Merge branch 'main' into flox-quantile

doc/whats-new.rst

@@ -59,6 +59,16 @@ Bug fixes
   `CFMaskCoder`/`CFScaleOffsetCoder` (:issue:`2304`, :issue:`5597`,
   :issue:`7691`, :pull:`8713`, see also discussion in :pull:`7654`).
   By `Kai Mühlbauer <https://github.com/kmuehlbauer>`_.
+- do not cast `_FillValue`/`missing_value` in `CFMaskCoder` if `_Unsigned` is provided
+  (:issue:`8844`, :pull:`8852`).
+- Adapt handling of copy keyword argument for numpy >= 2.0dev
+  (:issue:`8844`, :pull:`8851`, :pull:`8865``).
+  By `Kai Mühlbauer <https://github.com/kmuehlbauer>`_.
+- import trapz/trapezoid depending on numpy version.
+  (:issue:`8844`, :pull:`8865`).
+  By `Kai Mühlbauer <https://github.com/kmuehlbauer>`_.
+
+
 
 Documentation
 ~~~~~~~~~~~~~

xarray/backends/scipy_.py

@@ -28,6 +28,7 @@
     Frozen,
     FrozenDict,
     close_on_error,
+    module_available,
     try_read_magic_number_from_file_or_path,
 )
 from xarray.core.variable import Variable
@@ -39,6 +40,9 @@
     from xarray.core.dataset import Dataset
 
 
+HAS_NUMPY_2_0 = module_available("numpy", minversion="2.0.0.dev0")
+
+
 def _decode_string(s):
     if isinstance(s, bytes):
         return s.decode("utf-8", "replace")
@@ -76,6 +80,12 @@ def __getitem__(self, key):
         # with the netCDF4 library by ensuring we can safely read arrays even
         # after closing associated files.
         copy = self.datastore.ds.use_mmap
+
+        # adapt handling of copy-kwarg to numpy 2.0
+        # see https://github.com/numpy/numpy/issues/25916
+        # and https://github.com/numpy/numpy/pull/25922
+        copy = None if HAS_NUMPY_2_0 and copy is False else copy
+
         return np.array(data, dtype=self.dtype, copy=copy)
 
     def __setitem__(self, key, value):

xarray/coding/strings.py

@@ -15,10 +15,13 @@
     unpack_for_encoding,
 )
 from xarray.core import indexing
+from xarray.core.utils import module_available
 from xarray.core.variable import Variable
 from xarray.namedarray.parallelcompat import get_chunked_array_type
 from xarray.namedarray.pycompat import is_chunked_array
 
+HAS_NUMPY_2_0 = module_available("numpy", minversion="2.0.0.dev0")
+
 
 def create_vlen_dtype(element_type):
     if element_type not in (str, bytes):
@@ -156,8 +159,12 @@ def bytes_to_char(arr):
 
 def _numpy_bytes_to_char(arr):
     """Like netCDF4.stringtochar, but faster and more flexible."""
+    # adapt handling of copy-kwarg to numpy 2.0
+    # see https://github.com/numpy/numpy/issues/25916
+    # and https://github.com/numpy/numpy/pull/25922
+    copy = None if HAS_NUMPY_2_0 else False
     # ensure the array is contiguous
-    arr = np.array(arr, copy=False, order="C", dtype=np.bytes_)
+    arr = np.array(arr, copy=copy, order="C", dtype=np.bytes_)
     return arr.reshape(arr.shape + (1,)).view("S1")
 
 
@@ -199,8 +206,12 @@ def char_to_bytes(arr):
 
 def _numpy_char_to_bytes(arr):
     """Like netCDF4.chartostring, but faster and more flexible."""
+    # adapt handling of copy-kwarg to numpy 2.0
+    # see https://github.com/numpy/numpy/issues/25916
+    # and https://github.com/numpy/numpy/pull/25922
+    copy = None if HAS_NUMPY_2_0 else False
     # based on: http://stackoverflow.com/a/10984878/809705
-    arr = np.array(arr, copy=False, order="C")
+    arr = np.array(arr, copy=copy, order="C")
     dtype = "S" + str(arr.shape[-1])
     return arr.view(dtype).reshape(arr.shape[:-1])
 

xarray/coding/variables.py

@@ -309,6 +309,9 @@ def encode(self, variable: Variable, name: T_Name = None):
         dtype = np.dtype(encoding.get("dtype", data.dtype))
         fv = encoding.get("_FillValue")
         mv = encoding.get("missing_value")
+        # to properly handle _FillValue/missing_value below [a], [b]
+        # we need to check if unsigned data is written as signed data
+        unsigned = encoding.get("_Unsigned") is not None
 
         fv_exists = fv is not None
         mv_exists = mv is not None
@@ -323,13 +326,19 @@ def encode(self, variable: Variable, name: T_Name = None):
 
         if fv_exists:
             # Ensure _FillValue is cast to same dtype as data's
-            encoding["_FillValue"] = dtype.type(fv)
+            # [a] need to skip this if _Unsigned is available
+            if not unsigned:
+                encoding["_FillValue"] = dtype.type(fv)
             fill_value = pop_to(encoding, attrs, "_FillValue", name=name)
 
         if mv_exists:
             # try to use _FillValue, if it exists to align both values
             # or use missing_value and ensure it's cast to same dtype as data's
-            encoding["missing_value"] = attrs.get("_FillValue", dtype.type(mv))
+            # [b] need to provide mv verbatim if _Unsigned is available
+            encoding["missing_value"] = attrs.get(
+                "_FillValue",
+                (dtype.type(mv) if not unsigned else mv),
+            )
             fill_value = pop_to(encoding, attrs, "missing_value", name=name)
 
         # apply fillna
@@ -522,7 +531,6 @@ def encode(self, variable: Variable, name: T_Name = None) -> Variable:
     def decode(self, variable: Variable, name: T_Name = None) -> Variable:
         if "_Unsigned" in variable.attrs:
             dims, data, attrs, encoding = unpack_for_decoding(variable)
-
             unsigned = pop_to(attrs, encoding, "_Unsigned")
 
             if data.dtype.kind == "i":

xarray/core/dataset.py

@@ -5867,7 +5867,7 @@ def drop_vars(
         for var in names_set:
             maybe_midx = self._indexes.get(var, None)
             if isinstance(maybe_midx, PandasMultiIndex):
-                idx_coord_names = set(maybe_midx.index.names + [maybe_midx.dim])
+                idx_coord_names = set(list(maybe_midx.index.names) + [maybe_midx.dim])
                 idx_other_names = idx_coord_names - set(names_set)
                 other_names.update(idx_other_names)
         if other_names: