From ddbf35dacc674eb7eafc3868be65463daca60e55 Mon Sep 17 00:00:00 2001
From: David King <dking@redhat.com>
Date: Mon, 30 Mar 2026 16:26:49 +0100
Subject: [PATCH] Fix CVE-2025-69534 (RHEL-153747)

Resolves: RHEL-153747
---
 ...on-markdown-3.3.4-fix-CVE-2025-69534.patch | 512 ++++++++++++++++++
 python-markdown.spec                          |   7 +-
 2 files changed, 518 insertions(+), 1 deletion(-)
 create mode 100644 python-markdown-3.3.4-fix-CVE-2025-69534.patch

diff --git a/python-markdown-3.3.4-fix-CVE-2025-69534.patch b/python-markdown-3.3.4-fix-CVE-2025-69534.patch
new file mode 100644
index 0000000..823a138
--- /dev/null
+++ b/python-markdown-3.3.4-fix-CVE-2025-69534.patch
@@ -0,0 +1,512 @@
+From 3cc003e8693e50112189e9cd1b3116aa4c9003c4 Mon Sep 17 00:00:00 2001
+From: Waylan Limberg <waylan.limberg@icloud.com>
+Date: Wed, 18 Jun 2025 10:29:03 -0400
+Subject: [PATCH 1/3] Ensure incomplete markup declaration in raw HTML doesn't
+ crash parser.
+
+See Python bug report at gh-77057 for details. Until we drop support for
+Python < 3.13 (where this was fixed upstream), we need to avoid the
+unwanted error by checking for it explicitly. Fixes #1534.
+---
+ markdown/extensions/md_in_html.py            | 4 ++++
+ markdown/htmlparser.py                       | 4 ++++
+ tests/test_syntax/blocks/test_html_blocks.py | 7 +++++++
+ 3 files changed, 15 insertions(+)
+
+diff --git a/markdown/extensions/md_in_html.py b/markdown/extensions/md_in_html.py
+index 86cf00d..f95406e 100644
+--- a/markdown/extensions/md_in_html.py
++++ b/markdown/extensions/md_in_html.py
+@@ -218,6 +218,10 @@ class HTMLExtractorExtra(HTMLExtractor):
+ 
+     def parse_html_declaration(self, i):
+         if self.at_line_start() or self.intail or self.mdstack:
++            if self.rawdata[i:i+3] == '<![' and not self.rawdata[i:i+9] == '<![CDATA[':
++                # We have encountered the bug in #1534 (Python bug `gh-77057`).
++                # Provide an override until we drop support for Python < 3.13.
++                return self.parse_bogus_comment(i)
+             # The same override exists in HTMLExtractor without the check
+             # for mdstack. Therefore, use HTMLExtractor's parent instead.
+             return super(HTMLExtractor, self).parse_html_declaration(i)
+diff --git a/markdown/htmlparser.py b/markdown/htmlparser.py
+index c08856a..431505c 100644
+--- a/markdown/htmlparser.py
++++ b/markdown/htmlparser.py
+@@ -256,6 +256,10 @@ class HTMLExtractor(htmlparser.HTMLParser):
+ 
+     def parse_html_declaration(self, i):
+         if self.at_line_start() or self.intail:
++            if self.rawdata[i:i+3] == '<![' and not self.rawdata[i:i+9] == '<![CDATA[':
++                # We have encountered the bug in #1534 (Python bug `gh-77057`).
++                # Provide an override until we drop support for Python < 3.13.
++                return self.parse_bogus_comment(i)
+             return super().parse_html_declaration(i)
+         # This is not the beginning of a raw block so treat as plain data
+         # and avoid consuming any tags which may follow (see #1066).
+diff --git a/tests/test_syntax/blocks/test_html_blocks.py b/tests/test_syntax/blocks/test_html_blocks.py
+index 0ee47b6..76d21af 100644
+--- a/tests/test_syntax/blocks/test_html_blocks.py
++++ b/tests/test_syntax/blocks/test_html_blocks.py
+@@ -1275,6 +1275,13 @@ class TestHTMLBlocks(TestCase):
+             )
+         )
+ 
++    def test_not_actually_cdata(self):
++        # Ensure bug reported in #1534 is avoided.
