Skip to content

gh-135661: Fix parsing unterminated bogus comments in HTMLParser #137873

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 17, 2025
Merged

gh-135661: Fix parsing unterminated bogus comments in HTMLParser #137873

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 8 additions & 14 deletions Lib/html/parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -271,11 +271,8 @@ def goahead(self, end):
j -= len(suffix)
break
self.handle_comment(rawdata[i+4:j])
elif startswith("<![CDATA[", i):
if self._support_cdata:
self.unknown_decl(rawdata[i+3:])
else:
self.handle_comment(rawdata[i+1:])
elif startswith("<![CDATA[", i) and self._support_cdata:
self.unknown_decl(rawdata[i+3:])
elif rawdata[i:i+9].lower() == '<!doctype':
self.handle_decl(rawdata[i+2:])
elif startswith("<!", i):
Expand Down Expand Up @@ -350,15 +347,12 @@ def parse_html_declaration(self, i):
if rawdata[i:i+4] == '<!--':
# this case is actually already handled in goahead()
return self.parse_comment(i)
elif rawdata[i:i+9] == '<![CDATA[':
if self._support_cdata:
j = rawdata.find(']]>', i+9)
if j < 0:
return -1
self.unknown_decl(rawdata[i+3: j])
return j + 3
else:
return self.parse_bogus_comment(i)
elif rawdata[i:i+9] == '<![CDATA[' and self._support_cdata:
j = rawdata.find(']]>', i+9)
if j < 0:
return -1
self.unknown_decl(rawdata[i+3: j])
return j + 3
elif rawdata[i:i+9].lower() == '<!doctype':
# find the closing >
gtpos = rawdata.find('>', i+9)
Expand Down
2 changes: 1 addition & 1 deletion Lib/test/test_htmlparser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -791,7 +791,7 @@ def test_eof_in_cdata(self, content):
self._run_check('<![CDATA[' + content,
[('unknown decl', 'CDATA[' + content)])
self._run_check('<![CDATA[' + content,
[('comment', '![CDATA[' + content)],
[('comment', '[CDATA[' + content)],
collector=EventCollector(autocdata=True))
self._run_check('<svg><text y="100"><![CDATA[' + content,
[('starttag', 'svg', []),
Expand Down
Loading