thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-14 19:45:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix element_count for HASHED/SPARSE_HASHED with multiple attributes

Browse Source 
Previosly element_count was multplied by the number of attributes.

Fixes: #5440
Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com>
This commit is contained in:
Azat Khuzhin 2023-05-01 12:38:24 +02:00
parent 93201f21d9
commit 2fd1a73812
3 changed files with 7 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/Dictionaries/HashedDictionary.cpp
View File

@ -761,6 +761,9 @@ void HashedDictionary<dictionary_key_type, sparse, sharded>::blockToAttributes(c
auto & attribute = attributes[attribute_index];
bool attribute_is_nullable = attribute.is_nullable_sets.has_value();
/// Number of elements should not take into account multiple attributes.
new_element_count = 0;
getAttributeContainers(attribute_index, [&](auto & containers)
{
using ContainerType = std::decay_t<decltype(containers.front())>;

4
tests/queries/0_stateless/02730_dictionary_hashed_load_factor.reference
View File

@ -1,2 +1,2 @@
0.4768
0.4768
1000000 0.4768
1000000 0.4768

4
tests/queries/0_stateless/02730_dictionary_hashed_load_factor.sql
View File

@ -6,12 +6,12 @@ CREATE TABLE dict_data (key UInt64, v0 UInt16, v1 UInt16, v2 UInt16, v3 UInt16,
CREATE DICTIONARY dict_sharded (key UInt64, v0 UInt16) PRIMARY KEY key SOURCE(CLICKHOUSE(TABLE 'dict_data')) LIFETIME(MIN 0 MAX 0) LAYOUT(HASHED(SHARDS 32));
SYSTEM RELOAD DICTIONARY dict_sharded;
SELECT round(load_factor, 4) FROM system.dictionaries WHERE database = currentDatabase() AND name = 'dict_sharded';
SELECT element_count, round(load_factor, 4) FROM system.dictionaries WHERE database = currentDatabase() AND name = 'dict_sharded';
DROP DICTIONARY dict_sharded;
CREATE DICTIONARY dict_sharded_multi (key UInt64, v0 UInt16, v1 UInt16, v2 UInt16, v3 UInt16, v4 UInt16) PRIMARY KEY key SOURCE(CLICKHOUSE(TABLE 'dict_data')) LIFETIME(MIN 0 MAX 0) LAYOUT(HASHED(SHARDS 32));
SYSTEM RELOAD DICTIONARY dict_sharded_multi;
SELECT round(load_factor, 4) FROM system.dictionaries WHERE database = currentDatabase() AND name = 'dict_sharded_multi';
SELECT element_count, round(load_factor, 4) FROM system.dictionaries WHERE database = currentDatabase() AND name = 'dict_sharded_multi';
DROP DICTIONARY dict_sharded_multi;
DROP TABLE dict_data;