++        self.assertMarkdownRenders(
++            '<![',
++            '<p>&lt;![</p>'
++        )
++
+     def test_raw_cdata_code_span(self):
+         self.assertMarkdownRenders(
+             self.dedent(
+-- 
+2.54.0
+
+
+From 1cc3f662b7bafe526e1a2fe72fff1bb7f784e346 Mon Sep 17 00:00:00 2001
+From: Isaac Muse <faceless.shop@gmail.com>
+Date: Thu, 19 Jun 2025 09:46:13 -0600
+Subject: [PATCH 2/3] Fixes for Python 3.14
+
+- Fix codecs deprecation
+- Fix issue with unclosed `<![`
+- Fix issue with unclosed HTML tag `<foo`
+- Fix issue with unclosed comments
+- Add tests which run on the Python 3.14 beta which should automatically update after release
+
+Fixes #1537
+---
+ markdown/__main__.py              |  3 +--
+ markdown/core.py                  |  2 +-
+ markdown/extensions/md_in_html.py | 10 +++++++---
+ markdown/htmlparser.py            | 26 +++++++++++++++++++++++---
+ 6 files changed, 50 insertions(+), 16 deletions(-)
+
+diff --git a/markdown/__main__.py b/markdown/__main__.py
+index 7d78b7e..64e3d58 100644
+--- a/markdown/__main__.py
++++ b/markdown/__main__.py
+@@ -21,7 +21,6 @@ License: BSD (see LICENSE.md for details).
+ 
+ import sys
+ import optparse
+-import codecs
+ import warnings
+ import markdown
+ try:
+@@ -100,7 +99,7 @@ def parse_options(args=None, values=None):
+ 
+     extension_configs = {}
+     if options.configfile:
+-        with codecs.open(
++        with open(
+             options.configfile, mode="r", encoding=options.encoding
+         ) as fp:
+             try:
+diff --git a/markdown/core.py b/markdown/core.py
+index 2f7f2d5..f86fd87 100644
+--- a/markdown/core.py
++++ b/markdown/core.py
+@@ -318,7 +318,7 @@ class Markdown:
+         # Read the source
+         if input:
+             if isinstance(input, str):
+-                input_file = codecs.open(input, mode="r", encoding=encoding)
++                input_file = open(input, mode="r", encoding=encoding)
+             else:
+                 input_file = codecs.getreader(encoding)(input)
+             text = input_file.read()
+diff --git a/markdown/extensions/md_in_html.py b/markdown/extensions/md_in_html.py
+index f95406e..4514836 100644
+--- a/markdown/extensions/md_in_html.py
++++ b/markdown/extensions/md_in_html.py
+@@ -221,9 +221,13 @@ class HTMLExtractorExtra(HTMLExtractor):
+             if self.rawdata[i:i+3] == '<![' and not self.rawdata[i:i+9] == '<![CDATA[':
+                 # We have encountered the bug in #1534 (Python bug `gh-77057`).
+                 # Provide an override until we drop support for Python < 3.13.
+-                return self.parse_bogus_comment(i)
+-            # The same override exists in HTMLExtractor without the check
+-            # for mdstack. Therefore, use HTMLExtractor's parent instead.
++                result = self.parse_bogus_comment(i)
++                if result == -1:
++                    self.handle_data(self.rawdata[i:i + 1])
++                    return i + 1
++                return result
++            # The same override exists in `HTMLExtractor` without the check
++            # for `mdstack`. Therefore, use parent of `HTMLExtractor` instead.
+             return super(HTMLExtractor, self).parse_html_declaration(i)
+         # This is not the beginning of a raw block so treat as plain data
+         # and avoid consuming any tags which may follow (see #1066).
