address design review comments on method naming conventions

nmdc_runtime/site/graphs.py

@@ -2,7 +2,7 @@
 
 from nmdc_runtime.site.ops import (
     build_merged_db,
-    missing_gold_biosample_repair,
+    generate_biosample_set_for_nmdc_study_from_gold,
     nmdc_schema_database_export_filename,
     nmdc_schema_database_from_gold_study,
     nmdc_schema_object_to_dict,
@@ -59,8 +59,8 @@
     ncbi_submission_xml_from_nmdc_study,
     ncbi_submission_xml_asset,
     get_database_updater_inputs,
-    nmdc_study_id_filename,
-    missing_data_generation_repair,
+    post_submission_portal_biosample_ingest_record_stitching_filename,
+    generate_data_generation_set_post_biosample_ingest,
 )
 from nmdc_runtime.site.export.study_metadata import get_biosamples_by_study_id
 
@@ -474,25 +474,33 @@ def nmdc_study_to_ncbi_submission_export():
 
 
 @graph
-def fill_missing_data_generation_data_object_records():
+def generate_data_generation_set_for_biosamples_in_nmdc_study():
     (study_id, gold_nmdc_instrument_mapping_file_url) = get_database_updater_inputs()
     gold_nmdc_instrument_map_df = get_df_from_url(gold_nmdc_instrument_mapping_file_url)
 
-    database = missing_data_generation_repair(study_id, gold_nmdc_instrument_map_df)
+    database = generate_data_generation_set_post_biosample_ingest(
+        study_id, gold_nmdc_instrument_map_df
+    )
 
     database_dict = nmdc_schema_object_to_dict(database)
-    filename = nmdc_study_id_filename(study_id)
+    filename = post_submission_portal_biosample_ingest_record_stitching_filename(
+        study_id
+    )
     outputs = export_json_to_drs(database_dict, filename)
     add_output_run_event(outputs)
 
 
 @graph
-def fill_missing_biosample_records_from_gold():
+def generate_biosample_set_from_samples_in_gold():
     (study_id, gold_nmdc_instrument_mapping_file_url) = get_database_updater_inputs()
     gold_nmdc_instrument_map_df = get_df_from_url(gold_nmdc_instrument_mapping_file_url)
 
-    database = missing_gold_biosample_repair(study_id, gold_nmdc_instrument_map_df)
+    database = generate_biosample_set_for_nmdc_study_from_gold(
+        study_id, gold_nmdc_instrument_map_df
+    )
     database_dict = nmdc_schema_object_to_dict(database)
-    filename = nmdc_study_id_filename(study_id)
+    filename = post_submission_portal_biosample_ingest_record_stitching_filename(
+        study_id
+    )
     outputs = export_json_to_drs(database_dict, filename)
     add_output_run_event(outputs)

nmdc_runtime/site/ops.py

@@ -1249,7 +1249,9 @@ def ncbi_submission_xml_from_nmdc_study(
 
 
 @op
-def nmdc_study_id_filename(nmdc_study_id: str) -> str:
+def post_submission_portal_biosample_ingest_record_stitching_filename(
+    nmdc_study_id: str,
+) -> str:
     filename = nmdc_study_id_to_filename(nmdc_study_id)
     return f"missing_database_records_for_{filename}.json"
 
@@ -1278,7 +1280,7 @@ def get_database_updater_inputs(context: OpExecutionContext) -> Tuple[str, str]:
         "gold_api_client",
     }
 )
-def missing_data_generation_repair(
+def generate_data_generation_set_post_biosample_ingest(
     context: OpExecutionContext,
     nmdc_study_id: str,
     gold_nmdc_instrument_map_df: pd.DataFrame,
@@ -1298,7 +1300,9 @@ def missing_data_generation_repair(
         nmdc_study_id,
         gold_nmdc_instrument_map_df,
     )
-    database = database_updater.create_missing_dg_records()
+    database = (
+        database_updater.generate_data_generation_set_records_from_gold_api_for_study()
+    )
 
