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

Conflicts:
	sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/types/dataTypes.scala

LICENSE

@@ -712,18 +712,6 @@ THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
 NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
 EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
-========================================================================
-For colt:
-========================================================================
-
-Copyright (c) 1999 CERN - European Organization for Nuclear Research.
-Permission to use, copy, modify, distribute and sell this software and its documentation for any purpose is hereby granted without fee, provided that the above copyright notice appear in all copies and that both that copyright notice and this permission notice appear in supporting documentation. CERN makes no representations about the suitability of this software for any purpose. It is provided "as is" without expressed or implied warranty.
-
-Packages hep.aida.*
-
-Written by Pavel Binko, Dino Ferrero Merlino, Wolfgang Hoschek, Tony Johnson, Andreas Pfeiffer, and others. Check the FreeHEP home page for more info. Permission to use and/or redistribute this work is granted under the terms of the LGPL License, with the exception that any usage related to military applications is expressly forbidden. The software and documentation made available under the terms of this license are provided with no warranty.
-
-
 ========================================================================
 For SnapTree:
 ========================================================================

README.md

@@ -84,7 +84,7 @@ storage systems. Because the protocols have changed in different versions of
 Hadoop, you must build Spark against the same version that your cluster runs.
 
 Please refer to the build documentation at
-["Specifying the Hadoop Version"](http://spark.apache.org/docs/latest/building-spark.html#specifying-the-hadoop-version)
+["Specifying the Hadoop Version"](http://spark.apache.org/docs/latest/building-with-maven.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)

assembly/pom.xml

@@ -146,6 +146,10 @@
                     <exclude>com/google/common/base/Present*</exclude>
                   </excludes>
                 </relocation>
+                <relocation>
+                  <pattern>org.apache.commons.math3</pattern>
+                  <shadedPattern>org.spark-project.commons.math3</shadedPattern>
+                </relocation>
               </relocations>
               <transformers>
                 <transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer" />

bin/pyspark2.cmd

@@ -59,7 +59,12 @@ for /f %%i in ('echo %1^| findstr /R "\.py"') do (
 )
 
 if [%PYTHON_FILE%] == [] (
-  %PYSPARK_PYTHON%
+  set PYSPARK_SHELL=1
+  if [%IPYTHON%] == [1] (
+	ipython %IPYTHON_OPTS%
+  ) else (
+	%PYSPARK_PYTHON%
+  ) 
 ) else (
   echo.
   echo WARNING: Running python applications through ./bin/pyspark.cmd is deprecated as of Spark 1.0.

core/pom.xml

@@ -44,6 +44,11 @@
         </exclusion>
       </exclusions>
     </dependency>
+    <dependency>
+      <groupId>org.apache.spark</groupId>
+      <artifactId>network</artifactId>
+      <version>${project.version}</version>
+    </dependency>
     <dependency>
       <groupId>net.java.dev.jets3t</groupId>
       <artifactId>jets3t</artifactId>
@@ -85,8 +90,6 @@
     <dependency>
       <groupId>org.apache.commons</groupId>
       <artifactId>commons-math3</artifactId>
-      <version>3.3</version>
-      <scope>test</scope>
     </dependency>
     <dependency>
       <groupId>com.google.code.findbugs</groupId>
@@ -162,10 +165,6 @@
       <artifactId>json4s-jackson_${scala.binary.version}</artifactId>
       <version>3.2.10</version>
     </dependency>
-    <dependency>
-      <groupId>colt</groupId>
-      <artifactId>colt</artifactId>
-    </dependency>
     <dependency>
       <groupId>org.apache.mesos</groupId>
       <artifactId>mesos</artifactId>
@@ -247,6 +246,11 @@
         </exclusion>
       </exclusions>
     </dependency>
+    <dependency>
+      <groupId>org.seleniumhq.selenium</groupId>
+      <artifactId>selenium-java</artifactId>
+      <scope>test</scope>
+    </dependency>
     <dependency>
       <groupId>org.scalatest</groupId>
       <artifactId>scalatest_${scala.binary.version}</artifactId>

core/src/main/java/org/apache/spark/JobExecutionStatus.java

@@ -0,0 +1,25 @@
+/*
+ * 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.
+ */
+
+package org.apache.spark;
+
+public enum JobExecutionStatus {
+  RUNNING,
+  SUCCEEDED,
+  FAILED,
+  UNKNOWN
+}

core/src/main/scala/org/apache/spark/storage/BlockDataProvider.scala → core/src/main/java/org/apache/spark/SparkJobInfo.java

