You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by "MaxGekk (via GitHub)" <gi...@apache.org> on 2024/03/05 20:18:50 UTC
[PR] [WIP][SQL] Distribute tests from `DataFrameSuite` to more specific suites [spark]
MaxGekk opened a new pull request, #45392:
URL: https://github.com/apache/spark/pull/45392
<!--
Thanks for sending a pull request! Here are some tips for you:
1. If this is your first time, please read our contributor guidelines: https://spark.apache.org/contributing.html
2. Ensure you have added or run the appropriate tests for your PR: https://spark.apache.org/developer-tools.html
3. If the PR is unfinished, add '[WIP]' in your PR title, e.g., '[WIP][SPARK-XXXX] Your PR title ...'.
4. Be sure to keep the PR description updated to reflect all changes.
5. Please write your PR title to summarize what this PR proposes.
6. If possible, provide a concise example to reproduce the issue for a faster review.
7. If you want to add a new configuration, please read the guideline first for naming configurations in
'core/src/main/scala/org/apache/spark/internal/config/ConfigEntry.scala'.
8. If you want to add or modify an error type or message, please read the guideline first in
'common/utils/src/main/resources/error/README.md'.
-->
### What changes were proposed in this pull request?
<!--
Please clarify what changes you are proposing. The purpose of this section is to outline the changes and how this PR fixes the issue.
If possible, please consider writing useful notes for better and faster reviews in your PR. See the examples below.
1. If you refactor some codes with changing classes, showing the class hierarchy will help reviewers.
2. If you fix some SQL features, you can provide some references of other DBMSes.
3. If there is design documentation, please add the link.
4. If there is a discussion in the mailing list, please add the link.
-->
### Why are the changes needed?
<!--
Please clarify why the changes are needed. For instance,
1. If you propose a new API, clarify the use case for a new API.
2. If you fix a bug, you can clarify why it is a bug.
-->
### Does this PR introduce _any_ user-facing change?
<!--
Note that it means *any* user-facing change including all aspects such as the documentation fix.
If yes, please clarify the previous behavior and the change this PR proposes - provide the console output, description and/or an example to show the behavior difference if possible.
If possible, please also clarify if this is a user-facing change compared to the released Spark versions or within the unreleased branches such as master.
If no, write 'No'.
-->
### How was this patch tested?
<!--
If tests were added, say they were added here. Please make sure to add some test cases that check the changes thoroughly including negative and positive cases if possible.
If it was tested in a way different from regular unit tests, please clarify how you tested step by step, ideally copy and paste-able, so that other reviewers can test and check, and descendants can verify in the future.
If tests were not added, please describe why they were not added and/or why it was difficult to add.
If benchmark tests were added, please run the benchmarks in GitHub Actions for the consistent environment, and the instructions could accord to: https://spark.apache.org/developer-tools.html#github-workflow-benchmarks.
-->
### Was this patch authored or co-authored using generative AI tooling?
<!--
If generative AI tooling has been used in the process of authoring this patch, please include the
phrase: 'Generated-by: ' followed by the name of the tool and its version.
If no, write 'No'.
Please refer to the [ASF Generative Tooling Guidance](https://www.apache.org/legal/generative-tooling.html) for details.
-->
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-47304][SQL][TESTS] Distribute tests from `DataFrameSuite` to more specific suites [spark]
Posted by "MaxGekk (via GitHub)" <gi...@apache.org>.
