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.

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

Add dct identifier to publisher #301

Merged
merged 4 commits into from
Sep 12, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
10 changes: 9 additions & 1 deletion ckanext/dcat/converters.py
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,15 @@ def dcat_to_ckan(dcat_dict):
package_dict['extras'].append({'key': 'dcat_publisher_name', 'value': dcat_publisher})
elif isinstance(dcat_publisher, dict) and dcat_publisher.get('name'):
package_dict['extras'].append({'key': 'dcat_publisher_name', 'value': dcat_publisher.get('name')})
package_dict['extras'].append({'key': 'dcat_publisher_email', 'value': dcat_publisher.get('mbox')})

if dcat_publisher.get('mbox'):
package_dict['extras'].append({'key': 'dcat_publisher_email', 'value': dcat_publisher.get('mbox')})

if dcat_publisher.get('identifier'):
package_dict['extras'].append({
'key': 'dcat_publisher_id',
'value': dcat_publisher.get('identifier') # This could be a URI like https://ror.org/05wg1m734
})

package_dict['extras'].append({
'key': 'language',
Expand Down
3 changes: 2 additions & 1 deletion ckanext/dcat/processors.py
Original file line number Diff line number Diff line change
Expand Up @@ -407,7 +407,8 @@ def _get_from_extra(key):
('name', Literal, FOAF.name, True,),
('email', Literal, FOAF.mbox, False,),
('url', URIRef, FOAF.homepage,False,),
('type', Literal, DCT.type, False,))
('type', Literal, DCT.type, False,),
('identifier', URIRef, DCT.identifier, False,))

_pub = _get_from_extra('source_catalog_publisher')
if _pub:
Expand Down
2 changes: 2 additions & 0 deletions ckanext/dcat/profiles/base.py
Original file line number Diff line number Diff line change
Expand Up @@ -468,6 +468,8 @@ def _publisher(self, subject, predicate):

publisher["type"] = self._object_value(agent, DCT.type)

publisher['identifier'] = self._object_value(agent, DCT.identifier)

return publisher

def _contact_details(self, subject, predicate):
Expand Down
5 changes: 4 additions & 1 deletion ckanext/dcat/profiles/euro_dcat_ap_base.py
Original file line number Diff line number Diff line change
Expand Up @@ -123,7 +123,7 @@ def _parse_dataset_base(self, dataset_dict, dataset_ref):

# Publisher
publisher = self._publisher(dataset_ref, DCT.publisher)
for key in ("uri", "name", "email", "url", "type"):
for key in ("uri", "name", "email", "url", "type", "identifier"):
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This will take care of the DCAT -> CKAN mapping, but you also need to add the other way around, CKAN -> DCAT. This is done a bit further down in the file here and here.

Additionally, this will cover the legacy way of defining publisher fields based on namespaced publisher_* extra fields, but going forward we want to support scheming objects ("publisher": {"id": xx, "name": yy, "url": zz}). This is handled in the euro_dcat_ap_scheming profile here (for CKAN -> DCAT, the opposite should already be handled by the base profile). Do you mind adding support for the new field there as well? And if you extend this test to cover the new field, even better.

@hcvdwerf Let me know if all this makes sense

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Tnx for the comments. Verry helpful @amercader . Jut commit the changes

if publisher.get(key):
dataset_dict["extras"].append(
{"key": "publisher_{0}".format(key), "value": publisher.get(key)}
Expand Down Expand Up @@ -372,6 +372,7 @@ def _graph_from_dataset_base(self, dataset_dict, dataset_ref):
"email": self._get_dataset_value(dataset_dict, "publisher_email"),
"url": self._get_dataset_value(dataset_dict, "publisher_url"),
"type": self._get_dataset_value(dataset_dict, "publisher_type"),
"identifier": self._get_dataset_value(dataset_dict, "publisher_identifier"),
}
elif dataset_dict.get("organization"):
# Fall back to dataset org
Expand All @@ -396,6 +397,7 @@ def _graph_from_dataset_base(self, dataset_dict, dataset_ref):
"email": org_dict.get("email"),
"url": org_dict.get("url"),
"type": org_dict.get("dcat_type"),
"identifier": org_dict.get("identifier"),
}
# Add to graph
if publisher_ref:
Expand All @@ -406,6 +408,7 @@ def _graph_from_dataset_base(self, dataset_dict, dataset_ref):
("email", FOAF.mbox, None, Literal),
("url", FOAF.homepage, None, URIRef),
("type", DCT.type, None, URIRefOrLiteral),
("identifier", DCT.identifier, None, URIRefOrLiteral),
]
self._add_triples_from_dict(publisher_details, publisher_ref, items)

Expand Down
7 changes: 7 additions & 0 deletions ckanext/dcat/profiles/euro_dcat_ap_scheming.py
Original file line number Diff line number Diff line change
Expand Up @@ -187,6 +187,13 @@ def _not_empty_dict(data_dict):
_type=URIRef,
value_modifier=self._add_mailto,
)
self._add_triple_from_dict(
publisher,
publisher_ref,
DCT.identifier,
"identifier",
_type=URIRefOrLiteral
)

temporal = dataset_dict.get("temporal_coverage")
if (
Expand Down
4 changes: 4 additions & 0 deletions ckanext/dcat/profiles/schemaorg.py
Original file line number Diff line number Diff line change
Expand Up @@ -221,6 +221,10 @@ def _publisher_graph(self, dataset_ref, dataset_dict):

self._add_triples_from_dict(dataset_dict, contact_point, items)

publisher_identifier = self._get_dataset_value(dataset_dict, "publisher_identifier")
if publisher_identifier:
self.g.add((publisher_details, SCHEMA.identifier, Literal(publisher_identifier)))

def _temporal_graph(self, dataset_ref, dataset_dict):
start = self._get_dataset_value(dataset_dict, "temporal_start")
end = self._get_dataset_value(dataset_dict, "temporal_end")
Expand Down
4 changes: 4 additions & 0 deletions ckanext/dcat/schemas/dcat_ap_full.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -66,6 +66,10 @@ dataset_fields:

- field_name: type
label: Type

- field_name: identifier
label: Identifier
help_text: Unique identifier for the publisher, such as a ROR ID.
help_text: Entity responsible for making the dataset available.

