diff options
| -rw-r--r-- | tests/test_html5lib.py | 22 | ||||
| -rw-r--r-- | tests/test_lxml.py | 11 |
2 files changed, 33 insertions, 0 deletions
diff --git a/tests/test_html5lib.py b/tests/test_html5lib.py index 48f27ae..3efdebf 100644 --- a/tests/test_html5lib.py +++ b/tests/test_html5lib.py @@ -107,6 +107,28 @@ class TestHTML5BuilderInvalidMarkup(TestLXMLBuilderInvalidMarkup): ("<html><head></head><body><p>a</p>" "<!-- Foo = -8--></body></html>")) + def test_whitespace_in_doctype(self): + # A declaration that has extra whitespace is turned into a comment. + soup = self.soup(( + '<! DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN">' + '<p>foo</p>')) + self.assertEquals( + str(soup), + ('<!-- DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"-->' + '<html><head></head><body><p>foo</p></body></html>')) + + def test_incomplete_declaration(self): + # An incomplete declaration is treated as a comment. + markup = 'a<!b <p>c' + self.assertSoupEquals(markup, "a<!--b <p-->c") + + # Let's spell that out a little more explicitly. + soup = self.soup(markup) + str1, comment, str2 = soup.body.contents + self.assertEquals(str1, 'a') + self.assertEquals(comment.__class__, Comment) + self.assertEquals(comment, 'b <p') + self.assertEquals(str2, 'c') def test_foo(self): isolatin = """<html><meta http-equiv="Content-type" content="text/html; charset=ISO-Latin-1" />Sacr\xe9 bleu!</html>""" diff --git a/tests/test_lxml.py b/tests/test_lxml.py index cba5522..6adc2b3 100644 --- a/tests/test_lxml.py +++ b/tests/test_lxml.py @@ -302,6 +302,17 @@ class TestLXMLBuilderInvalidMarkup(SoupTest): # Declarations that don't make any sense are ignored. self.assertSoupEquals('<! Foo = -8><p>a</p>', "<p>a</p>") + def test_whitespace_in_doctype(self): + # A declaration that has extra whitespace is ignored. + self.assertSoupEquals( + ('<! DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN">' + '<p>foo</p>'), + '<p>foo</p>') + + def test_incomplete_declaration(self): + # An incomplete declaration will screw up the rest of the document. + self.assertSoupEquals('a<!b <p>c', '<p>a</p>') + def test_cdata_where_it_doesnt_belong(self): #CDATA sections are ignored. markup = "<div><![CDATA[foo]]>" |