style: update ruff and drop black (#283)

.github/workflows/backend_checks.yml

@@ -20,12 +20,13 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
-      - name: black
-        uses: psf/black@stable
+      - name: Setup Python
+        uses: actions/setup-python@v5
         with:
-          src: "./server"
+          python-version: "3.11"
 
-      - name: ruff
-        uses: chartboost/ruff-action@v1
-        with:
-          src: "./server"
+      - name: Install dependencies
+        run: python3 -m pip install "server/.[dev]"
+
+      - name: Check style
+        run: python3 -m ruff check server/ && python3 -m ruff format --check server/

.pre-commit-config.yaml

@@ -8,16 +8,12 @@ repos:
       - id: end-of-file-fixer
       - id: check-merge-conflict
       - id: detect-aws-credentials
-  - repo: https://github.com/psf/black
-    rev: 23.7.0
-    hooks:
-      - id: black
-        language_version: python3.11
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.0.286
+    rev: v0.5.0
     hooks:
+      - id: ruff-format
       - id: ruff
-        args: [--fix, --exit-non-zero-on-fix]
+        args: [--fix, --exit-non-zero-on-fix, --config=server/pyproject.toml]
   - repo: https://github.com/pre-commit/mirrors-eslint
     rev: "v8.20.0"
     hooks:

server/pyproject.toml

@@ -69,42 +69,104 @@ root = "../."
 addopts = "--cov=src --cov-report term-missing"
 testpaths = ["tests"]
 
-[tool.black]
-line-length = 88
-
 [tool.ruff]
-# pycodestyle (E, W)
-# Pyflakes (F)
-# flake8-annotations (ANN)
-# flake8-quotes (Q)
-# pydocstyle (D)
-# pep8-naming (N)
-# isort (I)
-select = ["E", "W", "F", "ANN", "Q", "D", "N", "I"]
-
-fixable = ["I"]
+src = ["curfu"]
 
+[tool.ruff.lint]
+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
+    "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 = [
+    "I",
+    "F401",
+    "D",
+    "UP",
+    "ANN",
+    "B",
+    "C4",
+    "LOG",
+    "G",
+    "PIE",
+    "PT",
+    "RSE",
+    "SIM",
+    "PERF",
+    "FURB",
+    "RUF"
+]
+# 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*
+# D213 - multi-line-summary-second-line
+# D300 - triple-single-quotes*
 # D400 - ends-in-period
 # D415 - ends-in-punctuation
-# ANN101 - missing-type-self
-# ANN003 - missing-type-kwargs
-# E501 - line-too-long
-ignore = ["D205", "D400", "D415", "ANN101", "ANN003", "E501"]
-
-[tool.ruff.flake8-quotes]
-docstring-quotes = "double"
+# E111 - indentation-with-invalid-multiple*
+# E114 - indentation-with-invalid-multiple-comment*
+# E117 - over-indented*
+# E501 - line-too-long*
+# W191 - tab-indentation*
+# S321 - suspicious-ftp-lib-usage
+# *ignored for compatibility with formatter
+ignore = [
+    "ANN003", "ANN101", "ANN102",
+    "D203", "D205", "D206", "D213", "D300", "D400", "D415",
+    "E111", "E114", "E117", "E501",
+    "W191",
+    "S321",
+]
 
-[tool.ruff.per-file-ignores]
+[tool.ruff.lint.per-file-ignores]
 # ANN001 - missing-type-function-argument
 # ANN2 - missing-return-type
 # ANN102 - missing-type-cls
-# N805 - invalid-first-argument-name-for-method
-# F821 - undefined-name
+# S101 - assert
+# B011 - assert-false
 # F401 - unused-import
-"tests/*" = ["ANN001", "ANN2", "ANN102"]
-"setup.py" = ["F821"]
+# N805 - invalid-first-argument-name-for-method
+# D301 - escape-sequence-in-docstring
+# INP001 - implicit-namespace-package
+# ARG001 - unused-function-argument
+# B008 - function-call-in-default-argument
+"**/tests/*" = ["ANN001", "ANN2", "ANN102", "S101", "B011", "INP001", "ARG001"]
 "*__init__.py" = ["F401"]
-"curfu/schemas.py" = ["ANN201", "N805", "ANN001"]
-"curfu/routers/*" = ["D301"]
-"curfu/cli.py" = ["D301"]
+"**/src/curfu/schemas.py" = ["ANN201", "N805", "ANN001"]
+"**/src/curfu/routers/*" = ["D301", "B008"]
+"**/src/curfu/cli.py" = ["D301"]
+
+[tool.ruff.format]
+docstring-code-format = true

server/src/curfu/__init__.py

@@ -1,4 +1,5 @@
 """Fusion curation interface."""
+
 import logging
 from importlib.metadata import PackageNotFoundError, version
 from os import environ
@@ -17,7 +18,7 @@
 # establish environment-dependent params
 if "FUSION_EB_PROD" in environ:
     environ["FUSION_EB_PROD"] = "true"
-    LOG_FN = "/tmp/curfu.log"
+    LOG_FN = "/tmp/curfu.log"  # noqa: S108
 else:
     LOG_FN = "curfu.log"
 
@@ -50,10 +51,7 @@
     UTA_DB_URL = "postgresql://uta_admin@localhost:5433/uta/uta_20210129"
 
