aboutsummaryrefslogtreecommitdiff
path: root/bin/pyspark
diff options
context:
space:
mode:
Diffstat (limited to 'bin/pyspark')
-rwxr-xr-xbin/pyspark18
1 files changed, 14 insertions, 4 deletions
diff --git a/bin/pyspark b/bin/pyspark
index 39a20e2a24..01d42025c9 100755
--- a/bin/pyspark
+++ b/bin/pyspark
@@ -23,12 +23,18 @@ FWDIR="$(cd `dirname $0`/..; pwd)"
# Export this as SPARK_HOME
export SPARK_HOME="$FWDIR"
+source $FWDIR/bin/utils.sh
+
SCALA_VERSION=2.10
-if [[ "$@" = *--help ]] || [[ "$@" = *-h ]]; then
+function usage() {
echo "Usage: ./bin/pyspark [options]" 1>&2
$FWDIR/bin/spark-submit --help 2>&1 | grep -v Usage 1>&2
exit 0
+}
+
+if [[ "$@" = *--help ]] || [[ "$@" = *-h ]]; then
+ usage
fi
# Exit if the user hasn't compiled Spark
@@ -66,10 +72,11 @@ fi
# Build up arguments list manually to preserve quotes and backslashes.
# We export Spark submit arguments as an environment variable because shell.py must run as a
# PYTHONSTARTUP script, which does not take in arguments. This is required for IPython notebooks.
-
+SUBMIT_USAGE_FUNCTION=usage
+gatherSparkSubmitOpts "$@"
PYSPARK_SUBMIT_ARGS=""
whitespace="[[:space:]]"
-for i in "$@"; do
+for i in "${SUBMISSION_OPTS[@]}"; do
if [[ $i =~ \" ]]; then i=$(echo $i | sed 's/\"/\\\"/g'); fi
if [[ $i =~ $whitespace ]]; then i=\"$i\"; fi
PYSPARK_SUBMIT_ARGS="$PYSPARK_SUBMIT_ARGS $i"
@@ -90,7 +97,10 @@ 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
- exec $FWDIR/bin/spark-submit "$@"
+ primary=$1
+ shift
+ gatherSparkSubmitOpts "$@"
+ exec $FWDIR/bin/spark-submit "${SUBMISSION_OPTS[@]}" $primary "${APPLICATION_OPTS[@]}"
else
# Only use ipython if no command line arguments were provided [SPARK-1134]
if [[ "$IPYTHON" = "1" ]]; then