diff options
Diffstat (limited to 'bin/pyspark')
-rwxr-xr-x | bin/pyspark | 59 |
1 files changed, 13 insertions, 46 deletions
diff --git a/bin/pyspark b/bin/pyspark index 0b4f695dd0..e7f6a1a072 100755 --- a/bin/pyspark +++ b/bin/pyspark @@ -18,36 +18,24 @@ # # Figure out where Spark is installed -FWDIR="$(cd "`dirname "$0"`"/..; pwd)" +export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)" -# Export this as SPARK_HOME -export SPARK_HOME="$FWDIR" - -source "$FWDIR/bin/utils.sh" - -source "$FWDIR"/bin/load-spark-env.sh +source "$SPARK_HOME"/bin/load-spark-env.sh function usage() { + if [ -n "$1" ]; then + echo $1 + fi echo "Usage: ./bin/pyspark [options]" 1>&2 - "$FWDIR"/bin/spark-submit --help 2>&1 | grep -v Usage 1>&2 - exit 0 + "$SPARK_HOME"/bin/spark-submit --help 2>&1 | grep -v Usage 1>&2 + exit $2 } +export -f usage if [[ "$@" = *--help ]] || [[ "$@" = *-h ]]; then usage fi -# Exit if the user hasn't compiled Spark -if [ ! -f "$FWDIR/RELEASE" ]; then - # Exit if the user hasn't compiled Spark - ls "$FWDIR"/assembly/target/scala-$SPARK_SCALA_VERSION/spark-assembly*hadoop*.jar >& /dev/null - if [[ $? != 0 ]]; then - echo "Failed to find Spark assembly in $FWDIR/assembly/target" 1>&2 - echo "You need to build Spark before running this program" 1>&2 - exit 1 - fi -fi - # In Spark <= 1.1, setting IPYTHON=1 would cause the driver to be launched using the `ipython` # executable, while the worker would still be launched using PYSPARK_PYTHON. # @@ -95,26 +83,13 @@ export PYTHONPATH="$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="$FWDIR/python/pyspark/shell.py" - -# Build up arguments list manually to preserve quotes and backslashes. -# We export Spark submit arguments as an environment variable because shell.py must run as a -# PYTHONSTARTUP script, which does not take in arguments. This is required for IPython notebooks. -SUBMIT_USAGE_FUNCTION=usage -gatherSparkSubmitOpts "$@" -PYSPARK_SUBMIT_ARGS="" -whitespace="[[:space:]]" -for i in "${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 $i" -done -export PYSPARK_SUBMIT_ARGS +export PYTHONSTARTUP="$SPARK_HOME/python/pyspark/shell.py" # For pyspark tests if [[ -n "$SPARK_TESTING" ]]; then unset YARN_CONF_DIR unset HADOOP_CONF_DIR + export PYSPARK_SUBMIT_ARGS=pyspark-shell if [[ -n "$PYSPARK_DOC_TEST" ]]; then exec "$PYSPARK_DRIVER_PYTHON" -m doctest $1 else @@ -123,14 +98,6 @@ if [[ -n "$SPARK_TESTING" ]]; then exit fi -# If a python file is provided, directly run spark-submit. -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="$1" - shift - gatherSparkSubmitOpts "$@" - exec "$FWDIR"/bin/spark-submit "${SUBMISSION_OPTS[@]}" "$primary" "${APPLICATION_OPTS[@]}" -else - exec "$PYSPARK_DRIVER_PYTHON" $PYSPARK_DRIVER_PYTHON_OPTS -fi +export PYSPARK_DRIVER_PYTHON +export PYSPARK_DRIVER_PYTHON_OPTS +exec "$SPARK_HOME"/bin/spark-submit pyspark-shell-main "$@" |