Apply repo-review suggestions (#559)

* Apply repo-review rule PP304

PP304: Sets the log level in pytest
log_cli_level should be set. This will allow logs to be displayed on failures.

* Apply repo-review rule PP305

PP305: Specifies xfail_strict
xfail_strict should be set. You can manually specify if a check should be strict when setting each xfail.

* Apply repo-review rules PP306, PP307, PP308

PP306: Specifies strict config
--strict-config should be in addopts = [...]. This forces an error if a config setting is misspelled.

PP307: Specifies strict markers
--strict-markers should be in addopts = [...]. This forces all markers to be specified in config, avoiding misspellings.

PP308: Specifies useful pytest summary
An explicit summary flag like -ra should be in addopts = [...] (print summary of all fails/errors).

* Apply ruff/pygrep-hooks rule PGH004

PGH004 Use specific rule codes when using `noqa`
PGH004 Use specific rule codes when using `ruff: noqa`

* Apply and enforce ruff rules (RUF)

Apply ruff rule RUF012:
RUF012 Mutable class attributes should be annotated with `typing.ClassVar`

Disable ruff rule RUF001

* Apply and enforce ruff/flake8-bugbear rules (B)

B007 Loop control variable not used within loop body

B028 No explicit `stacklevel` keyword argument found

B904 Within an `except` clause, raise exceptions with `raise ... from err` or
     `raise ... from None` to distinguish them from errors in exception handling

B905 `zip()` without an explicit `strict=` parameter

Co-authored-by: David Stansby <[email protected]>

* Apply and enforce ruff/isort rules (I)

* Apply repo-review rule PC100

PC100: Has pre-commit-hooks
Must have https://github.com/pre-commit/pre-commit-hooks repo in .pre-commit-config.yaml

* Enforce repo-review rules

* Apply ruff/flake8-implicit-str-concat rules (ISC)

ISC001 Implicitly concatenated string literals on one line

ISC003 Explicitly concatenated string should be implicitly concatenated

* Apply ruff/refurb rules (FURB)

FURB163 Prefer `math.log10`/`math.log2` over `math.log` with a redundant base

* Fix DeprecationWarning

	'pkgutil.find_loader' is deprecated and slated for removal
	in Python 3.14; use importlib.util.find_spec() instead

---------

Co-authored-by: David Stansby <[email protected]>

Author: DimitriPapadopoulos

.pre-commit-config.yaml

@@ -1,3 +1,4 @@
+exclude: ^fixture/  # files with trailing whitespaces on purpose
 ci:
   autoupdate_commit_msg: "chore: update pre-commit hooks"
   autofix_commit_msg: "style: pre-commit fixes"
@@ -6,9 +7,21 @@ default_stages: [commit, push]
 default_language_version:
   python: python3
 repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+    - id: trailing-whitespace
+    - id: check-yaml
+    - id: debug-statements
+
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: 'v0.6.9'
+    rev: v0.6.9
     hooks:
     - id: ruff
       args: ["--fix", "--show-fixes"]
     - id: ruff-format
+
+  - repo: https://github.com/scientific-python/cookie
+    rev: 2024.04.23
+    hooks:
+    - id: sp-repo-review

.pyup.yml

@@ -1,4 +1,4 @@
-# autogenerated pyup.io config file 
+# autogenerated pyup.io config file
 # see https://pyup.io/docs/configuration/ for all available options
 
 schedule: every month

README.rst

@@ -1,7 +1,7 @@
 Numcodecs
 =========
 
-Numcodecs is a Python package providing buffer compression and transformation 
+Numcodecs is a Python package providing buffer compression and transformation
 codecs for use in data storage and communication applications.
 
 .. image:: https://readthedocs.org/projects/numcodecs/badge/?version=latest

adhoc/blosc_memleak_check.py

@@ -1,13 +1,13 @@
 import sys
 
-import numcodecs
 import numpy as np
 from numpy.testing import assert_array_equal
 
+import numcodecs
 
 codec = numcodecs.Blosc()
 data = np.arange(int(sys.argv[1]))
-for i in range(int(sys.argv[2])):
+for _ in range(int(sys.argv[2])):
     enc = codec.encode(data)
     dec = codec.decode(enc)
     arr = np.frombuffer(dec, dtype=data.dtype)

docs/conf.py

@@ -13,9 +13,10 @@
 # serve to show the default.
 
