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

dev/deps/spark-deps-hadoop-palantir

@@ -65,7 +65,21 @@ hadoop-yarn-client/2.9.2-palantir.15//hadoop-yarn-client-2.9.2-palantir.15.jar
 hadoop-yarn-common/2.9.2-palantir.15//hadoop-yarn-common-2.9.2-palantir.15.jar
 hadoop-yarn-registry/2.9.2-palantir.15//hadoop-yarn-registry-2.9.2-palantir.15.jar
 hadoop-yarn-server-common/2.9.2-palantir.15//hadoop-yarn-server-common-2.9.2-palantir.15.jar
-hive-storage-api/2.7.1//hive-storage-api-2.7.1.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
+hive-exec/2.3.8/core/hive-exec-2.3.8-core.jar
+hive-jdbc/2.3.8//hive-jdbc-2.3.8.jar
+hive-llap-common/2.3.8//hive-llap-common-2.3.8.jar
+hive-metastore/2.3.8//hive-metastore-2.3.8.jar
+hive-serde/2.3.8//hive-serde-2.3.8.jar
+hive-service-rpc/3.1.2//hive-service-rpc-3.1.2.jar
+hive-shims-0.23/2.3.8//hive-shims-0.23-2.3.8.jar
+hive-shims-common/2.3.8//hive-shims-common-2.3.8.jar
+hive-shims-scheduler/2.3.8//hive-shims-scheduler-2.3.8.jar
+hive-shims/2.3.8//hive-shims-2.3.8.jar
+hive-storage-api/2.7.2//hive-storage-api-2.7.2.jar
+hive-vector-code-gen/2.3.8//hive-vector-code-gen-2.3.8.jar
 hk2-api/2.6.1//hk2-api-2.6.1.jar
 hk2-locator/2.6.1//hk2-locator-2.6.1.jar
 hk2-utils/2.6.1//hk2-utils-2.6.1.jar

docs/building-spark.md

@@ -83,9 +83,9 @@ Example:
 
 To enable Hive integration for Spark SQL along with its JDBC server and CLI,
 add the `-Phive` and `-Phive-thriftserver` profiles to your existing build options.
-By default Spark will build with Hive 2.3.7.
+By default Spark will build with Hive 2.3.8.
 
-    # With Hive 2.3.7 support
+    # With Hive 2.3.8 support
     ./build/mvn -Pyarn -Phive -Phive-thriftserver -DskipTests clean package
 
 ## Packaging without Hadoop Dependencies for YARN

docs/sql-data-sources-hive-tables.md

@@ -127,10 +127,10 @@ The following options can be used to configure the version of Hive that is used
   <tr><th>Property Name</th><th>Default</th><th>Meaning</th><th>Since Version</th></tr>
   <tr>
     <td><code>spark.sql.hive.metastore.version</code></td>
-    <td><code>2.3.7</code></td>
+    <td><code>2.3.8</code></td>
     <td>
       Version of the Hive metastore. Available
-      options are <code>0.12.0</code> through <code>2.3.7</code> and <code>3.0.0</code> through <code>3.1.2</code>.
+      options are <code>0.12.0</code> through <code>2.3.8</code> and <code>3.0.0</code> through <code>3.1.2</code>.
     </td>
     <td>1.4.0</td>
   </tr>
@@ -142,9 +142,9 @@ The following options can be used to configure the version of Hive that is used
       property can be one of three options:
       <ol>
         <li><code>builtin</code></li>
-        Use Hive 2.3.7, which is bundled with the Spark assembly when <code>-Phive</code> is
+        Use Hive 2.3.8, which is bundled with the Spark assembly when <code>-Phive</code> is
         enabled. When this option is chosen, <code>spark.sql.hive.metastore.version</code> must be
-        either <code>2.3.7</code> or not defined.
+        either <code>2.3.8</code> or not defined.
         <li><code>maven</code></li>
         Use Hive jars of specified version downloaded from Maven repositories. This configuration
         is not generally recommended for production deployments.

docs/sql-migration-guide.md

@@ -810,7 +810,7 @@ Python UDF registration is unchanged.
 Spark SQL is designed to be compatible with the Hive Metastore, SerDes and UDFs.
 Currently, Hive SerDes and UDFs are based on built-in Hive,
 and Spark SQL can be connected to different versions of Hive Metastore
-(from 0.12.0 to 2.3.7 and 3.0.0 to 3.1.2. Also see [Interacting with Different Versions of Hive Metastore](sql-data-sources-hive-tables.html#interacting-with-different-versions-of-hive-metastore)).
+(from 0.12.0 to 2.3.8 and 3.0.0 to 3.1.2. Also see [Interacting with Different Versions of Hive Metastore](sql-data-sources-hive-tables.html#interacting-with-different-versions-of-hive-metastore)).
 
 #### Deploying in Existing Hive Warehouses
 {:.no_toc}

pom.xml

@@ -131,8 +131,8 @@
     <hive.group>org.apache.hive</hive.group>
     <hive.classifier>core</hive.classifier>
     <!-- Version used in Maven Hive dependency -->
-    <hive.version>2.3.7</hive.version>
-    <hive23.version>2.3.7</hive23.version>
+    <hive.version>2.3.8</hive.version>
+    <hive23.version>2.3.8</hive23.version>
     <!-- Version used for internal directory structure -->
     <hive.version.short>2.3</hive.version.short>
     <!-- note that this should be compatible with Kafka brokers version 0.10 and up -->
@@ -1846,6 +1846,22 @@
             <groupId>org.apache.logging.log4j</groupId>
             <artifactId>*</artifactId>
           </exclusion>
+          <exclusion>
+            <groupId>net.hydromatic</groupId>
+            <artifactId>eigenbase-properties</artifactId>
+          </exclusion>
+          <exclusion>
+            <groupId>org.codehaus.janino</groupId>
+            <artifactId>commons-compiler</artifactId>
+          </exclusion>
+          <exclusion>
+            <groupId>org.codehaus.janino</groupId>
+            <artifactId>janino</artifactId>
+          </exclusion>
+          <exclusion>
+            <groupId>org.pentaho</groupId>
+            <artifactId>pentaho-aggdesigner-algorithm</artifactId>
+          </exclusion>
           <!-- End of Hive 2.3 exclusion -->
         </exclusions>
       </dependency>

sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/HiveThriftServer2Suites.scala

