[SPARK-7927] whitespace fixes for Hive and ThriftServer.

So we can enable a whitespace enforcement rule in the style checker to save code review time.

Author: Reynold Xin <rxin@databricks.com>

Closes #6478 from rxin/whitespace-hive and squashes the following commits:

e01b0e0 [Reynold Xin] Fixed tests.
a3bba22 [Reynold Xin] [SPARK-7927] whitespace fixes for Hive and ThriftServer.

(cherry picked from commit ee6a0e12fb)
Signed-off-by: Reynold Xin <rxin@databricks.com>

sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala

@@ -43,7 +43,7 @@ import org.apache.spark.util.Utils
 private[hive] object SparkSQLCLIDriver {
   private var prompt = "spark-sql"
   private var continuedPrompt = "".padTo(prompt.length, ' ')
-  private var transport:TSocket = _
+  private var transport: TSocket = _
 
   installSignalHandler()
 
@@ -276,13 +276,13 @@ private[hive] class SparkSQLCLIDriver extends CliDriver with Logging {
 
           driver.init()
           val out = sessionState.out
-          val start:Long = System.currentTimeMillis()
+          val start: Long = System.currentTimeMillis()
           if (sessionState.getIsVerbose) {
             out.println(cmd)
           }
           val rc = driver.run(cmd)
           val end = System.currentTimeMillis()
-          val timeTaken:Double = (end - start) / 1000.0
+          val timeTaken: Double = (end - start) / 1000.0
 
           ret = rc.getResponseCode
           if (ret != 0) {
@@ -310,7 +310,7 @@ private[hive] class SparkSQLCLIDriver extends CliDriver with Logging {
               res.clear()
             }
           } catch {
-            case e:IOException =>
+            case e: IOException =>
               console.printError(
                 s"""Failed with exception ${e.getClass.getName}: ${e.getMessage}
                    |${org.apache.hadoop.util.StringUtils.stringifyException(e)}

sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerPage.scala

@@ -77,7 +77,7 @@ private[ui] class ThriftServerPage(parent: ThriftServerTab) extends WebUIPage(""
             [{id}]
           </a>
         }
-        val detail = if(info.state == ExecutionState.FAILED) info.detail else info.executePlan
+        val detail = if (info.state == ExecutionState.FAILED) info.detail else info.executePlan
         <tr>
           <td>{info.userName}</td>
           <td>
@@ -85,7 +85,7 @@ private[ui] class ThriftServerPage(parent: ThriftServerTab) extends WebUIPage(""
           </td>
           <td>{info.groupId}</td>
           <td>{formatDate(info.startTimestamp)}</td>
-          <td>{if(info.finishTimestamp > 0) formatDate(info.finishTimestamp)}</td>
+          <td>{if (info.finishTimestamp > 0) formatDate(info.finishTimestamp)}</td>
           <td>{formatDurationOption(Some(info.totalTime))}</td>
           <td>{info.statement}</td>
           <td>{info.state}</td>
@@ -150,7 +150,7 @@ private[ui] class ThriftServerPage(parent: ThriftServerTab) extends WebUIPage(""
           <td> {session.ip} </td>
           <td> <a href={sessionLink}> {session.sessionId} </a> </td>
           <td> {formatDate(session.startTimestamp)} </td>
-          <td> {if(session.finishTimestamp > 0) formatDate(session.finishTimestamp)} </td>
+          <td> {if (session.finishTimestamp > 0) formatDate(session.finishTimestamp)} </td>
           <td> {formatDurationOption(Some(session.totalTime))} </td>
           <td> {session.totalExecution.toString} </td>
         </tr>

sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/ui/ThriftServerSessionPage.scala

@@ -87,7 +87,7 @@ private[ui] class ThriftServerSessionPage(parent: ThriftServerTab)
             [{id}]
           </a>
         }
-        val detail = if(info.state == ExecutionState.FAILED) info.detail else info.executePlan
+        val detail = if (info.state == ExecutionState.FAILED) info.detail else info.executePlan
         <tr>
           <td>{info.userName}</td>
           <td>

