fix: use file extension if filetype fails with PDF

Filetype library may not identify some files as PDF. Leverage the file extension as a simple solution. Signed-off-by: Cesar Berrospi Ramis <[email protected]>
DS4SD · Jan 28, 2025 · 6ca7daf · 6ca7daf
1 parent 5139b48
commit 6ca7daf
Showing 1 changed file with 2 additions and 0 deletions.
diff --git 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