[gRPC] Replace ensembl_name with production_name for GetGenomeUUID endpoint

protos/ensembl/production/metadata/grpc/ensembl_metadata.proto

@@ -293,11 +293,10 @@ message GenomeUUID {
 
 message OrganismsGroup {
   uint32 species_taxonomy_id = 1;
-  string ensembl_name = 2;
-  string common_name = 3;
-  string scientific_name = 4;
-  uint32 order = 5;
-  uint32 count = 6;
+  string common_name = 2;
+  string scientific_name = 3;
+  uint32 order = 4;
+  uint32 count = 5;
 }
 
 message OrganismsGroupCount {
@@ -420,7 +419,7 @@ message GenomeDatatypeRequest {
 Genome info filter used by Compara (EA-1090)
  */
 message GenomeInfoRequest {
-  string ensembl_name = 1;     // Mandatory
+  string production_name = 1;     // Mandatory
   string assembly_name = 2;    // Mandatory
   bool use_default = 3;        // Optional
 }

src/ensembl/production/metadata/api/sample/ensembl_metadata/genome.txt

@@ -1,9 +1,9 @@
-1	a7335667-93e7-11ec-a39d-005056b38ce3	1	1	2023-05-12 13:30:58	0	test
-2	3704ceb1-948d-11ec-a39d-005056b38ce3	2	1	2023-05-12 13:32:06	0	test1
-3	a73351f7-93e7-11ec-a39d-005056b38ce3	3	2	2023-05-12 13:32:14	0	test2
-4	a73356e1-93e7-11ec-a39d-005056b38ce3	4	3	2023-05-12 13:32:25	0	test3
-5	a73357ab-93e7-11ec-a39d-005056b38ce3	5	4	2023-05-12 13:32:36	0	test4
-6	a733574a-93e7-11ec-a39d-005056b38ce3	6	5	2023-05-12 13:32:46	0	test5
-7	a733550b-93e7-11ec-a39d-005056b38ce3	7	6	2023-05-12 13:32:52	0	test6
+1	a7335667-93e7-11ec-a39d-005056b38ce3	1	1	2023-05-12 13:30:58	0	homo_sapiens
+2	3704ceb1-948d-11ec-a39d-005056b38ce3	2	1	2023-05-12 13:32:06	0	homo_sapiens_37
+3	a73351f7-93e7-11ec-a39d-005056b38ce3	3	2	2023-05-12 13:32:14	0	escherichia_coli_str_k_12_substr_mg1655
+4	a73356e1-93e7-11ec-a39d-005056b38ce3	4	3	2023-05-12 13:32:25	0	plasmodium_falciparum
+5	a73357ab-93e7-11ec-a39d-005056b38ce3	5	4	2023-05-12 13:32:36	0	triticum_aestivum
+6	a733574a-93e7-11ec-a39d-005056b38ce3	6	5	2023-05-12 13:32:46	0	saccharomyces_cerevisiae
+7	a733550b-93e7-11ec-a39d-005056b38ce3	7	6	2023-05-12 13:32:52	0	caenorhabditis_elegans
 8	a7335667-93e7-11ec-a39d-00aasab38ce3	8	1	2023-09-07 16:30:58	0	test7
 9	90720316-006c-470b-a7dd-82d28f952264	9	8	2023-08-18 12:22:34 0	test8

src/ensembl/production/metadata/grpc/adaptors/genome.py

@@ -80,8 +80,8 @@ def fetch_taxonomy_ids(self, taxonomy_names):
 
     def fetch_genomes(self, genome_id=None, genome_uuid=None, genome_tag=None, organism_uuid=None, assembly_uuid=None,
                       assembly_accession=None, assembly_name=None, use_default_assembly=False, ensembl_name=None,
-                      taxonomy_id=None, group=None, group_type=None, allow_unreleased=False, unreleased_only=False,
-                      site_name=None, release_type=None, release_version=None, current_only=True):
+                      production_name=None, taxonomy_id=None, group=None, group_type=None, allow_unreleased=False,
+                      unreleased_only=False, site_name=None, release_type=None, release_version=None, current_only=True):
         """
         Fetches genome information based on the specified parameters.
 