+diff --git a/markdown/htmlparser.py b/markdown/htmlparser.py
+index 431505c..e9fe1e4 100644
+--- a/markdown/htmlparser.py
++++ b/markdown/htmlparser.py
+@@ -76,6 +76,8 @@ class HTMLExtractor(htmlparser.HTMLParser):
+         # Block tags that should contain no content (self closing)
+         self.empty_tags = set(['hr'])
+ 
++        self.override_comment_update = False
++
+         # This calls self.reset
+         super().__init__(*args, **kwargs)
+         self.md = md
+@@ -233,9 +235,22 @@ class HTMLExtractor(htmlparser.HTMLParser):
+     def handle_entityref(self, name):
+         self.handle_empty_tag('&{};'.format(name), is_block=False)
+ 
+-    def handle_comment(self, data):
++    def handle_comment(self, data: str):
++        # Check if the comment is unclosed, if so, we need to override position
++        i = self.line_offset + self.offset + len(data) + 4
++        if self.rawdata[i:i + 3] != '-->':
++            self.handle_data('<')
++            self.override_comment_update = True
++            return
+         self.handle_empty_tag('<!--{}-->'.format(data), is_block=True)
+ 
++    def updatepos(self, i: int, j: int) -> int:
++        if self.override_comment_update:
++            self.override_comment_update = False
++            i = 0
++            j = 1
++        return super().updatepos(i, j)
++
+     def handle_decl(self, data):
+         self.handle_empty_tag('<!{}>'.format(data), is_block=True)
+ 
+@@ -259,7 +274,11 @@ class HTMLExtractor(htmlparser.HTMLParser):
+             if self.rawdata[i:i+3] == '<![' and not self.rawdata[i:i+9] == '<![CDATA[':
+                 # We have encountered the bug in #1534 (Python bug `gh-77057`).
+                 # Provide an override until we drop support for Python < 3.13.
+-                return self.parse_bogus_comment(i)
++                result = self.parse_bogus_comment(i)
++                if result == -1:
++                    self.handle_data(self.rawdata[i:i + 1])
++                    return i + 1
++                return result
+             return super().parse_html_declaration(i)
+         # This is not the beginning of a raw block so treat as plain data
+         # and avoid consuming any tags which may follow (see #1066).
+@@ -280,7 +299,8 @@ class HTMLExtractor(htmlparser.HTMLParser):
+         self.__starttag_text = None
+         endpos = self.check_for_whole_start_tag(i)
+         if endpos < 0:
+-            return endpos
++            self.handle_data(self.rawdata[i:i + 1])
++            return i + 1
+         rawdata = self.rawdata
+         self.__starttag_text = rawdata[i:endpos]
+ 
+-- 
+2.54.0
+
+
+From 3ed20571a3b27f865c181419eb0f50b15e142927 Mon Sep 17 00:00:00 2001
+From: David King <dking@redhat.com>
+Date: Tue, 28 Apr 2026 16:57:49 +0100
+Subject: [PATCH 3/3] Backport upstream 3.10.1 to 3.10.2 fixes
+
+---
+ markdown/htmlparser.py                       | 92 +++++++++++++++----
+ markdown/inlinepatterns.py                   |  8 +-
+ tests/test_syntax/blocks/test_html_blocks.py | 97 ++++++++++++++++++--
+ 3 files changed, 172 insertions(+), 25 deletions(-)
+
+diff --git a/markdown/htmlparser.py b/markdown/htmlparser.py
+index e9fe1e4..9cdc05f 100644
+--- a/markdown/htmlparser.py
++++ b/markdown/htmlparser.py
+@@ -24,6 +24,9 @@ import importlib
+ import sys
+ 
+ 
++# Included for versions which do not have current comment fix
++commentclose = re.compile(r'--!?>')
++
+ # Import a copy of the html.parser lib as `htmlparser` so we can monkeypatch it.
+ # Users can still do `from html import parser` and get the default behavior.
+ spec = importlib.util.find_spec('html.parser')
+@@ -31,6 +34,12 @@ htmlparser = importlib.util.module_from_spec(spec)
+ spec.loader.exec_module(htmlparser)
+ sys.modules['htmlparser'] = htmlparser
+ 
++# This is a hack. We are sneaking in `</>` so we can capture it without the HTML parser
++# throwing it away. When we see it, we will process it as data.
++htmlparser.starttagopen = re.compile('<[a-zA-Z]|</>')
++
++htmlparser.endtagopen = re.compile('</[a-zA-Z]?')
++
+ # Monkeypatch HTMLParser to only accept `?>` to close Processing Instructions.
+ htmlparser.piclose = re.compile(r'\?>')
+ # Monkeypatch HTMLParser to only recognize entity references with a closing semicolon.
+@@ -55,12 +64,52 @@ htmlparser.locatestarttagend_tolerant = re.compile(r"""
+    )?