@@ -15,18 +15,16 @@
  * limitations under the License.
  */
 
-package org.apache.spark.storage
-
-import java.nio.ByteBuffer
-
+package org.apache.spark;
 
 /**
- * An interface for providing data for blocks.
- *
- * getBlockData returns either a FileSegment (for zero-copy send), or a ByteBuffer.
+ * Exposes information about Spark Jobs.
  *
- * Aside from unit tests, [[BlockManager]] is the main class that implements this.
+ * This interface is not designed to be implemented outside of Spark.  We may add additional methods
+ * which may break binary compatibility with outside implementations.
  */
-private[spark] trait BlockDataProvider {
-  def getBlockData(blockId: String): Either[FileSegment, ByteBuffer]
+public interface SparkJobInfo {
+  int jobId();
+  int[] stageIds();
+  JobExecutionStatus status();
 }

core/src/main/scala/org/apache/spark/network/netty/server/BlockHeader.scala → core/src/main/java/org/apache/spark/SparkStageInfo.java

@@ -15,18 +15,20 @@
  * limitations under the License.
  */
 
-package org.apache.spark.network.netty.server
+package org.apache.spark;
 
 /**
- * Header describing a block. This is used only in the server pipeline.
+ * Exposes information about Spark Stages.
  *
- * [[BlockServerHandler]] creates this, and [[BlockHeaderEncoder]] encodes it.
- *
- * @param blockSize length of the block content, excluding the length itself.
- *                 If positive, this is the header for a block (not part of the header).
- *                 If negative, this is the header and content for an error message.
- * @param blockId block id
- * @param error some error message from reading the block
+ * This interface is not designed to be implemented outside of Spark.  We may add additional methods
+ * which may break binary compatibility with outside implementations.
  */
-private[server]
-class BlockHeader(val blockSize: Int, val blockId: String, val error: Option[String] = None)
+public interface SparkStageInfo {
+  int stageId();
+  int currentAttemptId();
+  String name();
+  int numTasks();
+  int numActiveTasks();
+  int numCompletedTasks();
+  int numFailedTasks();
+}

core/src/main/java/org/apache/spark/TaskContext.java

@@ -71,15 +71,13 @@ static void unset() {
   /**
    * Add a (Java friendly) listener to be executed on task completion.
    * This will be called in all situation - success, failure, or cancellation.
-   * <p/>
    * An example use is for HadoopRDD to register a callback to close the input stream.
    */
   public abstract TaskContext addTaskCompletionListener(TaskCompletionListener listener);
 
   /**
    * Add a listener in the form of a Scala closure to be executed on task completion.
    * This will be called in all situations - success, failure, or cancellation.
-   * <p/>
    * An example use is for HadoopRDD to register a callback to close the input stream.
    */
   public abstract TaskContext addTaskCompletionListener(final Function1<TaskContext, Unit> f);

core/src/main/java/org/apache/spark/api/java/function/PairFunction.java

@@ -22,7 +22,8 @@
 import scala.Tuple2;
 
 /**
- * A function that returns key-value pairs (Tuple2<K, V>), and can be used to construct PairRDDs.
+ * A function that returns key-value pairs (Tuple2&lt;K, V&gt;), and can be used to
+ * construct PairRDDs.
  */
 public interface PairFunction<T, K, V> extends Serializable {
   public Tuple2<K, V> call(T t) throws Exception;