cognite-neat 0.111.1__py3-none-any.whl → 0.112.0__py3-none-any.whl

cognite/neat/_graph/extractors/_classic_cdf/_base.py

@@ -8,7 +8,7 @@ from abc import ABC, abstractmethod
 from collections.abc import Callable, Iterable, Sequence, Set
 from datetime import datetime, timezone
 from pathlib import Path
-from typing import Any, Generic, TypeVar
+from typing import Any, Generic, TypeVar, cast
 
 from cognite.client import CogniteClient
 from cognite.client.data_classes._base import WriteableCogniteResource
@@ -111,6 +111,8 @@ class ClassicCDFBaseExtractor(BaseExtractor, ABC, Generic[T_CogniteResource]):
         # Used by the ClassicGraphExtractor to log URIRefs
         self._log_urirefs = False
         self._uriref_by_external_id: dict[str, URIRef] = {}
+        self.asset_parent_uri_by_id: dict[int, URIRef] = {}
+        self.asset_parent_uri_by_external_id: dict[str, URIRef] = {}
 
     def extract(self) -> Iterable[Triple]:
         """Extracts an asset with the given asset_id."""
@@ -165,19 +167,36 @@ class ClassicCDFBaseExtractor(BaseExtractor, ABC, Generic[T_CogniteResource]):
             item = item.as_write()
         dumped = item.dump(self.camel_case)
         dumped.pop("id", None)
-        # We have parentId so we don't need parentExternalId
-        dumped.pop("parentExternalId", None)
+
         if "metadata" in dumped:
             triples.extend(self._metadata_to_triples(id_, dumped.pop("metadata")))
 
         triples.extend(self._item2triples_special_cases(id_, dumped))
 
+        parent_renaming = {"parent_external_id": "parent_id", "parentExternalId": "parentId"}
+        parent_key = set(parent_renaming.keys()) | set(parent_renaming.values())
+
         for key, value in dumped.items():
             if value is None or value == []:
                 continue
             values = value if isinstance(value, Sequence) and not isinstance(value, str) else [value]
             for raw in values:
-                triples.append((id_, self.namespace[key], self._as_object(raw, key)))
+                object_ = self._as_object(raw, key)
+                if object_ is None:
+                    continue
+                if key in parent_key:
+                    parent_id = cast(URIRef, object_)
+                    if isinstance(raw, str):
+                        self.asset_parent_uri_by_external_id[raw] = parent_id
+                    elif isinstance(raw, int):
+                        self.asset_parent_uri_by_id[raw] = parent_id
+                    # We add a triple to include the parent. This is such that for example the parent
+                    # externalID will remove the prefix when loading.
+                    triples.append((parent_id, RDF.type, self.namespace[self._get_rdf_type()]))
+                    # Parent external ID must be renamed to parent id to match the data model.
+                    key = parent_renaming.get(key, key)
+
+                triples.append((id_, self.namespace[key], object_))
         return triples
 
     def _item2triples_special_cases(self, id_: URIRef, dumped: dict[str, Any]) -> list[Triple]:
@@ -186,7 +205,7 @@ class ClassicCDFBaseExtractor(BaseExtractor, ABC, Generic[T_CogniteResource]):
 
     @classmethod
     def _external_id_as_uri_suffix(cls, external_id: str | None) -> str:
-        if external_id == "":
+        if external_id == "" or (isinstance(external_id, str) and external_id.strip() == ""):
             warnings.warn(NeatValueWarning(f"Empty external id in {cls._default_rdf_type}"), stacklevel=2)
             return "empty"
         elif external_id == "\x00":
@@ -223,7 +242,7 @@ class ClassicCDFBaseExtractor(BaseExtractor, ABC, Generic[T_CogniteResource]):
             type_ = f"{self.prefix}{type_}"
         return self._SPACE_PATTERN.sub("_", type_)
 
-    def _as_object(self, raw: Any, key: str) -> Literal | URIRef:
+    def _as_object(self, raw: Any, key: str) -> Literal | URIRef | None:
         """Return properly formatted object part of s-p-o triple"""
         if key in {"data_set_id", "dataSetId"}:
             if self.identifier == "externalId" and self.lookup_dataset_external_id:
@@ -237,13 +256,26 @@ class ClassicCDFBaseExtractor(BaseExtractor, ABC, Generic[T_CogniteResource]):
                     ]
             else:
                 return self.namespace[f"{InstanceIdPrefix.data_set}{raw}"]
-        elif key in {"assetId", "asset_id", "assetIds", "asset_ids", "parentId", "rootId", "parent_id", "root_id"}:
+        elif key in {"parentId", "parent_id", "parentExternalId", "parent_external_id"}:
+            if self.identifier == "id" and key in {"parent_id", "parentId"}:
+                return self.namespace[f"{InstanceIdPrefix.asset}{raw}"]
+            elif (
+                self.identifier == "externalId"
+                and key in {"parent_external_id", "parentExternalId"}
+                and isinstance(raw, str)
+            ):
+                return self.namespace[f"{InstanceIdPrefix.asset}{self._external_id_as_uri_suffix(raw)}"]
+            else:
+                # Skip it
+                return None
+        elif key in {"assetId", "asset_id", "assetIds", "asset_ids", "rootId", "root_id"}:
             if self.identifier == "id":
                 return self.namespace[f"{InstanceIdPrefix.asset}{raw}"]
             else:
                 try:
                     asset_external_id = self._external_id_as_uri_suffix(self.asset_external_ids_by_id[raw])
                 except KeyError:
+                    warnings.warn(NeatValueWarning(f"Unknown asset id {raw}"), stacklevel=2)
                     return Literal("Unknown asset", datatype=XSD.string)
                 else:
                     return self.namespace[f"{InstanceIdPrefix.asset}{asset_external_id}"]

