split out CFDatetimeCoder into coders, deprecate use_cftime as keywor…

…d argument
pydata · Dec 17, 2024 · a2d8e69 · a2d8e69
1 parent 86a408d
commit a2d8e69
Show file tree

Hide file tree

Showing 12 changed files with 176 additions and 52 deletions.
diff --git a/doc/api.rst b/doc/api.rst
@@ -1096,6 +1096,17 @@ DataTree methods
 ..    Missing:
 ..    ``open_mfdatatree``
 
+Encoding/Decoding
+=================
+
+Coder objects
+-------------
+
+.. autosummary::
+   :toctree: generated/
+
+   coders.CFDatetimeCoder
+
 Coordinates objects
 ===================
 

diff --git a/doc/whats-new.rst b/doc/whats-new.rst
@@ -42,6 +42,9 @@ Deprecations
 - Finalize deprecation of ``closed`` parameters of :py:func:`cftime_range` and
   :py:func:`date_range` (:pull:`9882`).
   By `Kai Mühlbauer <https://github.com/kmuehlbauer>`_.
+- Time decoding related kwarg ``use_cftime`` is deprecated. Use keyword argument
+  ``decode_times=CFDatetimeCoder(use_cftime=True)`` in the respective functions
+  instead.
 
 Bug fixes
 ~~~~~~~~~

diff --git a/xarray/__init__.py b/xarray/__init__.py
@@ -1,6 +1,6 @@
 from importlib.metadata import version as _version
 
-from xarray import groupers, testing, tutorial, ufuncs
+from xarray import coders, groupers, testing, tutorial, ufuncs
 from xarray.backends.api import (
     load_dataarray,
     load_dataset,
@@ -66,6 +66,7 @@
 # `mypy --strict` running in projects that import xarray.
 __all__ = (  # noqa: RUF022
     # Sub-packages
+    "coders",
     "groupers",
     "testing",
     "tutorial",

diff --git a/xarray/backends/api.py b/xarray/backends/api.py
@@ -33,6 +33,7 @@
     _normalize_path,
 )
 from xarray.backends.locks import _get_scheduler
+from xarray.coders import CFDatetimeCoder
 from xarray.core import indexing
 from xarray.core.combine import (
     _infer_concat_order_from_positions,
@@ -481,7 +482,10 @@ def open_dataset(
     cache: bool | None = None,
     decode_cf: bool | None = None,
     mask_and_scale: bool | Mapping[str, bool] | None = None,
-    decode_times: bool | Mapping[str, bool] | None = None,
+    decode_times: bool
+    | CFDatetimeCoder
+    | Mapping[str, bool | CFDatetimeCoder]
+    | None = None,
     decode_timedelta: bool | Mapping[str, bool] | None = None,
     use_cftime: bool | Mapping[str, bool] | None = None,
     concat_characters: bool | Mapping[str, bool] | None = None,
@@ -543,9 +547,9 @@ def open_dataset(
         be replaced by NA. Pass a mapping, e.g. ``{"my_variable": False}``,
         to toggle this feature per-variable individually.
         This keyword may not be supported by all the backends.
-    decode_times : bool or dict-like, optional
+    decode_times : bool, CFDatetimeCoder or dict-like, optional
         If True, decode times encoded in the standard NetCDF datetime format
-        into datetime objects. Otherwise, leave them encoded as numbers.
+        into datetime objects. Otherwise, use CFDatetimeCoder or leave them encoded as numbers.
         Pass a mapping, e.g. ``{"my_variable": False}``,
         to toggle this feature per-variable individually.
         This keyword may not be supported by all the backends.
@@ -569,6 +573,8 @@ def open_dataset(
         raise an error. Pass a mapping, e.g. ``{"my_variable": False}``,
         to toggle this feature per-variable individually.
         This keyword may not be supported by all the backends.
+        Usage of 'use_cftime' as kwarg is deprecated. Please initialize it
+        with CFDatetimeCoder and 'decode_times' kwarg.
     concat_characters : bool or dict-like, optional
         If True, concatenate along the last dimension of character arrays to
         form string arrays. Dimensions will only be concatenated over (and
@@ -698,7 +704,10 @@ def open_dataarray(
     cache: bool | None = None,
     decode_cf: bool | None = None,
     mask_and_scale: bool | None = None,
-    decode_times: bool | None = None,
+    decode_times: bool
+    | CFDatetimeCoder
+    | Mapping[str, bool | CFDatetimeCoder]
+    | None = None,
     decode_timedelta: bool | None = None,
     use_cftime: bool | None = None,
     concat_characters: bool | None = None,
@@ -761,9 +770,11 @@ def open_dataarray(
         `missing_value` attribute contains multiple values a warning will be
         issued and all array values matching one of the multiple values will
         be replaced by NA. This keyword may not be supported by all the backends.
-    decode_times : bool, optional
+    decode_times : bool, CFDatetimeCoder or dict-like, optional
         If True, decode times encoded in the standard NetCDF datetime format
-        into datetime objects. Otherwise, leave them encoded as numbers.
+        into datetime objects. Otherwise, use CFDatetimeCoder or leave them encoded as numbers.
+        Pass a mapping, e.g. ``{"my_variable": False}``,
+        to toggle this feature per-variable individually.
         This keyword may not be supported by all the backends.
     decode_timedelta : bool, optional
         If True, decode variables and coordinates with time units in
@@ -781,6 +792,8 @@ def open_dataarray(
         represented using ``np.datetime64[ns]`` objects.  If False, always
         decode times to ``np.datetime64[ns]`` objects; if this is not possible
         raise an error. This keyword may not be supported by all the backends.
+        Usage of 'use_cftime' as kwarg is deprecated. Please initialize it
+        with CFDatetimeCoder and 'decode_times' kwarg.
     concat_characters : bool, optional
         If True, concatenate along the last dimension of character arrays to
         form string arrays. Dimensions will only be concatenated over (and
@@ -903,7 +916,10 @@ def open_datatree(
     cache: bool | None = None,
     decode_cf: bool | None = None,
     mask_and_scale: bool | Mapping[str, bool] | None = None,
-    decode_times: bool | Mapping[str, bool] | None = None,
+    decode_times: bool
+    | CFDatetimeCoder
+    | Mapping[str, bool | CFDatetimeCoder]
+    | None = None,
     decode_timedelta: bool | Mapping[str, bool] | None = None,
     use_cftime: bool | Mapping[str, bool] | None = None,
     concat_characters: bool | Mapping[str, bool] | None = None,
@@ -961,9 +977,9 @@ def open_datatree(
         be replaced by NA. Pass a mapping, e.g. ``{"my_variable": False}``,
         to toggle this feature per-variable individually.
         This keyword may not be supported by all the backends.
-    decode_times : bool or dict-like, optional
+    decode_times : bool, CFDatetimeCoder or dict-like, optional
         If True, decode times encoded in the standard NetCDF datetime format
-        into datetime objects. Otherwise, leave them encoded as numbers.
+        into datetime objects. Otherwise, use CFDatetimeCoder or leave them encoded as numbers.
         Pass a mapping, e.g. ``{"my_variable": False}``,
         to toggle this feature per-variable individually.
         This keyword may not be supported by all the backends.
@@ -987,6 +1003,8 @@ def open_datatree(
         raise an error. Pass a mapping, e.g. ``{"my_variable": False}``,
         to toggle this feature per-variable individually.
         This keyword may not be supported by all the backends.
+        Usage of 'use_cftime' as kwarg is deprecated. Please initialize it
+        with CFDatetimeCoder and 'decode_times' kwarg.
     concat_characters : bool or dict-like, optional
         If True, concatenate along the last dimension of character arrays to
         form string arrays. Dimensions will only be concatenated over (and
@@ -1118,7 +1136,10 @@ def open_groups(
     cache: bool | None = None,
     decode_cf: bool | None = None,
     mask_and_scale: bool | Mapping[str, bool] | None = None,
-    decode_times: bool | Mapping[str, bool] | None = None,
+    decode_times: bool
+    | CFDatetimeCoder
+    | Mapping[str, bool | CFDatetimeCoder]
+    | None = None,
     decode_timedelta: bool | Mapping[str, bool] | None = None,
     use_cftime: bool | Mapping[str, bool] | None = None,
     concat_characters: bool | Mapping[str, bool] | None = None,
@@ -1180,9 +1201,9 @@ def open_groups(
         be replaced by NA. Pass a mapping, e.g. ``{"my_variable": False}``,
         to toggle this feature per-variable individually.
         This keyword may not be supported by all the backends.
-    decode_times : bool or dict-like, optional
+    decode_times : bool, CFDatetimeCoder or dict-like, optional
         If True, decode times encoded in the standard NetCDF datetime format
-        into datetime objects. Otherwise, leave them encoded as numbers.
+        into datetime objects. Otherwise, use CFDatetimeCoder or leave them encoded as numbers.
         Pass a mapping, e.g. ``{"my_variable": False}``,
         to toggle this feature per-variable individually.
         This keyword may not be supported by all the backends.
