style: update to ruff==0.5.0

.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: v0.2.0
+    rev: v0.5.0  # ruff version
     hooks:
       - id: ruff-format
       - id: ruff

pyproject.toml

@@ -44,7 +44,7 @@ etl = [
     "rich"
 ]
 test = ["pytest", "pytest-cov", "pytest-mock"]
-dev = ["pre-commit", "ruff==0.2.0", "lxml", "xmlformatter", "types-pyyaml"]
+dev = ["pre-commit", "ruff==0.5.0", "lxml", "xmlformatter", "types-pyyaml"]
 
 [project.urls]
 Homepage = "https://github.com/cancervariants/therapy-normalization"
@@ -97,16 +97,22 @@ select = [
     "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
+    "LOG",  # https://docs.astral.sh/ruff/rules/#flake8-logging-log
     "G",  # https://docs.astral.sh/ruff/rules/#flake8-logging-format-g
+    "INP",  # https://docs.astral.sh/ruff/rules/#flake8-no-pep420-inp
     "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
+    "SLF",  # https://docs.astral.sh/ruff/rules/#flake8-self-slf
     "SIM",  # https://docs.astral.sh/ruff/rules/#flake8-simplify-sim
+    "ARG",  # https://docs.astral.sh/ruff/rules/#flake8-unused-arguments-arg
     "PTH",  # https://docs.astral.sh/ruff/rules/#flake8-use-pathlib-pth
     "PGH",  # https://docs.astral.sh/ruff/rules/#pygrep-hooks-pgh
+    "PERF",  # https://docs.astral.sh/ruff/rules/#perflint-perf
+    "FURB",  # https://docs.astral.sh/ruff/rules/#refurb-furb
     "RUF",  # https://docs.astral.sh/ruff/rules/#ruff-specific-rules-ruf
 ]
 fixable = [
@@ -117,15 +123,19 @@ fixable = [
     "ANN",
     "B",
     "C4",
+    "LOG",
     "G",
     "PIE",
     "PT",
     "RSE",
     "SIM",
+    "PERF",
+    "FURB",
     "RUF"
 ]
-# ANN101 - missing-type-self
 # ANN003 - missing-type-kwargs
+# ANN101 - missing-type-self
+# ANN102 - missing-type-cls
 # D203 - one-blank-line-before-class
 # D205 - blank-line-after-summary
 # D206 - indent-with-spaces*
@@ -142,7 +152,7 @@ fixable = [
 # S321 - suspicious-ftp-lib-usage
 # *ignored for compatibility with formatter
 ignore = [
-    "ANN101", "ANN003",
+    "ANN003", "ANN101", "ANN102",
     "D203", "D205", "D206", "D213", "D300", "D400", "D415",
     "E111", "E114", "E117", "E501",
     "PGH003",
@@ -158,6 +168,12 @@ ignore = [
 # B011 - assert-false
 # N805 - invalid-first-argument-name-for-method
 # RUF001 - ambiguous-unicode-character-string
-"tests/*" = ["ANN001", "ANN2", "ANN102", "S101", "B011"]
+# INP001 - implicit-namespace-package
+# SLF001 - private-member-access
+# PERF401 - manual-list-comprehension
+"tests/*" = ["ANN001", "ANN2", "ANN102", "S101", "B011", "INP001", "SLF001", "PERF401"]
 "tests/unit/test_emit_warnings.py" = ["RUF001"]
 "src/therapy/schemas.py" = ["ANN001", "ANN201", "N805"]
+
+[tool.ruff.format]
+docstring-code-format = true

src/therapy/__init__.py

@@ -1,4 +1,5 @@
 """The VICC library for normalizing therapies."""
+
 import re
 from pathlib import Path
 

src/therapy/cli.py

@@ -1,4 +1,5 @@
 """Provides a CLI util to make updates to normalizer database."""
+
 import logging
 from collections.abc import Collection
 from timeit import default_timer as timer

src/therapy/database/__init__.py

@@ -1,4 +1,5 @@
 """Provide database clients."""
+
 from .database import (
     AWS_ENV_VAR_NAME,
     AbstractDatabase,

src/therapy/database/database.py

@@ -1,4 +1,5 @@
 """Provide abstract Database class and relevant tools for database initialization."""
+
 import abc
 import sys
 from collections.abc import Generator
@@ -313,8 +314,7 @@ def create_db(
     >>> local_db = create_db()  # creates DynamoDB connection on port 8001
     >>>
     >>> os.environ["THERAPY_NORM_ENV"] = "Prod"
-    >>> prod_db = create_db()  # creates connection to AWS cloud DynamoDB instance,
-    >>>                        # overruling `THERAPY_NORM_DB_URL` variable setting
+    >>> prod_db = create_db()  # creates connection to AWS cloud DynamoDB instance, overruling `THERAPY_NORM_DB_URL` variable setting
 