@@ -95,6 +95,7 @@ def fetch_genomes(self, genome_id=None, genome_uuid=None, genome_tag=None, organ
             assembly_name (Union[str, List[str]]): The name(s) of the assembly(s) to fetch.
             use_default_assembly (bool): Whether to use default assembly name or not.
             ensembl_name (Union[str, List[str]]): The Ensembl name(s) of the organism(s) to fetch.
+            production_name (Union[str, List[str]]): The production name(s) of the organism(s) to fetch.
             taxonomy_id (Union[int, List[int]]): The taxonomy ID(s) of the organism(s) to fetch.
             group (Union[str, List[str]]): The name(s) of the organism group(s) to filter by.
             group_type (Union[str, List[str]]): The type(s) of the organism group(s) to filter by.
@@ -132,6 +133,7 @@ def fetch_genomes(self, genome_id=None, genome_uuid=None, genome_tag=None, organ
         assembly_accession = check_parameter(assembly_accession)
         assembly_name = check_parameter(assembly_name)
         ensembl_name = check_parameter(ensembl_name)
+        production_name = check_parameter(production_name)
         taxonomy_id = check_parameter(taxonomy_id)
         group = check_parameter(group)
         group_type = check_parameter(group_type)
@@ -194,6 +196,9 @@ def fetch_genomes(self, genome_id=None, genome_uuid=None, genome_tag=None, organ
         if ensembl_name is not None:
             genome_select = genome_select.filter(Organism.ensembl_name.in_(ensembl_name))
 
+        if production_name is not None:
+            genome_select = genome_select.filter(Genome.production_name.in_(production_name))
+
         if taxonomy_id is not None:
             genome_select = genome_select.filter(Organism.taxonomy_id.in_(taxonomy_id))
 
@@ -612,7 +617,6 @@ def fetch_organisms_group_counts(self, release_version=None, group_code='popular
             # Get latest released organisms
             query = db.select(
                 o_species.species_taxonomy_id,
-                o_species.ensembl_name,
                 o_species.common_name,
                 o_species.scientific_name,
                 OrganismGroupMember.order.label('order'),
@@ -629,7 +633,6 @@ def fetch_organisms_group_counts(self, release_version=None, group_code='popular
 
             query = query.group_by(
                 o_species.species_taxonomy_id,
-                o_species.ensembl_name,
                 o_species.common_name,
                 o_species.scientific_name,
                 OrganismGroupMember.order

src/ensembl/production/metadata/grpc/client_examples.py

@@ -273,15 +273,15 @@ def get_dataset_infos_by_dataset_type(stub):
 
 def get_genome_uuid(stub):
     request1 = GenomeInfoRequest(
-        ensembl_name="homo_sapiens_37", assembly_name="GRCh37.p13"
+        production_name="homo_sapiens_37", assembly_name="GRCh37.p13"
     )
     genome_uuid1 = stub.GetGenomeUUID(request1)
     request2 = GenomeInfoRequest(
-        ensembl_name="homo_sapiens_37", assembly_name="GRCh37", use_default=True
+        production_name="homo_sapiens_37", assembly_name="GRCh37", use_default=True
     )
     genome_uuid2 = stub.GetGenomeUUID(request2)
     request3 = GenomeInfoRequest(
-        ensembl_name="homo_sapiens_37", assembly_name="GRCh37.p13", use_default=True
+        production_name="homo_sapiens_37", assembly_name="GRCh37.p13", use_default=True
     )
     genome_uuid3 = stub.GetGenomeUUID(request3)
 

src/ensembl/production/metadata/grpc/protobuf_msg_factory.py

@@ -396,11 +396,10 @@ def create_organisms_group_count(data, release_version):
     for organism in data:
         created_organism_group = ensembl_metadata_pb2.OrganismsGroup(
             species_taxonomy_id=organism[0],
-            ensembl_name=organism[1],
-            common_name=organism[2],
-            scientific_name=organism[3],
-            order=organism[4],
-            count=organism[5],
+            common_name=organism[1],
+            scientific_name=organism[2],
+            order=organism[3],
+            count=organism[4],
         )
         organisms_list.append(created_organism_group)
 

src/ensembl/production/metadata/grpc/servicer.py

@@ -39,7 +39,7 @@ def GetTopLevelStatisticsByUUID(self, request, context):
         return utils.get_top_level_statistics_by_uuid(self.db, request.genome_uuid)
 
     def GetGenomeUUID(self, request, context):
-        return utils.get_genome_uuid(self.db, request.ensembl_name, request.assembly_name, request.use_default)
+        return utils.get_genome_uuid(self.db, request.production_name, request.assembly_name, request.use_default)
 
     def GetGenomeByUUID(self, request, context):
         return utils.get_genome_by_uuid(self.db, request.genome_uuid, request.release_version)

src/ensembl/production/metadata/grpc/utils.py

@@ -179,12 +179,12 @@ def get_sub_species_info(db_conn, organism_uuid, group):
     return msg_factory.create_sub_species()
 
