cognite-neat 0.80.3__tar.gz → 0.81.1__tar.gz

{cognite_neat-0.80.3 → cognite_neat-0.81.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cognite-neat
-Version: 0.80.3
+Version: 0.81.1
 Summary: Knowledge graph transformation
 Home-page: https://cognite-neat.readthedocs-hosted.com/
 License: Apache-2.0

cognite_neat-0.81.1/cognite/neat/_version.py

@@ -0,0 +1 @@
+__version__ = "0.81.1"

{cognite_neat-0.80.3 → cognite_neat-0.81.1}/cognite/neat/graph/extractors/__init__.py

@@ -5,6 +5,7 @@ from ._classic_cdf._labels import LabelsExtractor
 from ._classic_cdf._relationships import RelationshipsExtractor
 from ._classic_cdf._sequences import SequencesExtractor
 from ._classic_cdf._timeseries import TimeSeriesExtractor
+from ._dexpi import DexpiExtractor
 from ._mock_graph_generator import MockGraphGenerator
 from ._rdf_file import RdfFileExtractor
 
@@ -18,6 +19,7 @@ __all__ = [
     "FilesExtractor",
     "LabelsExtractor",
     "RdfFileExtractor",
+    "DexpiExtractor",
 ]
 
 
@@ -31,4 +33,5 @@ TripleExtractors = (
     | FilesExtractor
     | LabelsExtractor
     | RdfFileExtractor
+    | DexpiExtractor
 )

{cognite_neat-0.80.3 → cognite_neat-0.81.1}/cognite/neat/graph/extractors/_classic_cdf/_assets.py

@@ -1,10 +1,9 @@
 from collections.abc import Iterable
-from datetime import datetime
+from datetime import datetime, timezone
 from pathlib import Path
 from typing import cast
 from urllib.parse import quote
 
-import pytz
 from cognite.client import CogniteClient
 from cognite.client.data_classes import Asset, AssetList
 from rdflib import RDF, Literal, Namespace
@@ -49,7 +48,7 @@ class AssetsExtractor(BaseExtractor):
     @classmethod
     def _asset2triples(cls, asset: Asset, namespace: Namespace) -> list[Triple]:
         """Converts an asset to triples."""
-        id_ = namespace[str(asset.id)]
+        id_ = namespace[f"Asset_{asset.id}"]
 
         # Set rdf type
         triples: list[Triple] = [(id_, RDF.type, namespace["Asset"])]
@@ -72,14 +71,14 @@ class AssetsExtractor(BaseExtractor):
             (
                 id_,
                 namespace.created_time,
-                Literal(datetime.fromtimestamp(asset.created_time / 1000, pytz.utc)),
+                Literal(datetime.fromtimestamp(asset.created_time / 1000, timezone.utc)),
             )
         )
         triples.append(
             (
                 id_,
                 namespace.last_updated_time,
-                Literal(datetime.fromtimestamp(asset.last_updated_time / 1000, pytz.utc)),
+                Literal(datetime.fromtimestamp(asset.last_updated_time / 1000, timezone.utc)),
             )
         )
 
@@ -87,7 +86,7 @@ class AssetsExtractor(BaseExtractor):
             for label in asset.labels:
                 # external_id can create ill-formed URIs, so we create websafe URIs
                 # since labels do not have internal ids, we use the external_id as the id
-                triples.append((id_, namespace.label, namespace[quote(label.dump()["externalId"])]))
+                triples.append((id_, namespace.label, namespace[f"Label_{quote(label.dump()['externalId'])}"]))
 
         if asset.metadata:
             for key, value in asset.metadata.items():
@@ -96,12 +95,12 @@ class AssetsExtractor(BaseExtractor):
 
         # Create connections:
         if asset.parent_id:
-            triples.append((id_, namespace.parent, namespace[str(asset.parent_id)]))
+            triples.append((id_, namespace.parent, namespace[f"Asset_{asset.parent_id}"]))
 
         if asset.root_id:
-            triples.append((id_, namespace.root, namespace[str(asset.root_id)]))
+            triples.append((id_, namespace.root, namespace[f"Asset_{asset.root_id}"]))
 
         if asset.data_set_id:
-            triples.append((id_, namespace.dataset, namespace[str(asset.data_set_id)]))
+            triples.append((id_, namespace.dataset, namespace[f"Dataset_{asset.data_set_id}"]))
 
         return triples

{cognite_neat-0.80.3 → cognite_neat-0.81.1}/cognite/neat/graph/extractors/_classic_cdf/_events.py

