This is an automated email from the ASF dual-hosted git repository.
yangjie01 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new 4cc41ea63f94 [SPARK-48943][TESTS] Upgrade `h2` to 2.3.230 and enhance
the test coverage of behavior changes of `asin` and `acos` complying Standard
SQL
4cc41ea63f94 is described below
commit 4cc41ea63f943b61be8f771f5cd95cfd4ea15c2e
Author: Wei Guo <[email protected]>
AuthorDate: Tue Jul 23 10:21:32 2024 +0800
[SPARK-48943][TESTS] Upgrade `h2` to 2.3.230 and enhance the test coverage
of behavior changes of `asin` and `acos` complying Standard SQL
### What changes were proposed in this pull request?
This PR aims to upgrade `h2` from 2.2.220 to 2.3.230 and enhance the test
coverage of behavior changes of `asin` and `acos` complying Standard SQL.
The detail of behavior changes as follows:
After this commit(
https://github.com/h2database/h2database/commit/186647d4a35d05681febf4f53502b306aa6d511a),
the behavior of `asin` and `acos` has changed in h2, complying with Standard
SQL, and throwing exceptions directly when the argument is invalid(< -1d || >
1d).
### Why are the changes needed?
2.3.230 is latest version of `h2`, there are a lot of bug fixes and
improvements.
Full change notes:
https://www.h2database.com/html/changelog.html
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Update a exist test case and add a new test case.
Pass GA and manually test `JDBCV2Suite`.
### Was this patch authored or co-authored using generative AI tooling?
No.
Closes #47414 from wayneguow/upgrade_h2.
Authored-by: Wei Guo <[email protected]>
Signed-off-by: yangjie01 <[email protected]>
---
connect/server/pom.xml | 2 +-
sql/core/pom.xml | 2 +-
.../org/apache/spark/sql/jdbc/JDBCV2Suite.scala | 58 +++++++++++++++-------
3 files changed, 42 insertions(+), 20 deletions(-)
diff --git a/connect/server/pom.xml b/connect/server/pom.xml
index 73a3310c8a38..ecbb22168aa1 100644
--- a/connect/server/pom.xml
+++ b/connect/server/pom.xml
@@ -254,7 +254,7 @@
<dependency>
<groupId>com.h2database</groupId>
<artifactId>h2</artifactId>
- <version>2.2.220</version>
+ <version>2.3.230</version>
<scope>test</scope>
</dependency>
<dependency>
diff --git a/sql/core/pom.xml b/sql/core/pom.xml
index 59d798e6e62f..c891763eb4e1 100644
--- a/sql/core/pom.xml
+++ b/sql/core/pom.xml
@@ -166,7 +166,7 @@
<dependency>
<groupId>com.h2database</groupId>
<artifactId>h2</artifactId>
- <version>2.2.220</version>
+ <version>2.3.230</version>
<scope>test</scope>
</dependency>
<dependency>
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCV2Suite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCV2Suite.scala
index e1a7971b283c..db06aac7f5e0 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCV2Suite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCV2Suite.scala
@@ -37,7 +37,7 @@ import org.apache.spark.sql.connector.expressions.Expression
import org.apache.spark.sql.execution.FormattedMode
import
org.apache.spark.sql.execution.datasources.v2.{DataSourceV2ScanRelation,
V1ScanWrapper}
import org.apache.spark.sql.execution.datasources.v2.jdbc.JDBCTableCatalog
-import org.apache.spark.sql.functions.{abs, acos, asin, atan, atan2, avg,
ceil, coalesce, cos, cosh, cot, count, count_distinct, degrees, exp, floor,
lit, log => logarithm, log10, not, pow, radians, round, signum, sin, sinh,
sqrt, sum, tan, tanh, udf, when}
+import org.apache.spark.sql.functions.{abs, acos, asin, avg, ceil, coalesce,
count, count_distinct, degrees, exp, floor, lit, log => logarithm, log10, not,
pow, radians, round, signum, sqrt, sum, udf, when}
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.test.SharedSparkSession
import org.apache.spark.sql.types.{DataType, IntegerType, StringType}
@@ -1258,25 +1258,29 @@ class JDBCV2Suite extends QueryTest with
SharedSparkSession with ExplainSuiteHel
checkAnswer(df15, Seq(Row(1, "cathy", 9000, 1200, false),
Row(2, "alex", 12000, 1200, false), Row(6, "jen", 12000, 1200, true)))
- val df16 = spark.table("h2.test.employee")
- .filter(sin($"bonus") < -0.08)
- .filter(sinh($"bonus") > 200)
- .filter(cos($"bonus") > 0.9)
- .filter(cosh($"bonus") > 200)
- .filter(tan($"bonus") < -0.08)
- .filter(tanh($"bonus") === 1)
- .filter(cot($"bonus") < -11)
- .filter(asin($"bonus") > 0.1)
- .filter(acos($"bonus") > 1.4)
- .filter(atan($"bonus") > 1.4)
- .filter(atan2($"bonus", $"bonus") > 0.7)
+ val df16 = sql(
+ """
+ |SELECT * FROM h2.test.employee
+ |WHERE sin(bonus) < -0.08
+ |AND sinh(bonus) > 200
+ |AND cos(bonus) > 0.9
+ |AND cosh(bonus) > 200
+ |AND tan(bonus) < -0.08
+ |AND tanh(bonus) = 1
+ |AND cot(bonus) < -11
+ |AND asin(bonus / salary) > 0.13
+ |AND acos(bonus / salary) < 1.47
+ |AND atan(bonus) > 1.4
+ |AND atan2(bonus, bonus) > 0.7
+ |""".stripMargin)
checkFiltersRemoved(df16)
checkPushedInfo(df16, "PushedFilters: [" +
- "BONUS IS NOT NULL, SIN(BONUS) < -0.08, SINH(BONUS) > 200.0, COS(BONUS)
> 0.9, " +
- "COSH(BONUS) > 200.0, TAN(BONUS) < -0.08, TANH(BONUS) = 1.0, COT(BONUS)
< -11.0, " +
- "ASIN(BONUS) > 0.1, ACOS(BONUS) > 1.4, ATAN(BONUS) > 1.4, (ATAN2(BONUS,
BONUS)) > 0.7],")
- checkAnswer(df16, Seq(Row(1, "cathy", 9000, 1200, false),
- Row(2, "alex", 12000, 1200, false), Row(6, "jen", 12000, 1200, true)))
+ "BONUS IS NOT NULL, SALARY IS NOT NULL, SIN(BONUS) < -0.08, SINH(BONUS)
> 200.0, " +
+ "COS(BONUS) > 0.9, COSH(BONUS) > 200.0, TAN(BONUS) < -0.08, TANH(BONUS)
= 1.0, " +
+ "COT(BONUS) < -11.0, ASIN(BONUS / CAST(SALARY AS double)) > 0.13, " +
+ "ACOS(BONUS / CAST(SALARY AS double)) < 1.47, " +
+ "ATAN(BONUS) > 1.4, (ATAN2(BONUS, BONUS)) > 0.7],")
+ checkAnswer(df16, Seq(Row(1, "cathy", 9000, 1200, false)))
// H2 does not support log2, asinh, acosh, atanh, cbrt
val df17 = sql(
@@ -1294,6 +1298,24 @@ class JDBCV2Suite extends QueryTest with
SharedSparkSession with ExplainSuiteHel
checkAnswer(df17, Seq(Row(6, "jen", 12000, 1200, true)))
}
+ test("SPARK-48943: arguments for asin and acos are invalid (< -1 || > 1) in
H2") {
+ val df1 = spark.table("h2.test.employee").filter(acos($"bonus") > 1.4)
+ val e1 = intercept[SparkException] {
+ checkAnswer(df1, Seq(Row(1, "cathy", 9000, 1200, false)))
+ }
+ assert(e1.getCause.getClass === classOf[org.h2.jdbc.JdbcSQLDataException])
+ assert(e1.getCause.getMessage.contains("Invalid value")
+ && e1.getCause.getMessage.contains("ACOS"))
+
+ val df2 = spark.table("h2.test.employee").filter(asin($"bonus") > 0.1)
+ val e2 = intercept[SparkException] {
+ checkAnswer(df2, Seq(Row(1, "cathy", 9000, 1200, false)))
+ }
+ assert(e2.getCause.getClass === classOf[org.h2.jdbc.JdbcSQLDataException])
+ assert(e2.getCause.getMessage.contains("Invalid value")
+ && e2.getCause.getMessage.contains("ASIN"))
+ }
+
test("SPARK-38432: escape the single quote, _ and % for DS V2 pushdown") {
val df1 =
spark.table("h2.test.address").filter($"email".startsWith("abc_"))
checkFiltersRemoved(df1)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
