implement a more meaningful v1/v2 migration test

tests/clinvar_xml_io/test_clinvar_dataset.py

@@ -7,7 +7,7 @@
 
 
 def test_dataset_write():
-    input_file = os.path.join(resources_dir, 'test_clinvar_dataset.xml.gz')
+    input_file = os.path.join(resources_dir, 'clinvar_dataset_v2.xml.gz')
     output_file = os.path.join(resources_dir, 'test_output.xml.gz')
 
     input_dataset = ClinVarDataset(input_file)

tests/clinvar_xml_io/test_clinvar_record.py

@@ -8,6 +8,21 @@
 resources_dir = os.path.join(os.path.dirname(__file__), 'resources')
 
 
+def test_clinvar_record_v1_v2_migration():
+    # Same RCV in both versions
+    v1_input_file = os.path.join(resources_dir, 'clinvar_dataset_v1.xml.gz')
+    v2_input_file = os.path.join(resources_dir, 'clinvar_dataset_v2.xml.gz')
+    record_v1 = next(iter(ClinVarDataset(v1_input_file)))
+    record_v2 = next(iter(ClinVarDataset(v2_input_file)))
+    assert record_v1.xsd_version == 1.6
+    assert record_v2.xsd_version == 2.0
+
+    assert record_v1.accession == record_v2.accession
+    assert record_v1.score == record_v2.score
+    assert set(record_v1.valid_clinical_significances) == set(record_v2.valid_clinical_significances)
+    assert set(record_v1.valid_allele_origins) == set(record_v2.valid_allele_origins)
+
+
 def test_multiple_clinical_classifications_record():
     # input dataset with only one record
     input_file = os.path.join(resources_dir, 'multiple_classifications.xml.gz')

tests/clinvar_xml_io/test_xml_parsing.py

@@ -7,7 +7,7 @@
 
 
 def test_parse_header_attributes():
-    input_file = os.path.join(resources_dir, 'test_clinvar_dataset.xml.gz')
+    input_file = os.path.join(resources_dir, 'clinvar_dataset_v2.xml.gz')
     header_attr = parse_header_attributes(input_file)
     assert header_attr['Dated'] == '2023-02-22'
     assert header_attr['xsi:noNamespaceSchemaLocation'] == 'https://ftp.ncbi.nlm.nih.gov/pub/clinvar/xsd_public/RCV/ClinVar_RCV_2.0.xsd'

tests/output_generation/test_annotated_clinvar.py

@@ -13,10 +13,12 @@ def test_string_to_set():
     assert string_to_set('{}') == set()
 
 
-def run_generate_annotated_xml(input_file, expected_output_file):
+def test_generate_annotated_xml():
+    input_file = os.path.join(resources_dir, 'test_annotation_input.xml.gz')
     efo_mapping_file = os.path.join(resources_dir, 'string_to_ontology_mappings.tsv')
     gene_mapping_file = os.path.join(resources_dir, 'snp2gene_extract.tsv')
     output_file = os.path.join(resources_dir, 'test_output.xml.gz')
+    expected_output_file = os.path.join(resources_dir, 'expected_annotation_output.xml.gz')
 
     generate_annotated_clinvar_xml(input_file, efo_mapping_file, gene_mapping_file, output_file)
 
@@ -31,15 +33,3 @@ def run_generate_annotated_xml(input_file, expected_output_file):
 
     if os.path.exists(output_file):
         os.remove(output_file)
-
-
-def test_generate_annotated_xml_v1():
-    input_file = os.path.join(resources_dir, 'test_annotation_input_v1.xml.gz')
-    expected_output_file = os.path.join(resources_dir, 'expected_annotation_output_v1.xml.gz')
-    run_generate_annotated_xml(input_file, expected_output_file)
-
-
-def test_generate_annotated_xml_v2():
-    input_file = os.path.join(resources_dir, 'test_annotation_input_v2.xml.gz')
-    expected_output_file = os.path.join(resources_dir, 'expected_annotation_output_v2.xml.gz')
-    run_generate_annotated_xml(input_file, expected_output_file)