From a1dcb0f1d4095399002ee22c01724ea5ede4cc64 Mon Sep 17 00:00:00 2001
From: Josh Rosen <joshrosen@databricks.com>
Date: Thu, 21 Apr 2016 10:43:22 -0700
Subject: [PATCH 1/2] [SPARK-14783] Preserve full exception stacktrace in
 IsolatedClientLoader

In IsolatedClientLoader, we have a`catch` block which throws an exception without wrapping the original exception, causing the full exception stacktrace and any nested exceptions to be lost. This patch fixes this, improving the usefulness of classloading error messages.

Author: Josh Rosen <joshrosen@databricks.com>

Closes #12548 from JoshRosen/improve-logging-for-hive-classloader-issues.
---
 .../org/apache/spark/sql/hive/client/IsolatedClientLoader.scala | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

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 e60048bbc48ca..c365b2a93d118 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
@@ -255,7 +255,7 @@ private[hive] class IsolatedClientLoader(
           throw new ClassNotFoundException(
             s"$cnf when creating Hive client using classpath: ${execJars.mkString(", ")}\n" +
             "Please make sure that jars for your version of hive and hadoop are included in the " +
-            s"paths passed to ${HiveContext.HIVE_METASTORE_JARS}.")
+            s"paths passed to ${HiveContext.HIVE_METASTORE_JARS}.", e)
         } else {
           throw e
         }

From 49b7b528a8928335e16bf6081f7dad1e819c77e2 Mon Sep 17 00:00:00 2001
From: Yin Huai <yhuai@databricks.com>
Date: Tue, 26 Apr 2016 20:12:11 -0700
Subject: [PATCH 2/2] [SPARK-14786] Remove hive-cli dependency from hive
 subproject

---
 sql/hive/pom.xml                              | 25 ++++++++++++++++---
 .../spark/sql/hive/client/ClientWrapper.scala | 13 ++++++++--
 .../hive/client/IsolatedClientLoader.scala    |  2 +-
 3 files changed, 33 insertions(+), 7 deletions(-)

diff --git a/sql/hive/pom.xml b/sql/hive/pom.xml
index fba08380b357f..b49b0d12f28bf 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>
       <plugin>
          <groupId>org.codehaus.mojo</groupId>
          <artifactId>build-helper-maven-plugin</artifactId>
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/ClientWrapper.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/ClientWrapper.scala
index e9b2e20236da1..d5fb4ffd31267 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/ClientWrapper.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/ClientWrapper.scala
@@ -24,7 +24,6 @@ import scala.collection.JavaConverters._
 import scala.language.reflectiveCalls
 
 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.api.{Database, FieldSchema}
 import org.apache.hadoop.hive.metastore.{TableType => HTableType}
@@ -172,10 +171,20 @@ private[hive] class ClientWrapper(
       }
     }
 
+    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 c365b2a93d118..a5fd8de555d97 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
@@ -97,7 +97,7 @@ 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")