cognite-neat 0.119.1__py3-none-any.whl → 0.119.3__py3-none-any.whl

cognite/neat/_constants.py

@@ -65,76 +65,40 @@ COGNITE_SPACES = frozenset(
     }
 )
 
-COGNITE_CORE_CONCEPTS = frozenset(
-    {
-        "CogniteFile",
-        "CogniteCubeMap",
-        "CogniteCADRevision",
-        "CognitePointCloudVolume",
-        "Cognite360ImageAnnotation",
-        "CogniteAnnotation",
-        "CogniteUnit",
-        "CogniteAsset",
-        "Cognite3DObject",
-        "Cognite3DRevision",
-        "Cognite360Image",
-        "CogniteDiagramAnnotation",
-        "Cognite360ImageCollection",
-        "Cognite360ImageStation",
-        "CognitePointCloudModel",
-        "CogniteTimeSeries",
-        "Cognite3DTransformation",
-        "CogniteEquipment",
-        "Cognite360ImageModel",
-        "CogniteAssetClass",
-        "CogniteAssetType",
-        "CogniteEquipmentType",
-        "Cognite3DModel",
-        "CogniteCADModel",
-        "CognitePointCloudRevision",
-        "CogniteCADNode",
-        "CogniteFileCategory",
-        "CogniteActivity",
-    }
-)
-
-
-COGNITE_CORE_FEATURES = frozenset(
-    {
-        "CogniteDescribable",
-        "CogniteSourceable",
-        "CogniteSourceSystem",
-        "CogniteSchedulable",
-        "CogniteVisualizable",
-    }
-)
-
-COGNITE_3D_CONCEPTS = frozenset(
-    {
-        "Cognite3DModel",
-        "Cognite3DObject",
-        "Cognite3DRevision",
-        "Cognite3DTransformation",
-        "Cognite360Image",
-        "Cognite360ImageAnnotation",
-        "Cognite360ImageCollection",
-        "Cognite360ImageModel",
-        "Cognite360ImageStation",
-        "CogniteCADModel",
-        "CogniteCADNode",
-        "CogniteCADRevision",
-        "CogniteCubeMap",
-        "CognitePointCloudModel",
-        "CognitePointCloudRevision",
-        "CognitePointCloudVolume",
-    }
-)
-
-COGNITE_ANNOTATION = frozenset(
-    {
-        "CogniteAnnotation",
-        "CogniteDiagramAnnotation",
-    }
+COGNITE_CONCEPTS = (
+    "CogniteAsset",
+    "CogniteEquipment",
+    "CogniteActivity",
+    "CogniteTimeSeries",
+    "CogniteFile",
+    "CogniteUnit",
+    "CogniteAssetClass",
+    "CogniteAssetType",
+    "CogniteEquipmentType",
+    "CogniteFileCategory",
+    "CogniteDescribable",
+    "CogniteSourceable",
+    "CogniteSourceSystem",
+    "CogniteSchedulable",
+    "CogniteVisualizable",
+    "CogniteAnnotation",
+    "CogniteDiagramAnnotation",
+    "CogniteCubeMap",
+    "CogniteCADRevision",
+    "CognitePointCloudVolume",
+    "Cognite360ImageAnnotation",
+    "Cognite3DObject",
+    "Cognite3DRevision",
+    "Cognite360Image",
+    "Cognite360ImageCollection",
+    "Cognite360ImageStation",
+    "CognitePointCloudModel",
+    "Cognite3DTransformation",
+    "Cognite360ImageModel",
+    "Cognite3DModel",
+    "CogniteCADModel",
+    "CognitePointCloudRevision",
+    "CogniteCADNode",
 )
 
 DMS_LISTABLE_PROPERTY_LIMIT = 1000

cognite/neat/_graph/extractors/__init__.py

@@ -10,11 +10,9 @@ 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 ._dict import DictExtractor
 from ._dms import DMSExtractor
 from ._dms_graph import DMSGraphExtractor
-from ._iodd import IODDExtractor
 from ._mock_graph_generator import MockGraphGenerator
 from ._raw import RAWExtractor
 from ._rdf_file import RdfFileExtractor
@@ -26,11 +24,9 @@ __all__ = [
     "DMSExtractor",
     "DMSGraphExtractor",
     "DataSetExtractor",
-    "DexpiExtractor",
     "DictExtractor",
     "EventsExtractor",
     "FilesExtractor",
-    "IODDExtractor",
     "KnowledgeGraphExtractor",
     "LabelsExtractor",
     "MockGraphGenerator",
@@ -52,8 +48,6 @@ TripleExtractors = (
     | FilesExtractor
     | LabelsExtractor
     | RdfFileExtractor
-    | DexpiExtractor
-    | IODDExtractor
     | DMSExtractor
     | ClassicGraphExtractor
     | DataSetExtractor

