This is an automated email from the ASF dual-hosted git repository.
morrysnow pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/doris.git
The following commit(s) were added to refs/heads/master by this push:
new 225f8ab2904 [Fix](nereids) Add semantic check that the hash bucket
column must be a key column when creating table for aggregate and unique models
(#31951)
225f8ab2904 is described below
commit 225f8ab2904146718f6d32167f113a46645b9448
Author: feiniaofeiafei <[email protected]>
AuthorDate: Fri Mar 8 16:32:32 2024 +0800
[Fix](nereids) Add semantic check that the hash bucket column must be a key
column when creating table for aggregate and unique models (#31951)
---
.../commands/info/DistributionDescriptor.java | 7 +++
.../ddl_p0/unique_aggregate_key_hash_check.groovy | 66 ++++++++++++++++++++++
.../test_rowset_writer_fault.groovy | 2 +-
.../test_group_commit_data_bytes_property.groovy | 2 +-
.../test_group_commit_interval_ms_property.groovy | 2 +-
.../schema_change_p0/test_schema_change_agg.groovy | 6 +-
6 files changed, 79 insertions(+), 6 deletions(-)
diff --git
a/fe/fe-core/src/main/java/org/apache/doris/nereids/trees/plans/commands/info/DistributionDescriptor.java
b/fe/fe-core/src/main/java/org/apache/doris/nereids/trees/plans/commands/info/DistributionDescriptor.java
index ba8b587812e..0b86bf74c58 100644
---
a/fe/fe-core/src/main/java/org/apache/doris/nereids/trees/plans/commands/info/DistributionDescriptor.java
+++
b/fe/fe-core/src/main/java/org/apache/doris/nereids/trees/plans/commands/info/DistributionDescriptor.java
@@ -82,6 +82,13 @@ public class DistributionDescriptor {
throw new AnalysisException(String.format("Distribution
column(%s) doesn't exist", c));
}
});
+ for (String columnName : cols) {
+ ColumnDefinition columnDefinition = columnMap.get(columnName);
+ if (!columnDefinition.isKey()
+ && (keysType == KeysType.UNIQUE_KEYS || keysType ==
KeysType.AGG_KEYS)) {
+ throw new AnalysisException("Distribution column[" +
columnName + "] is not key column");
+ }
+ }
} else {
if (keysType.equals(KeysType.UNIQUE_KEYS)) {
throw new AnalysisException("Create unique keys table should
not contain random distribution desc");
diff --git
a/regression-test/suites/ddl_p0/unique_aggregate_key_hash_check.groovy
b/regression-test/suites/ddl_p0/unique_aggregate_key_hash_check.groovy
new file mode 100644
index 00000000000..73b9959e4b6
--- /dev/null
+++ b/regression-test/suites/ddl_p0/unique_aggregate_key_hash_check.groovy
@@ -0,0 +1,66 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements. See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership. The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License. You may obtain a copy of the License at
+//
+// http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied. See the License for the
+// specific language governing permissions and limitations
+// under the License.
+suite("unique_aggregate_key_hash_check") {
+ sql "SET enable_nereids_planner=true"
+ sql "SET enable_fallback_to_original_planner=false"
+ sql "DROP TABLE IF EXISTS example_tbl_agg3"
+ sql "DROP TABLE IF EXISTS example_tbl_unique"
+
+ test {
+ sql """CREATE TABLE IF NOT EXISTS example_tbl_agg3
+ (
+ `user_id` LARGEINT NOT NULL COMMENT "用户id",
+ `date` DATE NOT NULL COMMENT "数据灌入日期时间",
+ `city` VARCHAR(20) COMMENT "用户所在城市",
+ `age` SMALLINT COMMENT "用户年龄",
+ `sex` TINYINT COMMENT "用户性别",
+ `last_visit_date` DATETIME REPLACE DEFAULT "1970-01-01
00:00:00" COMMENT "用户最后一次访问时间",
+ `cost` BIGINT SUM DEFAULT "0" COMMENT "用户总消费",
+ `max_dwell_time` INT MAX DEFAULT "0" COMMENT "用户最大停留时间",
+ `min_dwell_time` INT MIN DEFAULT "99999" COMMENT "用户最小停留时间"
+ )
+ AGGREGATE KEY(`user_id`, `date`, `city`, `age`, `sex`)
+ DISTRIBUTED BY HASH(`cost`) BUCKETS 1
+ PROPERTIES (
