[cherry] Making decoding arrays lazy too

Author: dcherian

xarray/coding/strings.py

@@ -250,14 +250,17 @@ def __repr__(self):
         return f"{type(self).__name__}({self.array!r})"
 
     def _vindex_get(self, key):
-        return _numpy_char_to_bytes(self.array.vindex[key])
+        return type(self)(self.array.vindex[key])
 
     def _oindex_get(self, key):
-        return _numpy_char_to_bytes(self.array.oindex[key])
+        return type(self)(self.array.oindex[key])
 
     def __getitem__(self, key):
         # require slicing the last dimension completely
         key = type(key)(indexing.expanded_indexer(key.tuple, self.array.ndim))
         if key.tuple[-1] != slice(None):
             raise IndexError("too many indices")
-        return _numpy_char_to_bytes(self.array[key])
+        return type(self)(self.array[key])
+
+    def get_duck_array(self):
+        return _numpy_char_to_bytes(self.array.get_duck_array())

xarray/coding/variables.py

@@ -58,13 +58,16 @@ def dtype(self) -> np.dtype:
         return np.dtype(self.array.dtype.kind + str(self.array.dtype.itemsize))
 
     def _oindex_get(self, key):
-        return np.asarray(self.array.oindex[key], dtype=self.dtype)
+        return type(self)(self.array.oindex[key])
 
     def _vindex_get(self, key):
-        return np.asarray(self.array.vindex[key], dtype=self.dtype)
+        return type(self)(self.array.vindex[key])
 
     def __getitem__(self, key) -> np.ndarray:
-        return np.asarray(self.array[key], dtype=self.dtype)
+        return type(self)(self.array[key], dtype=self.dtype)
+
+    def get_duck_array(self):
+        return duck_array_ops.astype(self.array.get_duck_array(), dtype=self.dtype)
 
 
 class BoolTypeArray(indexing.ExplicitlyIndexedNDArrayMixin):
@@ -96,14 +99,16 @@ def dtype(self) -> np.dtype:
         return np.dtype("bool")
 
     def _oindex_get(self, key):
-        return np.asarray(self.array.oindex[key], dtype=self.dtype)
+        return type(self)(self.array.oindex[key])
 
     def _vindex_get(self, key):
-        return np.asarray(self.array.vindex[key], dtype=self.dtype)
+        return type(self)(self.array.vindex[key])
 
     def __getitem__(self, key) -> np.ndarray:
-        return np.asarray(self.array[key], dtype=self.dtype)
+        return type(self)(self.array[key])
 
+    def get_duck_array(self):
+        return duck_array_ops.astype(self.array.get_duck_array(), dtype=self.dtype)
 
 
 def _apply_mask(