+   \s*                                 # trailing whitespace
+ """, re.VERBOSE)
++# Monkeypatch `locatetagend` if it exists (Python 3.14+) to also reject backticks.
++if hasattr(htmlparser, 'locatetagend'):
++    htmlparser.locatetagend = re.compile(r"""
++      [a-zA-Z][^`\t\n\r\f />\x00]*       # tag name <= added backtick here
++      [\t\n\r\f /]*                       # optional whitespace before attribute name
++      (?:(?<=['"\t\n\r\f /])[^`\t\n\r\f />][^`\t\n\r\f /=>]*  # attribute name <= added backtick here
++        (?:[\t\n\r\f ]*=[\t\n\r\f ]*      # value indicator
++          (?:'[^']*'                      # LITA-enclosed value
++            |"[^"]*"                      # LIT-enclosed value
++            |(?!['"])[^`>\t\n\r\f ]*      # bare value <= added backtick here
++           )
++         )?
++        [\t\n\r\f /]*                     # possibly followed by a space
++       )*
++       >?
++    """, re.VERBOSE)
+ 
+ # Match a blank line at the start of a block of text (two newlines).
+ # The newlines may be preceded by additional whitespace.
+ blank_line_re = re.compile(r'^([ ]*\n){2}')
+ 
+ 
++class _HTMLParser(htmlparser.HTMLParser):
++    """Handle special start and end tags."""
++
++    def parse_endtag(self, i):
++        start = self.rawdata[i:i+3]
++        c = ord(start[-1])
++        if len(start) < 3 or not (65 <= c <= 90 or 97 <= c <= 122):
++            self.handle_data(self.rawdata[i:i + 2])
++            return i + 2
++        return super().parse_endtag(i)
++
++    def parse_starttag(self, i):  # pragma: no cover
++        # Treat `</>` as normal data as it is not a real tag.
++        if self.rawdata[i:i + 3] == '</>':
++            self.handle_data(self.rawdata[i:i + 3])
++            return i + 3
++
++        return super().parse_starttag(i)
++
++
++# Overwrite our custom one for people like MkDocs that pull it in
++htmlparser.HTMLParser = _HTMLParser
++
++
+ class HTMLExtractor(htmlparser.HTMLParser):
+     """
+     Extract raw HTML from text.
+@@ -76,8 +125,6 @@ class HTMLExtractor(htmlparser.HTMLParser):
+         # Block tags that should contain no content (self closing)
+         self.empty_tags = set(['hr'])
+ 
+-        self.override_comment_update = False
+-
+         # This calls self.reset
+         super().__init__(*args, **kwargs)
+         self.md = md
+@@ -235,22 +282,9 @@ class HTMLExtractor(htmlparser.HTMLParser):
+     def handle_entityref(self, name):
+         self.handle_empty_tag('&{};'.format(name), is_block=False)
+ 
+-    def handle_comment(self, data: str):
+-        # Check if the comment is unclosed, if so, we need to override position
+-        i = self.line_offset + self.offset + len(data) + 4
+-        if self.rawdata[i:i + 3] != '-->':
+-            self.handle_data('<')
+-            self.override_comment_update = True
+-            return
++    def handle_comment(self, data):
+         self.handle_empty_tag('<!--{}-->'.format(data), is_block=True)
+ 
+-    def updatepos(self, i: int, j: int) -> int:
+-        if self.override_comment_update:
+-            self.override_comment_update = False
+-            i = 0
+-            j = 1
+-        return super().updatepos(i, j)
+-
+     def handle_decl(self, data):
+         self.handle_empty_tag('<!{}>'.format(data), is_block=True)
+ 
+@@ -269,6 +303,18 @@ class HTMLExtractor(htmlparser.HTMLParser):
+         self.handle_data('<?')
+         return i + 2
+ 
++    def parse_comment(self, i, report=True):
++        rawdata = self.rawdata
++        assert rawdata.startswith('<!--', i), 'unexpected call to parse_comment()'
++        match = commentclose.search(rawdata, i+4)
++        if not match:
++            self.handle_data('<')
++            return i + 1
++        if report:
++            j = match.start()
++            self.handle_comment(rawdata[i+4: j])
++        return match.end()
++
+     def parse_html_declaration(self, i):
+         if self.at_line_start() or self.intail:
+             if self.rawdata[i:i+3] == '<![' and not self.rawdata[i:i+9] == '<![CDATA[':
+@@ -285,6 +331,15 @@ class HTMLExtractor(htmlparser.HTMLParser):
+         self.handle_data('<!')
