wait, double quotes

pyproject.toml

@@ -28,9 +28,6 @@ fixable = ["I", "F401"]
 # *ignored for compatibility with formatter
 ignore = ["D203", "D205", "D206", "D213", "D400", "D415", "ANN101", "ANN003", "E501", "Q", "W191"]
 
-[tool.ruff.format]
-quote-style = "single"
-
 [tool.ruff.per-file-ignores]
 # ANN001 - missing-type-function-argument
 # ANN2 - missing-return-type

tests/conftest.py

@@ -17,56 +17,56 @@ def pytest_collection_modifyitems(items):
     When creating new test modules, be sure to add them here.
     """
     MODULE_ORDER = [  # noqa: N806
-        'test_chembl',
-        'test_chemidplus',
-        'test_drugbank',
-        'test_drugsatfda',
-        'test_guidetopharmacology',
-        'test_hemonc',
-        'test_ncit',
-        'test_rxnorm',
-        'test_wikidata',
-        'test_merge',
-        'test_database',
-        'test_query',
-        'test_emit_warnings',
-        'test_disease_indication',
+        "test_chembl",
+        "test_chemidplus",
+        "test_drugbank",
+        "test_drugsatfda",
+        "test_guidetopharmacology",
+        "test_hemonc",
+        "test_ncit",
+        "test_rxnorm",
+        "test_wikidata",
+        "test_merge",
+        "test_database",
+        "test_query",
+        "test_emit_warnings",
+        "test_disease_indication",
     ]
     items.sort(key=lambda i: MODULE_ORDER.index(i.module.__name__))
 
 
 TEST_ROOT = Path(__file__).resolve().parents[1]
-TEST_DATA_DIRECTORY = TEST_ROOT / 'tests' / 'data'
+TEST_DATA_DIRECTORY = TEST_ROOT / "tests" / "data"
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def test_data():
     """Provide test data location to test modules"""
     return TEST_DATA_DIRECTORY
 
 
-@pytest.fixture(scope='session', autouse=True)
+@pytest.fixture(scope="session", autouse=True)
 def db():
     """Provide a database instance to be used by tests."""
     database = Database()
-    if os.environ.get('THERAPY_TEST', '').lower() == 'true':
+    if os.environ.get("THERAPY_TEST", "").lower() == "true":
         if os.environ.get(AWS_ENV_VAR_NAME):
-            assert False, f'Cannot have both THERAPY_TEST and {AWS_ENV_VAR_NAME} set.'
-        existing_tables = database.dynamodb_client.list_tables()['TableNames']
-        if 'therapy_concepts' in existing_tables:
-            database.dynamodb_client.delete_table(TableName='therapy_concepts')
-        if 'therapy_metadata' in existing_tables:
-            database.dynamodb_client.delete_table(TableName='therapy_metadata')
-        existing_tables = database.dynamodb_client.list_tables()['TableNames']
+            assert False, f"Cannot have both THERAPY_TEST and {AWS_ENV_VAR_NAME} set."
+        existing_tables = database.dynamodb_client.list_tables()["TableNames"]
+        if "therapy_concepts" in existing_tables:
+            database.dynamodb_client.delete_table(TableName="therapy_concepts")
+        if "therapy_metadata" in existing_tables:
+            database.dynamodb_client.delete_table(TableName="therapy_metadata")
+        existing_tables = database.dynamodb_client.list_tables()["TableNames"]
         database.create_therapies_table(existing_tables)
         database.create_meta_data_table(existing_tables)
     return database
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def disease_normalizer():
     """Provide mock disease normalizer."""
-    with open(TEST_DATA_DIRECTORY / 'disease_normalization.json', 'r') as f:
+    with open(TEST_DATA_DIRECTORY / "disease_normalization.json", "r") as f:
         disease_data = json.load(f)
 
         def _normalize_disease(query: str):
@@ -75,7 +75,7 @@ def _normalize_disease(query: str):
     return _normalize_disease
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def test_source(db: Database, test_data: Path, disease_normalizer: Callable):
     """Provide query endpoint for testing sources. If THERAPY_TEST is set, will try to
     load DB from test data.
@@ -84,7 +84,7 @@ def test_source(db: Database, test_data: Path, disease_normalizer: Callable):
     """
 
     def test_source_factory(EtlClass: Base):  # noqa: N803
-        if os.environ.get('THERAPY_TEST', '').lower() == 'true':
+        if os.environ.get("THERAPY_TEST", "").lower() == "true":
             test_class = EtlClass(db, test_data)  # type: ignore
             test_class._normalize_disease = disease_normalizer  # type: ignore
             test_class.perform_etl(use_existing=True)
@@ -146,7 +146,7 @@ def _compare_records(actual: Drug, fixt: Drug):
             assert actual_inds[i] == fixture_inds[i]
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def compare_records():
     """Provide record comparison function"""
     return _compare_records
@@ -171,11 +171,11 @@ def _compare_response(
         fixture_list otherwise)
     """
     if fixture and fixture_list:
-        raise Exception('Args provided for both `fixture` and `fixture_list`')
+        raise Exception("Args provided for both `fixture` and `fixture_list`")
     elif not fixture and not fixture_list:
-        raise Exception('Must pass 1 of {fixture, fixture_list}')
+        raise Exception("Must pass 1 of {fixture, fixture_list}")
     if fixture and num_records:
-        raise Exception('`num_records` should only be given with ' '`fixture_list`.')
+        raise Exception("`num_records` should only be given with " "`fixture_list`.")
 