@@ -545,7 +545,7 @@ class HiveThriftBinaryServerSuite extends HiveThriftJdbcTest {
       }
 
       if (HiveUtils.isHive23) {
-        assert(conf.get(HiveUtils.FAKE_HIVE_VERSION.key) === Some("2.3.7"))
+        assert(conf.get(HiveUtils.FAKE_HIVE_VERSION.key) === Some("2.3.8"))
       } else {
         assert(conf.get(HiveUtils.FAKE_HIVE_VERSION.key) === Some("1.2.1"))
       }
@@ -562,7 +562,7 @@ class HiveThriftBinaryServerSuite extends HiveThriftJdbcTest {
       }
 
       if (HiveUtils.isHive23) {
-        assert(conf.get(HiveUtils.FAKE_HIVE_VERSION.key) === Some("2.3.7"))
+        assert(conf.get(HiveUtils.FAKE_HIVE_VERSION.key) === Some("2.3.8"))
       } else {
         assert(conf.get(HiveUtils.FAKE_HIVE_VERSION.key) === Some("1.2.1"))
       }

sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveUtils.scala

@@ -63,7 +63,7 @@ private[spark] object HiveUtils extends Logging {
 
   val HIVE_METASTORE_VERSION = buildStaticConf("spark.sql.hive.metastore.version")
     .doc("Version of the Hive metastore. Available options are " +
-        "<code>0.12.0</code> through <code>2.3.7</code> and " +
+        "<code>0.12.0</code> through <code>2.3.8</code> and " +
         "<code>3.0.0</code> through <code>3.1.2</code>.")
     .version("1.4.0")
     .stringConf

sql/hive/src/main/scala/org/apache/spark/sql/hive/client/IsolatedClientLoader.scala

@@ -104,8 +104,8 @@ private[hive] object IsolatedClientLoader extends Logging {
     case "2.0" | "2.0.0" | "2.0.1" => hive.v2_0
     case "2.1" | "2.1.0" | "2.1.1" => hive.v2_1
     case "2.2" | "2.2.0" => hive.v2_2
-    case "2.3" | "2.3.0" | "2.3.1" | "2.3.2" | "2.3.3" | "2.3.4" | "2.3.5" | "2.3.6" | "2.3.7" =>
-      hive.v2_3
+    case "2.3" | "2.3.0" | "2.3.1" | "2.3.2" | "2.3.3" | "2.3.4" | "2.3.5" | "2.3.6" | "2.3.7" |
+         "2.3.8" => hive.v2_3
     case "3.0" | "3.0.0" => hive.v3_0
     case "3.1" | "3.1.0" | "3.1.1" | "3.1.2" => hive.v3_1
     case version =>

sql/hive/src/main/scala/org/apache/spark/sql/hive/client/package.scala

@@ -87,11 +87,13 @@ package object client {
         "org.apache.curator:*",
         "org.pentaho:pentaho-aggdesigner-algorithm"))
 
-    // Since HIVE-14496, Hive materialized view need calcite-core.
+    // Since HIVE-23980, calcite-core included in Hive package jar.
     // For spark, only VersionsSuite currently creates a hive materialized view for testing.
-    case object v2_3 extends HiveVersion("2.3.7",
-      exclusions = Seq("org.apache.calcite:calcite-druid",
+    case object v2_3 extends HiveVersion("2.3.8",
+      exclusions = Seq("org.apache.calcite:calcite-core",
+        "org.apache.calcite:calcite-druid",
         "org.apache.calcite.avatica:avatica",
+        "com.fasterxml.jackson.core:*",
         "org.apache.curator:*",
         "org.pentaho:pentaho-aggdesigner-algorithm"))
 
@@ -101,7 +103,6 @@ package object client {
       extraDeps = Seq("org.apache.logging.log4j:log4j-api:2.10.0",
         "org.apache.derby:derby:10.14.1.0"),
       exclusions = Seq("org.apache.calcite:calcite-druid",
-        "org.apache.calcite.avatica:avatica",
         "org.apache.curator:*",
         "org.pentaho:pentaho-aggdesigner-algorithm"))
 
@@ -111,7 +112,6 @@ package object client {
       extraDeps = Seq("org.apache.logging.log4j:log4j-api:2.10.0",
         "org.apache.derby:derby:10.14.1.0"),
       exclusions = Seq("org.apache.calcite:calcite-druid",
-        "org.apache.calcite.avatica:avatica",
         "org.apache.curator:*",
         "org.pentaho:pentaho-aggdesigner-algorithm"))
 

sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveExternalCatalogVersionsSuite.scala

@@ -58,6 +58,11 @@ class HiveExternalCatalogVersionsSuite extends SparkSubmitTestUtils {
   // avoid downloading Spark of different versions in each run.
   private val sparkTestingDir = new File("/tmp/test-spark")
   private val unusedJar = TestUtils.createJarWithClasses(Seq.empty)
+  val hiveVersion = if (SystemUtils.isJavaVersionAtLeast(JavaVersion.JAVA_9)) {
+    "2.3.8"
+  } else {
+    "1.2.1"
+  }
 
   override def afterAll(): Unit = {
     try {