MaxGekk commented on code in PR #45392:
URL: https://github.com/apache/spark/pull/45392#discussion_r1514427320
##########
sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala:
##########
@@ -2200,6 +2200,115 @@ class DataFrameAggregateSuite extends QueryTest
checkAnswer(df, Row(1, 2, 2) :: Row(3, 1, 1) :: Nil)
}
}
+
+ private def assertDecimalSumOverflow(
+ df: DataFrame, ansiEnabled: Boolean, expectedAnswer: Row): Unit = {
+ if (!ansiEnabled) {
+ checkAnswer(df, expectedAnswer)
+ } else {
+ val e = intercept[ArithmeticException] {
+ df.collect()
+ }
+ assert(e.getMessage.contains("cannot be represented as Decimal") ||
+ e.getMessage.contains("Overflow in sum of decimals"))
+ }
+ }
+
+ def checkAggResultsForDecimalOverflow(aggFn: Column => Column): Unit = {
+ Seq("true", "false").foreach { wholeStageEnabled =>
+ withSQLConf((SQLConf.WHOLESTAGE_CODEGEN_ENABLED.key, wholeStageEnabled)) {
+ Seq(true, false).foreach { ansiEnabled =>
+ withSQLConf((SQLConf.ANSI_ENABLED.key, ansiEnabled.toString)) {
+ val df0 = Seq(
+ (BigDecimal("10000000000000000000"), 1),
+ (BigDecimal("10000000000000000000"), 1),
+ (BigDecimal("10000000000000000000"), 2)).toDF("decNum", "intNum")
+ val df1 = Seq(
+ (BigDecimal("10000000000000000000"), 2),
+ (BigDecimal("10000000000000000000"), 2),
+ (BigDecimal("10000000000000000000"), 2),
+ (BigDecimal("10000000000000000000"), 2),
+ (BigDecimal("10000000000000000000"), 2),
+ (BigDecimal("10000000000000000000"), 2),
+ (BigDecimal("10000000000000000000"), 2),
+ (BigDecimal("10000000000000000000"), 2),
+ (BigDecimal("10000000000000000000"), 2)).toDF("decNum", "intNum")
+ val df = df0.union(df1)
+ val df2 = df.withColumnRenamed("decNum", "decNum2").
+ join(df, "intNum").agg(aggFn($"decNum"))
+
+ val expectedAnswer = Row(null)
+ assertDecimalSumOverflow(df2, ansiEnabled, expectedAnswer)
+
+ val decStr = "1" + "0" * 19
+ val d1 = spark.range(0, 12, 1, 1)
+ val d2 = d1.select(expr(s"cast('$decStr' as decimal (38, 18)) as d")).agg(aggFn($"d"))
+ assertDecimalSumOverflow(d2, ansiEnabled, expectedAnswer)
+
+ val d3 = spark.range(0, 1, 1, 1).union(spark.range(0, 11, 1, 1))
+ val d4 = d3.select(expr(s"cast('$decStr' as decimal (38, 18)) as d")).agg(aggFn($"d"))
+ assertDecimalSumOverflow(d4, ansiEnabled, expectedAnswer)
+
+ val d5 = d3.select(expr(s"cast('$decStr' as decimal (38, 18)) as d"),
+ lit(1).as("key")).groupBy("key").agg(aggFn($"d").alias("aggd")).select($"aggd")
+ assertDecimalSumOverflow(d5, ansiEnabled, expectedAnswer)
+
+ val nullsDf = spark.range(1, 4, 1).select(expr(s"cast(null as decimal(38,18)) as d"))
+
+ val largeDecimals = Seq(BigDecimal("1"* 20 + ".123"), BigDecimal("9"* 20 + ".123")).
+ toDF("d")
+ assertDecimalSumOverflow(
+ nullsDf.union(largeDecimals).agg(aggFn($"d")), ansiEnabled, expectedAnswer)
+
+ val df3 = Seq(
+ (BigDecimal("10000000000000000000"), 1),
+ (BigDecimal("50000000000000000000"), 1),
+ (BigDecimal("10000000000000000000"), 2)).toDF("decNum", "intNum")
+
+ val df4 = Seq(
+ (BigDecimal("10000000000000000000"), 1),
+ (BigDecimal("10000000000000000000"), 1),
+ (BigDecimal("10000000000000000000"), 2)).toDF("decNum", "intNum")
+
+ val df5 = Seq(
+ (BigDecimal("10000000000000000000"), 1),
+ (BigDecimal("10000000000000000000"), 1),
+ (BigDecimal("20000000000000000000"), 2)).toDF("decNum", "intNum")
+
+ val df6 = df3.union(df4).union(df5)
+ val df7 = df6.groupBy("intNum").agg(sum("decNum"), countDistinct("decNum")).