 
-import sys
 import os
+import sys
 from unittest.mock import Mock as MagicMock
+
 import numcodecs
 
 

notebooks/benchmark_vlen.ipynb

@@ -25,6 +25,7 @@
    ],
    "source": [
     "import numpy as np\n",
+    "\n",
     "import numcodecs\n",
     "\n",
     "numcodecs.__version__"

numcodecs/__init__.py

@@ -1,4 +1,4 @@
-# flake8: noqa
+# ruff: noqa: E402,F401
 """Numcodecs is a Python package providing buffer compression and
 transformation codecs for use in data storage and communication
 applications. These include:
@@ -17,14 +17,12 @@
 
 """
 
-import multiprocessing
 import atexit
+import multiprocessing
 from contextlib import suppress
 
-
-from numcodecs.version import version as __version__
 from numcodecs.registry import get_codec, register_codec
-
+from numcodecs.version import version as __version__
 from numcodecs.zlib import Zlib
 
 register_codec(Zlib)
@@ -130,7 +128,7 @@
 
 with suppress(ImportError):
     from numcodecs import vlen
-    from numcodecs.vlen import VLenUTF8, VLenBytes, VLenArray
+    from numcodecs.vlen import VLenArray, VLenBytes, VLenUTF8
 
     register_codec(VLenUTF8)
     register_codec(VLenBytes)

numcodecs/astype.py

@@ -1,7 +1,7 @@
 import numpy as np
 
 from .abc import Codec
-from .compat import ndarray_copy, ensure_ndarray
+from .compat import ensure_ndarray, ndarray_copy
 
 
 class AsType(Codec):

numcodecs/bitround.py

@@ -1,6 +1,5 @@
 import numpy as np
 
-
 from .abc import Codec
 from .compat import ensure_ndarray_like, ndarray_copy
 

numcodecs/blosc.pyx

@@ -468,7 +468,7 @@ def decompress_partial(source, start, nitems, dest=None):
         raise RuntimeError('error during blosc partial decompression: %d', ret)
 
     return dest
-        
+
 
 # set the value of this variable to True or False to override the
 # default adaptive behaviour

numcodecs/bz2.py

@@ -1,8 +1,7 @@
 import bz2 as _bz2
 
-
 from numcodecs.abc import Codec
-from numcodecs.compat import ndarray_copy, ensure_contiguous_ndarray
+from numcodecs.compat import ensure_contiguous_ndarray, ndarray_copy
 
 
 class BZ2(Codec):

numcodecs/categorize.py

@@ -1,9 +1,8 @@
-from .abc import Codec
-from .compat import ensure_ndarray, ndarray_copy, ensure_text
-
-
 import numpy as np
 
+from .abc import Codec
+from .compat import ensure_ndarray, ensure_text, ndarray_copy
+
 
 class Categorize(Codec):
     """Filter encoding categorical string data as integers.
@@ -41,7 +40,7 @@ class Categorize(Codec):
     def __init__(self, labels, dtype, astype='u1'):
         self.dtype = np.dtype(dtype)
         if self.dtype.kind not in 'UO':
-            raise TypeError("only unicode ('U') and object ('O') dtypes are " "supported")
+            raise TypeError("only unicode ('U') and object ('O') dtypes are supported")
         self.labels = [ensure_text(label) for label in labels]
         self.astype = np.dtype(astype)
         if self.astype == np.dtype(object):

numcodecs/checksum32.py

@@ -1,9 +1,7 @@
+import struct
 import zlib
 
-
 import numpy as np
-import struct
-
 
 from .abc import Codec
 from .compat import ensure_contiguous_ndarray, ndarray_copy

numcodecs/compat.py

@@ -1,7 +1,7 @@
-# flake8: noqa
-import functools
-import codecs
+# ruff: noqa: F401
 import array
+import codecs
+import functools
 
 import numpy as np
 

numcodecs/delta.py

@@ -1,6 +1,5 @@
 import numpy as np
 
-
 from .abc import Codec
 from .compat import ensure_ndarray, ndarray_copy
 

numcodecs/fixedscaleoffset.py

@@ -1,6 +1,5 @@
 import numpy as np
 
-
 from .abc import Codec
 from .compat import ensure_ndarray, ndarray_copy
 

numcodecs/jenkins.pyx

@@ -168,7 +168,7 @@ cpdef uint32_t jenkins_lookup3(const uint8_t[::1] _data, uint32_t initval=0):
     if length == 12:
         c += (<uint32_t>k[11]) << 24
         length -= 1
-        
+
     if length == 11:
         c += (<uint32_t>k[10]) << 16
         length -= 1
@@ -231,7 +231,7 @@ cdef inline uint32_t _jenkins_lookup3_final(uint32_t a, uint32_t b, uint32_t c):
       the output delta to a Gray code (a^(a>>1)) so a string of 1's (as
       is commonly produced by subtraction) look like a single 1-bit
       difference.
-    * the base values were pseudorandom, all zero but one bit set, or 
+    * the base values were pseudorandom, all zero but one bit set, or
       all zero plus a counter that starts at zero.
 
     These constants passed:
@@ -279,7 +279,7 @@ cdef inline (uint32_t, uint32_t, uint32_t) _jenkins_lookup3_mix(uint32_t a, uint
       the output delta to a Gray code (a^(a>>1)) so a string of 1's (as
       is commonly produced by subtraction) look like a single 1-bit
       difference.
-    * the base values were pseudorandom, all zero but one bit set, or 
+    * the base values were pseudorandom, all zero but one bit set, or
       all zero plus a counter that starts at zero.
 
