Patch/1.2.1 palantir2

.gitignore

@@ -5,6 +5,7 @@
 *.ipr
 *.iml
 *.iws
+*.pyc
 .idea/
 .idea_modules/
 sbt/*.jar
@@ -49,7 +50,9 @@ dependency-reduced-pom.xml
 checkpoint
 derby.log
 dist/
-spark-*-bin.tar.gz
+dev/create-release/*txt
+dev/create-release/*final
+spark-*-bin-*.tgz
 unit-tests.log
 /lib/
 rat-results.txt

.rat-excludes

@@ -44,6 +44,7 @@ SparkImports.scala
 SparkJLineCompletion.scala
 SparkJLineReader.scala
 SparkMemberHandlers.scala
+SparkReplReporter.scala
 sbt
 sbt-launch-lib.bash
 plugins.sbt
@@ -63,3 +64,4 @@ dist/*
 logs
 .*scalastyle-output.xml
 .*dependency-reduced-pom.xml
+known_translations

LICENSE

@@ -646,7 +646,8 @@ THE SOFTWARE.
 
 ========================================================================
 For Scala Interpreter classes (all .scala files in repl/src/main/scala
-except for Main.Scala, SparkHelper.scala and ExecutorClassLoader.scala):
+except for Main.Scala, SparkHelper.scala and ExecutorClassLoader.scala),
+and for SerializableMapWrapper in JavaUtils.scala:
 ========================================================================
 
 Copyright (c) 2002-2013 EPFL
@@ -754,7 +755,7 @@ SUCH DAMAGE.
 
 
 ========================================================================
-For Timsort (core/src/main/java/org/apache/spark/util/collection/Sorter.java):
+For Timsort (core/src/main/java/org/apache/spark/util/collection/TimSort.java):
 ========================================================================
 Copyright (C) 2008 The Android Open Source Project
 
@@ -771,6 +772,25 @@ See the License for the specific language governing permissions and
 limitations under the License.
 
 
+========================================================================
+For LimitedInputStream
+  (network/common/src/main/java/org/apache/spark/network/util/LimitedInputStream.java):
+========================================================================
+Copyright (C) 2007 The Guava Authors
+
+Licensed 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.
+
+
 ========================================================================
 BSD-style licenses
 ========================================================================

README.md

@@ -13,7 +13,8 @@ and Spark Streaming for stream processing.
 ## Online Documentation
 
 You can find the latest Spark documentation, including a programming
-guide, on the [project web page](http://spark.apache.org/documentation.html).
+guide, on the [project web page](http://spark.apache.org/documentation.html)
+and [project wiki](https://cwiki.apache.org/confluence/display/SPARK).
 This README file only contains basic setup instructions.
 
 ## Building Spark
@@ -25,7 +26,7 @@ To build Spark and its example programs, run:
 
 (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 with Maven"](http://spark.apache.org/docs/latest/building-with-maven.html).
+["Building Spark"](http://spark.apache.org/docs/latest/building-spark.html).
 
 ## Interactive Scala Shell
 

assembly/pom.xml

@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent</artifactId>
-    <version>1.2.0-SNAPSHOT</version>
+    <version>1.2.1-palantir2</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 
@@ -66,22 +66,22 @@
     </dependency>
     <dependency>
       <groupId>org.apache.spark</groupId>
-      <artifactId>spark-repl_${scala.binary.version}</artifactId>
+      <artifactId>spark-streaming_${scala.binary.version}</artifactId>
       <version>${project.version}</version>
     </dependency>
     <dependency>
       <groupId>org.apache.spark</groupId>
-      <artifactId>spark-streaming_${scala.binary.version}</artifactId>
+      <artifactId>spark-graphx_${scala.binary.version}</artifactId>
       <version>${project.version}</version>
     </dependency>
     <dependency>
       <groupId>org.apache.spark</groupId>
-      <artifactId>spark-graphx_${scala.binary.version}</artifactId>
+      <artifactId>spark-sql_${scala.binary.version}</artifactId>
       <version>${project.version}</version>
     </dependency>
     <dependency>
       <groupId>org.apache.spark</groupId>
-      <artifactId>spark-sql_${scala.binary.version}</artifactId>
+      <artifactId>spark-repl_${scala.binary.version}</artifactId>
       <version>${project.version}</version>
     </dependency>
   </dependencies>
@@ -197,6 +197,11 @@
           <artifactId>spark-hive_${scala.binary.version}</artifactId>
           <version>${project.version}</version>
         </dependency>
+      </dependencies>
+    </profile>
+    <profile>
+      <id>hive-thriftserver</id>
+      <dependencies>
         <dependency>
           <groupId>org.apache.spark</groupId>
           <artifactId>spark-hive-thriftserver_${scala.binary.version}</artifactId>

