Skip to content

BUG: fix empty suffix and prefix handling in pyarrow string methods #63395

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
vkverma9534 wants to merge 7 commits into
base: main
Choose a base branch
from
+32 −12
Open

BUG: fix empty suffix and prefix handling in pyarrow string methods #63395

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
c64ef05
BUG: fix empty suffix and prefix handling in pyarrow string methods
vkverma9534 Dec 17, 2025
74fb4f9
BUG: add tests for empty prefix and suffix
vkverma9534 Dec 17, 2025
a1da54e
BUG: handle empty prefix in pyarrow-backed removeprefix
vkverma9534 Dec 17, 2025
f71a75c
BUG: fix empty prefix/suffix handling in pyarrow-backed string methods
vkverma9534 Dec 17, 2025
2ec810d
BUG: fix removeprefix/removesuffix for empty strings in pyarrow backend
vkverma9534 Dec 17, 2025
9a526ea
Fix for failing cases
vkverma9534 Dec 17, 2025
e733bfb
fix for failing tests
vkverma9534 Dec 17, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 18 additions & 10 deletions pandas/core/arrays/_arrow_string_mixins.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -201,18 +201,26 @@ def _str_title(self) -> Self:

def _str_swapcase(self) -> Self:
return self._from_pyarrow_array(pc.utf8_swapcase(self._pa_array))
def _str_removeprefix(self, prefix: str):
if prefix == "":
return self
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 self._from_pyarrow_array(result)


def _str_removesuffix(self, suffix: str):
if suffix == "":
return self
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 self._from_pyarrow_array(result)



def _str_removeprefix(self, prefix: str):
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 self._from_pyarrow_array(result)

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 self._from_pyarrow_array(result)
Comment on lines +204 to -215
Copy link
Member

@jorisvandenbossche jorisvandenbossche Dec 17, 2025 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
def _str_removeprefix(self, prefix: str):
if prefix == "":
return self
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 self._from_pyarrow_array(result)
def _str_removesuffix(self, suffix: str):
if suffix == "":
return self
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 self._from_pyarrow_array(result)
def _str_removeprefix(self, prefix: str):
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 self._from_pyarrow_array(result)
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 self._from_pyarrow_array(result)
def _str_removeprefix(self, prefix: str):
if prefix == "":
return self
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 self._from_pyarrow_array(result)
def _str_removesuffix(self, suffix: str):
if prefix == "":
return self
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 self._from_pyarrow_array(result)

I think this should fix it


def _str_startswith(
self, pat: str | tuple[str, ...], na: Scalar | lib.NoDefault = lib.no_default
Expand Down
16 changes: 14 additions & 2 deletions pandas/tests/strings/test_strings.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -544,7 +544,12 @@ def test_strip_lstrip_rstrip_args(any_string_dtype, method, exp):


@pytest.mark.parametrize(
"prefix, expected", [("a", ["b", " b c", "bc"]), ("ab", ["", "a b c", "bc"])]
"prefix, expected",
[
("a", ["b", " b c", "bc"]),
("ab", ["", "a b c", "bc"]),
("", ["ab", "a b c", "bc"]),
],
)
def test_removeprefix(any_string_dtype, prefix, expected):
ser = Series(["ab", "a b c", "bc"], dtype=any_string_dtype)
Expand All @@ -554,7 +559,12 @@ def test_removeprefix(any_string_dtype, prefix, expected):


@pytest.mark.parametrize(
"suffix, expected", [("c", ["ab", "a b ", "b"]), ("bc", ["ab", "a b c", ""])]
"suffix, expected",
[
("c", ["ab", "a b ", "b"]),
("bc", ["ab", "a b c", ""]),
("", ["ab", "a b c", "bc"]),
],
)
def test_removesuffix(any_string_dtype, suffix, expected):
ser = Series(["ab", "a b c", "bc"], dtype=any_string_dtype)
Expand All @@ -563,6 +573,8 @@ def test_removesuffix(any_string_dtype, suffix, expected):
tm.assert_series_equal(result, ser_expected)




def test_string_slice_get_syntax(any_string_dtype):
ser = Series(
["YYY", "B", "C", "YYYYYYbYYY", "BYYYcYYY", np.nan, "CYYYBYYY", "dog", "cYYYt"],
Expand Down
Loading