udata 10.0.3__py2.py3-none-any.whl → 10.0.3.dev32594__py2.py3-none-any.whl

udata/__init__.py

@@ -4,5 +4,5 @@
 udata
 """
 
-__version__ = "10.0.3"
+__version__ = "10.0.3.dev"
 __description__ = "Open data portal"

udata/commands/fixtures.py

@@ -39,7 +39,7 @@ COMMUNITY_RES_URL = "/api/1/datasets/community_resources"
 DISCUSSION_URL = "/api/1/discussions"
 
 
-DEFAULT_FIXTURE_FILE_TAG: str = "v4.0.0"
+DEFAULT_FIXTURE_FILE_TAG: str = "v3.0.0"
 DEFAULT_FIXTURE_FILE: str = f"https://raw.githubusercontent.com/opendatateam/udata-fixtures/{DEFAULT_FIXTURE_FILE_TAG}/results.json"  # noqa
 
 DEFAULT_FIXTURES_RESULTS_FILENAME: str = "results.json"
@@ -180,9 +180,7 @@ def get_or_create_user(data):
 def import_fixtures(source):
     """Build sample fixture data (users, datasets, reuses, dataservices) from local or remote file."""
     if source.startswith("http"):
-        response = requests.get(source)
-        response.raise_for_status()
-        json_fixtures = response.json()
+        json_fixtures = requests.get(source).json()
     else:
         with open(source) as f:
             json_fixtures = json.load(f)

udata/core/dataservices/rdf.py

@@ -7,10 +7,7 @@ from udata.core.dataset.models import Dataset, License
 from udata.core.dataset.rdf import dataset_to_graph_id, sanitize_html
 from udata.rdf import (
     DCAT,
-    DCATAP,
     DCT,
-    HVD_LEGISLATION,
-    TAG_TO_EU_HVD_CATEGORIES,
     contact_point_from_rdf,
     contact_point_to_rdf,
     namespace_manager,
@@ -141,29 +138,8 @@ def dataservice_to_rdf(dataservice: Dataservice, graph=None):
     if dataservice.endpoint_description_url:
         d.set(DCAT.endpointDescription, URIRef(dataservice.endpoint_description_url))
 
-    # Add DCAT-AP HVD properties if the dataservice is tagged hvd.
-    # See https://semiceu.github.io/DCAT-AP/releases/2.2.0-hvd/
-    is_hvd = current_app.config["HVD_SUPPORT"] and "hvd" in dataservice.tags
-    if is_hvd:
-        d.add(DCATAP.applicableLegislation, URIRef(HVD_LEGISLATION))
-
-    hvd_category_tags = set()
     for tag in dataservice.tags:
         d.add(DCAT.keyword, Literal(tag))
-        # Add HVD category if this dataservice is tagged HVD
-        if is_hvd and tag in TAG_TO_EU_HVD_CATEGORIES:
-            hvd_category_tags.add(tag)
-
-    if is_hvd:
-        # We also want to automatically add any HVD category tags of the dataservice's datasets.
-        for dataset in dataservice.datasets:
-            if "hvd" not in dataset.tags:  # Only check HVD datasets for their categories.
-                continue
-            for tag in dataset.tags:
-                if tag in TAG_TO_EU_HVD_CATEGORIES:
-                    hvd_category_tags.add(tag)
-    for tag in hvd_category_tags:
-        d.add(DCATAP.hvdCategory, URIRef(TAG_TO_EU_HVD_CATEGORIES[tag]))
 
     # `dataset_to_graph_id(dataset)` URIRef may not exist in the current page
     # but should exists in the catalog somewhere. Maybe we should create a Node

udata/core/dataset/constants.py

@@ -72,8 +72,6 @@ RESOURCE_FILETYPES = OrderedDict(
     ]
 )
 
-OGC_SERVICE_FORMATS = ["ogc:wms", "ogc:wfs", "wms", "wfs"]
-
 CHECKSUM_TYPES = ("sha1", "sha2", "sha256", "md5", "crc")
 DEFAULT_CHECKSUM_TYPE = "sha1"
 

udata/core/dataset/rdf.py

@@ -49,7 +49,7 @@ from udata.rdf import (
 from udata.uris import endpoint_for
 from udata.utils import get_by, safe_unicode
 
-from .constants import OGC_SERVICE_FORMATS, UPDATE_FREQUENCIES
+from .constants import UPDATE_FREQUENCIES
 from .models import Checksum, Dataset, License, Resource
 
 log = logging.getLogger(__name__)
@@ -126,44 +126,6 @@ def owner_to_rdf(dataset, graph=None):
     return
 