@@ -1,9 +1,8 @@
 from collections.abc import Iterable
-from datetime import datetime
+from datetime import datetime, timezone
 from pathlib import Path
 from typing import cast
 
-import pytz
 from cognite.client import CogniteClient
 from cognite.client.data_classes import Event, EventList
 from pydantic import AnyHttpUrl, ValidationError
@@ -44,7 +43,7 @@ class EventsExtractor(BaseExtractor):
 
     @classmethod
     def _event2triples(cls, event: Event, namespace: Namespace) -> list[Triple]:
-        id_ = namespace[str(event.id)]
+        id_ = namespace[f"Event_{event.id}"]
 
         # Set rdf type
         triples: list[Triple] = [(id_, RDF.type, namespace.Event)]
@@ -77,7 +76,7 @@ class EventsExtractor(BaseExtractor):
 
         if event.created_time:
             triples.append(
-                (id_, namespace.created_time, Literal(datetime.fromtimestamp(event.created_time / 1000, pytz.utc)))
+                (id_, namespace.created_time, Literal(datetime.fromtimestamp(event.created_time / 1000, timezone.utc)))
             )
 
         if event.last_updated_time:
@@ -85,7 +84,7 @@ class EventsExtractor(BaseExtractor):
                 (
                     id_,
                     namespace.last_updated_time,
-                    Literal(datetime.fromtimestamp(event.last_updated_time / 1000, pytz.utc)),
+                    Literal(datetime.fromtimestamp(event.last_updated_time / 1000, timezone.utc)),
                 )
             )
 
@@ -94,7 +93,7 @@ class EventsExtractor(BaseExtractor):
                 (
                     id_,
                     namespace.start_time,
-                    Literal(datetime.fromtimestamp(event.start_time / 1000, pytz.utc)),
+                    Literal(datetime.fromtimestamp(event.start_time / 1000, timezone.utc)),
                 )
             )
 
@@ -103,15 +102,15 @@ class EventsExtractor(BaseExtractor):
                 (
                     id_,
                     namespace.end_time,
-                    Literal(datetime.fromtimestamp(event.end_time / 1000, pytz.utc)),
+                    Literal(datetime.fromtimestamp(event.end_time / 1000, timezone.utc)),
                 )
             )
 
         if event.data_set_id:
-            triples.append((id_, namespace.data_set_id, namespace[str(event.data_set_id)]))
+            triples.append((id_, namespace.data_set_id, namespace[f"Dataset_{event.data_set_id}"]))
 
         if event.asset_ids:
             for asset_id in event.asset_ids:
-                triples.append((id_, namespace.asset, namespace[str(asset_id)]))
+                triples.append((id_, namespace.asset, namespace[f"Asset_{asset_id}"]))
 
         return triples

{cognite_neat-0.80.3 → cognite_neat-0.81.1}/cognite/neat/graph/extractors/_classic_cdf/_files.py

@@ -1,10 +1,9 @@
 from collections.abc import Iterable
-from datetime import datetime
+from datetime import datetime, timezone
 from pathlib import Path
 from typing import cast
 from urllib.parse import quote
 
-import pytz
 from cognite.client import CogniteClient
 from cognite.client.data_classes import FileMetadata, FileMetadataList
 from pydantic import AnyHttpUrl, ValidationError
@@ -45,7 +44,7 @@ class FilesExtractor(BaseExtractor):
 
     @classmethod
     def _file2triples(cls, file: FileMetadata, namespace: Namespace) -> list[Triple]:
-        id_ = namespace[str(file.id)]
+        id_ = namespace[f"File_{file.id}"]
 
         # Set rdf type
         triples: list[Triple] = [(id_, RDF.type, namespace.File)]
@@ -81,7 +80,7 @@ class FilesExtractor(BaseExtractor):
                 (
                     id_,
                     namespace.source_created_time,
-                    Literal(datetime.fromtimestamp(file.source_created_time / 1000, pytz.utc)),
+                    Literal(datetime.fromtimestamp(file.source_created_time / 1000, timezone.utc)),
                 )
             )
         if file.source_modified_time:
@@ -89,17 +88,17 @@ class FilesExtractor(BaseExtractor):
                 (
                     id_,
                     namespace.source_created_time,
-                    Literal(datetime.fromtimestamp(file.source_modified_time / 1000, pytz.utc)),
+                    Literal(datetime.fromtimestamp(file.source_modified_time / 1000, timezone.utc)),
                 )
             )
         if file.uploaded_time:
             triples.append(
-                (id_, namespace.uploaded_time, Literal(datetime.fromtimestamp(file.uploaded_time / 1000, pytz.utc)))
+                (id_, namespace.uploaded_time, Literal(datetime.fromtimestamp(file.uploaded_time / 1000, timezone.utc)))
             )
 
         if file.created_time:
             triples.append(
-                (id_, namespace.created_time, Literal(datetime.fromtimestamp(file.created_time / 1000, pytz.utc)))
+                (id_, namespace.created_time, Literal(datetime.fromtimestamp(file.created_time / 1000, timezone.utc)))
             )
 
         if file.last_updated_time:
@@ -107,7 +106,7 @@ class FilesExtractor(BaseExtractor):
                 (
                     id_,
                     namespace.last_updated_time,
-                    Literal(datetime.fromtimestamp(file.last_updated_time / 1000, pytz.utc)),
+                    Literal(datetime.fromtimestamp(file.last_updated_time / 1000, timezone.utc)),
                 )
             )
 
@@ -115,17 +114,17 @@ class FilesExtractor(BaseExtractor):
             for label in file.labels:
                 # external_id can create ill-formed URIs, so we create websafe URIs
                 # since labels do not have internal ids, we use the external_id as the id
-                triples.append((id_, namespace.label, namespace[quote(label.dump()["externalId"])]))
+                triples.append((id_, namespace.label, namespace[f"Label_{quote(label.dump()['externalId'])}"]))
 
         if file.security_categories:
             for category in file.security_categories:
                 triples.append((id_, namespace.security_categories, Literal(category)))
 
         if file.data_set_id:
-            triples.append((id_, namespace.data_set_id, namespace[str(file.data_set_id)]))
+            triples.append((id_, namespace.data_set_id, namespace[f"Dataset_{file.data_set_id}"]))
 
         if file.asset_ids:
             for asset_id in file.asset_ids:
-                triples.append((id_, namespace.asset, namespace[str(asset_id)]))
+                triples.append((id_, namespace.asset, namespace[f"Asset_{asset_id}"]))
 
         return triples

{cognite_neat-0.80.3 → cognite_neat-0.81.1}/cognite/neat/graph/extractors/_classic_cdf/_labels.py

@@ -1,10 +1,9 @@
 from collections.abc import Iterable
-from datetime import datetime
+from datetime import datetime, timezone
 from pathlib import Path
 from typing import cast
 from urllib.parse import quote
 
-import pytz
 from cognite.client import CogniteClient
 from cognite.client.data_classes import LabelDefinition, LabelDefinitionList
 from rdflib import RDF, Literal, Namespace
@@ -45,7 +44,7 @@ class LabelsExtractor(BaseExtractor):
 
     @classmethod
     def _labels2triples(cls, label: LabelDefinition, namespace: Namespace) -> list[Triple]:
-        id_ = namespace[quote(cast(str, label.external_id))]
+        id_ = namespace[f"Label_{quote(label.dump()['externalId'])}"]
 
         # Set rdf type
         triples: list[Triple] = [(id_, RDF.type, namespace.Label)]
@@ -63,10 +62,10 @@ class LabelsExtractor(BaseExtractor):
 
         if label.created_time:
             triples.append(
-                (id_, namespace.created_time, Literal(datetime.fromtimestamp(label.created_time / 1000, pytz.utc)))
+                (id_, namespace.created_time, Literal(datetime.fromtimestamp(label.created_time / 1000, timezone.utc)))
             )
 
         if label.data_set_id:
-            triples.append((id_, namespace.data_set_id, namespace[str(label.data_set_id)]))
+            triples.append((id_, namespace.data_set_id, namespace[f"Dataset_{label.data_set_id}"]))
 
         return triples

{cognite_neat-0.80.3 → cognite_neat-0.81.1}/cognite/neat/graph/extractors/_classic_cdf/_relationships.py

@@ -1,11 +1,10 @@
 import uuid
 from collections.abc import Iterable
-from datetime import datetime
+from datetime import datetime, timezone
 from pathlib import Path
 from typing import cast
 from urllib.parse import quote
 
-import pytz
 from cognite.client import CogniteClient
 from cognite.client.data_classes import Relationship, RelationshipList
 from rdflib import RDF, Literal, Namespace
@@ -49,27 +48,27 @@ class RelationshipsExtractor(BaseExtractor):
         """Converts an asset to triples."""
 
