Merge branch 'master' into yarn-tests

README.md

@@ -4,8 +4,8 @@ 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.
+data processing, MLlib for machine learning, GraphX for graph processing,
+and Spark Streaming for stream processing.
 
 <http://spark.apache.org/>
 

assembly/pom.xml

@@ -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>
 

bagel/pom.xml

@@ -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>
 

bin/beeline

@@ -24,7 +24,7 @@
 set -o posix
 
 # Figure out where Spark is installed
-FWDIR="$(cd `dirname $0`/..; pwd)"
+FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
 
 CLASS="org.apache.hive.beeline.BeeLine"
 exec "$FWDIR/bin/spark-class" $CLASS "$@"

bin/compute-classpath.sh

@@ -23,9 +23,9 @@
 SCALA_VERSION=2.10
 
 # Figure out where Spark is installed
-FWDIR="$(cd `dirname $0`/..; pwd)"
+FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
 
-. $FWDIR/bin/load-spark-env.sh
+. "$FWDIR"/bin/load-spark-env.sh
 
 # Build up classpath
 CLASSPATH="$SPARK_CLASSPATH:$SPARK_SUBMIT_CLASSPATH:$FWDIR/conf"
@@ -63,7 +63,7 @@ else
   assembly_folder="$ASSEMBLY_DIR"
 fi
 
-num_jars=$(ls "$assembly_folder" | grep "spark-assembly.*hadoop.*\.jar" | wc -l)
+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 $assembly_folder"
   echo "You need to build Spark before running this program."
@@ -77,7 +77,7 @@ if [ "$num_jars" -gt "1" ]; then
   exit 1
 fi
 
-ASSEMBLY_JAR=$(ls "$assembly_folder"/spark-assembly*hadoop*.jar 2>/dev/null)
+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 "$ASSEMBLY_JAR" nonexistent/class/path 2>&1)
@@ -103,8 +103,8 @@ else
   datanucleus_dir="$FWDIR"/lib_managed/jars
 fi
 
-datanucleus_jars=$(find "$datanucleus_dir" 2>/dev/null | grep "datanucleus-.*\\.jar")
-datanucleus_jars=$(echo "$datanucleus_jars" | tr "\n" : | sed s/:$//g)
+datanucleus_jars="$(find "$datanucleus_dir" 2>/dev/null | grep "datanucleus-.*\\.jar")"
+datanucleus_jars="$(echo "$datanucleus_jars" | tr "\n" : | sed s/:$//g)"
 
 if [ -n "$datanucleus_jars" ]; then
   hive_files=$("$JAR_CMD" -tf "$ASSEMBLY_JAR" org/apache/hadoop/hive/ql/exec 2>/dev/null)

bin/load-spark-env.sh

@@ -25,9 +25,9 @@ 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 $0`/..; pwd)"
+  parent_dir="$(cd "`dirname "$0"`"/..; pwd)"
 
-  user_conf_dir=${SPARK_CONF_DIR:-"$parent_dir/conf"}
+  user_conf_dir="${SPARK_CONF_DIR:-"$parent_dir"/conf}"
 
   if [ -f "${user_conf_dir}/spark-env.sh" ]; then
     # Promote all variable declarations to environment (exported) variables

bin/pyspark

@@ -18,18 +18,18 @@
 #
 
 # Figure out where Spark is installed
-FWDIR="$(cd `dirname $0`/..; pwd)"
+FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
 
 # Export this as SPARK_HOME
 export SPARK_HOME="$FWDIR"
 
-source $FWDIR/bin/utils.sh
+source "$FWDIR/bin/utils.sh"
 
 SCALA_VERSION=2.10
 
 function usage() {
   echo "Usage: ./bin/pyspark [options]" 1>&2
-  $FWDIR/bin/spark-submit --help 2>&1 | grep -v Usage 1>&2
+  "$FWDIR"/bin/spark-submit --help 2>&1 | grep -v Usage 1>&2
   exit 0
 }
 
@@ -48,7 +48,7 @@ if [ ! -f "$FWDIR/RELEASE" ]; then
   fi
 fi
 
-. $FWDIR/bin/load-spark-env.sh
+. "$FWDIR"/bin/load-spark-env.sh
 
 # Figure out which Python executable to use
 if [[ -z "$PYSPARK_PYTHON" ]]; then
@@ -57,12 +57,12 @@ fi
 export PYSPARK_PYTHON
 
