[PATCH v1 2/2] Use html.escape() for fix_utf8_chars()

[Muhammad Rizki <kiizuha@gnuweeb.org>]

We found a bug when receiving email payload like `<text>`, `&reg`, and
more. Using double html.escape() will fix the bug for now.

Signed-off-by: Muhammad Rizki <kiizuha@gnuweeb.org>
Reported-by: Alviro Iskandar Setiawan <alviro.iskandar@gnuweeb.org>
---
 daemon/scraper/utils.py | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/daemon/scraper/utils.py b/daemon/scraper/utils.py
index 765468c..c428a33 100644
--- a/daemon/scraper/utils.py
+++ b/daemon/scraper/utils.py
@@ -14,6 +14,7 @@ import os
 import re
 import shutil
 import httpx
+import html
 
 
 def get_email_msg_id(mail):
@@ -218,12 +219,8 @@ def clean_up_after_send_patch(tmp):
 
 
 def fix_utf8_char(text: str):
-	return (
-		text.rstrip()
-		.replace("<", "&lt;")
-		.replace(">","&gt;")
-		.replace("�"," ")
-	)
+	text = text.rstrip().replace("�"," ")
+	return html.escape(html.escape(text))
 
 
 EMAIL_MSG_ID_PATTERN = r"<([^\<\>]+)>"
-- 
Muhammad Rizki