cognite/neat/_graph/extractors/_classic_cdf/_classic.py

@@ -7,7 +7,7 @@ from typing import ClassVar, NamedTuple, cast
 
 from cognite.client import CogniteClient
 from cognite.client.exceptions import CogniteAPIError
-from rdflib import Namespace, URIRef
+from rdflib import Literal, Namespace, URIRef
 
 from cognite.neat._constants import CLASSIC_CDF_NAMESPACE, DEFAULT_NAMESPACE, get_default_prefixes_and_namespaces
 from cognite.neat._graph.extractors._base import KnowledgeGraphExtractor
@@ -136,6 +136,8 @@ class ClassicGraphExtractor(KnowledgeGraphExtractor):
         self._extracted_data_sets = False
         self._asset_external_ids_by_id: dict[int, str] = {}
         self._dataset_external_ids_by_id: dict[int, str] = {}
+        self._asset_parent_uri_by_id: dict[int, URIRef] = {}
+        self._asset_parent_uri_by_external_id: dict[str, URIRef] = {}
         self.neat_prefix_by_predicate_uri: dict[URIRef, str] = {
             self._namespace["dataSetId"]: InstanceIdPrefix.data_set,
             self._namespace["assetId"]: InstanceIdPrefix.asset,
@@ -197,6 +199,8 @@ class ClassicGraphExtractor(KnowledgeGraphExtractor):
         else:
             self._extracted_data_sets = True
 
+        yield from self._extract_asset_parent_data_sets()
+
     def get_information_rules(self) -> InformationRules:
         # To avoid circular imports
         from cognite.neat._rules.importers import ExcelImporter
@@ -288,6 +292,10 @@ class ClassicGraphExtractor(KnowledgeGraphExtractor):
             if self._identifier == "id":
                 self._uris_by_external_id_by_type[core_node.resource_type].update(extractor._uriref_by_external_id)
 
+            if isinstance(extractor, AssetsExtractor):
+                self._asset_parent_uri_by_id.update(extractor.asset_parent_uri_by_id)
+                self._asset_parent_uri_by_external_id.update(extractor.asset_parent_uri_by_external_id)
+
     def _extract_start_node_relationships(self):
         for start_resource_type, source_external_ids in self._source_external_ids_by_type.items():
             start_type = start_resource_type.removesuffix("_")
@@ -325,6 +333,10 @@ class ClassicGraphExtractor(KnowledgeGraphExtractor):
                     # the target nodes.
                     self._relationship_subject_predicate_type_external_id.extend(extractor._target_triples)
 
+                if isinstance(extractor, AssetsExtractor):
+                    self._asset_parent_uri_by_id.update(extractor.asset_parent_uri_by_id)
+                    self._asset_parent_uri_by_external_id.update(extractor.asset_parent_uri_by_external_id)
+
     def _extract_core_end_nodes(self):
         for core_node in self._classic_node_types:
             target_external_ids = self._target_external_ids_by_type[core_node.resource_type]
@@ -372,6 +384,36 @@ class ClassicGraphExtractor(KnowledgeGraphExtractor):
             )
             yield from DataSetExtractor(data_set_iterator, **self._extractor_args).extract()
 
+    def _extract_asset_parent_data_sets(self):
+        if self._asset_parent_uri_by_id:
+            for chunk in self._chunk(
+                list(self._asset_parent_uri_by_id.keys()), description="Extracting asset parent data sets"
+            ):
+                assets = self._client.assets.retrieve_multiple(id=list(chunk), ignore_unknown_ids=True)
+                for asset in assets:
+                    if asset.data_set_id is None:
+                        continue
+                    object_ = (
+                        Literal(self._lookup_dataset(asset.data_set_id))
+                        if self._identifier == "externalId"
+                        else Literal(asset.data_set_id)
+                    )
+                    yield self._asset_parent_uri_by_id[asset.id], self._namespace.dataSetId, object_
+        if self._asset_parent_uri_by_external_id:
+            for chunk in self._chunk(
+                list(self._asset_parent_uri_by_external_id.keys()), description="Extracting asset parent data sets"
+            ):
+                assets = self._client.assets.retrieve_multiple(external_ids=list(chunk), ignore_unknown_ids=True)
+                for asset in assets:
+                    if asset.data_set_id is None:
+                        continue
+                    object_ = (
+                        Literal(self._lookup_dataset(asset.data_set_id))
+                        if self._identifier == "externalId"
+                        else Literal(asset.data_set_id)
+                    )
+                    yield self._asset_parent_uri_by_external_id[asset.external_id], self._namespace.dataSetId, object_
+
     def _extract_with_logging_label_dataset(
         self, extractor: ClassicCDFBaseExtractor, resource_type: InstanceIdPrefix | None = None
     ) -> Iterable[Triple]:

cognite/neat/_graph/loaders/_rdf2dms.py

@@ -46,7 +46,7 @@ from cognite.neat._store import NeatGraphStore
 from cognite.neat._utils.auxiliary import create_sha256_hash
 from cognite.neat._utils.collection_ import iterate_progress_bar_if_above_config_threshold
 from cognite.neat._utils.rdf_ import namespace_as_space, remove_namespace_from_uri, split_uri
-from cognite.neat._utils.text import NamingStandardization, humanize_collection
+from cognite.neat._utils.text import NamingStandardization
 from cognite.neat._utils.upload import UploadResult
 
 from ._base import _END_OF_CLASS, _START_OF_CLASS, CDFLoader
@@ -59,14 +59,12 @@ class _ViewIterator:
     Args:
         view_id: The view to iterate over
         instance_count: The number of instances in the view
-        hierarchical_properties: The properties that are hierarchical, meaning they point to the same instances.
         query: The query to get the instances from the store.
         view: The view object from the client.
     """
 
     view_id: dm.ViewId
     instance_count: int
-    hierarchical_properties: set[str]
     query: ViewQuery
     view: dm.View | None = None
 
@@ -189,33 +187,12 @@ class DMSLoader(CDFLoader[dm.InstanceApply]):
             )
             yield _START_OF_CLASS(view.external_id)
             for identifier, properties in instance_iterable:
-                yield from self._create_instances(
-                    identifier, properties, projection, stop_on_exception, exclude=it.hierarchical_properties
-                )
-            if it.hierarchical_properties:
-                # Force the creation of instances, before we create the hierarchical properties.
-                yield _END_OF_CLASS
-                yield _START_OF_CLASS(f"{view.external_id} ({humanize_collection(it.hierarchical_properties)})")
-                yield from self._create_hierarchical_properties(it, projection, stop_on_exception)
-            if reader is not instance_iterable:
+                yield from self._create_instances(identifier, properties, projection, stop_on_exception)
+            if reader is instance_iterable:
                 print(f"Loaded {it.instance_count} instances for {it.view_id!r}")
 
             yield _END_OF_CLASS
 
-    def _create_hierarchical_properties(
-        self, it: _ViewIterator, projection: _Projection, stop_on_exception: bool
-    ) -> Iterable[dm.InstanceApply | NeatIssue]:
-        reader = self.graph_store.read(it.query.rdf_type, property_renaming_config=it.query.property_renaming_config)
-        instance_iterable = iterate_progress_bar_if_above_config_threshold(
-            reader,
-            it.instance_count,
-            f"Loading {it.view_id!r} hierarchical properties: {humanize_collection(it.hierarchical_properties)}",
-        )
-        for identifier, properties in instance_iterable:
-            yield from self._create_instances(
-                identifier, properties, projection, stop_on_exception, include=it.hierarchical_properties
-            )
-
     def _create_view_iterations(self) -> tuple[list[_ViewIterator], IssueList]:
         view_query_by_id = RulesAnalysis(self.info_rules, self.dms_rules).view_query_by_id
         iterations_by_view_id = self._select_views_with_instances(view_query_by_id)
@@ -228,8 +205,6 @@ class DMSLoader(CDFLoader[dm.InstanceApply]):
                 for missing_view in missing:
                     issues.append(ResourceNotFoundError(missing_view, "view", more="The view is not found in CDF."))
                 return [], issues
-            # Todo: Remove if this turns out to be unnecessary.
-            hierarchical_properties_by_view_id: dict[dm.ViewId, set[str]] = {}
         else:
             views = dm.ViewList([])
             with catch_issues() as issues:
@@ -237,7 +212,6 @@ class DMSLoader(CDFLoader[dm.InstanceApply]):
                 views.extend(read_model.views)
             if issues.has_errors:
                 return [], issues
-            hierarchical_properties_by_view_id = {}
         views_by_id = {view.as_id(): view for view in views}
 
         def sort_by_instance_type(id_: dm.ViewId) -> int:
@@ -254,7 +228,6 @@ class DMSLoader(CDFLoader[dm.InstanceApply]):
                 continue
             view_iteration = iterations_by_view_id[view_id]
             view_iteration.view = views_by_id.get(view_id)
-            view_iteration.hierarchical_properties = hierarchical_properties_by_view_id.get(view_id, set())
             view_iterations.append(view_iteration)
         return view_iterations, issues
 
