zarr.codecs#

Submodules#

Classes#

`BloscCname`	Enum for compression library used by blosc.
`BloscCodec`	Base class for bytes-to-bytes codecs.
`BloscShuffle`	Enum for shuffle filter used by blosc.
`BytesCodec`	Base class for array-to-bytes codecs.
`Crc32cCodec`	Base class for bytes-to-bytes codecs.
`Endian`	Enum for endian type used by bytes codec.
`GzipCodec`	Base class for bytes-to-bytes codecs.
`ShardingCodec`	Base class for array-to-bytes codecs.
`ShardingCodecIndexLocation`	Enum for index location used by the sharding codec.
`TransposeCodec`	Base class for array-to-array codecs.
`VLenBytesCodec`	Base class for array-to-bytes codecs.
`VLenUTF8Codec`	Base class for array-to-bytes codecs.
`ZstdCodec`	Base class for bytes-to-bytes codecs.

Package Contents#

class zarr.codecs.BloscCname(*args, **kwds)[source]#

Bases: enum.Enum

Enum for compression library used by blosc.

blosclz = 'blosclz'#

lz4 = 'lz4'#

lz4hc = 'lz4hc'#

snappy = 'snappy'#

zlib = 'zlib'#

zstd = 'zstd'#

class zarr.codecs.BloscCodec( *, typesize: int | None = None, cname: BloscCname | str = BloscCname.zstd, clevel: int = 5, shuffle: BloscShuffle | str | None = None, blocksize: int = 0, )[source]#

Bases: zarr.abc.codec.BytesBytesCodec

Base class for bytes-to-bytes codecs.

abstract compute_encoded_size( _input_byte_length: int, _chunk_spec: zarr.core.array_spec.ArraySpec, ) → int[source]#

Given an input byte length, this method returns the output byte length. Raises a NotImplementedError for codecs with variable-sized outputs (e.g. compressors).

Parameters:

input_byte_lengthint
chunk_specArraySpec

Returns:

int

evolve_from_array_spec(array_spec: zarr.core.array_spec.ArraySpec) → Self[source]#

Fills in codec configuration parameters that can be automatically inferred from the array metadata.

Parameters:

array_specArraySpec

Returns:

Self

classmethod from_dict(data: dict[str, zarr.core.common.JSON]) → Self[source]#: Create an instance of the model from a dictionary

to_dict() → dict[str, zarr.core.common.JSON][source]#: Recursively serialize this model to a dictionary. This method inspects the fields of self and calls x.to_dict() for any fields that are instances of Metadata. Sequences of Metadata are similarly recursed into, and the output of that recursion is collected in a list.

blocksize: int = 0#

clevel: int = 5#

cname: BloscCname#

is_fixed_size = False#

shuffle: BloscShuffle | None#

typesize: int | None#

class zarr.codecs.BloscShuffle(*args, **kwds)[source]#

Bases: enum.Enum

Enum for shuffle filter used by blosc.

classmethod from_int(num: int) → BloscShuffle[source]#

bitshuffle = 'bitshuffle'#

noshuffle = 'noshuffle'#

shuffle = 'shuffle'#

class zarr.codecs.BytesCodec(*, endian: Endian | str | None = default_system_endian)[source]#

Bases: zarr.abc.codec.ArrayBytesCodec

Base class for array-to-bytes codecs.

compute_encoded_size( input_byte_length: int, _chunk_spec: zarr.core.array_spec.ArraySpec, ) → int[source]#

Given an input byte length, this method returns the output byte length. Raises a NotImplementedError for codecs with variable-sized outputs (e.g. compressors).

Parameters:

input_byte_lengthint
chunk_specArraySpec

Returns:

int

evolve_from_array_spec(array_spec: zarr.core.array_spec.ArraySpec) → Self[source]#

Fills in codec configuration parameters that can be automatically inferred from the array metadata.

Parameters:

array_specArraySpec

Returns:

Self

classmethod from_dict(data: dict[str, zarr.core.common.JSON]) → Self[source]#: Create an instance of the model from a dictionary

to_dict() → dict[str, zarr.core.common.JSON][source]#: Recursively serialize this model to a dictionary. This method inspects the fields of self and calls x.to_dict() for any fields that are instances of Metadata. Sequences of Metadata are similarly recursed into, and the output of that recursion is collected in a list.

endian: Endian | None#

is_fixed_size = True#

class zarr.codecs.Crc32cCodec[source]#

Bases: zarr.abc.codec.BytesBytesCodec

Base class for bytes-to-bytes codecs.

compute_encoded_size( input_byte_length: int, _chunk_spec: zarr.core.array_spec.ArraySpec, ) → int[source]#

Given an input byte length, this method returns the output byte length. Raises a NotImplementedError for codecs with variable-sized outputs (e.g. compressors).

Parameters:

input_byte_lengthint
chunk_specArraySpec

Returns:

int

classmethod from_dict(data: dict[str, zarr.core.common.JSON]) → Self[source]#: Create an instance of the model from a dictionary

to_dict() → dict[str, zarr.core.common.JSON][source]#: Recursively serialize this model to a dictionary. This method inspects the fields of self and calls x.to_dict() for any fields that are instances of Metadata. Sequences of Metadata are similarly recursed into, and the output of that recursion is collected in a list.

is_fixed_size = True#

class zarr.codecs.Endian(*args, **kwds)[source]#

Bases: enum.Enum

Enum for endian type used by bytes codec.

big = 'big'#

little = 'little'#

class zarr.codecs.GzipCodec(*, level: int = 5)[source]#

Bases: zarr.abc.codec.BytesBytesCodec

Base class for bytes-to-bytes codecs.

abstract compute_encoded_size( _input_byte_length: int, _chunk_spec: zarr.core.array_spec.ArraySpec, ) → int[source]#

Given an input byte length, this method returns the output byte length. Raises a NotImplementedError for codecs with variable-sized outputs (e.g. compressors).

Parameters:

input_byte_lengthint
chunk_specArraySpec

Returns:

int

classmethod from_dict(data: dict[str, zarr.core.common.JSON]) → Self[source]#: Create an instance of the model from a dictionary

to_dict() → dict[str, zarr.core.common.JSON][source]#: Recursively serialize this model to a dictionary. This method inspects the fields of self and calls x.to_dict() for any fields that are instances of Metadata. Sequences of Metadata are similarly recursed into, and the output of that recursion is collected in a list.

is_fixed_size = False#

level: int = 5#

class zarr.codecs.ShardingCodec( *, chunk_shape: zarr.core.common.ChunkCoordsLike, codecs: collections.abc.Iterable[zarr.abc.codec.Codec | dict[str, zarr.core.common.JSON]] = (BytesCodec(),), index_codecs: collections.abc.Iterable[zarr.abc.codec.Codec | dict[str, zarr.core.common.JSON]] = (BytesCodec(), Crc32cCodec()), index_location: ShardingCodecIndexLocation | str = ShardingCodecIndexLocation.end, )[source]#

Bases: zarr.abc.codec.ArrayBytesCodec, zarr.abc.codec.ArrayBytesCodecPartialDecodeMixin, zarr.abc.codec.ArrayBytesCodecPartialEncodeMixin

Base class for array-to-bytes codecs.

compute_encoded_size( input_byte_length: int, shard_spec: zarr.core.array_spec.ArraySpec, ) → int[source]#

Given an input byte length, this method returns the output byte length. Raises a NotImplementedError for codecs with variable-sized outputs (e.g. compressors).

Parameters:

input_byte_lengthint
chunk_specArraySpec

Returns:

int

evolve_from_array_spec(array_spec: zarr.core.array_spec.ArraySpec) → Self[source]#

Fills in codec configuration parameters that can be automatically inferred from the array metadata.

Parameters:

array_specArraySpec

Returns:

Self

classmethod from_dict(data: dict[str, zarr.core.common.JSON]) → Self[source]#: Create an instance of the model from a dictionary

to_dict() → dict[str, zarr.core.common.JSON][source]#: Recursively serialize this model to a dictionary. This method inspects the fields of self and calls x.to_dict() for any fields that are instances of Metadata. Sequences of Metadata are similarly recursed into, and the output of that recursion is collected in a list.

validate( *, shape: zarr.core.common.ChunkCoords, dtype: numpy.dtype[Any], chunk_grid: zarr.core.chunk_grids.ChunkGrid, ) → None[source]#

Validates that the codec configuration is compatible with the array metadata. Raises errors when the codec configuration is not compatible.

Parameters:

shapeChunkCoords: The array shape
dtypenp.dtype[Any]: The array data type
chunk_gridChunkGrid: The array chunk grid

chunk_shape: zarr.core.common.ChunkCoords#

property codec_pipeline: zarr.abc.codec.CodecPipeline#

codecs: tuple[zarr.abc.codec.Codec, Ellipsis]#

index_codecs: tuple[zarr.abc.codec.Codec, Ellipsis]#

index_location: ShardingCodecIndexLocation#

class zarr.codecs.ShardingCodecIndexLocation(*args, **kwds)[source]#

Bases: enum.Enum

Enum for index location used by the sharding codec.

end = 'end'#

start = 'start'#

class zarr.codecs.TransposeCodec(*, order: zarr.core.common.ChunkCoordsLike)[source]#

Bases: zarr.abc.codec.ArrayArrayCodec

Base class for array-to-array codecs.

compute_encoded_size( input_byte_length: int, _chunk_spec: zarr.core.array_spec.ArraySpec, ) → int[source]#

Given an input byte length, this method returns the output byte length. Raises a NotImplementedError for codecs with variable-sized outputs (e.g. compressors).

