ruff update

.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: v0.8.4
   hooks:
     - id: ruff-format
     - id: ruff

Pipfile

@@ -17,7 +17,7 @@ matplotlib = "*"
 lxml = "*"
 xmlformatter = "*"
 psycopg = {version = "*", extras=["binary"]}
-ruff = "*"
+ruff = "==0.5.0"
 httpx = "*"
 
 [packages]

pyproject.toml

@@ -37,7 +37,7 @@ dynamic = ["version"]
 pg = ["psycopg[binary]", "requests"]
 etl = ["owlready2==0.40", "rdflib", "wags-tails>=0.1.2", "fastobo", "tqdm"]
 test = ["pytest>=6.0", "pytest-cov", "httpx"]
-dev = ["pre-commit", "ruff==0.2.0", "lxml", "xmlformatter"]
+dev = ["pre-commit", "ruff==0.8.4", "lxml", "xmlformatter"]
 docs = [
     "sphinx==6.1.3",
     "sphinx-autodoc-typehints==1.22.0",
@@ -84,7 +84,7 @@ branch = true
 
 [tool.ruff]
 src = ["src"]
-exclude = ["docs/source/conf.py"]
+exclude = ["docs/source/conf.py", "analysis/"]
 
 [tool.ruff.lint]
 select = [
@@ -103,16 +103,26 @@ 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
+    "SLOT",  # https://docs.astral.sh/ruff/rules/#flake8-slots-slot
     "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
+    "PLC",  # https://docs.astral.sh/ruff/rules/#convention-c
+    "PLE",  # https://docs.astral.sh/ruff/rules/#error-e_1
+    "TRY",  # https://docs.astral.sh/ruff/rules/#tryceratops-try
+    "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 = [
@@ -123,14 +133,19 @@ fixable = [
     "ANN",
     "B",
     "C4",
+    "LOG",
     "G",
     "PIE",
     "PT",
     "RSE",
     "SIM",
+    "PLC",
+    "PLE",
+    "TRY",
+    "PERF",
+    "FURB",
     "RUF"
 ]
-# ANN101 - missing-type-self
 # ANN003 - missing-type-kwargs
 # D203 - one-blank-line-before-class
 # D205 - blank-line-after-summary
@@ -144,21 +159,38 @@ fixable = [
 # E117 - over-indented*
 # E501 - line-too-long*
 # W191 - tab-indentation*
+# S321 - suspicious-ftp-lib-usage
+# PLC0206 - dict-index-missing-items
 # *ignored for compatibility with formatter
 ignore = [
-    "ANN101", "ANN003",
+    "ANN003",
     "D203", "D205", "D206", "D213", "D300", "D400", "D415",
     "E111", "E114", "E117", "E501",
-    "W191"
+    "W191",
+    "S321",
+    "PLC0206",
 ]
 
 [tool.ruff.lint.per-file-ignores]
 # ANN001 - missing-type-function-argument
 # ANN2 - missing-return-type
-# ANN102 - missing-type-cls
+# F401 - unused-import
 # N805 - invalid-first-argument-name-for-method
 # S101 - assert
-# RUF001 - ambiguous-unicode-character-string
-"tests/*" = ["ANN001", "ANN2", "ANN102", "S101"]
+# D100 - undocumented-public-module
+# D103 - undocumented-public-function
+# I001 - unsorted-imports
+# INP001 - implicit-namespace-package
+# ARG001 - unused-function-argument
+# SLF001 - private-member-acces
+"tests/*" = ["ANN001", "ANN2", "S101", "INP001", "SLF001", "ARG001"]
+"*__init__.py" = ["F401"]
 "tests/unit/test_emit_warnings.py" = ["RUF001"]
 "src/disease/schemas.py" = ["ANN201", "N805", "ANN001"]
+"docs/source/conf.py" = ["D100", "I001", "D103", "ANN201", "ANN001"]
+
+[tool.ruff.lint.flake8-annotations]
+mypy-init-return = true
+
+[tool.ruff.format]
+docstring-code-format = true

src/disease/__init__.py

@@ -1,7 +1,8 @@
 """The VICC library for normalizing diseases."""
+
 from pathlib import Path
 
-from .version import __version__  # noqa: F401
+from .version import __version__
 
 APP_ROOT = Path(__file__).resolve().parents[0]
 

src/disease/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 DISEASE_NORM_REMOTE_DB_URL environment variable.
@@ -170,7 +171,7 @@ def _load_source(
     n: SourceName,
     db: AbstractDatabase,
     delete_time: float,
-    processed_ids: List[str],
+    processed_ids: list[str],
     from_local: bool,
 ) -> None:
     """Load individual source data.
@@ -194,7 +195,7 @@ def _load_source(
             f"Encountered ModuleNotFoundError attempting to import {e.name}. Are ETL dependencies installed?"
         )
         click.get_current_context().exit()
-    SourceClass = eval(n.value)  # noqa: N806 S307 PGH001
+    SourceClass = eval(n.value)  # noqa: N806, S307
 
     source = SourceClass(database=db, silent=False)
     processed_ids += source.perform_etl(use_existing=from_local)
@@ -225,7 +226,7 @@ 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
@@ -309,13 +310,13 @@ def update_db(
 
