update

.gitignore

@@ -58,3 +58,4 @@ metastore_db/
 metastore/
 warehouse/
 TempStatsStore/
+sql/hive-thriftserver/test_warehouses

.rat-excludes

@@ -55,3 +55,4 @@ dist/*
 .*ipr
 .*iws
 logs
+.*scalastyle-output.xml

LICENSE

@@ -272,7 +272,7 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 
 ========================================================================
-For Py4J (python/lib/py4j0.7.egg and files in assembly/lib/net/sf/py4j):
+For Py4J (python/lib/py4j-0.8.2.1-src.zip)
 ========================================================================
 
 Copyright (c) 2009-2011, Barthelemy Dagenais All rights reserved.
@@ -532,7 +532,7 @@ The following components are provided under a BSD-style license. See project lin
      (New BSD license) Protocol Buffer Java API (org.spark-project.protobuf:protobuf-java:2.4.1-shaded - http://code.google.com/p/protobuf)
      (The BSD License) Fortran to Java ARPACK (net.sourceforge.f2j:arpack_combined_all:0.1 - http://f2j.sourceforge.net)
      (The BSD License) xmlenc Library (xmlenc:xmlenc:0.52 - http://xmlenc.sourceforge.net)
-     (The New BSD License) Py4J (net.sf.py4j:py4j:0.8.1 - http://py4j.sourceforge.net/)
+     (The New BSD License) Py4J (net.sf.py4j:py4j:0.8.2.1 - http://py4j.sourceforge.net/)
      (Two-clause BSD-style license) JUnit-Interface (com.novocode:junit-interface:0.10 - http://github.com/szeiger/junit-interface/)
      (ISC/BSD License) jbcrypt (org.mindrot:jbcrypt:0.3m - http://www.mindrot.org/)
 
@@ -549,3 +549,4 @@ The following components are provided under the MIT License. See project link fo
      (MIT License) pyrolite (org.spark-project:pyrolite:2.0.1 - http://pythonhosted.org/Pyro4/)
      (MIT License) scopt (com.github.scopt:scopt_2.10:3.2.0 - https://github.com/scopt/scopt)
      (The MIT License) Mockito (org.mockito:mockito-all:1.8.5 - http://www.mockito.org)
+     (MIT License) jquery (https://jquery.org/license/)

assembly/pom.xml

@@ -165,6 +165,16 @@
         </dependency>
       </dependencies>
     </profile>
+    <profile>
+      <id>hive-thriftserver</id>
+      <dependencies>
+        <dependency>
+          <groupId>org.apache.spark</groupId>
+          <artifactId>spark-hive-thriftserver_${scala.binary.version}</artifactId>
+          <version>${project.version}</version>
+        </dependency>
+      </dependencies>
+    </profile>
     <profile>
       <id>spark-ganglia-lgpl</id>
       <dependencies>

bagel/pom.xml

@@ -28,7 +28,7 @@
   <groupId>org.apache.spark</groupId>
   <artifactId>spark-bagel_2.10</artifactId>
   <properties>
-     <sbt.project.name>bagel</sbt.project.name>
+    <sbt.project.name>bagel</sbt.project.name>
   </properties>
   <packaging>jar</packaging>
   <name>Spark Project Bagel</name>

bin/beeline

@@ -0,0 +1,45 @@
+#!/usr/bin/env bash
+
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+# Figure out where Spark is installed
+FWDIR="$(cd `dirname $0`/..; pwd)"
+
+# Find the java binary
+if [ -n "${JAVA_HOME}" ]; then
+  RUNNER="${JAVA_HOME}/bin/java"
+else
+  if [ `command -v java` ]; then
+    RUNNER="java"
+  else
+    echo "JAVA_HOME is not set" >&2
+    exit 1
+  fi
+fi
+
+# Compute classpath using external script
+classpath_output=$($FWDIR/bin/compute-classpath.sh)
+if [[ "$?" != "0" ]]; then
+  echo "$classpath_output"
+  exit 1
+else
+  CLASSPATH=$classpath_output
+fi
+
+CLASS="org.apache.hive.beeline.BeeLine"
+exec "$RUNNER" -cp "$CLASSPATH" $CLASS "$@"

bin/compute-classpath.sh

@@ -52,6 +52,7 @@ if [ -n "$SPARK_PREPEND_CLASSES" ]; then
   CLASSPATH="$CLASSPATH:$FWDIR/sql/catalyst/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/sql/core/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/sql/hive/target/scala-$SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/sql/hive-thriftserver/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/yarn/stable/target/scala-$SCALA_VERSION/classes"
 fi
 

bin/pyspark

@@ -52,7 +52,7 @@ export PYSPARK_PYTHON
 
 # Add the PySpark classes to the Python path:
 export PYTHONPATH=$SPARK_HOME/python/:$PYTHONPATH
-export PYTHONPATH=$SPARK_HOME/python/lib/py4j-0.8.1-src.zip:$PYTHONPATH
+export PYTHONPATH=$SPARK_HOME/python/lib/py4j-0.8.2.1-src.zip:$PYTHONPATH
 
