Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 10 additions & 1 deletion packages/markitdown/src/markitdown/converters/_docx_converter.py
Original file line number Diff line number Diff line change
Expand Up @@ -75,7 +75,16 @@ def convert(
_dependency_exc_info[2]
)

style_map = kwargs.get("style_map", None)
# Default style map preserves underline formatting via HTML <u> tags,
# since Markdown has no native underline syntax. User-supplied style_map
# is appended so its rules take precedence over the defaults.
default_style_map = "u => u"
user_style_map = kwargs.get("style_map", None)
style_map = (
default_style_map + "\n" + user_style_map
if user_style_map
else default_style_map
)
pre_process_stream = pre_process_docx(file_stream)
return self._html_converter.convert_string(
mammoth.convert_to_html(pre_process_stream, style_map=style_map).value,
Expand Down
10 changes: 10 additions & 0 deletions packages/markitdown/src/markitdown/converters/_markdownify.py
Original file line number Diff line number Diff line change
Expand Up @@ -122,5 +122,15 @@ def convert_input(
return "[x] " if el.has_attr("checked") else "[ ] "
return ""

def convert_u(
self,
el: Any,
text: str,
convert_as_inline: Optional[bool] = False,
**kwargs,
) -> str:
"""Preserve underline formatting using HTML <u> tags (Markdown has no underline syntax)."""
return "<u>%s</u>" % text

def convert_soup(self, soup: Any) -> str:
return super().convert_soup(soup) # type: ignore