cognite/neat/_graph/loaders/_rdf2dms.py

@@ -259,7 +259,7 @@ class DMSLoader(CDFLoader[dm.InstanceApply]):
         """Selects the views with data."""
         view_iterations: dict[dm.ViewId, _ViewIterator] = {}
         for view_id, query in view_query_by_id.items():
-            count = self.graph_store.queries.count_of_type(query.rdf_type)
+            count = self.graph_store.queries.select.count_of_type(query.rdf_type)
             if count > 0:
                 view_iterations[view_id] = _ViewIterator(view_id, count, query)
         return view_iterations
@@ -269,7 +269,7 @@ class DMSLoader(CDFLoader[dm.InstanceApply]):
         if self._space_property is None:
             return issues
         total = sum(it.instance_count for it in view_iterations)
-        properties_by_uriref = self.graph_store.queries.properties()
+        properties_by_uriref = self.graph_store.queries.select.properties()
         space_property_uri = next((k for k, v in properties_by_uriref.items() if v == self._space_property), None)
         if space_property_uri is None:
             error: ResourceNotFoundError[str, str] = ResourceNotFoundError(
@@ -282,7 +282,7 @@ class DMSLoader(CDFLoader[dm.InstanceApply]):
             issues.append(error)
             return issues
 
-        instance_iterable = self.graph_store.queries.list_instances_ids_by_space(space_property_uri)
+        instance_iterable = self.graph_store.queries.select.list_instances_ids_by_space(space_property_uri)
         instance_iterable = iterate_progress_bar_if_above_config_threshold(
             instance_iterable, total, f"Looking up spaces for {total} instances..."
         )
@@ -308,8 +308,8 @@ class DMSLoader(CDFLoader[dm.InstanceApply]):
         if not self.neat_prefix_by_type_uri:
             return
 
-        count = sum(count for _, count in self.graph_store.queries.summarize_instances())
-        instance_iterable = self.graph_store.queries.list_instances_ids()
+        count = sum(count for _, count in self.graph_store.queries.select.summarize_instances())
+        instance_iterable = self.graph_store.queries.select.list_instances_ids()
         instance_iterable = iterate_progress_bar_if_above_config_threshold(
             instance_iterable, count, f"Looking up identifiers for {count} instances..."
         )

cognite/neat/_graph/queries/__init__.py

@@ -1,3 +1,3 @@
-from ._base import Queries
+from ._queries import Queries
 
 __all__ = ["Queries"]

cognite/neat/_graph/queries/_base.py

@@ -1,21 +1,8 @@
-import urllib.parse
-from collections import defaultdict
-from collections.abc import Iterable
-from typing import Any, Literal, cast, overload
-
-from rdflib import RDF, XSD, Dataset, Graph, Namespace, URIRef
-from rdflib import Literal as RdfLiteral
+from rdflib import Dataset, Graph, URIRef
 from rdflib.graph import DATASET_DEFAULT_GRAPH_ID
-from rdflib.query import ResultRow
-
-from cognite.neat._constants import NEAT
-from cognite.neat._shared import InstanceType
-from cognite.neat._utils.rdf_ import remove_instance_ids_in_batch, remove_namespace_from_uri
-
 
-class Queries:
-    """Helper class for storing standard queries for the graph store."""
 