         # relationships do not have an internal id, so we generate one
-        id_ = namespace[str(uuid.uuid4())]
+        id_ = namespace[f"Relationship_{uuid.uuid4()}"]
 
         # Set rdf type
         triples: list[Triple] = [(id_, RDF.type, namespace["Relationship"])]
 
         # Set source and target types
-        if relationship.source_type:
+        if source_type := relationship.source_type:
             triples.append(
                 (
                     id_,
                     namespace.source_type,
-                    namespace[relationship.source_type.title()],
+                    namespace[source_type.title()],
                 )
             )
 
-        if relationship.target_type:
+        if target_type := relationship.target_type:
             triples.append(
                 (
                     id_,
                     namespace.target_type,
-                    namespace[relationship.target_type.title()],
+                    namespace[target_type.title()],
                 )
             )
 
@@ -100,7 +99,7 @@ class RelationshipsExtractor(BaseExtractor):
                 (
                     id_,
                     namespace.start_time,
-                    Literal(datetime.fromtimestamp(relationship.start_time / 1000, pytz.utc)),
+                    Literal(datetime.fromtimestamp(relationship.start_time / 1000, timezone.utc)),
                 )
             )
 
@@ -109,7 +108,7 @@ class RelationshipsExtractor(BaseExtractor):
                 (
                     id_,
                     namespace.end_time,
-                    Literal(datetime.fromtimestamp(relationship.end_time / 1000, pytz.utc)),
+                    Literal(datetime.fromtimestamp(relationship.end_time / 1000, timezone.utc)),
                 )
             )
 
@@ -118,7 +117,7 @@ class RelationshipsExtractor(BaseExtractor):
                 (
                     id_,
                     namespace.created_time,
-                    Literal(datetime.fromtimestamp(relationship.created_time / 1000, pytz.utc)),
+                    Literal(datetime.fromtimestamp(relationship.created_time / 1000, timezone.utc)),
                 )
             )
 
@@ -127,7 +126,7 @@ class RelationshipsExtractor(BaseExtractor):
                 (
                     id_,
                     namespace.last_updated_time,
-                    Literal(datetime.fromtimestamp(relationship.last_updated_time / 1000, pytz.utc)),
+                    Literal(datetime.fromtimestamp(relationship.last_updated_time / 1000, timezone.utc)),
                 )
             )
 
@@ -144,10 +143,10 @@ class RelationshipsExtractor(BaseExtractor):
             for label in relationship.labels:
                 # external_id can create ill-formed URIs, so we create websafe URIs
                 # since labels do not have internal ids, we use the external_id as the id
-                triples.append((id_, namespace.label, namespace[quote(label.dump()["externalId"])]))
+                triples.append((id_, namespace.label, namespace[f"Label_{quote(label.dump()['externalId'])}"]))
 
         # Create connection
         if relationship.data_set_id:
-            triples.append((id_, namespace.dataset, namespace[str(relationship.data_set_id)]))
+            triples.append((id_, namespace.dataset, namespace[f"Dataset_{relationship.data_set_id}"]))
 
         return triples

{cognite_neat-0.80.3 → cognite_neat-0.81.1}/cognite/neat/graph/extractors/_classic_cdf/_sequences.py

@@ -1,9 +1,8 @@
 from collections.abc import Iterable
-from datetime import datetime
+from datetime import datetime, timezone
 from pathlib import Path
 from typing import cast
 
-import pytz
 from cognite.client import CogniteClient
 from cognite.client.data_classes import Sequence, SequenceList
 from pydantic import AnyHttpUrl, ValidationError
@@ -44,7 +43,7 @@ class SequencesExtractor(BaseExtractor):
 