+         return i + 2
+ 
++    def parse_bogus_comment(self, i, report=0):
++        # Override the default behavior so that bogus comments get passed
++        # through unaltered by setting `report` to `0` (see #1425).
++        pos = super().parse_bogus_comment(i, report)
++        if pos == -1:  # pragma: no cover
++            return -1
++        self.handle_empty_tag(self.rawdata[i:pos], is_block=False)
++        return pos
++
+     # The rest has been copied from base class in standard lib to address #1036.
+     # As __startag_text is private, all references to it must be in this subclass.
+     # The last few lines of parse_starttag are reversed so that handle_starttag
+@@ -296,6 +351,11 @@ class HTMLExtractor(htmlparser.HTMLParser):
+         return self.__starttag_text
+ 
+     def parse_starttag(self, i):  # pragma: no cover
++        # Treat `</>` as normal data as it is not a real tag.
++        if self.rawdata[i:i + 3] == '</>':
++            self.handle_data(self.rawdata[i:i + 3])
++            return i + 3
++
+         self.__starttag_text = None
+         endpos = self.check_for_whole_start_tag(i)
+         if endpos < 0:
+diff --git a/markdown/inlinepatterns.py b/markdown/inlinepatterns.py
+index b0621a8..66a59d3 100644
+--- a/markdown/inlinepatterns.py
++++ b/markdown/inlinepatterns.py
+@@ -163,7 +163,13 @@ AUTOLINK_RE = r'<((?:[Ff]|[Hh][Tt])[Tt][Pp][Ss]?://[^<>]*)>'
+ AUTOMAIL_RE = r'<([^<> !]*@[^@<> ]*)>'
+ 
+ # <...>
+-HTML_RE = r'(<([a-zA-Z/][^<>]*|!--(?:(?!<!--|-->).)*--)>)'
++HTML_RE = (
++    r'(<(\/?[a-zA-Z][^<>@ ]*( [^<>]*)?|'
++    r'!--(?:(?!<!--|-->).)*--|'
++    r'[?](?:(?!<[?]|[?]>).)*[?]|'
++    r'!\[CDATA\[(?:(?!<!\[CDATA\[|\]\]>).)*\]\]'
++    ')>)'
++)
+ 
+ # "&#38;" (decimal) or "&#x26;" (hex) or "&amp;" (named)
+ ENTITY_RE = r'(&(?:\#[0-9]+|\#x[0-9a-fA-F]+|[a-zA-Z0-9]+);)'
+diff --git a/tests/test_syntax/blocks/test_html_blocks.py b/tests/test_syntax/blocks/test_html_blocks.py
+index 76d21af..2a5d5f4 100644
+--- a/tests/test_syntax/blocks/test_html_blocks.py
++++ b/tests/test_syntax/blocks/test_html_blocks.py
+@@ -782,16 +782,10 @@ class TestHTMLBlocks(TestCase):
+             '<!-- *foo* -->'
+         )
+ 
+-    # Note: this is a change in behavior for Python-Markdown, which does *not* match the reference
+-    # implementation. However, it does match the HTML5 spec. Declarations must start with either
+-    # `<!DOCTYPE` or `<![`. Anything else that starts with `<!` is a comment. According to the
+-    # HTML5 spec, a comment without the hyphens is a "bogus comment", but a comment nonetheless.
+-    # See https://www.w3.org/TR/html52/syntax.html#markup-declaration-open-state.
+-    # If we wanted to change this behavior, we could override `HTMLParser.parse_bogus_comment()`.
+     def test_bogus_comment(self):
+         self.assertMarkdownRenders(
+-            '<!*foo*>',
+-            '<!--*foo*-->'
++            '<!invalid>',
++            '<p>&lt;!invalid&gt;</p>'
+         )
+ 
+     def test_raw_multiline_comment(self):
+@@ -1624,3 +1618,90 @@ class TestHTMLBlocks(TestCase):
+         placeholder = md.htmlStash.get_placeholder(md.htmlStash.html_counter + 1)
+         result = md.postprocessors['raw_html'].run(placeholder)
+         self.assertEqual(placeholder, result)
++
++    def test_bogus_comment_endtag(self):
++        self.assertMarkdownRenders(
++            '</#invalid>',
++            '<p>&lt;/#invalid&gt;</p>'
++        )
++
++    def test_issue_1590(self):
++        """Test case with comments in table for issue #1590."""