+class BaseQuery:
     def __init__(
         self,
         dataset: Dataset,
@@ -27,444 +14,3 @@ class Queries:
     def graph(self, named_graph: URIRef | None = None) -> Graph:
         """Get named graph from the dataset to query over"""
         return self.dataset.graph(named_graph or self.default_named_graph)
-
-    def summarize_instances(self, named_graph: URIRef | None = None) -> list[tuple[str, int]]:
-        """Summarize instances in the graph store by class and count"""
-        query_statement = """ SELECT ?class (COUNT(?instance) AS ?instanceCount)
-                             WHERE {
-                             ?instance a ?class .
-                             }
-                             GROUP BY ?class
-                             ORDER BY DESC(?instanceCount) """
-
-        return [  # type: ignore[misc]
-            (
-                remove_namespace_from_uri(cast(URIRef, class_)),
-                cast(RdfLiteral, count).value,
-            )
-            for class_, count in self.graph(named_graph=named_graph).query(query_statement)
-        ]
-
-    def types(self, named_graph: URIRef | None = None) -> dict[URIRef, str]:
-        """Types and their short form in the graph"""
-        query = """SELECT DISTINCT ?type
-                   WHERE {?s a ?type .}"""
-
-        return {  # type: ignore[misc, index, arg-type]
-            cast(URIRef, type_): remove_namespace_from_uri(cast(URIRef, type_))
-            for (type_,) in list(self.graph(named_graph).query(query))
-        }
-
-    def type_uri(self, type_: str, named_graph: URIRef | None = None) -> list[URIRef]:
-        """Get the URIRef of a type"""
-        return [k for k, v in self.types(named_graph).items() if v == type_]
-
-    def properties(self, named_graph: URIRef | None = None) -> dict[URIRef, str]:
-        """Properties and their short form in the graph
-
-        Args:
-            named_graph: Named graph to query over, default None (default graph)
-
-        """
-        query = """SELECT DISTINCT ?property
-               WHERE {?s ?property ?o . FILTER(?property != rdf:type)}"""
-        return {  # type: ignore[misc, index, arg-type]
-            cast(URIRef, type_): remove_namespace_from_uri(cast(URIRef, type_))
-            for (type_,) in list(self.graph(named_graph).query(query))
-        }
-
-    def properties_by_type(self, named_graph: URIRef | None = None) -> dict[URIRef, dict[URIRef, str]]:
-        """Properties and their short form in the graph by type
-
-        Args:
-            named_graph: Named graph to query over, default None (default graph)
-
-        """
-        query = """SELECT DISTINCT ?type ?property
-               WHERE {?s a ?type . ?s ?property ?o . FILTER(?property != rdf:type)}"""
-        properties_by_type: dict[URIRef, dict[URIRef, str]] = defaultdict(dict)
-        for type_, property_ in cast(ResultRow, list(self.graph(named_graph).query(query))):
-            properties_by_type[type_][property_] = remove_namespace_from_uri(property_)  # type: ignore[index]
-        return properties_by_type
-
-    def property_uri(self, property_: str, named_graph: URIRef | None = None) -> list[URIRef]:
-        """Get the URIRef of a property
-
-        Args:
-            property_: Property to find URIRef for
-            named_graph: Named graph to query over, default None (default graph)
-        """
-        return [k for k, v in self.properties(named_graph).items() if v == property_]
-
-    @overload
-    def list_instances_ids(
-        self, class_uri: None = None, limit: int = -1, named_graph: URIRef | None = None
-    ) -> Iterable[tuple[URIRef, URIRef]]: ...
-
-    @overload
-    def list_instances_ids(
-        self, class_uri: URIRef, limit: int = -1, named_graph: URIRef | None = None
-    ) -> Iterable[URIRef]: ...
-
-    def list_instances_ids(
-        self, class_uri: URIRef | None = None, limit: int = -1, named_graph: URIRef | None = None
-    ) -> Iterable[URIRef] | Iterable[tuple[URIRef, URIRef]]:
-        """List all instance IDs
-
-        Args:
-            class_uri: Class for which instances are to be found, default None (all instances)
-            limit: Max number of instances to return, by default -1 meaning all instances
-            named_graph: Named graph to query over, default None (default graph)
-
-        Returns:
-            List of class instance URIs
-        """
-        query = "SELECT DISTINCT ?subject"
-        if class_uri:
-            query += f" WHERE {{ ?subject a <{class_uri}> .}}"
-        else:
-            query += " ?type WHERE {{ ?subject a ?type .}}"
-        if limit != -1:
-            query += f" LIMIT {limit}"
-        # MyPy is not very happy with RDFLib, so just ignore the type hinting here
-        return (tuple(res) if class_uri is None else res[0] for res in self.graph(named_graph).query(query))  # type: ignore[index, return-value, arg-type]
