Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Improve metadata mapping for example datasets #63

Merged
merged 3 commits into from
Aug 21, 2024
Merged

Improve metadata mapping for example datasets #63

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4401683
Map dates between schema formats for test datasets
cc-a Aug 5, 2024
ec2c2b1
Map rights (licenses) between schema formats
cc-a Aug 5, 2024
1e04cbe
Map related_identifiers between schemas
cc-a Aug 20, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
32 changes: 23 additions & 9 deletions test_data/create_test_data_records.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,10 +71,11 @@ def datacite_to_invenio_schema(datacite):
}
version = data["version"]
description = data["descriptions"][0]["description"]
references = [
related_identifiers = [
ri
for ri in data["relatedIdentifiers"]
if ri["relationType"] in ("References", "IsReferencedBy")
if not FILE_URI_REGEX.match(ri.get("relatedIdentifier", ""))
and not ri.get("relatedMetadataScheme") == "ORE"
]

return {
Expand Down Expand Up @@ -130,22 +131,35 @@ def datacite_to_invenio_schema(datacite):
for contributor in data["contributors"][3:]
],
"languages": [],
"related_identifiers": [],
"related_identifiers": [
{
"identifier": ri["relatedIdentifier"],
"scheme": ri["relatedIdentifierType"].lower(),
"relation_type": dict(id=ri["relationType"].lower()),
}
for ri in related_identifiers
],
"sizes": [],
"formats": [],
"version": version,
"description": description,
"additional_descriptions": [],
"funding": [],
"references": [
"references": [],
"identifiers": [],
"dates": [
{
"reference": reference["relationType"],
"identifier": reference["relatedIdentifier"],
"scheme": reference["relatedIdentifierType"].lower(),
"date": date_meta["date"],
"type": {"id": date_meta["dateType"].lower()},
}
for reference in references
for date_meta in data["dates"]
],
"rights": [
{
"id": rights_meta.get("rightsIdentifier", "cc0-1.0").lower(),
}
for rights_meta in data["rightsList"]
],
"identifiers": [],
},
}

Expand Down
Loading