Skip to content

gh-130655: Add a test for big-endian MO files in gettext #132469

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
May 1, 2025
Merged

gh-130655: Add a test for big-endian MO files in gettext #132469

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
26 changes: 26 additions & 0 deletions Lib/test/test_gettext.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -115,6 +115,23 @@
0x62, 0x61, 0x72, 0x00, # Message data
]))


GNU_MO_DATA_BIG_ENDIAN = base64.b64encode(bytes([
Copy link
Member

Choose a reason for hiding this comment

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

It is weird to use b64encode here, and then decode it back. In future we may use bytes literals.

Copy link
Member Author

Choose a reason for hiding this comment

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

Noted, thanks for the review!

0x95, 0x04, 0x12, 0xDE, # Magic
0x00, 0x00, 0x00, 0x00, # Version
0x00, 0x00, 0x00, 0x01, # Message count
0x00, 0x00, 0x00, 0x1C, # Message offset
0x00, 0x00, 0x00, 0x24, # Translation offset
0x00, 0x00, 0x00, 0x00, # Hash table size
0x00, 0x00, 0x00, 0x2C, # Hash table offset
0x00, 0x00, 0x00, 0x03, # 1st message length
0x00, 0x00, 0x00, 0x2C, # 1st message offset
0x00, 0x00, 0x00, 0x03, # 1st trans length
0x00, 0x00, 0x00, 0x30, # 1st trans offset
0x66, 0x6F, 0x6F, 0x00, # Message data
0x62, 0x61, 0x72, 0x00, # Message data
]))

UMO_DATA = b'''\
3hIElQAAAAADAAAAHAAAADQAAAAAAAAAAAAAAAAAAABMAAAABAAAAE0AAAAQAAAAUgAAAA8BAABj
AAAABAAAAHMBAAAWAAAAeAEAAABhYsOeAG15Y29udGV4dMOeBGFiw54AUHJvamVjdC1JZC1WZXJz
Expand Down Expand Up @@ -142,6 +159,7 @@
MOFILE_BAD_MAJOR_VERSION = os.path.join(LOCALEDIR, 'gettext_bad_major_version.mo')
MOFILE_BAD_MINOR_VERSION = os.path.join(LOCALEDIR, 'gettext_bad_minor_version.mo')
MOFILE_CORRUPT = os.path.join(LOCALEDIR, 'gettext_corrupt.mo')
MOFILE_BIG_ENDIAN = os.path.join(LOCALEDIR, 'gettext_big_endian.mo')
UMOFILE = os.path.join(LOCALEDIR, 'ugettext.mo')
MMOFILE = os.path.join(LOCALEDIR, 'metadata.mo')

Expand All @@ -168,6 +186,8 @@ def setUpClass(cls):
fp.write(base64.decodebytes(GNU_MO_DATA_BAD_MINOR_VERSION))
with open(MOFILE_CORRUPT, 'wb') as fp:
fp.write(base64.decodebytes(GNU_MO_DATA_CORRUPT))
with open(MOFILE_BIG_ENDIAN, 'wb') as fp:
fp.write(base64.decodebytes(GNU_MO_DATA_BIG_ENDIAN))
with open(UMOFILE, 'wb') as fp:
fp.write(base64.decodebytes(UMO_DATA))
with open(MMOFILE, 'wb') as fp:
Expand Down Expand Up @@ -293,6 +313,12 @@ def test_corrupt_file(self):
self.assertEqual(exception.strerror, "File is corrupt")
self.assertEqual(exception.filename, MOFILE_CORRUPT)

def test_big_endian_file(self):
with open(MOFILE_BIG_ENDIAN, 'rb') as fp:
t = gettext.GNUTranslations(fp)

self.assertEqual(t.gettext('foo'), 'bar')

def test_some_translations(self):
eq = self.assertEqual
# test some translations
Expand Down
Loading