 
-def ogc_service_to_rdf(dataset, resource, graph=None, is_hvd=False):
-    """
-    Build a dataservice on the fly for OGC services distributions
-    Inspired from https://github.com/SEMICeu/iso-19139-to-dcat-ap/blob/f61b2921dd398b90b2dd2db14085e75687f7616b/iso-19139-to-dcat-ap.xsl#L1419
-    """
-    graph = graph or Graph(namespace_manager=namespace_manager)
-    service = graph.resource(BNode())
-    service.set(RDF.type, DCAT.DataService)
-    service.set(DCT.title, Literal(resource.title))
-    service.set(DCAT.endpointURL, URIRef(resource.url.split("?")[0]))
-    if "request=getcapabilities" in resource.url.lower():
-        service.set(DCAT.endpointDescription, URIRef(resource.url))
-    service.set(
-        DCT.conformsTo,
-        URIRef("http://www.opengeospatial.org/standards/" + resource.format.split(":")[-1]),
-    )
-
-    if dataset and dataset.license:
-        service.add(DCT.rights, Literal(dataset.license.title))
-        if dataset.license.url:
-            service.add(DCT.license, URIRef(dataset.license.url))
-
-    if dataset and dataset.contact_point:
-        contact_point = contact_point_to_rdf(dataset.contact_point, graph)
-        if contact_point:
-            service.set(DCAT.contactPoint, contact_point)
-
-    if is_hvd:
-        # DCAT-AP HVD applicable legislation is also expected at the distribution > accessService level
-        service.add(DCATAP.applicableLegislation, URIRef(HVD_LEGISLATION))
-        for tag in dataset.tags:
-            # Add HVD category if this dataset is tagged HVD
-            if tag in TAG_TO_EU_HVD_CATEGORIES:
-                service.add(DCATAP.hvdCategory, URIRef(TAG_TO_EU_HVD_CATEGORIES[tag]))
-
-    return service
-
-
 def resource_to_rdf(resource, dataset=None, graph=None, is_hvd=False):
     """
     Map a Resource domain model to a DCAT/RDF graph
@@ -213,11 +175,6 @@ def resource_to_rdf(resource, dataset=None, graph=None, is_hvd=False):
     if is_hvd:
         # DCAT-AP HVD applicable legislation is also expected at the distribution level
         r.add(DCATAP.applicableLegislation, URIRef(HVD_LEGISLATION))
-
-    # Add access service for known OGC service formats
-    if resource.format in OGC_SERVICE_FORMATS:
-        r.add(DCAT.accessService, ogc_service_to_rdf(dataset, resource, graph, is_hvd))
-
     return r
 
 

udata/harvest/backends/dcat.py

@@ -54,9 +54,6 @@ URIS_TO_REPLACE = {
 }
 
 
-SAFE_PARSER = ET.XMLParser(resolve_entities=False)
-
-
 def extract_graph(source, target, node, specs):
     for p, o in source.predicate_objects(node):
         target.add((node, p, o))
@@ -253,7 +250,7 @@ class CswDcatBackend(DcatBackend):
         )
         response.raise_for_status()
         content = response.content
-        tree = ET.fromstring(content, parser=SAFE_PARSER)
+        tree = ET.fromstring(content)
         if tree.tag == "{" + OWS_NAMESPACE + "}ExceptionReport":
             raise ValueError(f"Failed to query CSW:\n{content}")
         while tree is not None:
@@ -279,8 +276,7 @@ class CswDcatBackend(DcatBackend):
             tree = ET.fromstring(
                 self.post(
                     url, data=body.format(start=start, schema=self.DCAT_SCHEMA), headers=headers
-                ).content,
-                parser=SAFE_PARSER,
+                ).content
             )
 
 
@@ -313,7 +309,7 @@ class CswIso19139DcatBackend(DcatBackend):
         See https://github.com/SEMICeu/iso-19139-to-dcat-ap for more information on the XSLT.
         """
         # Load XSLT
-        xsl = ET.fromstring(self.get(self.XSL_URL).content, parser=SAFE_PARSER)
+        xsl = ET.fromstring(self.get(self.XSL_URL).content)
         transform = ET.XSLT(xsl)
 
         # Start querying and parsing graph
@@ -355,7 +351,7 @@ class CswIso19139DcatBackend(DcatBackend):
         )
         response.raise_for_status()
 
-        tree_before_transform = ET.fromstring(response.content, parser=SAFE_PARSER)
+        tree_before_transform = ET.fromstring(response.content)
         # Disabling CoupledResourceLookUp to prevent failure on xlink:href
         # https://github.com/SEMICeu/iso-19139-to-dcat-ap/blob/master/documentation/HowTo.md#parameter-coupledresourcelookup
         tree = transform(tree_before_transform, CoupledResourceLookUp="'disabled'")
@@ -390,5 +386,5 @@ class CswIso19139DcatBackend(DcatBackend):
             )
             response.raise_for_status()
 
-            tree_before_transform = ET.fromstring(response.content, parser=SAFE_PARSER)
+            tree_before_transform = ET.fromstring(response.content)
             tree = transform(tree_before_transform, CoupledResourceLookUp="'disabled'")