79 lines
2.7 KiB
YAML
79 lines
2.7 KiB
YAML
# https://taskfile.dev
|
|
|
|
version: '3'
|
|
|
|
tasks:
|
|
default:
|
|
desc: miami ULB Münster
|
|
vars:
|
|
PROJECT: muenster
|
|
MINIMUM: 1250 # Mindestanzahl der zu erwartenden Datensätze
|
|
cmds:
|
|
- task: harvest
|
|
- task: refine
|
|
# Folgende Tasks beginnend mit ":" sind für alle Datenquellen gleich in Taskfile.yml definiert
|
|
# - task: :check
|
|
# vars: {PROJECT: '{{.PROJECT}}', MINIMUM: '{{.MINIMUM}}'}
|
|
# - task: :split
|
|
# vars: {PROJECT: '{{.PROJECT}}'}
|
|
# - task: :validate
|
|
# vars: {PROJECT: '{{.PROJECT}}'}
|
|
# - task: :zip
|
|
# vars: {PROJECT: '{{.PROJECT}}'}
|
|
# - task: :diff
|
|
# vars: {PROJECT: '{{.PROJECT}}'}
|
|
|
|
harvest:
|
|
dir: data/{{.PROJECT}}/harvest
|
|
vars:
|
|
URL: http://repositorium.uni-muenster.de/oai/miami
|
|
FORMAT: mets
|
|
PROJECT: muenster
|
|
cmds:
|
|
- METHA_DIR=$PWD metha-sync --format {{.FORMAT}} {{.URL}}
|
|
- METHA_DIR=$PWD metha-cat --format {{.FORMAT}} {{.URL}} > {{.PROJECT}}.xml
|
|
|
|
refine:
|
|
dir: data/{{.PROJECT}}/refine
|
|
ignore_error: true # provisorisch verwaisten Java-Prozess bei Exit vermeiden https://github.com/go-task/task/issues/141
|
|
vars:
|
|
PORT: 3334
|
|
RAM: 4G
|
|
PROJECT: muenster
|
|
cmds:
|
|
- task: :openrefine-start
|
|
vars: {PROJECT: '{{.PROJECT}}', PORT: '{{.PORT}}', RAM: '{{.RAM}}'}
|
|
# Import (erfordert absoluten Pfad zur XML-Datei)
|
|
- $OPENREFINE_CLIENT -P {{.PORT}} --create "$(readlink -e ../harvest/{{.PROJECT}}.xml)" --recordPath Records --recordPath Record --recordPath metadata --recordPath mets:mets --storeEmptyStrings false --trimStrings true --projectName {{.PROJECT}}
|
|
# Vorverarbeitung: Identifier in erste Spalte; nicht benötigte Spalten (ohne differenzierende Merkmale) löschen
|
|
- $OPENREFINE_CLIENT -P {{.PORT}} --apply ../../../rules/{{.PROJECT}}/vorverarbeitung.json {{.PROJECT}}
|
|
# # Export in METS:MODS mit Templating
|
|
# - |
|
|
# $OPENREFINE_CLIENT -P {{.PORT}} --export --template "$(< ../../../rules/{{.PROJECT}}/template.txt)" --rowSeparator "
|
|
# <!-- SPLIT -->
|
|
# " --suffix "
|
|
# " --output {{.PROJECT}}.txt {{.PROJECT}}
|
|
- task: :openrefine-stop
|
|
vars: {PROJECT: '{{.PROJECT}}', PORT: '{{.PORT}}'}
|
|
sources:
|
|
- ../harvest/{{.PROJECT}}.xml
|
|
- ../../../rules/{{.PROJECT}}/*.json
|
|
# - ../../../rules/{{.PROJECT}}/template.txt
|
|
#TODO - ../../../rules/common/*.json
|
|
generates:
|
|
- openrefine.log
|
|
# - '{{.PROJECT}}.txt'
|
|
- '{{.PROJECT}}.openrefine.tar.gz'
|
|
|
|
linkcheck:
|
|
desc: miami ULB Münster links überprüfen
|
|
cmds:
|
|
- task: :linkcheck
|
|
vars: {PROJECT: "muenster"}
|
|
|
|
delete:
|
|
desc: miami ULB Münster cache löschen
|
|
cmds:
|
|
- task: :delete
|
|
vars: {PROJECT: "muenster"}
|