 # get local seqrepo location
-if "SEQREPO_DATA_PATH" not in environ:
-    SEQREPO_DATA_PATH = f"{APP_ROOT}/data/seqrepo/latest"
-else:
-    SEQREPO_DATA_PATH = environ["SEQREPO_DATA_PATH"]
+SEQREPO_DATA_PATH = environ.get("SEQREPO_DATA_PATH", f"{APP_ROOT}/data/seqrepo/latest")
 
 
 class LookupServiceError(Exception):

server/src/curfu/cli.py

@@ -1,7 +1,7 @@
 """Provide command-line interface to application and associated utilities."""
+
 import os
 from pathlib import Path
-from typing import Optional
 
 import click
 
@@ -21,8 +21,8 @@ def serve(port: int) -> None:
     """
     # calling uvicorn.run() doesn't get logs printed to console --
     # performing a syscall for now until a more elegant solution appears
-    os.system(
-        f"uvicorn curfu.main:app --reload --port={port} --reload-dir={str(APP_ROOT.absolute())}"
+    os.system(  # noqa: S605
+        f"uvicorn curfu.main:app --reload --port={port} --reload-dir={APP_ROOT.absolute()!s}"
     )
 
 
@@ -57,29 +57,16 @@ def devtools() -> None:
     "--uniprot", "-u", help="Path to uniprot_sprot_YYYYMMDD.xml", default=None
 )
 def domains(
-    types: str, protein2ipr: Optional[str], refs: Optional[str], uniprot: Optional[str]
+    types: str, protein2ipr: str | None, refs: str | None, uniprot: str | None
 ) -> None:
     """Build domain mappings for use in Fusion Curation app.
     \f
     :param str types: comma-separated list
     """
     types_split = set(types.lower().replace(" ", "").split(","))
-
-    if protein2ipr:
-        protein2ipr_path = Path(protein2ipr)
-    else:
-        protein2ipr_path = None
-
-    if uniprot:
-        uniprot_path = Path(uniprot)
-    else:
-        uniprot_path = None
-
-    if refs:
-        refs_path = Path(refs)
-    else:
-        refs_path = None
-
+    protein2ipr_path = Path(protein2ipr) if protein2ipr else None
+    uniprot_path = Path(uniprot) if uniprot else None
+    refs_path = Path(refs) if refs else None
     build_gene_domain_maps(
         interpro_types=types_split,
         protein_ipr_path=protein2ipr_path,

server/src/curfu/devtools/__init__.py

@@ -1,6 +1,7 @@
 """Utility functions for application setup."""
+
 import ftplib
-from typing import Callable
+from collections.abc import Callable
 
 from curfu import logger
 
@@ -18,7 +19,7 @@ def ftp_download(domain: str, path: str, fname: str, callback: Callable) -> None
             ftp.retrbinary(f"RETR {fname}", callback)
     except ftplib.all_errors as e:
         logger.error(f"FTP download failed: {e}")
-        raise Exception(e)
+        raise Exception(e) from e
 
 
 # default interpro entry types to try to gather for domains

server/src/curfu/devtools/build_client_types.py

@@ -1,4 +1,5 @@
 """Provide client type generation tooling."""
+
 from pathlib import Path
 
 from pydantic2ts.cli.script import generate_typescript_defs

server/src/curfu/devtools/build_gene_suggest.py

@@ -1,9 +1,9 @@
 """Provide tools to build backend data relating to gene identification."""
+
 import csv
-from datetime import datetime as dt
+import datetime
 from pathlib import Path
 from timeit import default_timer as timer
-from typing import Dict, List, Optional
 
 import click
 from biocommons.seqrepo.seqrepo import SeqRepo
@@ -25,7 +25,7 @@ def __init__(self) -> None:
         self.sr = SeqRepo(SEQREPO_DATA_PATH)
         self.genes = []
 
-    def _get_chromosome(self, record: Dict) -> Optional[str]:
+    def _get_chromosome(self, record: dict) -> str | None:
         """Extract readable chromosome identifier from gene extensions.
 
         :param record: stored normalized record
@@ -42,7 +42,7 @@ def _get_chromosome(self, record: Dict) -> Optional[str]:
         return None
 
     @staticmethod
-    def _make_list_column(values: List[str]) -> str:
+    def _make_list_column(values: list[str]) -> str:
         """Convert a list of strings into a comma-separated string, filtering out
         non-alphabetic values.
 
@@ -62,12 +62,13 @@ def _make_list_column(values: List[str]) -> str:
         :param values: A list of strings to be converted into a comma-separated string.
         :return: A comma-separated string containing unique, alphabetic values from the
             input list.
+
         """
         unique = {v.upper() for v in values}
         filtered = {v for v in unique if any(char.isalpha() for char in v)}
         return ",".join(filtered)
 
-    def _process_gene_record(self, record: Dict) -> None:
+    def _process_gene_record(self, record: dict) -> None:
         """Add the gene record to processed suggestions.
 
         :param record: gene record object retrieved from DB
@@ -117,8 +118,10 @@ def _save_suggest_file(self, output_dir: Path) -> None:
             "chromosome",
             "strand",
         ]
-        today = dt.strftime(dt.today(), "%Y%m%d")
-        with open(output_dir / f"gene_suggest_{today}.csv", "w") as csvfile:
+        today = datetime.datetime.strftime(
+            datetime.datetime.now(tz=datetime.timezone.utc), "%Y%m%d"
+        )
+        with (output_dir / f"gene_suggest_{today}.csv").open("w") as csvfile:
             writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
             writer.writeheader()
             for row in self.genes: