From 10ec265a444de13dad0d796c8bb5ca93380d9e9d Mon Sep 17 00:00:00 2001
From: LUIS NOVO <lfnovo@gmail.com>
Date: Thu, 24 Oct 2024 13:24:39 -0300
Subject: [PATCH] fix pdf encoding

---
 open_notebook/graphs/content_process.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/open_notebook/graphs/content_process.py b/open_notebook/graphs/content_process.py
index 9534db0..2a8b9c3 100644
--- a/open_notebook/graphs/content_process.py
+++ b/open_notebook/graphs/content_process.py
@@ -1,4 +1,5 @@
 import re
+import unicodedata
 
 import fitz  # type: ignore
 import magic
@@ -68,7 +69,8 @@ def _extract_text_from_pdf(pdf_path):
     for page in doc:
         text += page.get_text()
     doc.close()
-    return text
+    normalized_content = unicodedata.normalize("NFKD", text)
+    return normalized_content
 
 
 def extract_pdf(state: SourceState):