Merge remote-tracking branch 'upstream/main' into gpu-codecs

Author: TomAugspurger

.github/workflows/check_changelogs.yml

@@ -0,0 +1,18 @@
+name: Check changelog entries
+
+on:
+  pull_request:
+
+jobs:
+  check-changelogs:
+    name: Check changelog entries
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@e92bafb6253dcd438e0484186d7669ea7a8ca1cc # v6.4.3
+
+      - name: Check changelog entries
+        run: uv run --no-sync python ci/check_changelog_entries.py

LICENSE.txt

@@ -1,6 +1,6 @@
 The MIT License (MIT)
 
-Copyright (c) 2015-2024 Zarr Developers <https://github.com/zarr-developers>
+Copyright (c) 2015-2025 Zarr Developers <https://github.com/zarr-developers>
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

changes/3251.fix.rst renamed to changes/3251.bugfix.rst

@@ -0,0 +1,4 @@
+- Expand the range of types accepted by ``parse_data_type`` to include strings and Sequences.
+- Move the functionality of ``parse_data_type`` to a new function called ``parse_dtype``. This change
+  ensures that nomenclature is consistent across the codebase. ``parse_data_type`` remains, so this
+  change is not breaking.

changes/+c563f4d4.bugfix.rst renamed to changes/3258.bugfix.rst

@@ -0,0 +1 @@
+Add a section on codecs to the migration guide.

changes/3264.bugfix.rst

@@ -0,0 +1,2 @@
+Fix a regression introduced in 3.1.0 that prevented ``inf``, ``-inf``, and ``nan`` values
+from being stored in ``attributes``.

changes/3273.doc.rst

@@ -0,0 +1 @@
+Fixes Group.nmembers() ignoring depth when using consolidated metadata.

changes/3280.bugfix.rst

@@ -0,0 +1,51 @@
+"""
+Check changelog entries have the correct filename structure.
+"""
+
+import sys
+from pathlib import Path
+
+VALID_CHANGELOG_TYPES = ["feature", "bugfix", "doc", "removal", "misc"]
+CHANGELOG_DIRECTORY = (Path(__file__).parent.parent / "changes").resolve()
+
+
+def is_int(s: str) -> bool:
+    try:
+        int(s)
+    except ValueError:
+        return False
+    else:
+        return True
+
+
+if __name__ == "__main__":
+    print(f"Looking for changelog entries in {CHANGELOG_DIRECTORY}")
+    entries = CHANGELOG_DIRECTORY.glob("*")
+    entries = [e for e in entries if e.name not in [".gitignore", "README.md"]]
+    print(f"Found {len(entries)} entries")
+    print()
+
+    bad_suffix = [e for e in entries if e.suffix != ".rst"]
+    bad_issue_no = [e for e in entries if not is_int(e.name.split(".")[0])]
+    bad_type = [e for e in entries if e.name.split(".")[1] not in VALID_CHANGELOG_TYPES]
+
+    if len(bad_suffix) or len(bad_issue_no) or len(bad_type):
+        if len(bad_suffix):
+            print("Changelog entries without .rst suffix")
+            print("-------------------------------------")
+            print("\n".join([p.name for p in bad_suffix]))
+            print()
+        if len(bad_issue_no):
+            print("Changelog entries without integer issue number")
+            print("----------------------------------------------")
+            print("\n".join([p.name for p in bad_issue_no]))
+            print()
+        if len(bad_type):
+            print("Changelog entries without valid type")
+            print("------------------------------------")
+            print("\n".join([p.name for p in bad_type]))
+            print(f"Valid types are: {VALID_CHANGELOG_TYPES}")
+            print()
+        sys.exit(1)
+
+    sys.exit(0)

changes/3287.bugfix.rst

@@ -412,17 +412,17 @@ attempt data type resolution against *every* data type class, and if, for some r
 type matches multiple Zarr data types, we treat this as an error and raise an exception.
 
 If you have a NumPy data type and you want to get the corresponding ``ZDType`` instance, you can use
-the ``parse_data_type`` function, which will use the dynamic resolution described above. ``parse_data_type``
+the ``parse_dtype`` function, which will use the dynamic resolution described above. ``parse_dtype``
 handles a range of input types:
 
 - NumPy data types:
 
   .. code-block:: python
 
     >>> import numpy as np
-    >>> from zarr.dtype import parse_data_type
+    >>> from zarr.dtype import parse_dtype
     >>> my_dtype = np.dtype('>M8[10s]')
-    >>> parse_data_type(my_dtype, zarr_format=2)
+    >>> parse_dtype(my_dtype, zarr_format=2)
     DateTime64(endianness='big', scale_factor=10, unit='s')
 
 
@@ -431,7 +431,7 @@ handles a range of input types:
   .. code-block:: python
 
     >>> dtype_str = '>M8[10s]'
-    >>> parse_data_type(dtype_str, zarr_format=2)
+    >>> parse_dtype(dtype_str, zarr_format=2)
     DateTime64(endianness='big', scale_factor=10, unit='s')
 
 - ``ZDType`` instances:
@@ -440,7 +440,7 @@ handles a range of input types:
 
     >>> from zarr.dtype import DateTime64
     >>> zdt = DateTime64(endianness='big', scale_factor=10, unit='s')
-    >>> parse_data_type(zdt, zarr_format=2) # Use a ZDType (this is a no-op)
+    >>> parse_dtype(zdt, zarr_format=2) # Use a ZDType (this is a no-op)
     DateTime64(endianness='big', scale_factor=10, unit='s')
 
 - Python dictionaries (requires ``zarr_format=3``). These dictionaries must be consistent with the
@@ -449,7 +449,7 @@ handles a range of input types:
   .. code-block:: python
 
     >>> dt_dict = {"name": "numpy.datetime64", "configuration": {"unit": "s", "scale_factor": 10}}
-    >>> parse_data_type(dt_dict, zarr_format=3)
+    >>> parse_dtype(dt_dict, zarr_format=3)
     DateTime64(endianness='little', scale_factor=10, unit='s')
-    >>> parse_data_type(dt_dict, zarr_format=3).to_json(zarr_format=3)
+    >>> parse_dtype(dt_dict, zarr_format=3).to_json(zarr_format=3)
     {'name': 'numpy.datetime64', 'configuration': {'unit': 's', 'scale_factor': 10}}