spark源码阅读-脚本篇

# The launcher library will print arguments separated by a NULL character, to allow arguments with
# characters that would be otherwise interpreted by the shell. Read that in a while loop, populating
# an array that will be used to exec the final command.
CMD=()
while IFS= read -d ‘‘ -r ARG; do
   CMD+=("$ARG")
 done < <("$RUNNER" -cp "$LAUNCH_CLASSPATH" org.apache.spark.launcher.Main "$@")

exec "${CMD[@]}"

#!/usr/bin/env bash

# Shell script for starting the Spark Shell REPL

#验证是否是cygwin
cygwin=false
case "`uname`" in
  CYGWIN*) cygwin=true;;
esac

# 开启posix模式
set -o posix

#获取父级目录的绝对路径，$0为当前脚本名
export FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
export _SPARK_CMD_USAGE="Usage: ./bin/spark-shell [options]"

#手动添加 -Dscala.usejavacp=true，scala 默认不会使用 java classpath
SPARK_SUBMIT_OPTS="$SPARK_SUBMIT_OPTS -Dscala.usejavacp=true"

#脚本入口，实际调用的是spark-submit脚本
function main() {
  if $cygwin; then
    
    stty -icanon min 1 -echo > /dev/null 2>&1
    export SPARK_SUBMIT_OPTS="$SPARK_SUBMIT_OPTS -Djline.terminal=unix"
    "$FWDIR"/bin/spark-submit --class org.apache.spark.repl.Main --name "Spark shell" "$@"
    stty icanon echo > /dev/null 2>&1
  else
    export SPARK_SUBMIT_OPTS
    "$FWDIR"/bin/spark-submit --class org.apache.spark.repl.Main --name "Spark shell" "$@"
  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
}

# 中断时进行的操作
trap onExit INT

# 保存终止设置
saved_stty=$(stty -g 2>/dev/null)
# clear on error so we don‘t later try to restore them
if [[ ! $? ]]; then
  saved_stty=""
fi

#调用main函数
main "$@"

# 记录脚本退出状态
# then reenable echo and propagate the code.
exit_status=$?
onExit

export FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
export _SPARK_CMD_USAGE="Usage: ./bin/spark-sql [options] [cli option]"
exec "$FWDIR"/bin/spark-submit --class org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver "$@"

SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"

# disable randomized hash for string in Python 3.3+
export PYTHONHASHSEED=0

exec "$SPARK_HOME"/bin/spark-class org.apache.spark.deploy.SparkSubmit "$@"

export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
source "$SPARK_HOME"/bin/load-spark-env.sh
export _SPARK_CMD_USAGE="Usage: ./bin/sparkR [options]"
exec "$SPARK_HOME"/bin/spark-submit sparkr-shell-main "$@"