diff options
| author | Leonard Richardson <leonard.richardson@canonical.com> | 2012-04-18 08:45:51 -0400 |
|---|---|---|
| committer | Leonard Richardson <leonard.richardson@canonical.com> | 2012-04-18 08:45:51 -0400 |
| commit | 3d0ae02cc3d0b947ef6102b31f4b354eec9b543a (patch) | |
| tree | e4ee65c0f4d9c32c6bf738a3524c66b6a5737d40 /bs4/tests/test_lxml.py | |
| parent | 4a587ff6996a2192944d7fec341180c2a116ea17 (diff) | |
Fixed a bug that made the HTMLParser treebuilder generate XML definitions ending with two question marks instead of one. [bug=984258]
Diffstat (limited to 'bs4/tests/test_lxml.py')
| -rw-r--r-- | bs4/tests/test_lxml.py | 15 |
1 files changed, 15 insertions, 0 deletions
diff --git a/bs4/tests/test_lxml.py b/bs4/tests/test_lxml.py index 4e0b12e..39e26bf 100644 --- a/bs4/tests/test_lxml.py +++ b/bs4/tests/test_lxml.py @@ -48,6 +48,21 @@ class LXMLTreeBuilderSmokeTest(SoupTest, HTMLTreeBuilderSmokeTest): soup = BeautifulStoneSoup("<b />") self.assertEqual(u"<b/>", unicode(soup.b)) + def test_real_xhtml_document(self): + """lxml strips the XML definition from an XHTML doc, which is fine.""" + markup = b"""<?xml version="1.0" encoding="utf-8"?> +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"> +<html xmlns="http://www.w3.org/1999/xhtml"> +<head><title>Hello.</title></head> +<body>Goodbye.</body> +</html>""" + soup = self.soup(markup) + self.assertEqual( + soup.encode("utf-8").replace(b"\n", b''), + markup.replace(b'\n', b'').replace( + b'<?xml version="1.0" encoding="utf-8"?>', b'')) + + @skipIf( not LXML_PRESENT, "lxml seems not to be present, not testing its XML tree builder.") |