https://github.com/python/cpython/commit/f3c6f882cddc8dc30320d2e73edf019e201394fc
commit: f3c6f882cddc8dc30320d2e73edf019e201394fc
branch: 3.11
author: Serhiy Storchaka <storch...@gmail.com>
committer: ambv <luk...@langa.pl>
date: 2025-07-03T23:05:46+02:00
summary:
[3.11] gh-135462: Fix quadratic complexity in processing special input in
HTMLParser (GH-135464) (GH-135484)
End-of-file errors are now handled according to the HTML5 specs --
comments and declarations are automatically closed, tags are ignored.
(cherry picked from commit 6eb6c5dbfb528bd07d77b60fd71fd05d81d45c41)
files:
A Misc/NEWS.d/next/Security/2025-06-13-15-55-22.gh-issue-135462.KBeJpc.rst
M Lib/html/parser.py
M Lib/test/test_htmlparser.py
diff --git a/Lib/html/parser.py b/Lib/html/parser.py
index bef0f4fe4bf776..9c38008bbfd06b 100644
--- a/Lib/html/parser.py
+++ b/Lib/html/parser.py
@@ -25,6 +25,7 @@
charref = re.compile('&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]')
starttagopen = re.compile('<[a-zA-Z]')
+endtagopen = re.compile('</[a-zA-Z]')
piclose = re.compile('>')
commentclose = re.compile(r'--\s*>')
# Note:
@@ -176,7 +177,7 @@ def goahead(self, end):
k = self.parse_pi(i)
elif startswith("<!", i):
k = self.parse_html_declaration(i)
- elif (i + 1) < n:
+ elif (i + 1) < n or end:
self.handle_data("<")
k = i + 1
else:
@@ -184,17 +185,35 @@ def goahead(self, end):
if k < 0:
if not end:
break
- k = rawdata.find('>', i + 1)
- if k < 0:
- k = rawdata.find('<', i + 1)
- if k < 0:
- k = i + 1
- else:
- k += 1
- if self.convert_charrefs and not self.cdata_elem:
- self.handle_data(unescape(rawdata[i:k]))
+ if starttagopen.match(rawdata, i): # < + letter
+ pass
+ elif startswith("</", i):
+ if i + 2 == n:
+ self.handle_data("</")
+ elif endtagopen.match(rawdata, i): # </ + letter
+ pass
+ else:
+ # bogus comment
+ self.handle_comment(rawdata[i+2:])
+ elif startswith("<!--", i):
+ j = n
+ for suffix in ("--!", "--", "-"):
+ if rawdata.endswith(suffix, i+4):
+ j -= len(suffix)
+ break
+ self.handle_comment(rawdata[i+4:j])
+ elif startswith("<![CDATA[", i):
+ self.unknown_decl(rawdata[i+3:])
+ elif rawdata[i:i+9].lower() == '<!doctype':
+ self.handle_decl(rawdata[i+2:])
+ elif startswith("<!", i):
+ # bogus comment
+ self.handle_comment(rawdata[i+2:])
+ elif startswith("<?", i):
+ self.handle_pi(rawdata[i+2:])
else:
- self.handle_data(rawdata[i:k])
+ raise AssertionError("we should not get here!")
+ k = n
i = self.updatepos(i, k)
elif startswith("&#", i):
match = charref.match(rawdata, i)
diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py
index 12917755a56017..df775c11310146 100644
--- a/Lib/test/test_htmlparser.py
+++ b/Lib/test/test_htmlparser.py
@@ -4,6 +4,8 @@
import pprint
import unittest
+from test import support
+
class EventCollector(html.parser.HTMLParser):
@@ -391,28 +393,34 @@ def test_tolerant_parsing(self):
('data', '<'),
('starttag', 'bc<', [('a', None)]),
('endtag', 'html'),
- ('data', '\n<img src="URL>'),
- ('comment', '/img'),
- ('endtag', 'html<')])
+ ('data', '\n')])
def test_starttag_junk_chars(self):
+ self._run_check("<", [('data', '<')])
+ self._run_check("<>", [('data', '<>')])
+ self._run_check("< >", [('data', '< >')])
+ self._run_check("< ", [('data', '< ')])
self._run_check("</>", [])
+ self._run_check("<$>", [('data', '<$>')])
self._run_check("</$>", [('comment', '$')])
self._run_check("</", [('data', '</')])
- self._run_check("</a", [('data', '</a')])
+ self._run_check("</a", [])
+ self._run_check("</ a>", [('endtag', 'a')])
+ self._run_check("</ a", [('comment', ' a')])
self._run_check("<a<a>", [('starttag', 'a<a', [])])
self._run_check("</a<a>", [('endtag', 'a<a')])
- self._run_check("<!", [('data', '<!')])
