mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-21 17:25:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 13

#13960: HTMLParser is now able to handle broken comments.

Browse source
This commit is contained in:
Ezio Melotti 2012-02-13 16:10:44 +02:00
parent 32b6371460
commit 4b92cc3f79
3 changed files with 74 additions and 22 deletions
Download patch file Download diff file Expand all files Collapse all files

58
Lib/test/test_htmlparser.py
View file

@ -114,7 +114,7 @@ comment1b-->
<Img sRc='Bar' isMAP>sample
text
&#x201C;
<!--comment2a-- --comment2b--><!>
<!--comment2a-- --comment2b-->
</Html>
""", [
("data", "\n"),
@ -142,24 +142,6 @@ text
("data", " foo"),
])
def test_doctype_decl(self):
inside = """\
DOCTYPE html [
<!ELEMENT html - O EMPTY>
<!ATTLIST html
version CDATA #IMPLIED
profile CDATA 'DublinCore'>
<!NOTATION datatype SYSTEM 'http://xml.python.org/notations/python-module'>
<!ENTITY myEntity 'internal parsed entity'>
<!ENTITY anEntity SYSTEM 'http://xml.python.org/entities/something.xml'>
<!ENTITY % paramEntity 'name|name|name'>
%paramEntity;
<!-- comment -->
]"""
self._run_check("<!%s>" % inside, [
("decl", inside),
])
def test_bad_nesting(self):
# Strangely, this *is* supposed to test that overlapping
# elements are allowed. HTMLParser is more geared toward
@ -182,7 +164,8 @@ DOCTYPE html [
])
def test_illegal_declarations(self):
self._parse_error('<!spacer type="block" height="25">')
self._run_check('<!spacer type="block" height="25">',
[('comment', 'spacer type="block" height="25"')])
def test_starttag_end_boundary(self):
self._run_check("""<a b='<'>""", [("starttag", "a", [("b", "<")])])
@ -233,7 +216,7 @@ DOCTYPE html [
self._parse_error("<a foo='>")
def test_declaration_junk_chars(self):
self._parse_error("<!DOCTYPE foo $ >")
self._run_check("<!DOCTYPE foo $ >", [('decl', 'DOCTYPE foo $ ')])
def test_startendtag(self):
self._run_check("<p/>", [
@ -449,6 +432,39 @@ class AttributesTestCase(TestCaseBase):
[("href", "http://www.example.org/\">;")]),
("data", "spam"), ("endtag", "a")])
def test_comments(self):
html = ("<!-- I'm a valid comment -->"
'<!--me too!-->'
'<!------>'
'<!---->'
'<!----I have many hyphens---->'
'<!-- I have a > in the middle -->'
'<!-- and I have -- in the middle! -->')
expected = [('comment', " I'm a valid comment "),
('comment', 'me too!'),
('comment', '--'),
('comment', ''),
('comment', '--I have many hyphens--'),
('comment', ' I have a > in the middle '),
('comment', ' and I have -- in the middle! ')]
self._run_check(html, expected)
def test_broken_comments(self):
html = ('<! not really a comment >'
'<! not a comment either -->'
'<! -- close enough -->'
'<!><!<-- this was an empty comment>'
'<!!! another bogus comment !!!>')
expected = [
('comment', ' not really a comment '),
('comment', ' not a comment either --'),
('comment', ' -- close enough --'),
('comment', ''),
('comment', '<-- this was an empty comment'),
('comment', '!! another bogus comment !!!'),
]
self._run_check(html, expected)
def test_condcoms(self):
html = ('<!--[if IE & !(lte IE 8)]>aren\'t<![endif]-->'
'<!--[if IE 8]>condcoms<![endif]-->'