Update preprocess.py

preprocess.py

@@ -25,7 +25,7 @@ def preprocess(legislation_dir="./legislation"):
         for filename in os.listdir(directory):
             if filename.endswith(".html"):
                 file_path = os.path.join(directory, filename)
-                with open(file_path, "r", encoding="utf-8") as f:
+                with open(file_path, "r", encoding="latin-1") as f:
                     soup = BeautifulSoup(f, "html.parser")
                     text = soup.get_text(separator=" ", strip=True)
                     documents.append(text)