Merge branch 'master' of https://github.com/apache/spark into master_nravi

Author: nishkamravi2

.gitignore

@@ -1,9 +1,12 @@
 *~
+*.#*
+*#*#
 *.swp
 *.ipr
 *.iml
 *.iws
 .idea/
+.idea_modules/
 sbt/*.jar
 .settings
 .cache
@@ -15,10 +18,11 @@ out/
 third_party/libmesos.so
 third_party/libmesos.dylib
 conf/java-opts
-conf/spark-env.sh
-conf/streaming-env.sh
-conf/log4j.properties
-conf/spark-defaults.conf
+conf/*.sh
+conf/*.cmd
+conf/*.properties
+conf/*.conf
+conf/*.xml
 docs/_site
 docs/api
 target/
@@ -49,10 +53,11 @@ unit-tests.log
 /lib/
 rat-results.txt
 scalastyle.txt
-conf/*.conf
+scalastyle-output.xml
 
 # For Hive
 metastore_db/
 metastore/
 warehouse/
 TempStatsStore/
+sql/hive-thriftserver/test_warehouses

.rat-excludes

@@ -20,16 +20,19 @@ log4j.properties.template
 metrics.properties.template
 slaves
 spark-env.sh
+spark-env.cmd
 spark-env.sh.template
 log4j-defaults.properties
 bootstrap-tooltip.js
 jquery-1.11.1.min.js
 sorttable.js
+.*avsc
 .*txt
 .*json
 .*data
 .*log
 cloudpickle.py
+heapq3.py
 join.py
 SparkExprTyper.scala
 SparkILoop.scala
@@ -55,3 +58,5 @@ dist/*
 .*ipr
 .*iws
 logs
+.*scalastyle-output.xml
+.*dependency-reduced-pom.xml

CONTRIBUTING.md

@@ -0,0 +1,12 @@
+## Contributing to Spark
+
+Contributions via GitHub pull requests are gladly accepted from their original
+author. Along with any pull requests, please state that the contribution is
+your original work and that you license the work to the project under the
+project's open source license. Whether or not you state this explicitly, by
+submitting any copyrighted material via pull request, email, or other means
+you agree to license the material under the project's open source license and
+warrant that you have the legal authority to do so.
+
+Please see the [Contributing to Spark wiki page](https://cwiki.apache.org/SPARK/Contributing+to+Spark)
+for more information.

LICENSE

@@ -1,21 +1,31 @@
 # Apache Spark
 
-Lightning-Fast Cluster Computing - <http://spark.apache.org/>
+Spark is a fast and general cluster computing system for Big Data. It provides
+high-level APIs in Scala, Java, and Python, and an optimized engine that
+supports general computation graphs for data analysis. It also supports a
+rich set of higher-level tools including Spark SQL for SQL and structured
+data processing, MLlib for machine learning, GraphX for graph processing,
+and Spark Streaming for stream processing.
+
+<http://spark.apache.org/>
 
 
 ## Online Documentation
 
 You can find the latest Spark documentation, including a programming
-guide, on the project webpage at <http://spark.apache.org/documentation.html>.
+guide, on the [project web page](http://spark.apache.org/documentation.html).
 This README file only contains basic setup instructions.
 
 ## Building Spark
 
-Spark is built on Scala 2.10. To build Spark and its example programs, run:
+Spark is built using [Apache Maven](http://maven.apache.org/).
+To build Spark and its example programs, run:
 
-    ./sbt/sbt assembly
+    mvn -DskipTests clean package
 
 (You do not need to do this if you downloaded a pre-built package.)
+More detailed documentation is available from the project site, at
+["Building Spark"](http://spark.apache.org/docs/latest/building-spark.html).
 
 ## Interactive Scala Shell
 
@@ -62,65 +72,26 @@ Many of the example programs print usage help if no params are given.
 Testing first requires [building Spark](#building-spark). Once Spark is built, tests
 can be run using:
 
-    ./sbt/sbt test
+    ./dev/run-tests
+
+Please see the guidance on how to 
+[run all automated tests](https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark#ContributingtoSpark-AutomatedTesting).
 