 # Load the PySpark shell.py script when ./pyspark is used interactively:
 export OLD_PYTHONSTARTUP=$PYTHONSTARTUP

bin/pyspark2.cmd

@@ -45,7 +45,7 @@ rem Figure out which Python to use.
 if [%PYSPARK_PYTHON%] == [] set PYSPARK_PYTHON=python
 
 set PYTHONPATH=%FWDIR%python;%PYTHONPATH%
-set PYTHONPATH=%FWDIR%python\lib\py4j-0.8.1-src.zip;%PYTHONPATH%
+set PYTHONPATH=%FWDIR%python\lib\py4j-0.8.2.1-src.zip;%PYTHONPATH%
 
 set OLD_PYTHONSTARTUP=%PYTHONSTARTUP%
 set PYTHONSTARTUP=%FWDIR%python\pyspark\shell.py

bin/run-example

@@ -29,7 +29,8 @@ if [ -n "$1" ]; then
 else
   echo "Usage: ./bin/run-example <example-class> [example-args]" 1>&2
   echo "  - set MASTER=XX to use a specific master" 1>&2
-  echo "  - can use abbreviated example class name (e.g. SparkPi, mllib.LinearRegression)" 1>&2
+  echo "  - can use abbreviated example class name relative to com.apache.spark.examples" 1>&2
+  echo "     (e.g. SparkPi, mllib.LinearRegression, streaming.KinesisWordCountASL)" 1>&2
   exit 1
 fi
 

bin/run-example2.cmd

@@ -32,7 +32,8 @@ rem Test that an argument was given
 if not "x%1"=="x" goto arg_given
   echo Usage: run-example ^<example-class^> [example-args]
   echo   - set MASTER=XX to use a specific master
-  echo   - can use abbreviated example class name (e.g. SparkPi, mllib.LinearRegression)
+  echo   - can use abbreviated example class name relative to com.apache.spark.examples
+  echo      (e.g. SparkPi, mllib.LinearRegression, streaming.KinesisWordCountASL)
   goto exit
 :arg_given
 

bin/spark-shell

@@ -46,11 +46,11 @@ function main(){
         # (see https://github.com/sbt/sbt/issues/562).
         stty -icanon min 1 -echo > /dev/null 2>&1
         export SPARK_SUBMIT_OPTS="$SPARK_SUBMIT_OPTS -Djline.terminal=unix"
-        $FWDIR/bin/spark-submit spark-shell "$@" --class org.apache.spark.repl.Main
+        $FWDIR/bin/spark-submit --class org.apache.spark.repl.Main spark-shell "$@"
         stty icanon echo > /dev/null 2>&1
     else
         export SPARK_SUBMIT_OPTS
-        $FWDIR/bin/spark-submit spark-shell "$@" --class org.apache.spark.repl.Main
+        $FWDIR/bin/spark-submit --class org.apache.spark.repl.Main spark-shell "$@"
     fi
 }
 

bin/spark-shell.cmd

@@ -19,4 +19,4 @@ rem
 
 set SPARK_HOME=%~dp0..
 
-cmd /V /E /C %SPARK_HOME%\bin\spark-submit.cmd spark-shell %* --class org.apache.spark.repl.Main
+cmd /V /E /C %SPARK_HOME%\bin\spark-submit.cmd spark-shell --class org.apache.spark.repl.Main %*

bin/spark-sql

@@ -0,0 +1,36 @@
+#!/usr/bin/env bash
+
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+#
+# Shell script for starting the Spark SQL CLI
+
+# Enter posix mode for bash
+set -o posix
+
+# Figure out where Spark is installed
+FWDIR="$(cd `dirname $0`/..; pwd)"
+
+if [[ "$@" = *--help ]] || [[ "$@" = *-h ]]; then
+  echo "Usage: ./sbin/spark-sql [options]"
+  $FWDIR/bin/spark-submit --help 2>&1 | grep -v Usage 1>&2
+  exit 0
+fi
+
+CLASS="org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver"
+exec "$FWDIR"/bin/spark-submit --class $CLASS spark-internal $@

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>
@@ -150,7 +150,7 @@
     <dependency>
       <groupId>org.json4s</groupId>
       <artifactId>json4s-jackson_${scala.binary.version}</artifactId>
-      <version>3.2.6</version>
+      <version>3.2.10</version>
     </dependency>
     <dependency>
       <groupId>colt</groupId>
@@ -192,8 +192,8 @@
     </dependency>
     <dependency>
       <groupId>org.tachyonproject</groupId>
-      <artifactId>tachyon</artifactId>
-      <version>0.4.1-thrift</version>
+      <artifactId>tachyon-client</artifactId>
+      <version>0.5.0</version>
       <exclusions>
         <exclusion>
           <groupId>org.apache.hadoop</groupId>
@@ -262,6 +262,11 @@
       <artifactId>asm</artifactId>
       <scope>test</scope>
     </dependency>
+    <dependency>
+      <groupId>junit</groupId>
+      <artifactId>junit</artifactId>
+      <scope>test</scope>
+    </dependency>
     <dependency>
       <groupId>com.novocode</groupId>
       <artifactId>junit-interface</artifactId>
@@ -275,7 +280,7 @@
     <dependency>
       <groupId>net.sf.py4j</groupId>
       <artifactId>py4j</artifactId>
-      <version>0.8.1</version>
+      <version>0.8.2.1</version>
     </dependency>
   </dependencies>
   <build>

