fix imf import error (#586)

* fix imf import error

* fix failures with OWL

* added test

* bump version added changelog

Makefile

@@ -1,5 +1,5 @@
 .PHONY: run-explorer run-tests run-linters build-ui build-python build-docker run-docker compose-up
-version="0.88.2"
+version="0.88.3"
 run-explorer:
 	@echo "Running explorer API server..."
 	# open "http://localhost:8000/static/index.html" || true

cognite/neat/_version.py

@@ -1 +1 @@
-__version__ = "0.88.2"
+__version__ = "0.88.3"

cognite/neat/rules/importers/_rdf/_imf2rules/_imf2classes.py

@@ -53,7 +53,7 @@ def parse_imf_to_classes(graph: Graph, language: str = "en") -> list[dict]:
         BIND(IF(!bound(?parent) && ?type = imf:AttributeType, imf:Attribute, ?parent) AS ?parentClass)
 
         # Rebind the IRI of the IMF-type to the ?reference variable to align with dataframe column headers
-        # This is solely for readability, the ?imfClass could have been returnered directly instead of ?reference
+        # This is solely for readability, the ?imfClass could have been returned directly instead of ?reference
         BIND(?imfClass AS ?reference)
 
         FILTER (!isBlank(?class))

cognite/neat/rules/importers/_rdf/_imf2rules/_imf2rules.py

@@ -36,7 +36,7 @@ class IMFImporter(BaseImporter):
     """
 
     def __init__(self, filepath: Path):
-        self.owl_filepath = filepath
+        self.filepath = filepath
 
     @overload
     def to_rules(self, errors: Literal["raise"], role: RoleTypes | None = None) -> VerifiedRules: ...
@@ -47,11 +47,13 @@ def to_rules(
     ) -> tuple[VerifiedRules | None, IssueList]: ...
 
     def to_rules(
-        self, errors: Literal["raise", "continue"] = "continue", role: RoleTypes | None = None
+        self,
+        errors: Literal["raise", "continue"] = "continue",
+        role: RoleTypes | None = None,
     ) -> tuple[VerifiedRules | None, IssueList] | VerifiedRules:
         graph = Graph()
         try:
-            graph.parse(self.owl_filepath)
+            graph.parse(self.filepath)
         except Exception as e:
             raise Exception(f"Could not parse owl file: {e}") from e
 

cognite/neat/rules/importers/_rdf/_owl2rules/_owl2classes.py

@@ -34,6 +34,7 @@ def parse_owl_classes(graph: Graph, language: str = "en") -> list[dict]:
         FILTER (!bound(?parentClass) || !isBlank(?parentClass))
         FILTER (!bound(?name) || LANG(?name) = "" || LANGMATCHES(LANG(?name), "en"))
         FILTER (!bound(?description) || LANG(?description) = "" || LANGMATCHES(LANG(?description), "en"))
+        BIND(?class AS ?reference)
     }
     """
 

cognite/neat/rules/importers/_rdf/_owl2rules/_owl2properties.py

@@ -40,6 +40,7 @@ def parse_owl_properties(graph: Graph, language: str = "en") -> list[dict]:
         FILTER (!bound(?description) || LANG(?description) = "" || LANGMATCHES(LANG(?description), "en"))
         BIND(IF(bound(?minCount), ?minCount, 0) AS ?minCount)
         BIND(IF(bound(?maxCount), ?maxCount, 1) AS ?maxCount)
+        BIND(?property AS ?reference)
     }
     """
 

cognite/neat/rules/importers/_rdf/_shared.py

@@ -23,13 +23,13 @@ def parse_raw_classes_dataframe(query_results: list[tuple]) -> pd.DataFrame:
             "Comment",
         ],
     )
+
     if df.empty:
         return df
 
     # # remove NaNs
     df.replace(np.nan, "", regex=True, inplace=True)
 
-    df.Reference = df.Class
     df.Class = df.Class.apply(lambda x: remove_namespace_from_uri(x))
     df["Match Type"] = len(df) * [MatchType.exact]
     df["Comment"] = len(df) * [None]
@@ -202,7 +202,7 @@ def parse_raw_properties_dataframe(query_results: list[tuple]) -> pd.DataFrame:
         return df
 
     df.replace(np.nan, "", regex=True, inplace=True)
-    df.Reference = df.Reference if df.Reference.unique() else df.Property.copy(deep=True)
+
     df.Class = df.Class.apply(lambda x: remove_namespace_from_uri(x))
     df.Property = df.Property.apply(lambda x: remove_namespace_from_uri(x))
     df["Value Type"] = df["Value Type"].apply(lambda x: remove_namespace_from_uri(x))
@@ -231,7 +231,7 @@ def clean_up_properties(df: pd.DataFrame) -> pd.DataFrame:
                     "Min Count": property_grouped_df["Min Count"].unique()[0],
                     "Max Count": property_grouped_df["Max Count"].unique()[0],
                     "Default": property_grouped_df["Default"].unique()[0],
-                    "Reference": property_grouped_df["Reference"].unique()[0] or property_,
+                    "Reference": property_grouped_df["Reference"].unique()[0],
                     "Match Type": property_grouped_df["Match Type"].unique()[0],
                     "Comment": property_grouped_df["Comment"].unique()[0],
                     "_property_type": property_grouped_df["_property_type"].unique()[0],

docs/CHANGELOG.md

@@ -16,6 +16,15 @@ Changes are grouped as follows:
 - `Security` in case of vulnerabilities.
 
 
+## [0.88.3] - 20-08-24
+### Fixed
+- IMF rules importer failing due to references
+### Improved
+- Handling of references for OWL importer
+### Added
+- Test for IMF importer
+
+
 ## [0.88.2] - 24-07-24
 ### Added
 - IMF rules importer

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "cognite-neat"
-version = "0.88.2"
+version = "0.88.3"
 readme = "README.md"
 description = "Knowledge graph transformation"
 authors = [

tests/config.py

@@ -28,5 +28,6 @@
 GRAPH_CAPTURING_SHEET = DATA_FOLDER / "sheet2cdf-graph-capturing.xlsx"
 WIND_ONTOLOGY = DATA_FOLDER / "wind-energy.owl"
 DEXPI_EXAMPLE = DATA_FOLDER / "depxi_example.xml"
+IMF_EXAMPLE = DATA_FOLDER / "TempTransmitterComplete.ttl"
 
 CLASSIC_CDF_EXTRACTOR_DATA = DATA_FOLDER / "class_cdf_extractor_data"