metacache-partition-genomes

#!/bin/bash

# Copyright 2016-2021, André Müller <muellan@uni-mainz.de>
#
# This file is part of the MetaCache taxonomic sequence classification tool.
#
# MetaCache is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# MetaCache is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with MetaCache.  If not, see <http://www.gnu.org/licenses/>.

# This script will partition genome files contained in <path to genome files>
# into separate directories <path to genome files>_## for partioned database construction.

set -u  # Protect against uninitialized vars.
set -e  # Stop on error

if [ $# -lt 2 ]; then
  echo "Partition genome files into separate directories for partioned database construction."
  echo "Usage:    $0 <path to genomes> <partition size in MB>"
  exit
fi

directory=$1
sizelimit=$(expr $2 \* 1024 \* 1024)

sizesofar=0
dircount=1

while read -r size file
do
  if ((sizesofar + size > sizelimit))
  then
    (( dircount++ ))
    sizesofar=0
  fi
  (( sizesofar += size ))
  if [ ! -e  "${directory}_$dircount" ]
  then
    echo "Creating folder ${directory}_$dircount"
    mkdir -p -- "${directory}_$dircount"
  fi
  filepath=$(realpath $file)
  ln -s -- "$filepath" "${directory}_$dircount"
done < <(find "$directory" -type f -printf "%s %p\n")

echo "Created" "$dircount" "directories. You can now run metacache build for each one."