style: update ruff to 0.5.0 (#355)

.pre-commit-config.yaml

@@ -8,7 +8,7 @@ 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
   hooks:
     - id: ruff
     - id: ruff-format

Pipfile

@@ -9,7 +9,7 @@ fastapi = "*"
 uvicorn = "*"
 click = "*"
 boto3 = "*"
-"ga4gh.vrs" = "~=2.0.0a1"
+"ga4gh.vrs" = "~=2.0.0a8"
 
 [dev-packages]
 gene = {editable = true, path = "."}
@@ -19,7 +19,7 @@ wags-tails = ">=0.1.1"
 psycopg = {version = "*", extras=["binary"]}
 pytest = "*"
 pre-commit = "*"
-ruff = ">=0.1.2"
+ruff = "==0.5.0"
 pytest-cov = "*"
 httpx = "*"
 mock = "*"

docs/scripts/generate_normalize_figure.py

@@ -6,9 +6,9 @@
 
 Embeddable HTML for the normalization figure should be deposited in the correct
 location, within docs/source/_static/html/.
-"""
+"""  # noqa: INP001
+
 import json
-from typing import Dict
 
 import gravis as gv
 
@@ -24,7 +24,7 @@
 ]
 
 
-def create_gjgf(result: UnmergedNormalizationService) -> Dict:
+def create_gjgf(result: UnmergedNormalizationService) -> dict:
     """Create gravis input.
 
     :param result: result from Unmerged Normalization search
@@ -43,36 +43,39 @@ def create_gjgf(result: UnmergedNormalizationService) -> Dict:
         }
     }
 
-    for i, (source, matches) in enumerate(result.source_matches.items()):
+    for i, (_, matches) in enumerate(result.source_matches.items()):
         for match in matches.records:
             graph["graph"]["nodes"][match.concept_id] = {
                 "metadata": {
                     "color": COLORS[i],
-                    "hover": f"{match.concept_id}\n{match.symbol}\n<i>{match.label}</i>",  # noqa: E501
-                    "click": f"<p color='black'>{json.dumps(match.model_dump(), indent=2)}</p>",  # noqa: E501
+                    "hover": f"{match.concept_id}\n{match.symbol}\n<i>{match.label}</i>",
+                    "click": f"<p color='black'>{json.dumps(match.model_dump(), indent=2)}</p>",
                 }
             }
             for xref in match.xrefs:
                 graph["graph"]["edges"].append(
                     {"source": match.concept_id, "target": xref}
                 )
 
-    included_edges = []
-    for edge in graph["graph"]["edges"]:
+    included_edges = [
+        edge
+        for edge in graph["graph"]["edges"]
         if (
             edge["target"] in graph["graph"]["nodes"]
             and edge["source"] in graph["graph"]["nodes"]
-        ):
-            included_edges.append(edge)
+        )
+    ]
+
     graph["graph"]["edges"] = included_edges
 
     included_nodes = {k["source"] for k in graph["graph"]["edges"]}.union(
         {k["target"] for k in graph["graph"]["edges"]}
     )
-    new_nodes = {}
-    for key, value in graph["graph"]["nodes"].items():
-        if key in included_nodes:
-            new_nodes[key] = value
+    new_nodes = {
+        key: value
+        for key, value in graph["graph"]["nodes"].items()
+        if key in included_nodes
+    }
     graph["graph"]["nodes"] = new_nodes
 
     return graph

docs/source/conf.py

@@ -79,7 +79,7 @@ def linkcode_resolve(domain, info):
     if not info["module"]:
         return None
     filename = info["module"].replace(".", "/")
-    return f"https://github.com/cancervariants/gene-normalization/blob/main/{filename}.py"  # noqa: E501
+    return f"https://github.com/cancervariants/gene-normalization/blob/main/{filename}.py"
 
 
 # -- code block style --------------------------------------------------------

pyproject.toml

@@ -37,7 +37,7 @@ dynamic = ["version"]
 pg = ["psycopg[binary]"]
 etl = ["gffutils", "biocommons.seqrepo", "wags-tails>=0.1.1"]
 test = ["pytest>=6.0", "pytest-cov", "mock", "httpx"]
-dev = ["pre-commit", "ruff==0.2.0"]
+dev = ["pre-commit", "ruff==0.5.0"]
 docs = [
     "sphinx==6.1.3",
     "sphinx-autodoc-typehints==1.22.0",
@@ -107,16 +107,22 @@ 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 = [
@@ -127,15 +133,19 @@ 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*
@@ -151,7 +161,7 @@ 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",
     "W191",
@@ -169,7 +179,13 @@ ignore = [
 # D100 - undocumented-public-module
 # D103 - undocumented-public-function
 # I001 - unsorted-imports
-"tests/*" = ["ANN001", "ANN2", "ANN102", "S101", "B011"]
+# INP001 - implicit-namespace-package
+# ARG001 - unused-function-argument
+# SLF001 - private-member-acces
+"tests/*" = ["ANN001", "ANN2", "ANN102", "S101", "INP001", "SLF001", "ARG001"]
 "*__init__.py" = ["F401"]
 "gene/schemas.py" = ["ANN001", "ANN201", "N805"]
 "docs/source/conf.py" = ["D100", "I001", "D103", "ANN201", "ANN001"]
+
+[tool.ruff.format]
+docstring-code-format = true

src/gene/__init__.py

@@ -1,8 +1,9 @@
 """The VICC library for normalizing genes."""
+
 from os import environ
 from pathlib import Path
 
