opencultureconsulting
/
openrefine-batch
mirror of https://github.com/opencultureconsulting/openrefine-batch.git
2
0
Fork 0
Code Issues Releases Activity

release v0.4

This commit is contained in:
Felix Lohmeier 2017-02-27 18:12:06 +01:00
parent 7d11206f42
commit b80fe929bc
2 changed files with 25 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
README.md
View File

@ -48,7 +48,7 @@ clone or [download GitHub repository](https://github.com/felixlohmeier/openrefin
#### Options
```
./openrefine-batch.sh $inputdir $configdir $outputdir $crossdir $ram $version $inputformat $inputoptions
./openrefine-batch.sh $inputdir $configdir $outputdir $crossdir $ram $version $restart $inputformat $inputoptions
```
1. inputdir: path to directory with source files (multiple files may be imported into a single project [by providing a zip or tar.gz archive](https://github.com/OpenRefine/OpenRefine/wiki/Importers))
@ -57,8 +57,9 @@ clone or [download GitHub repository](https://github.com/felixlohmeier/openrefin
4. crossdir: path to directory with additional OpenRefine projects (will be copied to workspace before transformation step to support the [cross function](https://github.com/OpenRefine/OpenRefine/wiki/GREL-Other-Functions#crosscell-c-string-projectname-string-columnname))
5. ram: maximum RAM for OpenRefine java heap space (default: 4G)
6. version: OpenRefine version (2.7rc1, 2.6rc2, 2.6rc1, dev)
7. inputformat: csv, tsv, xml, json, line-based, fixed-width, xlsx or ods
8. inputoptions: several options provided by [openrefine-client](https://hub.docker.com/r/felixlohmeier/openrefine-client/)
7. restart: restart docker container after each transformation to clear memory (restart-true/restart-false)
8. inputformat: (csv, tsv, xml, json, line-based, fixed-width, xlsx, ods)
9. inputoptions: several options provided by [openrefine-client](https://hub.docker.com/r/felixlohmeier/openrefine-client/)
inputoptions (mandatory for xml, json, fixed-width, xslx, ods):
* `--recordPath=RECORDPATH` (xml, json): please provide path in multiple arguments without slashes, e.g. /collection/record/ should be entered like this: `--recordPath=collection --recordPath=record`
@ -85,7 +86,7 @@ more inputoptions (optional, only together with inputformat):
The script uses `docker attach` to print log messages from OpenRefine server and `ps` to show statistics for each step. Here is a sample log:
```
[03:27 felix ~/openrefine-batch (master *)]$ ./openrefine-batch.sh examples/powerhouse-museum/input/ examples/powerhouse-museum/config/ examples/powerhouse-museum/output/ examples/powerhouse-museum/cross/ 4G 2.7rc1 tsv --processQuotes=false --guessCellValueTypes=true
[03:27 felix ~/openrefine-batch (master *)]$ ./openrefine-batch.sh examples/powerhouse-museum/input/ examples/powerhouse-museum/config/ examples/powerhouse-museum/output/ examples/powerhouse-museum/cross/ 4G 2.7rc1 restart-true tsv --processQuotes=false --guessCellValueTypes=true
Input directory: /home/felix/openrefine-batch/examples/powerhouse-museum/input
Input files: phm-collection.tsv
Input format: --format=tsv
@ -96,6 +97,7 @@ Cross directory: /home/felix/openrefine-batch/examples/powerhouse-museum/
Cross projects:
OpenRefine heap space: 4G
OpenRefine version: 2.7rc1
Docker restart: restart-true
Docker container: 6b7eb36f-fc72-4040-b135-acee36948c13
Output directory: /home/felix/openrefine-batch/examples/powerhouse-museum/output

29
openrefine-batch.sh
View File

@ -1,5 +1,5 @@
#!/bin/bash
# openrefine-batch.sh, Felix Lohmeier, v0.3, 27.02.2017
# openrefine-batch.sh, Felix Lohmeier, v0.4, 27.02.2017
# https://github.com/felixlohmeier/openrefine-batch
# user input
@ -49,15 +49,21 @@ if [ -z "$6" ]
fi
if [ -z "$7" ]
then
inputformat=""
restart="restart-true"
else
inputformat="--format=${7}"
restart="$7"
fi
if [ -z "$8" ]
then
inputformat=""
else
inputformat="--format=${8}"
fi
if [ -z "$9" ]
then
inputoptions=""
else
inputoptions=( "$8" "$9" "${10}" "${11}" "${12}" "${13}" "${14}" "${15}" "${16}" "${17}" "${18}" "${19}" "${20}" )
inputoptions=( "$9" "${10}" "${11}" "${12}" "${13}" "${14}" "${15}" "${16}" "${17}" "${18}" "${19}" "${20}" )
fi
# variables
@ -73,6 +79,7 @@ echo "Cross projects: ${crossprojects[@]}"
echo "OpenRefine heap space: $ram"
echo "OpenRefine version: $version"
echo "Docker container: $uuid"
echo "Docker restart: $restart"
echo "Output directory: $outputdir"
echo ""
@ -127,12 +134,14 @@ if [ -n "$jsonfiles" ]; then
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
if [ "$restart" = "restart-true" ]; then
# 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
fi
done
# export files
echo "export to file ${projectid}.tsv..."