Skip to content

Check and fix chararray string dimension names #10395

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 13 commits into from
Jun 20, 2025
Merged
Show file tree
Hide file tree
Changes from 1 commit
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
Next Next commit
MIN: forward variable name down to coders for CharacterArrayCoder
  • Loading branch information
kmuehlbauer committed Jun 4, 2025
commit e01580aefa89abe9dcb26d4e03fd58a7fba9e7f7
6 changes: 3 additions & 3 deletions xarray/backends/common.py
Original file line number Diff line number Diff line change
Expand Up @@ -389,11 +389,11 @@ def encode(self, variables, attributes):
attributes : dict-like

"""
variables = {k: self.encode_variable(v) for k, v in variables.items()}
variables = {k: self.encode_variable(v, name=k) for k, v in variables.items()}
attributes = {k: self.encode_attribute(v) for k, v in attributes.items()}
return variables, attributes

def encode_variable(self, v):
def encode_variable(self, v, name=None):
"""encode one variable"""
return v

Expand Down Expand Up @@ -641,7 +641,7 @@ def encode(self, variables, attributes):
variables = {
k: ensure_dtype_not_object(v, name=k) for k, v in variables.items()
}
variables = {k: self.encode_variable(v) for k, v in variables.items()}
variables = {k: self.encode_variable(v, name=k) for k, v in variables.items()}
attributes = {k: self.encode_attribute(v) for k, v in attributes.items()}
return variables, attributes

Expand Down
4 changes: 2 additions & 2 deletions xarray/backends/h5netcdf_.py
Original file line number Diff line number Diff line change
Expand Up @@ -286,8 +286,8 @@ def set_dimension(self, name, length, is_unlimited=False):
def set_attribute(self, key, value):
self.ds.attrs[key] = value

def encode_variable(self, variable):
return _encode_nc4_variable(variable)
def encode_variable(self, variable, name=None):
return _encode_nc4_variable(variable, name=name)

def prepare_variable(
self, name, variable, check_encoding=False, unlimited_dims=None
Expand Down
25 changes: 15 additions & 10 deletions xarray/backends/netCDF4_.py
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,6 @@

import numpy as np

from xarray import coding
from xarray.backends.common import (
BACKEND_ENTRYPOINTS,
BackendArray,
Expand All @@ -30,6 +29,12 @@
)
from xarray.backends.netcdf3 import encode_nc3_attr_value, encode_nc3_variable
from xarray.backends.store import StoreBackendEntrypoint
from xarray.coding.strings import (
CharacterArrayCoder,
EncodedStringCoder,
create_vlen_dtype,
is_unicode_dtype,
)
from xarray.coding.variables import pop_to
from xarray.core import indexing
from xarray.core.utils import (
Expand Down Expand Up @@ -73,7 +78,7 @@ def __init__(self, variable_name, datastore):
# check vlen string dtype in further steps
# it also prevents automatic string concatenation via
# conventions.decode_cf_variable
dtype = coding.strings.create_vlen_dtype(str)
dtype = create_vlen_dtype(str)
self.dtype = dtype

def __setitem__(self, key, value):
Expand Down Expand Up @@ -127,12 +132,12 @@ def _getitem(self, key):
return array


def _encode_nc4_variable(var):
def _encode_nc4_variable(var, name=None):
for coder in [
coding.strings.EncodedStringCoder(allows_unicode=True),
coding.strings.CharacterArrayCoder(),
EncodedStringCoder(allows_unicode=True),
CharacterArrayCoder(),
]:
var = coder.encode(var)
var = coder.encode(var, name=name)
return var


Expand Down Expand Up @@ -164,7 +169,7 @@ def _nc4_dtype(var):
if "dtype" in var.encoding:
dtype = var.encoding.pop("dtype")
_check_encoding_dtype_is_vlen_string(dtype)
elif coding.strings.is_unicode_dtype(var.dtype):
elif is_unicode_dtype(var.dtype):
dtype = str
elif var.dtype.kind in ["i", "u", "f", "c", "S"]:
dtype = var.dtype
Expand Down Expand Up @@ -535,12 +540,12 @@ def set_attribute(self, key, value):
else:
self.ds.setncattr(key, value)

def encode_variable(self, variable):
def encode_variable(self, variable, name=None):
variable = _force_native_endianness(variable)
if self.format == "NETCDF4":
variable = _encode_nc4_variable(variable)
variable = _encode_nc4_variable(variable, name=name)
else:
variable = encode_nc3_variable(variable)
variable = encode_nc3_variable(variable, name=name)
return variable

def prepare_variable(
Expand Down
4 changes: 2 additions & 2 deletions xarray/backends/netcdf3.py
Original file line number Diff line number Diff line change
Expand Up @@ -118,12 +118,12 @@ def _maybe_prepare_times(var):
return data


def encode_nc3_variable(var):
def encode_nc3_variable(var, name=None):
for coder in [
coding.strings.EncodedStringCoder(allows_unicode=False),
coding.strings.CharacterArrayCoder(),
]:
var = coder.encode(var)
var = coder.encode(var, name=name)
data = _maybe_prepare_times(var)
data = coerce_nc3_dtype(data)
attrs = encode_nc3_attrs(var.attrs)
Expand Down
4 changes: 2 additions & 2 deletions xarray/backends/scipy_.py
Original file line number Diff line number Diff line change
Expand Up @@ -227,8 +227,8 @@ def set_attribute(self, key, value):
value = encode_nc3_attr_value(value)
setattr(self.ds, key, value)

def encode_variable(self, variable):
variable = encode_nc3_variable(variable)
def encode_variable(self, variable, name=None):
variable = encode_nc3_variable(variable, name=name)
return variable

def prepare_variable(
Expand Down
4 changes: 2 additions & 2 deletions xarray/backends/zarr.py
Original file line number Diff line number Diff line change
Expand Up @@ -916,8 +916,8 @@ def set_dimensions(self, variables, unlimited_dims=None):
def set_attributes(self, attributes):
_put_attrs(self.zarr_group, attributes)

def encode_variable(self, variable):
variable = encode_zarr_variable(variable)
def encode_variable(self, variable, name=None):
variable = encode_zarr_variable(variable, name=name)
return variable

def encode_attribute(self, a):
Expand Down
pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy