Merge in master

Author: holdenk

.gitignore

@@ -7,6 +7,7 @@
 sbt/*.jar
 .settings
 .cache
+.mima-excludes
 /build/
 work/
 out/
@@ -45,3 +46,5 @@ dist/
 spark-*-bin.tar.gz
 unit-tests.log
 /lib/
+rat-results.txt
+scalastyle.txt

.rat-excludes

@@ -0,0 +1,45 @@
+target
+.gitignore
+.project
+.classpath
+.mima-excludes
+.rat-excludes
+.*md
+derby.log
+TAGS
+RELEASE
+control
+docs
+fairscheduler.xml.template
+spark-defaults.conf.template
+log4j.properties
+log4j.properties.template
+metrics.properties.template
+slaves
+spark-env.sh
+spark-env.sh.template
+log4j-defaults.properties
+sorttable.js
+.*txt
+.*data
+.*log
+cloudpickle.py
+join.py
+SparkExprTyper.scala
+SparkILoop.scala
+SparkILoopInit.scala
+SparkIMain.scala
+SparkImports.scala
+SparkJLineCompletion.scala
+SparkJLineReader.scala
+SparkMemberHandlers.scala
+sbt
+sbt-launch-lib.bash
+plugins.sbt
+work
+.*\.q
+golden
+test.out/*
+.*iml
+service.properties
+db.lck

.travis.yml

@@ -0,0 +1,32 @@
+# 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.
+ 
+ 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"

NOTICE

@@ -1,5 +1,14 @@
 Apache Spark
-Copyright 2013 The Apache Software Foundation.
+Copyright 2014 The Apache Software Foundation.
 
 This product includes software developed at
 The Apache Software Foundation (http://www.apache.org/).
+
+In addition, this product includes:
+
+- JUnit (http://www.junit.org) is a testing framework for Java. We included it
+  under the terms of the Eclipse Public License v1.0.
+
+- JTransforms (https://sites.google.com/site/piotrwendykier/software/jtransforms)
+  provides fast transforms in Java. It is tri-licensed, and we included it under 
+  the terms of the Mozilla Public License v1.1.

README.md

@@ -10,20 +10,33 @@ guide, on the project webpage at <http://spark.apache.org/documentation.html>.
 This README file only contains basic setup instructions.
 
 
-## Building
+## Building Spark
 
-Spark requires Scala 2.10. The project is built using Simple Build Tool (SBT),
-which can be obtained [here](http://www.scala-sbt.org). If SBT is installed we
-will use the system version of sbt otherwise we will attempt to download it
-automatically. To build Spark and its example programs, run:
+Spark is built on Scala 2.10. To build Spark and its example programs, run:
 
     ./sbt/sbt assembly
 
-Once you've built Spark, the easiest way to start using it is the shell:
+## Interactive Scala Shell
+
+The easiest way to start using Spark is through the Scala shell:
 
     ./bin/spark-shell
 
-Or, for the Python API, the Python shell (`./bin/pyspark`).
+Try the following command, which should return 1000:
+
+    scala> sc.parallelize(1 to 1000).count()
+
+## Interactive Python Shell
+
+Alternatively, if you prefer Python, you can use the Python shell:
+
+    ./bin/pyspark
+    
+And run the following command, which should also return 1000:
+
+    >>> sc.parallelize(range(1000)).count()
+
+## Example Programs
 
 Spark also comes with several sample programs in the `examples` directory.
 To run one of them, use `./bin/run-example <class> <params>`. For example:
@@ -38,13 +51,13 @@ All of the Spark samples take a `<master>` parameter that is the cluster URL
 to connect to. This can be a mesos:// or spark:// URL, or "local" to run
 locally with one thread, or "local[N]" to run locally with N threads.
 