 ## A Note About Hadoop Versions
 
 Spark uses the Hadoop core library to talk to HDFS and other Hadoop-supported
 storage systems. Because the protocols have changed in different versions of
 Hadoop, you must build Spark against the same version that your cluster runs.
-You can change the version by setting `-Dhadoop.version` when building Spark.
-
-For Apache Hadoop versions 1.x, Cloudera CDH MRv1, and other Hadoop
-versions without YARN, use:
-
-    # Apache Hadoop 1.2.1
-    $ sbt/sbt -Dhadoop.version=1.2.1 assembly
-
-    # Cloudera CDH 4.2.0 with MapReduce v1
-    $ sbt/sbt -Dhadoop.version=2.0.0-mr1-cdh4.2.0 assembly
-
-For Apache Hadoop 2.2.X, 2.1.X, 2.0.X, 0.23.x, Cloudera CDH MRv2, and other Hadoop versions
-with YARN, also set `-Pyarn`:
-
-    # Apache Hadoop 2.0.5-alpha
-    $ sbt/sbt -Dhadoop.version=2.0.5-alpha -Pyarn assembly
-
-    # Cloudera CDH 4.2.0 with MapReduce v2
-    $ sbt/sbt -Dhadoop.version=2.0.0-cdh4.2.0 -Pyarn assembly
-
-    # Apache Hadoop 2.2.X and newer
-    $ sbt/sbt -Dhadoop.version=2.2.0 -Pyarn assembly
-
-When developing a Spark application, specify the Hadoop version by adding the
-"hadoop-client" artifact to your project's dependencies. For example, if you're
-using Hadoop 1.2.1 and build your application using SBT, add this entry to
-`libraryDependencies`:
-
-    "org.apache.hadoop" % "hadoop-client" % "1.2.1"
-
-If your project is built with Maven, add this to your POM file's `<dependencies>` section:
-
-    <dependency>
-      <groupId>org.apache.hadoop</groupId>
-      <artifactId>hadoop-client</artifactId>
-      <version>1.2.1</version>
-    </dependency>
 
+Please refer to the build documentation at
+["Specifying the Hadoop Version"](http://spark.apache.org/docs/latest/building-spark.html#specifying-the-hadoop-version)
+for detailed guidance on building for a particular distribution of Hadoop, including
+building for particular Hive and Hive Thriftserver distributions. See also
+["Third Party Hadoop Distributions"](http://spark.apache.org/docs/latest/hadoop-third-party-distributions.html)
+for guidance on building a Spark application that works with a particular
+distribution.
 
 ## Configuration
 
 Please refer to the [Configuration guide](http://spark.apache.org/docs/latest/configuration.html)
 in the online documentation for an overview on how to configure Spark.
-
-
-## Contributing to Spark
-
-Contributions via GitHub pull requests are gladly accepted from their original
-author. Along with any pull requests, please state that the contribution is
-your original work and that you license the work to the project under the
-project's open source license. Whether or not you state this explicitly, by
-submitting any copyrighted material via pull request, email, or other means
-you agree to license the material under the project's open source license and
-warrant that you have the legal authority to do so.
-

README.md

@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent</artifactId>
-    <version>1.1.0-SNAPSHOT</version>
+    <version>1.2.0-SNAPSHOT</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 
@@ -39,9 +39,16 @@
     <deb.pkg.name>spark</deb.pkg.name>
     <deb.install.path>/usr/share/spark</deb.install.path>
     <deb.user>root</deb.user>
+    <deb.bin.filemode>744</deb.bin.filemode>
   </properties>
 
   <dependencies>
+    <!-- Promote Guava to compile scope in this module so it's included while shading. -->
+    <dependency>
+      <groupId>com.google.guava</groupId>
+      <artifactId>guava</artifactId>
+      <scope>compile</scope>
+    </dependency>
     <dependency>
       <groupId>org.apache.spark</groupId>
       <artifactId>spark-core_${scala.binary.version}</artifactId>
@@ -81,6 +88,20 @@
 
