path: root/graphx-shell

#!/usr/bin/env bash

#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements.  See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License.  You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#

#
# Shell script for starting the Spark Shell REPL
# Note that it will set MASTER to spark://${SPARK_MASTER_IP}:${SPARK_MASTER_PORT}
# if those two env vars are set in spark-env.sh but MASTER is not.
# Options:
#    -c <cores>    Set the number of cores for REPL to use
#

# Enter posix mode for bash
set -o posix


# Update the the banner logo
export SPARK_BANNER_TEXT="Welcome to 
        ______                 __   _  __ 
       / ____/________ _____  / /_ | |/ / 
      / / __/ ___/ __ \`/ __ \/ __ \|   / 
     / /_/ / /  / /_/ / /_/ / / / /   |   
     \____/_/   \__,_/ .___/_/ /_/_/|_|   
                    /_/  Alpha Release               

Powered by: 
       ____              __
      / __/__  ___ _____/ /__
     _\ \/ _ \/ _ \`/ __/  '_/
    /___/ .__/\_,_/_/ /_/\_\   
       /_/ version 0.9.0

Example:

 scala> val graph = GraphLoader.textFile(sc, \"hdfs://links\")
 scala> graph.numVertices
 scala> graph.numEdges
 scala> val pageRankGraph = Analytics.pagerank(graph, 10) // 10 iterations
 scala> val maxPr = pageRankGraph.vertices.map{ case (vid, pr) => pr }.max
 scala> println(maxPr)

"

export SPARK_SHELL_INIT_BLOCK="import org.apache.spark.graph._;"

# Set the serializer to use Kryo for graphx objects
SPARK_JAVA_OPTS+=" -Dspark.serializer=org.apache.spark.serializer.KryoSerializer "
SPARK_JAVA_OPTS+="-Dspark.kryo.registrator=org.apache.spark.graph.GraphKryoRegistrator  "
SPARK_JAVA_OPTS+="-Dspark.kryoserializer.buffer.mb=10 "



FWDIR="`dirname $0`"

for o in "$@"; do
  if [ "$1" = "-c" -o "$1" = "--cores" ]; then
    shift
    if [ -n "$1" ]; then
      OPTIONS="-Dspark.cores.max=$1"
      shift
    fi
  fi
done

# Set MASTER from spark-env if possible
if [ -z "$MASTER" ]; then
  if [ -e "$FWDIR/conf/spark-env.sh" ]; then
    . "$FWDIR/conf/spark-env.sh"
  fi
  if [[ "x" != "x$SPARK_MASTER_IP" && "y" != "y$SPARK_MASTER_PORT" ]]; then
    MASTER="spark://${SPARK_MASTER_IP}:${SPARK_MASTER_PORT}"
    export MASTER
  fi
fi

# Copy restore-TTY-on-exit functions from Scala script so spark-shell exits properly even in
# binary distribution of Spark where Scala is not installed
exit_status=127
saved_stty=""

# restore stty settings (echo in particular)
function restoreSttySettings() {
  stty $saved_stty
  saved_stty=""
}

function onExit() {
  if [[ "$saved_stty" != "" ]]; then
    restoreSttySettings
  fi
  exit $exit_status
}

# to reenable echo if we are interrupted before completing.
trap onExit INT

# save terminal settings
saved_stty=$(stty -g 2>/dev/null)
# clear on error so we don't later try to restore them
if [[ ! $? ]]; then
  saved_stty=""
fi

$FWDIR/spark-class $OPTIONS org.apache.spark.repl.Main "$@"

# record the exit status lest it be overwritten:
# then reenable echo and propagate the code.
exit_status=$?
onExit