bagel/pom.xml

@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent</artifactId>
-    <version>1.2.0-SNAPSHOT</version>
+    <version>1.2.1-palantir2</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 

bin/beeline.cmd

@@ -0,0 +1,21 @@
+@echo off
+
+rem
+rem Licensed to the Apache Software Foundation (ASF) under one or more
+rem contributor license agreements.  See the NOTICE file distributed with
+rem this work for additional information regarding copyright ownership.
+rem The ASF licenses this file to You under the Apache License, Version 2.0
+rem (the "License"); you may not use this file except in compliance with
+rem the License.  You may obtain a copy of the License at
+rem
+rem    http://www.apache.org/licenses/LICENSE-2.0
+rem
+rem Unless required by applicable law or agreed to in writing, software
+rem distributed under the License is distributed on an "AS IS" BASIS,
+rem WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+rem See the License for the specific language governing permissions and
+rem limitations under the License.
+rem
+
+set SPARK_HOME=%~dp0..
+cmd /V /E /C %SPARK_HOME%\bin\spark-class.cmd org.apache.hive.beeline.BeeLine %*

bin/compute-classpath.sh

@@ -20,8 +20,6 @@
 # This script computes Spark's classpath and prints it to stdout; it's used by both the "run"
 # script and the ExecutorRunner in standalone cluster mode.
 
-SCALA_VERSION=2.10
-
 # Figure out where Spark is installed
 FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
 
@@ -36,7 +34,7 @@ else
   CLASSPATH="$CLASSPATH:$FWDIR/conf"
 fi
 
-ASSEMBLY_DIR="$FWDIR/assembly/target/scala-$SCALA_VERSION"
+ASSEMBLY_DIR="$FWDIR/assembly/target/scala-$SPARK_SCALA_VERSION"
 
 if [ -n "$JAVA_HOME" ]; then
   JAR_CMD="$JAVA_HOME/bin/jar"
@@ -48,19 +46,19 @@ fi
 if [ -n "$SPARK_PREPEND_CLASSES" ]; then
   echo "NOTE: SPARK_PREPEND_CLASSES is set, placing locally compiled Spark"\
     "classes ahead of assembly." >&2
-  CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SPARK_SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/core/target/jars/*"
-  CLASSPATH="$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"
-  CLASSPATH="$CLASSPATH:$FWDIR/sql/hive-thriftserver/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/yarn/stable/target/scala-$SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/repl/target/scala-$SPARK_SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SPARK_SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/bagel/target/scala-$SPARK_SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/graphx/target/scala-$SPARK_SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/streaming/target/scala-$SPARK_SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/tools/target/scala-$SPARK_SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/sql/catalyst/target/scala-$SPARK_SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/sql/core/target/scala-$SPARK_SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/sql/hive/target/scala-$SPARK_SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/sql/hive-thriftserver/target/scala-$SPARK_SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/yarn/stable/target/scala-$SPARK_SCALA_VERSION/classes"
 fi
 
 # Use spark-assembly jar from either RELEASE or assembly directory
@@ -70,22 +68,25 @@ else
   assembly_folder="$ASSEMBLY_DIR"
 fi
 
-num_jars="$(ls "$assembly_folder" | grep "spark-assembly.*hadoop.*\.jar" | wc -l)"
-if [ "$num_jars" -eq "0" ]; then
-  echo "Failed to find Spark assembly in $assembly_folder"
-  echo "You need to build Spark before running this program."
-  exit 1
-fi
+num_jars=0
+
+for f in ${assembly_folder}/spark-assembly*hadoop*.jar; do
+  if [[ ! -e "$f" ]]; then
+    echo "Failed to find Spark assembly in $assembly_folder" 1>&2
+    echo "You need to build Spark before running this program." 1>&2
+    exit 1
+  fi
+  ASSEMBLY_JAR="$f"
+  num_jars=$((num_jars+1))
+done
+
 if [ "$num_jars" -gt "1" ]; then
-  jars_list=$(ls "$assembly_folder" | grep "spark-assembly.*hadoop.*.jar")
-  echo "Found multiple Spark assembly jars in $assembly_folder:"
-  echo "$jars_list"
-  echo "Please remove all but one jar."
+  echo "Found multiple Spark assembly jars in $assembly_folder:" 1>&2
+  ls ${assembly_folder}/spark-assembly*hadoop*.jar 1>&2
+  echo "Please remove all but one jar." 1>&2
   exit 1
 fi
 