+ filter("intNum == 1")
+ assertDecimalSumOverflow(df7, ansiEnabled, Row(1, null, 2))
+ }
+ }
+ }
+ }
+ }
+
+ test("SPARK-28067: Aggregate sum should not return wrong results for decimal overflow") {
+ checkAggResultsForDecimalOverflow(c => sum(c))
+ }
+
+ test("SPARK-35955: Aggregate avg should not return wrong results for decimal overflow") {
+ checkAggResultsForDecimalOverflow(c => avg(c))
+ }
+
+ test("SPARK-28224: Aggregate sum big decimal overflow") {
+ val largeDecimals = spark.sparkContext.parallelize(
+ DecimalData(BigDecimal("1"* 20 + ".123"), BigDecimal("1"* 20 + ".123")) ::
+ DecimalData(BigDecimal("9"* 20 + ".123"), BigDecimal("9"* 20 + ".123")) :: Nil).toDF()
+
+ Seq(true, false).foreach { ansiEnabled =>
+ withSQLConf((SQLConf.ANSI_ENABLED.key, ansiEnabled.toString)) {
+ val structDf = largeDecimals.select("a").agg(sum("a"))
+ assertDecimalSumOverflow(structDf, ansiEnabled, Row(null))
+ }
+ }
+ }
+
+ test("SPARK-32761: aggregating multiple distinct CONSTANT columns") {
+ checkAnswer(sql("select count(distinct 2), count(distinct 2,3)"), Row(1, 1))
+ }
}
Review Comment:
1 min 5 sec on my laptop.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-47304][SQL][TESTS] Distribute tests from `DataFrameSuite` to more specific suites [spark]
Posted by "cloud-fan (via GitHub)" <gi...@apache.org>.
cloud-fan commented on code in PR #45392:
URL: https://github.com/apache/spark/pull/45392#discussion_r1514386052
##########
sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala:
##########
@@ -2200,6 +2200,115 @@ class DataFrameAggregateSuite extends QueryTest
checkAnswer(df, Row(1, 2, 2) :: Row(3, 1, 1) :: Nil)
}
}
+
+ private def assertDecimalSumOverflow(
+ df: DataFrame, ansiEnabled: Boolean, expectedAnswer: Row): Unit = {
+ if (!ansiEnabled) {
+ checkAnswer(df, expectedAnswer)
+ } else {
+ val e = intercept[ArithmeticException] {
+ df.collect()
+ }
+ assert(e.getMessage.contains("cannot be represented as Decimal") ||
+ e.getMessage.contains("Overflow in sum of decimals"))
+ }
+ }
+
+ def checkAggResultsForDecimalOverflow(aggFn: Column => Column): Unit = {
+ Seq("true", "false").foreach { wholeStageEnabled =>
+ withSQLConf((SQLConf.WHOLESTAGE_CODEGEN_ENABLED.key, wholeStageEnabled)) {
+ Seq(true, false).foreach { ansiEnabled =>
+ withSQLConf((SQLConf.ANSI_ENABLED.key, ansiEnabled.toString)) {
+ val df0 = Seq(
+ (BigDecimal("10000000000000000000"), 1),
+ (BigDecimal("10000000000000000000"), 1),
+ (BigDecimal("10000000000000000000"), 2)).toDF("decNum", "intNum")
+ val df1 = Seq(
+ (BigDecimal("10000000000000000000"), 2),
+ (BigDecimal("10000000000000000000"), 2),
+ (BigDecimal("10000000000000000000"), 2),
+ (BigDecimal("10000000000000000000"), 2),
+ (BigDecimal("10000000000000000000"), 2),
+ (BigDecimal("10000000000000000000"), 2),
+ (BigDecimal("10000000000000000000"), 2),
+ (BigDecimal("10000000000000000000"), 2),
+ (BigDecimal("10000000000000000000"), 2)).toDF("decNum", "intNum")
+ val df = df0.union(df1)
+ val df2 = df.withColumnRenamed("decNum", "decNum2").