     return database
 
@@ -1310,7 +1314,7 @@ def missing_data_generation_repair(
         "gold_api_client",
     }
 )
-def missing_gold_biosample_repair(
+def generate_biosample_set_for_nmdc_study_from_gold(
     context: OpExecutionContext,
     nmdc_study_id: str,
     gold_nmdc_instrument_map_df: pd.DataFrame,

nmdc_runtime/site/repair/database_updater.py

@@ -58,7 +58,9 @@ def _fetch_gold_projects(self, gold_biosample_id: str):
         """
         return self.gold_api_client.fetch_projects_by_biosample(gold_biosample_id)
 
-    def create_missing_dg_records(self) -> nmdc.Database:
+    def generate_data_generation_set_records_from_gold_api_for_study(
+        self,
+    ) -> nmdc.Database:
         """This method creates missing data generation records for a given study in the NMDC database using
         metadata from GOLD. The way the logic works is, it first fetches all the biosamples associated
         with the study from the NMDC database. Then, it fetches all the biosample and project data data

nmdc_runtime/site/repository.py

@@ -25,7 +25,7 @@
 from nmdc_runtime.api.models.trigger import Trigger
 from nmdc_runtime.site.export.study_metadata import export_study_biosamples_metadata
 from nmdc_runtime.site.graphs import (
-    fill_missing_biosample_records_from_gold,
+    generate_biosample_set_from_samples_in_gold,
     translate_metadata_submission_to_nmdc_schema_database,
     ingest_metadata_submission,
     gold_study_to_database,
@@ -45,7 +45,7 @@
     ingest_neon_surface_water_metadata,
     ensure_alldocs,
     nmdc_study_to_ncbi_submission_export,
-    fill_missing_data_generation_data_object_records,
+    generate_data_generation_set_for_biosamples_in_nmdc_study,
 )
 from nmdc_runtime.site.resources import (
     get_mongo,
@@ -925,10 +925,11 @@ def biosample_export():
 
 
 @repository
-def database_record_repair():
+def database_records_stitching():
     normal_resources = run_config_frozen__normal_env["resources"]
     return [
-        fill_missing_data_generation_data_object_records.to_job(
+        generate_data_generation_set_for_biosamples_in_nmdc_study.to_job(
+            description="This job can be used to create a data_generation_set JSON for biosamples that are already present in the NMDC database.",
             resource_defs=resource_defs,
             config={
                 "resources": merge(
@@ -969,7 +970,8 @@ def database_record_repair():
                 },
             },
         ),
-        fill_missing_biosample_records_from_gold.to_job(
+        generate_biosample_set_from_samples_in_gold.to_job(
+            description="This job can be used to create a biosample_set JSON from samples in GOLD for a given study in NMDC.",
             resource_defs=resource_defs,
             config={
                 "resources": merge(

tests/test_data/test_database_updater.py

@@ -47,7 +47,7 @@ def db_updater(mock_clients):
 
 
 @patch("nmdc_runtime.site.repair.database_updater.GoldStudyTranslator")
-def test_create_missing_dg_records(
+def test_generate_data_generation_set_records_from_gold_api_for_study(
     MockGoldStudyTranslator, db_updater, mock_clients, test_minter
 ):
     mock_runtime_api_user_client = mock_clients["runtime_api_user_client"]
@@ -95,7 +95,7 @@ def test_create_missing_dg_records(
     mint_id_mock.json.return_value = test_minter("nmdc:NucleotideSequencing", 1)
     mock_runtime_api_site_client.mint_id.return_value = mint_id_mock
 
-    database = db_updater.create_missing_dg_records()
+    database = db_updater.generate_data_generation_set_records_from_gold_api_for_study()
 
     assert database is not None
     assert len(database.data_generation_set) > 0