 # Add the PySpark classes to the Python path:
-export PYTHONPATH=$SPARK_HOME/python/:$PYTHONPATH
-export PYTHONPATH=$SPARK_HOME/python/lib/py4j-0.8.2.1-src.zip:$PYTHONPATH
+export PYTHONPATH="$SPARK_HOME/python/:$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=$PYTHONSTARTUP
-export PYTHONSTARTUP=$FWDIR/python/pyspark/shell.py
+export OLD_PYTHONSTARTUP="$PYTHONSTARTUP"
+export PYTHONSTARTUP="$FWDIR/python/pyspark/shell.py"
 
 # If IPython options are specified, assume user wants to run IPython
 if [[ -n "$IPYTHON_OPTS" ]]; then
@@ -85,6 +85,8 @@ export PYSPARK_SUBMIT_ARGS
 
 # For pyspark tests
 if [[ -n "$SPARK_TESTING" ]]; then
+  unset YARN_CONF_DIR
+  unset HADOOP_CONF_DIR
   if [[ -n "$PYSPARK_DOC_TEST" ]]; then
     exec "$PYSPARK_PYTHON" -m doctest $1
   else
@@ -97,10 +99,10 @@ fi
 if [[ "$1" =~ \.py$ ]]; then
   echo -e "\nWARNING: Running python applications through ./bin/pyspark is deprecated as of Spark 1.0." 1>&2
   echo -e "Use ./bin/spark-submit <python file>\n" 1>&2
-  primary=$1
+  primary="$1"
   shift
   gatherSparkSubmitOpts "$@"
-  exec $FWDIR/bin/spark-submit "${SUBMISSION_OPTS[@]}" $primary "${APPLICATION_OPTS[@]}"
+  exec "$FWDIR"/bin/spark-submit "${SUBMISSION_OPTS[@]}" "$primary" "${APPLICATION_OPTS[@]}"
 else
   # PySpark shell requires special handling downstream
   export PYSPARK_SHELL=1

bin/run-example

@@ -19,7 +19,7 @@
 
 SCALA_VERSION=2.10
 
-FWDIR="$(cd `dirname $0`/..; pwd)"
+FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
 export SPARK_HOME="$FWDIR"
 EXAMPLES_DIR="$FWDIR"/examples
 
@@ -35,12 +35,12 @@ else
 fi
 
 if [ -f "$FWDIR/RELEASE" ]; then
-  export SPARK_EXAMPLES_JAR=`ls "$FWDIR"/lib/spark-examples-*hadoop*.jar`
+  export SPARK_EXAMPLES_JAR="`ls "$FWDIR"/lib/spark-examples-*hadoop*.jar`"
 elif [ -e "$EXAMPLES_DIR"/target/scala-$SCALA_VERSION/spark-examples-*hadoop*.jar ]; then
-  export SPARK_EXAMPLES_JAR=`ls "$EXAMPLES_DIR"/target/scala-$SCALA_VERSION/spark-examples-*hadoop*.jar`
+  export SPARK_EXAMPLES_JAR="`ls "$EXAMPLES_DIR"/target/scala-$SCALA_VERSION/spark-examples-*hadoop*.jar`"
 fi
 
-if [[ -z $SPARK_EXAMPLES_JAR ]]; then
+if [[ -z "$SPARK_EXAMPLES_JAR" ]]; then
   echo "Failed to find Spark examples assembly in $FWDIR/lib or $FWDIR/examples/target" 1>&2
   echo "You need to build Spark before running this program" 1>&2
   exit 1

bin/spark-class

@@ -27,12 +27,12 @@ esac
 SCALA_VERSION=2.10
 
 # Figure out where Spark is installed
-FWDIR="$(cd `dirname $0`/..; pwd)"
+FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
 
 # Export this as SPARK_HOME
 export SPARK_HOME="$FWDIR"
 
-. $FWDIR/bin/load-spark-env.sh
+. "$FWDIR"/bin/load-spark-env.sh
 
 if [ -z "$1" ]; then
   echo "Usage: spark-class <class> [<args>]" 1>&2
@@ -105,7 +105,7 @@ else
     exit 1
   fi
 fi
-JAVA_VERSION=$($RUNNER -version 2>&1 | sed 's/java version "\(.*\)\.\(.*\)\..*"/\1\2/; 1q')
+JAVA_VERSION=$("$RUNNER" -version 2>&1 | sed 's/java version "\(.*\)\.\(.*\)\..*"/\1\2/; 1q')
 
