Updated markdownify dependency.

packages/markitdown/pyproject.toml

@@ -26,7 +26,7 @@ classifiers = [
 dependencies = [
   "beautifulsoup4",
   "requests",
-  "markdownify~=0.14.1",
+  "markdownify",
   "puremagic",
   "pathvalidate",
   "charset-normalizer",
@@ -78,11 +78,14 @@ extra-dependencies = [
 ]
 
 [tool.hatch.envs.types]
+features = ["all"]
 extra-dependencies = [
+  "openai",
   "mypy>=1.0.0",
 ]
+
 [tool.hatch.envs.types.scripts]
-check = "mypy --install-types --non-interactive {args:src/markitdown tests}"
+check = "mypy --install-types --non-interactive --ignore-missing-imports {args:src/markitdown tests}"
 
 [tool.coverage.run]
 source_pkgs = ["markitdown", "tests"]

packages/markitdown/src/markitdown/_exceptions.py

@@ -68,6 +68,9 @@ class FileConversionException(MarkItDownException):
             else:
                 message = f"File conversion failed after {len(attempts)} attempts:\n"
                 for attempt in attempts:
+                    if attempt.exc_info is None:
+                        message += " -  {type(attempt.converter).__name__} provided no execution info."
+                    else:
                         message += f" - {type(attempt.converter).__name__} threw {attempt.exc_info[0].__name__} with message: {attempt.exc_info[1]}\n"
 
         super().__init__(message)

packages/markitdown/src/markitdown/_stream_info.py

@@ -62,7 +62,8 @@ def _guess_stream_info_from_stream(
     # Add a guess purely based on the filename hint
     if filename_hint:
         try:
-            mimetype, _ = mimetypes.guess_file_type(filename_hint)
+            # Requires Python 3.13+
+            mimetype, _ = mimetypes.guess_file_type(filename_hint)  # type: ignore
         except AttributeError:
             mimetype, _ = mimetypes.guess_type(filename_hint)
 

packages/markitdown/src/markitdown/converters/_markdownify.py

@@ -1,7 +1,7 @@
 import re
 import markdownify
 
-from typing import Any
+from typing import Any, Optional
 from urllib.parse import quote, unquote, urlparse, urlunparse
 
 
@@ -20,7 +20,14 @@ class _CustomMarkdownify(markdownify.MarkdownConverter):
         # Explicitly cast options to the expected type if necessary
         super().__init__(**options)
 
-    def convert_hn(self, n: int, el: Any, text: str, convert_as_inline: bool) -> str:
+    def convert_hn(
+        self,
+        n: int,
+        el: Any,
+        text: str,
+        convert_as_inline: Optional[bool] = False,
+        **kwargs,
+    ) -> str:
         """Same as usual, but be sure to start with a new line"""
         if not convert_as_inline:
             if not re.search(r"^\n", text):
@@ -28,7 +35,13 @@ class _CustomMarkdownify(markdownify.MarkdownConverter):
 
         return super().convert_hn(n, el, text, convert_as_inline)  # type: ignore
 
-    def convert_a(self, el: Any, text: str, convert_as_inline: bool):
+    def convert_a(
+        self,
+        el: Any,
+        text: str,
+        convert_as_inline: Optional[bool] = False,
+        **kwargs,
+    ):
         """Same as usual converter, but removes Javascript links and escapes URIs."""
         prefix, suffix, text = markdownify.chomp(text)  # type: ignore
         if not text:
@@ -68,7 +81,13 @@ class _CustomMarkdownify(markdownify.MarkdownConverter):
             else text
         )
 
-    def convert_img(self, el: Any, text: str, convert_as_inline: bool) -> str:
+    def convert_img(
+        self,
+        el: Any,
+        text: str,
+        convert_as_inline: Optional[bool] = False,
+        **kwargs,
+    ) -> str:
         """Same as usual converter, but removes data URIs"""
 
         alt = el.attrs.get("alt", None) or ""