Test Datasets

.gitignore

@@ -73,3 +73,6 @@ data/.minio.sys
 
 # Celery
 celerybeat-schedule
+
+# test datasets
+test_data/10.14469_hpc_*

README.md

@@ -137,9 +137,15 @@ Note that overriding settings by environment variable still works.
 The default configuration is suitable for development. A production oriented settings
 file is also provided in `ic_data_repo.config.production`.
 
+## Test Data
+
+Instructions for accessing and working with realistic test data records are provided in
+the [test_data directory].
+
 [configuration approach]: https://inveniordm.docs.cern.ch/install/configuration/
 [getting started]: #getting-started
 [invenio-cli]: https://github.com/inveniosoftware/invenio-cli
 [pre-commit]: https://pre-commit.com/
 [pytest-flask]: https://pytest-flask.readthedocs.io/en/latest/
 [pytest-invenio]: https://pytest-invenio.readthedocs.io/en/latest/
+[test_data directory]: ./test_data/README.md

app_data/vocabularies.yaml

@@ -17,10 +17,10 @@ subjects:
 #  pid-type: lng
 #  data-file: vocabularies/languages.yaml
 # TODO: Uncoment this if you want to have all affiliations with ROR identifiers.
-# affiliations:
-#   pid-type: aff
-#   schemes:
-#     - id: ROR
-#       name: Research Organization Registry
-#       uri: "https://ror.org/"
-#       data-file: vocabularies/affiliations_ror.yaml
+affiliations:
+  pid-type: aff
+  data-file: vocabularies/affiliations_ror.yaml
+  schemes:
+    - id: ROR
+      name: Research Organization Registry
+      uri: "https://ror.org/"