fix types, config for mypy

.pre-commit-config.yaml

@@ -16,19 +16,16 @@ repos:
         description: Check for files with names that would conflict on case-insensitive filesystems like MacOS/Windows.
       - id: no-commit-to-branch
         description: Protect specific branches from direct checkins.
-  - repo: https://github.com/charliermarsh/ruff-pre-commit
-    rev: 'v0.0.263'
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.5.1
     hooks:
       - id: ruff
+        args: [ --fix ]
+      - id: ruff-format
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.950
+    rev: v1.10.1
     hooks:
       - id: mypy
-  - repo: https://github.com/ambv/black
-    rev: 22.6.0
-    hooks:
-      - id: black
-        args: [--preview]
   - repo: local
     hooks:
       - id: unittest

pyproject.toml

@@ -3,5 +3,11 @@ requires = ["setuptools >= 40.6.0", "wheel"]
 build-backend = "setuptools.build_meta"
 
 [tool.ruff]
-select = ["E", "F", "B", "I001", "I002"]
-target-version = "py38"
+target-version = "py311"
+
+[[tool.mypy.overrides]]
+module = [
+    "tqdm.*",
+    "ahocorasick.*",
+]
+ignore_missing_imports = true

reach/__init__.py

@@ -1,4 +1,5 @@
 """A package for reading and manipulating word embeddings."""
+
 from reach.reach import Reach, normalize
 
 try:

reach/autoreach.py

@@ -1,6 +1,5 @@
 import re
 from string import punctuation
-from typing import Hashable, List, Optional, Union
 
 try:
     from ahocorasick import Automaton
@@ -59,10 +58,10 @@ class AutoReach(Reach):
     def __init__(
         self,
         vectors: Matrix,
-        items: List[Hashable],
-        lowercase: Union[str, bool] = "auto",
+        items: list[str],
+        lowercase: str | bool = "auto",
         name: str = "",
-        unk_index: Optional[int] = None,
+        unk_index: int | None = None,
     ) -> None:
         """Initialize a Reach instance with an array and list of strings."""
         super().__init__(vectors, items, name, unk_index)
@@ -96,7 +95,7 @@ def is_valid_token(self, token: str, tokens: str, end_index: int) -> bool:
 
         return True
 
-    def bow(self, tokens: Tokens, remove_oov: bool = True) -> List[int]:
+    def bow(self, tokens: Tokens, remove_oov: bool = True) -> list[int]:
         """
         Create a bow representation from a string.