filter species at api endpoints

app/api/v1/endpoints/species.py

@@ -8,6 +8,7 @@
 from app.api import deps
 from app.db.base_class import Base
 from app.models import SpeciesCommonNames, SpeciesSynonyms, stations_species_table
+from app.utils.species import binomial_only
 
 router = APIRouter()
 
@@ -30,7 +31,7 @@ def read_all_species(
 ) -> Any:
     """Retrieve all species."""
     species = crud.species.get_all(db, order_by=order_by)
-    return species
+    return binomial_only(species)
 
 
 @router.post("/search/", response_model=List[schemas.SpeciesSummary])
@@ -47,7 +48,7 @@ def read_species_by_search(
         order_by=order_by,
         limit=limit,
     )
-    return species
+    return binomial_only(species)
 
 
 @router.get("/fuzzymatch/", response_model=List[schemas.SpeciesSummary])
@@ -120,7 +121,7 @@ def read_fuzzy_species_by_search(
         order_by=order_by,
         limit=limit,
     )
-    return species
+    return binomial_only(species)
 
 
 @router.get(

app/crud/crud_station.py

@@ -1,17 +1,22 @@
-from typing import Any, Optional
+from typing import Any, Optional, cast
 
 from sqlalchemy.orm import Session
 
 from app.crud.base import CRUDBase
 from app.models import Station
 from app.schemas import StationCreate, StationSummaryPagination, StationUpdate
+from app.utils.species import binomial_only
 
 
 class CRUDStation(
     CRUDBase[Station, StationCreate, StationUpdate, StationSummaryPagination]
 ):
     def get(self, db: Session, id: Any) -> Optional[Station]:
-        return db.query(self.model).filter(self.model.name == id).first()
+        station = cast(
+            Station, db.query(self.model).filter(self.model.name == id).first()
+        )
+        station.species = binomial_only(station.species)
+        return station
 
 
 station = CRUDStation(Station)

app/utils/species.py

@@ -0,0 +1,17 @@
+from typing import List
+
+from app.models import Species
+
+
+def binomial_only(species: List[Species]) -> List[Species]:
+    """
+    TODO: This is a temporary fix. In the future, we could consider filtering out genera
+    when loading data into the database or as part of the OCR workflow.
+    """
+    # Unlike `current_name`, `current_canonical_full_name` doesn't include
+    # author(s) and year of publication, so for a genus, there won't be any spaces.
+    return [
+        sp
+        for sp in species
+        if sp.current_canonical_simple_name and " " in sp.current_canonical_simple_name
+    ]