Skip to content

Issue 21 encoding #27

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
Thomas-S-Allen merged 3 commits into from
Oct 16, 2025
Merged

Issue 21 encoding #27

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
497c580
issue_21_encoding
Thomas-S-Allen Oct 16, 2025
1d26e35
cleanup comments
Thomas-S-Allen Oct 16, 2025
03711e8
update unit test
Thomas-S-Allen Oct 16, 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
3 changes: 2 additions & 1 deletion adsrefpipe/refparsers/unicode.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -244,7 +244,8 @@ def __sub_hexnumasc_entity(self, match: re.Match) -> str:
elif entno < 255:
return self.u2asc(chr(entno))
except IndexError:
raise UnicodeHandlerError('Unknown hexadecimal entity: %s' % match.group(0))
logger.error(UnicodeHandlerError('Unknown hexadecimal entity: %s' % match.group(0)))
return ""

def __sub_hexnum_toent(self, match: re.Match) -> str:
"""
Expand Down
9 changes: 3 additions & 6 deletions adsrefpipe/tests/unittests/test_ref_parsers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -304,14 +304,11 @@ def test_sub_hexnumasc_entity(self):
handler.unicode = MagicMock()
handler.unicode.__getitem__.side_effect = IndexError

# large invalid hex value to trigger the IndexError exception
# large invalid hex value to trigger returning and empty string ""
match = re.match(r'&#x(?P<hexnum>[0-9A-Fa-f]+);', "&#x99999;")
if match:
# check that the correct exception is raised
with self.assertRaises(UnicodeHandlerError) as context:
handler._UnicodeHandler__sub_hexnumasc_entity(match)
# ensure the exception message is correct
self.assertEqual(str(context.exception), "Unknown hexadecimal entity: &#x99999;")
result = handler._UnicodeHandler__sub_hexnumasc_entity(match)
self.assertEqual(result, "")

def test_sub_hexnum_toent(self):
""" test __sub_hexnum_toent method """
Expand Down