fix(docx): preserve underlined text

packages/markitdown/src/markitdown/converters/_docx_converter.py

@@ -27,6 +27,8 @@
 
 ACCEPTED_FILE_EXTENSIONS = [".docx"]
 
+_UNDERLINE_STYLE_MAP = "u => u"
+
 
 class DocxConverter(HtmlConverter):
     """
@@ -76,6 +78,10 @@ def convert(
             )
 
         style_map = kwargs.get("style_map", None)
+        if style_map:
+            style_map = f"{style_map}\n{_UNDERLINE_STYLE_MAP}"
+        else:
+            style_map = _UNDERLINE_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,

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

@@ -122,5 +122,17 @@ 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:
+        prefix, suffix, text = markdownify.chomp(text)  # type: ignore
+        if not text:
+            return ""
+        return f"{prefix}<u>{text}</u>{suffix}"
+
     def convert_soup(self, soup: Any) -> str:
         return super().convert_soup(soup)  # type: ignore

packages/markitdown/tests/test_module_misc.py

@@ -3,6 +3,7 @@
 import os
 import re
 import shutil
+import zipfile
 import pytest
 from unittest.mock import MagicMock
 
@@ -261,6 +262,42 @@ def test_docx_comments() -> None:
     validate_strings(result, DOCX_COMMENT_TEST_STRINGS)
 
 
+def test_docx_underlined_text_is_preserved(tmp_path) -> None:
+    docx_file = tmp_path / "underlined.docx"
+    document_xml = """<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
+  <w:body>
+    <w:p>
+      <w:r><w:t>plain </w:t></w:r>
+      <w:r><w:rPr><w:u w:val="single"/></w:rPr><w:t>underlined</w:t></w:r>
+    </w:p>
+  </w:body>
+</w:document>"""
+
+    with zipfile.ZipFile(docx_file, "w") as archive:
+        archive.writestr(
+            "[Content_Types].xml",
+            """<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">
+  <Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/>
+  <Default Extension="xml" ContentType="application/xml"/>
+  <Override PartName="/word/document.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"/>
+</Types>""",
+        )
+        archive.writestr(
+            "_rels/.rels",
+            """<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
+  <Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="word/document.xml"/>
+</Relationships>""",
+        )
+        archive.writestr("word/document.xml", document_xml)
+
+    result = MarkItDown().convert(str(docx_file))
+
+    assert "plain <u>underlined</u>" in result.text_content
+
+
 def test_docx_equations() -> None:
     markitdown = MarkItDown()
     docx_file = os.path.join(TEST_FILES_DIR, "equations.docx")