-
Notifications
You must be signed in to change notification settings - Fork 2.5k
[HUDI-5989] Fix date conversion issue when performing partition pruning on Spark #8298
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
Merged
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
97 changes: 97 additions & 0 deletions
97
...e/hudi-spark/src/test/scala/org/apache/spark/sql/hudi/TestLazyPartitionPathFetching.scala
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,97 @@ | ||
| /* | ||
| * 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. | ||
| */ | ||
|
|
||
| package org.apache.spark.sql.hudi | ||
|
|
||
| class TestLazyPartitionPathFetching extends HoodieSparkSqlTestBase { | ||
|
|
||
| test("Test querying with string column + partition pruning") { | ||
| withTempDir { tmp => | ||
| val tableName = generateTableName | ||
| spark.sql( | ||
| s""" | ||
| |create table $tableName ( | ||
| | id int, | ||
| | name string, | ||
| | price double, | ||
| | ts long, | ||
| | date_par date | ||
| |) using hudi | ||
| | location '${tmp.getCanonicalPath}' | ||
| | tblproperties ( | ||
| | primaryKey ='id', | ||
| | type = 'cow', | ||
| | preCombineField = 'ts' | ||
| | ) | ||
| | PARTITIONED BY (date_par) | ||
| """.stripMargin) | ||
| spark.sql(s"insert into $tableName values(1, 'a1', 10, 1000, date '2023-02-27')") | ||
| spark.sql(s"insert into $tableName values(2, 'a2', 10, 1000, date '2023-02-28')") | ||
| spark.sql(s"insert into $tableName values(3, 'a3', 10, 1000, date '2023-03-01')") | ||
|
|
||
| checkAnswer(s"select id, name, price, ts from $tableName where date_par='2023-03-01' order by id")( | ||
| Seq(3, "a3", 10.0, 1000) | ||
| ) | ||
|
|
||
| withSQLConf("spark.sql.session.timeZone" -> "UTC+2") { | ||
| checkAnswer(s"select id, name, price, ts from $tableName where date_par='2023-03-01' order by id")( | ||
| Seq(3, "a3", 10.0, 1000) | ||
| ) | ||
| } | ||
| } | ||
| } | ||
|
|
||
| test("Test querying with date column + partition pruning (multi-level partitioning)") { | ||
| withTempDir { tmp => | ||
| val tableName = generateTableName | ||
| spark.sql( | ||
| s""" | ||
| |create table $tableName ( | ||
| | id int, | ||
| | name string, | ||
| | price double, | ||
| | ts long, | ||
| | country string, | ||
| | date_par date | ||
| |) using hudi | ||
| | location '${tmp.getCanonicalPath}' | ||
| | tblproperties ( | ||
| | primaryKey ='id', | ||
| | type = 'cow', | ||
| | preCombineField = 'ts' | ||
| | ) | ||
| | PARTITIONED BY (country, date_par) | ||
| """.stripMargin) | ||
| spark.sql(s"insert into $tableName values(1, 'a1', 10, 1000, 'ID', date '2023-02-27')") | ||
| spark.sql(s"insert into $tableName values(2, 'a2', 10, 1000, 'ID', date '2023-02-28')") | ||
| spark.sql(s"insert into $tableName values(3, 'a3', 10, 1000, 'ID', date '2023-03-01')") | ||
|
|
||
| // for lazy fetching partition path & file slice to be enabled, filter must be applied on all partitions | ||
| checkAnswer(s"select id, name, price, ts from $tableName " + | ||
| s"where date_par='2023-03-01' and country='ID' order by id")( | ||
| Seq(3, "a3", 10.0, 1000) | ||
| ) | ||
|
|
||
| withSQLConf("spark.sql.session.timeZone" -> "UTC+2") { | ||
| checkAnswer(s"select id, name, price, ts from $tableName " + | ||
| s"where date_par='2023-03-01' and country='ID' order by id")( | ||
| Seq(3, "a3", 10.0, 1000) | ||
| ) | ||
| } | ||
| } | ||
| } | ||
| } |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.