[WIP] Arrow string array: Common base class

pandas/core/arrays/_mixins.py

@@ -8,6 +8,7 @@
 from pandas.util._decorators import cache_readonly, doc
 from pandas.util._validators import validate_fillna_kwargs
 
+from pandas.core.dtypes.base import ExtensionDtype
 from pandas.core.dtypes.common import is_dtype_equal
 from pandas.core.dtypes.inference import is_array_like
 from pandas.core.dtypes.missing import array_equivalent
@@ -240,3 +241,11 @@ def _reduce(self, name: str, skipna: bool = True, **kwargs):
         else:
             msg = f"'{type(self).__name__}' does not implement reduction '{name}'"
             raise TypeError(msg)
+
+
+class StringArrayBase(ExtensionArray):
+    pass
+
+
+class StringDtypeBase(ExtensionDtype):
+    pass

pandas/core/arrays/base.py

@@ -454,15 +454,17 @@ def astype(self, dtype, copy=True):
         array : ndarray
             NumPy ndarray with 'dtype' for its dtype.
         """
-        from pandas.core.arrays.string_ import StringDtype
+        from pandas.core.arrays._mixins import StringDtypeBase
 
         dtype = pandas_dtype(dtype)
         if is_dtype_equal(dtype, self.dtype):
             if not copy:
                 return self
             elif copy:
                 return self.copy()
-        if isinstance(dtype, StringDtype):  # allow conversion to StringArrays
+
+        # FIXME: Really hard-code here?
+        if isinstance(dtype, StringDtypeBase):  # allow conversion to StringArrays
             return dtype.construct_array_type()._from_sequence(self, copy=False)
 
         return np.array(self, dtype=dtype, copy=copy)

pandas/core/arrays/string_.py

@@ -4,7 +4,7 @@
 
 from pandas._libs import lib, missing as libmissing
 
-from pandas.core.dtypes.base import ExtensionDtype, register_extension_dtype
+from pandas.core.dtypes.base import register_extension_dtype
 from pandas.core.dtypes.common import (
     is_array_like,
     is_bool_dtype,
@@ -21,12 +21,14 @@
 from pandas.core.indexers import check_array_indexer
 from pandas.core.missing import isna
 
+from pandas.core.arrays._mixins import StringArrayBase, StringDtypeBase
+
 if TYPE_CHECKING:
     import pyarrow
 
 
 @register_extension_dtype
-class StringDtype(ExtensionDtype):
+class StringDtype(StringDtypeBase):
     """
     Extension dtype for string data.
 
@@ -100,7 +102,7 @@ def __from_arrow__(
         return StringArray._concat_same_type(results)
 
 
-class StringArray(PandasArray):
+class StringArray(StringArrayBase, PandasArray):
     """
     Extension array for string data.