 # Set JAVA_OPTS to be able to load native libraries and to set heap size
 if [ "$JAVA_VERSION" -ge 18 ]; then
@@ -117,7 +117,7 @@ JAVA_OPTS="$JAVA_OPTS -Xms$OUR_JAVA_MEM -Xmx$OUR_JAVA_MEM"
 
 # Load extra JAVA_OPTS from conf/java-opts, if it exists
 if [ -e "$FWDIR/conf/java-opts" ] ; then
-  JAVA_OPTS="$JAVA_OPTS `cat $FWDIR/conf/java-opts`"
+  JAVA_OPTS="$JAVA_OPTS `cat "$FWDIR"/conf/java-opts`"
 fi
 
 # Attention: when changing the way the JAVA_OPTS are assembled, the change must be reflected in CommandUtils.scala!
@@ -126,21 +126,21 @@ TOOLS_DIR="$FWDIR"/tools
 SPARK_TOOLS_JAR=""
 if [ -e "$TOOLS_DIR"/target/scala-$SCALA_VERSION/spark-tools*[0-9Tg].jar ]; then
   # Use the JAR from the SBT build
-  export SPARK_TOOLS_JAR=`ls "$TOOLS_DIR"/target/scala-$SCALA_VERSION/spark-tools*[0-9Tg].jar`
+  export SPARK_TOOLS_JAR="`ls "$TOOLS_DIR"/target/scala-$SCALA_VERSION/spark-tools*[0-9Tg].jar`"
 fi
 if [ -e "$TOOLS_DIR"/target/spark-tools*[0-9Tg].jar ]; then
   # Use the JAR from the Maven build
   # TODO: this also needs to become an assembly!
-  export SPARK_TOOLS_JAR=`ls "$TOOLS_DIR"/target/spark-tools*[0-9Tg].jar`
+  export SPARK_TOOLS_JAR="`ls "$TOOLS_DIR"/target/spark-tools*[0-9Tg].jar`"
 fi
 
 # Compute classpath using external script
-classpath_output=$($FWDIR/bin/compute-classpath.sh)
+classpath_output=$("$FWDIR"/bin/compute-classpath.sh)
 if [[ "$?" != "0" ]]; then
   echo "$classpath_output"
   exit 1
 else
-  CLASSPATH=$classpath_output
+  CLASSPATH="$classpath_output"
 fi
 
 if [[ "$1" =~ org.apache.spark.tools.* ]]; then
@@ -153,9 +153,9 @@ if [[ "$1" =~ org.apache.spark.tools.* ]]; then
 fi
 
 if $cygwin; then
-  CLASSPATH=`cygpath -wp $CLASSPATH`
+  CLASSPATH="`cygpath -wp "$CLASSPATH"`"
   if [ "$1" == "org.apache.spark.tools.JavaAPICompletenessChecker" ]; then
-    export SPARK_TOOLS_JAR=`cygpath -w $SPARK_TOOLS_JAR`
+    export SPARK_TOOLS_JAR="`cygpath -w "$SPARK_TOOLS_JAR"`"
   fi
 fi
 export CLASSPATH

bin/spark-shell

@@ -29,19 +29,19 @@ esac
 set -o posix
 
 ## Global script variables
-FWDIR="$(cd `dirname $0`/..; pwd)"
+FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
 
 function usage() {
   echo "Usage: ./bin/spark-shell [options]"
-  $FWDIR/bin/spark-submit --help 2>&1 | grep -v Usage 1>&2
+  "$FWDIR"/bin/spark-submit --help 2>&1 | grep -v Usage 1>&2
   exit 0
 }
 
 if [[ "$@" = *--help ]] || [[ "$@" = *-h ]]; then
   usage
 fi
 
-source $FWDIR/bin/utils.sh
+source "$FWDIR"/bin/utils.sh
 SUBMIT_USAGE_FUNCTION=usage
 gatherSparkSubmitOpts "$@"
 
