Skip to content

ENH: Implement more string accessors through PyArrow #54960

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

Merged
merged 1 commit into from
Sep 6, 2023
Merged

ENH: Implement more string accessors through PyArrow #54960

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
31 changes: 23 additions & 8 deletions pandas/core/arrays/string_arrow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,8 @@


if TYPE_CHECKING:
from collections.abc import Sequence

from pandas._typing import (
Dtype,
Scalar,
Expand Down Expand Up @@ -334,19 +336,13 @@ def _str_startswith(self, pat: str, na=None):
result = pc.starts_with(self._pa_array, pattern=pat)
if not isna(na):
result = result.fill_null(na)
result = self._result_converter(result)
if not isna(na):
result[isna(result)] = bool(na)
return result
return self._result_converter(result)

def _str_endswith(self, pat: str, na=None):
result = pc.ends_with(self._pa_array, pattern=pat)
if not isna(na):
result = result.fill_null(na)
result = self._result_converter(result)
if not isna(na):
result[isna(result)] = bool(na)
return result
return self._result_converter(result)

def _str_replace(
self,
Expand All @@ -365,6 +361,12 @@ def _str_replace(
result = func(self._pa_array, pattern=pat, replacement=repl, max_replacements=n)
return type(self)(result)

def _str_repeat(self, repeats: int | Sequence[int]):
if not isinstance(repeats, int):
return super()._str_repeat(repeats)
else:
return type(self)(pc.binary_repeat(self._pa_array, repeats))

def _str_match(
self, pat: str, case: bool = True, flags: int = 0, na: Scalar | None = None
):
Expand All @@ -379,6 +381,19 @@ def _str_fullmatch(
pat = f"{pat}$"
return self._str_match(pat, case, flags, na)

def _str_slice(
self, start: int | None = None, stop: int | None = None, step: int | None = None
):
if stop is None:
return super()._str_slice(start, stop, step)
if start is None:
start = 0
if step is None:
step = 1
return type(self)(
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._result_converter(result)
Expand Down