From c9e1e6ef6fcabf061323d8a70177793cbaecb635 Mon Sep 17 00:00:00 2001
From: Pietro Martino Lugato <pmlugato@submit02.mit.edu>
Date: Wed, 25 Sep 2024 14:54:17 -0400
Subject: [PATCH] fix mailbox service to handle bad chars

---
 A2rchi/utils/mailbox.py | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/A2rchi/utils/mailbox.py b/A2rchi/utils/mailbox.py
index 6462a48..a64854b 100644
--- a/A2rchi/utils/mailbox.py
+++ b/A2rchi/utils/mailbox.py
@@ -5,6 +5,7 @@
 import email
 import imaplib
 import os
+import re
 
 ### DEFINITIONS
 # this constant defines an offset into the message description
@@ -184,11 +185,33 @@ def _get_fields(self, msg):
 
         body, body_html = self._get_email_body(msg)
         description = body if body else body_html
+        description = self._clear_text(description)
         print("BODY:")
         print(description)
 
         return sender, cc, subject, description
 
+    def _clear_text(self,string):
+        emoj = re.compile("["
+            u"\U0001F600-\U0001F64F"  # emoticons
+            u"\U0001F300-\U0001F5FF"  # symbols & pictographs
+            u"\U0001F680-\U0001F6FF"  # transport & map symbols
+            u"\U0001F1E0-\U0001F1FF"  # flags (iOS)
+            u"\U00002500-\U00002BEF"  # chinese char
+            u"\U00002702-\U000027B0"
+            u"\U000024C2-\U0001F251"
+            u"\U0001f926-\U0001f937"
+            u"\U00010000-\U0010ffff"
+            u"\u2640-\u2642" 
+            u"\u2600-\u2B55"
+            u"\u200d"
+            u"\u23cf"
+            u"\u23e9"
+            u"\u231a"
+            u"\ufe0f"  # dingbats
+            u"\u3030"
+                          "]+", re.UNICODE)
+        return re.sub(emoj, '', string)
 
     def _connect(self):
         """