From adf635348365f82daa64e3f879076a7baf71edc0 Mon Sep 17 00:00:00 2001
From: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
Date: Tue, 28 Jan 2025 19:03:54 +0100
Subject: [PATCH] fix: use file extension if filetype fails with PDF (#827)

Filetype library may not identify some files as PDF. Leverage the file extension
as a simple solution.

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
---
 docling/datamodel/document.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/docling/datamodel/document.py b/docling/datamodel/document.py
index a2a93aa3..e37541b7 100644
--- a/docling/datamodel/document.py
+++ b/docling/datamodel/document.py
@@ -352,6 +352,8 @@ def _mime_from_extension(ext):
             mime = FormatToMimeType[InputFormat.MD][0]
         elif ext in FormatToExtensions[InputFormat.JSON_DOCLING]:
             mime = FormatToMimeType[InputFormat.JSON_DOCLING][0]
+        elif ext in FormatToExtensions[InputFormat.PDF]:
+            mime = FormatToMimeType[InputFormat.PDF][0]
         return mime
 
     @staticmethod