hive之执行shell脚本注解

2019独角兽企业重金招聘Python工程师标准>>>

#!/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.

#cygwin是一个在windows平台上运行的unix模拟环境,确定是否为虚拟unix环境
cygwin=false
case "`uname`" in
   CYGWIN*) cygwin=true;;
esac

#确定脚本存放的目录
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`

#导入脚本存放目录下的hive-config.sh配置文件
. "$bin"/hive-config.sh

SERVICE=""
HELP=""
#判定参数是否大于0
while [ $# -gt 0 ]; do
  case "$1" in
    --service)
      #弹出第一个参数,即跳过--service
      shift
      SERVICE=$1
      shift
      ;;
    --rcfilecat)
      SERVICE=rcfilecat
      shift
      ;;
    --help)
      HELP=_help
      shift
      ;;
    *)
      break
      ;;
  esac
done

if [ "$SERVICE" = "" ] ; then
  if [ "$HELP" = "_help" ] ; then
    SERVICE="help"
  else
    SERVICE="cli"
  fi
fi

#判断文件是否存在(导入脚本存放目录下的hive-config.sh配置文件中)
if [ -f "${HIVE_CONF_DIR}/hive-env.sh" ]; then
  . "${HIVE_CONF_DIR}/hive-env.sh"
fi

CLASSPATH="${HIVE_CONF_DIR}"

HIVE_LIB=${HIVE_HOME}/lib

# needed for execution
if [ ! -f ${HIVE_LIB}/hive-exec-*.jar ]; then
  echo "Missing Hive Execution Jar: ${HIVE_LIB}/hive-exec-*.jar"
  exit 1;
fi

if [ ! -f ${HIVE_LIB}/hive-metastore-*.jar ]; then
  echo "Missing Hive MetaStore Jar"
  exit 2;
fi

# cli specific code
if [ ! -f ${HIVE_LIB}/hive-cli-*.jar ]; then
  echo "Missing Hive CLI Jar"
  exit 3;
fi

#将jar包添加到环境变量中
for f in ${HIVE_LIB}/*.jar; do
  CLASSPATH=${CLASSPATH}:$f;
done

# add the auxillary jars such as serdes
if [ -d "${HIVE_AUX_JARS_PATH}" ]; then
  for f in ${HIVE_AUX_JARS_PATH}/*.jar; do
    if [[ ! -f $f ]]; then
        continue;
    fi
    if $cygwin; then
 f=`cygpath -w "$f"`
    fi
    AUX_CLASSPATH=${AUX_CLASSPATH}:$f
    if [ "${AUX_PARAM}" == "" ]; then
        AUX_PARAM=file://$f
    else
        AUX_PARAM=${AUX_PARAM},file://$f;
    fi
  done
elif [ "${HIVE_AUX_JARS_PATH}" != "" ]; then
  if $cygwin; then
      HIVE_AUX_JARS_PATH=`echo $HIVE_AUX_JARS_PATH | sed 's/,/:/g'`
      HIVE_AUX_JARS_PATH=`cygpath -p -w "$HIVE_AUX_JARS_PATH"`
      HIVE_AUX_JARS_PATH=`echo $HIVE_AUX_JARS_PATH | sed 's/;/,/g'`
  fi
  AUX_CLASSPATH=${HIVE_AUX_JARS_PATH}
  # AUX_PARAM needs to be a comma separated list of "file" scheme paths
  # Replace colons and semicolons with commas; eliminate repeats
  AUX_PARAM=`echo $AUX_CLASSPATH | awk '{gsub(/[:;,]+/, ",");print}'`
  # Strip leading/trailing commas
  AUX_PARAM=`echo $AUX_PARAM | awk '{gsub(/^,|,$/, "");print}'`
  # Replace commas with file://
  AUX_PARAM=file://`echo $AUX_PARAM | awk '{gsub(/,/, ",file://");print}'`
fi

# adding jars from auxlib directory
for f in ${HIVE_HOME}/auxlib/*.jar; do
  if [[ ! -f $f ]]; then
      continue;
  fi
  if $cygwin; then
      f=`cygpath -w "$f"`
  fi
  AUX_CLASSPATH=${AUX_CLASSPATH}:$f
  if [ "${AUX_PARAM}" == "" ]; then
    AUX_PARAM=file://$f
  else
    AUX_PARAM=${AUX_PARAM},file://$f;
  fi
done
if $cygwin; then
    CLASSPATH=`cygpath -p -w "$CLASSPATH"`
    CLASSPATH=${CLASSPATH};${AUX_CLASSPATH}
else
    CLASSPATH=${CLASSPATH}:${AUX_CLASSPATH}
fi

# pass classpath to hadoop
export HADOOP_CLASSPATH="${HADOOP_CLASSPATH}:${CLASSPATH}"

# check for hadoop in the path
HADOOP_IN_PATH=`which hadoop 2>/dev/null`
if [ -f ${HADOOP_IN_PATH} ]; then
  HADOOP_DIR=`dirname "$HADOOP_IN_PATH"`/..
fi
# HADOOP_HOME env variable overrides hadoop in the path
HADOOP_HOME=${HADOOP_HOME:-$HADOOP_DIR}
if [ "$HADOOP_HOME" == "" ]; then
  echo "Cannot find hadoop installation: \$HADOOP_HOME must be set or hadoop must be in the path";
  exit 4;
fi

HADOOP=$HADOOP_HOME/bin/hadoop
if [ ! -f ${HADOOP} ]; then
  echo "Cannot find hadoop installation: \$HADOOP_HOME must be set or hadoop must be in the path";
  exit 4;
fi

# Make sure we're using a compatible version of Hadoop
hadoop_version=$($HADOOP version | awk '{if (NR == 1) {print $2;}}');

# Save the regex to a var to workaround quoting incompatabilities
# between Bash 3.1 and 3.2
hadoop_version_re="^([[:digit:]]+)\.([[:digit:]]+)(\.([[:digit:]]+))?.*$"

if [[ "$hadoop_version" =~ $hadoop_version_re ]]; then
    hadoop_major_ver=${BASH_REMATCH[1]}
    hadoop_minor_ver=${BASH_REMATCH[2]}
    hadoop_patch_ver=${BASH_REMATCH[4]}
else
    echo "Unable to determine Hadoop version information."
    echo "'hadoop version' returned:"
    echo `$HADOOP version`
    exit 5
fi

if [ $hadoop_minor_ver -ne 20 -o $hadoop_patch_ver -eq 0 ]; then
    echo "Hive requires Hadoop 0.20.x (x >= 1)."
    echo "'hadoop version' returned:"
    echo `$HADOOP version`
    exit 6
fi

if [ "${AUX_PARAM}" != "" ]; then
  HIVE_OPTS="$HIVE_OPTS -hiveconf hive.aux.jars.path=${AUX_PARAM}"
  AUX_JARS_CMD_LINE="-libjars ${AUX_PARAM}"
fi

SERVICE_LIST=""

for i in "$bin"/ext/*.sh ; do
  . $i
done

for i in "$bin"/ext/util/*.sh ; do
  . $i
done

TORUN=""
for j in $SERVICE_LIST ; do
  if [ "$j" = "$SERVICE" ] ; then
    TORUN=${j}$HELP
  fi
done

if [ "$TORUN" = "" ] ; then
  echo "Service $SERVICE not found"
  echo "Available Services: $SERVICE_LIST"
  exit 7
else
  $TORUN "$@"
fi

转载于:https://my.oschina.net/u/230121/blog/133863