feat: add escaping_underscores option to markdown export (#135)

feat: add escaping_underscores option to markdown

BREAKING CHANGE: export to text no longer escapes underscores.

Add `escaping_underscores` option to `export_to_markdown().
Set default value to `escaping_underscores` to True.

Signed-off-by: Vdaleke <[email protected]>

Author: Vdaleke

docling_core/types/doc/document.py

@@ -1995,6 +1995,7 @@ def save_as_markdown(
         to_element: int = sys.maxsize,
         labels: set[DocItemLabel] = DEFAULT_EXPORT_LABELS,
         strict_text: bool = False,
+        escaping_underscores: bool = True,
         image_placeholder: str = "<!-- image -->",
         image_mode: ImageRefMode = ImageRefMode.PLACEHOLDER,
         indent: int = 4,
@@ -2017,6 +2018,7 @@ def save_as_markdown(
             to_element=to_element,
             labels=labels,
             strict_text=strict_text,
+            escaping_underscores=escaping_underscores,
             image_placeholder=image_placeholder,
             image_mode=image_mode,
             indent=indent,
@@ -2034,6 +2036,7 @@ def export_to_markdown(  # noqa: C901
         to_element: int = sys.maxsize,
         labels: set[DocItemLabel] = DEFAULT_EXPORT_LABELS,
         strict_text: bool = False,
+        escaping_underscores: bool = True,
         image_placeholder: str = "<!-- image -->",
         image_mode: ImageRefMode = ImageRefMode.PLACEHOLDER,
         indent: int = 4,
@@ -2059,6 +2062,9 @@ def export_to_markdown(  # noqa: C901
         :param strict_text: bool: Whether to only include the text content
             of the document. (Default value = False).
         :type strict_text: bool = False
+        :param escaping_underscores: bool: Whether to escape underscores in the
+            text content of the document. (Default value = True).
+        :type escaping_underscores: bool = True
         :param image_placeholder: The placeholder to include to position
             images in the markdown. (Default value = "\<!-- image --\>").
         :type image_placeholder: str = "<!-- image -->"
@@ -2227,7 +2233,8 @@ def escape_underscores(text):
 
             return "".join(parts)
 
-        mdtext = escape_underscores(mdtext)
+        if escaping_underscores:
+            mdtext = escape_underscores(mdtext)
 
         return mdtext
 
@@ -2245,6 +2252,7 @@ def export_to_text(  # noqa: C901
             to_element,
             labels,
             strict_text=True,
+            escaping_underscores=False,
             image_placeholder="",
         )