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

feat: Harvest dataset field 'documentation' #74

Merged
merged 5 commits into from
Sep 18, 2023
Merged

feat: Harvest dataset field 'documentation' #74

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
81a86a0
feat: Harvest dataset field 'documentation'
bellisk Sep 13, 2023
cda611f
feat: Map DCAT-AP CH v2 documentation property
bellisk Sep 13, 2023
4e1dcb0
tests: Test dataset documentation mapping
bellisk Sep 13, 2023
0347e5e
tests: Update fixture
bellisk Sep 13, 2023
f9114be
test: Test serialization of dataset document field
bellisk Sep 13, 2023
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
14 changes: 12 additions & 2 deletions ckanext/dcatapchharvest/profiles.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -487,6 +487,11 @@ def parse_dataset(self, dataset_dict, dataset_ref): # noqa
dataset_uri = dh.dataset_uri(dataset_dict, dataset_ref)
dataset_dict['extras'].append({'key': 'uri', 'value': dataset_uri})

# Documentation
dataset_dict['documentation'] = self._object_value_list(
dataset_ref, FOAF.page
)

# Resources
for distribution in self._distributions(dataset_ref):
resource_dict = {
Expand Down Expand Up @@ -645,7 +650,6 @@ def graph_from_dataset(self, dataset_dict, dataset_ref): # noqa
('theme', DCAT.theme, None, URIRef),
('conforms_to', DCT.conformsTo, None, Literal),
('alternate_identifier', ADMS.identifier, None, Literal),
('documentation', FOAF.page, None, Literal),
('has_version', DCT.hasVersion, None, Literal),
('is_version_of', DCT.isVersionOf, None, Literal),
('source', DCT.source, None, Literal),
Expand Down Expand Up @@ -725,6 +729,13 @@ def graph_from_dataset(self, dataset_dict, dataset_ref): # noqa
)
g.add((dataset_ref, DCT.temporal, temporal_extent))

# Documentation
documentation = dataset_dict.get('documentation', [])
for link in documentation:
doc = URIRef(link)
g.add((doc, RDF.type, FOAF.Document))
g.add((dataset_ref, FOAF.page, doc))

# Themes
groups = self._get_dataset_value(dataset_dict, 'groups', [])
for group_name in groups:
Expand Down Expand Up @@ -1066,7 +1077,6 @@ def graph_from_dataset(self, dataset_dict, dataset_ref):

# Lists
items = [
("documentation", FOAF.page, None, Literal),
("language", DCT.language, None, Literal),
("conforms_to", DCT.conformsTo, None, Literal),
]
Expand Down
6 changes: 6 additions & 0 deletions ckanext/dcatapchharvest/tests/fixtures/1901.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,5 +55,11 @@
<dcat:keyword xml:lang="it">basi-statistiche-e-presentazioni-generali</dcat:keyword>
<dct:title xml:lang="fr">Annuaire statistique de la Suisse 1901</dct:title>
<dcat:keyword xml:lang="de">statistische-grundlagen-und-ubersichten</dcat:keyword>
<foaf:page>
<foaf:Document rdf:about="https://example.com/documentation-dataset-1"/>
</foaf:page>
<foaf:page>
<foaf:Document rdf:about="https://example.com/documentation-dataset-2"/>
</foaf:page>
</dcat:Dataset>
</rdf:RDF>
8 changes: 4 additions & 4 deletions ckanext/dcatapchharvest/tests/fixtures/dataset.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,6 +93,10 @@
"en": "English Description",
"it": ""
},
"documentation": [
"http://dataset.info.org/doc1",
"http://dataset.info.org/doc2"
],
"extras": [
{
"key": "alternate_identifier",
Expand Down Expand Up @@ -126,10 +130,6 @@
"key": "access_rights",
"value": "public"
},
{
"key": "documentation",
"value": "[\"http://dataset.info.org/doc1\", \"http://dataset.info.org/doc2\"]"
},
{
"key": "provenance",
"value": "Some statement about provenance"
Expand Down
4 changes: 4 additions & 0 deletions ckanext/dcatapchharvest/tests/test_dcatap_ch_parse.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,6 +86,10 @@ def test_dataset_all_fields(self):
# Lists
eq_(sorted(dataset['language']), [u'de', u'fr'])
eq_(sorted(dataset['groups']), [{'name': u'statistical-basis'}])
eq_(
sorted(dataset['documentation']),
['https://example.com/documentation-dataset-1', 'https://example.com/documentation-dataset-2']
)

# Dataset URI
eq_(extras['uri'], u'https://opendata.swiss/dataset/7451e012-64b2-4bbc-af20-a0e2bc61b585')
Expand Down
6 changes: 5 additions & 1 deletion ckanext/dcatapchharvest/tests/test_dcatap_ch_serialize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,10 +56,14 @@ def test_graph_from_dataset(self):
for keyword in keywords:
assert self._triple(g, dataset_ref, DCAT.keyword, Literal(keyword, lang=key))

# Documentation
eq_(len([t for t in g.triples((dataset_ref, FOAF.page, None))]), 2)
for documentation_link in dataset['documentation']:
assert self._triple(g, dataset_ref, FOAF.page, URIRef(documentation_link))

# List
for item in [
('language', DCT.language, Literal),
# ('documentation', FOAF.page, URIRef, FOAF.Document),
]:
values = json.loads(extras[item[0]])
eq_(len([t for t in g.triples((dataset_ref, item[1], None))]), len(values))
Expand Down