PRECEDING AND CURRENT ROW], mode=[Sorted]04)------SortExec: TopK(fetch=5), expr=[depname@0 ASC NULLS LAST, empno@1 ASC NULLS LAST], preserve_partitioning=[true]-05)--------CoalesceBatchesExec: target_batch_size=8192-06)----------RepartitionExec: partitioning=Hash([depname@0], 4), input_partitions=1-07)------------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100_with_dates.csv]]}, projection=[depname, empno, salary], file_type=csv, has_header=true+05)--------RepartitionExec: partitioning=Hash([depname@0], 4), input_partitions=1+06)----------DataSourceExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100_with_dates.csv]]}, projection=[depname, empno, salary], file_type=csv, has_header=true# unbounded followingstatement ok