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: 1 addition & 0 deletions docs/about/releases.md
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@
## v2.7.1 (unreleased)

### New Features
- Added [VirtualiZarrDatasetAccessor.nrefs][virtualizarr.accessor.VirtualiZarrDatasetAccessor.nrefs] — a method that returns the total number of virtual chunk references in the dataset, ignoring non-virtual variables. Closes #573.

### Breaking changes

Expand Down
2 changes: 2 additions & 0 deletions docs/api/virtualizarr.md
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,8 @@ Users can use xarray for every step apart from reading and serializing virtual r

::: virtualizarr.accessor.VirtualiZarrDatasetAccessor.nbytes

::: virtualizarr.accessor.VirtualiZarrDatasetAccessor.nrefs

## Renaming paths

::: virtualizarr.accessor.VirtualiZarrDatasetAccessor.rename_paths
21 changes: 21 additions & 0 deletions virtualizarr/accessor.py
Original file line number Diff line number Diff line change
Expand Up @@ -285,6 +285,27 @@ def nbytes(self) -> int:
for var in self.ds.variables.values()
)

def nrefs(self) -> int:
"""Count the total number of virtual chunk references in the dataset.

Ignores non-virtual variables (i.e. those not backed by a ManifestArray).

Returns
-------
int
Total number of virtual references across all virtual variables.

Examples
--------
>>> vds.vz.nrefs() # doctest: +SKIP
42
"""
return sum(
len(var.data.manifest)
for var in self.ds.variables.values()
if isinstance(var.data, ManifestArray)
)


@xr.register_dataset_accessor("vz")
class VirtualiZarrDatasetAccessor(_VirtualiZarrDatasetAccessor):
Expand Down
22 changes: 22 additions & 0 deletions virtualizarr/tests/test_xarray.py
Original file line number Diff line number Diff line change
Expand Up @@ -1163,3 +1163,25 @@ def test_isel_iterative_append_simulation(self, array_v3_metadata):

# every original chunk should have been visited exactly once
assert sorted(seen_refs) == [0, 100, 200, 300]


@requires_hdf5plugin
@requires_imagecodecs
def test_nrefs(simple_netcdf4, local_registry):
parser = HDFParser()
with open_virtual_dataset(
url=simple_netcdf4,
registry=local_registry,
parser=parser,
) as vds:
# simple_netcdf4 has one virtual variable 'foo' with a single chunk
assert vds.vz.nrefs() == 1

with open_virtual_dataset(
url=simple_netcdf4,
registry=local_registry,
parser=parser,
loadable_variables=["foo"],
) as vds:
# when the only variable is loadable (non-virtual), nrefs should be 0
assert vds.vz.nrefs() == 0
Loading