-
-    def type_with_property(self, type_: URIRef, property_uri: URIRef, named_graph: URIRef | None = None) -> bool:
-        """Check if a property exists in the graph store
-
-        Args:
-            type_: Type URI to check
-            property_uri: Property URI to check
-            named_graph: Named graph to query over, default None (default graph)
-
-        Returns:
-            True if property exists, False otherwise
-        """
-        query = f"SELECT ?o WHERE {{ ?s a <{type_}> ; <{property_uri}> ?o .}} Limit 1"
-        return bool(list(self.graph(named_graph).query(query)))
-
-    def has_namespace(self, namespace: Namespace, named_graph: URIRef | None = None) -> bool:
-        """Check if a namespace exists in the graph store
-
-        Args:
-            namespace: Namespace to check
-            named_graph: Named graph to query over, default None (default graph)
-
-        Returns:
-            True if namespace exists, False otherwise
-        """
-        query = f"ASK WHERE {{ ?s ?p ?o . FILTER(STRSTARTS(STR(?p), STR(<{namespace}>))) }}"
-        return bool(self.graph(named_graph).query(query))
-
-    def has_data(self) -> bool:
-        """Check if the graph store has data"""
-        return cast(bool, next(iter(self.dataset.query("ASK WHERE { ?s ?p ?o }"))))
-
-    def has_type(self, type_: URIRef, named_graph: URIRef | None = None) -> bool:
-        """Check if a type exists in the graph store
-
-        Args:
-            type_: Type to check
-            named_graph: Named graph to query over, default None (default graph)
-
-        Returns:
-            True if type exists, False otherwise
-        """
-        query = f"ASK WHERE {{ ?s a <{type_}> }}"
-        return bool(self.graph(named_graph).query(query))
-
-    def describe(
-        self,
-        instance_id: URIRef,
-        instance_type: URIRef | None = None,
-        property_renaming_config: dict | None = None,
-        named_graph: URIRef | None = None,
-        remove_uri_namespace: bool = True,
-    ) -> tuple[URIRef, dict[str | InstanceType, list[Any]]] | None:
-        """DESCRIBE instance for a given class from the graph store
-
-        Args:
-            instance_id: Instance id for which we want to generate query
-            instance_type: Type of the instance, default None (will be inferred from triples)
-            property_renaming_config: Dictionary to rename properties, default None (no renaming)
-            named_graph: Named graph to query over, default None (default graph)
-            remove_uri_namespace: Whether to remove the namespace from the URI, by default True
-
-
-        Returns:
-            Dictionary of instance properties
-        """
-        property_values: dict[str, list[str] | list[URIRef]] = defaultdict(list)
-        for _, predicate, object_ in cast(list[ResultRow], self.graph(named_graph).query(f"DESCRIBE <{instance_id}>")):
-            if object_.lower() in [
-                "",
-                "none",
-                "nan",
-                "null",
-            ]:
-                continue
-
-            # set property
-            if property_renaming_config and predicate != RDF.type:
-                property_ = remove_namespace_from_uri(predicate, validation="prefix")
-                renamed_property_ = property_renaming_config.get(predicate, property_)
-
-            elif not property_renaming_config and predicate != RDF.type:
-                property_ = remove_namespace_from_uri(predicate, validation="prefix")
-                renamed_property_ = property_
-
-            else:
-                property_ = RDF.type
-                renamed_property_ = property_
-
-            value: Any
-            if isinstance(object_, URIRef) and remove_uri_namespace:
-                # These properties contain the space in the Namespace.
-                value = remove_namespace_from_uri(object_, validation="prefix")
-            elif isinstance(object_, URIRef):
-                value = object_
-            elif isinstance(object_, RdfLiteral):
-                if object_.datatype == XSD._NS["json"]:
-                    # For JSON literals, the .toPython() returns a Literal object.
-                    value = str(object_)
-                else:
-                    value = object_.toPython()
-            else:
-                # It is a blank node
-                value = str(object_)
-
-            # add type to the dictionary
-            if predicate != RDF.type:
-                property_values[renamed_property_].append(value)  # type: ignore[arg-type]
-            else:
-                # guarding against multiple rdf:type values as this is not allowed in CDF
-                if RDF.type not in property_values:
-                    property_values[RDF.type].append(
-                        remove_namespace_from_uri(instance_type, validation="prefix") if instance_type else value  # type: ignore[arg-type]
-                    )
-                else:
-                    # we should not have multiple rdf:type values
-                    continue
-        if property_values:
-            return (
-                instance_id,
-                property_values,
-            )
-        else:
-            return None
-
-    def list_triples(self, limit: int = 25, named_graph: URIRef | None = None) -> list[ResultRow]:
-        """List triples in the graph store
-
-        Args:
-            limit: Max number of triples to return, by default 25
-            named_graph: Named graph to query over, default None (default graph)
-
-        Returns:
-            List of triples
-        """
-        query = f"SELECT ?subject ?predicate ?object WHERE {{ ?subject ?predicate ?object }} LIMIT {limit}"
-        return cast(list[ResultRow], list(self.graph(named_graph).query(query)))
-
-    @overload
-    def list_types(self, remove_namespace: Literal[False] = False, limit: int = 25) -> list[ResultRow]: ...
-
-    @overload
-    def list_types(
-        self,
-        remove_namespace: Literal[True],
-        limit: int = 25,
-        named_graph: URIRef | None = None,
-    ) -> list[str]: ...
-
-    def list_types(
-        self,
-        remove_namespace: bool = False,
-        limit: int | None = 25,
-        named_graph: URIRef | None = None,
-    ) -> list[ResultRow] | list[str]:
-        """List types in the graph store
-
-        Args:
-            limit: Max number of types to return, by default 25
-            remove_namespace: Whether to remove the namespace from the type, by default False
-
-        Returns:
-            List of types
-        """
-        query = "SELECT DISTINCT ?type WHERE { ?subject a ?type }"
-        if limit is not None:
-            query += f" LIMIT {limit}"
-        result = cast(list[ResultRow], list(self.graph(named_graph).query(query)))
-        if remove_namespace:
-            return [remove_namespace_from_uri(res[0]) for res in result]
-        return result
-
-    def multi_value_type_property(
-        self,
-        named_graph: URIRef | None = None,
-    ) -> Iterable[tuple[URIRef, URIRef, list[URIRef]]]:
-        query = """SELECT ?sourceType ?property
-                          (GROUP_CONCAT(DISTINCT STR(?valueType); SEPARATOR=",") AS ?valueTypes)
-
-                   WHERE {{
-                       ?s ?property ?o .
-                       ?s a ?sourceType .
-                       OPTIONAL {{ ?o a ?type }}
-
-                       # Key part to determine value type: either object, data or unknown
-                       BIND(   IF(isLiteral(?o),DATATYPE(?o),
-                               IF(BOUND(?type), ?type,
-                                               <{unknownType}>)) AS ?valueType)
-                   }}
-
-                   GROUP BY ?sourceType ?property
-                   HAVING (COUNT(DISTINCT ?valueType) > 1)"""
-
-        for (
-            source_type,
-            property_,
-            value_types,
-        ) in cast(
-            ResultRow,
-            self.graph(named_graph).query(query.format(unknownType=str(NEAT.UnknownType))),
-        ):
-            yield cast(URIRef, source_type), cast(URIRef, property_), [URIRef(uri) for uri in value_types.split(",")]
-
-    def drop_types(
-        self,
-        type_: list[URIRef],
-        named_graph: URIRef | None = None,
-    ) -> dict[URIRef, int]:
-        """Drop types from the graph store
-
-        Args:
-            type_: List of types to drop
-            named_graph: Named graph to query over, default None (default graph
-
-        Returns:
-            Dictionary of dropped types
-        """
-        dropped_types: dict[URIRef, int] = {}
-        for t in type_:
-            instance_ids = list(self.list_instances_ids(t))
-            dropped_types[t] = len(instance_ids)
-            remove_instance_ids_in_batch(self.graph(named_graph), instance_ids)
-        return dropped_types
-
-    def multi_type_instances(self, named_graph: URIRef | None = None) -> dict[str, list[str]]:
-        """Find instances with multiple types
-
-        Args:
-            named_graph: Named graph to query over, default None (default graph)
-
-        """
-
-        query = """
-        SELECT ?instance (GROUP_CONCAT(str(?type); SEPARATOR=",") AS ?types)
-        WHERE {
-            ?instance a ?type .
-        }
-        GROUP BY ?instance
-        HAVING (COUNT(?type) > 1)
-        """
-
-        result = {}
-        for instance, types in self.graph(named_graph).query(query):  # type: ignore
-            result[remove_namespace_from_uri(instance)] = remove_namespace_from_uri(types.split(","))
-
-        return result
-
-    def count_of_type(self, class_uri: URIRef, named_graph: URIRef | None = None) -> int:
-        query = f"SELECT (COUNT(?instance) AS ?instanceCount) WHERE {{ ?instance a <{class_uri}> }}"
-        return int(next(iter(self.graph(named_graph).query(query)))[0])  # type: ignore[arg-type, index]
-
-    def types_with_instance_and_property_count(
-        self, remove_namespace: bool = True, named_graph: URIRef | None = None
-    ) -> list[dict[str, Any]]:
-        query = """
-        SELECT ?type (COUNT(DISTINCT ?instance) AS ?instanceCount) (COUNT(DISTINCT ?property) AS ?propertyCount)
-                WHERE {
-                  ?instance a ?type .
-                  ?instance ?property ?value .
-                  FILTER(?property != rdf:type)
-                }
-                GROUP BY ?type
-                ORDER BY DESC(?instanceCount)"""
-        return [
-            {
-                "type": urllib.parse.unquote(remove_namespace_from_uri(type_)) if remove_namespace else type_,
-                "instanceCount": cast(RdfLiteral, instance_count).toPython(),
-                "propertyCount": cast(RdfLiteral, property_count).toPython(),
-            }
-            for type_, instance_count, property_count in list(
-                cast(list[ResultRow], self.graph(named_graph).query(query))
-            )
-        ]
-
-    def properties_with_count(
-        self, remove_namespace: bool = True, named_graph: URIRef | None = None
-    ) -> list[dict[str, Any]]:
-        instance_count_by_type = {
-            entry["type"]: entry["instanceCount"]
-            for entry in self.types_with_instance_and_property_count(remove_namespace=False, named_graph=named_graph)
-        }
-        query = """SELECT ?type ?property (COUNT(DISTINCT ?instance) AS ?instanceCount)
-WHERE {
-  ?instance a ?type .
-  ?instance ?property ?value .
-  FILTER(?property != rdf:type)
-}
-GROUP BY ?type ?property
-ORDER BY ASC(?type) ASC(?property)"""
-        return [
-            {
-                "type": urllib.parse.unquote(remove_namespace_from_uri(type_)) if remove_namespace else type_,
-                "property": urllib.parse.unquote(remove_namespace_from_uri(property)) if remove_namespace else property,
-                "instanceCount": cast(RdfLiteral, instance_count).toPython(),
-                "total": instance_count_by_type[type_],
-            }
-            for type_, property, instance_count in list(cast(list[ResultRow], self.graph(named_graph).query(query)))
-        ]
-
-    @overload
-    def instances_with_properties(
-        self, type: URIRef, remove_namespace: Literal[False], named_graph: URIRef | None = None
-    ) -> dict[URIRef, set[URIRef]]: ...
-
-    @overload
-    def instances_with_properties(
-        self, type: URIRef, remove_namespace: Literal[True], named_graph: URIRef | None = None
-    ) -> dict[str, set[str]]: ...
-
-    def instances_with_properties(
-        self, type: URIRef, remove_namespace: bool = True, named_graph: URIRef | None = None
-    ) -> dict[str, set[str]] | dict[URIRef, set[URIRef]]:
-        query = """SELECT DISTINCT ?instance ?property
-WHERE {{
-    ?instance a <{type}> .
-    ?instance ?property ?value .
-    FILTER(?property != rdf:type)
-}}"""
-        result = defaultdict(set)
-        for instance, property_ in cast(Iterable[ResultRow], self.graph(named_graph).query(query.format(type=type))):
-            instance_str = urllib.parse.unquote(remove_namespace_from_uri(instance)) if remove_namespace else instance
-            property_str = urllib.parse.unquote(remove_namespace_from_uri(property_)) if remove_namespace else property_
-            result[instance_str].add(property_str)
-        return result
-
-    def list_instances_ids_by_space(
-        self, space_property: URIRef, named_graph: URIRef | None = None
-    ) -> Iterable[tuple[URIRef, str]]:
-        """Returns instance ids by space"""
-        query = f"""SELECT DISTINCT ?instance ?space
-                   WHERE {{?instance <{space_property}> ?space}}"""
-
-        for result in cast(Iterable[ResultRow], self.graph(named_graph).query(query)):
-            instance_id, space = cast(tuple[URIRef, URIRef | RdfLiteral], result)
-            if isinstance(space, URIRef):
-                yield instance_id, remove_namespace_from_uri(space)
-            elif isinstance(space, RdfLiteral):
-                yield instance_id, str(space.toPython())
-            else:
-                yield instance_id, str(space)

cognite/neat/_graph/queries/_queries.py

@@ -0,0 +1,16 @@
+from rdflib import Dataset, URIRef
+
+from ._select import SelectQueries
+from ._update import UpdateQueries
+
+
+class Queries:
+    """Helper class for storing standard queries for the graph store."""
+
+    def __init__(
+        self,
+        dataset: Dataset,
+        default_named_graph: URIRef | None = None,
+    ) -> None:
+        self.select = SelectQueries(dataset, default_named_graph)
+        self.update = UpdateQueries(self.select, dataset, default_named_graph)