     assert response.match_type == match_type
     if fixture:
@@ -195,7 +195,7 @@ def _compare_response(
                 assert False  # test fixture not found in response
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def compare_response():
     """Provide response comparison function"""
     return _compare_response

tests/scripts/build_chembl_data.py

@@ -20,7 +20,7 @@
 ch = ChEMBL(Database())
 ch._extract_data()
 
-TEST_DATA_DIR = Path(__file__).resolve().parents[1] / 'data' / 'chembl'
+TEST_DATA_DIR = Path(__file__).resolve().parents[1] / "data" / "chembl"
 out_db_path = TEST_DATA_DIR / ch._src_file.name
 
 try:

tests/scripts/build_chemidplus_data.py

@@ -7,25 +7,25 @@
 from therapy.etl import ChemIDplus
 
 TEST_IDS = [
-    '87-08-1',
-    '152459-95-5',
-    '220127-57-1',
-    '15663-27-1',
-    '50-06-6',
-    '51186-83-5',
-    '8025-81-8',
-    '112901-68-5',
-    '20537-88-6',
+    "87-08-1",
+    "152459-95-5",
+    "220127-57-1",
+    "15663-27-1",
+    "50-06-6",
+    "51186-83-5",
+    "8025-81-8",
+    "112901-68-5",
+    "20537-88-6",
 ]
 
 ch = ChemIDplus(Database())
 ch._extract_data()
-TEST_DATA_DIR = Path(__file__).resolve().parents[1] / 'data' / 'chemidplus'
+TEST_DATA_DIR = Path(__file__).resolve().parents[1] / "data" / "chemidplus"
 outfile_path = TEST_DATA_DIR / ch._src_file.name
 
-root = ElementTree.Element('file')
-root.set('name', ch._src_file.name)
-root.set('date', ch._src_file.stem.split('chemidplus_')[1])
+root = ElementTree.Element("file")
+root.set("name", ch._src_file.name)
+root.set("date", ch._src_file.stem.split("chemidplus_")[1])
 
 
 def parse_xml(path: Path) -> Generator:
@@ -34,31 +34,31 @@ def parse_xml(path: Path) -> Generator:
     :param str tag: XML tag
     :return: generator yielding elements of corresponding tag
     """
-    context = iter(ElementTree.iterparse(path, events=('start', 'end')))
+    context = iter(ElementTree.iterparse(path, events=("start", "end")))
     _, root = next(context)
     for event, elem in context:
-        if event == 'end' and elem.tag == 'Chemical':
+        if event == "end" and elem.tag == "Chemical":
             yield elem
             root.clear()
 
 
 parser = parse_xml(ch._src_file)
 for chemical in parser:
-    regno = chemical.find('NumberList').find('CASRegistryNumber')
+    regno = chemical.find("NumberList").find("CASRegistryNumber")
     if not regno:
         continue
 
     if regno.text in TEST_IDS:
         root.append(chemical)
 
-with open(outfile_path, 'w') as f:
-    ElementTree.ElementTree(root).write(f, encoding='unicode')
+with open(outfile_path, "w") as f:
+    ElementTree.ElementTree(root).write(f, encoding="unicode")
 
 pi = ElementTree.ProcessingInstruction(
     target='xml version="1.0" encoding="UTF-8" standalone="yes"'
 )
-pi_string = ElementTree.tostring(pi).decode('UTF8')
-with open(outfile_path, 'r+') as f:
+pi_string = ElementTree.tostring(pi).decode("UTF8")
+with open(outfile_path, "r+") as f:
     content = f.read()
     f.seek(0, 0)
-    f.write(pi_string.rstrip('\r\n') + '\n' + content)
+    f.write(pi_string.rstrip("\r\n") + "\n" + content)

tests/scripts/build_disease_normalizer_data.py

@@ -12,13 +12,13 @@
 from therapy.etl import ChEMBL, HemOnc
 
 TEST_ROOT = Path(__file__).resolve().parents[1]
-TEST_DATA_DIRECTORY = TEST_ROOT / 'data'
+TEST_DATA_DIRECTORY = TEST_ROOT / "data"
 
 
 class ReadOnlyDatabase(Database):
     """Provide read-only instance of database for security's sake"""
 
-    def add_record(self, record: Dict, record_type: str = 'identity') -> None:
+    def add_record(self, record: Dict, record_type: str = "identity") -> None:
         """Add new record to database"""
         pass
 
