Merge remote-tracking branch 'upstream/main' into perf/codec-chain

# Conflicts:
#	src/zarr/abc/store.py
#	src/zarr/storage/_common.py
#	src/zarr/storage/_local.py
#	src/zarr/testing/store.py
#	tests/test_codecs/test_zstd.py

Author: d-v-b

docs/_static/favicon-96x96.png

@@ -56,11 +56,6 @@
 .md-header .md-search__input {
   background-color: rgba(255, 255, 255, 0.15);
   border: 1px solid rgba(255, 255, 255, 0.2);
-  color: white;
-}
-
-.md-header .md-search__input::placeholder {
-  color: rgba(255, 255, 255, 0.7);
 }
 
 /* Navigation tabs */

docs/overrides/stylesheets/extra.css

@@ -0,0 +1,110 @@
+# Glossary
+
+This page defines key terms used throughout the zarr-python documentation and API.
+
+## Array Structure
+
+### Array
+
+An N-dimensional typed array stored in a Zarr [store](#store). An array's
+[metadata](#metadata) defines its shape, data type, chunk layout, and codecs.
+
+### Chunk
+
+The fundamental unit of data in a Zarr array. An array is divided into chunks
+along each dimension according to the [chunk grid](#chunk-grid), which is currently
+part of Zarr's private API. Each chunk is independently compressed and encoded
+through the array's [codec](#codec) pipeline.
+
+When [sharding](#shard) is used, "chunk" refers to the inner chunks within each
+shard, because those are the compressible units. The chunks are the smallest units
+that can be read independently.
+
+!!! warning "Convention specific to zarr-python"
+    The use of "chunk" to mean the inner sub-chunk within a shard is a convention
+    adopted by zarr-python's `Array` API. In the Zarr V3 specification and in other
+    Zarr implementations, "chunk" may refer to the top-level grid cells (which
+    zarr-python calls "shards" when the sharding codec is used). Be aware of this
+    distinction when working across libraries.
+
+**API**: [`Array.chunks`][zarr.Array.chunks] returns the chunk shape. When
+sharding is used, this is the inner chunk shape.
+
+### Chunk Grid
+
+The partitioning of an array's elements into [chunks](#chunk). In Zarr V3, the
+chunk grid is defined in the array [metadata](#metadata) and determines the
+boundaries of each storage object.
+
+When sharding is used, the chunk grid defines the [shard](#shard) boundaries,
+not the inner chunk boundaries. The inner chunk shape is defined within the
+[sharding codec](#shard).
+
+**API**: The `chunk_grid` field in array metadata contains the storage-level
+grid.
+
+### Shard
+
+A storage object that contains one or more [chunks](#chunk). Sharding reduces the
+number of objects in a [store](#store) by grouping chunks together, which
+improves performance on file systems and object storage.
+
+Within each shard, chunks are compressed independently and can be read
+individually. However, writing requires updating the full shard for consistency,
+making shards the unit of writing and chunks the unit of reading.
+
+Sharding is implemented as a [codec](#codec) (the sharding indexed codec).
+When sharding is used:
+
+- The [chunk grid](#chunk-grid) in metadata defines the shard boundaries
+- The sharding codec's `chunk_shape` defines the inner chunk size
+- Each shard contains `shard_shape / chunk_shape` chunks per dimension
+
+**API**: [`Array.shards`][zarr.Array.shards] returns the shard shape, or `None`
+if sharding is not used. [`Array.chunks`][zarr.Array.chunks] returns the inner
+chunk shape.
+
+## Storage
+
+### Store
+
+A key-value storage backend that holds Zarr data and metadata. Stores implement
+the [`zarr.abc.store.Store`][] interface. Examples include local file systems,
+cloud object storage (S3, GCS, Azure), zip files, and in-memory dictionaries.
+
+Each [chunk](#chunk) or [shard](#shard) is stored as a single value (object or
+file) in the store, addressed by a key derived from its grid coordinates.
+
+### Metadata
+
+The JSON document (`zarr.json`) that describes an [array](#array) or group. For
+arrays, metadata includes the shape, data type, [chunk grid](#chunk-grid), fill
+value, and [codec](#codec) pipeline. Metadata is stored alongside the data in
+the [store](#store). Zarr-Python does not yet expose its internal metadata
+representation as part of its public API.
+
+## Codecs
+
+### Codec
+
+A transformation applied to array data during reading and writing. Codecs are
+chained into a pipeline and come in three types:
+
+- **Array-to-array**: Transforms like transpose that rearrange array elements
+- **Array-to-bytes**: Serialization that converts an array to a byte sequence
+  (exactly one required)
+- **Bytes-to-bytes**: Compression or checksums applied to the serialized bytes
+
+The [sharding indexed codec](#shard) is a special array-to-bytes codec that
+groups multiple [chunks](#chunk) into a single storage object.
+
+## API Properties
+
+The following properties are available on [`zarr.Array`][]:
+
+| Property | Description |
+|----------|-------------|
+| `.chunks` | Chunk shape — the inner chunk shape when sharding is used |
+| `.shards` | Shard shape, or `None` if no sharding |
+| `.nchunks` | Total number of independently compressible units across the array |
+| `.cdata_shape` | Number of independently compressible units per dimension |

docs/user-guide/glossary.md

@@ -35,6 +35,10 @@ Take your skills to the next level:
 - **[Extending](extending.md)** - Extend functionality with custom code
 - **[Consolidated Metadata](consolidated_metadata.md)** - Advanced metadata management
 
+## Reference
+
+- **[Glossary](glossary.md)** - Definitions of key terms (chunks, shards, codecs, etc.)
+
 ## Need Help?
 
 - Browse the [API Reference](../api/zarr/index.md) for detailed function documentation

docs/user-guide/index.md

@@ -27,6 +27,7 @@ nav:
       - user-guide/gpu.md
       - user-guide/consolidated_metadata.md
       - user-guide/experimental.md
+      - user-guide/glossary.md
   - Examples:
       - user-guide/examples/custom_dtype.md
   - API Reference:
@@ -84,6 +85,7 @@ theme:
   name: material
   custom_dir: docs/overrides
   logo: _static/logo_bw.png
+  favicon: _static/favicon-96x96.png
 
   palette:
     # Light mode

mkdocs.yml

@@ -22,7 +22,6 @@
     "Store",
     "SupportsDeleteSync",
     "SupportsGetSync",
-    "SupportsSetRangeSync",
     "SupportsSetSync",
     "SupportsSyncStore",
     "set_or_delete",
@@ -726,20 +725,13 @@ class SupportsSetSync(Protocol):
     def set_sync(self, key: str, value: Buffer) -> None: ...
 
 
-@runtime_checkable
-class SupportsSetRangeSync(Protocol):
-    def set_range_sync(self, key: str, value: Buffer, start: int) -> None: ...
-
-
 @runtime_checkable
 class SupportsDeleteSync(Protocol):
     def delete_sync(self, key: str) -> None: ...
 
 
 @runtime_checkable
-class SupportsSyncStore(
-    SupportsGetSync, SupportsSetSync, SupportsSetRangeSync, SupportsDeleteSync, Protocol
-): ...
+class SupportsSyncStore(SupportsGetSync, SupportsSetSync, SupportsDeleteSync, Protocol): ...
 
 
 async def set_or_delete(byte_setter: ByteSetter, value: Buffer | None) -> None:

src/zarr/abc/store.py

@@ -126,11 +126,14 @@ def normalize_chunks(chunks: Any, shape: tuple[int, ...], typesize: int) -> tupl
         chunks = tuple(int(chunks) for _ in shape)
 
     # handle dask-style chunks (iterable of iterables)
-    if all(isinstance(c, (tuple | list)) for c in chunks):
-        # take first chunk size for each dimension
-        chunks = tuple(
-            c[0] for c in chunks
-        )  # TODO: check/error/warn for irregular chunks (e.g. if c[0] != c[1:-1])
+    if all(isinstance(c, (tuple, list)) for c in chunks):
+        for i, c in enumerate(chunks):
+            if any(x != y for x, y in itertools.pairwise(c[:-1])) or (len(c) > 1 and c[-1] > c[0]):
+                raise ValueError(
+                    f"Irregular chunk sizes in dimension {i}: {tuple(c)}. "
+                    "Only uniform chunks (with an optional smaller final chunk) are supported."
+                )
+        chunks = tuple(c[0] for c in chunks)
 
