REF (string): de-duplicate str_isfoo methods (pandas-dev#59705)

Author: jbrockmendel

pandas/core/arrays/_arrow_string_mixins.py

@@ -52,10 +52,10 @@ def _str_pad(
         elif side == "both":
             if pa_version_under17p0:
                 # GH#59624 fall back to object dtype
-                from pandas import array
+                from pandas import array as pd_array
 
                 obj_arr = self.astype(object, copy=False)  # type: ignore[attr-defined]
-                obj = array(obj_arr, dtype=object)
+                obj = pd_array(obj_arr, dtype=object)
                 result = obj._str_pad(width, side, fillchar)  # type: ignore[attr-defined]
                 return type(self)._from_sequence(result, dtype=self.dtype)  # type: ignore[attr-defined]
             else:
@@ -150,3 +150,39 @@ def _str_endswith(self, pat: str | tuple[str, ...], na: Scalar | None = None):
         if not isna(na):  # pyright: ignore [reportGeneralTypeIssues]
             result = result.fill_null(na)
         return self._convert_bool_result(result)
+
+    def _str_isalnum(self):
+        result = pc.utf8_is_alnum(self._pa_array)
+        return self._convert_bool_result(result)
+
+    def _str_isalpha(self):
+        result = pc.utf8_is_alpha(self._pa_array)
+        return self._convert_bool_result(result)
+
+    def _str_isdecimal(self):
+        result = pc.utf8_is_decimal(self._pa_array)
+        return self._convert_bool_result(result)
+
+    def _str_isdigit(self):
+        result = pc.utf8_is_digit(self._pa_array)
+        return self._convert_bool_result(result)
+
+    def _str_islower(self):
+        result = pc.utf8_is_lower(self._pa_array)
+        return self._convert_bool_result(result)
+
+    def _str_isnumeric(self):
+        result = pc.utf8_is_numeric(self._pa_array)
+        return self._convert_bool_result(result)
+
+    def _str_isspace(self):
+        result = pc.utf8_is_space(self._pa_array)
+        return self._convert_bool_result(result)
+
+    def _str_istitle(self):
+        result = pc.utf8_is_title(self._pa_array)
+        return self._convert_bool_result(result)
+
+    def _str_isupper(self):
+        result = pc.utf8_is_upper(self._pa_array)
+        return self._convert_bool_result(result)

pandas/core/arrays/arrow/array.py

@@ -2411,33 +2411,6 @@ def _str_slice(
             pc.utf8_slice_codeunits(self._pa_array, start=start, stop=stop, step=step)
         )
 
-    def _str_isalnum(self):
-        return type(self)(pc.utf8_is_alnum(self._pa_array))
-
-    def _str_isalpha(self):
-        return type(self)(pc.utf8_is_alpha(self._pa_array))
-
-    def _str_isdecimal(self):
-        return type(self)(pc.utf8_is_decimal(self._pa_array))
-
-    def _str_isdigit(self):
-        return type(self)(pc.utf8_is_digit(self._pa_array))
-
-    def _str_islower(self):
-        return type(self)(pc.utf8_is_lower(self._pa_array))
-
-    def _str_isnumeric(self):
-        return type(self)(pc.utf8_is_numeric(self._pa_array))
-
-    def _str_isspace(self):
-        return type(self)(pc.utf8_is_space(self._pa_array))
-
-    def _str_istitle(self):
-        return type(self)(pc.utf8_is_title(self._pa_array))
-
-    def _str_isupper(self):
-        return type(self)(pc.utf8_is_upper(self._pa_array))
-
     def _str_len(self):
         return type(self)(pc.utf8_length(self._pa_array))
 

pandas/core/arrays/string_arrow.py

@@ -283,6 +283,16 @@ def _data(self):
     # ------------------------------------------------------------------------
     # String methods interface
 
+    _str_isalnum = ArrowStringArrayMixin._str_isalnum
+    _str_isalpha = ArrowStringArrayMixin._str_isalpha
+    _str_isdecimal = ArrowStringArrayMixin._str_isdecimal
+    _str_isdigit = ArrowStringArrayMixin._str_isdigit
+    _str_islower = ArrowStringArrayMixin._str_islower
+    _str_isnumeric = ArrowStringArrayMixin._str_isnumeric
+    _str_isspace = ArrowStringArrayMixin._str_isspace
+    _str_istitle = ArrowStringArrayMixin._str_istitle
+    _str_isupper = ArrowStringArrayMixin._str_isupper
+
     _str_map = BaseStringArray._str_map
     _str_startswith = ArrowStringArrayMixin._str_startswith
     _str_endswith = ArrowStringArrayMixin._str_endswith
@@ -360,42 +370,6 @@ def _str_slice(
             pc.utf8_slice_codeunits(self._pa_array, start=start, stop=stop, step=step)
         )
 
-    def _str_isalnum(self):
-        result = pc.utf8_is_alnum(self._pa_array)
-        return self._convert_bool_result(result)
-
-    def _str_isalpha(self):
-        result = pc.utf8_is_alpha(self._pa_array)
-        return self._convert_bool_result(result)
-
-    def _str_isdecimal(self):
-        result = pc.utf8_is_decimal(self._pa_array)
-        return self._convert_bool_result(result)
-
-    def _str_isdigit(self):
-        result = pc.utf8_is_digit(self._pa_array)
-        return self._convert_bool_result(result)
-
-    def _str_islower(self):
-        result = pc.utf8_is_lower(self._pa_array)
-        return self._convert_bool_result(result)
-
-    def _str_isnumeric(self):
-        result = pc.utf8_is_numeric(self._pa_array)
-        return self._convert_bool_result(result)
-
-    def _str_isspace(self):
-        result = pc.utf8_is_space(self._pa_array)
-        return self._convert_bool_result(result)
-
-    def _str_istitle(self):
-        result = pc.utf8_is_title(self._pa_array)
-        return self._convert_bool_result(result)
-
-    def _str_isupper(self):
-        result = pc.utf8_is_upper(self._pa_array)
-        return self._convert_bool_result(result)
-
     def _str_len(self):
         result = pc.utf8_length(self._pa_array)
         return self._convert_int_result(result)