From f2313a6e0845db4ff3ebe2cd29c632db3d77dec7 Mon Sep 17 00:00:00 2001
From: henrynguyen0x <56329400+henrynguyen0x@users.noreply.github.com>
Date: Thu, 1 Dec 2022 15:19:56 +0000
Subject: [PATCH] Update encoding

Add encoding utf-8 for file to avoid charmap error
---
 main.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/main.py b/main.py
index c6cabac..bac8f92 100644
--- a/main.py
+++ b/main.py
@@ -58,7 +58,7 @@ def split_into_sentences(text):
 
 def get_book_sentences():
     """Get the book file, and tokenize it."""
-    text = open('caesar-and-christ.txt').read()
+    text = open('caesar-and-christ.txt', encoding = "utf-8").read()
     sentences = split_into_sentences(text)
     return sentences[5004:10000] # TODO: generalize this