@@ -264,7 +237,7 @@ class DMSLoader(CDFLoader[dm.InstanceApply]):
         for view_id, query in view_query_by_id.items():
             count = self.graph_store.queries.count_of_type(query.rdf_type)
             if count > 0:
-                view_iterations[view_id] = _ViewIterator(view_id, count, set(), query)
+                view_iterations[view_id] = _ViewIterator(view_id, count, query)
         return view_iterations
 
     def _lookup_space_by_uri(self, view_iterations: list[_ViewIterator], stop_on_exception: bool = False) -> IssueList:
@@ -500,8 +473,6 @@ class DMSLoader(CDFLoader[dm.InstanceApply]):
         properties: dict[str | InstanceType, list[Any]],
         projection: _Projection,
         stop_on_exception: Literal[True, False] = False,
-        exclude: set[str] | None = None,
-        include: set[str] | None = None,
     ) -> Iterable[dm.InstanceApply | NeatIssue]:
         instance_id = self._create_instance_id(instance_uri, "node", stop_on_exception)
         if not isinstance(instance_id, InstanceId):
@@ -529,17 +500,16 @@ class DMSLoader(CDFLoader[dm.InstanceApply]):
             yield error
             return
         _ = properties.pop(RDF.type)[0]
-        if exclude:
-            properties = {k: v for k, v in properties.items() if k not in exclude}
-        if include:
-            properties = {k: v for k, v in properties.items() if k in include}
 
         sources = []
         with catch_issues() as property_issues:
             sources = [
                 dm.NodeOrEdgeData(
                     projection.view_id,
-                    projection.pydantic_cls.model_validate(properties).model_dump(exclude_unset=True),
+                    projection.pydantic_cls.model_validate(properties).model_dump(
+                        exclude_unset=True,
+                        exclude_none=True,
+                    ),
                 )
             ]
         for issue in property_issues:

cognite/neat/_rules/exporters/_rules2excel.py

@@ -20,10 +20,15 @@ from cognite.neat._rules.models import (
     SchemaCompleteness,
     SheetRow,
 )
+from cognite.neat._rules.models.data_types import _DATA_TYPE_BY_DMS_TYPE
 from cognite.neat._rules.models.dms import DMSMetadata
+from cognite.neat._rules.models.dms._rules import DMSRules
 from cognite.neat._rules.models.information import InformationMetadata
 from cognite.neat._rules.models.information._rules import InformationRules
-from cognite.neat._utils.spreadsheet import find_column_with_value
+from cognite.neat._utils.spreadsheet import (
+    find_column_with_value,
+    generate_data_validation,
+)
 
 from ._base import BaseExporter
 
@@ -54,6 +59,7 @@ class ExcelExporter(BaseExporter[VerifiedRules, Workbook]):
 
     Style = Literal["none", "minimal", "default", "maximal"]
     DumpOptions = Literal["user", "last", "reference"]
+    _helper_sheet_name: str = "_helper"
     _main_header_by_sheet_name: ClassVar[dict[str, str]] = {
         "Properties": "Definition of Properties",
         "Classes": "Definition of Classes",
@@ -74,6 +80,7 @@ class ExcelExporter(BaseExporter[VerifiedRules, Workbook]):
         add_empty_rows: bool = False,
         hide_internal_columns: bool = True,
         include_properties: Literal["same-space", "all"] = "all",
+        add_drop_downs: bool = True,
     ):
         self.sheet_prefix = sheet_prefix or ""
         if styling not in self.style_options:
@@ -85,6 +92,7 @@ class ExcelExporter(BaseExporter[VerifiedRules, Workbook]):
         self.add_empty_rows = add_empty_rows
         self.hide_internal_columns = hide_internal_columns
         self.include_properties = include_properties
+        self.add_drop_downs = add_drop_downs
 
     @property
     def description(self) -> str:
@@ -130,8 +138,114 @@ class ExcelExporter(BaseExporter[VerifiedRules, Workbook]):
                     if column_letter:
                         ws.column_dimensions[column_letter].hidden = True
 
+        # Only add drop downs if the rules are DMSRules
+        if self.add_drop_downs and isinstance(rules, DMSRules):
+            self._add_drop_downs(workbook)
+
         return workbook
 