+ join(df, "intNum").agg(aggFn($"decNum"))
+
+ val expectedAnswer = Row(null)
+ assertDecimalSumOverflow(df2, ansiEnabled, expectedAnswer)
+
+ val decStr = "1" + "0" * 19
+ val d1 = spark.range(0, 12, 1, 1)
+ val d2 = d1.select(expr(s"cast('$decStr' as decimal (38, 18)) as d")).agg(aggFn($"d"))
+ assertDecimalSumOverflow(d2, ansiEnabled, expectedAnswer)
+
+ val d3 = spark.range(0, 1, 1, 1).union(spark.range(0, 11, 1, 1))
+ val d4 = d3.select(expr(s"cast('$decStr' as decimal (38, 18)) as d")).agg(aggFn($"d"))
+ assertDecimalSumOverflow(d4, ansiEnabled, expectedAnswer)
+
+ val d5 = d3.select(expr(s"cast('$decStr' as decimal (38, 18)) as d"),
+ lit(1).as("key")).groupBy("key").agg(aggFn($"d").alias("aggd")).select($"aggd")
+ assertDecimalSumOverflow(d5, ansiEnabled, expectedAnswer)
+
+ val nullsDf = spark.range(1, 4, 1).select(expr(s"cast(null as decimal(38,18)) as d"))
+
+ val largeDecimals = Seq(BigDecimal("1"* 20 + ".123"), BigDecimal("9"* 20 + ".123")).
+ toDF("d")
+ assertDecimalSumOverflow(
+ nullsDf.union(largeDecimals).agg(aggFn($"d")), ansiEnabled, expectedAnswer)
+
+ val df3 = Seq(
+ (BigDecimal("10000000000000000000"), 1),
+ (BigDecimal("50000000000000000000"), 1),
+ (BigDecimal("10000000000000000000"), 2)).toDF("decNum", "intNum")
+
+ val df4 = Seq(
+ (BigDecimal("10000000000000000000"), 1),
+ (BigDecimal("10000000000000000000"), 1),
+ (BigDecimal("10000000000000000000"), 2)).toDF("decNum", "intNum")
+
+ val df5 = Seq(
+ (BigDecimal("10000000000000000000"), 1),
+ (BigDecimal("10000000000000000000"), 1),
+ (BigDecimal("20000000000000000000"), 2)).toDF("decNum", "intNum")
+
+ val df6 = df3.union(df4).union(df5)
+ val df7 = df6.groupBy("intNum").agg(sum("decNum"), countDistinct("decNum")).
+ filter("intNum == 1")
+ assertDecimalSumOverflow(df7, ansiEnabled, Row(1, null, 2))
+ }
+ }
+ }
+ }
+ }
+
+ test("SPARK-28067: Aggregate sum should not return wrong results for decimal overflow") {
+ checkAggResultsForDecimalOverflow(c => sum(c))
+ }
+
+ test("SPARK-35955: Aggregate avg should not return wrong results for decimal overflow") {
+ checkAggResultsForDecimalOverflow(c => avg(c))
+ }
+
+ test("SPARK-28224: Aggregate sum big decimal overflow") {
+ val largeDecimals = spark.sparkContext.parallelize(
+ DecimalData(BigDecimal("1"* 20 + ".123"), BigDecimal("1"* 20 + ".123")) ::
+ DecimalData(BigDecimal("9"* 20 + ".123"), BigDecimal("9"* 20 + ".123")) :: Nil).toDF()
+
+ Seq(true, false).foreach { ansiEnabled =>
+ withSQLConf((SQLConf.ANSI_ENABLED.key, ansiEnabled.toString)) {
+ val structDf = largeDecimals.select("a").agg(sum("a"))
+ assertDecimalSumOverflow(structDf, ansiEnabled, Row(null))
+ }
+ }
+ }
+
+ test("SPARK-32761: aggregating multiple distinct CONSTANT columns") {
+ checkAnswer(sql("select count(distinct 2), count(distinct 2,3)"), Row(1, 1))
+ }
}
Review Comment:
just for curiosity, what's the runtime of `DataFrameAggregateSuite`? It has more than 2000 LOC...
