update pre-commit

maxbachmann · maxbachmann · commit 01c36f9f4790 · 2025-04-11T14:49:04.000+02:00
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -20,7 +20,7 @@ exclude: |
 repos:
 # Standard hooks
 - repo: https://github.com/pre-commit/pre-commit-hooks
-  rev: "v4.5.0"
+  rev: "v5.0.0"
   hooks:
   - id: check-added-large-files
   - id: check-case-conflict
@@ -37,13 +37,13 @@ repos:
 
 # Black, the code formatter, natively supports pre-commit
 - repo: https://github.com/psf/black-pre-commit-mirror
-  rev: "24.2.0" # Keep in sync with blacken-docs
+  rev: "25.1.0" # Keep in sync with blacken-docs
   hooks:
   - id: black
 
 # Also code format the docs
 - repo: https://github.com/asottile/blacken-docs
-  rev: "1.16.0"
+  rev: "1.19.1"
   hooks:
   - id: blacken-docs
     additional_dependencies:
@@ -56,7 +56,7 @@ repos:
   - id: remove-tabs
 
 - repo: https://github.com/sirosen/texthooks
-  rev: "0.6.4"
+  rev: "0.6.8"
   hooks:
   - id: fix-ligatures
   - id: fix-smartquotes
@@ -73,7 +73,7 @@ repos:
 
 # PyLint has native support - not always usable, but works for us
 - repo: https://github.com/PyCQA/pylint
-  rev: "v3.1.0"
+  rev: "v3.3.6"
   hooks:
   - id: pylint
     files: ^pybind11
@@ -98,30 +98,30 @@ repos:
 
 # Checks the manifest for missing files (native support)
 - repo: https://github.com/mgedmin/check-manifest
-  rev: "0.49"
+  rev: "0.50"
   hooks:
   - id: check-manifest
     # This is a slow hook, so only run this if --hook-stage manual is passed
     stages: [manual]
     additional_dependencies: [cmake, ninja]
 
 - repo: https://github.com/charliermarsh/ruff-pre-commit
-  rev: v0.3.0
+  rev: v0.11.5
   hooks:
   - id: ruff
     args: ["--fix", "--show-fixes"]
 
 # Check for spelling
 - repo: https://github.com/codespell-project/codespell
-  rev: "v2.2.6"
+  rev: "v2.4.1"
   hooks:
   - id: codespell
     exclude: ".*/test_.*.py"
     args: ["-x", ".codespell-ignore-lines"]
 
 # Check for common shell mistakes
 - repo: https://github.com/shellcheck-py/shellcheck-py
-  rev: "v0.9.0.6"
+  rev: "v0.10.0.1"
   hooks:
   - id: shellcheck
 
@@ -136,7 +136,7 @@ repos:
 
 # Clang format the codebase automatically
 - repo: https://github.com/pre-commit/mirrors-clang-format
-  rev: "v17.0.6"
+  rev: "v20.1.0"
   hooks:
   - id: clang-format
     types_or: [c++, c]
diff --git a/api_differences.md b/api_differences.md
@@ -44,7 +44,7 @@ that it does not provide the optional argument `force_ascii` which removes any n
 - `fuzz.UWRatio`
 - `fuzz.UQRatio`
 
-With the exception `fuzz.UWRatio` and `fuzz.UQRatio` of all have `force_ascii` enabled forthe peprocessing function by default.
+With the exception `fuzz.UWRatio` and `fuzz.UQRatio` of all have `force_ascii` enabled for the peprocessing function by default.
 
 In `RapidFuzz` no scorer preprocesses strings by default to keep the interface consistent. However a preprocessing function can be provided using the `processor` argument. In addition the functions `fuzz.UWRatio` and `fuzz.UQRatio` do not exist, since they are the same as  `fuzz.WRatio` / `fuzz.QRatio` with `force_ascii` disabled. Since in `RapidFuzz` the `force_ascii` argument does not exist these functions do not provide any value.
 
