[SPARK-2410][SQL] Merging Hive Thrift/JDBC server

(This is a replacement of #1399, trying to fix potential `HiveThriftServer2` port collision between parallel builds. Please refer to [these comments](https://github.com/apache/spark/pull/1399#issuecomment-50212572) for details.)

JIRA issue: [SPARK-2410](https://issues.apache.org/jira/browse/SPARK-2410)

Merging the Hive Thrift/JDBC server from [branch-1.0-jdbc](https://github.com/apache/spark/tree/branch-1.0-jdbc).

Thanks chenghao-intel for his initial contribution of the Spark SQL CLI.

Author: Cheng Lian <lian.cs.zju@gmail.com>

Closes #1600 from liancheng/jdbc and squashes the following commits:

ac4618b [Cheng Lian] Uses random port for HiveThriftServer2 to avoid collision with parallel builds
090beea [Cheng Lian] Revert changes related to SPARK-2678, decided to move them to another PR
21c6cf4 [Cheng Lian] Updated Spark SQL programming guide docs
fe0af31 [Cheng Lian] Reordered spark-submit options in spark-shell[.cmd]
199e3fb [Cheng Lian] Disabled MIMA for hive-thriftserver
1083e9d [Cheng Lian] Fixed failed test suites
7db82a1 [Cheng Lian] Fixed spark-submit application options handling logic
9cc0f06 [Cheng Lian] Starts beeline with spark-submit
cfcf461 [Cheng Lian] Updated documents and build scripts for the newly added hive-thriftserver profile
061880f [Cheng Lian] Addressed all comments by @pwendell
7755062 [Cheng Lian] Adapts test suites to spark-submit settings
40bafef [Cheng Lian] Fixed more license header issues
e214aab [Cheng Lian] Added missing license headers
b8905ba [Cheng Lian] Fixed minor issues in spark-sql and start-thriftserver.sh
f975d22 [Cheng Lian] Updated docs for Hive compatibility and Shark migration guide draft
3ad4e75 [Cheng Lian] Starts spark-sql shell with spark-submit
a5310d1 [Cheng Lian] Make HiveThriftServer2 play well with spark-submit
61f39f4 [Cheng Lian] Starts Hive Thrift server via spark-submit
2c4c539 [Cheng Lian] Cherry picked the Hive Thrift server

3 files changed, 16 insertions, 5 deletions

diff --git a/core/pom.xml b/core/pom.xml
index 1054cec4d7..a24743495b 100644
--- a/core/pom.xml
+++ b/core/pom.xml
@@ -28,7 +28,7 @@
   <groupId>org.apache.spark</groupId>
   <artifactId>spark-core_2.10</artifactId>
   <properties>
-     <sbt.project.name>core</sbt.project.name>
+    <sbt.project.name>core</sbt.project.name>
   </properties>
   <packaging>jar</packaging>
   <name>Spark Project Core</name>
diff --git a/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala b/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala
index 3b5642b6ca..c9cec33eba 100644
--- a/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala
+++ b/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala
@@ -46,6 +46,10 @@ object SparkSubmit {
   private val CLUSTER = 2
   private val ALL_DEPLOY_MODES = CLIENT | CLUSTER
 
+  // A special jar name that indicates the class being run is inside of Spark itself, and therefore
+  // no user jar is needed.
+  private val SPARK_INTERNAL = "spark-internal"
+
   // Special primary resource names that represent shells rather than application jars.
   private val SPARK_SHELL = "spark-shell"
   private val PYSPARK_SHELL = "pyspark-shell"
@@ -257,7 +261,9 @@ object SparkSubmit {
     // In yarn-cluster mode, use yarn.Client as a wrapper around the user class
     if (clusterManager == YARN && deployMode == CLUSTER) {
       childMainClass = "org.apache.spark.deploy.yarn.Client"
-      childArgs += ("--jar", args.primaryResource)
+      if (args.primaryResource != SPARK_INTERNAL) {
+        childArgs += ("--jar", args.primaryResource)
+      }
       childArgs += ("--class", args.mainClass)
       if (args.childArgs != null) {
         args.childArgs.foreach { arg => childArgs += ("--arg", arg) }
@@ -332,7 +338,7 @@ object SparkSubmit {
    * Return whether the given primary resource represents a user jar.
    */
   private def isUserJar(primaryResource: String): Boolean = {
-    !isShell(primaryResource) && !isPython(primaryResource)
+    !isShell(primaryResource) && !isPython(primaryResource) && !isInternal(primaryResource)
   }
 
   /**
@@ -349,6 +355,10 @@ object SparkSubmit {
     primaryResource.endsWith(".py") || primaryResource == PYSPARK_SHELL
   }
 
+  private[spark] def isInternal(primaryResource: String): Boolean = {
+    primaryResource == SPARK_INTERNAL
+  }
+
   /**
    * Merge a sequence of comma-separated file lists, some of which may be null to indicate
    * no files, into a single comma-separated string.
diff --git a/core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala b/core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala
index 3ab67a43a3..01d0ae541a 100644
--- a/core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala
+++ b/core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala
@@ -204,8 +204,9 @@ private[spark] class SparkSubmitArguments(args: Seq[String]) {
 
   /** Fill in values by parsing user options. */
   private def parseOpts(opts: Seq[String]): Unit = {
-    // Delineates parsing of Spark options from parsing of user options.
     var inSparkOpts = true
+
+    // Delineates parsing of Spark options from parsing of user options.
     parse(opts)
 
     def parse(opts: Seq[String]): Unit = opts match {
@@ -318,7 +319,7 @@ private[spark] class SparkSubmitArguments(args: Seq[String]) {
               SparkSubmit.printErrorAndExit(errMessage)
             case v =>
               primaryResource =
-                if (!SparkSubmit.isShell(v)) {
+                if (!SparkSubmit.isShell(v) && !SparkSubmit.isInternal(v)) {
                   Utils.resolveURI(v).toString
                 } else {
                   v