Skip to content

gh-130655: Add a test for corrupt MO files in gettext #131911

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 2 commits into from
Apr 4, 2025
Merged

gh-130655: Add a test for corrupt MO files in gettext #131911

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
db513dc
Add a test for corrupt MO files in gettext
tomasr8 Mar 30, 2025
9ce9e1d
Merge branch 'main' into gettext-corrupt
picnixz Apr 4, 2025
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
39 changes: 39 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 @@ -85,6 +85,32 @@
ciBUQUgKdHJnZ3JrZyB6cmZmbnRyIHBuZ255YnQgeXZvZW5lbC4AYmFjb24Ad2luayB3aW5rAA==
'''

# Corrupt .mo file
# Generated from
#
# msgid "foo"
# msgstr "bar"
#
# with msgfmt --no-hash
#
# The translation offset is changed to 0xFFFFFFFF,
# making it larger than the file size, which should
# raise an error when parsing.
GNU_MO_DATA_CORRUPT = base64.b64encode(bytes([
0xDE, 0x12, 0x04, 0x95, # Magic
0x00, 0x00, 0x00, 0x00, # Version
0x01, 0x00, 0x00, 0x00, # Message count
0x1C, 0x00, 0x00, 0x00, # Message offset
0x24, 0x00, 0x00, 0x00, # Translation offset
0x00, 0x00, 0x00, 0x00, # Hash table size
0x2C, 0x00, 0x00, 0x00, # Hash table offset
0x03, 0x00, 0x00, 0x00, # 1st message length
0x2C, 0x00, 0x00, 0x00, # 1st message offset
0x03, 0x00, 0x00, 0x00, # 1st trans length
0xFF, 0xFF, 0xFF, 0xFF, # 1st trans offset (Modified to make it invalid)
0x66, 0x6F, 0x6F, 0x00, # Message data
0x62, 0x61, 0x72, 0x00, # Message data
]))

UMO_DATA = b'''\
3hIElQAAAAADAAAAHAAAADQAAAAAAAAAAAAAAAAAAABMAAAABAAAAE0AAAAQAAAAUgAAAA8BAABj
Expand All @@ -111,6 +137,7 @@
MOFILE = os.path.join(LOCALEDIR, 'gettext.mo')
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')
UMOFILE = os.path.join(LOCALEDIR, 'ugettext.mo')
MMOFILE = os.path.join(LOCALEDIR, 'metadata.mo')

Expand All @@ -133,6 +160,8 @@ def setUpClass(cls):
fp.write(base64.decodebytes(GNU_MO_DATA_BAD_MAJOR_VERSION))
with open(MOFILE_BAD_MINOR_VERSION, 'wb') as fp:
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(UMOFILE, 'wb') as fp:
fp.write(base64.decodebytes(UMO_DATA))
with open(MMOFILE, 'wb') as fp:
Expand Down Expand Up @@ -238,6 +267,16 @@ def test_bad_minor_version(self):
# Check that no error is thrown with a bad minor version number
gettext.GNUTranslations(fp)

def test_corrupt_file(self):
with open(MOFILE_CORRUPT, 'rb') as fp:
with self.assertRaises(OSError) as cm:
gettext.GNUTranslations(fp)

exception = cm.exception
self.assertEqual(exception.errno, 0)
self.assertEqual(exception.strerror, "File is corrupt")
self.assertEqual(exception.filename, MOFILE_CORRUPT)

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