diff --git a/bench/benchmark_cdist.py b/bench/benchmark_cdist.py
@@ -65,7 +65,7 @@ def benchmark():
     print("System:", get_platform())
     print("Words :", len(words))
     print("Sample:", len(sample))
-    print("Total : %s calls\n" % total)
+    print(f"Total : {total} calls\n")
 
     def wrap_cdist(scorer, processor):
         from rapidfuzz.process import cdist
diff --git a/bench/benchmark_cpdist.py b/bench/benchmark_cpdist.py
@@ -55,7 +55,7 @@ def benchmark():
     print("System:", get_platform())
     print("Words :", len(words1))
     print("Sample:", len(words2))
-    print("Total : %s calls\n" % total)
+    print(f"Total : {total} calls\n")
 
     def wrap_cpdist(scorer):
         from rapidfuzz.process import cpdist
diff --git a/bench/benchmark_scorer.py b/bench/benchmark_scorer.py
@@ -55,7 +55,7 @@ def benchmark():
     print("System:", get_platform())
     print("Words :", len(words))
     print("Sample:", len(sample))
-    print("Total : %s calls\n" % total)
+    print(f"Total : {total} calls\n")
 
     def wrap(f):
         def func():
diff --git a/src/rapidfuzz/__init__.py b/src/rapidfuzz/__init__.py
@@ -10,7 +10,7 @@
 
 from rapidfuzz import distance, fuzz, process, utils
 
-__all__ = ["distance", "fuzz", "process", "utils", "get_include"]
+__all__ = ["distance", "fuzz", "get_include", "process", "utils"]
 
 
 def get_include():
diff --git a/src/rapidfuzz/_utils.py b/src/rapidfuzz/_utils.py
@@ -64,10 +64,7 @@ def is_none(s: Any) -> bool:
     if s is None or s is pandas_NA:
         return True
 
-    if isinstance(s, float) and isnan(s):
-        return True
-
-    return False
+    return isinstance(s, float) and isnan(s)
 
 
 def add_scorer_attrs(func: Any, cached_scorer_call: dict[str, Callable[..., dict[str, Any]]]):
diff --git a/src/rapidfuzz/distance/__init__.py b/src/rapidfuzz/distance/__init__.py
@@ -18,20 +18,20 @@
 from ._initialize import Editop, Editops, MatchingBlock, Opcode, Opcodes, ScoreAlignment
 
 __all__ = [
+    "OSA",
+    "DamerauLevenshtein",
     "Editop",
     "Editops",
-    "Opcode",
-    "Opcodes",
-    "ScoreAlignment",
-    "MatchingBlock",
-    "DamerauLevenshtein",
     "Hamming",
     "Indel",
     "Jaro",
     "JaroWinkler",
     "LCSseq",
     "Levenshtein",
-    "OSA",
-    "Prefix",
+    "MatchingBlock",
+    "Opcode",
+    "Opcodes",
     "Postfix",
+    "Prefix",
+    "ScoreAlignment",
 ]
diff --git a/src/rapidfuzz/distance/metrics_py.py b/src/rapidfuzz/distance/metrics_py.py
@@ -246,11 +246,11 @@ def _get_scorer_flags_levenshtein_normalized_similarity(
 
 __all__ += [
     "levenshtein_distance",
+    "levenshtein_editops",
     "levenshtein_normalized_distance",
     "levenshtein_normalized_similarity",
-    "levenshtein_similarity",
-    "levenshtein_editops",
     "levenshtein_opcodes",
+    "levenshtein_similarity",
 ]
 
 
@@ -261,11 +261,11 @@ def _get_scorer_flags_levenshtein_normalized_similarity(
 
 __all__ += [
     "lcs_seq_distance",
+    "lcs_seq_editops",
     "lcs_seq_normalized_distance",
     "lcs_seq_normalized_similarity",
-    "lcs_seq_similarity",
-    "lcs_seq_editops",
     "lcs_seq_opcodes",
+    "lcs_seq_similarity",
 ]
 
 
@@ -276,11 +276,11 @@ def _get_scorer_flags_levenshtein_normalized_similarity(
 
 __all__ += [
     "indel_distance",
+    "indel_editops",
     "indel_normalized_distance",
     "indel_normalized_similarity",
-    "indel_similarity",
-    "indel_editops",
     "indel_opcodes",
+    "indel_similarity",
 ]
 
 
@@ -291,9 +291,9 @@ def _get_scorer_flags_levenshtein_normalized_similarity(
 
 __all__ += [
     "hamming_distance",
+    "hamming_editops",
     "hamming_normalized_distance",
     "hamming_normalized_similarity",
-    "hamming_similarity",
-    "hamming_editops",
     "hamming_opcodes",
+    "hamming_similarity",
 ]
diff --git a/src/rapidfuzz/process_cpp.py b/src/rapidfuzz/process_cpp.py
@@ -21,7 +21,7 @@
     extractOne,
 )
 
