style: add ruff updates (#406)

.pre-commit-config.yaml

@@ -7,7 +7,7 @@ repos:
       - id: trailing-whitespace
       - id: end-of-file-fixer
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.1.6
+    rev: v0.1.14
     hooks:
       - id: ruff-format
       - id: ruff

pyproject.toml

@@ -37,7 +37,7 @@ dynamic = ["version"]
 [project.optional-dependencies]
 etl = ["disease-normalizer[etl]~=0.4.0.dev0", "owlready2", "rdflib", "wikibaseintegrator>=0.12.0", "wags-tails"]
 test = ["pytest", "pytest-cov", "pytest-mock"]
-dev = ["pre-commit", "ruff>=0.1.2", "lxml", "xmlformatter", "mypy", "types-pyyaml"]
+dev = ["pre-commit", "ruff>=0.1.14", "lxml", "xmlformatter", "mypy", "types-pyyaml"]
 
 [project.urls]
 Homepage = "https://github.com/cancervariants/therapy-normalization"
@@ -76,15 +76,49 @@ ignore_missing_imports = true
 
 [tool.ruff]
 src = ["src"]
-# pycodestyle (E, W)
-# Pyflakes (F)
-# flake8-annotations (ANN)
-# pydocstyle (D)
-# pep8-naming (N)
-# isort (I)
-select = ["E", "W", "F", "ANN", "D", "N", "I"]
-fixable = ["I", "F401"]
-
+select = [
+    "F",  # https://docs.astral.sh/ruff/rules/#pyflakes-f
+    "E", "W",  # https://docs.astral.sh/ruff/rules/#pycodestyle-e-w
+    "I",  # https://docs.astral.sh/ruff/rules/#isort-i
+    "N",  # https://docs.astral.sh/ruff/rules/#pep8-naming-n
+    "D",  # https://docs.astral.sh/ruff/rules/#pydocstyle-d
+    "UP",  # https://docs.astral.sh/ruff/rules/#pyupgrade-up
+    "ANN",  # https://docs.astral.sh/ruff/rules/#flake8-annotations-ann
+    "ASYNC",  # https://docs.astral.sh/ruff/rules/#flake8-async-async
+    "S",  # https://docs.astral.sh/ruff/rules/#flake8-bandit-s
+    "B",  # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
+    "A",  # https://docs.astral.sh/ruff/rules/#flake8-builtins-a
+    "C4",  # https://docs.astral.sh/ruff/rules/#flake8-comprehensions-c4
+    "DTZ",  # https://docs.astral.sh/ruff/rules/#flake8-datetimez-dtz
+    "T10",  # https://docs.astral.sh/ruff/rules/#flake8-datetimez-dtz
+    "EM",  # https://docs.astral.sh/ruff/rules/#flake8-errmsg-em
+    "G",  # https://docs.astral.sh/ruff/rules/#flake8-logging-format-g
+    "PIE",  # https://docs.astral.sh/ruff/rules/#flake8-pie-pie
+    "T20",  # https://docs.astral.sh/ruff/rules/#flake8-print-t20
+    "PT",  # https://docs.astral.sh/ruff/rules/#flake8-pytest-style-pt
+    "Q",  # https://docs.astral.sh/ruff/rules/#flake8-quotes-q
+    "RSE",  # https://docs.astral.sh/ruff/rules/#flake8-raise-rse
+    "RET",  # https://docs.astral.sh/ruff/rules/#flake8-return-ret
+    "SIM",  # https://docs.astral.sh/ruff/rules/#flake8-simplify-sim
+    "PTH",  # https://docs.astral.sh/ruff/rules/#flake8-use-pathlib-pth
+    "PGH",  # https://docs.astral.sh/ruff/rules/#pygrep-hooks-pgh
+    "RUF",  # https://docs.astral.sh/ruff/rules/#ruff-specific-rules-ruf
+]
+fixable = [
+    "I",
+    "F401",
+    "D",
+    "UP",
+    "ANN",
+    "B",
+    "C4",
+    "G",
+    "PIE",
+    "PT",
+    "RSE",
+    "SIM",
+    "RUF"
+]
 # ANN101 - missing-type-self
 # ANN003 - missing-type-kwargs
 # D203 - one-blank-line-before-class
@@ -99,12 +133,14 @@ fixable = ["I", "F401"]
 # E117 - over-indented*
 # E501 - line-too-long*
 # W191 - tab-indentation*
+# PGH003 - blanket-type-ignore
 # *ignored for compatibility with formatter
 ignore = [
     "ANN101", "ANN003",
     "D203", "D205", "D206", "D213", "D300", "D400", "D415",
     "E111", "E114", "E117", "E501",
-    "W191"
+    "W191",
+    "PGH003",
 ]
 