@@ -31,7 +31,7 @@ def update_record(
         concept_id: str,
         field: str,
         new_value: Any,  # noqa
-        item_type: str = 'identity',
+        item_type: str = "identity",
     ) -> None:
         """Update an individual record"""
         pass
@@ -66,5 +66,5 @@ def normalize(self, query: str) -> DiseaseNormalizationService:
 h.perform_etl(use_existing=True)
 
 
-with open(TEST_DATA_DIRECTORY / 'disease_normalization.json', 'w') as f:
+with open(TEST_DATA_DIRECTORY / "disease_normalization.json", "w") as f:
     json.dump(disease_normalizer_table, f)

tests/scripts/build_drugsatfda_data.py

@@ -6,39 +6,39 @@
 from therapy.etl import DrugsAtFDA
 
 TEST_IDS = [
-    'NDA020221',
-    'NDA022334',
-    'NDA050682',
-    'ANDA074656',
-    'ANDA075036',
-    'ANDA074735',
-    'ANDA206774',
-    'ANDA207323',
-    'NDA018057',
-    'ANDA072267',
-    'NDA017604',
-    'NDA210595',
-    'NDA202450',
-    'NDA091141',
-    'NDA022007',
-    'NDA050682',
-    'NDA017604',
-    'ANDA214475',
+    "NDA020221",
+    "NDA022334",
+    "NDA050682",
+    "ANDA074656",
+    "ANDA075036",
+    "ANDA074735",
+    "ANDA206774",
+    "ANDA207323",
+    "NDA018057",
+    "ANDA072267",
+    "NDA017604",
+    "NDA210595",
+    "NDA202450",
+    "NDA091141",
+    "NDA022007",
+    "NDA050682",
+    "NDA017604",
+    "ANDA214475",
 ]
 
 daf = DrugsAtFDA(Database())
 daf._extract_data()
-TEST_DATA_DIR = Path(__file__).resolve().parents[1] / 'data' / 'drugsatfda'
+TEST_DATA_DIR = Path(__file__).resolve().parents[1] / "data" / "drugsatfda"
 outfile_path = TEST_DATA_DIR / daf._src_file.name
 
-with open(daf._src_file, 'r') as f:
+with open(daf._src_file, "r") as f:
     data = json.load(f)
 
-out_data = {'meta': data['meta'], 'results': []}
+out_data = {"meta": data["meta"], "results": []}
 
-for record in data['results']:
-    if record['application_number'] in TEST_IDS:
-        out_data['results'].append(record)
+for record in data["results"]:
+    if record["application_number"] in TEST_IDS:
+        out_data["results"].append(record)
 
-with open(outfile_path, 'w') as f:
+with open(outfile_path, "w") as f:
     json.dump(out_data, f)

tests/scripts/build_gtop_data.py

@@ -5,38 +5,38 @@
 from therapy.database import Database
 from therapy.etl import GuideToPHARMACOLOGY
 
-TEST_IDS = {'5343', '2169', '2804', '240', '3303', '5260'}
+TEST_IDS = {"5343", "2169", "2804", "240", "3303", "5260"}
 
 gtop = GuideToPHARMACOLOGY(Database())
 gtop._extract_data()
-TEST_DATA_DIR = Path(__file__).resolve().parents[1] / 'data' / 'guidetopharmacology'
+TEST_DATA_DIR = Path(__file__).resolve().parents[1] / "data" / "guidetopharmacology"
 ligands_file_path = TEST_DATA_DIR / gtop._ligands_file.name
 mapping_file_path = TEST_DATA_DIR / gtop._mapping_file.name
 
 ligands_rows = []
-with open(gtop._ligands_file, 'r') as f:
-    reader = csv.reader(f, delimiter='\t')
+with open(gtop._ligands_file, "r") as f:
+    reader = csv.reader(f, delimiter="\t")
     ligands_rows.append(next(reader))
     ligands_rows.append(next(reader))
 
     for row in reader:
         if row[0] in TEST_IDS:
             ligands_rows.append(row)
 
-with open(ligands_file_path, 'w') as f:
-    writer = csv.writer(f, delimiter='\t', quoting=csv.QUOTE_ALL)
+with open(ligands_file_path, "w") as f:
+    writer = csv.writer(f, delimiter="\t", quoting=csv.QUOTE_ALL)
     writer.writerows(ligands_rows)
 
 map_rows = []
-with open(gtop._mapping_file, 'r') as f:
-    reader = csv.reader(f, delimiter='\t')
+with open(gtop._mapping_file, "r") as f:
+    reader = csv.reader(f, delimiter="\t")
     map_rows.append(next(reader))
     map_rows.append(next(reader))
 
     for row in reader:
         if row[0] in TEST_IDS:
             map_rows.append(row)
 
-with open(mapping_file_path, 'w') as f:
-    writer = csv.writer(f, delimiter='\t', quoting=csv.QUOTE_ALL)
+with open(mapping_file_path, "w") as f:
+    writer = csv.writer(f, delimiter="\t", quoting=csv.QUOTE_ALL)
     writer.writerows(map_rows)