thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-10 09:32:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fixed :a elimate AMBIGUOUS_COLUMN_NAME exception

Browse Source 
elimate AMBIGUOUS_COLUMN_NAME exception in hdfs/s3 cluster when run a query with join
This commit is contained in:
lgbo-ustc 2022-03-30 16:19:16 +08:00
parent a842a81aba
commit 08e1fdc6b8
4 changed files with 31 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/Storages/HDFS/StorageHDFSCluster.cpp
View File

@ -93,7 +93,7 @@ Pipe StorageHDFSCluster::read(
/// So, task_identifier is passed as constructor argument. It is more obvious.
auto remote_query_executor = std::make_shared<RemoteQueryExecutor>(
connection,
queryToString(query_info.query),
queryToString(query_info.original_query),
header,
context,
/*throttler=*/nullptr,

2
src/Storages/StorageS3Cluster.cpp
View File

@ -134,7 +134,7 @@ Pipe StorageS3Cluster::read(
/// So, task_identifier is passed as constructor argument. It is more obvious.
auto remote_query_executor = std::make_shared<RemoteQueryExecutor>(
connection,
queryToString(query_info.query),
queryToString(query_info.original_query),
header,
context,
/*throttler=*/nullptr,

19
tests/integration/test_s3_cluster/test.py
View File

@ -153,3 +153,22 @@ def test_wrong_cluster(started_cluster):
)
assert "not found" in error
def test_ambiguous_join(started_cluster):
node = started_cluster.instances["s0_0_0"]
result = node.query(
"""
SELECT l.name, r.value from s3Cluster(
'cluster_simple',
'http://minio1:9001/root/data/{clickhouse,database}/*', 'minio', 'minio123', 'CSV',
'name String, value UInt32, polygon Array(Array(Tuple(Float64, Float64)))') as l
JOIN s3Cluster(
'cluster_simple',
'http://minio1:9001/root/data/{clickhouse,database}/*', 'minio', 'minio123', 'CSV',
'name String, value UInt32, polygon Array(Array(Tuple(Float64, Float64)))') as r
ON l.name = r.name
"""
)
assert "AMBIGUOUS_COLUMN_NAME" not in result

10
tests/integration/test_storage_hdfs/test.py
View File

@ -553,6 +553,16 @@ def test_insert_select_schema_inference(started_cluster):
result = node1.query(f"select * from hdfs('hdfs://hdfs1:9000/test.native.zst')")
assert int(result) == 1
def test_cluster_join(started_cluster):
result = node1.query(
'''
SELECT l.id,r.id FROM hdfsCluster('test_cluster_two_shards', 'hdfs://hdfs1:9000/test_hdfsCluster/file*', 'TSV', 'id UInt32') as l
JOIN hdfsCluster('test_cluster_two_shards', 'hdfs://hdfs1:9000/test_hdfsCluster/file*', 'TSV', 'id UInt32') as r
ON l.id = r.id
'''
)
assert "AMBIGUOUS_COLUMN_NAME" not in result
if __name__ == "__main__":
cluster.start()