Parameters:

input_byte_lengthint
chunk_specArraySpec

Returns:

int

evolve_from_array_spec(array_spec: zarr.core.array_spec.ArraySpec) → Self[source]#

Fills in codec configuration parameters that can be automatically inferred from the array metadata.

Parameters:

array_specArraySpec

Returns:

Self

classmethod from_dict(data: dict[str, zarr.core.common.JSON]) → Self[source]#: Create an instance of the model from a dictionary

resolve_metadata( chunk_spec: zarr.core.array_spec.ArraySpec, ) → zarr.core.array_spec.ArraySpec[source]#

Computed the spec of the chunk after it has been encoded by the codec. This is important for codecs that change the shape, data type or fill value of a chunk. The spec will then be used for subsequent codecs in the pipeline.

Parameters:

chunk_specArraySpec

Returns:

ArraySpec

to_dict() → dict[str, zarr.core.common.JSON][source]#: Recursively serialize this model to a dictionary. This method inspects the fields of self and calls x.to_dict() for any fields that are instances of Metadata. Sequences of Metadata are similarly recursed into, and the output of that recursion is collected in a list.

validate( shape: tuple[int, Ellipsis], dtype: numpy.dtype[Any], chunk_grid: zarr.core.chunk_grids.ChunkGrid, ) → None[source]#

Validates that the codec configuration is compatible with the array metadata. Raises errors when the codec configuration is not compatible.

Parameters:

shapeChunkCoords: The array shape
dtypenp.dtype[Any]: The array data type
chunk_gridChunkGrid: The array chunk grid

is_fixed_size = True#

order: tuple[int, Ellipsis]#

class zarr.codecs.VLenBytesCodec[source]#

Bases: zarr.abc.codec.ArrayBytesCodec

Base class for array-to-bytes codecs.

abstract compute_encoded_size( input_byte_length: int, _chunk_spec: zarr.core.array_spec.ArraySpec, ) → int[source]#

Given an input byte length, this method returns the output byte length. Raises a NotImplementedError for codecs with variable-sized outputs (e.g. compressors).

Parameters:

input_byte_lengthint
chunk_specArraySpec

Returns:

int

evolve_from_array_spec(array_spec: zarr.core.array_spec.ArraySpec) → Self[source]#

Fills in codec configuration parameters that can be automatically inferred from the array metadata.

Parameters:

array_specArraySpec

Returns:

Self

classmethod from_dict(data: dict[str, zarr.core.common.JSON]) → Self[source]#: Create an instance of the model from a dictionary

to_dict() → dict[str, zarr.core.common.JSON][source]#: Recursively serialize this model to a dictionary. This method inspects the fields of self and calls x.to_dict() for any fields that are instances of Metadata. Sequences of Metadata are similarly recursed into, and the output of that recursion is collected in a list.

class zarr.codecs.VLenUTF8Codec[source]#

Bases: zarr.abc.codec.ArrayBytesCodec

Base class for array-to-bytes codecs.

abstract compute_encoded_size( input_byte_length: int, _chunk_spec: zarr.core.array_spec.ArraySpec, ) → int[source]#

Given an input byte length, this method returns the output byte length. Raises a NotImplementedError for codecs with variable-sized outputs (e.g. compressors).

Parameters:

input_byte_lengthint
chunk_specArraySpec

Returns:

int

evolve_from_array_spec(array_spec: zarr.core.array_spec.ArraySpec) → Self[source]#

Fills in codec configuration parameters that can be automatically inferred from the array metadata.

Parameters:

array_specArraySpec

Returns:

Self

classmethod from_dict(data: dict[str, zarr.core.common.JSON]) → Self[source]#: Create an instance of the model from a dictionary

to_dict() → dict[str, zarr.core.common.JSON][source]#: Recursively serialize this model to a dictionary. This method inspects the fields of self and calls x.to_dict() for any fields that are instances of Metadata. Sequences of Metadata are similarly recursed into, and the output of that recursion is collected in a list.

class zarr.codecs.ZstdCodec(*, level: int = 0, checksum: bool = False)[source]#

Bases: zarr.abc.codec.BytesBytesCodec

Base class for bytes-to-bytes codecs.

abstract compute_encoded_size( _input_byte_length: int, _chunk_spec: zarr.core.array_spec.ArraySpec, ) → int[source]#

Given an input byte length, this method returns the output byte length. Raises a NotImplementedError for codecs with variable-sized outputs (e.g. compressors).

Parameters:

input_byte_lengthint
chunk_specArraySpec

Returns:

int

classmethod from_dict(data: dict[str, zarr.core.common.JSON]) → Self[source]#: Create an instance of the model from a dictionary

to_dict() → dict[str, zarr.core.common.JSON][source]#: Recursively serialize this model to a dictionary. This method inspects the fields of self and calls x.to_dict() for any fields that are instances of Metadata. Sequences of Metadata are similarly recursed into, and the output of that recursion is collected in a list.

checksum: bool = False#

is_fixed_size = True#

level: int = 0#