openrefine-batch/openrefine-batch.sh

165 lines
5.9 KiB
Bash
Raw Normal View History

2017-02-27 00:47:34 +01:00
#!/bin/bash
2017-02-27 03:48:43 +01:00
# openrefine-batch.sh, Felix Lohmeier, v0.2, 27.02.2017
2017-02-27 01:03:33 +01:00
# https://github.com/felixlohmeier/openrefine-batch
2017-02-27 00:47:34 +01:00
# user input
if [ -z "$1" ]
then
2017-02-27 03:48:43 +01:00
echo 1>&2 "please provide path to directory with source files (leave empty to transform only)"
2017-02-27 00:47:34 +01:00
exit 2
else
inputdir=$(readlink -f $1)
2017-02-27 03:48:43 +01:00
inputfiles=($(find ${inputdir}/* -type f -printf "%f\n"))
2017-02-27 00:47:34 +01:00
fi
if [ -z "$2" ]
then
2017-02-27 03:48:43 +01:00
echo 1>&2 "please provide path to directory with config files (leave empty to import only)"
2017-02-27 00:47:34 +01:00
exit 2
else
configdir=$(readlink -f $2)
2017-02-27 03:48:43 +01:00
jsonfiles=($(find ${configdir}/* -type f -printf "%f\n"))
2017-02-27 00:47:34 +01:00
fi
if [ -z "$3" ]
then
echo 1>&2 "please provide path to output directory"
exit 2
else
outputdir=$(readlink -f $3)
mkdir -p ${outputdir}
fi
if [ -z "$4" ]
then
2017-02-27 03:48:43 +01:00
echo 1>&2 "please provide path to directory with additional OpenRefine projects for use with cross function (may be empty)"
exit 2
2017-02-27 00:47:34 +01:00
else
2017-02-27 03:48:43 +01:00
crossdir=$(readlink -f $4)
crossprojects=($(find ${crossdir}/* -maxdepth 0 -type d -printf "%f\n"))
2017-02-27 00:47:34 +01:00
fi
if [ -z "$5" ]
then
2017-02-27 03:48:43 +01:00
ram="4G"
2017-02-27 00:47:34 +01:00
else
2017-02-27 03:48:43 +01:00
ram="$5"
2017-02-27 00:47:34 +01:00
fi
if [ -z "$6" ]
2017-02-27 03:48:43 +01:00
then
inputformat=""
else
inputformat="--format=${6}"
fi
if [ -z "$7" ]
2017-02-27 00:47:34 +01:00
then
inputoptions=""
else
2017-02-27 03:48:43 +01:00
inputoptions=( "$7" "$8" "$9" "${10}" "${11}" "${12}" "${13}" "${14}" "${15}" "${16}" "${17}" "${18}" "${19}" "${20}" )
2017-02-27 00:47:34 +01:00
fi
# variables
version="2.7rc1"
uuid=$(cat /proc/sys/kernel/random/uuid)
2017-02-27 03:48:43 +01:00
echo "Input directory: $inputdir"
2017-02-27 00:47:34 +01:00
echo "Input files: ${inputfiles[@]}"
echo "Input format: $inputformat"
echo "Input options: ${inputoptions[@]}"
2017-02-27 03:48:43 +01:00
echo "Config directory: $configdir"
2017-02-27 00:47:34 +01:00
echo "Transformation rules: ${jsonfiles[@]}"
2017-02-27 03:48:43 +01:00
echo "Cross directory: $crossdir"
echo "Cross projects: ${crossprojects[@]}"
2017-02-27 00:47:34 +01:00
echo "OpenRefine heap space: $ram"
echo "OpenRefine version: $version"
echo "Docker container: $uuid"
echo "Output directory: $outputdir"
echo ""
# time
echo "begin: $(date)"
echo ""
# launch openrefine server
echo "start OpenRefine server..."
sudo docker run -d --name=${uuid} -v ${outputdir}:/data felixlohmeier/openrefine:${version} -i 0.0.0.0 -m ${ram} -d /data
until sudo docker run --rm --link ${uuid} --entrypoint /usr/bin/curl felixlohmeier/openrefine-client --silent -N http://${uuid}:3333 | cat | grep -q -o "OpenRefine" ; do sleep 1; done
echo ""
2017-02-27 03:48:43 +01:00
if [ -n "$inputfiles" ]; then
# import all files
for inputfile in "${inputfiles[@]}" ; do
echo "import ${inputfile}..."
