Simplify PySpark installation.

- Bundle Py4J binaries, since it's hard to install
- Uses Spark's `run` script to launch the Py4J
  gateway, inheriting the settings in spark-env.sh

With these changes, (hopefully) nothing more than
running `sbt/sbt package` will be necessary to run
PySpark.

1 files changed, 4 insertions, 0 deletions

diff --git a/run b/run
index 15db23bbe0..8fa61b086f 100755
--- a/run
+++ b/run
@@ -40,6 +40,7 @@ CORE_DIR="$FWDIR/core"
 REPL_DIR="$FWDIR/repl"
 EXAMPLES_DIR="$FWDIR/examples"
 BAGEL_DIR="$FWDIR/bagel"
+PYSPARK_DIR="$FWDIR/pyspark"
 
 # Build up classpath
 CLASSPATH="$SPARK_CLASSPATH"
@@ -61,6 +62,9 @@ for jar in `find $REPL_DIR/lib -name '*jar'`; do
   CLASSPATH+=":$jar"
 done
 CLASSPATH+=":$BAGEL_DIR/target/scala-$SCALA_VERSION/classes"
+for jar in `find $PYSPARK_DIR/lib -name '*jar'`; do
+  CLASSPATH+=":$jar"
+done
 export CLASSPATH # Needed for spark-shell
 
 # Figure out whether to run our class with java or with the scala launcher.