Merge branch 'main' into ruff_0.9.1

.pre-commit-config.yaml

@@ -14,19 +14,19 @@ repos:
     - id: debug-statements
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.9.1
+    rev: v0.9.4
     hooks:
     - id: ruff
       args: ["--fix", "--show-fixes"]
     - id: ruff-format
 
   - repo: https://github.com/scientific-python/cookie
-    rev: 2024.08.19
+    rev: 2025.01.22
     hooks:
     - id: sp-repo-review
 
   -   repo: https://github.com/pre-commit/mirrors-mypy
-      rev: v1.14.0
+      rev: v1.14.1
       hooks:
       -   id: mypy
           args: [--config-file, pyproject.toml]

docs/release.rst

@@ -11,11 +11,27 @@ Release notes
     Unreleased
     ----------
 
+
 .. _unreleased:
 
 Unreleased
 ----------
 
+Improvements
+~~~~~~~~~~~~
+* Raise a custom `UnknownCodecError` when trying to retrieve an unavailable codec.
+  By :user:`Cas Wognum <cwognum>`.
+
+Fixes
+~~~~~
+* Remove redundant ``id`` from codec metadata serialization in Zarr3 codecs.
+  By :user:`Norman Rzepka <normanrz>`, :issue:`685`
+
+.. _release_0.15.0:
+
+0.15.0
+------
+
 Breaking changes
 ~~~~~~~~~~~~~~~~
 * All arguments to the ``PCodec`` constructor except for ``level``
@@ -36,11 +52,16 @@ This is because they are not intended to be public API.
 In addition, ``numcodecs.blosc.decompress_partial`` is deprecated as
 has always been experimental and there is no equivalent in the official
 blsoc Python package.
+By :user:`David Stansby <dstansby>`, :issue`619`
 
 Fixes
 ~~~~~
 * Fixes issue with ``Delta`` Zarr 3 codec not working with ``astype``.
   By :user:`Norman Rzepka <normanrz>`, :issue:`664`
+* Cleanup ``PCodec`` soft dependency.
+  Previously importing ``numcodecs.pcodec`` would work if ``pcodec`` is not installed,
+  but now it will fail to import. This mirrors the behaviour of other optional dependencies.
+  By :user:`John Kirkham <jakirkham>`, :issue:`647`
 * Fixes issues with the upcoming ``zarr`` 3.0.0 release.
   By :user:`Norman Rzepka <normanrz>`, :issue:`675`
 
@@ -64,6 +85,7 @@ Improvements
   are still silently caught.
   By :user:`David Stansby <dstansby>`, :issue:`550`.
 
+.. _release_0.14.1:
 
 0.14.1
 ------

numcodecs/checksum32.py

@@ -13,7 +13,7 @@
 
 _crc32c: Optional[ModuleType] = None
 with suppress(ImportError):
-    import crc32c as _crc32c  # type: ignore[no-redef]
+    import crc32c as _crc32c  # type: ignore[no-redef, unused-ignore]
 
 if TYPE_CHECKING:  # pragma: no cover
     from typing_extensions import Buffer

numcodecs/delta.py

@@ -63,12 +63,7 @@ def encode(self, buf):
         enc[0] = arr[0]
 
         # compute differences
-        # using np.subtract for in-place operations
-        if arr.dtype == bool:
-            np.not_equal(arr[1:], arr[:-1], out=enc[1:])
-        else:
-            np.subtract(arr[1:], arr[:-1], out=enc[1:])
-
+        enc[1:] = np.diff(arr)
         return enc
 
     def decode(self, buf, out=None):

numcodecs/errors.py

@@ -0,0 +1,26 @@
+"""
+This module defines custom exceptions that are raised in the `numcodecs` codebase.
+"""
+
+
+class UnknownCodecError(ValueError):
+    """
+    An exception that is raised when trying to receive a codec that has not been registered.
+
+    Parameters
+    ----------
+    codec_id : str
+        Codec identifier.
+
+    Examples
+    ----------
+    >>> import numcodecs
+    >>> numcodecs.get_codec({"codec_id": "unknown"})
+    Traceback (most recent call last):
+        ...
+    UnknownCodecError: codec not available: 'unknown'
+    """
+
+    def __init__(self, codec_id: str):
+        self.codec_id = codec_id
+        super().__init__(f"codec not available: '{codec_id}'")

numcodecs/json.py

@@ -68,7 +68,7 @@ def __init__(
     def encode(self, buf):
         try:
             buf = np.asarray(buf)
-        except ValueError:
+        except ValueError:  # pragma: no cover
             buf = np.asarray(buf, dtype=object)
         items = np.atleast_1d(buf).tolist()
         items.append(buf.dtype.str)

numcodecs/pcodec.py

@@ -2,12 +2,7 @@
 
 from numcodecs.abc import Codec
 from numcodecs.compat import ensure_contiguous_ndarray
-
-try:
-    from pcodec import ChunkConfig, DeltaSpec, ModeSpec, PagingSpec, standalone
-except ImportError:  # pragma: no cover
-    standalone = None
-
+from pcodec import ChunkConfig, DeltaSpec, ModeSpec, PagingSpec, standalone
 
