Skip to content

gh-44827: Improve error if BOM on first line of .po file #130187

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.

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 3 commits into from
Feb 18, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
8 changes: 8 additions & 0 deletions Lib/test/test_tools/test_msgfmt.py
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,14 @@ def test_compilation(self):

self.assertDictEqual(actual._catalog, expected._catalog)

def test_po_with_bom(self):
with temp_cwd():
Path('bom.po').write_bytes(b'\xef\xbb\xbfmsgid "Python"\nmsgstr "Pioton"\n')

res = assert_python_failure(msgfmt, 'bom.po')
err = res.err.decode('utf-8')
self.assertIn('The file bom.po starts with a UTF-8 BOM', err)

def test_invalid_msgid_plural(self):
with temp_cwd():
Path('invalid.po').write_text('''\
Expand Down
10 changes: 10 additions & 0 deletions Tools/i18n/msgfmt.py
Original file line number Diff line number Diff line change
Expand Up @@ -32,9 +32,11 @@
import struct
import array
from email.parser import HeaderParser
import codecs

__version__ = "1.2"


MESSAGES = {}


Expand Down Expand Up @@ -116,6 +118,14 @@ def make(filename, outfile):
print(msg, file=sys.stderr)
sys.exit(1)

if lines[0].startswith(codecs.BOM_UTF8):
print(
f"The file {infile} starts with a UTF-8 BOM which is not allowed in .po files.\n"
"Please save the file without a BOM and try again.",
file=sys.stderr
)
sys.exit(1)

section = msgctxt = None
fuzzy = 0

Expand Down
Loading