Change ingest code to include new DOI Class

microbiomedata · Nov 29, 2023 · e249491 · e249491
1 parent 070a874
commit e249491
Show file tree

Hide file tree

Showing 4 changed files with 17 additions and 42 deletions.
diff --git a/nmdc_server/ingest/doi.py b/nmdc_server/ingest/doi.py
@@ -43,7 +43,7 @@ def upsert_doi(db: Session, doi: str, doi_type: DOIType):
             return
         info = {}
 
-    statement = insert(DOIInfo.__table__).values(id=doi, info=info, doi_type=doi_type)
+    statement = insert(DOIInfo.__table__).values(id=doi, info=info, doi_type=DOIType(doi_type))
     statement = statement.on_conflict_do_update(constraint="pk_doi_info", set_=dict(info=info))
     db.execute(statement)
     db.flush()
diff --git a/nmdc_server/ingest/study.py b/nmdc_server/ingest/study.py
@@ -65,27 +65,18 @@ def load(db: Session, cursor: Cursor):
             obj["principal_investigator_id"] = get_or_create_pi(db, pi_name, pi_url, pi_orcid)
             obj["principal_investigator_websites"] = obj.pop("websites", [])
         obj["image"] = get_study_image_data(obj.pop("study_image", []))
+        dois=obj.pop("associated_dois", None)
+        if dois:
+            for doi in dois:
+                doi["doi_value"] = transform_doi(doi.pop("doi_value"))
 
-        publication_dois = [transform_doi(d) for d in obj.pop("publications", [])] + [
-            transform_doi(d) for d in obj.pop("publication_dois", [])
-        ]
-        award_dois = [transform_doi(doi) for doi in obj.pop("award_dois", [])] + [
-            transform_doi(d) for d in obj.pop("emsl_project_dois", [])
-        ]
-        dataset_dois = [transform_doi(doi) for doi in obj.pop("dataset_dois", [])]
+            for doi in dois:
+                upsert_doi(db, doi["doi_value"], doi["doi_category"])
 
-        for doi in publication_dois:
-            upsert_doi(db, doi, DOIType.PUBLICATION)
-
-        for doi in award_dois:
-            upsert_doi(db, doi, DOIType.AWARD)
-
-        for doi in dataset_dois:
-            upsert_doi(db, doi, DOIType.DATASET)
 
         new_study = create_study(db, Study(**obj))
-
-        for doi_id in publication_dois + award_dois + dataset_dois:
-            doi_object = get_doi(db, doi_id)
-            if doi_object:
-                new_study.dois.append(doi_object)  # type: ignore
+        if dois:
+            for doi in dois:
+                doi_object = get_doi(db, doi["doi_value"])
+                if doi_object:
+                    new_study.dois.append(doi_object)  # type: ignore
diff --git a/nmdc_server/models.py b/nmdc_server/models.py
@@ -181,9 +181,9 @@ class PrincipalInvestigator(Base):
 
 
 class DOIType(enum.Enum):
-    AWARD = "award"
-    DATASET = "dataset"
-    PUBLICATION = "publication"
+    AWARD = 'award_doi'
+    DATASET = 'dataset_doi'
+    PUBLICATION = 'publication_doi'
 
 
 study_doi_association = Table(
@@ -273,18 +273,6 @@ def open_in_gold(self) -> Optional[str]:
             self.gold_study_identifiers,  # type: ignore
         )
 
-    @property
-    def award_dois(self) -> list[DOIInfo]:
-        return [d for d in self.dois if d.doi_type == DOIType.AWARD]  # type: ignore
-
-    @property
-    def publication_dois(self) -> list[DOIInfo]:
-        return [d for d in self.dois if d.doi_type == DOIType.PUBLICATION]  # type: ignore
-
-    @property
-    def dataset_dois(self) -> list[DOIInfo]:
-        return [d for d in self.dois if d.doi_type == DOIType.DATASET]  # type: ignore
-
     @property
     def doi_map(self) -> Dict[str, Any]:
         doi_info = {}

diff --git a/nmdc_server/schemas.py b/nmdc_server/schemas.py
@@ -216,7 +216,8 @@ class CreditAssociation(BaseModel):
 class DOIInfo(BaseModel):
     id: str
     info: dict
-    doi_type: models.DOIType
+    doi_category: models.DOIType
+    doi_provider:str
 
     class Config:
         orm_mode = True
@@ -232,8 +233,6 @@ class StudyBase(AnnotatedBase):
     has_credit_associations: Optional[List[CreditAssociation]]
     relevant_protocols: Optional[List[str]]
     funding_sources: Optional[List[str]]
-    ess_dive_datasets: Optional[List[str]]
-    massive_study_identifiers: Optional[List[str]]
     gold_study_identifiers: Optional[List[str]]
 
     @validator("principal_investigator_websites", pre=True, each_item=True)
@@ -269,9 +268,6 @@ class Study(StudyBase):
     doi_map: Dict[str, Any] = {}
     multiomics: int
 
-    award_dois: Optional[List[DOIInfo]]
-    publication_dois: Optional[List[DOIInfo]]
-    dataset_dois: Optional[List[DOIInfo]]
 
     class Config:
         orm_mode = True