     Precedence is handled for connection settings like so:
 

src/therapy/database/dynamodb.py

@@ -1,4 +1,5 @@
 """Provide DynamoDB client."""
+
 import atexit
 import logging
 import sys
@@ -607,7 +608,7 @@ def delete_source(self, src_name: SourceName) -> None:
                                 "concept_id": record["concept_id"],
                             }
                         )
-                    except ClientError as e:
+                    except ClientError as e:  # noqa: PERF203
                         raise DatabaseWriteError(e) from e
 
     def complete_write_transaction(self) -> None:

src/therapy/etl/__init__.py

@@ -1,4 +1,5 @@
 """Module to load and init namespace at package level"""
+
 from .base import EtlError
 from .chembl import ChEMBL
 from .chemidplus import ChemIDplus

src/therapy/etl/base.py

@@ -1,4 +1,5 @@
 """A base class for extraction, transformation, and loading of data."""
+
 import contextlib
 import json
 import logging
@@ -71,9 +72,17 @@ def __init__(
         # self._name = SourceName[self.__class__.__name__.upper()]
         self._silent = silent
         self._name = SourceName(self.__class__.__name__)
-        self._data_source: ChemblData | ChemIDplusData | DrugBankData | DrugsAtFdaData | GToPLigandData | HemOncData | NcitData | RxNormData | CustomData = self._get_data_handler(
-            data_path
-        )  # type: ignore
+        self._data_source: (
+            ChemblData
+            | ChemIDplusData
+            | DrugBankData
+            | DrugsAtFdaData
+            | GToPLigandData
+            | HemOncData
+            | NcitData
+            | RxNormData
+            | CustomData
+        ) = self._get_data_handler(data_path)  # type: ignore
         self.database = database
         self._added_ids: list[str] = []
         self._rules = Rules(self._name)

src/therapy/etl/chembl.py

@@ -1,4 +1,5 @@
 """Defines the ChEMBL ETL methods."""
+
 import sqlite3
 
 from tqdm import tqdm

src/therapy/etl/chemidplus.py

@@ -2,6 +2,7 @@
 
 Courtesy of the U.S. National Library of Medicine.
 """
+
 import re
 import xml.etree.ElementTree as ElTree
 from collections.abc import Generator
@@ -61,9 +62,9 @@ def _transform_data(self) -> None:
                 reg_no = chemical.find("NumberList").find("CASRegistryNumber")
                 if not reg_no:
                     continue
-                params[
-                    "concept_id"
-                ] = f"{NamespacePrefix.CASREGISTRY.value}:{reg_no.text}"
+                params["concept_id"] = (
+                    f"{NamespacePrefix.CASREGISTRY.value}:{reg_no.text}"
+                )
 
                 # get aliases
                 aliases = []

src/therapy/etl/drugbank.py

@@ -1,4 +1,5 @@
 """Defines the DrugBank ETL methods."""
+
 import csv
 from typing import Any
 

src/therapy/etl/drugsatfda.py

@@ -1,4 +1,5 @@
 """ETL methods for the Drugs@FDA source."""
+
 import json
 import logging
 

src/therapy/etl/guidetopharmacology.py

@@ -1,4 +1,5 @@
 """Module for Guide to PHARMACOLOGY ETL methods."""
+
 import csv
 import html
 import logging

src/therapy/etl/hemonc.py

@@ -1,4 +1,5 @@
 """Provide ETL methods for HemOnc.org data."""
+
 import csv
 import logging
 

src/therapy/etl/ncit.py

@@ -1,4 +1,5 @@
 """ETL methods for NCIt source"""
+
 import logging
 
 import owlready2 as owl

src/therapy/etl/rules.py

@@ -1,4 +1,5 @@
 """Apply manual data restrictions and annotations to extracted records."""
+
 import csv
 
 from therapy import APP_ROOT

src/therapy/etl/rxnorm.py

@@ -5,6 +5,7 @@
  and Human Services; NLM is not responsible for the product and does not
  endorse or recommend this or any other product."
 """
+
 import csv
 import logging
 import re
@@ -89,7 +90,7 @@ def _extract_data(self, use_existing: bool) -> None:
             src_name="rxnorm_drug_forms",
             filetype="yaml",
             latest_version_cb=lambda: self._version,
-            download_cb=lambda version, file: self._create_drug_form_yaml(
+            download_cb=lambda version, file: self._create_drug_form_yaml(  # noqa: ARG005
                 file,
                 self._data_file,  # type: ignore
             ),
@@ -194,7 +195,7 @@ def _get_trade_names(
 
         if "PIN" in value and value["PIN"] in precise_ingredient:
             for pin in precise_ingredient[value["PIN"]]:
-                labels.append(pin.lower())
+                labels.append(pin.lower())  # noqa: PERF401
 
         for label in labels:
             trade_names: list[str] = [

src/therapy/etl/wikidata.py

@@ -1,4 +1,5 @@
 """Defines the Wikidata ETL methods."""
+
 import datetime
 import json
 from pathlib import Path
@@ -90,7 +91,7 @@ class Wikidata(Base):
     """Class for Wikidata ETL methods."""
 
