upgrade linters

.pre-commit-config.yaml

@@ -15,7 +15,7 @@
 repos:
 # Standard hooks
 - repo: https://github.com/pre-commit/pre-commit-hooks
-  rev: "v4.4.0"
+  rev: "v4.5.0"
   hooks:
   - id: check-added-large-files
   - id: check-case-conflict
@@ -38,7 +38,7 @@ repos:
 
 # Also code format the docs
 - repo: https://github.com/asottile/blacken-docs
-  rev: "1.13.0"
+  rev: "1.16.0"
   hooks:
   - id: blacken-docs
     additional_dependencies:
@@ -46,12 +46,12 @@ repos:
 
 # Changes tabs to spaces
 - repo: https://github.com/Lucas-C/pre-commit-hooks
-  rev: "v1.5.1"
+  rev: "v1.5.5"
   hooks:
   - id: remove-tabs
 
 - repo: https://github.com/sirosen/texthooks
-  rev: "0.5.0"
+  rev: "0.6.4"
   hooks:
   - id: fix-ligatures
   - id: fix-smartquotes
@@ -101,14 +101,14 @@ repos:
     additional_dependencies: [cmake, ninja]
 
 - repo: https://github.com/charliermarsh/ruff-pre-commit
-  rev: v0.0.261
+  rev: v0.3.0
   hooks:
   - id: ruff
     args: ["--fix", "--show-fixes"]
 
 # Check for spelling
 - repo: https://github.com/codespell-project/codespell
-  rev: "v2.2.4"
+  rev: "v2.2.6"
   hooks:
   - id: codespell
     exclude: ".*/test_.*.py"
@@ -116,7 +116,7 @@ repos:
 
 # Check for common shell mistakes
 - repo: https://github.com/shellcheck-py/shellcheck-py
-  rev: "v0.9.0.2"
+  rev: "v0.9.0.6"
   hooks:
   - id: shellcheck
 
@@ -131,7 +131,7 @@ repos:
 
 # Clang format the codebase automatically
 - repo: https://github.com/pre-commit/mirrors-clang-format
-  rev: "v16.0.0"
+  rev: "v17.0.6"
   hooks:
   - id: clang-format
     types_or: [c++, c]

README.md

@@ -211,8 +211,8 @@ The first benchmark compares the performance of the scorers in FuzzyWuzzy and Ra
 from Python in the following way:
 ```python3
 for sample in samples:
-  for word in words:
-    scorer(sample, word)
+    for word in words:
+        scorer(sample, word)
 ```
 The following graph shows how many elements are processed per second with each of the scorers. There are big performance differences between the different scorers. However each of the scorers is faster in RapidFuzz
 

bench/benchmark.py

@@ -121,6 +121,7 @@ def run_benchmarks_rapidfuzz(rapidfuzz_version, func_name, dataset, result_df):
                 [sys.executable, "-m", "pip", "install", f"rapidfuzz=={version}"],
                 stdout=subprocess.DEVNULL,
                 stderr=subprocess.DEVNULL,
+                check=False,
             )
             # older versions are likely not installable
             if res.returncode:

bench/benchmark_partial_ratio_long_needle.py

@@ -43,7 +43,7 @@ time_fuzzywuzzy = (
         list(range(0, 256, 2)),
         count,
     )
-    + [np.NaN] * 128
+    + [np.nan] * 128
 )
 
 results = pd.DataFrame(

bench/benchmark_partial_ratio_short_needle.py

@@ -43,7 +43,7 @@ time_fuzzywuzzy = (
         list(range(64, 256, 2)),
         count,
     )
-    + [np.NaN] * 128
+    + [np.nan] * 128
 )
 
 results = pd.DataFrame(

pyproject.toml

@@ -45,8 +45,12 @@ disable = [
   "missing-module-docstring",
 ]
 
-
 [tool.ruff]
+target-version = "py37"
+src = ["src"]
+exclude = []
+
+[tool.ruff.lint]
 select = [
   "E", "F", "W", # flake8
   "B",           # flake8-bugbear
@@ -78,17 +82,14 @@ extend-ignore = [
   "PT004",  # Use underscore for non-returning fixture (use usefixture instead)
   "PTH123", # use pathlib instead of builtin open
 ]
-target-version = "py37"
-src = ["src"]
 unfixable = [
   "T20",  # Removes print statements
   "F841", # Removes unused variables
 ]
-exclude = []
 flake8-unused-arguments.ignore-variadic-names = true
 isort.required-imports = ["from __future__ import annotations"]
 
-[tool.ruff.per-file-ignores]
+[tool.ruff.lint.per-file-ignores]
 "tests/**" = ["T20"]
 "bench/**" = ["T20"]
 "_custom_build/backend.py" = ["T20"]

src/rapidfuzz/distance/_initialize_py.py

@@ -42,7 +42,7 @@ def _list_to_editops(
         blocks.append(Editop(edit_type, src_pos, dest_pos))
 
     # validate order of editops
-    for i in range(0, len(blocks) - 1):
+    for i in range(len(blocks) - 1):
         if blocks[i + 1].src_pos < blocks[i].src_pos or blocks[i + 1].dest_pos < blocks[i].dest_pos:
             msg = "List of edit operations out of order"
             raise ValueError(msg)
@@ -104,7 +104,7 @@ def _list_to_opcodes(
     if blocks[-1].src_end != src_len or blocks[-1].dest_end != dest_len:
         msg = "List of edit operations does not end at the string ends"
         raise ValueError(msg)
-    for i in range(0, len(blocks) - 1):
+    for i in range(len(blocks) - 1):
         if blocks[i + 1].src_start != blocks[i].src_end or blocks[i + 1].dest_start != blocks[i].dest_end:
             msg = "List of edit operations is not continuous"
             raise ValueError(msg)