-## Running tests
+## Running Tests
 
-Testing first requires [Building](#building) Spark. Once Spark is built, tests
+Testing first requires [building Spark](#building-spark). Once Spark is built, tests
 can be run using:
 
-`./sbt/sbt test`
- 
+    ./sbt/sbt test
+
 ## A Note About Hadoop Versions
 
 Spark uses the Hadoop core library to talk to HDFS and other Hadoop-supported

assembly/pom.xml

@@ -79,6 +79,11 @@
       <artifactId>spark-graphx_${scala.binary.version}</artifactId>
       <version>${project.version}</version>
     </dependency>
+    <dependency>
+      <groupId>org.apache.spark</groupId>
+      <artifactId>spark-sql_${scala.binary.version}</artifactId>
+      <version>${project.version}</version>
+    </dependency>
     <dependency>
       <groupId>net.sf.py4j</groupId>
       <artifactId>py4j</artifactId>
@@ -158,6 +163,16 @@
         </dependency>
       </dependencies>
     </profile>
+    <profile>
+      <id>hive</id>
+      <dependencies>
+        <dependency>
+          <groupId>org.apache.spark</groupId>
+          <artifactId>spark-hive_${scala.binary.version}</artifactId>
+          <version>${project.version}</version>
+        </dependency>
+      </dependencies>
+    </profile>
     <profile>
       <id>spark-ganglia-lgpl</id>
       <dependencies>
@@ -203,7 +218,7 @@
           <plugin>
             <groupId>org.codehaus.mojo</groupId>
             <artifactId>buildnumber-maven-plugin</artifactId>
-            <version>1.1</version>
+            <version>1.2</version>
             <executions>
               <execution>
                 <phase>validate</phase>

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

@@ -220,27 +220,31 @@ object Bagel extends Logging {
    */
   private def comp[K: Manifest, V <: Vertex, M <: Message[K], C](
     sc: SparkContext,
-    grouped: RDD[(K, (Seq[C], Seq[V]))],
+    grouped: RDD[(K, (Iterable[C], Iterable[V]))],
     compute: (V, Option[C]) => (V, Array[M]),
     storageLevel: StorageLevel
   ): (RDD[(K, (V, Array[M]))], Int, Int) = {
     var numMsgs = sc.accumulator(0)
     var numActiveVerts = sc.accumulator(0)
-    val processed = grouped.flatMapValues {
-      case (_, vs) if vs.size == 0 => None
-      case (c, vs) =>
+    val processed = grouped.mapValues(x => (x._1.iterator, x._2.iterator))
+      .flatMapValues {
+      case (_, vs) if !vs.hasNext => None
+      case (c, vs) => {
         val (newVert, newMsgs) =
-          compute(vs(0), c match {
-            case Seq(comb) => Some(comb)
-            case Seq() => None
-          })
+          compute(vs.next,
+            c.hasNext match {
+              case true => Some(c.next)
+              case false => None
+            }
+          )
 
         numMsgs += newMsgs.size
         if (newVert.active) {
           numActiveVerts += 1
         }
 
         Some((newVert, newMsgs))
+      }
     }.persist(storageLevel)
 
     // Force evaluation of processed RDD for accurate performance measurements

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

@@ -24,13 +24,15 @@ 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
 
 class BagelSuite extends FunSuite with Assertions with BeforeAndAfter with Timeouts {
-  
+
   var sc: SparkContext = _
-  
+
   after {
     if (sc != null) {
       sc.stop()

bin/compute-classpath.sh

@@ -25,35 +25,55 @@ SCALA_VERSION=2.10
 # Figure out where Spark is installed
 FWDIR="$(cd `dirname $0`/..; pwd)"
 
-# Load environment variables from conf/spark-env.sh, if it exists
-if [ -e "$FWDIR/conf/spark-env.sh" ] ; then
-  . $FWDIR/conf/spark-env.sh
-fi
+. $FWDIR/bin/load-spark-env.sh
 
 # Build up classpath
 CLASSPATH="$SPARK_CLASSPATH:$FWDIR/conf"
 
+ASSEMBLY_DIR="$FWDIR/assembly/target/scala-$SCALA_VERSION"
+
 # First check if we have a dependencies jar. If so, include binary classes with the deps jar
-if [ -f "$FWDIR"/assembly/target/scala-$SCALA_VERSION/spark-assembly*hadoop*-deps.jar ]; then
+if [ -f "$ASSEMBLY_DIR"/spark-assembly*hadoop*-deps.jar ]; then
   CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/repl/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/bagel/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/graphx/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/streaming/target/scala-$SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/tools/target/scala-$SCALA_VERSION/classes"
+  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"
 
