diff options
| -rw-r--r-- | tests/test_html5lib.py | 9 | ||||
| -rw-r--r-- | tests/test_lxml.py | 4 |
2 files changed, 11 insertions, 2 deletions
diff --git a/tests/test_html5lib.py b/tests/test_html5lib.py index 3efdebf..1034720 100644 --- a/tests/test_html5lib.py +++ b/tests/test_html5lib.py @@ -3,6 +3,7 @@ from beautifulsoup.element import Comment from test_lxml import ( TestLXMLBuilder, TestLXMLBuilderInvalidMarkup, + TestLXMLBuilderEncodingConversion, ) class TestHTML5Builder(TestLXMLBuilder): @@ -138,3 +139,11 @@ class TestHTML5BuilderInvalidMarkup(TestLXMLBuilderInvalidMarkup): utf8 = utf8.replace("\xe9", "\xc3\xa9") #print soup + + +class TestHTML5LibEncodingConversion(TestLXMLBuilderEncodingConversion): + @property + def default_builder(self): + return HTML5TreeBuilder() + + pass diff --git a/tests/test_lxml.py b/tests/test_lxml.py index 0f54e78..1218763 100644 --- a/tests/test_lxml.py +++ b/tests/test_lxml.py @@ -383,10 +383,10 @@ class TestLXMLBuilderEncodingConversion(SoupTest): def setUp(self): super(TestLXMLBuilderEncodingConversion, self).setUp() - self.unicode_data = u"<html><body><foo>\xe9</foo></body></html>" + self.unicode_data = u"<html><head></head><body><foo>\xe9</foo></body></html>" self.utf8_data = self.unicode_data.encode("utf-8") self.assertEqual( - self.utf8_data, "<html><body><foo>\xc3\xa9</foo></body></html>") + self.utf8_data, "<html><head></head><body><foo>\xc3\xa9</foo></body></html>") def test_ascii_in_unicode_out(self): # ASCII input is converted to Unicode. The originalEncoding |