From 76986d7b7331f34d35198068107b58e3dce4d18b Mon Sep 17 00:00:00 2001
From: Oliver Baer <75138893+mrwind-up-bird@users.noreply.github.com>
Date: Thu, 26 Feb 2026 15:18:01 +0100
Subject: [PATCH] fix(autofix): Unhandled encoding errors in text extraction

---
 app/services/extract.py | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/app/services/extract.py b/app/services/extract.py
index c606d24..27a48dc 100644
--- a/app/services/extract.py
+++ b/app/services/extract.py
@@ -23,7 +23,12 @@ def extract_text(filename: str, content: bytes) -> str:
         ValueError: If the file extension is not supported.
     """
     ext = Path(filename).suffix.lower()
-
+        try:
+            return content.decode("utf-8")
+        except UnicodeDecodeError:
+            # Fallback to latin-1 which can decode any byte sequence
+            # then attempt to detect and convert to proper encoding
+            return content.decode("latin-1", errors="replace")
     if ext in {".txt", ".md", ".csv"}:
         return content.decode("utf-8")