diff options
| author | Leonard Richardson <leonard.richardson@canonical.com> | 2013-06-02 19:12:07 -0400 |
|---|---|---|
| committer | Leonard Richardson <leonard.richardson@canonical.com> | 2013-06-02 19:12:07 -0400 |
| commit | 4f9a654766df9ddd05e3ef274b4715b42668724f (patch) | |
| tree | 32020441f20ecf34ad85557f41a076bef0b78b7a /bs4/tests/test_soup.py | |
| parent | 6d9221a42dd3fdd679b8e222cb9c73065eeeb747 (diff) | |
Turns out we had two bits of code to strip byte-order marks.
Diffstat (limited to 'bs4/tests/test_soup.py')
| -rw-r--r-- | bs4/tests/test_soup.py | 5 |
1 files changed, 2 insertions, 3 deletions
diff --git a/bs4/tests/test_soup.py b/bs4/tests/test_soup.py index c275228..0b69318 100644 --- a/bs4/tests/test_soup.py +++ b/bs4/tests/test_soup.py @@ -306,9 +306,8 @@ class TestUnicodeDammit(unittest.TestCase): logging.disable(logging.NOTSET) bs4.dammit.chardet_dammit = chardet - def test_sniffed_xml_encoding(self): - # A document written in UTF-16LE will be converted by a different - # code path that sniffs the byte order markers. + def test_byte_order_mark_removed(self): + # A document written in UTF-16LE will have its byte order marker stripped. data = b'\xff\xfe<\x00a\x00>\x00\xe1\x00\xe9\x00<\x00/\x00a\x00>\x00' dammit = UnicodeDammit(data) self.assertEqual(u"<a>áé</a>", dammit.unicode_markup) |