-from .version import __version__  # noqa: F401
+from .version import __version__
 
 APP_ROOT = Path(__file__).resolve().parent
 
@@ -37,7 +38,7 @@ class DownloadException(Exception):  # noqa: N818
 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__
 }
 
 # use to generate namespace prefix from source ID value

src/gene/cli.py

@@ -1,9 +1,10 @@
 """Provides a CLI util to make updates to normalizer database."""
+
 import logging
 import os
+from collections.abc import Collection
 from pathlib import Path
 from timeit import default_timer as timer
-from typing import Collection, List, Optional, Set
 
 import click
 
@@ -61,7 +62,7 @@ def check_db(db_url: str, verbose: bool = False) -> None:
 @click.command()
 @click.option("--data_url", help="URL to data dump")
 @click.option("--db_url", help="URL endpoint for the application database.")
-def update_from_remote(data_url: Optional[str], db_url: str) -> None:
+def update_from_remote(data_url: str | None, db_url: str) -> None:
     """Update data from remotely-hosted DB dump. By default, fetches from latest
     available dump on VICC S3 bucket; specific URLs can be provided instead by
     command line option or GENE_NORM_REMOTE_DB_URL environment variable.
@@ -81,10 +82,10 @@ def update_from_remote(data_url: Optional[str], db_url: str) -> None:
     except NotImplementedError:
         click.echo(
             f"Error: Fetching remote data dump not supported for {db.__class__.__name__}"
-        )  # noqa: E501
+        )
         click.get_current_context().exit(1)
     except DatabaseException as e:
-        click.echo(f"Encountered exception during update: {str(e)}")
+        click.echo(f"Encountered exception during update: {e!s}")
         click.get_current_context().exit(1)
     _logger.info("Successfully loaded data from remote snapshot.")
 
@@ -106,18 +107,18 @@ def dump_database(output_directory: Path, db_url: str) -> None:
     """  # noqa: D301
     _configure_logging()
     if not output_directory:
-        output_directory = Path(".")
+        output_directory = Path()
 
     db = create_db(db_url, False)
     try:
         db.export_db(output_directory)
     except NotImplementedError:
         click.echo(
             f"Error: Dumping data to file not supported for {db.__class__.__name__}"
-        )  # noqa: E501
+        )
         click.get_current_context().exit(1)
     except DatabaseException as e:
-        click.echo(f"Encountered exception during update: {str(e)}")
+        click.echo(f"Encountered exception during update: {e!s}")
         click.get_current_context().exit(1)
     _logger.info("Database dump successful.")
 
@@ -137,7 +138,7 @@ def _update_normalizer(
     :param use_existing: if True, use most recent local version of source data instead of
         fetching from remote
     """
-    processed_ids = list()
+    processed_ids = []
     for n in sources:
         delete_time = _delete_source(n, db)
         _load_source(n, db, delete_time, processed_ids, use_existing)
@@ -173,7 +174,7 @@ def _load_source(
     n: SourceName,
     db: AbstractDatabase,
     delete_time: float,
-    processed_ids: List[str],
+    processed_ids: list[str],
     use_existing: bool,
 ) -> None:
     """Load individual source data.
@@ -199,7 +200,7 @@ def _load_source(
             f"Encountered ModuleNotFoundError attempting to import {e.name}. {_etl_dependency_help}"
         )
         click.get_current_context().exit()
-    SourceClass = eval(n.value)  # noqa: N806
+    SourceClass = eval(n.value)  # noqa: N806, S307
 
     source = SourceClass(database=db, silent=False)
     try:
@@ -234,7 +235,7 @@ def _delete_normalized_data(database: AbstractDatabase) -> None:
     click.echo(f"Deleted normalized records in {delete_time:.5f} seconds.")
 
 
-def _load_merge(db: AbstractDatabase, processed_ids: Set[str]) -> None:
+def _load_merge(db: AbstractDatabase, processed_ids: set[str]) -> None:
     """Load merged concepts
 
     :param db: database instance
@@ -313,19 +314,21 @@ def update_normalizer_db(
             ctx = click.get_current_context()
             click.echo(
                 "Must either enter 1 or more sources, or use `--update_all` parameter"
-            )  # noqa: E501
+            )
             click.echo(ctx.get_help())
             ctx.exit()
     else:
         sources_split = sources.lower().split()
 
         if len(sources_split) == 0:
-            raise Exception("Must enter 1 or more source names to update")
+            err_msg = "Must enter 1 or more source names to update"
+            raise Exception(err_msg)
 
         non_sources = set(sources_split) - set(SOURCES)
 
         if len(non_sources) != 0:
-            raise Exception(f"Not valid source(s): {non_sources}")
+            err_msg = f"Not valid source(s): {non_sources}"
+            raise Exception(err_msg)
 
         parsed_source_names = {SourceName(SOURCES[s]) for s in sources_split}
         _update_normalizer(parsed_source_names, db, update_merged, use_existing)

src/gene/database/__init__.py

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