   <build>
     <plugins>
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-deploy-plugin</artifactId>
+        <configuration>
+          <skip>true</skip>
+        </configuration>
+      </plugin>
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-install-plugin</artifactId>
+        <configuration>
+          <skip>true</skip>
+        </configuration>
+      </plugin>
       <!-- Use the shade plugin to create a big JAR with all the dependencies -->
       <plugin>
         <groupId>org.apache.maven.plugins</groupId>
@@ -112,6 +133,18 @@
               <goal>shade</goal>
             </goals>
             <configuration>
+              <relocations>
+                <relocation>
+                  <pattern>com.google</pattern>
+                  <shadedPattern>org.spark-project.guava</shadedPattern>
+                  <includes>
+                    <include>com.google.common.**</include>
+                  </includes>
+                  <excludes>
+                    <exclude>com.google.common.base.Optional**</exclude>
+                  </excludes>
+                </relocation>
+              </relocations>
               <transformers>
                 <transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer" />
                 <transformer implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer">
@@ -162,6 +195,11 @@
           <artifactId>spark-hive_${scala.binary.version}</artifactId>
           <version>${project.version}</version>
         </dependency>
+        <dependency>
+          <groupId>org.apache.spark</groupId>
+          <artifactId>spark-hive-thriftserver_${scala.binary.version}</artifactId>
+          <version>${project.version}</version>
+        </dependency>
       </dependencies>
     </profile>
     <profile>
@@ -276,7 +314,7 @@
                         <user>${deb.user}</user>
                         <group>${deb.user}</group>
                         <prefix>${deb.install.path}/bin</prefix>
-                        <filemode>744</filemode>
+                        <filemode>${deb.bin.filemode}</filemode>
                       </mapper>
                     </data>
                     <data>

assembly/pom.xml

@@ -21,14 +21,14 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent</artifactId>
-    <version>1.1.0-SNAPSHOT</version>
+    <version>1.2.0-SNAPSHOT</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 
   <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>

bagel/pom.xml

@@ -72,6 +72,7 @@ object Bagel extends Logging {
     var verts = vertices
     var msgs = messages
     var noActivity = false
+    var lastRDD: RDD[(K, (V, Array[M]))] = null
     do {
       logInfo("Starting superstep " + superstep + ".")
       val startTime = System.currentTimeMillis
@@ -83,6 +84,10 @@ object Bagel extends Logging {
       val superstep_ = superstep  // Create a read-only copy of superstep for capture in closure
       val (processed, numMsgs, numActiveVerts) =
         comp[K, V, M, C](sc, grouped, compute(_, _, aggregated, superstep_), storageLevel)
+      if (lastRDD != null) {
+        lastRDD.unpersist(false)
+      }
+      lastRDD = processed
 
       val timeTaken = System.currentTimeMillis - startTime
       logInfo("Superstep %d took %d s".format(superstep, timeTaken / 1000))

bagel/src/main/scala/org/apache/spark/bagel/Bagel.scala

@@ -24,8 +24,6 @@ import org.scalatest.time.SpanSugar._
 import org.apache.spark._
 import org.apache.spark.storage.StorageLevel
 
-import scala.language.postfixOps
-
 class TestVertex(val active: Boolean, val age: Int) extends Vertex with Serializable
 class TestMessage(val targetId: String) extends Message[String] with Serializable
 

bagel/src/test/scala/org/apache/spark/bagel/BagelSuite.scala

@@ -1,3 +1,6 @@
+#!/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.
@@ -12,21 +15,16 @@
 # 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.
- 
- language: scala
- scala:
-   - "2.10.3"
- jdk:
-   - oraclejdk7
- env:
-  matrix:
-   - TEST="scalastyle assembly/assembly"
-   - TEST="catalyst/test sql/test streaming/test mllib/test graphx/test bagel/test"
-   - TEST=hive/test
- cache:
-   directories:
-     - $HOME/.m2
-     - $HOME/.ivy2
-     - $HOME/.sbt
- script:
-   - "sbt ++$TRAVIS_SCALA_VERSION $TEST"
+#
+
+#
+# Shell script for starting BeeLine
+
+# Enter posix mode for bash
+set -o posix
+
+# Figure out where Spark is installed
+FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
+
+CLASS="org.apache.hive.beeline.BeeLine"
+exec "$FWDIR/bin/spark-class" $CLASS "$@"