+    def _add_drop_downs(self, workbook: Workbook, no_rows: int = 100) -> None:
+        """Adds drop down menus to specific columns for fast and accurate data entry.
+
+        Args:
+            workbook: Workbook representation of the Excel file.
+            no_rows: number of rows to add drop down menus. Defaults to 100*100.
+
+        !!! note "Why no_rows=100?"
+            Maximum number of views per data model is 100, thus this value is set accordingly
+
+        !!! note "Why defining individual data validation per desired column?
+            This is due to the internal working of openpyxl. Adding same validation to
+            different column leads to unexpected behavior when the openpyxl workbook is exported
+            as and Excel file. Probably, the validation is not copied to the new column,
+            but instead reference to the data validation object is added.
+        """
+
+        self._make_helper_sheet(workbook)
+
+        # We need create individual data validation and cannot re-use the same one due
+        # the internals of openpyxl
+        dv_views = generate_data_validation(self._helper_sheet_name, "A", no_header_rows=0, no_rows=no_rows)
+        dv_containers = generate_data_validation(self._helper_sheet_name, "b", no_header_rows=0, no_rows=no_rows)
+        dv_value_types = generate_data_validation(self._helper_sheet_name, "C", no_header_rows=0, no_rows=no_rows)
+
+        dv_immutable = generate_data_validation(self._helper_sheet_name, "D", no_header_rows=0, no_rows=3)
+        dv_nullable = generate_data_validation(self._helper_sheet_name, "D", no_header_rows=0, no_rows=3)
+        dv_is_list = generate_data_validation(self._helper_sheet_name, "D", no_header_rows=0, no_rows=3)
+        dv_in_model = generate_data_validation(self._helper_sheet_name, "D", no_header_rows=0, no_rows=3)
+        dv_used_for = generate_data_validation(self._helper_sheet_name, "E", no_header_rows=0, no_rows=3)
+
+        workbook["Properties"].add_data_validation(dv_views)
+        workbook["Properties"].add_data_validation(dv_containers)
+        workbook["Properties"].add_data_validation(dv_value_types)
+        workbook["Properties"].add_data_validation(dv_nullable)
+        workbook["Properties"].add_data_validation(dv_is_list)
+        workbook["Properties"].add_data_validation(dv_immutable)
+        workbook["Views"].add_data_validation(dv_in_model)
+        workbook["Containers"].add_data_validation(dv_used_for)
+
+        # we multiply no_rows with 100 since a view can have max 100 properties per view
+        if column := find_column_with_value(workbook["Properties"], "View"):
+            dv_views.add(f"{column}{3}:{column}{no_rows * 100}")
+
+        if column := find_column_with_value(workbook["Properties"], "Container"):
+            dv_containers.add(f"{column}{3}:{column}{no_rows * 100}")
+
+        if column := find_column_with_value(workbook["Properties"], "Value Type"):
+            dv_value_types.add(f"{column}{3}:{column}{no_rows * 100}")
+
+        if column := find_column_with_value(workbook["Properties"], "Nullable"):
+            dv_nullable.add(f"{column}{3}:{column}{no_rows * 100}")
+
+        if column := find_column_with_value(workbook["Properties"], "Is List"):
+            dv_is_list.add(f"{column}{3}:{column}{no_rows * 100}")
+
+        if column := find_column_with_value(workbook["Properties"], "Immutable"):
+            dv_immutable.add(f"{column}{3}:{column}{no_rows * 100}")
+
+        if column := find_column_with_value(workbook["Views"], "In Model"):
+            dv_in_model.add(f"{column}{3}:{column}{no_rows}")
+
+        if column := find_column_with_value(workbook["Containers"], "Used For"):
+            dv_used_for.add(f"{column}{3}:{column}{no_rows}")
+
+    def _make_helper_sheet(self, workbook: Workbook) -> None:
+        """This helper sheet is used as source of data for drop down menus creation
+
+        !!! note "Why 100 rows?"
+            The number of rows is set to 100 since this is the maximum number of views
+            per data model.
+        """
+        workbook.create_sheet(title=self._helper_sheet_name)
+
+        for counter, dtype in enumerate(_DATA_TYPE_BY_DMS_TYPE):
+            workbook[self._helper_sheet_name].cell(row=counter + 1, column=3, value=dtype)
+
+        for i in range(100):
+            workbook[self._helper_sheet_name].cell(
+                row=i + 1,
+                column=1,
+                value=f'=IF(ISBLANK(Views!A{i + 3}), "", Views!A{i + 3})',
+            )
+            workbook[self._helper_sheet_name].cell(
+                row=i + 1,
+                column=2,
+                value=f'=IF(ISBLANK(Containers!A{i + 3}), "", Containers!A{i + 3})',
+            )
+            workbook[self._helper_sheet_name].cell(
+                row=counter + i + 2,
+                column=3,
+                value=f'=IF(ISBLANK(Views!A{i + 3}), "", Views!A{i + 3})',
+            )
+
+        for i, value in enumerate([True, False, ""]):
+            workbook[self._helper_sheet_name].cell(row=i + 1, column=4, value=cast(bool | str, value))
+
+        for i, value in enumerate(["node", "edge", "all"]):
+            workbook[self._helper_sheet_name].cell(row=i + 1, column=5, value=value)
+
+        workbook[self._helper_sheet_name].sheet_state = "hidden"
+
     def _write_sheets(
         self,
         workbook: Workbook,

