openrefine-task-runner/example-duplicates/Taskfile.yml

58 lines
2.1 KiB
YAML

version: '3'
tasks:
main:
desc: Removing duplicates in a very small test dataset
vars: {DIR: '{{splitList ":" .TASK | first}}'}
cmds:
- task: refine
- task: :check # check OpenRefine log for any warnings and exit on error
vars: {DIR: '{{.DIR}}'}
refine:
dir: ./{{.DIR}}
vars:
PORT: 3335 # assign a different port for each project
RAM: 2048M # maximum RAM for OpenRefine java heap space
DIR: '{{splitList ":" .TASK | first}}'
PROJECT: '{{splitList ":" .TASK | first}}'
cmds:
- task: :start # launch OpenRefine
vars: {DIR: '{{.DIR}}', PORT: '{{.PORT}}', RAM: '{{.RAM}}'}
- > # import file
"$CLIENT" -P {{.PORT}}
--create "$(readlink -m input/duplicates.csv)"
--encoding UTF-8
--projectName {{.PROJECT}}
> >(tee -a openrefine.log) 2>&1
- > # apply transformation rules
"$CLIENT" -P {{.PORT}} {{.PROJECT}}
--apply config/duplicates-deletion.json
> >(tee -a openrefine.log) 2>&1
- > # export to file
mkdir -p output &&
"$CLIENT" -P {{.PORT}} {{.PROJECT}}
--output "$(readlink -m output/deduped.xls)"
> >(tee -a openrefine.log) 2>&1
- | # print allocated system resources
PID="$(lsof -t -i:{{.PORT}})"
echo "used $(($(ps --no-headers -o rss -p "$PID") / 1024)) MB RAM" \
> >(tee -a openrefine.log)
echo "used $(ps --no-headers -o cputime -p "$PID") CPU time" \
> >(tee -a openrefine.log)
- task: :stop # shut down OpenRefine and archive the OpenRefine project
vars: {DIR: '{{.DIR}}', PROJECT: '{{.PROJECT}}', PORT: '{{.PORT}}'}
sources:
- input/**
- config/**
generates:
- openrefine.log
- ./{{.PROJECT}}.openrefine.tar.gz
- output/**
ignore_error: true # workaround to avoid an orphaned Java process on error
# https://github.com/go-task/task/issues/141
default: # enable standalone execution (running `task` in project directory)
cmds:
- DIR="${PWD##*/}:main" && cd .. && task "$DIR"