Fixes for Python 3.14 and fixes for deprecations

- Fix codecs deprecation
- Fix issue with unclosed `<![`
- Fix issue with unclosed HTML tag `<foo`

Fixes #1537

Author: facelessuser

docs/changelog.md

@@ -9,6 +9,14 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 See the [Contributing Guide](contributing.md) for details.
 
+## Unreleased
+
+### Fixed
+
+* Fix `codecs` deprecation.
+* Fix issue with unclosed `<![` in Python 3.14.
+* Fix issue with unclosed HTML tag `<foo` and Python 3.14.
+
 ## [3.8.1] - 2025-06-18
 
 ### Fixed

markdown/__main__.py

@@ -21,7 +21,6 @@
 
 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:

markdown/core.py

@@ -417,7 +417,7 @@ def convertFile(
         # 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()

markdown/extensions/md_in_html.py

@@ -283,7 +283,10 @@ def parse_html_declaration(self, i: int) -> int:
             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
             # 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)

markdown/htmlparser.py

@@ -278,7 +278,11 @@ def parse_html_declaration(self, i: int) -> int:
             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).
@@ -313,7 +317,8 @@ def parse_starttag(self, i: int) -> int:  # pragma: no cover
         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]