Skip to content

Accept normalized UTF-8 encoding declarations with a BOM #1371

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
harbinresearcher wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Accept normalized UTF-8 encoding declarations with a BOM #1371

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
3 changes: 2 additions & 1 deletion babel/util.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,7 +91,8 @@ def parse_encoding(fp: IO[bytes]) -> str | None:
if has_bom:
if m:
magic_comment_encoding = m.group(1).decode('latin-1')
if magic_comment_encoding != 'utf-8':
normalized_encoding = magic_comment_encoding.lower().replace('_', '-')
if normalized_encoding != 'utf-8' and not normalized_encoding.startswith('utf-8-'):
raise SyntaxError(f"encoding problem: {magic_comment_encoding} with BOM")
return 'utf-8'
elif m:
Expand Down
21 changes: 21 additions & 0 deletions tests/test_util.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@

import __future__

import codecs
from io import BytesIO

import pytest
Expand Down Expand Up @@ -73,6 +74,26 @@ def test_parse_encoding_non_ascii():
assert parse_encoding('K\xf6ln') is None


@pytest.mark.parametrize('encoding', ['utf-8', 'UTF-8', 'utf_8', 'UTF_8', 'utf-8-sig'])
@pytest.mark.parametrize('prefix', [b'', b'# source file\n'])
def test_parse_encoding_bom(encoding, prefix):
source = codecs.BOM_UTF8 + prefix + f'# coding: {encoding}\n'.encode('ascii')
compile(source, '<test>', 'exec')
stream = BytesIO(source)
stream.seek(3)
assert util.parse_encoding(stream) == 'utf-8'
assert stream.tell() == 3


@pytest.mark.parametrize('encoding', ['latin-1', 'utf8', 'cp65001'])
def test_parse_encoding_bom_incompatible(encoding):
stream = BytesIO(codecs.BOM_UTF8 + f'# coding: {encoding}\n'.encode('ascii'))
stream.seek(3)
with pytest.raises(SyntaxError, match=f'encoding problem: {encoding} with BOM'):
util.parse_encoding(stream)
assert stream.tell() == 3


@pytest.mark.parametrize(('source', 'result'), [
('''
from __future__ import print_function,
Expand Down