String dtype: use 'str' string alias and representation for NaN-variant of the dtype (#59388)

Author: jorisvandenbossche

pandas/_testing/__init__.py

@@ -14,6 +14,7 @@
 
 import numpy as np
 
+from pandas._config import using_string_dtype
 from pandas._config.localization import (
     can_set_locale,
     get_locales,
@@ -110,7 +111,10 @@
 ALL_FLOAT_DTYPES: list[Dtype] = [*FLOAT_NUMPY_DTYPES, *FLOAT_EA_DTYPES]
 
 COMPLEX_DTYPES: list[Dtype] = [complex, "complex64", "complex128"]
-STRING_DTYPES: list[Dtype] = [str, "str", "U"]
+if using_string_dtype():
+    STRING_DTYPES: list[Dtype] = [str, "U"]
+else:
+    STRING_DTYPES: list[Dtype] = [str, "str", "U"]  # type: ignore[no-redef]
 
 DATETIME64_DTYPES: list[Dtype] = ["datetime64[ns]", "M8[ns]"]
 TIMEDELTA64_DTYPES: list[Dtype] = ["timedelta64[ns]", "m8[ns]"]

pandas/core/arrays/arrow/array.py

@@ -570,7 +570,10 @@ def __getitem__(self, item: PositionalIndexer):
         if isinstance(item, np.ndarray):
             if not len(item):
                 # Removable once we migrate StringDtype[pyarrow] to ArrowDtype[string]
-                if self._dtype.name == "string" and self._dtype.storage == "pyarrow":
+                if (
+                    isinstance(self._dtype, StringDtype)
+                    and self._dtype.storage == "pyarrow"
+                ):
                     # TODO(infer_string) should this be large_string?
                     pa_dtype = pa.string()
                 else: