Fix after review

Author: ianton-ru

src/Storages/IStorageCluster.cpp

@@ -24,6 +24,7 @@
 #include <Analyzer/QueryTreeBuilder.h>
 #include <Analyzer/QueryNode.h>
 #include <Analyzer/ColumnNode.h>
+#include <Analyzer/ConstantNode.h>
 #include <Analyzer/JoinNode.h>
 #include <Analyzer/InDepthQueryTreeVisitor.h>
 #include <Analyzer/Utils.h>
@@ -105,9 +106,9 @@ class SearcherVisitor : public InDepthQueryTreeVisitorWithContext<SearcherVisito
 
     explicit SearcherVisitor(std::unordered_set<QueryTreeNodeType> types_, ContextPtr context) : Base(context), types(types_) {}
 
-    bool needChildVisit(QueryTreeNodePtr &, QueryTreeNodePtr & /*child*/)
+    bool needChildVisit(QueryTreeNodePtr & /*parent*/, QueryTreeNodePtr & /*child*/)
     {
-        return !passed_node;
+        return getSubqueryDepth() <= 2 && !passed_node;
     }
 
     void enterImpl(QueryTreeNodePtr & node)
@@ -245,12 +246,22 @@ void IStorageCluster::updateQueryWithJoinToSendIfNeeded(
             collector.visit(modified_query_tree);
             const auto & columns = collector.getColumns();
 
-            query_node.resolveProjectionColumns(columns);
-            auto column_nodes_to_select = std::make_shared<ListNode>();
-            column_nodes_to_select->getNodes().reserve(columns.size());
-            for (auto & column : columns)
-                column_nodes_to_select->getNodes().emplace_back(std::make_shared<ColumnNode>(column, table_function_node));
-            query_node.getProjectionNode() = column_nodes_to_select;
+            if (columns.empty())
+            {
+                auto column_nodes_to_select = std::make_shared<ListNode>();
+                column_nodes_to_select->getNodes().reserve(1);
+                column_nodes_to_select->getNodes().emplace_back(std::make_shared<ConstantNode>(1));
+                query_node.getProjectionNode() = column_nodes_to_select;
+            }
+            else
+            {
+                query_node.resolveProjectionColumns(columns);
+                auto column_nodes_to_select = std::make_shared<ListNode>();
+                column_nodes_to_select->getNodes().reserve(columns.size());
+                for (auto & column : columns)
+                    column_nodes_to_select->getNodes().emplace_back(std::make_shared<ColumnNode>(column, table_function_node));
+                query_node.getProjectionNode() = column_nodes_to_select;
+            }
 
             if (info.has_local_columns_in_where)
             {

tests/integration/test_s3_cluster/test.py

@@ -829,3 +829,34 @@ def test_joins(started_cluster):
     )
     res = list(map(str.split, result6.splitlines()))
     assert len(res) == 25
+
+    result7 = node.query(
+        f"""
+        SELECT count() FROM
+            s3Cluster('cluster_simple',
+                'http://minio1:9001/root/data/{{clickhouse,database}}/*', 'minio', '{minio_secret_key}', 'CSV',
+                'name String, value UInt32, polygon Array(Array(Tuple(Float64, Float64)))') AS t1
+        JOIN
+            join_table AS t2
+        ON 1
+        GROUP BY ALL
+        SETTINGS object_storage_cluster_join_mode='local';
+        """
+    )
+    assert result7.strip() == "625"
+
+    result8 = node.query(
+        f"""
+        SELECT count(), t2.id FROM
+            s3Cluster('cluster_simple',
+                'http://minio1:9001/root/data/{{clickhouse,database}}/*', 'minio', '{minio_secret_key}', 'CSV',
+                'name String, value UInt32, polygon Array(Array(Tuple(Float64, Float64)))') AS t1
+        JOIN
+            join_table AS t2
+        ON 1
+        GROUP BY ALL
+        SETTINGS object_storage_cluster_join_mode='local';
+        """
+    )
+    res = list(map(str.split, result8.splitlines()))
+    assert len(res) == 25

tests/queries/0_stateless/02126_dist_desc.sql.j2

@@ -10,7 +10,7 @@ select * from remote('{{host}}', {{args}}) format Null;
 {% endfor -%}
 
 system flush logs query_log;
-select anyIf(query, is_initial_query), groupArrayIf(query, query_kind = 'Describe' and not is_initial_query) from system.query_log
+select anyIf(query, initial_query_id == query_id), groupArrayIf(query, query_kind = 'Describe' and initial_query_id != query_id) from system.query_log
 where
     type = 'QueryFinish' and
     -- current_database is not set for queries on shards

tests/queries/0_stateless/03620_analyzer_distributed_global_in.reference

@@ -60,7 +60,7 @@ CreatingSets (Create sets before main query execution)
       ReadFromSystemNumbers
 system flush logs query_log;
 -- SKIP: current_database = currentDatabase()
-select normalizeQuery(replace(query, currentDatabase(), 'default')) from system.query_log where event_date >= yesterday() and log_comment like '%' || currentDatabase() || '%' and not is_initial_query and type != 'QueryStart' and query_kind = 'Select' order by event_time_microseconds;
+select normalizeQuery(replace(query, currentDatabase(), 'default')) from system.query_log where event_date >= yesterday() and log_comment like '%' || currentDatabase() || '%' and initial_query_id != query_id and type != 'QueryStart' and query_kind = 'Select' order by event_time_microseconds;
 SELECT `__table1`.`x` AS `x`, `__table1`.`y` AS `y` FROM `default`.`tab0` AS `__table1` HAVING in(`x`, (SELECT `__table1`.`number` + ? AS `?` FROM numbers(?) AS `__table1`))
 SELECT `__table1`.`x` AS `x`, `__table1`.`y` AS `y` FROM `default`.`tab0` AS `__table1` HAVING globalIn(`x`, `?`)
 SELECT `__table1`.`x` AS `x`, `__table1`.`y` AS `y` FROM `default`.`tab0` AS `__table1` HAVING in(`x`, (SELECT `__table1`.`number` + ? AS `?` FROM numbers(?) AS `__table1`))

tests/queries/0_stateless/03620_analyzer_distributed_global_in.sql

@@ -24,4 +24,4 @@ select * from (explain indexes=1, distributed=1
 );
 system flush logs query_log;
 -- SKIP: current_database = currentDatabase()
-select normalizeQuery(replace(query, currentDatabase(), 'default')) from system.query_log where event_date >= yesterday() and log_comment like '%' || currentDatabase() || '%' and not is_initial_query and type != 'QueryStart' and query_kind = 'Select' order by event_time_microseconds;
+select normalizeQuery(replace(query, currentDatabase(), 'default')) from system.query_log where event_date >= yesterday() and log_comment like '%' || currentDatabase() || '%' and initial_query_id != query_id and type != 'QueryStart' and query_kind = 'Select' order by event_time_microseconds;