fix: robust synthetic property handling for score sets

- Refactored ScoreSet view models to ensure robust handling of synthetic and required fields for both ORM and dict contexts.
- Added tests to verify all key attributes and synthetic properties are correctly handled in both construction modes.
- Ensured creation from both dict and ORM contexts, mirroring the approach used for other models.

Author: bencap

src/mavedb/view_models/score_set.py

@@ -311,12 +311,11 @@ class Config:
         arbitrary_types_allowed = True
 
     # These 'synthetic' fields are generated from other model properties. Transform data from other properties as needed, setting
-    # the appropriate field on the model itself. Then, proceed with Pydantic ingestion once fields are created.
+    # the appropriate field on the model itself. Then, proceed with Pydantic ingestion once fields are created. Only perform these
+    # transformations if the relevant attributes are present on the input data (i.e., when creating from an ORM object).
     @model_validator(mode="before")
     def generate_primary_and_secondary_publications(cls, data: Any):
-        if not hasattr(data, "primary_publication_identifiers") or not hasattr(
-            data, "secondary_publication_identifiers"
-        ):
+        if hasattr(data, "publication_identifier_associations"):
             try:
                 publication_identifiers = transform_record_publication_identifiers(
                     data.publication_identifier_associations
@@ -327,9 +326,9 @@ def generate_primary_and_secondary_publications(cls, data: Any):
                 data.__setattr__(
                     "secondary_publication_identifiers", publication_identifiers["secondary_publication_identifiers"]
                 )
-            except AttributeError as exc:
+            except (AttributeError, KeyError) as exc:
                 raise ValidationError(
-                    f"Unable to create {cls.__name__} without attribute: {exc}."  # type: ignore
+                    f"Unable to coerce publication identifier attributes for {cls.__name__}: {exc}."  # type: ignore
                 )
         return data
 
@@ -384,12 +383,11 @@ def publication_identifiers_validator(cls, value: Any) -> list[PublicationIdenti
         return list(value)  # Re-cast into proper list-like type
 
     # These 'synthetic' fields are generated from other model properties. Transform data from other properties as needed, setting
-    # the appropriate field on the model itself. Then, proceed with Pydantic ingestion once fields are created.
+    # the appropriate field on the model itself. Then, proceed with Pydantic ingestion once fields are created. Only perform these
+    # transformations if the relevant attributes are present on the input data (i.e., when creating from an ORM object).
     @model_validator(mode="before")
     def generate_primary_and_secondary_publications(cls, data: Any):
-        if not hasattr(data, "primary_publication_identifiers") or not hasattr(
-            data, "secondary_publication_identifiers"
-        ):
+        if hasattr(data, "publication_identifier_associations"):
             try:
                 publication_identifiers = transform_record_publication_identifiers(
                     data.publication_identifier_associations
@@ -400,33 +398,35 @@ def generate_primary_and_secondary_publications(cls, data: Any):
                 data.__setattr__(
                     "secondary_publication_identifiers", publication_identifiers["secondary_publication_identifiers"]
                 )
-            except AttributeError as exc:
-                raise ValidationError(
-                    f"Unable to create {cls.__name__} without attribute: {exc}."  # type: ignore
-                )
+            except (AttributeError, KeyError) as exc:
+                raise ValidationError(f"Unable to coerce publication identifier attributes for {cls.__name__}: {exc}.")
         return data
 
     @model_validator(mode="before")
     def transform_meta_analysis_objects_to_urns(cls, data: Any):
-        if not hasattr(data, "meta_analyzes_score_set_urns"):
+        if hasattr(data, "meta_analyzes_score_sets"):
             try:
                 data.__setattr__(
                     "meta_analyzes_score_set_urns", transform_score_set_list_to_urn_list(data.meta_analyzes_score_sets)
                 )
-            except AttributeError as exc:
-                raise ValidationError(f"Unable to create {cls.__name__} without attribute: {exc}.")  # type: ignore
+            except (AttributeError, KeyError) as exc:
+                raise ValidationError(
+                    f"Unable to coerce meta analyzes score set urn attribute for {cls.__name__}: {exc}."
+                )
         return data
 