++
++        self.assertMarkdownRenders(
++            self.dedent(
++                '''
++                <table>
++                <!--[if mso]>-->
++                <td>foo</td>
++                <!--<!endif]-->
++                <td>bar</td>
++                </table>
++                '''
++            ),
++            self.dedent(
++                '''
++                <table>
++                <!--[if mso]>-->
++                <td>foo</td>
++                <!--<!endif]-->
++                <td>bar</td>
++                </table>
++                '''
++            )
++        )
++
++    def test_stress_comment_handling(self):
++        """Stress test the comment handling."""
++
++        self.assertMarkdownRenders(
++            self.dedent(
++                '''
++                `</` <!-- `<!--[if mso]>` and <!-- </> and `<!--[if mso]>`
++
++                <!-- and <!-- `<!--[if mso]>` and </> `</` and `<!--[if mso]>`
++
++                <!-- Real comment -->
++
++                `<!--[if mso]>` `</` `<!--[if mso]>` and </> <!-- and <!--
++
++                </> `<!--[if mso]>` `</` <!--  and <!--  and `<!--[if mso]>`
++                '''
++            ),
++            self.dedent(
++                '''
++                <p><code>&lt;/</code> &lt;!-- <code>&lt;!--[if mso]&gt;</code> and &lt;!-- &lt;/&gt; and <code>&lt;!--[if mso]&gt;</code></p>
++                <p>&lt;!-- and &lt;!-- <code>&lt;!--[if mso]&gt;</code> and &lt;/&gt; <code>&lt;/</code> and <code>&lt;!--[if mso]&gt;</code></p>
++                <!-- Real comment -->
++                <p><code>&lt;!--[if mso]&gt;</code> <code>&lt;/</code> <code>&lt;!--[if mso]&gt;</code> and &lt;/&gt; &lt;!-- and &lt;!--</p>
++                <p>&lt;/&gt; <code>&lt;!--[if mso]&gt;</code> <code>&lt;/</code> &lt;!--  and &lt;!--  and <code>&lt;!--[if mso]&gt;</code></p>
++                '''  # noqa: E501
++            )
++        )
++
++    def test_unclosed_endtag(self):
++        """Ensure unclosed end tag does not have side effects."""
++
++        self.assertMarkdownRenders(
++            self.dedent(
++                '''
++                `</`
++
++                <div>
++                <!--[if mso]>-->
++                <p>foo</p>
++                <!--<!endif]-->
++                </div>
++                '''
++            ),
++            self.dedent(
++                '''
++                <p><code>&lt;/</code></p>
++                <div>
++                <!--[if mso]>-->
++                <p>foo</p>
++                <!--<!endif]-->
++                </div>
++                '''
++            )
++        )
+-- 
+2.54.0
+
diff --git a/python-markdown.spec b/python-markdown.spec
index 9957b8b..c4e4ac5 100644
--- a/python-markdown.spec
+++ b/python-markdown.spec
@@ -3,11 +3,13 @@
 
 Name:           python-%{pkgname}
 Version:        3.3.4
-Release:        4%{?dist}
+Release:        5%{?dist}
 Summary:        Markdown implementation in Python
 License:        BSD
 URL:            https://python-markdown.github.io/
 Source0:        %{pypi_source}
+# https://redhat.atlassian.net/browse/RHEL-153747
+Patch0:         python-markdown-3.3.4-fix-CVE-2025-69534.patch
 BuildArch:      noarch
 
 %description
@@ -65,6 +67,9 @@ PYTHONPATH=%{buildroot}%{python3_sitelib} \
 
 
 %changelog
+* Mon Mar 30 2026 David King <dking@redhat.com> - 3.3.4-5
+- Fix CVE-2025-69534 (RHEL-153747)
+
 * Tue Aug 10 2021 Mohan Boddu <mboddu@redhat.com> - 3.3.4-4
 - Rebuilt for IMA sigs, glibc 2.34, aarch64 flags
   Related: rhbz#1991688