From 47c21a5edc038a90ff3b25829f52f5684dba3b6b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jo=C3=A3o?= <joao@0xcarbon.org>
Date: Thu, 9 Jan 2025 18:24:26 -0300
Subject: [PATCH] disabled auto file mime type detection, rely on extension

---
 docling/datamodel/document.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/docling/datamodel/document.py b/docling/datamodel/document.py
index 0483dc2a..0966de83 100644
--- a/docling/datamodel/document.py
+++ b/docling/datamodel/document.py
@@ -273,7 +273,8 @@ class _DocumentConversionInput(BaseModel):
         formats: list[InputFormat] = []
 
         if isinstance(obj, Path):
-            mime = filetype.guess_mime(str(obj))
+            # mime = filetype.guess_mime(str(obj))  # We're having too much conflicts with documents being worngly classified as ZIP
+            mime = None
             if mime is None:
                 ext = obj.suffix[1:]
                 mime = _DocumentConversionInput._mime_from_extension(ext)
@@ -359,7 +360,7 @@ class _DocumentConversionInput(BaseModel):
             mime = FormatToMimeType[InputFormat.PPTX][0]
         elif ext in FormatToExtensions[InputFormat.XLSX]:
             mime = FormatToMimeType[InputFormat.XLSX][0]
-            
+
         return mime
 
     @staticmethod