Fix filtering for instances where depth is a range in mongo

nmdc_server/attribute_units.py

@@ -20,10 +20,10 @@ def get_attribute_units(table: str, attribute: str) -> Optional[PlainUnit]:
     return _unit_info.get(table, {}).get(attribute)
 
 
-def extract_quantity(obj: dict, table: str, attribute: str) -> Optional[float]:
+def extract_quantity(obj: dict, table: str, attribute: str, value_field: str = "has_numeric_value", ) -> Optional[float]:
     """Extract units from https://microbiomedata.github.io/nmdc-schema/QuantityValue/"""
     expected_units = get_attribute_units(table, attribute)
-    value = obj.get("has_numeric_value", None)
+    value = obj.get(value_field, None)
     units = obj.get("has_unit", None)
     if value is None:
         return None

nmdc_server/ingest/biosample.py

@@ -118,7 +118,14 @@ def load_biosample(db: Session, obj: Dict[str, Any]):
 
     obj["study_id"] = associated_studies[0]
     depth_obj = obj.get("depth", {})
-    obj["depth"] = extract_quantity(depth_obj, "biosample", "depth")
+
+    # Handle depth, which may be a range or a single value
+    if "has_numeric_value" in depth_obj:
+        obj["depth_min"] = extract_quantity(depth_obj, "biosample", "depth", "has_numeric_value")
+        obj["depth_max"] = extract_quantity(depth_obj, "biosample", "depth", "has_numeric_value")
+    elif "has_minimum_numeric_value" in depth_obj and "has_maximum_numeric_value" in depth_obj:
+        obj["depth_min"] = extract_quantity(depth_obj, "biosample", "depth", "has_minimum_numeric_value")
+        obj["depth_max"] = extract_quantity(depth_obj, "biosample", "depth", "has_maximum_numeric_value")
 
     biosample = Biosample(**obj)
 

nmdc_server/migrations/versions/dc2a4cca7c66_.py

@@ -0,0 +1,34 @@
+"""empty message
+
+Revision ID: dc2a4cca7c66
+Revises: 9a0ff33a4e6b
+Create Date: 2025-09-11 21:38:15.666750
+
+"""
+from typing import Optional
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision: str = 'dc2a4cca7c66'
+down_revision: Optional[str] = '9a0ff33a4e6b'
+branch_labels: Optional[str] = None
+depends_on: Optional[str] = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column('biosample', sa.Column('depth_min', sa.Float(), nullable=True))
+    op.add_column('biosample', sa.Column('depth_max', sa.Float(), nullable=True))
+    op.drop_column('biosample', 'depth')
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column('biosample', sa.Column('depth', postgresql.DOUBLE_PRECISION(precision=53), autoincrement=False, nullable=True))
+    op.drop_column('biosample', 'depth_max')
+    op.drop_column('biosample', 'depth_min')
+    # ### end Alembic commands ###

nmdc_server/models.py

@@ -380,7 +380,8 @@ class Biosample(Base, AnnotatedModel):
     add_date = Column(DateTime, nullable=True)
     mod_date = Column(DateTime, nullable=True)
     collection_date = Column(DateTime, nullable=True)
-    depth = Column(Float, nullable=True)
+    depth_min = Column(Float, nullable=True)
+    depth_max = Column(Float, nullable=True)
     env_broad_scale_id = Column(String, ForeignKey(EnvoTerm.id), nullable=True)
     env_local_scale_id = Column(String, ForeignKey(EnvoTerm.id), nullable=True)
     env_medium_id = Column(String, ForeignKey(EnvoTerm.id), nullable=True)