From a01c59b91a8d3dcf2672936c462db4fa3f73bcdd Mon Sep 17 00:00:00 2001
From: Maksym Lysak <mly@zurich.ibm.com>
Date: Fri, 25 Oct 2024 11:19:52 +0200
Subject: [PATCH] Escaping underscore characters in md export

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
---
 docling_core/types/doc/document.py | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/docling_core/types/doc/document.py b/docling_core/types/doc/document.py
index 50a4e77..f1f249b 100644
--- a/docling_core/types/doc/document.py
+++ b/docling_core/types/doc/document.py
@@ -1291,6 +1291,17 @@ def export_to_markdown(  # noqa: C901
         mdtext = re.sub(
             r"\n\n\n+", "\n\n", mdtext
         )  # remove cases of double or more empty lines.
+
+        # Our export markdown doesn't contain any emphasis styling:
+        # Bold, Italic, or Bold-Italic
+        # Hence, any underscore that we print into Markdown is coming from document text
+        # That means we need to escape it, to properly reflect content in the markdown
+        def escape_underscores(text):
+            # Replace "_" with "\_" only if it's not already escaped
+            escaped_text = re.sub(r'(?<!\\)_', r'\_', text)
+            return escaped_text
+        mdtext = escape_underscores(mdtext)
+
         return mdtext
 
     def export_to_text(  # noqa: C901