-  DEPS_ASSEMBLY_JAR=`ls "$FWDIR"/assembly/target/scala-$SCALA_VERSION/spark-assembly*hadoop*-deps.jar`
+  DEPS_ASSEMBLY_JAR=`ls "$ASSEMBLY_DIR"/spark-assembly*hadoop*-deps.jar`
   CLASSPATH="$CLASSPATH:$DEPS_ASSEMBLY_JAR"
 else
   # Else use spark-assembly jar from either RELEASE or assembly directory
   if [ -f "$FWDIR/RELEASE" ]; then
-    ASSEMBLY_JAR=`ls "$FWDIR"/jars/spark-assembly*.jar`
+    ASSEMBLY_JAR=`ls "$FWDIR"/jars/spark*-assembly*.jar`
   else
-    ASSEMBLY_JAR=`ls "$FWDIR"/assembly/target/scala-$SCALA_VERSION/spark-assembly*hadoop*.jar`
+    ASSEMBLY_JAR=`ls "$ASSEMBLY_DIR"/spark*-assembly*hadoop*.jar`
   fi
   CLASSPATH="$CLASSPATH:$ASSEMBLY_JAR"
 fi
 
+# When Hive support is needed, Datanucleus jars must be included on the classpath.
+# Datanucleus jars do not work if only included in the  uber jar as plugin.xml metadata is lost.
+# Both sbt and maven will populate "lib_managed/jars/" with the datanucleus jars when Spark is
+# built with Hive, so first check if the datanucleus jars exist, and then ensure the current Spark
+# assembly is built for Hive, before actually populating the CLASSPATH with the jars.
+# Note that this check order is faster (by up to half a second) in the case where Hive is not used.
+num_datanucleus_jars=$(ls "$FWDIR"/lib_managed/jars/ 2>/dev/null | grep "datanucleus-.*\\.jar" | wc -l)
+if [ $num_datanucleus_jars -gt 0 ]; then
+  AN_ASSEMBLY_JAR=${ASSEMBLY_JAR:-$DEPS_ASSEMBLY_JAR}
+  num_hive_files=$(jar tvf "$AN_ASSEMBLY_JAR" org/apache/hadoop/hive/ql/exec 2>/dev/null | wc -l)
+  if [ $num_hive_files -gt 0 ]; then
+    echo "Spark assembly has been built with Hive, including Datanucleus jars on classpath" 1>&2
+    DATANUCLEUSJARS=$(echo "$FWDIR/lib_managed/jars"/datanucleus-*.jar | tr " " :)
+    CLASSPATH=$CLASSPATH:$DATANUCLEUSJARS
+  fi
+fi
+
 # Add test classes if we're running from SBT or Maven with SPARK_TESTING set to 1
 if [[ $SPARK_TESTING == 1 ]]; then
   CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SCALA_VERSION/test-classes"
@@ -62,6 +82,9 @@ if [[ $SPARK_TESTING == 1 ]]; then
   CLASSPATH="$CLASSPATH:$FWDIR/bagel/target/scala-$SCALA_VERSION/test-classes"
   CLASSPATH="$CLASSPATH:$FWDIR/graphx/target/scala-$SCALA_VERSION/test-classes"
   CLASSPATH="$CLASSPATH:$FWDIR/streaming/target/scala-$SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/sql/catalyst/target/scala-$SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/sql/core/target/scala-$SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/sql/hive/target/scala-$SCALA_VERSION/test-classes"
 fi
 
 # Add hadoop conf dir if given -- otherwise FileSystem.*, etc fail !

bin/load-spark-env.sh

@@ -0,0 +1,38 @@
+#!/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.
+#
+
+# This script loads spark-env.sh if it exists, and ensures it is only loaded once.
+# spark-env.sh is loaded from SPARK_CONF_DIR if set, or within the current directory's
+# conf/ subdirectory.
+
+if [ -z "$SPARK_ENV_LOADED" ]; then
+  export SPARK_ENV_LOADED=1
+
+  # Returns the parent of the directory this script lives in.
+  parent_dir="$(cd `dirname $0`/..; pwd)"
+
+  use_conf_dir=${SPARK_CONF_DIR:-"$parent_dir/conf"}
+
+  if [ -f "${use_conf_dir}/spark-env.sh" ]; then
+    # Promote all variable declarations to environment (exported) variables
+    set -a
+    . "${use_conf_dir}/spark-env.sh"
+    set +a
+  fi
+fi