[SPARK-8962] Add Scalastyle rule to ban direct use of Class.forName; fix existing uses

This pull request adds a Scalastyle regex rule which fails the style check if `Class.forName` is used directly.  `Class.forName` always loads classes from the default / system classloader, but in a majority of cases, we should be using Spark's own `Utils.classForName` instead, which tries to load classes from the current thread's context classloader and falls back to the classloader which loaded Spark when the context classloader is not defined.

<!-- Reviewable:start -->
[<img src="https://reviewable.io/review_button.png" height=40 alt="Review on Reviewable"/>](https://reviewable.io/reviews/apache/spark/7350)
<!-- Reviewable:end -->

Author: Josh Rosen <joshrosen@databricks.com>

Closes #7350 from JoshRosen/ban-Class.forName and squashes the following commits:

e3e96f7 [Josh Rosen] Merge remote-tracking branch 'origin/master' into ban-Class.forName
c0b7885 [Josh Rosen] Hopefully fix the last two cases
d707ba7 [Josh Rosen] Fix uses of Class.forName that I missed in my first cleanup pass
046470d [Josh Rosen] Merge remote-tracking branch 'origin/master' into ban-Class.forName
62882ee [Josh Rosen] Fix uses of Class.forName or add exclusion.
d9abade [Josh Rosen] Add stylechecker rule to ban uses of Class.forName

3 files changed, 9 insertions, 12 deletions

diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala
index d65d29daac..dc35569085 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala
@@ -78,9 +78,7 @@ class HadoopTableReader(
   override def makeRDDForTable(hiveTable: HiveTable): RDD[InternalRow] =
     makeRDDForTable(
       hiveTable,
-      Class.forName(
-        relation.tableDesc.getSerdeClassName, true, Utils.getContextOrSparkClassLoader)
-        .asInstanceOf[Class[Deserializer]],
+      Utils.classForName(relation.tableDesc.getSerdeClassName).asInstanceOf[Class[Deserializer]],
       filterOpt = None)
 
   /**
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 1f280c6429..8adda54754 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
@@ -21,9 +21,6 @@ import java.io.{File, PrintStream}
 import java.util.{Map => JMap}
 import javax.annotation.concurrent.GuardedBy
 
-import org.apache.spark.sql.catalyst.expressions.Expression
-import org.apache.spark.util.CircularBuffer
-
 import scala.collection.JavaConversions._
 import scala.language.reflectiveCalls
 
@@ -37,7 +34,9 @@ import org.apache.hadoop.hive.ql.session.SessionState
 import org.apache.hadoop.hive.ql.{Driver, metadata}
 
 import org.apache.spark.Logging
+import org.apache.spark.sql.catalyst.expressions.Expression
 import org.apache.spark.sql.execution.QueryExecutionException
+import org.apache.spark.util.{CircularBuffer, Utils}
 
 
 /**
@@ -249,10 +248,10 @@ private[hive] class ClientWrapper(
   }
 
   private def toInputFormat(name: String) =
-    Class.forName(name).asInstanceOf[Class[_ <: org.apache.hadoop.mapred.InputFormat[_, _]]]
+    Utils.classForName(name).asInstanceOf[Class[_ <: org.apache.hadoop.mapred.InputFormat[_, _]]]
 
   private def toOutputFormat(name: String) =
-    Class.forName(name)
+    Utils.classForName(name)
       .asInstanceOf[Class[_ <: org.apache.hadoop.hive.ql.io.HiveOutputFormat[_, _]]]
 
   private def toQlTable(table: HiveTable): metadata.Table = {
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveSparkSubmitSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveSparkSubmitSuite.scala
index 917900e5f4..bee2ecbedb 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveSparkSubmitSuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveSparkSubmitSuite.scala
@@ -120,8 +120,8 @@ object SparkSubmitClassLoaderTest extends Logging {
     logInfo("Testing load classes at the driver side.")
     // First, we load classes at driver side.
     try {
-      Class.forName(args(0), true, Thread.currentThread().getContextClassLoader)
-      Class.forName(args(1), true, Thread.currentThread().getContextClassLoader)
+      Utils.classForName(args(0))
+      Utils.classForName(args(1))
     } catch {
       case t: Throwable =>
         throw new Exception("Could not load user class from jar:\n", t)
@@ -131,8 +131,8 @@ object SparkSubmitClassLoaderTest extends Logging {
     val result = df.mapPartitions { x =>
       var exception: String = null
       try {
-        Class.forName(args(0), true, Thread.currentThread().getContextClassLoader)
-        Class.forName(args(1), true, Thread.currentThread().getContextClassLoader)
+        Utils.classForName(args(0))
+        Utils.classForName(args(1))
       } catch {
         case t: Throwable =>
           exception = t + "\n" + t.getStackTraceString