Enable Arrow implementation for removeprefix (#54972)

Author: phofl

pandas/core/arrays/arrow/array.py

@@ -2192,11 +2192,11 @@ def _str_rstrip(self, to_strip=None):
         return type(self)(result)
 
     def _str_removeprefix(self, prefix: str):
-        # TODO: Should work once https://github.com/apache/arrow/issues/14991 is fixed
-        # starts_with = pc.starts_with(self._pa_array, pattern=prefix)
-        # removed = pc.utf8_slice_codeunits(self._pa_array, len(prefix))
-        # result = pc.if_else(starts_with, removed, self._pa_array)
-        # return type(self)(result)
+        if not pa_version_under13p0:
+            starts_with = pc.starts_with(self._pa_array, pattern=prefix)
+            removed = pc.utf8_slice_codeunits(self._pa_array, len(prefix))
+            result = pc.if_else(starts_with, removed, self._pa_array)
+            return type(self)(result)
         predicate = lambda val: val.removeprefix(prefix)
         result = self._apply_elementwise(predicate)
         return type(self)(pa.chunked_array(result))

pandas/core/arrays/string_arrow.py

@@ -15,7 +15,10 @@
     lib,
     missing as libmissing,
 )
-from pandas.compat import pa_version_under7p0
+from pandas.compat import (
+    pa_version_under7p0,
+    pa_version_under13p0,
+)
 from pandas.util._exceptions import find_stack_level
 
 from pandas.core.dtypes.common import (
@@ -446,6 +449,20 @@ def _str_rstrip(self, to_strip=None):
             result = pc.utf8_rtrim(self._pa_array, characters=to_strip)
         return type(self)(result)
 
+    def _str_removeprefix(self, prefix: str):
+        if not pa_version_under13p0:
+            starts_with = pc.starts_with(self._pa_array, pattern=prefix)
+            removed = pc.utf8_slice_codeunits(self._pa_array, len(prefix))
+            result = pc.if_else(starts_with, removed, self._pa_array)
+            return type(self)(result)
+        return super()._str_removeprefix(prefix)
+
+    def _str_removesuffix(self, suffix: str):
+        ends_with = pc.ends_with(self._pa_array, pattern=suffix)
+        removed = pc.utf8_slice_codeunits(self._pa_array, 0, stop=-len(suffix))
+        result = pc.if_else(ends_with, removed, self._pa_array)
+        return type(self)(result)
+
     def _str_count(self, pat: str, flags: int = 0):
         if flags:
             return super()._str_count(pat, flags)