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-47304][SQL][TESTS] Distribute tests from `DataFrameSuite` to more specific suites [spark]
Posted by "MaxGekk (via GitHub)" <gi...@apache.org>.
MaxGekk commented on PR #45392:
URL: https://github.com/apache/spark/pull/45392#issuecomment-1981172448
Merging to master. Thank you, @cloud-fan for review.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-47304][SQL][TESTS] Distribute tests from `DataFrameSuite` to more specific suites [spark]
Posted by "cloud-fan (via GitHub)" <gi...@apache.org>.
cloud-fan commented on code in PR #45392:
URL: https://github.com/apache/spark/pull/45392#discussion_r1514382831
##########
sql/core/src/test/scala/org/apache/spark/sql/DataFrameShowSuite.scala:
##########
@@ -0,0 +1,433 @@
+/*
+ * 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
+
+import java.nio.charset.StandardCharsets
+import java.sql.{Date, Timestamp}
+
+import org.apache.spark.sql.functions.rand
+import org.apache.spark.sql.internal.SQLConf
+import org.apache.spark.sql.test.SharedSparkSession
+
+class DataFrameShowSuiteextends extends QueryTest with SharedSparkSession {
Review Comment:
```suggestion
class DataFrameShowSuite extends QueryTest with SharedSparkSession {
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-47304][SQL][TESTS] Distribute tests from `DataFrameSuite` to more specific suites [spark]
Posted by "cloud-fan (via GitHub)" <gi...@apache.org>.
cloud-fan commented on code in PR #45392:
URL: https://github.com/apache/spark/pull/45392#discussion_r1514383692
##########
sql/core/src/test/scala/org/apache/spark/sql/DataFrameToSchemaSuite.scala:
##########
@@ -365,4 +367,57 @@ class DataFrameToSchemaSuite extends QueryTest with SharedSparkSession {
errorClass = "NOT_NULL_CONSTRAINT_VIOLATION.MAP_VALUE",
parameters = Map("columnPath" -> "`map`"))
}
+
Review Comment:
This test suite is for the `df.to` API. I feel it's better to put these tests in `DataFrameShowSuite`, as `printSchema` is more related to `df.show`
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-47304][SQL][TESTS] Distribute tests from `DataFrameSuite` to more specific suites [spark]
Posted by "MaxGekk (via GitHub)" <gi...@apache.org>.
MaxGekk closed pull request #45392: [SPARK-47304][SQL][TESTS] Distribute tests from `DataFrameSuite` to more specific suites
URL: https://github.com/apache/spark/pull/45392
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-47304][SQL][TESTS] Distribute tests from `DataFrameSuite` to more specific suites [spark]
Posted by "MaxGekk (via GitHub)" <gi...@apache.org>.
MaxGekk commented on code in PR #45392:
URL: https://github.com/apache/spark/pull/45392#discussion_r1514451415
##########
sql/core/src/test/scala/org/apache/spark/sql/DataFrameToSchemaSuite.scala:
##########
@@ -365,4 +367,57 @@ class DataFrameToSchemaSuite extends QueryTest with SharedSparkSession {
errorClass = "NOT_NULL_CONSTRAINT_VIOLATION.MAP_VALUE",
parameters = Map("columnPath" -> "`map`"))
}
+
Review Comment:
moved
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org