hadoop-common-project/hadoop-common/src/main/conf/hadoop-user-functions.sh.example

#
# 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.

#######
# Advanced Users Only
######

# You can do things like replace parts of the shell underbelly.
# Most of this code is in hadoop-functions.sh.
#
#
# For example, if you want to add compression to the rotation
# menthod for the .out files that daemons generate, you can do
# that by redefining the hadoop_rotate_log function by
# uncommenting this code block:

#function hadoop_rotate_log
#{
#  local log=$1;
#  local num=${2:-5};
#
#  if [[ -f "${log}" ]]; then
#    while [[ ${num} -gt 1 ]]; do
#      #shellcheck disable=SC2086
#      let prev=${num}-1
#      if [[ -f "${log}.${prev}.gz" ]]; then
#        mv "${log}.${prev}.gz" "${log}.${num}.gz"
#      fi
#      num=${prev}
#    done
#    mv "${log}" "${log}.${num}"
#    gzip -9 "${log}.${num}"
#  fi
#}
#
#

#
# Example:  finding java
#
# By default, Hadoop assumes that $JAVA_HOME is always defined
# outside of its configuration. Eons ago, Apple standardized
# on a helper program called java_home to find it for you.
#
#function hadoop_java_setup
#{
#
#  if [[ -z "${JAVA_HOME}" ]]; then
#     case $HADOOP_OS_TYPE in
#       Darwin*)
#          JAVA_HOME=$(/usr/libexec/java_home)
#          ;;
#     esac
#  fi
#
#  # Bail if we did not detect it
#  if [[ -z "${JAVA_HOME}" ]]; then
#    echo "ERROR: JAVA_HOME is not set and could not be found." 1>&2
#    exit 1
#  fi
#
#  if [[ ! -d "${JAVA_HOME}" ]]; then
#     echo "ERROR: JAVA_HOME (${JAVA_HOME}) does not exist." 1>&2
#     exit 1
#  fi
#
#  JAVA="${JAVA_HOME}/bin/java"
#
#  if [[ ! -x ${JAVA} ]]; then
#    echo "ERROR: ${JAVA} is not executable." 1>&2
#    exit 1
#  fi
#}

#
# Example:  efficient command execution for the workers
#
# To improve performance, you can use xargs -P
# instead of the for loop, if supported.
#
#function hadoop_connect_to_hosts_without_pdsh
#{
#  local tmpslvnames
#
#  # quoting here gets tricky. it's easier to push it into a function
#  # so that we don't have to deal with it. However...
#  # xargs can't use a function so instead we'll export it out
#  # and force it into a subshell
#  # moral of the story: just use pdsh.
#  export -f hadoop_actual_ssh
#  export HADOOP_SSH_OPTS
#
#  # xargs is used with option -I to replace the placeholder in arguments
#  # list with each hostname read from stdin/pipe. But it consider one
#  # line as one argument while reading from stdin/pipe. So place each
#  # hostname in different lines while passing via pipe.
#  tmpslvnames=$(echo "${HADOOP_WORKER_NAMES}" | tr ' ' '\n' )
#    echo "${tmpslvnames}" | \
#    xargs -n 1 -P"${HADOOP_SSH_PARALLEL}" \
#    -I {} bash -c --  "hadoop_actual_ssh {} ${params}"
#  wait
#}