From acfe2876b57aa4766e15df4a955991c19eb9dc8e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ra=C3=BAl=20Mar=C3=ADn?= <git@rmr.ninja>
Date: Mon, 3 Jun 2024 21:06:02 +0200
Subject: [PATCH] Fix OrderByLimitByDuplicateEliminationVisitor across
 subqueries

---
 ...OrderByLimitByDuplicateEliminationPass.cpp |  7 +---
 .../03165_order_by_duplicate.reference        | 39 +++++++++++++++++++
 .../0_stateless/03165_order_by_duplicate.sql  | 16 ++++++++
 3 files changed, 57 insertions(+), 5 deletions(-)
 create mode 100644 tests/queries/0_stateless/03165_order_by_duplicate.reference
 create mode 100644 tests/queries/0_stateless/03165_order_by_duplicate.sql

diff --git a/src/Analyzer/Passes/OrderByLimitByDuplicateEliminationPass.cpp b/src/Analyzer/Passes/OrderByLimitByDuplicateEliminationPass.cpp
index 26ca5984b49..15919c4a2fe 100644
--- a/src/Analyzer/Passes/OrderByLimitByDuplicateEliminationPass.cpp
+++ b/src/Analyzer/Passes/OrderByLimitByDuplicateEliminationPass.cpp
@@ -22,6 +22,7 @@ public:
 
         if (query_node->hasOrderBy())
         {
+            QueryTreeNodeConstRawPtrWithHashSet unique_expressions_nodes_set;
             QueryTreeNodes result_nodes;
 
             auto & query_order_by_nodes = query_node->getOrderBy().getNodes();
@@ -45,10 +46,9 @@ public:
             query_order_by_nodes = std::move(result_nodes);
         }
 
-        unique_expressions_nodes_set.clear();
-
         if (query_node->hasLimitBy())
         {
+            QueryTreeNodeConstRawPtrWithHashSet unique_expressions_nodes_set;
             QueryTreeNodes result_nodes;
 
             auto & query_limit_by_nodes = query_node->getLimitBy().getNodes();
@@ -63,9 +63,6 @@ public:
             query_limit_by_nodes = std::move(result_nodes);
         }
     }
-
-private:
-    QueryTreeNodeConstRawPtrWithHashSet unique_expressions_nodes_set;
 };
 
 }
diff --git a/tests/queries/0_stateless/03165_order_by_duplicate.reference b/tests/queries/0_stateless/03165_order_by_duplicate.reference
new file mode 100644
index 00000000000..5d5e7a33f4a
--- /dev/null
+++ b/tests/queries/0_stateless/03165_order_by_duplicate.reference
@@ -0,0 +1,39 @@
+QUERY id: 0
+  PROJECTION COLUMNS
+    id UInt64
+  PROJECTION
+    LIST id: 1, nodes: 1
+      COLUMN id: 2, column_name: id, result_type: UInt64, source_id: 3
+  JOIN TREE
+    TABLE id: 3, alias: __table1, table_name: default.test, final: 1
+  WHERE
+    FUNCTION id: 4, function_name: in, function_type: ordinary, result_type: UInt8
+      ARGUMENTS
+        LIST id: 5, nodes: 2
+          COLUMN id: 2, column_name: id, result_type: UInt64, source_id: 3
+          QUERY id: 6, is_subquery: 1, is_distinct: 1
+            PROJECTION COLUMNS
+              id UInt64
+            PROJECTION
+              LIST id: 7, nodes: 1
+                COLUMN id: 8, column_name: id, result_type: UInt64, source_id: 9
+            JOIN TREE
+              TABLE id: 9, alias: __table1, table_name: default.test, final: 1
+            ORDER BY
+              LIST id: 10, nodes: 1
+                SORT id: 11, sort_direction: ASCENDING, with_fill: 0
+                  EXPRESSION
+                    COLUMN id: 8, column_name: id, result_type: UInt64, source_id: 9
+            LIMIT
+              CONSTANT id: 12, constant_value: UInt64_4, constant_value_type: UInt64
+  ORDER BY
+    LIST id: 13, nodes: 1
+      SORT id: 14, sort_direction: ASCENDING, with_fill: 0
+        EXPRESSION
+          COLUMN id: 2, column_name: id, result_type: UInt64, source_id: 3
+  LIMIT BY LIMIT
+    CONSTANT id: 15, constant_value: UInt64_1, constant_value_type: UInt64
+  LIMIT BY
+    LIST id: 16, nodes: 1
+      COLUMN id: 2, column_name: id, result_type: UInt64, source_id: 3
+  SETTINGS allow_experimental_analyzer=1
diff --git a/tests/queries/0_stateless/03165_order_by_duplicate.sql b/tests/queries/0_stateless/03165_order_by_duplicate.sql
new file mode 100644
index 00000000000..0054cbc36a6
--- /dev/null
+++ b/tests/queries/0_stateless/03165_order_by_duplicate.sql
@@ -0,0 +1,16 @@
+CREATE TABLE test
+ENGINE = ReplacingMergeTree
+PRIMARY KEY id
+AS SELECT number AS id FROM numbers(100);
+
+EXPLAIN QUERY TREE SELECT id
+FROM test FINAL
+WHERE id IN (
+    SELECT DISTINCT id
+    FROM test FINAL
+    ORDER BY id ASC
+    LIMIT 4
+)
+ORDER BY id ASC
+LIMIT 1 BY id
+SETTINGS allow_experimental_analyzer = 1;