     @staticmethod
-    def _download_data(version: str, file: Path) -> None:
+    def _download_data(version: str, file: Path) -> None:  # noqa: ARG004
         """Download latest Wikidata source dump.
 
         :param version: not used by this method

src/therapy/main.py

@@ -1,4 +1,5 @@
 """Main application for FastAPI"""
+
 import html
 
 from fastapi import FastAPI, HTTPException, Query

src/therapy/query.py

@@ -1,4 +1,5 @@
 """Provides methods for handling queries."""
+
 import datetime
 import json
 import re
@@ -143,7 +144,7 @@ def _fetch_records(
                     raise KeyError(msg)
                 (response, src) = self._add_record(response, match, match_type)
                 matched_sources.add(src)
-            except ClientError as e:
+            except ClientError as e:  # noqa: PERF203
                 logger.error(e.response["Error"]["Message"])
 
         return response, matched_sources
@@ -302,9 +303,7 @@ def search(
             if invalid source names are given.
         """
         sources = {}
-        for k, v in SOURCES.items():
-            if self.db.get_source_metadata(v):
-                sources[k] = v
+        sources = {k: v for k, v in SOURCES.items() if self.db.get_source_metadata(v)}
         if not incl and not excl:
             query_sources = set(sources.values())
         elif incl and excl:
@@ -359,7 +358,7 @@ def _add_merged_meta(self, response: NormalizationService) -> NormalizationServi
         for src in sources:
             try:
                 src_name = SourceName(PREFIX_LOOKUP[src])
-            except KeyError:
+            except KeyError:  # noqa: PERF203
                 # not an imported source
                 continue
             else:
@@ -382,7 +381,6 @@ def _add_therapeutic_agent(
         self,
         response: NormalizationService,
         record: dict,
-        query: str,
         match_type: MatchType,
     ) -> NormalizationService:
         """Format received DB record as therapeutic agent and update response object.
@@ -538,10 +536,9 @@ def normalize(self, query: str, infer: bool = True) -> NormalizationService:
         # prepare basic response
         response = NormalizationService(**self._prepare_normalized_response(query))
 
-        add_ta_curry = lambda res, rec, mat: self._add_therapeutic_agent(  # noqa: E731
-            res, rec, query, mat
+        return self._perform_normalized_lookup(
+            response, query, infer, self._add_therapeutic_agent
         )
-        return self._perform_normalized_lookup(response, query, infer, add_ta_curry)
 
     def _construct_drug_match(self, record: dict) -> Therapy:
         """Create individual Drug match for unmerged normalization endpoint.

src/therapy/schemas.py

@@ -1,4 +1,5 @@
 """Contains data models for representing VICC therapy records."""
+
 from datetime import datetime
 from enum import Enum, IntEnum
 from typing import Any, Literal
@@ -354,9 +355,9 @@ class ServiceMeta(BaseModel):
     name: Literal["thera-py"] = "thera-py"
     version: Literal[__version__] = __version__  # type: ignore[valid-type]
     response_datetime: datetime
-    url: Literal[
+    url: Literal["https://github.com/cancervariants/therapy-normalization"] = (
         "https://github.com/cancervariants/therapy-normalization"
-    ] = "https://github.com/cancervariants/therapy-normalization"
+    )
 
     model_config = ConfigDict(
         json_schema_extra={

src/therapy/version.py

@@ -1,2 +1,3 @@
 """Therapy normalizer version"""
+
 __version__ = "0.5.0-dev5"

tests/conftest.py

@@ -1,4 +1,5 @@
 """Pytest test config tools."""
+
 import json
 import logging
 import os

tests/scripts/build_chembl_data.py

@@ -1,4 +1,5 @@
 """Construct test data for ChEMBL source."""
+
 import contextlib
 import sqlite3
 from pathlib import Path

tests/scripts/build_chemidplus_data.py

@@ -1,4 +1,5 @@
 """Build chemidplus test data."""
+
 from collections.abc import Generator
 from pathlib import Path
 from xml.etree import ElementTree

tests/scripts/build_disease_normalizer_data.py

@@ -1,6 +1,7 @@
 """Construct static mapping of disease normalizer input.
 Assumes complete and functioning disease normalizer endpoint is available.
 """
+
 import json
 from pathlib import Path
 

tests/scripts/build_drugbank_data.py

@@ -1,4 +1,5 @@
 """Build DrugBank test data."""
+
 import csv
 from pathlib import Path
 

tests/scripts/build_drugsatfda_data.py

@@ -1,4 +1,5 @@
 """Build drugsatfda test data"""
+
 import json
 from pathlib import Path
 

tests/scripts/build_gtop_data.py

@@ -1,4 +1,5 @@
 """Build test data for GuideToPharmacology"""
+
 import csv
 from pathlib import Path