Merge branch 'v3' into use_map_str_tst_accessed

Author: jhamman

.gitignore

@@ -84,3 +84,5 @@ fixture/
 .DS_Store
 tests/.hypothesis
 .hypothesis/
+
+zarr/version.py

pyproject.toml

@@ -208,18 +208,26 @@ extend-exclude = [
 [tool.ruff.lint]
 extend-select = [
     "B",   # flake8-bugbear
+    "FLY", # flynt
     "I",   # isort
     "ISC", # flake8-implicit-str-concat
     "PGH", # pygrep-hooks
+    "PT",  # flake8-pytest-style
     "PYI", # flake8-pyi
     "RSE", # flake8-raise
+    "RET", # flake8-return
     "RUF",
     "TCH", # flake8-type-checking
     "TRY", # tryceratops
     "UP",  # pyupgrade
 ]
 ignore = [
+    "PT004",  # deprecated
+    "PT011",  # TODO: apply this rule
+    "PT012",  # TODO: apply this rule
     "PYI013",
+    "RET505",
+    "RET506",
     "RUF005",
     "TRY003",
     # https://docs.astral.sh/ruff/formatter/#conflicting-lint-rules

src/zarr/abc/store.py

@@ -170,7 +170,7 @@ async def _set_many(self, values: Iterable[tuple[str, Buffer]]) -> None:
         Insert multiple (key, value) pairs into storage.
         """
         await gather(*(self.set(key, value) for key, value in values))
-        return None
+        return
 
     @property
     @abstractmethod

src/zarr/codecs/_v2.py

@@ -8,16 +8,18 @@
 
 from zarr.abc.codec import ArrayArrayCodec, ArrayBytesCodec
 from zarr.core.buffer import Buffer, NDBuffer, default_buffer_prototype
-from zarr.core.common import JSON, to_thread
+from zarr.core.common import to_thread
 from zarr.registry import get_ndbuffer_class
 
 if TYPE_CHECKING:
+    import numcodecs.abc
+
     from zarr.core.array_spec import ArraySpec
 
 
 @dataclass(frozen=True)
 class V2Compressor(ArrayBytesCodec):
-    compressor: dict[str, JSON] | None
+    compressor: numcodecs.abc.Codec | None
 
     is_fixed_size = False
 
@@ -27,9 +29,8 @@ async def _decode_single(
         chunk_spec: ArraySpec,
     ) -> NDBuffer:
         if self.compressor is not None:
-            compressor = numcodecs.get_codec(self.compressor)
             chunk_numpy_array = ensure_ndarray(
-                await to_thread(compressor.decode, chunk_bytes.as_array_like())
+                await to_thread(self.compressor.decode, chunk_bytes.as_array_like())
             )
         else:
             chunk_numpy_array = ensure_ndarray(chunk_bytes.as_array_like())
@@ -47,14 +48,13 @@ async def _encode_single(
     ) -> Buffer | None:
         chunk_numpy_array = chunk_array.as_numpy_array()
         if self.compressor is not None:
-            compressor = numcodecs.get_codec(self.compressor)
             if (
                 not chunk_numpy_array.flags.c_contiguous
                 and not chunk_numpy_array.flags.f_contiguous
             ):
                 chunk_numpy_array = chunk_numpy_array.copy(order="A")
             encoded_chunk_bytes = ensure_bytes(
-                await to_thread(compressor.encode, chunk_numpy_array)
+                await to_thread(self.compressor.encode, chunk_numpy_array)
             )
         else:
             encoded_chunk_bytes = ensure_bytes(chunk_numpy_array)

src/zarr/core/array.py

@@ -9,7 +9,6 @@
 import numpy.typing as npt
 
 from zarr._compat import _deprecate_positional_args
-from zarr.abc.codec import Codec, CodecPipeline
 from zarr.abc.store import set_or_delete
 from zarr.codecs import BytesCodec
 from zarr.codecs._v2 import V2Compressor, V2Filters
@@ -252,12 +251,6 @@ async def _create_v3(
         shape = parse_shapelike(shape)
         codecs = list(codecs) if codecs is not None else [BytesCodec()]
 
-        if fill_value is None:
-            if dtype == np.dtype("bool"):
-                fill_value = False
-            else:
-                fill_value = 0
-
         if chunk_key_encoding is None:
             chunk_key_encoding = ("default", "/")
         assert chunk_key_encoding is not None
@@ -281,7 +274,6 @@ async def _create_v3(
         )
 
         array = cls(metadata=metadata, store_path=store_path)
-
         await array._save_metadata(metadata)
         return array
 

src/zarr/core/buffer/core.py

@@ -464,10 +464,14 @@ def __repr__(self) -> str:
 
     def all_equal(self, other: Any, equal_nan: bool = True) -> bool:
         """Compare to `other` using np.array_equal."""
+        if other is None:
+            # Handle None fill_value for Zarr V2
+            return False
         # use array_equal to obtain equal_nan=True functionality
         data, other = np.broadcast_arrays(self._data, other)
-        result = np.array_equal(self._data, other, equal_nan=equal_nan)
-        return result
+        return np.array_equal(
+            self._data, other, equal_nan=equal_nan if self._data.dtype.kind not in "US" else False
+        )
 
     def fill(self, value: Any) -> None:
         self._data.fill(value)

src/zarr/core/group.py

@@ -676,7 +676,7 @@ async def _members(
                     async for child_key, val in obj._members(
                         max_depth=max_depth, current_depth=current_depth + 1
                     ):
-                        yield "/".join([key, child_key]), val
+                        yield f"{key}/{child_key}", val
             except KeyError:
                 # keyerror is raised when `key` names an object (in the object storage sense),
                 # as opposed to a prefix, in the store under the prefix associated with this group

src/zarr/core/metadata/v2.py

@@ -100,6 +100,8 @@ def _json_convert(
                     return o.str
                 else:
                     return o.descr
+            if isinstance(o, numcodecs.abc.Codec):
+                return o.get_config()
             if np.isscalar(o):
                 out: Any
                 if hasattr(o, "dtype") and o.dtype.kind == "M" and hasattr(o, "view"):

src/zarr/core/metadata/v3.py

@@ -360,7 +360,7 @@ def parse_fill_value(
     if fill_value is None:
         return dtype.type(0)
     if isinstance(fill_value, Sequence) and not isinstance(fill_value, str):
-        if dtype in (np.complex64, np.complex128):
+        if dtype.type in (np.complex64, np.complex128):
             dtype = cast(COMPLEX_DTYPE, dtype)
             if len(fill_value) == 2:
                 # complex datatypes serialize to JSON arrays with two elements
@@ -391,7 +391,7 @@ def parse_fill_value(
         pass
     elif fill_value in ["Infinity", "-Infinity"] and not np.isfinite(casted_value):
         pass
-    elif dtype.kind == "f":
+    elif dtype.kind in "cf":
         # float comparison is not exact, especially when dtype <float64
         # so we us np.isclose for this comparison.
         # this also allows us to compare nan fill_values

src/zarr/store/memory.py

@@ -1,6 +1,5 @@
 from __future__ import annotations
 
-from collections.abc import AsyncGenerator, MutableMapping
 from typing import TYPE_CHECKING
 
 from zarr.abc.store import Store