core/src/main/scala/org/apache/spark/Accumulators.scala

@@ -36,15 +36,21 @@ import org.apache.spark.serializer.JavaSerializer
  *
  * @param initialValue initial value of accumulator
  * @param param helper object defining how to add elements of type `R` and `T`
+ * @param name human-readable name for use in Spark's web UI
  * @tparam R the full accumulated data (result type)
  * @tparam T partial data that can be added in
  */
 class Accumulable[R, T] (
     @transient initialValue: R,
-    param: AccumulableParam[R, T])
+    param: AccumulableParam[R, T],
+    val name: Option[String])
   extends Serializable {
 
-  val id = Accumulators.newId
+  def this(@transient initialValue: R, param: AccumulableParam[R, T]) =
+    this(initialValue, param, None)
+
+  val id: Long = Accumulators.newId
+
   @transient private var value_ = initialValue // Current value on master
   val zero = param.zero(initialValue)  // Zero value to be passed to workers
   private var deserialized = false
@@ -219,8 +225,10 @@ GrowableAccumulableParam[R <% Growable[T] with TraversableOnce[T] with Serializa
  * @param param helper object defining how to add elements of type `T`
  * @tparam T result type
  */
-class Accumulator[T](@transient initialValue: T, param: AccumulatorParam[T])
-  extends Accumulable[T,T](initialValue, param)
+class Accumulator[T](@transient initialValue: T, param: AccumulatorParam[T], name: Option[String])
+    extends Accumulable[T,T](initialValue, param, name) {
+  def this(initialValue: T, param: AccumulatorParam[T]) = this(initialValue, param, None)
+}
 
 /**
  * A simpler version of [[org.apache.spark.AccumulableParam]] where the only data type you can add
@@ -281,4 +289,7 @@ private object Accumulators {
       }
     }
   }
+
+  def stringifyPartialValue(partialValue: Any) = "%s".format(partialValue)
+  def stringifyValue(value: Any) = "%s".format(value)
 }

core/src/main/scala/org/apache/spark/Aggregator.scala

@@ -56,18 +56,23 @@ case class Aggregator[K, V, C] (
     } else {
       val combiners = new ExternalAppendOnlyMap[K, V, C](createCombiner, mergeValue, mergeCombiners)
       combiners.insertAll(iter)
-      // TODO: Make this non optional in a future release
-      Option(context).foreach(c => c.taskMetrics.memoryBytesSpilled = combiners.memoryBytesSpilled)
-      Option(context).foreach(c => c.taskMetrics.diskBytesSpilled = combiners.diskBytesSpilled)
+      // Update task metrics if context is not null
+      // TODO: Make context non optional in a future release
+      Option(context).foreach { c =>
+        c.taskMetrics.memoryBytesSpilled += combiners.memoryBytesSpilled
+        c.taskMetrics.diskBytesSpilled += combiners.diskBytesSpilled
+      }
       combiners.iterator
     }
   }
 
   @deprecated("use combineCombinersByKey with TaskContext argument", "0.9.0")
-  def combineCombinersByKey(iter: Iterator[(K, C)]) : Iterator[(K, C)] =
+  def combineCombinersByKey(iter: Iterator[_ <: Product2[K, C]]) : Iterator[(K, C)] =
     combineCombinersByKey(iter, null)
 
-  def combineCombinersByKey(iter: Iterator[(K, C)], context: TaskContext) : Iterator[(K, C)] = {
+  def combineCombinersByKey(iter: Iterator[_ <: Product2[K, C]], context: TaskContext)
+      : Iterator[(K, C)] =
+  {
     if (!externalSorting) {
       val combiners = new AppendOnlyMap[K,C]
       var kc: Product2[K, C] = null
@@ -85,9 +90,12 @@ case class Aggregator[K, V, C] (
         val pair = iter.next()
         combiners.insert(pair._1, pair._2)
       }
-      // TODO: Make this non optional in a future release
-      Option(context).foreach(c => c.taskMetrics.memoryBytesSpilled = combiners.memoryBytesSpilled)
-      Option(context).foreach(c => c.taskMetrics.diskBytesSpilled = combiners.diskBytesSpilled)
+      // Update task metrics if context is not null
+      // TODO: Make context non-optional in a future release
+      Option(context).foreach { c =>
+        c.taskMetrics.memoryBytesSpilled += combiners.memoryBytesSpilled
+        c.taskMetrics.diskBytesSpilled += combiners.diskBytesSpilled
+      }
       combiners.iterator
     }
   }