+ "replication_allocation" = "tag.location.default: 1"
+ );
+ """
+ exception "Distribution column[cost] is not key column"
+ }
+ test {
+ sql """
+ CREATE TABLE IF NOT EXISTS example_tbl_unique
+ (
+ `user_id` LARGEINT NOT NULL COMMENT "用户id",
+ `username` VARCHAR(50) NOT NULL COMMENT "用户昵称",
+ `city` VARCHAR(20) COMMENT "用户所在城市",
+ `age` SMALLINT COMMENT "用户年龄",
+ `sex` TINYINT COMMENT "用户性别",
+ `PHONE` LARGEINT COMMENT "用户电话",
+ `address` VARCHAR(500) COMMENT "用户地址",
+ `register_time` DATETIME COMMENT "用户注册时间"
+ )
+ UNIQUE KEY(`user_id`, `username`)
+ DISTRIBUTED BY HASH(`phone`) BUCKETS 1
+ PROPERTIES (
+ "replication_allocation" = "tag.location.default: 1"
+ );
+ """
+ exception "Distribution column[phone] is not key column"
+ }
+
+}
diff --git
a/regression-test/suites/fault_injection_p0/test_rowset_writer_fault.groovy
b/regression-test/suites/fault_injection_p0/test_rowset_writer_fault.groovy
index 84192e12b51..005e4b6bc97 100644
--- a/regression-test/suites/fault_injection_p0/test_rowset_writer_fault.groovy
+++ b/regression-test/suites/fault_injection_p0/test_rowset_writer_fault.groovy
@@ -35,7 +35,7 @@ suite("test_rowset_writer_fault", "nonConcurrent") {
`k13` largeint(40) null comment ""
) engine=olap
UNIQUE KEY (k0)
- DISTRIBUTED BY HASH(`k1`) BUCKETS 5 properties("replication_num" = "1")
+ DISTRIBUTED BY HASH(`k0`) BUCKETS 5 properties("replication_num" = "1")
"""
GetDebugPoint().clearDebugPointsForAllBEs()
diff --git
a/regression-test/suites/insert_p0/test_group_commit_data_bytes_property.groovy
b/regression-test/suites/insert_p0/test_group_commit_data_bytes_property.groovy
index b71ebe0d099..cba4349e16d 100644
---
a/regression-test/suites/insert_p0/test_group_commit_data_bytes_property.groovy
+++
b/regression-test/suites/insert_p0/test_group_commit_data_bytes_property.groovy
@@ -51,7 +51,7 @@ suite("test_group_commit_data_bytes_property") {
v bigint
)
UNIQUE KEY(k)
- DISTRIBUTED BY HASH (v) BUCKETS 8
+ DISTRIBUTED BY HASH (k) BUCKETS 8
PROPERTIES(
"replication_num" = "1",
"group_commit_data_bytes"="1024"
diff --git
a/regression-test/suites/insert_p0/test_group_commit_interval_ms_property.groovy
b/regression-test/suites/insert_p0/test_group_commit_interval_ms_property.groovy
index c4bf3bd0002..5d8962d07ac 100644
---
a/regression-test/suites/insert_p0/test_group_commit_interval_ms_property.groovy
+++
b/regression-test/suites/insert_p0/test_group_commit_interval_ms_property.groovy
@@ -51,7 +51,7 @@ suite("test_group_commit_interval_ms_property") {
v bigint
)
UNIQUE KEY(k)
- DISTRIBUTED BY HASH (v) BUCKETS 8
+ DISTRIBUTED BY HASH (k) BUCKETS 8
PROPERTIES(
"replication_num" = "1",
"group_commit_interval_ms"="10000"
diff --git
a/regression-test/suites/schema_change_p0/test_schema_change_agg.groovy
b/regression-test/suites/schema_change_p0/test_schema_change_agg.groovy
index e2931bda9ac..905dd3f8c35 100644
--- a/regression-test/suites/schema_change_p0/test_schema_change_agg.groovy
+++ b/regression-test/suites/schema_change_p0/test_schema_change_agg.groovy
@@ -176,7 +176,7 @@ suite("test_schema_change_agg", "p0") {
partition `old_p1` values [("1"), ("2")),
partition `old_p2` values [("2"), ("3"))
)
- DISTRIBUTED BY HASH(pv) BUCKETS 1
+ DISTRIBUTED BY HASH(citycode) BUCKETS 1
PROPERTIES (
"replication_num" = "1"
);
@@ -204,8 +204,8 @@ suite("test_schema_change_agg", "p0") {
//distribution key
test {
- sql "alter table ${tableName3} modify column pv bigint sum default '0'
comment 'pv'"
- exception "Can not modify distribution column[pv].
index[${tableName3}]"
+ sql "alter table ${tableName3} modify column citycode smallint
comment 'citycode'"
+ exception "Can not modify distribution column[citycode].
index[${tableName3}]"
}
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