 [tool.ruff.per-file-ignores]
@@ -113,5 +149,9 @@ ignore = [
 # ANN201 - Missing type annotation
 # ANN102 - missing-type-cls
 # N805 - invalid-first-argument-name-for-method
-"tests/*" = ["ANN001", "ANN102", "ANN2"]
+# S101 - assert
+# B011 - assert-false
+# RUF001 - ambiguous-unicode-character-string
+"tests/*" = ["ANN001", "ANN102", "ANN2", "S101", "B011"]
+"tests/unit/test_emit_warnings.py" = ["RUF001"]
 "src/therapy/schemas.py" = ["ANN001", "ANN201", "N805"]

src/therapy/__init__.py

@@ -7,7 +7,7 @@
 APP_ROOT: Path = Path(__file__).resolve().parents[0]
 
 
-from therapy.schemas import (  # noqa: E402, I100, I202
+from therapy.schemas import (  # noqa: E402
     NamespacePrefix,
     RefType,
     SourceName,
@@ -29,7 +29,7 @@
 PREFIX_LOOKUP = {
     v.value: SourceName[k].value
     for k, v in NamespacePrefix.__members__.items()
-    if k in SourceName.__members__.keys()
+    if k in SourceName.__members__
 }
 
 # Namespace LUI patterns. Use for namespace inference.
@@ -43,7 +43,7 @@
 )
 
 # Sources that we import directly
-XREF_SOURCES = {source for source in SourceName.__members__}
+XREF_SOURCES = set(SourceName.__members__)
 
 # Sources that are found in data from imported sources
-ASSOC_WITH_SOURCES = {source for source in NamespacePrefix.__members__} - XREF_SOURCES
+ASSOC_WITH_SOURCES = set(NamespacePrefix.__members__) - XREF_SOURCES

src/therapy/cli.py

@@ -100,7 +100,7 @@ def _load_source(
             f"Encountered ModuleNotFoundError attempting to import {e.name}. Are ETL dependencies installed?"
         )
         click.get_current_context().exit()
-    SourceClass = eval(name.value)  # noqa: N806
+    SourceClass = eval(name.value)  # noqa: N806 PGH001 S307
 
     source = SourceClass(database=db, silent=False)
     try:
@@ -177,7 +177,7 @@ def _update_normalizer(
     :param use_existing: if True, use most recent local version of source data instead of
         fetching from remote
     """
-    processed_ids: List[str] = list()
+    processed_ids: List[str] = []
     for n in sources:
         delete_time = _delete_source(n, db)
         _load_source(n, db, delete_time, processed_ids, use_existing)
@@ -255,12 +255,14 @@ def update_normalizer_db(
         sources_split = sources.lower().split()
 
         if len(sources_split) == 0:
-            raise Exception("Must enter 1 or more source names to update")
+            msg = "Must enter 1 or more source names to update"
+            raise Exception(msg)
 
         non_sources = set(sources_split) - set(SOURCES)
 
         if len(non_sources) != 0:
-            raise Exception(f"Not valid source(s): {non_sources}")
+            msg = f"Not valid source(s): {non_sources}"
+            raise Exception(msg)
 
         parsed_source_names = {SourceName(SOURCES[s]) for s in sources_split}
         if (

src/therapy/database/database.py

@@ -63,12 +63,10 @@ def _check_delete_okay() -> bool:
         """
         if environ.get(AWS_ENV_VAR_NAME) == AwsEnvName.PRODUCTION:
             if environ.get(SKIP_AWS_DB_ENV_NAME) == "true":
-                raise DatabaseWriteError(
-                    f"Must unset {SKIP_AWS_DB_ENV_NAME} env variable to enable drop_db()"
-                )
+                msg = f"Must unset {SKIP_AWS_DB_ENV_NAME} env variable to enable drop_db()"
+                raise DatabaseWriteError(msg)
             return click.confirm("Are you sure you want to delete existing data?")
-        else:
-            return True
+        return True
 
     @abc.abstractmethod
     def drop_db(self) -> None:
@@ -347,7 +345,7 @@ def create_db(
     else:
         if db_url:
             endpoint_url = db_url
-        elif "THERAPY_NORM_DB_URL" in environ.keys():
+        elif "THERAPY_NORM_DB_URL" in environ:
             endpoint_url = environ["THERAPY_NORM_DB_URL"]
         else:
             endpoint_url = "http://localhost:8000"