Merge pull request #58660 from ClickHouse/backport/23.12/58608

Backport #58608 to 23.12: Remove order by requierement in PASTE JOIN
ClickHouse · Jan 10, 2024 · e502a3f · e502a3f
2 parents 56527c7 + e298838
commit e502a3f
Show file tree

Hide file tree

Showing 4 changed files with 43 additions and 3 deletions.
diff --git a/docs/en/sql-reference/statements/select/join.md b/docs/en/sql-reference/statements/select/join.md
@@ -296,6 +296,34 @@ PASTE JOIN
 │ 1 │    0 │
 └───┴──────┘
 ```
+Note: In this case result can be nondeterministic if the reading is parallel. Example:
+```SQL
+SELECT *
+FROM
+(
+    SELECT number AS a
+    FROM numbers_mt(5)
+) AS t1
+PASTE JOIN
+(
+    SELECT number AS a
+    FROM numbers(10)
+    ORDER BY a DESC
+) AS t2
+SETTINGS max_block_size = 2;
+
+┌─a─┬─t2.a─┐
+│ 2 │    9 │
+│ 3 │    8 │
+└───┴──────┘
+┌─a─┬─t2.a─┐
+│ 0 │    7 │
+│ 1 │    6 │
+└───┴──────┘
+┌─a─┬─t2.a─┐
+│ 4 │    5 │
+└───┴──────┘
+```
 
 ## Distributed JOIN
 

diff --git a/src/QueryPipeline/QueryPipelineBuilder.cpp b/src/QueryPipeline/QueryPipelineBuilder.cpp
@@ -37,7 +37,6 @@ namespace ErrorCodes
 {
     extern const int LOGICAL_ERROR;
     extern const int NOT_IMPLEMENTED;
-    extern const int BAD_ARGUMENTS;
 }
 
 void QueryPipelineBuilder::checkInitialized()
@@ -357,7 +356,10 @@ std::unique_ptr<QueryPipelineBuilder> QueryPipelineBuilder::joinPipelinesYShaped
     left->pipe.dropExtremes();
     right->pipe.dropExtremes();
     if ((left->getNumStreams() != 1 || right->getNumStreams() != 1) && join->getTableJoin().kind() == JoinKind::Paste)
-        throw Exception(ErrorCodes::BAD_ARGUMENTS, "Paste JOIN requires sorted tables only");
+    {
+        left->pipe.resize(1, true);
+        right->pipe.resize(1, true);
+    }
     else if (left->getNumStreams() != 1 || right->getNumStreams() != 1)
         throw Exception(ErrorCodes::LOGICAL_ERROR, "Join is supported only for pipelines with one output port");
 

diff --git a/tests/queries/0_stateless/02933_paste_join.reference b/tests/queries/0_stateless/02933_paste_join.reference
@@ -72,3 +72,13 @@ UInt64
 UInt64
 UInt64
 UInt64
+0	9
+1	8
+2	7
+3	6
+4	5
+5	4
+6	3
+7	2
+8	1
+9	0
diff --git a/tests/queries/0_stateless/02933_paste_join.sql b/tests/queries/0_stateless/02933_paste_join.sql
@@ -32,6 +32,6 @@ INSERT INTO t2 SELECT number, number FROM numbers(15, 15);
 SELECT * FROM ( SELECT * from t1 ) t1 PASTE JOIN ( SELECT * from t2 ) t2 SETTINGS max_threads = 1;
 SELECT toTypeName(a) FROM (SELECT number as a FROM numbers(11)) t1 PASTE JOIN (select number as a from numbers(10)) t2 SETTINGS join_use_nulls = 1;
 SET max_threads = 2;
+select * from (SELECT number as a FROM numbers_mt(10)) t1 PASTE JOIN (select number as a from numbers(10) ORDER BY a DESC) t2 SETTINGS max_block_size=10;
 select * from (SELECT number as a FROM numbers(10)) t1 ANY PASTE JOIN (select number as a from numbers(10)) t2; -- { clientError SYNTAX_ERROR }
 select * from (SELECT number as a FROM numbers(10)) t1 ALL PASTE JOIN (select number as a from numbers(10)) t2; -- { clientError SYNTAX_ERROR }
-select * from (SELECT number as a FROM numbers_mt(10)) t1 PASTE JOIN (select number as a from numbers(10) ORDER BY a DESC) t2 SETTINGS max_block_size=3; -- { serverError BAD_ARGUMENTS }