add metagenome json file && cover the missing line

lib/GenomeFileUtil/core/GenomeInterface.py

@@ -267,6 +267,7 @@ def _update_metagenome(self, genome):
         """Checks for missing required fields and fixes breaking changes"""
         if 'molecule_type' not in genome:
             genome['molecule_type'] = 'Unknown'
+        return genome
 
     def _update_genome(self, genome):
         """Checks for missing required fields and fixes breaking changes"""

test/data/metagenomes/toy/metagenome.json

@@ -0,0 +1,53 @@
+{
+    "contig_ids": [
+        "Ga0065724_100001"
+    ],
+    "contig_lengths": [
+        538871
+    ],
+    "dna_size": 538871,
+    "domain": "Eukaryota",
+    "environment": null,
+    "external_source_origination_date": null,
+    "feature_counts": {
+        "CDS": 20,
+        "gene": 20,
+        "non_coding_features": 0,
+        "protein_encoding_gene": 20
+    },
+    "features_handle_ref": "KBH_736245",
+    "gc_content": 0.64469,
+    "genetic_code": 1,
+    "genome_type": "Metagenome",
+    "gff_handle_ref": "KBH_736244",
+    "id": "MyMetagenome",
+    "md5": "e2ccbd5a9bed0148015bd6b784e3c1c3",
+    "molecule_type": "SingleLetterAlphabet",
+    "notes": null,
+    "num_contigs": 1,
+    "num_features": 40,
+    "ontologies_present": {},
+    "ontology_events": [
+        {
+            "id": "GO",
+            "method": "GenomeFileUtils Genbank uploader from annotations",
+            "method_version": "0.11.7",
+            "ontology_ref": "KBaseOntology/gene_ontology",
+            "timestamp": "2024_09_05_06_45_31"
+        }
+    ],
+    "original_source_file_name": null,
+    "protein_handle_ref": "KBH_736243",
+    "publications": [],
+    "scientific_name": "Arabidopsis thaliana",
+    "source": "GFF",
+    "source_id": "unknown",
+    "suspect": 1,
+    "taxon_assignments": {
+        "ncbi": "3702"
+    },
+    "taxonomy": "cellular organisms; Eukaryota; Viridiplantae; Streptophyta; Streptophytina; Embryophyta; Tracheophyta; Euphyllophyta; Spermatophyta; Magnoliopsida; Mesangiospermae; eudicotyledons; Gunneridae; Pentapetalae; rosids; malvids; Brassicales; Brassicaceae; Camelineae; Arabidopsis",
+    "warnings": [
+        "SUSPECT: This genome has 20 genes that needed to be spoofed for existing parentless CDS."
+    ]
+}

test/problematic_tests/save_genome_test.py

@@ -23,6 +23,9 @@
 from GenomeFileUtil.core.GenomeInterface import GenomeInterface
 from installed_clients.WorkspaceClient import Workspace as workspaceService
 
+KBASE_GENOME = "KBaseGenomes.Genome"
+KBASE_METAGENOME = "KBaseMetagenomes.AnnotatedMetagenomeAssembly"
+
 
 class SaveGenomeTest(unittest.TestCase):
 
@@ -115,17 +118,36 @@ def delete_shock_node(cls, node_id):
 
     @classmethod
     def prepare_data(cls):
-        assembly_file_path = os.path.join(cls.scratch,
-                                          'e_coli_assembly.fasta')
+
+        assembly_file_path = os.path.join(cls.scratch,'e_coli_assembly.fasta')
+        meta_file_path = os.path.join(cls.scratch,'metagenome.fa')
+
         shutil.copy('data/e_coli/e_coli_assembly.fasta', assembly_file_path)
+        shutil.copy('data/metagenomes/toy/metagenome.fa', meta_file_path)
+
         au = AssemblyUtil(os.environ['SDK_CALLBACK_URL'])
-        assembly_ref = au.save_assembly_from_fasta({
-            'workspace_name': cls.wsName,
-            'assembly_name': 'e_coli.assembly',
-            'file': {'path': assembly_file_path}
-        })
+
+        assembly_refs = au.save_assemblies_from_fastas(
+            {
+                'workspace_id': cls.wsID,
+                'inputs': [
+                    {
+                        'assembly_name': 'e_coli.assembly',
+                        'file': assembly_file_path
+                    },
+                    {
+                        'assembly_name': 'metagenome.assembly',
+                        'file': meta_file_path
+                    }
+                ]
+            }
+        )["results"]
+
         cls.test_genome_data = json.load(open('data/e_coli/e_coli.json'))
-        cls.test_genome_data['assembly_ref'] = assembly_ref
+        cls.test_genome_data['assembly_ref'] = assembly_refs[0]["upa"]
+
+        cls.test_metagenome_data = json.load(open('data/metagenomes/toy/metagenome.json'))
+        cls.test_metagenome_data['assembly_ref'] = assembly_refs[1]["upa"]
 
     def getWsClient(self):
         return self.__class__.wsClient
@@ -154,12 +176,12 @@ def fail_save_genome(self, params, error, exception=ValueError, contains=False,
         else:
             self.assertEqual(error, str(context.exception))
 
-    def check_save_one_genome_output(self, ret, genome_name):
+    def check_save_one_genome_output(self, ret, genome_name, data_type=KBASE_GENOME):
         self.assertTrue('info' in ret)
 
         genome_info = ret['info']
         self.assertEqual(genome_info[1], genome_name)
-        self.assertEqual(genome_info[2].split('-')[0], 'KBaseGenomes.Genome')
+        self.assertEqual(genome_info[2].split('-')[0], data_type)
         self.assertEqual(genome_info[5], self.user_id)
 
     def test_bad_one_genome_params(self):
@@ -211,18 +233,18 @@ def test_genomes(self):
 
     def test_genomes_with_upgrade(self):
         self.start_test()
-        genome_name = 'test_genome'
+        genome_name = 'MyMetagenome'
         inputs = [
             {
                 'name': genome_name,
-                'data': self.test_genome_data,
-                'workspace_datatype': "KBaseMetagenomes.AnnotatedMetagenomeAssembly",
+                'data': self.test_metagenome_data,
+                'workspace_datatype': KBASE_METAGENOME,
                 'upgrade': True,
             }
         ]
         params = {'workspace_id': self.wsID, 'inputs': inputs}
         ret = self.genome_interface.save_genome_mass(params)[0]
-        self.check_save_one_genome_output(ret, genome_name)
+        self.check_save_one_genome_output(ret, genome_name, data_type=KBASE_METAGENOME)
 
     def test_genomes_with_hidden(self):
         self.start_test()