@@ -1206,6 +1227,8 @@ def open_groups(
         raise an error. Pass a mapping, e.g. ``{"my_variable": False}``,
         to toggle this feature per-variable individually.
         This keyword may not be supported by all the backends.
+        Usage of 'use_cftime' as kwarg is deprecated. Please initialize it
+        with CFDatetimeCoder and 'decode_times' kwarg.
     concat_characters : bool or dict-like, optional
         If True, concatenate along the last dimension of character arrays to
         form string arrays. Dimensions will only be concatenated over (and

diff --git a/xarray/coders.py b/xarray/coders.py
@@ -0,0 +1,10 @@
+"""
+This module provides coder objects that encapsulate the
+"encoding/decoding" process.
+"""
+
+from xarray.coding.times import CFDatetimeCoder
+
+__all__ = [
+    "CFDatetimeCoder",
+]
diff --git a/xarray/coding/times.py b/xarray/coding/times.py
@@ -36,7 +36,11 @@
 except ImportError:
     cftime = None
 
-from xarray.core.types import CFCalendar, NPDatetimeUnitOptions, T_DuckArray
+from xarray.core.types import (
+    CFCalendar,
+    NPDatetimeUnitOptions,
+    T_DuckArray,
+)
 
 T_Name = Union[Hashable, None]
 
@@ -204,7 +208,10 @@ def _unpack_time_units_and_ref_date(units: str) -> tuple[str, pd.Timestamp]:
 
 
 def _decode_cf_datetime_dtype(
-    data, units: str, calendar: str | None, use_cftime: bool | None
+    data,
+    units: str,
+    calendar: str | None,
+    use_cftime: bool | None,
 ) -> np.dtype:
     # Verify that at least the first and last date can be decoded
     # successfully. Otherwise, tracebacks end up swallowed by
@@ -311,7 +318,10 @@ def _decode_datetime_with_pandas(
 
 
 def decode_cf_datetime(
-    num_dates, units: str, calendar: str | None = None, use_cftime: bool | None = None
+    num_dates,
+    units: str,
+    calendar: str | None = None,
+    use_cftime: bool | None = None,
 ) -> np.ndarray:
     """Given an array of numeric dates in netCDF format, convert it into a
     numpy array of date time objects.
@@ -974,7 +984,10 @@ def _lazily_encode_cf_timedelta(
 
 
 class CFDatetimeCoder(VariableCoder):
-    def __init__(self, use_cftime: bool | None = None) -> None:
+    def __init__(
+        self,
+        use_cftime: bool | None = None,
+    ) -> None:
         self.use_cftime = use_cftime
 
     def encode(self, variable: Variable, name: T_Name = None) -> Variable:

diff --git a/xarray/conventions.py b/xarray/conventions.py
@@ -7,6 +7,7 @@
 
 import numpy as np
 
+from xarray.coders import CFDatetimeCoder
 from xarray.coding import strings, times, variables
 from xarray.coding.variables import SerializationWarning, pop_to
 from xarray.core import indexing
@@ -88,7 +89,7 @@ def encode_cf_variable(
     ensure_not_multiindex(var, name=name)
 
     for coder in [
-        times.CFDatetimeCoder(),
+        CFDatetimeCoder(),
         times.CFTimedeltaCoder(),
         variables.CFScaleOffsetCoder(),
         variables.CFMaskCoder(),
@@ -109,7 +110,7 @@ def decode_cf_variable(
     var: Variable,
     concat_characters: bool = True,
     mask_and_scale: bool = True,
-    decode_times: bool = True,
+    decode_times: bool | CFDatetimeCoder = True,
     decode_endianness: bool = True,
     stack_char_dim: bool = True,
     use_cftime: bool | None = None,
@@ -136,7 +137,7 @@ def decode_cf_variable(
         Lazily scale (using scale_factor and add_offset) and mask
         (using _FillValue). If the _Unsigned attribute is present
         treat integer arrays as unsigned.
-    decode_times : bool
+    decode_times : bool or CFDatetimeCoder
         Decode cf times ("hours since 2000-01-01") to np.datetime64.
     decode_endianness : bool
         Decode arrays from non-native to native endianness.
@@ -154,6 +155,8 @@ def decode_cf_variable(
         represented using ``np.datetime64[ns]`` objects.  If False, always
         decode times to ``np.datetime64[ns]`` objects; if this is not possible
         raise an error.
+        Usage of use_cftime as kwarg is deprecated, please initialize it with
+        CFDatetimeCoder and ``decode_times``.
 
     Returns
     -------
@@ -167,7 +170,7 @@ def decode_cf_variable(
     original_dtype = var.dtype
 
     if decode_timedelta is None:
-        decode_timedelta = decode_times
+        decode_timedelta = True if decode_times else False
 
     if concat_characters:
         if stack_char_dim:
@@ -191,7 +194,28 @@ def decode_cf_variable(
     if decode_timedelta:
         var = times.CFTimedeltaCoder().decode(var, name=name)
     if decode_times:
-        var = times.CFDatetimeCoder(use_cftime=use_cftime).decode(var, name=name)
+        # remove checks after end of deprecation cycle
+        if not isinstance(decode_times, CFDatetimeCoder):
+            if use_cftime is not None:
+                from warnings import warn
+
+                warn(
+                    "Usage of 'use_cftime' as kwarg is deprecated. "
+                    "Please initialize it with CFDatetimeCoder and "
+                    "'decode_times' kwarg.",
+                    DeprecationWarning,
+                    stacklevel=2,
+                )
+            decode_times = CFDatetimeCoder(use_cftime=use_cftime)
+        else:
+            if use_cftime is not None:
+                raise TypeError(
+                    "Usage of 'use_cftime' as kwarg is not allowed, "
+                    "if 'decode_times' is initialized with "
+                    "CFDatetimeCoder. Please add 'use_cftime' "
+                    "when initializing CFDatetimeCoder."
+                )
+        var = decode_times.decode(var, name=name)
 
     if decode_endianness and not var.dtype.isnative:
         var = variables.EndianCoder().decode(var)
@@ -302,7 +326,7 @@ def decode_cf_variables(
     attributes: T_Attrs,
     concat_characters: bool | Mapping[str, bool] = True,
     mask_and_scale: bool | Mapping[str, bool] = True,
-    decode_times: bool | Mapping[str, bool] = True,
+    decode_times: bool | CFDatetimeCoder | Mapping[str, bool | CFDatetimeCoder] = True,
     decode_coords: bool | Literal["coordinates", "all"] = True,
     drop_variables: T_DropVariables = None,
     use_cftime: bool | Mapping[str, bool] | None = None,
@@ -439,7 +463,7 @@ def decode_cf(
     obj: T_DatasetOrAbstractstore,
     concat_characters: bool = True,
     mask_and_scale: bool = True,
-    decode_times: bool = True,
+    decode_times: bool | CFDatetimeCoder = True,
     decode_coords: bool | Literal["coordinates", "all"] = True,
     drop_variables: T_DropVariables = None,
     use_cftime: bool | None = None,
@@ -458,7 +482,7 @@ def decode_cf(
     mask_and_scale : bool, optional
         Lazily scale (using scale_factor and add_offset) and mask
         (using _FillValue).
-    decode_times : bool, optional
+    decode_times : bool or CFDatetimeCoder, optional
         Decode cf times (e.g., integers since "hours since 2000-01-01") to
         np.datetime64.
     decode_coords : bool or {"coordinates", "all"}, optional
@@ -483,6 +507,8 @@ def decode_cf(
         represented using ``np.datetime64[ns]`` objects.  If False, always
         decode times to ``np.datetime64[ns]`` objects; if this is not possible
         raise an error.
+        Usage of use_cftime as kwarg is deprecated, please initialize it with
+        CFDatetimeCoder and ``decode_times``.
     decode_timedelta : bool, optional
         If True, decode variables and coordinates with time units in
         {"days", "hours", "minutes", "seconds", "milliseconds", "microseconds"}
@@ -536,7 +562,7 @@ def cf_decoder(
     attributes: T_Attrs,
     concat_characters: bool = True,
     mask_and_scale: bool = True,
-    decode_times: bool = True,
+    decode_times: bool | CFDatetimeCoder = True,
 ) -> tuple[T_Variables, T_Attrs]:
     """
     Decode a set of CF encoded variables and attributes.
@@ -553,7 +579,7 @@ def cf_decoder(
     mask_and_scale : bool
         Lazily scale (using scale_factor and add_offset) and mask
         (using _FillValue).
-    decode_times : bool
+    decode_times : bool | CFDatetimeCoder
         Decode cf times ("hours since 2000-01-01") to np.datetime64.
 
     Returns

diff --git a/xarray/convert.py b/xarray/convert.py
@@ -4,7 +4,8 @@
 
 import numpy as np
 
-from xarray.coding.times import CFDatetimeCoder, CFTimedeltaCoder
+from xarray.coders import CFDatetimeCoder
+from xarray.coding.times import CFTimedeltaCoder
 from xarray.conventions import decode_cf
 from xarray.core import duck_array_ops
 from xarray.core.dataarray import DataArray