cognite/neat/_session/_fix.py

@@ -9,7 +9,7 @@ from .exceptions import session_class_wrapper
 
 @session_class_wrapper
 class FixAPI:
-    """Apply variety of fix methods to data model and isntances"""
+    """Apply variety of fix methods to data model and instances"""
 
     def __init__(self, state: SessionState, verbose: bool) -> None:
         self._state = state

cognite/neat/_session/_subset.py

@@ -25,6 +25,24 @@ class SubsetAPI:
         self._state = state
 
     def data_model(self, concepts: str | list[str]) -> IssueList:
+        """Subset the data model to the desired concepts.
+
+        Args:
+            concepts: The concepts to subset the data model to.
+
+        Returns:
+            IssueList: A list of issues that occurred during the transformation.
+
+        Example:
+            Read the CogniteCore data model and reduce the data model to only the 'CogniteAsset' concept.
+            ```python
+            neat = NeatSession(CogniteClient())
+
+            neat.read.examples.core_data_model()
+
+            neat.subset.data_model("CogniteAsset")
+            ```
+        """
         if self._state.rule_store.empty:
             raise NeatSessionError("No rules to set the data model ID.")
 

cognite/neat/_utils/spreadsheet.py

@@ -3,6 +3,7 @@ from typing import Any, Literal, cast, overload
 
 import pandas as pd
 from openpyxl import load_workbook
+from openpyxl.worksheet.datavalidation import DataValidation
 from openpyxl.worksheet.worksheet import Worksheet
 
 from cognite.neat._rules._constants import get_internal_properties
@@ -133,3 +134,12 @@ def find_column_with_value(sheet: Worksheet, value: Any) -> str | None:
                 return cell.column_letter  # type: ignore
 
     return None
+
+
+def generate_data_validation(sheet: str, column: str, no_header_rows: int, no_rows: int) -> DataValidation:
+    "Creates openpyxl data validation object for a cell in a sheet"
+
+    return DataValidation(
+        type="list",
+        formula1=f"={sheet}!{column}${no_header_rows + 1}:{column}${no_rows}",
+    )

cognite/neat/_version.py

@@ -1,2 +1,2 @@
-__version__ = "0.111.1"
+__version__ = "0.112.0"
 __engine__ = "^2.0.4"

{cognite_neat-0.111.1.dist-info → cognite_neat-0.112.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: cognite-neat
-Version: 0.111.1
+Version: 0.112.0
 Summary: Knowledge graph transformation
 License: Apache-2.0
 Author: Nikola Vasiljevic

{cognite_neat-0.111.1.dist-info → cognite_neat-0.112.0.dist-info}/RECORD

@@ -25,8 +25,8 @@ cognite/neat/_graph/extractors/__init__.py,sha256=v7hPDaRzI4koBTesbCgcxTb2W0Eoqy
 cognite/neat/_graph/extractors/_base.py,sha256=qQE-fl3f1hfqZg5KLF3zLHybP0u8ofRKf4jk7pEHnl4,1907
 cognite/neat/_graph/extractors/_classic_cdf/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 cognite/neat/_graph/extractors/_classic_cdf/_assets.py,sha256=9WVFrAtUFAp_AAlb26Rtt2Axz9xsPQYetg7SKVrNCr4,1474
-cognite/neat/_graph/extractors/_classic_cdf/_base.py,sha256=ZDnxqbgKE2ps8kVFLOqDGYPT0SPvEBg5D977NAxWRSA,15836
-cognite/neat/_graph/extractors/_classic_cdf/_classic.py,sha256=uf1lo-OfsXwBqRyfHsvIbw7Gaf3d8lZZxhvLYrACdqg,20331
+cognite/neat/_graph/extractors/_classic_cdf/_base.py,sha256=bYAoxsmiF6j5VB5Ptz2Kbkk8viEt8j_c-895cAI6E3Q,17639
+cognite/neat/_graph/extractors/_classic_cdf/_classic.py,sha256=lkiuGLPwRBQgmoO5ev-UfKIkm0QzV5vRXa4n26r264M,22666
 cognite/neat/_graph/extractors/_classic_cdf/_data_sets.py,sha256=xRFv9pVFgIMTZ45E8teMC0Ynku_CuZdcZkVCbhPuPBk,1294
 cognite/neat/_graph/extractors/_classic_cdf/_events.py,sha256=B8hRoMAg8GQvApjxals5PfPyjmdPO93U3nj_G7g0kDQ,1394
 cognite/neat/_graph/extractors/_classic_cdf/_files.py,sha256=Q816cVQ9qS7Art66HJfErL2OV7MxH_eSIG7bJ8_HJ7Q,1406
@@ -44,7 +44,7 @@ cognite/neat/_graph/extractors/_raw.py,sha256=xU3SmeLBCeqbs1WBdGCge8ZMnlOU6wgkKX
 cognite/neat/_graph/extractors/_rdf_file.py,sha256=vz145N1_ZDAlAzCuMiv2z5-7Z4nG2fciLMnl9OpEc3M,2857
 cognite/neat/_graph/loaders/__init__.py,sha256=XS6vwmxgBzntg7UuG_ct_1hfhShVnFH5u0gGrdA8WfA,699
 cognite/neat/_graph/loaders/_base.py,sha256=Xq91-4GeQF2XN90-QgEFCU4aJabBXkeFeFXS2k4mWU4,4472
-cognite/neat/_graph/loaders/_rdf2dms.py,sha256=04vU32Jlma2YYzJQuUEPCAfRJoXgygHJQZ4t72fISYI,34308
+cognite/neat/_graph/loaders/_rdf2dms.py,sha256=2EpuElmYFjfDFp7DCccV4ruQvhFefdb5cSTz5OnMuag,32400
 cognite/neat/_graph/queries/__init__.py,sha256=BgDd-037kvtWwAoGAy8eORVNMiZ5-E9sIV0txIpeaN4,50
 cognite/neat/_graph/queries/_base.py,sha256=xs_kCiqQFJfaPyYrKhpyPIAvyDOf19RgYcdg3WxjB6s,19344
 cognite/neat/_graph/transformers/__init__.py,sha256=YzC1Z8BuT77NwagWX4Z-F9R9BARLSS7zM4bCdxBbqKg,1761
@@ -84,7 +84,7 @@ cognite/neat/_rules/catalog/info-rules-imf.xlsx,sha256=vrE5g8vBtsGpwJqygxG3t9I3x
 cognite/neat/_rules/exporters/__init__.py,sha256=IYBa0DIYlx8cFItgYRw9W4FY_LmVEjuaqMz3JORZZX0,1204
 cognite/neat/_rules/exporters/_base.py,sha256=VkNMy8wsH-x4tAjS44cXgzzNH0CM2k_4RhkMwK50J7g,2284
 cognite/neat/_rules/exporters/_rules2dms.py,sha256=7I3a8ZPwkIBQAClQbMjJ2D2aIITY-OBVUD-8hirCmzM,19183
-cognite/neat/_rules/exporters/_rules2excel.py,sha256=zI3uyb42Efxm9o4ZG3St3TUZSUx4kD_Bt25txvxZHNc,13682
+cognite/neat/_rules/exporters/_rules2excel.py,sha256=TWtiF18Vp1sekGRwTCvfxw6IBt7u41xXpDE9e-aj3no,19382
 cognite/neat/_rules/exporters/_rules2instance_template.py,sha256=gI0tWFKzAhuFtnxVA7A9_AGYyL9lH_Yst-OYPNtTguA,5937
 cognite/neat/_rules/exporters/_rules2ontology.py,sha256=8GIawhTeNIS59zWYX2j3F63Ix9-xNGxgTzU1HiGkN98,22105
 cognite/neat/_rules/exporters/_rules2yaml.py,sha256=ggaPR8FO8PwZk1_nhwb5wVHk_C4s6qh1RrlbPkNcbBo,3160
@@ -140,7 +140,7 @@ cognite/neat/_session/_collector.py,sha256=RcOGY0DjTCCKJt9j_p0gnQXn4omhsIX2G8Aq3
 cognite/neat/_session/_create.py,sha256=doDCbDIWMbHCYe3cyk1obQaFdYJjvARg3X4lRUVicCk,7214
 cognite/neat/_session/_drop.py,sha256=gOkDAnddASpFxYxkPjlTyhkpNfnmDEj94GRI8tnHFR0,4167
 cognite/neat/_session/_explore.py,sha256=hrL0ASLtEXLlZn0dgDsKNySO10qEMBT8cE8mti2lOws,1561
-cognite/neat/_session/_fix.py,sha256=gpmbJ4TbB_v2nw4fEA2Qtf0ifO3UDEMHGdztha28S_U,898
+cognite/neat/_session/_fix.py,sha256=wYXIIHKmWTNmOLr9RvDSkBJllKoomP2mCnMdB9x2ojw,898
 cognite/neat/_session/_inspect.py,sha256=qoBAfCQnzC40ef91gxJmhonWo1Kr_VEjBb2KhbCOO_s,10084
 cognite/neat/_session/_mapping.py,sha256=AkQwmqYH-0EgqoXHqCFwJY92hNSGzfojOelhVFlqH4c,2655
 cognite/neat/_session/_prepare.py,sha256=BZ1NurenrsZDU4tg629wnt1Iuw_zVLRA58FNTQMYS9I,12636
@@ -148,7 +148,7 @@ cognite/neat/_session/_read.py,sha256=kULWbdP9T5jR9bW8S09Ix0aGRxN6PtcMrDy_IFJTyc
 cognite/neat/_session/_set.py,sha256=dCZ5zEmNAw8tiqOGT7-EigSXOIGlfVP2ldA7nmC8LJ8,4451
 cognite/neat/_session/_show.py,sha256=2lnkud996ouwf6-aKGvU0cU0ttfMeQ3vcb__g_7Yko4,10539
 cognite/neat/_session/_state.py,sha256=CPyjYbgUe6uUnCG6h-UqDtdIaWKVLjY4lAz4ar2_75A,4222
-cognite/neat/_session/_subset.py,sha256=-uwSBM2-PsKgky4VtQCSUuSRNJHLE54MVnRdVxvzKAE,2113
+cognite/neat/_session/_subset.py,sha256=vKtBiEnOruqe_749Nd8vzRS5HIZMR-sXSxyEH9Fa6Gk,2673
 cognite/neat/_session/_to.py,sha256=3bZGaXAXFvgzmNPmOtjzLiJLSlRXXaD6vYp4Cotx9Ks,18692
 cognite/neat/_session/_wizard.py,sha256=9idlzhZy54h2Iwupe9iXKX3RDb5jJQuBZFEouni50L0,1476
 cognite/neat/_session/engine/__init__.py,sha256=D3MxUorEs6-NtgoICqtZ8PISQrjrr4dvca6n48bu_bI,120
@@ -171,15 +171,15 @@ cognite/neat/_utils/io_.py,sha256=D2Mg8sOxfBoDg3fC0jBzaxO3vkXmr0QvZSgYIv6xRkM,38
 cognite/neat/_utils/rdf_.py,sha256=v4m8DD9dcHkALSx6wStC2h3kj-e3BmhxJT20fydtw7g,9897
 cognite/neat/_utils/reader/__init__.py,sha256=fPkrNB_9hLB7CyHTCFV_xEbIfOMqUQzNly5JN33-QfM,146
 cognite/neat/_utils/reader/_base.py,sha256=Q35hz8tqAiQiELjE4DsDDKQHLtRmSTrty4Gep9rg_CU,5444
-cognite/neat/_utils/spreadsheet.py,sha256=Z2R2qcN0oYE3BLMCE9cbmCwi2rPMGKJ3u21jzzIoZg0,4279
+cognite/neat/_utils/spreadsheet.py,sha256=_QaziVzo83X6vuXdAmqp4HgMmF3eb9PrTRwq8F1POl4,4652
 cognite/neat/_utils/text.py,sha256=BFJoEOQBFgpelysL92FdF0OVRVFl0q9tRNoz-oRanNc,7779
 cognite/neat/_utils/time_.py,sha256=O30LUiDH9TdOYz8_a9pFqTtJdg8vEjC3qHCk8xZblG8,345
 cognite/neat/_utils/upload.py,sha256=xWtM6mFuD2QYQHaZ7zCAuGptbEpPIxcH-raWQu93-Ug,5845
 cognite/neat/_utils/xml_.py,sha256=FQkq84u35MUsnKcL6nTMJ9ajtG9D5i1u4VBnhGqP2DQ,1710
-cognite/neat/_version.py,sha256=-VM_CDLZVdKqCx3xnkerorrUtOUOFliXjm2ugsCJsBE,46
+cognite/neat/_version.py,sha256=W7xZS6jccWmomymHy0HgbVW_-n6rOs454M4iJwFADDg,46
 cognite/neat/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-cognite_neat-0.111.1.dist-info/LICENSE,sha256=W8VmvFia4WHa3Gqxq1Ygrq85McUNqIGDVgtdvzT-XqA,11351
-cognite_neat-0.111.1.dist-info/METADATA,sha256=DEgM33cOnPe1FEPvz3idx5dCRV-i0Q22H7xsW97gmyE,5361
-cognite_neat-0.111.1.dist-info/WHEEL,sha256=XbeZDeTWKc1w7CSIyre5aMDU_-PohRwTQceYnisIYYY,88
-cognite_neat-0.111.1.dist-info/entry_points.txt,sha256=SsQlnl8SNMSSjE3acBI835JYFtsIinLSbVmHmMEXv6E,51
-cognite_neat-0.111.1.dist-info/RECORD,,
+cognite_neat-0.112.0.dist-info/LICENSE,sha256=W8VmvFia4WHa3Gqxq1Ygrq85McUNqIGDVgtdvzT-XqA,11351
+cognite_neat-0.112.0.dist-info/METADATA,sha256=5I-isgVln98HgiP59TJnX8IbvlHTenc46CgNBJT_6mc,5361
+cognite_neat-0.112.0.dist-info/WHEEL,sha256=XbeZDeTWKc1w7CSIyre5aMDU_-PohRwTQceYnisIYYY,88
+cognite_neat-0.112.0.dist-info/entry_points.txt,sha256=SsQlnl8SNMSSjE3acBI835JYFtsIinLSbVmHmMEXv6E,51
+cognite_neat-0.112.0.dist-info/RECORD,,