- field_name: license_id
Expand Down
5 changes: 5 additions & 0 deletions ckanext/dcat/schemas/dcat_ap_recommended.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -66,6 +66,11 @@ dataset_fields:

- field_name: type
label: Type

- field_name: identifier
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you add it to the dcat_ap_full.yaml file as well?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I will do

label: Identifier
help_text: Unique identifier for the publisher, such as a ROR ID.

help_text: Entity responsible for making the dataset available.

- field_name: license_id
Expand Down
2 changes: 2 additions & 0 deletions ckanext/dcat/tests/profiles/base/test_base_profile.py
Original file line number Diff line number Diff line change
Expand Up @@ -647,6 +647,7 @@ def test_publisher_foaf(self):
<foaf:mbox>contact@some.org</foaf:mbox>
<foaf:homepage>http://some.org</foaf:homepage>
<dct:type rdf:resource="http://purl.org/adms/publishertype/NonProfitOrganisation"/>
<dct:identifier rdf:resource="https://ror.org/05wg1m734"/>
</foaf:Organization>
</dct:publisher>
</rdfs:SomeClass>
Expand All @@ -666,6 +667,7 @@ def test_publisher_foaf(self):
assert publisher['email'] == 'contact@some.org'
assert publisher['url'] == 'http://some.org'
assert publisher['type'] == 'http://purl.org/adms/publishertype/NonProfitOrganisation'
assert publisher['identifier'] == 'https://ror.org/05wg1m734'

def test_publisher_ref(self):

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -113,6 +113,7 @@ def _get_extra_value_as_list(key):
assert _get_extra_value('publisher_email') == 'contact@some.org'
assert _get_extra_value('publisher_url') == 'http://some.org'
assert _get_extra_value('publisher_type') == 'http://purl.org/adms/publishertype/NonProfitOrganisation'
assert _get_extra_value('publisher_identifier') == 'https://ror.org/05wg1m734'
assert _get_extra_value('contact_name') == 'Point of Contact'
# mailto gets removed for storage and is added again on output
assert _get_extra_value('contact_email') == 'contact@some.org'
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -94,6 +94,7 @@ def test_e2e_ckan_to_dcat(self):
"email": "publisher@example.org",
"url": "https://example.org",
"type": "public_body",
"identifier": "http://example.org/publisher-id",
},
],
"temporal_coverage": [
Expand Down Expand Up @@ -301,6 +302,12 @@ def test_e2e_ckan_to_dcat(self):
DCT.type,
dataset_dict["publisher"][0]["type"],
)
assert self._triple(
g,
publisher[0][2],
DCT.identifier,
URIRef(dataset_dict["publisher"][0]["identifier"])
)

temporal = [t for t in g.triples((dataset_ref, DCT.temporal, None))]

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -105,6 +105,7 @@ def test_publisher_extras(self):
{'key': 'publisher_email', 'value': 'publisher@example.com'},
{'key': 'publisher_url', 'value': 'http://example.com/publisher/home'},
{'key': 'publisher_type', 'value': 'http://purl.org/adms/publishertype/Company'},
{'key': 'publisher_identifier', 'value': 'https://ror.org/05wg1m734'},
]


Expand All @@ -121,6 +122,7 @@ def test_publisher_extras(self):
assert str(publisher) == extras['publisher_uri']
assert self._triple(g, publisher, RDF.type, SCHEMA.Organization)
assert self._triple(g, publisher, SCHEMA.name, extras['publisher_name'])
assert self._triple(g, publisher, SCHEMA.identifier, extras['publisher_identifier'])

contact_point = self._triple(g, publisher, SCHEMA.contactPoint, None)[2]
assert contact_point
Expand All @@ -144,6 +146,7 @@ def test_publisher_no_uri(self):
{'key': 'publisher_email', 'value': 'publisher@example.com'},
{'key': 'publisher_url', 'value': 'http://example.com/publisher/home'},
{'key': 'publisher_type', 'value': 'http://purl.org/adms/publishertype/Company'},
{'key': 'publisher_identifier', 'value': 'https://ror.org/05wg1m734'},
]
}
extras = self._extras(dataset)
Expand All @@ -158,6 +161,7 @@ def test_publisher_no_uri(self):
assert isinstance(publisher, BNode)
assert self._triple(g, publisher, RDF.type, SCHEMA.Organization)
assert self._triple(g, publisher, SCHEMA.name, extras['publisher_name'])
assert self._triple(g, publisher, SCHEMA.identifier, extras['publisher_identifier'])

contact_point = self._triple(g, publisher, SCHEMA.contactPoint, None)[2]
assert contact_point
Expand Down
1 change: 1 addition & 0 deletions ckanext/dcat/utils.py
Original file line number Diff line number Diff line change
Expand Up @@ -78,6 +78,7 @@ def field_labels():
'publisher_email': _('Publisher email'),
'publisher_url': _('Publisher URL'),
'publisher_type': _('Publisher type'),
'publisher_identifier': _('Publisher identifier'),
'contact_name': _('Contact name'),
'contact_email': _('Contact email'),
'contact_uri': _('Contact URI'),
Expand Down
Loading