From 8d810467dd95a2cb7e34fa83324dc07d35801a04 Mon Sep 17 00:00:00 2001
From: Anish Sarkar <104695310+AnishSarkar22@users.noreply.github.com>
Date: Tue, 7 Apr 2026 05:57:13 +0530
Subject: [PATCH] refactor: add support for XHTML file conversion to markdown
 in document processors

---
 .../app/tasks/document_processors/_direct_converters.py      | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/surfsense_backend/app/tasks/document_processors/_direct_converters.py b/surfsense_backend/app/tasks/document_processors/_direct_converters.py
index b1a69ef4f..bbff4838e 100644
--- a/surfsense_backend/app/tasks/document_processors/_direct_converters.py
+++ b/surfsense_backend/app/tasks/document_processors/_direct_converters.py
@@ -4,8 +4,8 @@ Lossless file-to-markdown converters for text-based formats.
 These converters handle file types that can be faithfully represented as
 markdown without any external ETL/OCR service:
 
-- CSV / TSV  → markdown table  (stdlib ``csv``)
-- HTML / HTM → markdown        (``markdownify``)
+- CSV / TSV          → markdown table  (stdlib ``csv``)
+- HTML / HTM / XHTML → markdown        (``markdownify``)
 """
 
 from __future__ import annotations
@@ -73,6 +73,7 @@ _CONVERTER_MAP: dict[str, Callable[..., str]] = {
     ".tsv": tsv_to_markdown,
     ".html": html_to_markdown,
     ".htm": html_to_markdown,
+    ".xhtml": html_to_markdown,
 }