Remove Zarr chunk manifest writing functionality (#426)

* pr to remove to_zarr chunk manifest method

* missed one in test_backend

* Update docs/releases.rst

Co-authored-by: Tom Nicholas <tom@cworthy.org>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* nits to docs/releases.rst

* lint

* release notes only in breaking changes section

---------

Co-authored-by: Tom Nicholas <tom@cworthy.org>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

docs/api.rst

@@ -29,7 +29,6 @@ Serialization
     :toctree: generated/
 
     VirtualiZarrDatasetAccessor.to_kerchunk
-    VirtualiZarrDatasetAccessor.to_zarr
     VirtualiZarrDatasetAccessor.to_icechunk
 
 Information

docs/releases.rst

@@ -12,6 +12,9 @@ New Features
 Breaking changes
 ~~~~~~~~~~~~~~~~
 
+- Reading and writing Zarr chunk manifest formats are no longer supported.
+  (:issue:`359`), (:pull:`426`). By `Raphael Hagen <https://github.com/norlandrhagen>`_.
+
 Deprecations
 ~~~~~~~~~~~~
 

docs/usage.md

@@ -456,30 +456,7 @@ session.commit("Appended second dataset")
 
 See the [Icechunk documentation](https://icechunk.io/icechunk-python/virtual/#creating-a-virtual-dataset-with-virtualizarr) for more details.
 
-### Writing as Zarr
 
-Alternatively, we can write these references out as an actual Zarr store, at least one that is compliant with the [proposed "Chunk Manifest" ZEP](https://github.com/zarr-developers/zarr-specs/issues/287). To do this we simply use the {py:meth}`vds.virtualize.to_zarr <virtualizarr.VirtualiZarrDatasetAccessor.to_zarr>` accessor method.
-
-```python
-combined_vds.virtualize.to_zarr('combined.zarr')
-```
-
-The result is a zarr v3 store on disk which contains the chunk manifest information written out as `manifest.json` files, so the store looks like this:
-
-```
-combined/zarr.json  <- group metadata
-combined/air/zarr.json  <- array metadata
-combined/air/manifest.json <- array manifest
-...
-```
-
-The advantage of this format is that any zarr v3 reader that understands the chunk manifest ZEP could read from this store, no matter what language it is written in (e.g. via `zarr-python`, `zarr-js`, or rust). This reading would also not require `fsspec`.
-
-```{note}
-Currently there are not yet any zarr v3 readers which understand the chunk manifest ZEP, so until then this feature cannot be used for data processing.
-
-This store can however be read by {py:func}`~virtualizarr.open_virtual_dataset`, by passing `filetype="zarr_v3"`.
-```
 
 ## Opening Kerchunk references as virtual datasets
 

virtualizarr/accessor.py

@@ -7,7 +7,6 @@
 from virtualizarr.manifests import ManifestArray
 from virtualizarr.types.kerchunk import KerchunkStoreRefs
 from virtualizarr.writers.kerchunk import dataset_to_kerchunk_refs
-from virtualizarr.writers.zarr import dataset_to_zarr
 
 if TYPE_CHECKING:
     from icechunk import IcechunkStore  # type: ignore[import-not-found]
@@ -24,21 +23,6 @@ class VirtualiZarrDatasetAccessor:
     def __init__(self, ds: Dataset):
         self.ds: Dataset = ds
 
-    def to_zarr(self, storepath: str) -> None:
-        """
-        Serialize all virtualized arrays in this xarray dataset as a Zarr store.
-
-        Currently requires all variables to be backed by ManifestArray objects.
-
-        Not very useful until some implementation of a Zarr reader can actually read these manifest.json files.
-        See https://github.com/zarr-developers/zarr-specs/issues/287
-
-        Parameters
-        ----------
-        storepath : str
-        """
-        dataset_to_zarr(self.ds, storepath)
-
     def to_icechunk(
         self,
         store: "IcechunkStore",

virtualizarr/backend.py

@@ -17,15 +17,13 @@
     KerchunkVirtualBackend,
     NetCDF3VirtualBackend,
     TIFFVirtualBackend,
-    ZarrV3VirtualBackend,
 )
 from virtualizarr.readers.common import VirtualBackend
 from virtualizarr.utils import _FsspecFSFromFilepath, check_for_collisions
 
 # TODO add entrypoint to allow external libraries to add to this mapping
 VIRTUAL_BACKENDS = {
     "kerchunk": KerchunkVirtualBackend,
-    "zarr_v3": ZarrV3VirtualBackend,
     "dmrpp": DMRPPVirtualBackend,
     "hdf5": HDFVirtualBackend,
     "netcdf4": HDFVirtualBackend,  # note this is the same as for hdf5
@@ -51,9 +49,7 @@ class FileType(AutoName):
     grib = auto()
     tiff = auto()
     fits = auto()
-    zarr = auto()
     dmrpp = auto()
-    zarr_v3 = auto()
     kerchunk = auto()
 
 
@@ -130,7 +126,7 @@ def open_virtual_dataset(
         File path to open as a set of virtualized zarr arrays.
     filetype : FileType or str, default None
         Type of file to be opened. Used to determine which kerchunk file format backend to use.
-        Can be one of {'netCDF3', 'netCDF4', 'HDF', 'TIFF', 'GRIB', 'FITS', 'dmrpp', 'zarr_v3', 'kerchunk'}.
+        Can be one of {'netCDF3', 'netCDF4', 'HDF', 'TIFF', 'GRIB', 'FITS', 'dmrpp', 'kerchunk'}.
         If not provided will attempt to automatically infer the correct filetype from header bytes.
     group : str, default is None
         Path to the HDF5/netCDF4 group in the given file to open. Given as a str, supported by filetypes “netcdf4”, “hdf5”, and "dmrpp".

virtualizarr/readers/__init__.py

@@ -5,7 +5,6 @@
 from virtualizarr.readers.kerchunk import KerchunkVirtualBackend
 from virtualizarr.readers.netcdf3 import NetCDF3VirtualBackend
 from virtualizarr.readers.tiff import TIFFVirtualBackend
-from virtualizarr.readers.zarr_v3 import ZarrV3VirtualBackend
 
 __all__ = [
     "DMRPPVirtualBackend",
@@ -15,5 +14,4 @@
     "KerchunkVirtualBackend",
     "NetCDF3VirtualBackend",
     "TIFFVirtualBackend",
-    "ZarrV3VirtualBackend",
 ]

virtualizarr/tests/test_backend.py

@@ -79,7 +79,6 @@ def test_FileType():
     assert "grib" == FileType("grib").name
     assert "tiff" == FileType("tiff").name
     assert "fits" == FileType("fits").name
-    assert "zarr" == FileType("zarr").name
     with pytest.raises(ValueError):
         FileType(None)