REF: Create StorageExtensionDtype (#46537)

Author: mroeschke

pandas/core/arrays/string_.py

@@ -1,9 +1,6 @@
 from __future__ import annotations
 
-from typing import (
-    TYPE_CHECKING,
-    Any,
-)
+from typing import TYPE_CHECKING
 
 import numpy as np
 
@@ -24,6 +21,7 @@
 
 from pandas.core.dtypes.base import (
     ExtensionDtype,
+    StorageExtensionDtype,
     register_extension_dtype,
 )
 from pandas.core.dtypes.common import (
@@ -55,7 +53,7 @@
 
 
 @register_extension_dtype
-class StringDtype(ExtensionDtype):
+class StringDtype(StorageExtensionDtype):
     """
     Extension dtype for string data.
 
@@ -67,7 +65,7 @@ class StringDtype(ExtensionDtype):
        parts of the API may change without warning.
 
        In particular, StringDtype.na_value may change to no longer be
-       ``numpy.nan``.
+       ``pd.NA``.
 
     Parameters
     ----------
@@ -141,7 +139,6 @@ def construct_from_string(cls, string):
         -----
         TypeError
             If the string is not a valid option.
-
         """
         if not isinstance(string, str):
             raise TypeError(
@@ -156,15 +153,6 @@ def construct_from_string(cls, string):
         else:
             raise TypeError(f"Cannot construct a '{cls.__name__}' from '{string}'")
 
-    def __eq__(self, other: Any) -> bool:
-        if isinstance(other, str) and other == "string":
-            return True
-        return super().__eq__(other)
-
-    def __hash__(self) -> int:
-        # custom __eq__ so have to override __hash__
-        return super().__hash__()
-
     # https://github.com/pandas-dev/pandas/issues/36126
     # error: Signature of "construct_array_type" incompatible with supertype
     # "ExtensionDtype"
@@ -185,12 +173,6 @@ def construct_array_type(  # type: ignore[override]
         else:
             return ArrowStringArray
 
-    def __repr__(self):
-        return f"string[{self.storage}]"
-
-    def __str__(self):
-        return self.name
-
     def __from_arrow__(
         self, array: pyarrow.Array | pyarrow.ChunkedArray
     ) -> BaseStringArray:

pandas/core/dtypes/base.py

@@ -1,7 +1,6 @@
 """
 Extend pandas with custom array types.
 """
-
 from __future__ import annotations
 
 from typing import (
@@ -14,6 +13,7 @@
 
 import numpy as np
 
+from pandas._libs import missing as libmissing
 from pandas._libs.hashtable import object_hash
 from pandas._typing import (
     DtypeObj,
@@ -391,6 +391,32 @@ def _can_hold_na(self) -> bool:
         return True
 
 
+class StorageExtensionDtype(ExtensionDtype):
+    """ExtensionDtype that may be backed by more than one implementation."""
+
+    name: str
+    na_value = libmissing.NA
+    _metadata = ("storage",)
+
+    def __init__(self, storage=None) -> None:
+        self.storage = storage
+
+    def __repr__(self):
+        return f"{self.name}[{self.storage}]"
+
+    def __str__(self):
+        return self.name
+
+    def __eq__(self, other: Any) -> bool:
+        if isinstance(other, self.type) and other == self.name:
+            return True
+        return super().__eq__(other)
+
+    def __hash__(self) -> int:
+        # custom __eq__ so have to override __hash__
+        return super().__hash__()
+
+
 def register_extension_dtype(cls: type_t[ExtensionDtypeT]) -> type_t[ExtensionDtypeT]:
     """
     Register an ExtensionType with pandas as class decorator.