feature/mx-1533 prepare graph identity provider (#67)

# PR Context
Small prep for robert-koch-institut/mex-backend#24

# Added
- constant for MEX_PRIMARY_SOURCE_IDENTIFIER

# Fixed
- ExtractedData raises proper ValidationError when parsing wrong base type

CHANGELOG.md

@@ -11,6 +11,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - cruft template link
 - workflow that syncs main branch to openCoDE
+- constant for MEX_PRIMARY_SOURCE_IDENTIFIER
 
 ### Changes
 
@@ -22,6 +23,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Fixed
 
+- ExtractedData raises proper ValidationError when parsing wrong base type
+
 ### Security
 
 

mex/common/models/__init__.py

@@ -18,6 +18,7 @@
     MergedDistribution,
 )
 from mex.common.models.extracted_data import (
+    MEX_PRIMARY_SOURCE_IDENTIFIER,
     MEX_PRIMARY_SOURCE_IDENTIFIER_IN_PRIMARY_SOURCE,
     MEX_PRIMARY_SOURCE_STABLE_TARGET_ID,
     BaseExtractedData,
@@ -62,26 +63,26 @@
     "BaseResource",
     "BaseVariable",
     "BaseVariableGroup",
+    "EXTRACTED_MODEL_CLASSES_BY_NAME",
+    "EXTRACTED_MODEL_CLASSES",
     "ExtractedAccessPlatform",
     "ExtractedActivity",
     "ExtractedContactPoint",
     "ExtractedData",
     "ExtractedDistribution",
-    "EXTRACTED_MODEL_CLASSES",
-    "EXTRACTED_MODEL_CLASSES_BY_NAME",
     "ExtractedOrganization",
     "ExtractedOrganizationalUnit",
     "ExtractedPerson",
     "ExtractedPrimarySource",
     "ExtractedResource",
     "ExtractedVariable",
     "ExtractedVariableGroup",
+    "MERGED_MODEL_CLASSES_BY_NAME",
     "MergedAccessPlatform",
     "MergedActivity",
     "MergedContactPoint",
     "MergedDistribution",
     "MergedItem",
-    "MERGED_MODEL_CLASSES_BY_NAME",
     "MergedOrganization",
     "MergedOrganizationalUnit",
     "MergedPerson",
@@ -90,6 +91,7 @@
     "MergedVariable",
     "MergedVariableGroup",
     "MEX_PRIMARY_SOURCE_IDENTIFIER_IN_PRIMARY_SOURCE",
+    "MEX_PRIMARY_SOURCE_IDENTIFIER",
     "MEX_PRIMARY_SOURCE_STABLE_TARGET_ID",
     "MExModel",
 )

mex/common/models/extracted_data.py

@@ -1,12 +1,13 @@
 from typing import Annotated, Any
 
-from pydantic import Field, model_validator
+from pydantic import Field, model_validator, validate_call
 
 from mex.common.models.base import MExModel
-from mex.common.types import PrimarySourceID
+from mex.common.types import Identifier, PrimarySourceID
 
-MEX_PRIMARY_SOURCE_STABLE_TARGET_ID = PrimarySourceID("00000000000000")
+MEX_PRIMARY_SOURCE_IDENTIFIER = Identifier("00000000000000")
 MEX_PRIMARY_SOURCE_IDENTIFIER_IN_PRIMARY_SOURCE = "mex"
+MEX_PRIMARY_SOURCE_STABLE_TARGET_ID = PrimarySourceID("00000000000000")
 
 
 class BaseExtractedData(MExModel):
@@ -65,11 +66,11 @@ class ExtractedData(BaseExtractedData):
     to automatically set identifiers for provenance. See below, for description.
     """
 
+    # TODO make stable_target_id and identifier computed fields (MX-1435)
     @model_validator(mode="before")
     @classmethod
-    def set_identifiers(  # noqa: C901 # TODO in https://jira.rki.local/browse/MX-1435
-        cls, values: dict[str, Any]
-    ) -> dict[str, Any]:
+    @validate_call
+    def set_identifiers(cls, values: dict[str, Any]) -> dict[str, Any]:  # noqa: C901
         """Ensure identifier and provenance attributes are set for this instance.
 
         All extracted data classes have four important identifiers that are defined

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "mex-common"
-version = "0.19.0"
+version = "0.19.1"
 description = "Common library for MEx python projects."
 authors = ["RKI MEx Team <[email protected]>"]
 readme = "README.md"
@@ -16,7 +16,7 @@ langdetect = "^1.0.9"
 ldap3 = "^2.9.1"
 numpy = "^1.26.2"
 pandas = "^2.1.4"
-pydantic = "^2.5.2"
+pydantic = "^2.5.3"
 pydantic-settings = "^2.1.0"
 requests = "^2.31.0"
 

tests/models/test_extracted_data.py

@@ -30,6 +30,11 @@ class ExtractedThing(BaseThing, ExtractedData):
     """Extracted version of a dummy thing model."""
 
 
+def test_extracted_data_requires_dict_for_construction() -> None:
+    with pytest.raises(ValidationError, match="Input should be a valid dictionary"):
+        ExtractedThing.model_validate(["this is a list"])
+
+
 def test_extracted_data_requires_identifier_in_primary_source() -> None:
     with pytest.raises(ValidationError, match="identifierInPrimarySource"):
         ExtractedThing(