Skip to content

fix: anchor newline-end strip to whole alternation #249

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
santhreal wants to merge 1 commit into
base: main
Choose a base branch
from
+12 −2
Open

fix: anchor newline-end strip to whole alternation #249

Show file tree
Hide file tree
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
7 changes: 5 additions & 2 deletions path/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,8 +98,9 @@
U_LINESEPS = LINESEPS + ['\u0085', '\u2028', '\u2029']
B_NEWLINE = re.compile('|'.join(LINESEPS).encode())
U_NEWLINE = re.compile('|'.join(U_LINESEPS))
B_NL_END = re.compile(B_NEWLINE.pattern + b'$')
U_NL_END = re.compile(U_NEWLINE.pattern + '$')
# Group the alternation so $ anchors the whole newline, not only the last alt.
B_NL_END = re.compile(b'(?:' + B_NEWLINE.pattern + b')$')
U_NL_END = re.compile('(?:' + U_NEWLINE.pattern + ')$')

_default_linesep = object()

Expand Down Expand Up @@ -155,6 +156,8 @@ def _strip_newlines(lines: Iterable[str]) -> Iterator[str]:
r"""
>>> list(_strip_newlines(['Hello World\r\n', 'foo']))
['Hello World', 'foo']
>>> list(_strip_newlines(['Hello\nWorld\n', 'foo']))
['Hello\nWorld', 'foo']
"""
return (U_NL_END.sub('', line) for line in lines)

Expand Down
7 changes: 7 additions & 0 deletions tests/test_path.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -318,6 +318,13 @@ def test_read_write(self, tmpdir):
assert file.read_text(encoding='utf-8') == 'hello world'
assert file.read_bytes() == b'hello world'

def test_write_lines_preserves_embedded_newlines(self, tmpdir):
file = path.Path(tmpdir) / 'filename'
file.write_lines(['Hello\nWorld', 'foo\r\nbar\n'], encoding='utf-8')
assert file.read_bytes() == (
f'Hello\nWorld{os.linesep}foo\r\nbar{os.linesep}'.encode()
)


class TestPerformance:
@staticmethod
Expand Down