From 4f4a9884d9268ba9808744b3d612ac23c75f105a Mon Sep 17 00:00:00 2001
From: Kousuke Saruta <sarutak@oss.nttdata.co.jp>
Date: Sat, 9 Aug 2014 21:10:43 -0700
Subject: [SPARK-2894] spark-shell doesn't accept flags

As sryza reported, spark-shell doesn't accept any flags.
The root cause is wrong usage of spark-submit in spark-shell and it come to the surface by #1801

Author: Kousuke Saruta <sarutak@oss.nttdata.co.jp>
Author: Cheng Lian <lian.cs.zju@gmail.com>

Closes #1715, Closes #1864, and Closes #1861

Closes #1825 from sarutak/SPARK-2894 and squashes the following commits:

47f3510 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into SPARK-2894
2c899ed [Kousuke Saruta] Removed useless code from java_gateway.py
98287ed [Kousuke Saruta] Removed useless code from java_gateway.py
513ad2e [Kousuke Saruta] Modified util.sh to enable to use option including white spaces
28a374e [Kousuke Saruta] Modified java_gateway.py to recognize arguments
5afc584 [Cheng Lian] Filter out spark-submit options when starting Python gateway
e630d19 [Cheng Lian] Fixing pyspark and spark-shell CLI options
---
 bin/pyspark | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

(limited to 'bin/pyspark')

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
-- 
cgit v1.2.3