# import
sudo docker run --rm --link ${uuid} -v ${inputdir}:/data felixlohmeier/openrefine-client -H ${uuid} -c $inputfile $inputformat ${inputoptions[@]}
# show server logs
sudo docker attach ${uuid} &
# statistics
ps -o start,etime,%mem,%cpu,rss -C java
# restart server to clear memory
echo "save project and restart OpenRefine server..."
sudo docker stop -t=5000 ${uuid}
sudo docker rm ${uuid}
sudo docker run -d --name=${uuid} -v ${outputdir}:/data felixlohmeier/openrefine:${version} -i 0.0.0.0 -m ${ram} -d /data
until sudo docker run --rm --link ${uuid} --entrypoint /usr/bin/curl felixlohmeier/openrefine-client --silent -N http://${uuid}:3333 | cat | grep -q -o "OpenRefine" ; do sleep 1; done
echo ""
done
fi
2017-02-27 00:47:34 +01:00
2017-02-27 03:48:43 +01:00
if [ -n "$jsonfiles" ]; then
# get project ids
projects=($(sudo docker run --rm --link ${uuid} felixlohmeier/openrefine-client -H ${uuid} -l | cut -c 2-14))
2017-02-27 00:47:34 +01:00
2017-02-27 03:48:43 +01:00
# copy existing projects for use with OpenRefine cross function
if [ -n "$crossprojects" ]; then
cp -r $crossdir/*.project $outputdir/
fi
# loop for all projects
for projectid in "${projects[@]}" ; do
echo "begin project $projectid @ $(date)"
# apply transformation rules
for jsonfile in "${jsonfiles[@]}" ; do
echo "transform ${jsonfile}..."
# show server logs
sudo docker attach ${uuid} &
# apply
sudo docker run --rm --link ${uuid} -v ${configdir}:/data felixlohmeier/openrefine-client -H ${uuid} -f ${jsonfile} ${projectid}
# statistics
ps -o start,etime,%mem,%cpu,rss -C java
# restart server to clear memory
echo "save project and restart OpenRefine server..."
sudo docker stop -t=5000 ${uuid}
sudo docker rm ${uuid}
sudo docker run -d --name=${uuid} -v ${outputdir}:/data felixlohmeier/openrefine:${version} -i 0.0.0.0 -m ${ram} -d /data
until sudo docker run --rm --link ${uuid} --entrypoint /usr/bin/curl felixlohmeier/openrefine-client --silent -N http://${uuid}:3333 | cat | grep -q -o "OpenRefine" ; do sleep 1; done
done
# export files
echo "export to file ${projectid}.tsv..."
2017-02-27 00:47:34 +01:00
# show server logs
sudo docker attach ${uuid} &
2017-02-27 03:48:43 +01:00
# export
sudo docker run --rm --link ${uuid} -v ${outputdir}:/data felixlohmeier/openrefine-client -H ${uuid} -E --output=${projectid}.tsv ${projectid}
2017-02-27 00:47:34 +01:00
# statistics
ps -o start,etime,%mem,%cpu,rss -C java
# restart server to clear memory
2017-02-27 03:48:43 +01:00
echo "restart OpenRefine server..."
2017-02-27 00:47:34 +01:00
sudo docker stop -t=5000 ${uuid}
sudo docker rm ${uuid}
sudo docker run -d --name=${uuid} -v ${outputdir}:/data felixlohmeier/openrefine:${version} -i 0.0.0.0 -m ${ram} -d /data
until sudo docker run --rm --link ${uuid} --entrypoint /usr/bin/curl felixlohmeier/openrefine-client --silent -N http://${uuid}:3333 | cat | grep -q -o "OpenRefine" ; do sleep 1; done
2017-02-27 03:48:43 +01:00
# time
echo "finished project $projectid @ $(date)"
echo ""
2017-02-27 00:47:34 +01:00
done
2017-02-27 03:48:43 +01:00
# list output files
echo "output (number of lines / size in bytes):"
wc -c -l ${outputdir}/*.tsv
2017-02-27 00:47:34 +01:00
echo ""
2017-02-27 03:48:43 +01:00
fi
2017-02-27 00:47:34 +01:00
# cleanup
echo "cleanup..."
sudo docker stop -t=5000 ${uuid}
sudo docker rm ${uuid}
sudo rm -r -f ${outputdir}/workspace*.json
echo ""
# time
echo "finish: $(date)"