From 82018658211df6aa2a3f6e891dd1a190b9b101ae Mon Sep 17 00:00:00 2001
From: Aris Katsikaridis <arisk@transifex.com>
Date: Wed, 23 Oct 2024 19:20:55 +0300
Subject: [PATCH] Read and write file in binary mode to remove BOM (Byte Order
 Mark) bytes

---
 openformats/formats/docx.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/openformats/formats/docx.py b/openformats/formats/docx.py
index 9f20c465..faee4683 100644
--- a/openformats/formats/docx.py
+++ b/openformats/formats/docx.py
@@ -127,6 +127,10 @@ def get_document(self):
             with io.open(self.__document_path, 'r') as f:
                 self.__document = f.read()
 
+            if self.__document.startswith("\ufeff"):
+                # Remove BOM                
+                self.__document = self.__document.replace("\ufeff", "")
+
         return self.__document
 
     def set_document(self, document):