@@ -54,11 +54,11 @@ 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"
-    $FWDIR/bin/spark-submit --class org.apache.spark.repl.Main "${SUBMISSION_OPTS[@]}" spark-shell "${APPLICATION_OPTS[@]}"
+    "$FWDIR"/bin/spark-submit --class org.apache.spark.repl.Main "${SUBMISSION_OPTS[@]}" spark-shell "${APPLICATION_OPTS[@]}"
     stty icanon echo > /dev/null 2>&1
   else
     export SPARK_SUBMIT_OPTS
-    $FWDIR/bin/spark-submit --class org.apache.spark.repl.Main "${SUBMISSION_OPTS[@]}" spark-shell "${APPLICATION_OPTS[@]}"
+    "$FWDIR"/bin/spark-submit --class org.apache.spark.repl.Main "${SUBMISSION_OPTS[@]}" spark-shell "${APPLICATION_OPTS[@]}"
   fi
 }
 

bin/spark-sql

@@ -27,7 +27,7 @@ CLASS="org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver"
 CLASS_NOT_FOUND_EXIT_STATUS=1
 
 # Figure out where Spark is installed
-FWDIR="$(cd `dirname $0`/..; pwd)"
+FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
 
 function usage {
   echo "Usage: ./bin/spark-sql [options] [cli option]"
@@ -38,18 +38,18 @@ function usage {
   pattern+="\|--help"
   pattern+="\|======="
 
-  $FWDIR/bin/spark-submit --help 2>&1 | grep -v Usage 1>&2
+  "$FWDIR"/bin/spark-submit --help 2>&1 | grep -v Usage 1>&2
   echo
   echo "CLI options:"
-  $FWDIR/bin/spark-class $CLASS --help 2>&1 | grep -v "$pattern" 1>&2
+  "$FWDIR"/bin/spark-class $CLASS --help 2>&1 | grep -v "$pattern" 1>&2
 }
 
 if [[ "$@" = *--help ]] || [[ "$@" = *-h ]]; then
   usage
   exit 0
 fi
 
-source $FWDIR/bin/utils.sh
+source "$FWDIR"/bin/utils.sh
 SUBMIT_USAGE_FUNCTION=usage
 gatherSparkSubmitOpts "$@"
 

bin/spark-submit

@@ -19,7 +19,7 @@
 
 # NOTE: Any changes in this file must be reflected in SparkSubmitDriverBootstrapper.scala!
 
-export SPARK_HOME="$(cd `dirname $0`/..; pwd)"
+export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
 ORIG_ARGS=("$@")
 
 while (($#)); do
@@ -59,5 +59,5 @@ if [[ "$SPARK_SUBMIT_DEPLOY_MODE" == "client" && -f "$SPARK_SUBMIT_PROPERTIES_FI
   fi
 fi
 
-exec $SPARK_HOME/bin/spark-class org.apache.spark.deploy.SparkSubmit "${ORIG_ARGS[@]}"
+exec "$SPARK_HOME"/bin/spark-class org.apache.spark.deploy.SparkSubmit "${ORIG_ARGS[@]}"
 

core/pom.xml

@@ -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>
 

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

@@ -49,6 +49,7 @@ import org.apache.spark.scheduler.cluster.{CoarseGrainedSchedulerBackend, SparkD
 import org.apache.spark.scheduler.cluster.mesos.{CoarseMesosSchedulerBackend, MesosSchedulerBackend}
 import org.apache.spark.scheduler.local.LocalBackend
 import org.apache.spark.storage._
+import org.apache.spark.SPARK_VERSION
 import org.apache.spark.ui.SparkUI
 import org.apache.spark.util.{CallSite, ClosureCleaner, MetadataCleaner, MetadataCleanerType, TimeStampedWeakValueHashMap, Utils}
 
@@ -825,7 +826,7 @@ class SparkContext(config: SparkConf) extends Logging {
   }
 
   /** The version of Spark on which this application is running. */
-  def version = SparkContext.SPARK_VERSION
+  def version = SPARK_VERSION
 
   /**
    * Return a map from the slave to the max memory available for caching and the remaining
@@ -1297,8 +1298,6 @@ class SparkContext(config: SparkConf) extends Logging {
  */
 object SparkContext extends Logging {
 
-  private[spark] val SPARK_VERSION = "1.0.0"
-
   private[spark] val SPARK_JOB_DESCRIPTION = "spark.job.description"
 
   private[spark] val SPARK_JOB_GROUP_ID = "spark.jobGroup.id"