Merge branch 'master' into master-merge

Conflicts:
	core/pom.xml
	core/src/main/scala/spark/MapOutputTracker.scala
	core/src/main/scala/spark/RDD.scala
	core/src/main/scala/spark/RDDCheckpointData.scala
	core/src/main/scala/spark/SparkContext.scala
	core/src/main/scala/spark/Utils.scala
	core/src/main/scala/spark/api/python/PythonRDD.scala
	core/src/main/scala/spark/deploy/client/Client.scala
	core/src/main/scala/spark/deploy/master/MasterWebUI.scala
	core/src/main/scala/spark/deploy/worker/Worker.scala
	core/src/main/scala/spark/deploy/worker/WorkerWebUI.scala
	core/src/main/scala/spark/rdd/BlockRDD.scala
	core/src/main/scala/spark/rdd/ZippedRDD.scala
	core/src/main/scala/spark/scheduler/cluster/StandaloneSchedulerBackend.scala
	core/src/main/scala/spark/storage/BlockManager.scala
	core/src/main/scala/spark/storage/BlockManagerMaster.scala
	core/src/main/scala/spark/storage/BlockManagerMasterActor.scala
	core/src/main/scala/spark/storage/BlockManagerUI.scala
	core/src/main/scala/spark/util/AkkaUtils.scala
	core/src/test/scala/spark/SizeEstimatorSuite.scala
	pom.xml
	project/SparkBuild.scala
	repl/src/main/scala/spark/repl/SparkILoop.scala
	repl/src/test/scala/spark/repl/ReplSuite.scala
	streaming/src/main/scala/spark/streaming/StreamingContext.scala
	streaming/src/main/scala/spark/streaming/api/java/JavaStreamingContext.scala
	streaming/src/main/scala/spark/streaming/dstream/KafkaInputDStream.scala
	streaming/src/main/scala/spark/streaming/util/MasterFailureTest.scala

1 files changed, 89 insertions, 0 deletions

diff --git a/bin/compute-classpath.sh b/bin/compute-classpath.sh
new file mode 100755
index 0000000000..3a78880290
--- /dev/null
+++ b/bin/compute-classpath.sh
@@ -0,0 +1,89 @@
+#!/bin/bash
+
+# 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=2.9.3
+
+# 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
+  . $FWDIR/conf/spark-env.sh
+fi
+
+CORE_DIR="$FWDIR/core"
+REPL_DIR="$FWDIR/repl"
+REPL_BIN_DIR="$FWDIR/repl-bin"
+EXAMPLES_DIR="$FWDIR/examples"
+BAGEL_DIR="$FWDIR/bagel"
+STREAMING_DIR="$FWDIR/streaming"
+PYSPARK_DIR="$FWDIR/python"
+
+# Build up classpath
+CLASSPATH="$SPARK_CLASSPATH"
+CLASSPATH="$CLASSPATH:$FWDIR/conf"
+CLASSPATH="$CLASSPATH:$CORE_DIR/target/scala-$SCALA_VERSION/classes"
+if [ -n "$SPARK_TESTING" ] ; then
+  CLASSPATH="$CLASSPATH:$CORE_DIR/target/scala-$SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$STREAMING_DIR/target/scala-$SCALA_VERSION/test-classes"
+fi
+CLASSPATH="$CLASSPATH:$CORE_DIR/src/main/resources"
+CLASSPATH="$CLASSPATH:$REPL_DIR/target/scala-$SCALA_VERSION/classes"
+CLASSPATH="$CLASSPATH:$EXAMPLES_DIR/target/scala-$SCALA_VERSION/classes"
+CLASSPATH="$CLASSPATH:$STREAMING_DIR/target/scala-$SCALA_VERSION/classes"
+CLASSPATH="$CLASSPATH:$STREAMING_DIR/lib/org/apache/kafka/kafka/0.7.2-spark/*" # <-- our in-project Kafka Jar
+if [ -e "$FWDIR/lib_managed" ]; then
+  CLASSPATH="$CLASSPATH:$FWDIR/lib_managed/jars/*"
+  CLASSPATH="$CLASSPATH:$FWDIR/lib_managed/bundles/*"
+fi
+CLASSPATH="$CLASSPATH:$REPL_DIR/lib/*"
+# Add the shaded JAR for Maven builds
+if [ -e $REPL_BIN_DIR/target ]; then
+  for jar in `find "$REPL_BIN_DIR/target" -name 'spark-repl-*-shaded-hadoop*.jar'`; do
+    CLASSPATH="$CLASSPATH:$jar"
+  done
+  # The shaded JAR doesn't contain examples, so include those separately
+  EXAMPLES_JAR=`ls "$EXAMPLES_DIR/target/spark-examples"*[0-9T].jar`
+  CLASSPATH+=":$EXAMPLES_JAR"
+fi
+CLASSPATH="$CLASSPATH:$BAGEL_DIR/target/scala-$SCALA_VERSION/classes"
+for jar in `find $PYSPARK_DIR/lib -name '*jar'`; do
+  CLASSPATH="$CLASSPATH:$jar"
+done
+
+# Figure out the JAR file that our examples were packaged into. This includes a bit of a hack
+# to avoid the -sources and -doc packages that are built by publish-local.
+if [ -e "$EXAMPLES_DIR/target/scala-$SCALA_VERSION/spark-examples"*[0-9T].jar ]; then
+  # Use the JAR from the SBT build
+  export SPARK_EXAMPLES_JAR=`ls "$EXAMPLES_DIR/target/scala-$SCALA_VERSION/spark-examples"*[0-9T].jar`
+fi
+if [ -e "$EXAMPLES_DIR/target/spark-examples"*[0-9T].jar ]; then
+  # Use the JAR from the Maven build
+  export SPARK_EXAMPLES_JAR=`ls "$EXAMPLES_DIR/target/spark-examples"*[0-9T].jar`
+fi
+
+# Add hadoop conf dir - else FileSystem.*, etc fail !
+# Note, this assumes that there is either a HADOOP_CONF_DIR or YARN_CONF_DIR which hosts
+# the configurtion files.
+if [ "x" != "x$HADOOP_CONF_DIR" ]; then
+  CLASSPATH="$CLASSPATH:$HADOOP_CONF_DIR"
+fi
+if [ "x" != "x$YARN_CONF_DIR" ]; then
+  CLASSPATH="$CLASSPATH:$YARN_CONF_DIR"
+fi
+
+# Add Scala standard library
+if [ -z "$SCALA_LIBRARY_PATH" ]; then
+  if [ -z "$SCALA_HOME" ]; then
+    echo "SCALA_HOME is not set" >&2
+    exit 1
+  fi
+  SCALA_LIBRARY_PATH="$SCALA_HOME/lib"
+fi
+CLASSPATH="$CLASSPATH:$SCALA_LIBRARY_PATH/scala-library.jar"
+CLASSPATH="$CLASSPATH:$SCALA_LIBRARY_PATH/scala-compiler.jar"
+CLASSPATH="$CLASSPATH:$SCALA_LIBRARY_PATH/jline.jar"
+
+echo "$CLASSPATH"