     @classmethod
     def _sequence2triples(cls, sequence: Sequence, namespace: Namespace) -> list[Triple]:
-        id_ = namespace[str(sequence.id)]
+        id_ = namespace[f"Sequence_{sequence.id}"]
 
         # Set rdf type
         triples: list[Triple] = [(id_, RDF.type, namespace.Sequence)]
@@ -71,7 +70,11 @@ class SequencesExtractor(BaseExtractor):
 
         if sequence.created_time:
             triples.append(
-                (id_, namespace.created_time, Literal(datetime.fromtimestamp(sequence.created_time / 1000, pytz.utc)))
+                (
+                    id_,
+                    namespace.created_time,
+                    Literal(datetime.fromtimestamp(sequence.created_time / 1000, timezone.utc)),
+                )
             )
 
         if sequence.last_updated_time:
@@ -79,14 +82,14 @@ class SequencesExtractor(BaseExtractor):
                 (
                     id_,
                     namespace.last_updated_time,
-                    Literal(datetime.fromtimestamp(sequence.last_updated_time / 1000, pytz.utc)),
+                    Literal(datetime.fromtimestamp(sequence.last_updated_time / 1000, timezone.utc)),
                 )
             )
 
         if sequence.data_set_id:
-            triples.append((id_, namespace.data_set_id, namespace[str(sequence.data_set_id)]))
+            triples.append((id_, namespace.data_set_id, namespace[f"Dataset_{sequence.data_set_id}"]))
 
         if sequence.asset_id:
-            triples.append((id_, namespace.asset, namespace[str(sequence.asset_id)]))
+            triples.append((id_, namespace.asset, namespace[f"Asset_{sequence.asset_id}"]))
 
         return triples

{cognite_neat-0.80.3 → cognite_neat-0.81.1}/cognite/neat/graph/extractors/_classic_cdf/_timeseries.py

@@ -1,9 +1,8 @@
 from collections.abc import Iterable
-from datetime import datetime
+from datetime import datetime, timezone
 from pathlib import Path
 from typing import cast
 
-import pytz
 from cognite.client import CogniteClient
 from cognite.client.data_classes import TimeSeries, TimeSeriesList
 from pydantic import AnyHttpUrl, ValidationError
@@ -46,7 +45,7 @@ class TimeSeriesExtractor(BaseExtractor):
 
     @classmethod
     def _timeseries2triples(cls, timeseries: TimeSeries, namespace: Namespace) -> list[Triple]:
-        id_ = namespace[str(timeseries.id)]
+        id_ = namespace[f"TimeSeries_{timeseries.id}"]
 
         # Set rdf type
         triples: list[Triple] = [(id_, RDF.type, namespace.TimeSeries)]
@@ -86,7 +85,11 @@ class TimeSeriesExtractor(BaseExtractor):
 
         if timeseries.created_time:
             triples.append(
-                (id_, namespace.created_time, Literal(datetime.fromtimestamp(timeseries.created_time / 1000, pytz.utc)))
+                (
+                    id_,
+                    namespace.created_time,
+                    Literal(datetime.fromtimestamp(timeseries.created_time / 1000, timezone.utc)),
+                )
             )
 
         if timeseries.last_updated_time:
@@ -94,7 +97,7 @@ class TimeSeriesExtractor(BaseExtractor):
                 (
                     id_,
                     namespace.last_updated_time,
-                    Literal(datetime.fromtimestamp(timeseries.last_updated_time / 1000, pytz.utc)),
+                    Literal(datetime.fromtimestamp(timeseries.last_updated_time / 1000, timezone.utc)),
                 )
             )
 
@@ -110,9 +113,9 @@ class TimeSeriesExtractor(BaseExtractor):
                 triples.append((id_, namespace.unit_external_id, Literal(timeseries.unit_external_id)))
 
         if timeseries.data_set_id:
-            triples.append((id_, namespace.dataset, namespace[str(timeseries.data_set_id)]))
+            triples.append((id_, namespace.dataset, namespace[f"Dataset_{timeseries.data_set_id}"]))
 
         if timeseries.asset_id:
-            triples.append((id_, namespace.asset, namespace[str(timeseries.asset_id)]))
+            triples.append((id_, namespace.asset, namespace[f"Asset_{timeseries.asset_id}"]))
 
         return triples