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

@@ -73,7 +73,7 @@ class UISeleniumSuite
   }
 
   ignore("thrift server ui test") {
-    withJdbcStatement(statement =>{
+    withJdbcStatement { statement =>
       val baseURL = s"http://localhost:$uiPort"
 
       val queries = Seq(
@@ -97,6 +97,6 @@ class UISeleniumSuite
           findAll(cssSelector("""ul table tbody tr td""")).map(_.text).toList should contain (line)
         }
       }
-    })
+    }
   }
 }

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

@@ -29,10 +29,10 @@ import org.apache.spark.sql.hive.execution.{AddJar, AddFile, HiveNativeCommand}
 private[hive] class ExtendedHiveQlParser extends AbstractSparkSQLParser {
   // Keyword is a convention with AbstractSparkSQLParser, which will scan all of the `Keyword`
   // properties via reflection the class in runtime for constructing the SqlLexical object
-  protected val ADD  = Keyword("ADD")
-  protected val DFS  = Keyword("DFS")
+  protected val ADD = Keyword("ADD")
+  protected val DFS = Keyword("DFS")
   protected val FILE = Keyword("FILE")
-  protected val JAR  = Keyword("JAR")
+  protected val JAR = Keyword("JAR")
 
   protected lazy val start: Parser[LogicalPlan] = dfs | addJar | addFile | hiveQl
 

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

@@ -530,7 +530,7 @@ private[hive] object HiveContext {
     val propMap: HashMap[String, String] = HashMap()
     // We have to mask all properties in hive-site.xml that relates to metastore data source
     // as we used a local metastore here.
-    HiveConf.ConfVars.values().foreach { confvar  =>
+    HiveConf.ConfVars.values().foreach { confvar =>
       if (confvar.varname.contains("datanucleus") || confvar.varname.contains("jdo")) {
         propMap.put(confvar.varname, confvar.defaultVal)
       }
@@ -553,7 +553,7 @@ private[hive] object HiveContext {
       }.mkString("{", ",", "}")
     case (seq: Seq[_], ArrayType(typ, _)) =>
       seq.map(v => (v, typ)).map(toHiveStructString).mkString("[", ",", "]")
-    case (map: Map[_,_], MapType(kType, vType, _)) =>
+    case (map: Map[_, _], MapType(kType, vType, _)) =>
       map.map {
         case (key, value) =>
           toHiveStructString((key, kType)) + ":" + toHiveStructString((value, vType))

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

@@ -335,7 +335,7 @@ private[hive] trait HiveInspectors {
       val allRefs = si.getAllStructFieldRefs
       new GenericRow(
         allRefs.map(r =>
-          unwrap(si.getStructFieldData(data,r), r.getFieldObjectInspector)).toArray)
+          unwrap(si.getStructFieldData(data, r), r.getFieldObjectInspector)).toArray)
   }
 
 
@@ -561,8 +561,8 @@ private[hive] trait HiveInspectors {
     case DecimalType() => PrimitiveObjectInspectorFactory.javaHiveDecimalObjectInspector
     case StructType(fields) =>
       ObjectInspectorFactory.getStandardStructObjectInspector(
-        java.util.Arrays.asList(fields.map(f => f.name) :_*),
-        java.util.Arrays.asList(fields.map(f => toInspector(f.dataType)) :_*))
+        java.util.Arrays.asList(fields.map(f => f.name) : _*),
+        java.util.Arrays.asList(fields.map(f => toInspector(f.dataType)) : _*))
   }
 
   /**
@@ -677,8 +677,8 @@ private[hive] trait HiveInspectors {
         getListTypeInfo(elemType.toTypeInfo)
       case StructType(fields) =>
         getStructTypeInfo(
-          java.util.Arrays.asList(fields.map(_.name) :_*),
-          java.util.Arrays.asList(fields.map(_.dataType.toTypeInfo) :_*))
+          java.util.Arrays.asList(fields.map(_.name) : _*),
+          java.util.Arrays.asList(fields.map(_.dataType.toTypeInfo) : _*))
       case MapType(keyType, valueType, _) =>
         getMapTypeInfo(keyType.toTypeInfo, valueType.toTypeInfo)
       case BinaryType => binaryTypeInfo