- self._run_check("<a", [('data', '<a')])
- self._run_check("<a foo='bar'", [('data', "<a foo='bar'")])
- self._run_check("<a foo='bar", [('data', "<a foo='bar")])
- self._run_check("<a foo='>'", [('data', "<a foo='>'")])
- self._run_check("<a foo='>", [('data', "<a foo='>")])
+ self._run_check("<!", [('comment', '')])
+ self._run_check("<a", [])
+ self._run_check("<a foo='bar'", [])
+ self._run_check("<a foo='bar", [])
+ self._run_check("<a foo='>'", [])
+ self._run_check("<a foo='>", [])
self._run_check("<a$>", [('starttag', 'a$', [])])
self._run_check("<a$b>", [('starttag', 'a$b', [])])
self._run_check("<a$b/>", [('startendtag', 'a$b', [])])
self._run_check("<a$b >", [('starttag', 'a$b', [])])
self._run_check("<a$b />", [('startendtag', 'a$b', [])])
+ self._run_check("</a$b>", [('endtag', 'a$b')])
def test_slashes_in_starttag(self):
self._run_check('<a foo="var"/>', [('startendtag', 'a', [('foo',
'var')])])
@@ -537,13 +545,56 @@ def test_EOF_in_charref(self):
for html, expected in data:
self._run_check(html, expected)
- def test_broken_comments(self):
- html = ('<! not really a comment >'
+ def test_eof_in_comments(self):
+ data = [
+ ('<!--', [('comment', '')]),
+ ('<!---', [('comment', '')]),
+ ('<!----', [('comment', '')]),
+ ('<!-----', [('comment', '-')]),
+ ('<!------', [('comment', '--')]),
+ ('<!----!', [('comment', '')]),
+ ('<!---!', [('comment', '-!')]),
+ ('<!---!>', [('comment', '-!>')]),
+ ('<!--foo', [('comment', 'foo')]),
+ ('<!--foo-', [('comment', 'foo')]),
+ ('<!--foo--', [('comment', 'foo')]),
+ ('<!--foo--!', [('comment', 'foo')]),
+ ('<!--<!--', [('comment', '<!')]),
+ ('<!--<!--!', [('comment', '<!')]),
+ ]
+ for html, expected in data:
+ self._run_check(html, expected)
+
+ def test_eof_in_declarations(self):
+ data = [
+ ('<!', [('comment', '')]),
+ ('<!-', [('comment', '-')]),
+ ('<![', [('comment', '[')]),
+ ('<![CDATA[', [('unknown decl', 'CDATA[')]),
+ ('<![CDATA[x', [('unknown decl', 'CDATA[x')]),
+ ('<![CDATA[x]', [('unknown decl', 'CDATA[x]')]),
+ ('<![CDATA[x]]', [('unknown decl', 'CDATA[x]]')]),
+ ('<!DOCTYPE', [('decl', 'DOCTYPE')]),
+ ('<!DOCTYPE ', [('decl', 'DOCTYPE ')]),
+ ('<!DOCTYPE html', [('decl', 'DOCTYPE html')]),
+ ('<!DOCTYPE html ', [('decl', 'DOCTYPE html ')]),
+ ('<!DOCTYPE html PUBLIC', [('decl', 'DOCTYPE html PUBLIC')]),
+ ('<!DOCTYPE html PUBLIC "foo', [('decl', 'DOCTYPE html PUBLIC
"foo')]),
+ ('<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN" "foo',
+ [('decl', 'DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN"
"foo')]),
+ ]
+ for html, expected in data:
+ self._run_check(html, expected)
+
+ def test_bogus_comments(self):
+ html = ('<!ELEMENT br EMPTY>'
+ '<! not really a comment >'
'<! not a comment either -->'
'<! -- close enough -->'
'<!><!<-- this was an empty comment>'
'<!!! another bogus comment !!!>')
expected = [
+ ('comment', 'ELEMENT br EMPTY'),
('comment', ' not really a comment '),
('comment', ' not a comment either --'),
('comment', ' -- close enough --'),
@@ -598,6 +649,26 @@ def test_convert_charrefs_dropped_text(self):
('endtag', 'a'), ('data', ' bar & baz')]
)
+ @support.requires_resource('cpu')
+ def test_eof_no_quadratic_complexity(self):
+ # Each of these examples used to take about an hour.
+ # Now they take a fraction of a second.
+ def check(source):
+ parser = html.parser.HTMLParser()
+ parser.feed(source)
+ parser.close()
+ n = 120_000
+ check("<a " * n)
+ check("<a a=" * n)
+ check("</a " * 14 * n)
+ check("</a a=" * 11 * n)
+ check("<!--" * 4 * n)
+ check("<!" * 60 * n)
+ check("<?" * 19 * n)
+ check("</$" * 15 * n)
+ check("<