-ASSEMBLY_JAR="$(ls "$assembly_folder"/spark-assembly*hadoop*.jar 2>/dev/null)"
-
 # Verify that versions of java used to build the jars and run Spark are compatible
 jar_error_check=$("$JAR_CMD" -tf "$ASSEMBLY_JAR" nonexistent/class/path 2>&1)
 if [[ "$jar_error_check" =~ "invalid CEN header" ]]; then
@@ -123,15 +124,15 @@ 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"
-  CLASSPATH="$CLASSPATH:$FWDIR/repl/target/scala-$SCALA_VERSION/test-classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SCALA_VERSION/test-classes"
-  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"
+  CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SPARK_SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/repl/target/scala-$SPARK_SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SPARK_SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/bagel/target/scala-$SPARK_SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/graphx/target/scala-$SPARK_SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/streaming/target/scala-$SPARK_SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/sql/catalyst/target/scala-$SPARK_SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/sql/core/target/scala-$SPARK_SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/sql/hive/target/scala-$SPARK_SCALA_VERSION/test-classes"
 fi
 
 # Add hadoop conf dir if given -- otherwise FileSystem.*, etc fail !

bin/load-spark-env.sh

@@ -36,3 +36,23 @@ if [ -z "$SPARK_ENV_LOADED" ]; then
     set +a
   fi
 fi
+
+# Setting SPARK_SCALA_VERSION if not already set.
+
+if [ -z "$SPARK_SCALA_VERSION" ]; then
+
+    ASSEMBLY_DIR2="$FWDIR/assembly/target/scala-2.11"
+    ASSEMBLY_DIR1="$FWDIR/assembly/target/scala-2.10"
+
+    if [[ -d "$ASSEMBLY_DIR2" && -d "$ASSEMBLY_DIR1" ]]; then
+        echo -e "Presence of build for both scala versions(SCALA 2.10 and SCALA 2.11) detected." 1>&2
+        echo -e 'Either clean one of them or, export SPARK_SCALA_VERSION=2.11 in spark-env.sh.' 1>&2
+        exit 1
+    fi
+
+    if [ -d "$ASSEMBLY_DIR2" ]; then
+        export SPARK_SCALA_VERSION="2.11"
+    else
+        export SPARK_SCALA_VERSION="2.10"
+    fi        
+fi

bin/pyspark

@@ -25,7 +25,7 @@ export SPARK_HOME="$FWDIR"
 
 source "$FWDIR/bin/utils.sh"
 
-SCALA_VERSION=2.10
+source "$FWDIR"/bin/load-spark-env.sh
 
 function usage() {
   echo "Usage: ./bin/pyspark [options]" 1>&2
@@ -40,16 +40,14 @@ fi
 # Exit if the user hasn't compiled Spark
 if [ ! -f "$FWDIR/RELEASE" ]; then
   # Exit if the user hasn't compiled Spark
-  ls "$FWDIR"/assembly/target/scala-$SCALA_VERSION/spark-assembly*hadoop*.jar >& /dev/null
+  ls "$FWDIR"/assembly/target/scala-$SPARK_SCALA_VERSION/spark-assembly*hadoop*.jar >& /dev/null
   if [[ $? != 0 ]]; then
     echo "Failed to find Spark assembly in $FWDIR/assembly/target" 1>&2
     echo "You need to build Spark before running this program" 1>&2
     exit 1
   fi
 fi
 
-. "$FWDIR"/bin/load-spark-env.sh
-
 # In Spark <= 1.1, setting IPYTHON=1 would cause the driver to be launched using the `ipython`
 # executable, while the worker would still be launched using PYSPARK_PYTHON.
 #
@@ -134,7 +132,5 @@ if [[ "$1" =~ \.py$ ]]; then
   gatherSparkSubmitOpts "$@"
   exec "$FWDIR"/bin/spark-submit "${SUBMISSION_OPTS[@]}" "$primary" "${APPLICATION_OPTS[@]}"
 else
-  # PySpark shell requires special handling downstream
-  export PYSPARK_SHELL=1
   exec "$PYSPARK_DRIVER_PYTHON" $PYSPARK_DRIVER_PYTHON_OPTS
 fi

bin/pyspark2.cmd

@@ -59,7 +59,6 @@ for /f %%i in ('echo %1^| findstr /R "\.py"') do (
 )
 
 if [%PYTHON_FILE%] == [] (
-  set PYSPARK_SHELL=1
   if [%IPYTHON%] == [1] (
 	ipython %IPYTHON_OPTS%
   ) else (