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

@@ -546,13 +546,17 @@ private[hive] class HiveMetastoreCatalog(val client: ClientInterface, hive: Hive
    * UNIMPLEMENTED: It needs to be decided how we will persist in-memory tables to the metastore.
    * For now, if this functionality is desired mix in the in-memory [[OverrideCatalog]].
    */
-  override def registerTable(tableIdentifier: Seq[String], plan: LogicalPlan): Unit = ???
+  override def registerTable(tableIdentifier: Seq[String], plan: LogicalPlan): Unit = {
+    throw new UnsupportedOperationException
+  }
 
   /**
    * UNIMPLEMENTED: It needs to be decided how we will persist in-memory tables to the metastore.
    * For now, if this functionality is desired mix in the in-memory [[OverrideCatalog]].
    */
-  override def unregisterTable(tableIdentifier: Seq[String]): Unit = ???
+  override def unregisterTable(tableIdentifier: Seq[String]): Unit = {
+    throw new UnsupportedOperationException
+  }
 
   override def unregisterAllTables(): Unit = {}
 }
@@ -725,7 +729,7 @@ private[hive] case class MetastoreRelation
   val output = attributes ++ partitionKeys
 
   /** An attribute map that can be used to lookup original attributes based on expression id. */
-  val attributeMap = AttributeMap(output.map(o => (o,o)))
+  val attributeMap = AttributeMap(output.map(o => (o, o)))
 
   /** An attribute map for determining the ordinal for non-partition columns. */
   val columnOrdinals = AttributeMap(attributes.zipWithIndex)

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

@@ -665,7 +665,7 @@ https://cwiki.apache.org/confluence/display/Hive/Enhanced+Aggregation%2C+Cube%2C
                 HiveColumn(field.getName, field.getType, field.getComment)
               })
           }
-        case Token("TOK_TABLEROWFORMAT", Token("TOK_SERDEPROPS", child :: Nil) :: Nil)=>
+        case Token("TOK_TABLEROWFORMAT", Token("TOK_SERDEPROPS", child :: Nil) :: Nil) =>
           val serdeParams = new java.util.HashMap[String, String]()
           child match {
             case Token("TOK_TABLEROWFORMATFIELD", rowChild1 :: rowChild2) =>
@@ -775,7 +775,7 @@ https://cwiki.apache.org/confluence/display/Hive/Enhanced+Aggregation%2C+Cube%2C
 
     // Support "TRUNCATE TABLE table_name [PARTITION partition_spec]"
     case Token("TOK_TRUNCATETABLE",
-          Token("TOK_TABLE_PARTITION",table)::Nil) =>  NativePlaceholder
+          Token("TOK_TABLE_PARTITION", table) :: Nil) => NativePlaceholder
 
     case Token("TOK_QUERY", queryArgs)
         if Seq("TOK_FROM", "TOK_INSERT").contains(queryArgs.head.getText) =>
@@ -1151,7 +1151,7 @@ https://cwiki.apache.org/confluence/display/Hive/Enhanced+Aggregation%2C+Cube%2C
         case Seq(false, false) => Inner
       }.toBuffer
 
-      val joinedTables = tables.reduceLeft(Join(_,_, Inner, None))
+      val joinedTables = tables.reduceLeft(Join(_, _, Inner, None))
 
       // Must be transform down.
       val joinedResult = joinedTables transform {
@@ -1171,7 +1171,8 @@ https://cwiki.apache.org/confluence/display/Hive/Enhanced+Aggregation%2C+Cube%2C
       // worth the number of hacks that will be required to implement it.  Namely, we need to add
       // some sort of mapped star expansion that would expand all child output row to be similarly
       // named output expressions where some aggregate expression has been applied (i.e. First).
-      ??? // Aggregate(groups, Star(None, First(_)) :: Nil, joinedResult)
+      // Aggregate(groups, Star(None, First(_)) :: Nil, joinedResult)
+      throw new UnsupportedOperationException
 
     case Token(allJoinTokens(joinToken),
            relation1 ::

sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveTable.scala

@@ -194,10 +194,9 @@ case class InsertIntoHiveTable(
     if (partition.nonEmpty) {
 