         if len(sources_split) == 0:
             msg = "Must enter one or more source names"
-            raise Exception(msg)
+            raise ValueError(msg)
 
         non_sources = set(sources_split) - set(SOURCES_LOWER_LOOKUP)
 
         if len(non_sources) != 0:
             msg = f"Not valid source(s): {non_sources}"
-            raise Exception(msg)
+            raise ValueError(msg)
 
         sources_to_update = {SourceName(SOURCES_LOWER_LOOKUP[s]) for s in sources_split}
         _update_sources(sources_to_update, db, update_merged, from_local)

src/disease/database/__init__.py

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

src/disease/database/database.py

@@ -4,12 +4,14 @@
 :py:meth:`~disease.database.database.create_db` is the recommended way to create a
 database connection.
 """
+
 import abc
 import sys
+from collections.abc import Generator
 from enum import Enum
 from os import environ
 from pathlib import Path
-from typing import Any, Dict, Generator, List, Optional, Set, Union
+from typing import Any
 
 import click
 
@@ -36,7 +38,7 @@ class AbstractDatabase(abc.ABC):
     """Define a database interface."""
 
     @abc.abstractmethod
-    def __init__(self, db_url: Optional[str] = None, **db_args) -> None:
+    def __init__(self, db_url: str | None = None, **db_args) -> None:
         """Initialize database instance.
 
         Generally, implementing classes should be able to construct a connection by
@@ -49,7 +51,7 @@ def __init__(self, db_url: Optional[str] = None, **db_args) -> None:
         """
 
     @abc.abstractmethod
-    def list_tables(self) -> List[str]:
+    def list_tables(self) -> list[str]:
         """Return names of tables in database.
 
         :return: Table names in database
@@ -106,9 +108,7 @@ def initialize_db(self) -> None:
         """
 
     @abc.abstractmethod
-    def get_source_metadata(
-        self, src_name: Union[str, SourceName]
-    ) -> Optional[SourceMeta]:
+    def get_source_metadata(self, src_name: str | SourceName) -> SourceMeta | None:
         """Get license, versioning, data lookup, etc information for a source.
 
         :param src_name: name of the source to get data for
@@ -118,7 +118,7 @@ def get_source_metadata(
     @abc.abstractmethod
     def get_record_by_id(
         self, concept_id: str, case_sensitive: bool = True, merge: bool = False
-    ) -> Optional[Dict]:
+    ) -> dict | None:
         """Fetch record corresponding to provided concept ID
 
         :param concept_id: concept ID for record
@@ -130,7 +130,7 @@ def get_record_by_id(
         """
 
     @abc.abstractmethod
-    def get_refs_by_type(self, search_term: str, ref_type: RefType) -> List[str]:
+    def get_refs_by_type(self, search_term: str, ref_type: RefType) -> list[str]:
         """Retrieve concept IDs for records matching the user's query. Other methods
         are responsible for actually retrieving full records.
 
@@ -140,15 +140,15 @@ def get_refs_by_type(self, search_term: str, ref_type: RefType) -> List[str]:
         """
 
     @abc.abstractmethod
-    def get_all_concept_ids(self, source: Optional[SourceName] = None) -> Set[str]:
+    def get_all_concept_ids(self, source: SourceName | None = None) -> set[str]:
         """Retrieve all available concept IDs for use in generating normalized records.
 
         :param source: optionally, just get all IDs for a specific source
         :return: Set of concept IDs as strings.
         """
 
     @abc.abstractmethod
-    def get_all_records(self, record_type: RecordType) -> Generator[Dict, None, None]:
+    def get_all_records(self, record_type: RecordType) -> Generator[dict, None, None]:
         """Retrieve all source or normalized records. Either return all source records,
         or all records that qualify as "normalized" (i.e., merged groups + source
         records that are otherwise ungrouped).
@@ -176,15 +176,15 @@ def add_source_metadata(self, src_name: SourceName, meta: SourceMeta) -> None:
         """
 
     @abc.abstractmethod
-    def add_record(self, record: Dict, src_name: SourceName) -> None:
+    def add_record(self, record: dict, src_name: SourceName) -> None:
         """Add new record to database.
 
         :param record: record to upload
         :param src_name: name of source for record.
         """
 
     @abc.abstractmethod
-    def add_merged_record(self, record: Dict) -> None:
+    def add_merged_record(self, record: dict) -> None:
         """Add merged record to database.
 
         :param record: merged record to add
@@ -228,7 +228,7 @@ def close_connection(self) -> None:
         """Perform any manual connection closure procedures if necessary."""
 
     @abc.abstractmethod
-    def load_from_remote(self, url: Optional[str] = None) -> None:
+    def load_from_remote(self, url: str | None = None) -> None:
         """Load DB from remote dump. Warning: Deletes all existing data.
 
         :param url: remote location to retrieve gzipped dump file from
@@ -276,7 +276,7 @@ def confirm_aws_db_use(env_name: str) -> None:
 
 
 def create_db(
-    db_url: Optional[str] = None, aws_instance: bool = False
+    db_url: str | None = None, aws_instance: bool = False
 ) -> AbstractDatabase:
     """Database factory method. Checks environment variables and provided parameters
     and creates a DB instance.