Revert "Test + workaround for SanityCheck plan"

This reverts commit 3819810.
influxdata · Feb 3, 2025 · 7b9263f · 7b9263f
1 parent 6762c73
commit 7b9263f
Show file tree

Hide file tree

Showing 2 changed files with 49 additions and 37 deletions.
diff --git a/datafusion/physical-optimizer/src/sanity_checker.rs b/datafusion/physical-optimizer/src/sanity_checker.rs
@@ -32,8 +32,6 @@ use datafusion_common::tree_node::{Transformed, TransformedResult, TreeNode};
 use datafusion_physical_expr::intervals::utils::{check_support, is_datatype_supported};
 use datafusion_physical_plan::execution_plan::{Boundedness, EmissionType};
 use datafusion_physical_plan::joins::SymmetricHashJoinExec;
-use datafusion_physical_plan::sorts::sort::SortExec;
-use datafusion_physical_plan::union::UnionExec;
 use datafusion_physical_plan::{get_plan_string, ExecutionPlanProperties};
 
 use crate::PhysicalOptimizerRule;
@@ -137,14 +135,6 @@ pub fn check_plan_sanity(
         plan.required_input_ordering(),
         plan.required_input_distribution(),
     ) {
-        // TEMP HACK WORKAROUND https://github.com/apache/datafusion/issues/11492
-        if child.as_any().downcast_ref::<UnionExec>().is_some() {
-            continue;
-        }
-        if child.as_any().downcast_ref::<SortExec>().is_some() {
-            continue;
-        }
-
         let child_eq_props = child.equivalence_properties();
         if let Some(sort_req) = sort_req {
             if !child_eq_props.ordering_satisfy_requirement(&sort_req) {

diff --git a/datafusion/sqllogictest/test_files/union.slt b/datafusion/sqllogictest/test_files/union.slt
@@ -538,9 +538,6 @@ physical_plan
 # Clean up after the test
 ########
 
-statement ok
-drop table t
-
 statement ok
 drop table t1;
 
@@ -781,36 +778,61 @@ select make_array(make_array(1)) x UNION ALL SELECT make_array(arrow_cast(make_a
 [[-1]]
 [[1]]
 
-###
-# Test for https://github.com/apache/datafusion/issues/11492
-###
-
-# Input data is
-# a,b,c
-# 1,2,3
-
 statement ok
-CREATE EXTERNAL TABLE t (
-  a INT,
-  b INT,
-  c INT
+CREATE EXTERNAL TABLE aggregate_test_100 (
+  c1  VARCHAR NOT NULL,
+  c2  TINYINT NOT NULL,
+  c3  SMALLINT NOT NULL,
+  c4  SMALLINT,
+  c5  INT,
+  c6  BIGINT NOT NULL,
+  c7  SMALLINT NOT NULL,
+  c8  INT NOT NULL,
+  c9  BIGINT UNSIGNED NOT NULL,
+  c10 VARCHAR NOT NULL,
+  c11 FLOAT NOT NULL,
+  c12 DOUBLE NOT NULL,
+  c13 VARCHAR NOT NULL
 )
 STORED AS CSV
-LOCATION '../core/tests/data/example.csv'
-WITH ORDER (a ASC)
+LOCATION '../../testing/data/csv/aggregate_test_100.csv'
 OPTIONS ('format.has_header' 'true');
 
-query T
-SELECT (SELECT a from t ORDER BY a) UNION ALL (SELECT 'bar' as a from t) ORDER BY a;
-----
-1
-bar
+statement ok
+set datafusion.execution.batch_size = 2;
 
-query I
-SELECT (SELECT a from t ORDER BY a) UNION ALL (SELECT NULL as a from t) ORDER BY a;
+# Constant value tracking across union
+query TT
+explain
+SELECT * FROM(
+(
+    SELECT * FROM aggregate_test_100 WHERE c1='a'
+)
+UNION ALL
+(
+    SELECT * FROM aggregate_test_100 WHERE c1='a'
+))
+ORDER BY c1
 ----
-1
-NULL 
+logical_plan
+01)Sort: aggregate_test_100.c1 ASC NULLS LAST
+02)--Union
+03)----Filter: aggregate_test_100.c1 = Utf8("a")
+04)------TableScan: aggregate_test_100 projection=[c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13], partial_filters=[aggregate_test_100.c1 = Utf8("a")]
+05)----Filter: aggregate_test_100.c1 = Utf8("a")
+06)------TableScan: aggregate_test_100 projection=[c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13], partial_filters=[aggregate_test_100.c1 = Utf8("a")]
+physical_plan
+01)CoalescePartitionsExec
+02)--UnionExec
+03)----CoalesceBatchesExec: target_batch_size=2
+04)------FilterExec: c1@0 = a
+05)--------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1
+06)----------CsvExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13], has_header=true
+07)----CoalesceBatchesExec: target_batch_size=2
+08)------FilterExec: c1@0 = a
+09)--------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1
+10)----------CsvExec: file_groups={1 group: [[WORKSPACE_ROOT/testing/data/csv/aggregate_test_100.csv]]}, projection=[c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13], has_header=true
 
+# Clean up after the test
 statement ok
-drop table t
+drop table aggregate_test_100;