-__all__ = ["extract", "extract_iter", "extractOne", "cdist", "cpdist"]
+__all__ = ["cdist", "cpdist", "extract", "extractOne", "extract_iter"]
 
 
 def _dtype_to_type_num(dtype):
diff --git a/src/rapidfuzz/process_py.py b/src/rapidfuzz/process_py.py
@@ -7,7 +7,7 @@
 from rapidfuzz._utils import ScorerFlag, is_none, setupPandas
 from rapidfuzz.fuzz import WRatio, ratio
 
-__all__ = ["extract", "extract_iter", "extractOne", "cdist"]
+__all__ = ["cdist", "extract", "extractOne", "extract_iter"]
 
 
 def _get_scorer_flags_py(scorer, scorer_kwargs):
diff --git a/tests/common.py b/tests/common.py
@@ -30,10 +30,7 @@ def is_none(s):
     if s is None or s is pandas_NA:
         return True
 
-    if isinstance(s, float) and isnan(s):
-        return True
-
-    return False
+    return isinstance(s, float) and isnan(s)
 
 
 def call_and_maybe_catch(call, *args, catch_exceptions=False, **kwargs):
diff --git a/tests/distance/test_distance.py b/tests/distance/test_distance.py
@@ -55,9 +55,8 @@ def test_empty_strings(scorer):
 
 def unicodeArray(text):
     if sys.version_info >= (3, 13, 0):
-        return array("w", [c for c in text])
-    else:
-        return array("u", text)
+        return array("w", list(text))
+    return array("u", text)
 
 
 @pytest.mark.parametrize("scorer", all_scorer_modules)
diff --git a/tests/test_cpp_fallback.py b/tests/test_cpp_fallback.py
@@ -4,4 +4,4 @@
 import os
 
 os.environ["RAPIDFUZZ_IMPLEMENTATION"] = "cpp"
-import rapidfuzz  # noqa: E402, F401
+import rapidfuzz  # noqa: F401
diff --git a/tests/test_fuzz.py b/tests/test_fuzz.py
@@ -258,9 +258,8 @@ def test_invalid_input(scorer):
 
 def unicodeArray(text):
     if sys.version_info >= (3, 13, 0):
-        return array("w", [c for c in text])
-    else:
-        return array("u", text)
+        return array("w", list(text))
+    return array("u", text)
 
 
 @pytest.mark.parametrize("scorer", scorers)
diff --git a/tests/test_process.py b/tests/test_process.py
@@ -721,10 +721,12 @@ def test_cdist_multiplier():
         expected_res,
     )
 
+
 def test_str_dtype():
     np = pytest.importorskip("numpy")
-    assert process.cdist(["test"], ["test"], scorer=fuzz.ratio, dtype='uint8').dtype == np.uint8
-    assert process.cpdist(["test"], ["test"], scorer=fuzz.ratio, dtype='uint8').dtype == np.uint8
+    assert process.cdist(["test"], ["test"], scorer=fuzz.ratio, dtype="uint8").dtype == np.uint8
+    assert process.cpdist(["test"], ["test"], scorer=fuzz.ratio, dtype="uint8").dtype == np.uint8
+
 
 def test_generators():
     """
diff --git a/tests/test_pure_python_fallback.py b/tests/test_pure_python_fallback.py
@@ -4,4 +4,4 @@
 import os
 
 os.environ["RAPIDFUZZ_IMPLEMENTATION"] = "python"
-import rapidfuzz  # noqa: E402, F401
+import rapidfuzz  # noqa: F401

Original file line number	Diff line number	Diff line change
`@@ -21,7 +21,7 @@`
`21`	`21`	`extractOne,`
`22`	`22`	`)`
`23`	`23`
`24`		`-__all__ = ["extract", "extract_iter", "extractOne", "cdist", "cpdist"]`
	`24`	`+__all__ = ["cdist", "cpdist", "extract", "extractOne", "extract_iter"]`
`25`	`25`
`26`	`26`
`27`	`27`	`def _dtype_to_type_num(dtype):`