BUG (string): ArrowStringArray.find corner cases

Author: jbrockmendel

pandas/core/arrays/arrow/array.py

@@ -2395,7 +2395,7 @@ def _str_find(self, sub: str, start: int = 0, end: int | None = None) -> Self:
             if sub == "":
                 # GH 56792
                 result = self._apply_elementwise(lambda val: val.find(sub, start, end))
-                return type(self)(pa.chunked_array(result))
+                return self._convert_int_result(pa.chunked_array(result))
             if start is None:
                 start_offset = 0
                 start = 0
@@ -2409,7 +2409,7 @@ def _str_find(self, sub: str, start: int = 0, end: int | None = None) -> Self:
             found = pc.not_equal(result, pa.scalar(-1, type=result.type))
             offset_result = pc.add(result, start_offset)
             result = pc.if_else(found, offset_result, -1)
-        return type(self)(result)
+        return self._convert_int_result(result)
 
     def _str_join(self, sep: str) -> Self:
         if pa.types.is_string(self._pa_array.type) or pa.types.is_large_string(

pandas/core/arrays/string_arrow.py

@@ -285,6 +285,7 @@ def astype(self, dtype, copy: bool = True):
     _str_startswith = ArrowStringArrayMixin._str_startswith
     _str_endswith = ArrowStringArrayMixin._str_endswith
     _str_pad = ArrowStringArrayMixin._str_pad
+    _str_find = ArrowExtensionArray._str_find
 
     def _str_contains(
         self, pat, case: bool = True, flags: int = 0, na=np.nan, regex: bool = True
@@ -447,20 +448,6 @@ def _str_count(self, pat: str, flags: int = 0):
         result = pc.count_substring_regex(self._pa_array, pat)
         return self._convert_int_result(result)
 
-    def _str_find(self, sub: str, start: int = 0, end: int | None = None):
-        if start != 0 and end is not None:
-            slices = pc.utf8_slice_codeunits(self._pa_array, start, stop=end)
-            result = pc.find_substring(slices, sub)
-            not_found = pc.equal(result, -1)
-            offset_result = pc.add(result, end - start)
-            result = pc.if_else(not_found, result, offset_result)
-        elif start == 0 and end is None:
-            slices = self._pa_array
-            result = pc.find_substring(slices, sub)
-        else:
-            return super()._str_find(sub, start, end)
-        return self._convert_int_result(result)
-
     def _str_get_dummies(self, sep: str = "|"):
         dummies_pa, labels = ArrowExtensionArray(self._pa_array)._str_get_dummies(sep)
         if len(labels) == 0:

pandas/tests/extension/test_arrow.py

@@ -32,8 +32,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas._libs import lib
 from pandas._libs.tslibs import timezones
 from pandas.compat import (
@@ -1978,7 +1976,6 @@ def test_str_find_large_start():
         tm.assert_series_equal(result, expected)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.skipif(
     pa_version_under13p0, reason="https://github.com/apache/arrow/issues/36311"
 )
@@ -1990,11 +1987,15 @@ def test_str_find_e2e(start, end, sub):
         ["abcaadef", "abc", "abcdeddefgj8292", "ab", "a", ""],
         dtype=ArrowDtype(pa.string()),
     )
-    object_series = s.astype(pd.StringDtype())
+    object_series = s.astype(pd.StringDtype(storage="python"))
     result = s.str.find(sub, start, end)
     expected = object_series.str.find(sub, start, end).astype(result.dtype)
     tm.assert_series_equal(result, expected)
 
+    arrow_str_series = s.astype(pd.StringDtype(storage="pyarrow"))
+    result2 = arrow_str_series.str.find(sub, start, end).astype(result.dtype)
+    tm.assert_series_equal(result2, expected)
+
 
 def test_str_find_negative_start_negative_end_no_match():
     # GH 56791