Skip to content

[SPARK-33696][BUILD][SQL] Upgrade built-in Hive to 2.3.8 #30657

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.

Sign up for GitHub

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

Closed
wangyum wants to merge 10 commits into from
Closed

[SPARK-33696][BUILD][SQL] Upgrade built-in Hive to 2.3.8 #30657

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
fc9f735
Upgrade built-in Hive to 2.3.8
wangyum Dec 8, 2020
34a4da2
Fix test error.
wangyum Dec 10, 2020
8a4e20e
Add com.fasterxml.jackson.core:* to exclusions.
wangyum Dec 10, 2020
127cb2d
Merge remote-tracking branch 'upstream/master' into SPARK-33696
wangyum Dec 11, 2020
e0632ca
Merge remote-tracking branch 'upstream/master' into SPARK-33696
wangyum Dec 16, 2020
dcd001e
exclusion
wangyum Jan 8, 2021
fce63a1
Merge remote-tracking branch 'origin/SPARK-33696' into SPARK-33696
wangyum Jan 8, 2021
2248a9c
Trigger GithubAction
wangyum Jan 9, 2021
86df2cc
Merge remote-tracking branch 'upstream/master' into SPARK-33696
wangyum Jan 15, 2021
bb418bb
Remove hive-staged-releases
wangyum Jan 16, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 2 additions & 16 deletions dev/deps/spark-deps-hadoop-3.2-hive-2.3
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,22 +56,8 @@ flatbuffers-java/1.9.0//flatbuffers-java-1.9.0.jar
generex/1.0.2//generex-1.0.2.jar
gson/2.2.4//gson-2.2.4.jar
guava/14.0.1//guava-14.0.1.jar
guice-servlet/4.0//guice-servlet-4.0.jar
guice/4.0//guice-4.0.jar
hadoop-annotations/3.2.0//hadoop-annotations-3.2.0.jar
hadoop-auth/3.2.0//hadoop-auth-3.2.0.jar
hadoop-client/3.2.0//hadoop-client-3.2.0.jar
hadoop-common/3.2.0//hadoop-common-3.2.0.jar
hadoop-hdfs-client/3.2.0//hadoop-hdfs-client-3.2.0.jar
hadoop-mapreduce-client-common/3.2.0//hadoop-mapreduce-client-common-3.2.0.jar
hadoop-mapreduce-client-core/3.2.0//hadoop-mapreduce-client-core-3.2.0.jar
hadoop-mapreduce-client-jobclient/3.2.0//hadoop-mapreduce-client-jobclient-3.2.0.jar
hadoop-yarn-api/3.2.0//hadoop-yarn-api-3.2.0.jar
hadoop-yarn-client/3.2.0//hadoop-yarn-client-3.2.0.jar
hadoop-yarn-common/3.2.0//hadoop-yarn-common-3.2.0.jar
hadoop-yarn-registry/3.2.0//hadoop-yarn-registry-3.2.0.jar
hadoop-yarn-server-common/3.2.0//hadoop-yarn-server-common-3.2.0.jar
hadoop-yarn-server-web-proxy/3.2.0//hadoop-yarn-server-web-proxy-3.2.0.jar
hadoop-client-api/3.2.2//hadoop-client-api-3.2.2.jar
hadoop-client-runtime/3.2.2//hadoop-client-runtime-3.2.2.jar
hive-beeline/2.3.8//hive-beeline-2.3.8.jar
hive-cli/2.3.8//hive-cli-2.3.8.jar
hive-common/2.3.8//hive-common-2.3.8.jar
Expand Down
11 changes: 0 additions & 11 deletions pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -296,17 +296,6 @@
<enabled>false</enabled>
</snapshots>
</repository>
<repository>
<id>staged</id>
<name>hive-staged-releases</name>
<url>https://repository.apache.org/content/repositories/staging/</url>
<releases>
<enabled>true</enabled>
</releases>
<snapshots>
<enabled>true</enabled>
</snapshots>
</repository>
</repositories>
<pluginRepositories>
<pluginRepository>
Expand Down
3 changes: 0 additions & 3 deletions project/SparkBuild.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -271,9 +271,6 @@ object SparkBuild extends PomBuild {
DefaultMavenRepository,
Resolver.mavenLocal,
Resolver.file("ivyLocal", file(Path.userHome.absolutePath + "/.ivy2/local"))(Resolver.ivyStylePatterns)
) ++ Seq(
"hive-staged-releases-mirror" at "https://repository.apache.org/content/repositories/staging/",
Resolver.file("local", file(Path.userHome.absolutePath + "/.ivy2/local"))(Resolver.ivyStylePatterns)
),
externalResolvers := resolvers.value,
otherResolvers := SbtPomKeys.mvnLocalRepository(dotM2 => Seq(Resolver.file("dotM2", dotM2))).value,
Expand Down
3 changes: 1 addition & 2 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2748,8 +2748,7 @@ object SQLConf {
.stringConf
.createWithDefault(
sys.env.getOrElse("DEFAULT_ARTIFACT_REPOSITORY",
"https://maven-central.storage-download.googleapis.com/maven2/," +
"https://repository.apache.org/content/repositories/staging/"))
"https://maven-central.storage-download.googleapis.com/maven2/"))

val LEGACY_FROM_DAYTIME_STRING =
buildConf("spark.sql.legacy.fromDayTimeString.enabled")
Expand Down
11 changes: 6 additions & 5 deletions sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3724,20 +3724,21 @@ class SQLQuerySuite extends QueryTest with SharedSparkSession with AdaptiveSpark

test("SPARK-33084: Add jar support Ivy URI in SQL") {
val sc = spark.sparkContext
val hiveVersion = "2.3.8"
// default transitive=false, only download specified jar
sql("ADD JAR ivy://org.apache.hive.hcatalog:hive-hcatalog-core:2.3.7")
sql(s"ADD JAR ivy://org.apache.hive.hcatalog:hive-hcatalog-core:$hiveVersion")
assert(sc.listJars()
.exists(_.contains("org.apache.hive.hcatalog_hive-hcatalog-core-2.3.7.jar")))
.exists(_.contains(s"org.apache.hive.hcatalog_hive-hcatalog-core-$hiveVersion.jar")))

// test download ivy URL jar return multiple jars
sql("ADD JAR ivy://org.scala-js:scalajs-test-interface_2.12:1.2.0?transitive=true")
assert(sc.listJars().exists(_.contains("scalajs-library_2.12")))
assert(sc.listJars().exists(_.contains("scalajs-test-interface_2.12")))

sql("ADD JAR ivy://org.apache.hive:hive-contrib:2.3.7" +
sql(s"ADD JAR ivy://org.apache.hive:hive-contrib:$hiveVersion" +
"?exclude=org.pentaho:pentaho-aggdesigner-algorithm&transitive=true")
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-contrib-2.3.7.jar")))
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-exec-2.3.7.jar")))
assert(sc.listJars().exists(_.contains(s"org.apache.hive_hive-contrib-$hiveVersion.jar")))
assert(sc.listJars().exists(_.contains(s"org.apache.hive_hive-exec-$hiveVersion.jar")))
assert(!sc.listJars().exists(_.contains("org.pentaho.pentaho_aggdesigner-algorithm")))
}

Expand Down
7 changes: 4 additions & 3 deletions sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,7 @@ import org.apache.spark.sql.catalyst.expressions.Cast
import org.apache.spark.sql.catalyst.parser.ParseException
import org.apache.spark.sql.catalyst.plans.logical.Project
import org.apache.spark.sql.execution.joins.BroadcastNestedLoopJoinExec
import org.apache.spark.sql.hive.HiveUtils.{builtinHiveVersion => hiveVersion}
import org.apache.spark.sql.hive.test.{HiveTestJars, TestHive}
import org.apache.spark.sql.hive.test.TestHive._
import org.apache.spark.sql.internal.SQLConf
Expand Down Expand Up @@ -1223,17 +1224,17 @@ class HiveQuerySuite extends HiveComparisonTest with SQLTestUtils with BeforeAnd
test("SPARK-33084: Add jar support Ivy URI in SQL") {
val testData = TestHive.getHiveFile("data/files/sample.json").toURI
withTable("t") {
sql("ADD JAR ivy://org.apache.hive.hcatalog:hive-hcatalog-core:2.3.7")
sql(s"ADD JAR ivy://org.apache.hive.hcatalog:hive-hcatalog-core:$hiveVersion")
sql(
"""CREATE TABLE t(a string, b string)
|ROW FORMAT SERDE 'org.apache.hive.hcatalog.data.JsonSerDe'""".stripMargin)
sql(s"""LOAD DATA LOCAL INPATH "$testData" INTO TABLE t""")
sql("SELECT * FROM src JOIN t on src.key = t.a")
assert(sql("LIST JARS").filter(_.getString(0).contains(
"org.apache.hive.hcatalog_hive-hcatalog-core-2.3.7.jar")).count() > 0)
s"org.apache.hive.hcatalog_hive-hcatalog-core-$hiveVersion.jar")).count() > 0)
assert(sql("LIST JAR").
filter(_.getString(0).contains(
"org.apache.hive.hcatalog_hive-hcatalog-core-2.3.7.jar")).count() > 0)
s"org.apache.hive.hcatalog_hive-hcatalog-core-$hiveVersion.jar")).count() > 0)
}
}
}
Expand Down
2 changes: 1 addition & 1 deletion sql/hive/src/test/scala/org/apache/spark/sql/hive/test/TestHive.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -666,7 +666,7 @@ private[sql] class TestHiveSessionStateBuilder(
}

private[hive] object HiveTestJars {
private val repository = SQLConf.ADDITIONAL_REMOTE_REPOSITORIES.defaultValueString.split(",").last
private val repository = SQLConf.ADDITIONAL_REMOTE_REPOSITORIES.defaultValueString.split(",")(0)
private val hiveTestJarsDir = Utils.createTempDir()

def getHiveContribJar(version: String = HiveUtils.builtinHiveVersion): File =
Expand Down