[SPARK-14786] Remove hive-cli dependency from hive subproject

The `hive` subproject currently depends on `hive-cli` in order to perform a check to see whether a `SessionState` is an instance of `org.apache.hadoop.hive.cli.CliSessionState` (see #9589). The introduction of this `hive-cli` dependency has caused problems for users whose Hive metastore JAR classpaths don't include the `hive-cli` classes (such as in #11495).

This patch removes this dependency on `hive-cli` and replaces the `isInstanceOf` check by reflection. I added a Maven Enforcer rule to ban `hive-cli` from the `hive` subproject in order to make sure that this dependency is not accidentally reintroduced.

/cc rxin yhuai adrian-wang preecet

Author: Josh Rosen <joshrosen@databricks.com>

Closes #12551 from JoshRosen/remove-hive-cli-dep-from-hive-subproject.

3 files changed, 33 insertions, 7 deletions

diff --git a/sql/hive/pom.xml b/sql/hive/pom.xml
index 61504becf1..177b6884fa 100644
--- a/sql/hive/pom.xml
+++ b/sql/hive/pom.xml
@@ -73,10 +73,6 @@
       <version>${protobuf.version}</version>
     </dependency>
 -->
-    <dependency>
-      <groupId>${hive.group}</groupId>
-      <artifactId>hive-cli</artifactId>
-    </dependency>
 <!--
     <dependency>
       <groupId>${hive.group}</groupId>
@@ -225,6 +221,27 @@
           <argLine>-da -Xmx3g -XX:MaxPermSize=${MaxPermGen} -XX:ReservedCodeCacheSize=512m</argLine>
         </configuration>
       </plugin>
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-enforcer-plugin</artifactId>
+        <executions>
+          <execution>
+            <id>enforce-versions</id>
+            <goals>
+              <goal>enforce</goal>
+            </goals>
+            <configuration>
+              <rules>
+                <bannedDependencies>
+                  <excludes combine.children="append">
+                    <exclude>*:hive-cli</exclude>
+                  </excludes>
+                </bannedDependencies>
+              </rules>
+            </configuration>
+          </execution>
+        </executions>
+      </plugin>
     </plugins>
   </build>
 </project>
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala
index 69f7dbf6ce..703d991829 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala
@@ -24,7 +24,6 @@ import scala.language.reflectiveCalls
 
 import org.apache.hadoop.conf.Configuration
 import org.apache.hadoop.fs.Path
-import org.apache.hadoop.hive.cli.CliSessionState
 import org.apache.hadoop.hive.conf.HiveConf
 import org.apache.hadoop.hive.metastore.{PartitionDropOptions, TableType => HiveTableType}
 import org.apache.hadoop.hive.metastore.api.{Database => HiveDatabase, FieldSchema, Function => HiveFunction, FunctionType, PrincipalType, ResourceType, ResourceUri}
@@ -110,10 +109,20 @@ private[hive] class HiveClientImpl(
       }
     }
 
+    def isCliSessionState(state: SessionState): Boolean = {
+      var temp: Class[_] = if (state != null) state.getClass else null
+      var found = false
+      while (temp != null && !found) {
+        found = temp.getName == "org.apache.hadoop.hive.cli.CliSessionState"
+        temp = temp.getSuperclass
+      }
+      found
+    }
+
     val ret = try {
       // originState will be created if not exists, will never be null
       val originalState = SessionState.get()
-      if (originalState.isInstanceOf[CliSessionState]) {
+      if (isCliSessionState(originalState)) {
         // In `SparkSQLCLIDriver`, we have already started a `CliSessionState`,
         // which contains information like configurations from command line. Later
         // we call `SparkSQLEnv.init()` there, which would run into this part again.
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/IsolatedClientLoader.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/IsolatedClientLoader.scala
index f45264af34..1d502e01d9 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/IsolatedClientLoader.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/IsolatedClientLoader.scala
@@ -103,7 +103,7 @@ private[hive] object IsolatedClientLoader extends Logging {
       hadoopVersion: String,
       ivyPath: Option[String]): Seq[URL] = {
     val hiveArtifacts = version.extraDeps ++
-      Seq("hive-metastore", "hive-exec", "hive-common", "hive-serde", "hive-cli")
+      Seq("hive-metastore", "hive-exec", "hive-common", "hive-serde")
         .map(a => s"org.apache.hive:$a:${version.fullVersion}") ++
       Seq("com.google.guava:guava:14.0.1",
         s"org.apache.hadoop:hadoop-client:$hadoopVersion")