Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion .pre-commit-config.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,6 @@ repos:
- numcodecs
- numpy
- typing_extensions
- zstandard
# Tests
- pytest
# Zarr v2
Expand Down
5 changes: 2 additions & 3 deletions pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,6 @@ dependencies = [
'numcodecs>=0.10.0',
'fsspec>2024',
'crc32c',
'zstandard',
'typing_extensions',
'donfig',
]
Expand Down Expand Up @@ -85,8 +84,8 @@ docs = [
'pydata-sphinx-theme',
'numpydoc',
'numcodecs[msgpack]',
"msgpack",
"lmdb",
'msgpack',
'lmdb',
]
extra = [
'msgpack',
Expand Down
30 changes: 18 additions & 12 deletions src/zarr/codecs/zstd.py
Original file line number Diff line number Diff line change
@@ -1,10 +1,11 @@
from __future__ import annotations

from dataclasses import dataclass
from typing import TYPE_CHECKING, Any
from functools import cached_property
from importlib.metadata import version
from typing import TYPE_CHECKING

import numpy.typing as npt
from zstandard import ZstdCompressor, ZstdDecompressor
from numcodecs.zstd import Zstd

from zarr.abc.codec import BytesBytesCodec
from zarr.array_spec import ArraySpec
Expand Down Expand Up @@ -38,6 +39,14 @@ class ZstdCodec(BytesBytesCodec):
checksum: bool = False

def __init__(self, *, level: int = 0, checksum: bool = False) -> None:
# numcodecs 0.13.0 introduces the checksum attribute for the zstd codec
_numcodecs_version = tuple(map(int, version("numcodecs").split(".")))
if _numcodecs_version < (0, 13, 0): # pragma: no cover
raise RuntimeError(
"numcodecs version >= 0.13.0 is required to use the zstd codec. "
f"Version {_numcodecs_version} is currently installed."
)

level_parsed = parse_zstd_level(level)
checksum_parsed = parse_checksum(checksum)

Expand All @@ -52,21 +61,18 @@ def from_dict(cls, data: dict[str, JSON]) -> Self:
def to_dict(self) -> dict[str, JSON]:
return {"name": "zstd", "configuration": {"level": self.level, "checksum": self.checksum}}

def _compress(self, data: npt.NDArray[Any]) -> bytes:
ctx = ZstdCompressor(level=self.level, write_checksum=self.checksum)
return ctx.compress(data.tobytes())

def _decompress(self, data: npt.NDArray[Any]) -> bytes:
ctx = ZstdDecompressor()
return ctx.decompress(data.tobytes())
@cached_property
def _zstd_codec(self) -> Zstd:
config_dict = {"level": self.level, "checksum": self.checksum}
return Zstd.from_config(config_dict)

async def _decode_single(
self,
chunk_bytes: Buffer,
chunk_spec: ArraySpec,
) -> Buffer:
return await to_thread(
as_numpy_array_wrapper, self._decompress, chunk_bytes, chunk_spec.prototype
as_numpy_array_wrapper, self._zstd_codec.decode, chunk_bytes, chunk_spec.prototype
)

async def _encode_single(
Expand All @@ -75,7 +81,7 @@ async def _encode_single(
chunk_spec: ArraySpec,
) -> Buffer | None:
return await to_thread(
as_numpy_array_wrapper, self._compress, chunk_bytes, chunk_spec.prototype
as_numpy_array_wrapper, self._zstd_codec.encode, chunk_bytes, chunk_spec.prototype
)

def compute_encoded_size(self, _input_byte_length: int, _chunk_spec: ArraySpec) -> int:
Expand Down