       // loadPartition call orders directories created on the iteration order of the this map
-      val orderedPartitionSpec = new util.LinkedHashMap[String,String]()
-      table.hiveQlTable.getPartCols().foreach{
-        entry=>
-          orderedPartitionSpec.put(entry.getName,partitionSpec.get(entry.getName).getOrElse(""))
+      val orderedPartitionSpec = new util.LinkedHashMap[String, String]()
+      table.hiveQlTable.getPartCols().foreach { entry =>
+        orderedPartitionSpec.put(entry.getName, partitionSpec.get(entry.getName).getOrElse(""))
       }
       val partVals = MetaStoreUtils.getPvals(table.hiveQlTable.getPartCols, partitionSpec)
 

sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/ScriptTransformation.scala

@@ -216,7 +216,7 @@ case class HiveScriptIOSchema (
     val columnTypes = attrs.map {
       case aref: AttributeReference => aref.dataType
       case e: NamedExpression => e.dataType
-      case _ =>  null
+      case _ => null
     }
 
     (columns, columnTypes)

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

@@ -316,7 +316,7 @@ private[hive] case class HiveWindowFunction(
 
   // The object inspector of values returned from the Hive window function.
   @transient
-  protected lazy val returnInspector  = {
+  protected lazy val returnInspector = {
     evaluator.init(GenericUDAFEvaluator.Mode.COMPLETE, inputInspectors)
   }
 
@@ -413,7 +413,7 @@ private[hive] case class HiveGenericUdaf(
   protected lazy val resolver: AbstractGenericUDAFResolver = funcWrapper.createFunction()
 
   @transient
-  protected lazy val objectInspector  = {
+  protected lazy val objectInspector = {
     val parameterInfo = new SimpleGenericUDAFParameterInfo(inspectors.toArray, false, false)
     resolver.getEvaluator(parameterInfo)
       .init(GenericUDAFEvaluator.Mode.COMPLETE, inspectors.toArray)
@@ -446,7 +446,7 @@ private[hive] case class HiveUdaf(
     new GenericUDAFBridge(funcWrapper.createFunction())
 
   @transient
-  protected lazy val objectInspector  = {
+  protected lazy val objectInspector = {
     val parameterInfo = new SimpleGenericUDAFParameterInfo(inspectors.toArray, false, false)
     resolver.getEvaluator(parameterInfo)
       .init(GenericUDAFEvaluator.Mode.COMPLETE, inspectors.toArray)

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

@@ -71,7 +71,7 @@ private[hive] class SparkHiveWriterContainer(
   @transient protected lazy val jobContext = newJobContext(conf.value, jID.value)
   @transient private lazy val taskContext = newTaskAttemptContext(conf.value, taID.value)
   @transient private lazy val outputFormat =
-    conf.value.getOutputFormat.asInstanceOf[HiveOutputFormat[AnyRef,Writable]]
+    conf.value.getOutputFormat.asInstanceOf[HiveOutputFormat[AnyRef, Writable]]
 
   def driverSideSetup() {
     setIDs(0, 0, 0)

sql/hive/src/main/scala/org/apache/spark/sql/hive/test/TestHive.scala

@@ -189,7 +189,7 @@ class TestHiveContext(sc: SparkContext) extends HiveContext(sc) {
     }
   }
 
-  case class TestTable(name: String, commands: (()=>Unit)*)
+  case class TestTable(name: String, commands: (() => Unit)*)
 
   protected[hive] implicit class SqlCmd(sql: String) {
     def cmd: () => Unit = {
@@ -253,8 +253,8 @@ class TestHiveContext(sc: SparkContext) extends HiveContext(sc) {
          |  'serialization.format'='${classOf[TBinaryProtocol].getName}'
          |)
          |STORED AS
-         |INPUTFORMAT '${classOf[SequenceFileInputFormat[_,_]].getName}'
-         |OUTPUTFORMAT '${classOf[SequenceFileOutputFormat[_,_]].getName}'
+         |INPUTFORMAT '${classOf[SequenceFileInputFormat[_, _]].getName}'
+         |OUTPUTFORMAT '${classOf[SequenceFileOutputFormat[_, _]].getName}'
         """.stripMargin)
 
       runSqlHive(