 DEFAULT_MAX_PAGE_N = 262144
 
@@ -58,9 +53,6 @@ def __init__(
         delta_encoding_order: int | None = None,
         equal_pages_up_to: int = DEFAULT_MAX_PAGE_N,
     ):
-        if standalone is None:  # pragma: no cover
-            raise ImportError("pcodec must be installed to use the PCodec codec.")
-
         # note that we use `level` instead of `compression_level` to
         # match other codecs
         self.level = level

numcodecs/quantize.py

@@ -65,9 +65,9 @@ def encode(self, buf):
         precision = 10.0**-self.digits
         exp = math.log10(precision)
         if exp < 0:
-            exp = int(math.floor(exp))
+            exp = math.floor(exp)
         else:
-            exp = int(math.ceil(exp))
+            exp = math.ceil(exp)
         bits = math.ceil(math.log2(10.0**-exp))
         scale = 2.0**bits
         enc = np.around(scale * arr) / scale

numcodecs/registry.py

@@ -5,6 +5,7 @@
 from importlib.metadata import EntryPoints, entry_points
 
 from numcodecs.abc import Codec
+from numcodecs.errors import UnknownCodecError
 
 logger = logging.getLogger("numcodecs")
 codec_registry: dict[str, Codec] = {}
@@ -50,7 +51,7 @@ def get_codec(config):
         register_codec(cls, codec_id=codec_id)
     if cls:
         return cls.from_config(config)
-    raise ValueError(f'codec not available: {codec_id!r}')
+    raise UnknownCodecError(f"{codec_id!r}")
 
 
 def register_codec(cls, codec_id=None):

numcodecs/tests/test_pcodec.py

@@ -1,11 +1,8 @@
 import numpy as np
 import pytest
 
-from numcodecs.pcodec import PCodec
-
 try:
-    # initializing codec triggers ImportError
-    PCodec()
+    from numcodecs.pcodec import PCodec
 except ImportError:  # pragma: no cover
     pytest.skip("pcodec not available", allow_module_level=True)
 

numcodecs/tests/test_registry.py

@@ -3,11 +3,12 @@
 import pytest
 
 import numcodecs
+from numcodecs.errors import UnknownCodecError
 from numcodecs.registry import get_codec
 
 
 def test_registry_errors():
-    with pytest.raises(ValueError):
+    with pytest.raises(UnknownCodecError, match='foo'):
         get_codec({'id': 'foo'})
 
 

numcodecs/tests/test_vlen_bytes.py

@@ -84,6 +84,9 @@ def test_decode_errors():
         codec.decode(enc, out=np.zeros(10, dtype='i4'))
 
 
+# TODO: fix this test on GitHub actions somehow...
+# See https://github.com/zarr-developers/numcodecs/issues/683
+@pytest.mark.skip("Test is failing on GitHub actions.")
 def test_encode_none():
     a = np.array([b'foo', None, b'bar'], dtype=object)
     codec = VLenBytes()

numcodecs/tests/test_zarr3.py

@@ -225,11 +225,11 @@ def test_generic_bytes_codec(
 ):
     try:
         codec_class()._codec  # noqa: B018
-    except ValueError as e:
+    except ValueError as e:  # pragma: no cover
         if "codec not available" in str(e):
             pytest.xfail(f"{codec_class.codec_name} is not available: {e}")
         else:
-            raise  # pragma: no cover
+            raise
     except ImportError as e:  # pragma: no cover
         pytest.xfail(f"{codec_class.codec_name} is not available: {e}")
 
@@ -272,3 +272,8 @@ def test_delta_astype(store: StorePath):
 def test_repr():
     codec = numcodecs.zarr3.LZ4(level=5)
     assert repr(codec) == "LZ4(codec_name='numcodecs.lz4', codec_config={'level': 5})"
+
+
+def test_to_dict():
+    codec = numcodecs.zarr3.LZ4(level=5)
+    assert codec.to_dict() == {"name": "numcodecs.lz4", "configuration": {"level": 5}}

numcodecs/zarr3.py

@@ -112,6 +112,7 @@ def from_dict(cls, data: dict[str, JSON]) -> Self:
 
     def to_dict(self) -> dict[str, JSON]:
         codec_config = self.codec_config.copy()
+        codec_config.pop("id", None)
         return {
             "name": self.codec_name,
             "configuration": codec_config,

pyproject.toml

@@ -235,3 +235,6 @@ enable_error_code = ["ignore-without-code", "redundant-expr", "truthy-bool"]
 # TODO: set options below to true
 strict = false
 warn_unreachable = false
+warn_redundant_casts = true
+warn_unused_ignores = true
+warn_unused_configs = true