carbon-spark-sql

#!/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 carbondata sql CLI

# Enter posix mode for bash
set -o posix
export CLASS="org.apache.spark.sql.hive.cli.CarbonSQLCLIDriver"

# Figure out where Spark is installed
if [ -z "$SPARK_HOME" ]
then
echo "\$SPARK_HOME is not set"
fi

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

ASSEMBLY_DIR="$CARBON_SOURCE/assembly/target/scala-2.10"
if [ -d "$CARBON_SOURCE/assembly/target/scala-2.11" ]; then
  ASSEMBLY_DIR="$CARBON_SOURCE/assembly/target/scala-2.11"
fi

GREP_OPTIONS=
num_jars="$(ls -1 "$ASSEMBLY_DIR" | grep "^carbondata.*hadoop.*\.jar$" | wc -l)"
if [ "$num_jars" -eq "0" -a -z "$ASSEMBLY_DIR" ]; then
  echo "Failed to find Carbondata assembly in $ASSEMBLY_DIR." 1>&2
  echo "You need to build Carbondata before running this program." 1>&2
  exit 1
fi
ASSEMBLY_JARS="$(ls -1 "$ASSEMBLY_DIR" | grep "^carbondata.*hadoop.*\.jar$" || true)"
if [ "$num_jars" -gt "1" ]; then
  echo "Found multiple Carbondata assembly jars in $ASSEMBLY_DIR:" 1>&2
  echo "$ASSEMBLY_JARS" 1>&2
  echo "Please remove all but one jar." 1>&2
  exit 1
fi

ASSEMBLY_JAR="${ASSEMBLY_DIR}/${ASSEMBLY_JARS}"
export JAR="$ASSEMBLY_JAR"
export CARBON_HOME=$CARBON_SOURCE

function usage {
  if [ -n "$1" ]; then
    echo "$1"
  fi
  echo "Usage: ./bin/carbon-spark-sql [options] [cli option]"
  pattern="usage"
  pattern+="\|Spark assembly has been built"
  pattern+="\|NOTE: SPARK_PREPEND_CLASSES is set"
  pattern+="\|Spark Command: "
  pattern+="\|--help"
  pattern+="\|======="

  "$FWDIR"/bin/spark-sql --help 2>&1 | grep -v Usage 1>&2
  exit "$2"
}
export -f usage

if [[ "$@" = *--help ]] || [[ "$@" = *-h ]]; then
  usage "" 0
fi

#split options and cli_options, final submit example is spark-submit options --class xxx xxx.jar cli_options
options=""
while true ; do
    case "$1" in
        -d|--define|-f|-i|--hiveconf|--hivevar|--database|-e|-S|--silent) cmd="$1"; break;;
        -v|--verbose) options="$options $1" ; shift  ;;
        -*) options="$options $1 $2" ; shift 2 ;;
        *) break ;;
    esac
done

echo "$FWDIR"/bin/spark-submit $options --class "$CLASS" "$JAR" "$@"
exec "$FWDIR"/bin/spark-submit $options --class "$CLASS" "$JAR" "$@"