Backport #64801 to 24.3: Fix distributed array join by nested

This commit is contained in:
robot-clickhouse 2024-06-24 16:07:56 +00:00
parent 55d2592888
commit 9d00c8918f
3 changed files with 52 additions and 2 deletions

View File

@ -1,5 +1,8 @@
#include <Analyzer/ArrayJoinNode.h>
#include <Analyzer/ColumnNode.h>
#include <Analyzer/FunctionNode.h>
#include <Analyzer/Utils.h>
#include <IO/Operators.h>
#include <IO/WriteBuffer.h>
#include <IO/WriteHelpers.h>
#include <IO/Operators.h>
@ -63,7 +66,12 @@ ASTPtr ArrayJoinNode::toASTImpl(const ConvertToASTOptions & options) const
auto * column_node = array_join_expression->as<ColumnNode>();
if (column_node && column_node->getExpression())
{
if (const auto * function_node = column_node->getExpression()->as<FunctionNode>(); function_node && function_node->getFunctionName() == "nested")
array_join_expression_ast = array_join_expression->toAST(options);
else
array_join_expression_ast = column_node->getExpression()->toAST(options);
}
else
array_join_expression_ast = array_join_expression->toAST(options);

View File

@ -0,0 +1,14 @@
Hello [1,2] 1
Hello [1,2] 2
Hello [1,2] 1
Hello [1,2] 1
Hello [1,2] 2
Hello [1,2] 2
Hello 1
Hello 2
Hello 1
Hello 1
Hello 2
Hello 2
2020-01-01 a 2
2020-01-01 b 4

View File

@ -0,0 +1,28 @@
CREATE TABLE arrays_test (s String, arr Array(UInt8)) ENGINE = MergeTree() ORDER BY (s);
INSERT INTO arrays_test VALUES ('Hello', [1,2]), ('World', [3,4,5]), ('Goodbye', []);
SELECT s, arr, a FROM remote('127.0.0.2', currentDatabase(), arrays_test) ARRAY JOIN arr AS a WHERE a < 3 ORDER BY a;
SELECT s, arr, a FROM remote('127.0.0.{1,2}', currentDatabase(), arrays_test) ARRAY JOIN arr AS a WHERE a < 3 ORDER BY a;
SELECT s, arr FROM remote('127.0.0.2', currentDatabase(), arrays_test) ARRAY JOIN arr WHERE arr < 3 ORDER BY arr;
SELECT s, arr FROM remote('127.0.0.{1,2}', currentDatabase(), arrays_test) ARRAY JOIN arr WHERE arr < 3 ORDER BY arr;
create table hourly(
hour datetime,
`metric.names` Array(String),
`metric.values` Array(Int64)
) Engine=Memory
as select '2020-01-01', ['a', 'b'], [1,2];
SELECT
toDate(hour) AS day,
`metric.names`,
sum(`metric.values`)
FROM remote('127.0.0.{1,2}', currentDatabase(), hourly)
ARRAY JOIN metric
GROUP BY
day,
metric.names
ORDER BY metric.names;