 
-def get_genome_uuid(db_conn, ensembl_name, assembly_name, use_default=False):
-    if ensembl_name is None or assembly_name is None:
+def get_genome_uuid(db_conn, production_name, assembly_name, use_default=False):
+    if production_name is None or assembly_name is None:
         return msg_factory.create_genome_uuid()
 
     genome_uuid_result = db_conn.fetch_genomes(
-        ensembl_name=ensembl_name,
+        production_name=production_name,
         assembly_name=assembly_name,
         use_default_assembly=use_default,
         allow_unreleased=cfg.allow_unreleased
@@ -194,18 +194,6 @@ def get_genome_uuid(db_conn, ensembl_name, assembly_name, use_default=False):
         return msg_factory.create_genome_uuid(
             {"genome_uuid": genome_uuid_result[0].Genome.genome_uuid}
         )
-    # PATCH: This is a special case, see EA-1112 for more details
-    elif len(genome_uuid_result) == 0:
-        # Try looking using only assembly_default (no ensembl_name is needed)
-        using_default_assembly_only_result = db_conn.fetch_genomes(
-            assembly_name=assembly_name,
-            use_default_assembly=True,
-            allow_unreleased=cfg.allow_unreleased
-        )
-        if len(using_default_assembly_only_result) == 1:
-            return msg_factory.create_genome_uuid(
-                {"genome_uuid": using_default_assembly_only_result[0].Genome.genome_uuid}
-            )
 
     return msg_factory.create_genome_uuid()
 

src/tests/test_grpc.py

@@ -376,13 +376,13 @@ def test_fetch_organisms_group_counts(self, multi_dbs, species_taxonomy_id, expe
         test = conn.fetch_organisms_group_counts()
         # When fetching everything:
         # First result should be Human
-        assert test[0][2] == expected_organism
+        assert test[0][1] == expected_organism
         # We should have three assemblies associated with Human (Two for grch37.38 organism + one t2t)
-        assert test[0][5] == expected_assemblies_count
+        assert test[0][4] == expected_assemblies_count
 
         for data in test[1:]:
             # All others have only one genome in test DB
-            assert data[5] == 1
+            assert data[4] == 1
 
     @pytest.mark.parametrize(
         "organism_uuid, expected_assemblies_count",

src/tests/test_protobuf_msg_factory.py

@@ -243,7 +243,6 @@ def test_create_organisms_group_count(self, multi_dbs, genome_db_conn):
 			"organismsGroupCount": [
 				{
 					"speciesTaxonomyId": 9606,
-					"ensemblName": "Homo_sapiens",
 					"commonName": "Human",
 					"scientificName": "Homo sapiens",
 					"order": 1,

src/tests/test_utils.py

@@ -683,21 +683,20 @@ def test_get_dataset_by_genome_id_no_results(self, genome_db_conn):
 		assert output == {}
 
 	@pytest.mark.parametrize(
-		"ensembl_name, assembly_name, use_default, expected_output",
+		"production_name, assembly_name, use_default, expected_output",
 		[
 			("homo_sapiens", "GRCh38.p13", False, {"genomeUuid": "a7335667-93e7-11ec-a39d-005056b38ce3"}),
 			("homo_sapiens", "GRCh38.p13", True, {}),
 			("homo_sapiens", "GRCh38", True, {"genomeUuid": "a7335667-93e7-11ec-a39d-005056b38ce3"}),
-			("random_ensembl_name", "GRCh38", False, {"genomeUuid": "a7335667-93e7-11ec-a39d-005056b38ce3"}),
-			("random_ensembl_name", "random_assembly_name", True, {}),
-			("random_ensembl_name", "random_assembly_name", False, {}),
+			("random_production_name", "random_assembly_name", True, {}),
+			("random_production_name", "random_assembly_name", False, {}),
 		]
 	)
-	def test_get_genome_uuid(self, genome_db_conn, ensembl_name, assembly_name, use_default, expected_output):
+	def test_get_genome_uuid(self, genome_db_conn, production_name, assembly_name, use_default, expected_output):
 		output = json_format.MessageToJson(
 			utils.get_genome_uuid(
 				db_conn=genome_db_conn,
-				ensembl_name=ensembl_name,
+				production_name=production_name,
 				assembly_name=assembly_name,
 				use_default=use_default
 			))
@@ -1109,7 +1108,6 @@ def test_get_organisms_group_count(self, genome_db_conn):
 			"organismsGroupCount": [
 				{
 					"speciesTaxonomyId": 9606,
-					"ensemblName": "Homo_sapiens",
 					"commonName": "Human",
 					"scientificName": "Homo sapiens",
 					"order": 1,