     # handle bad dimensionality
     if len(chunks) > len(shape):

src/zarr/core/chunk_grids.py

@@ -370,6 +370,8 @@ async def read_batch(
                 chunk_array_batch, batch_info, strict=False
             ):
                 if chunk_array is not None:
+                    if drop_axes:
+                        chunk_array = chunk_array.squeeze(axis=drop_axes)
                     out[out_selection] = chunk_array
                 else:
                     out[out_selection] = fill_value_or_default(chunk_spec)
@@ -392,7 +394,7 @@ async def read_batch(
             ):
                 if chunk_array is not None:
                     tmp = chunk_array[chunk_selection]
-                    if drop_axes != ():
+                    if drop_axes:
                         tmp = tmp.squeeze(axis=drop_axes)
                     out[out_selection] = tmp
                 else:
@@ -431,7 +433,7 @@ def _merge_chunk_array(
         else:
             chunk_value = value[out_selection]
             # handle missing singleton dimensions
-            if drop_axes != ():
+            if drop_axes:
                 item = tuple(
                     None  # equivalent to np.newaxis
                     if idx in drop_axes

src/zarr/core/codec_pipeline.py

@@ -5,7 +5,13 @@
 from pathlib import Path
 from typing import TYPE_CHECKING, Any, Literal, Self, TypeAlias
 
-from zarr.abc.store import ByteRequest, Store
+from zarr.abc.store import (
+    ByteRequest,
+    Store,
+    SupportsDeleteSync,
+    SupportsGetSync,
+    SupportsSetSync,
+)
 from zarr.core.buffer import Buffer, default_buffer_prototype
 from zarr.core.common import (
     ANY_ACCESS_MODE,
@@ -239,21 +245,25 @@ def get_sync(
         byte_range: ByteRequest | None = None,
     ) -> Buffer | None:
         """Synchronous read — delegates to ``self.store.get_sync(self.path, ...)``."""
+        if not isinstance(self.store, SupportsGetSync):
+            raise TypeError(f"Store {type(self.store).__name__} does not support synchronous get.")
         if prototype is None:
             prototype = default_buffer_prototype()
-        return self.store.get_sync(self.path, prototype=prototype, byte_range=byte_range)  # type: ignore[attr-defined, no-any-return]
+        return self.store.get_sync(self.path, prototype=prototype, byte_range=byte_range)
 
     def set_sync(self, value: Buffer) -> None:
         """Synchronous write — delegates to ``self.store.set_sync(self.path, value)``."""
-        self.store.set_sync(self.path, value)  # type: ignore[attr-defined]
-
-    def set_range_sync(self, value: Buffer, start: int) -> None:
-        """Synchronous byte-range write."""
-        self.store.set_range_sync(self.path, value, start)  # type: ignore[attr-defined]
+        if not isinstance(self.store, SupportsSetSync):
+            raise TypeError(f"Store {type(self.store).__name__} does not support synchronous set.")
+        self.store.set_sync(self.path, value)
 
     def delete_sync(self) -> None:
         """Synchronous delete — delegates to ``self.store.delete_sync(self.path)``."""
-        self.store.delete_sync(self.path)  # type: ignore[attr-defined]
+        if not isinstance(self.store, SupportsDeleteSync):
+            raise TypeError(
+                f"Store {type(self.store).__name__} does not support synchronous delete."
+            )
+        self.store.delete_sync(self.path)
 
     def __truediv__(self, other: str) -> StorePath:
         """Combine this store path with another path"""

src/zarr/storage/_common.py

@@ -85,19 +85,6 @@ def _put(path: Path, value: Buffer, exclusive: bool = False) -> int:
         return f.write(view)
 
 
-def _put_range(path: Path, value: Buffer, start: int) -> None:
-    view = value.as_buffer_like()
-    file_size = path.stat().st_size
-    if start + len(view) > file_size:
-        raise ValueError(
-            f"set_range would write beyond the end of the stored value: "
-            f"start={start}, len(value)={len(view)}, stored size={file_size}"
-        )
-    with path.open("r+b") as f:
-        f.seek(start)
-        f.write(view)
-
-
 class LocalStore(Store):
     """
     Store for the local file system.
@@ -241,12 +228,6 @@ def set_sync(self, key: str, value: Buffer) -> None:
         path = self.root / key
         _put(path, value)
 
-    def set_range_sync(self, key: str, value: Buffer, start: int) -> None:
-        self._ensure_open_sync()
-        self._check_writable()
-        path = self.root / key
-        _put_range(path, value, start)
-
     def delete_sync(self, key: str) -> None:
         self._ensure_open_sync()
         self._check_writable()