From 9043edabc7e2f0dd655146e0a4571e2a0b2906af Mon Sep 17 00:00:00 2001
From: Serhiy Storchaka <storchaka@gmail.com>
Date: Fri, 13 Jun 2025 19:57:48 +0300
Subject: [PATCH] gh-135462: Fix quadratic complexity in processing special
 input in HTMLParser (GH-135464)

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)

Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
---
 Lib/html/parser.py                                                       |   41 +++++---
 Lib/test/test_htmlparser.py                                              |   51 +++++++---
 Misc/NEWS.d/next/Security/2025-06-13-15-55-22.gh-issue-135462.KBeJpc.rst |    4 
 3 files changed, 74 insertions(+), 22 deletions(-)
 create mode 100644 Misc/NEWS.d/next/Security/2025-06-13-15-55-22.gh-issue-135462.KBeJpc.rst

Index: Python-3.11.13/Lib/html/parser.py
===================================================================
--- Python-3.11.13.orig/Lib/html/parser.py	2025-07-02 18:12:07.084569398 +0200
+++ Python-3.11.13/Lib/html/parser.py	2025-07-02 18:12:12.582519793 +0200
@@ -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 @@
                     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 @@
                 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
+                    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:
-                        k += 1
-                    if self.convert_charrefs and not self.cdata_elem:
-                        self.handle_data(unescape(rawdata[i:k]))
-                    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)
Index: Python-3.11.13/Lib/test/test_htmlparser.py
===================================================================
--- Python-3.11.13.orig/Lib/test/test_htmlparser.py	2025-07-02 18:12:08.523658593 +0200
+++ Python-3.11.13/Lib/test/test_htmlparser.py	2025-07-02 18:13:32.674943007 +0200
@@ -4,6 +4,8 @@
 import pprint
 import unittest
 
+from test import support
+
 
 class EventCollector(html.parser.HTMLParser):
 
@@ -391,28 +393,34 @@
                             ('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')])])
@@ -549,8 +557,9 @@
             ('comment', ' -- close enough --'),
             ('comment', ''),
             ('comment', '<-- this was an empty comment'),
-            ('comment', '!! another bogus comment !!!'),
+            ('comment', '!! another bogus comment !!!')
         ]
+
         self._run_check(html, expected)
 
     def test_broken_condcoms(self):
@@ -598,6 +607,26 @@
              ('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("<![CDATA[" * 9 * n)
+        check("<!doctype" * 35 * n)
+
 
 class AttributesTestCase(TestCaseBase):
 
Index: Python-3.11.13/Misc/NEWS.d/next/Security/2025-06-13-15-55-22.gh-issue-135462.KBeJpc.rst
===================================================================
--- /dev/null	1970-01-01 00:00:00.000000000 +0000
+++ Python-3.11.13/Misc/NEWS.d/next/Security/2025-06-13-15-55-22.gh-issue-135462.KBeJpc.rst	2025-07-02 18:12:12.583386736 +0200
@@ -0,0 +1,4 @@
+Fix quadratic complexity in processing specially crafted input in
+:class:`html.parser.HTMLParser`. End-of-file errors are now handled according
+to the HTML5 specs -- comments and declarations are automatically closed,
+tags are ignored.