ENH: Basis for a StringDtype using Arrow (#35259)

Co-authored-by: Simon Hawkins <simonjayhawkins@gmail.com> Co-authored-by: Joris Van den Bossche <jorisvandenbossche@gmail.com>

Author: 3 people

pandas/_libs/lib.pyx

@@ -636,7 +636,7 @@ cpdef ndarray[object] ensure_string_array(
  ----------
  arr : array-like
  The values to be converted to str, if needed.
- na_value : Any
+ na_value : Any, default np.nan
  The value to use for na. For example, np.nan or pd.NA.
  convert_na_value : bool, default True
  If False, existing na values will be used unchanged in the new array.

pandas/core/arrays/base.py

@@ -471,14 +471,19 @@ def astype(self, dtype, copy=True):
  NumPy ndarray with 'dtype' for its dtype.
  """
  from pandas.core.arrays.string_ import StringDtype
+ from pandas.core.arrays.string_arrow import ArrowStringDtype
 
  dtype = pandas_dtype(dtype)
  if is_dtype_equal(dtype, self.dtype):
  if not copy:
  return self
  else:
  return self.copy()
- if isinstance(dtype, StringDtype): # allow conversion to StringArrays
+
+ # FIXME: Really hard-code here?
+ if isinstance(
+ dtype, (ArrowStringDtype, StringDtype)
+ ): # allow conversion to StringArrays
  return dtype.construct_array_type()._from_sequence(self, copy=False)
 
  return np.array(self, dtype=dtype, copy=copy)