     @model_validator(mode="before")
     def transform_meta_analyzed_objects_to_urns(cls, data: Any):
-        if not hasattr(data, "meta_analyzed_by_score_set_urns"):
+        if hasattr(data, "meta_analyzed_by_score_sets"):
             try:
                 data.__setattr__(
                     "meta_analyzed_by_score_set_urns",
                     transform_score_set_list_to_urn_list(data.meta_analyzed_by_score_sets),
                 )
-            except AttributeError as exc:
-                raise ValidationError(f"Unable to create {cls.__name__} without attribute: {exc}.")  # type: ignore
+            except (AttributeError, KeyError) as exc:
+                raise ValidationError(
+                    f"Unable to coerce meta analyzed by score set urn attribute for {cls.__name__}: {exc}."
+                )
         return data
 
 

tests/view_models/test_score_set.py

@@ -3,7 +3,13 @@
 import pytest
 
 from mavedb.view_models.publication_identifier import PublicationIdentifier, PublicationIdentifierCreate
-from mavedb.view_models.score_set import SavedScoreSet, ScoreSetCreate, ScoreSetModify, ScoreSetUpdateAllOptional
+from mavedb.view_models.score_set import (
+    SavedScoreSet,
+    ScoreSet,
+    ScoreSetCreate,
+    ScoreSetModify,
+    ScoreSetUpdateAllOptional,
+)
 from mavedb.view_models.target_gene import SavedTargetGene, TargetGeneCreate
 from tests.helpers.constants import (
     EXTRA_LICENSE,
@@ -17,6 +23,7 @@
     TEST_MINIMAL_SEQ_SCORESET_RESPONSE,
     TEST_PATHOGENICITY_SCORE_CALIBRATION,
     TEST_PUBMED_IDENTIFIER,
+    VALID_EXPERIMENT_SET_URN,
     VALID_EXPERIMENT_URN,
     VALID_SCORE_SET_URN,
     VALID_TMP_URN,
@@ -372,10 +379,14 @@ def test_score_set_update_all_optional(attribute, updated_data):
 
 
 @pytest.mark.parametrize(
-    "exclude",
-    ["publication_identifier_associations", "meta_analyzes_score_sets", "meta_analyzed_by_score_sets"],
+    "exclude,expected_missing_fields",
+    [
+        ("publication_identifier_associations", ["primaryPublicationIdentifiers", "secondaryPublicationIdentifiers"]),
+        ("meta_analyzes_score_sets", ["metaAnalyzesScoreSetUrns"]),
+        ("meta_analyzed_by_score_sets", ["metaAnalyzedByScoreSetUrns"]),
+    ],
 )
-def test_cannot_create_saved_score_set_without_all_attributed_properties(exclude):
+def test_cannot_create_saved_score_set_without_all_attributed_properties(exclude, expected_missing_fields):
     score_set = TEST_MINIMAL_SEQ_SCORESET_RESPONSE.copy()
     score_set["urn"] = "urn:score-set-xxx"
 
@@ -429,8 +440,9 @@ def test_cannot_create_saved_score_set_without_all_attributed_properties(exclude
     with pytest.raises(ValueError) as exc_info:
         SavedScoreSet.model_validate(score_set_attributed_object)
 
-    assert "Unable to create SavedScoreSet without attribute" in str(exc_info.value)
-    assert exclude in str(exc_info.value)
+    assert "Field required" in str(exc_info.value)
+    for exclude_field in expected_missing_fields:
+        assert exclude_field in str(exc_info.value)
 
 
 def test_can_create_score_set_with_none_type_superseded_score_set_urn():
@@ -543,3 +555,14 @@ def test_cant_create_score_set_without_experiment_urn_if_not_meta_analysis():
         ScoreSetCreate(**score_set_test)
 
     assert "experiment URN is required unless your score set is a meta-analysis" in str(exc_info.value)
+
+
+def test_can_create_score_set_from_non_orm_context():
+    score_set_test = TEST_MINIMAL_SEQ_SCORESET_RESPONSE.copy()
+    score_set_test["urn"] = "urn:score-set-xxx"
+    score_set_test["experiment"]["urn"] = VALID_EXPERIMENT_URN
+    score_set_test["experiment"]["experimentSetUrn"] = VALID_EXPERIMENT_SET_URN
+
+    saved_score_set = ScoreSet.model_validate(score_set_test)
+
+    assert saved_score_set.urn == "urn:score-set-xxx"