     Some k values for my "a-=c; a^=rot(c,k); c+=b;" arrangement that
@@ -289,7 +289,7 @@ cdef inline (uint32_t, uint32_t, uint32_t) _jenkins_lookup3_mix(uint32_t a, uint
        14  9  3  7 17  3
     Well, "9 15 3 18 27 15" didn't quite get 32 bits diffing
     for "differ" defined as + with a one-bit base and a two-bit delta.  I
-    used http://burtleburtle.net/bob/hash/avalanche.html to choose 
+    used http://burtleburtle.net/bob/hash/avalanche.html to choose
     the operations, constants, and arrangements of the variables.
 
     This does not achieve avalanche.  There are input bits of (a,b,c)

numcodecs/json.py

@@ -1,10 +1,8 @@
 import json as _json
 import textwrap
 
-
 import numpy as np
 
-
 from .abc import Codec
 from .compat import ensure_text
 

numcodecs/lzma.py

@@ -10,7 +10,7 @@
 
 if _lzma:
     from .abc import Codec
-    from .compat import ndarray_copy, ensure_contiguous_ndarray
+    from .compat import ensure_contiguous_ndarray, ndarray_copy
 
     # noinspection PyShadowingBuiltins
     class LZMA(Codec):

numcodecs/msgpacks.py

@@ -1,6 +1,5 @@
-import numpy as np
 import msgpack
-
+import numpy as np
 
 from .abc import Codec
 from .compat import ensure_contiguous_ndarray

numcodecs/ndarray_like.py

@@ -1,4 +1,4 @@
-from typing import Any, Optional, Protocol, runtime_checkable
+from typing import Any, ClassVar, Optional, Protocol, runtime_checkable
 
 
 class _CachedProtocolMeta(Protocol.__class__):
@@ -11,7 +11,7 @@ class _CachedProtocolMeta(Protocol.__class__):
     isinstance checks using the object's class as the cache key.
     """
 
-    _instancecheck_cache: dict[tuple[type, type], bool] = {}
+    _instancecheck_cache: ClassVar[dict[tuple[type, type], bool]] = {}
 
     def __instancecheck__(self, instance):
         key = (self, instance.__class__)

numcodecs/packbits.py

@@ -1,6 +1,5 @@
 import numpy as np
 
-
 from .abc import Codec
 from .compat import ensure_ndarray, ndarray_copy
 

numcodecs/pcodec.py

@@ -1,11 +1,11 @@
-from typing import Optional, Literal
+from typing import Literal, Optional
 
 import numcodecs
 import numcodecs.abc
 from numcodecs.compat import ensure_contiguous_ndarray
 
 try:
-    from pcodec import standalone, ChunkConfig, PagingSpec, ModeSpec
+    from pcodec import ChunkConfig, ModeSpec, PagingSpec, standalone
 except ImportError:  # pragma: no cover
     standalone = None
 

numcodecs/quantize.py

@@ -1,9 +1,7 @@
 import math
 
-
 import numpy as np
 
-
 from .abc import Codec
 from .compat import ensure_ndarray, ndarray_copy
 
@@ -65,12 +63,12 @@ def encode(self, buf):
 
         # apply scaling
         precision = 10.0**-self.digits
-        exp = math.log(precision, 10)
+        exp = math.log10(precision)
         if exp < 0:
             exp = int(math.floor(exp))
         else:
             exp = int(math.ceil(exp))
-        bits = math.ceil(math.log(10.0**-exp, 2))
+        bits = math.ceil(math.log2(10.0**-exp))
         scale = 2.0**bits
         enc = np.around(scale * arr) / scale
 

numcodecs/registry.py

@@ -1,8 +1,8 @@
 """The registry module provides some simple convenience functions to enable
 applications to dynamically register and look-up codec classes."""
 
-from importlib.metadata import entry_points
 import logging
+from importlib.metadata import entry_points
 
 logger = logging.getLogger("numcodecs")
 codec_registry = {}

numcodecs/shuffle.py

@@ -1,7 +1,8 @@
 import numpy as np
-from .compat import ensure_contiguous_ndarray
-from .abc import Codec
+
 from ._shuffle import _doShuffle, _doUnshuffle
+from .abc import Codec
+from .compat import ensure_contiguous_ndarray
 
 
 class Shuffle(Codec):

numcodecs/tests/common.py

@@ -3,19 +3,15 @@
 import os
 from glob import glob
 
-
 import numpy as np
-from numpy.testing import assert_array_almost_equal, assert_array_equal
 import pytest
+from numpy.testing import assert_array_almost_equal, assert_array_equal
 
-
+# star import needed for repr tests so eval finds names
+from numcodecs import *  # noqa: F403
 from numcodecs.compat import ensure_bytes, ensure_ndarray
 from numcodecs.registry import get_codec
 
-# star import needed for repr tests so eval finds names
-from numcodecs import *  # noqa
-
-
 greetings = [
     '¡Hola mundo!',
     'Hej Världen!',
@@ -200,7 +196,7 @@ def assert_array_items_equal(res, arr):
     # and values
     arr = arr.ravel().tolist()
     res = res.ravel().tolist()
-    for a, r in zip(arr, res):
+    for a, r in zip(arr, res, strict=True):
         if isinstance(a, np.ndarray):
             assert_array_equal(a, r)
         elif a != a: