From fd058d2c78c92bc7c97e557e61fae3418fb9e170 Mon Sep 17 00:00:00 2001
From: ninya9k <originalcocaineninja@protonmail.com>
Date: Sun, 18 Jul 2021 04:59:06 +0000
Subject: [PATCH] regex word filters, optional case-sensitivity

---
 config.toml     |  3 +++
 website/chat.py | 11 +++++++----
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/config.toml b/config.toml
index c8dae7e..c4b16f7 100644
--- a/config.toml
+++ b/config.toml
@@ -11,9 +11,12 @@ host = "Broadcaster"
 anon = "Anonymous"
 
 [chat.filters]
+# prepend strings with "re:" for regular expressions
+# e.g. ban = ["re:\\bmelons?\\b", "re:(https?://)?([^.]+?\\.)*?example\\.com\\S*"]
 ban     = [] # block message & ban poster
 block   = [] # block message
 censor  = [] # censor word in message
+ignore_case = true
 tyranny = true # word filters don't apply to broadcaster
 
 [secret_club]
diff --git a/website/chat.py b/website/chat.py
index 697c145..696cc45 100644
--- a/website/chat.py
+++ b/website/chat.py
@@ -139,10 +139,13 @@ def _comment(text, token, c_response, c_ciphertext, nonce):
         reaction = None
         for key in ['censor', 'block', 'ban']:
             for word in filters[key]:
-                word = escape(word)    # escape for html
-                word = re.escape(word) # escape for regex
-                regex = r'\b{}\b'.format(word)
-                markup, n = re.subn(regex, '<b class="censored">[CENSORED]</b>', markup, flags=re.IGNORECASE)
+                word = escape(word) # escape for html
+                if word.startswith('re:'):
+                    regex = word[3:]
+                else:
+                    word = re.escape(word) # escape for regex
+                    regex = r'\b{}\b'.format(word)
+                markup, n = re.subn(regex, '<b class="censored">[CENSORED]</b>', markup, flags=re.IGNORECASE if filters['ignore_case'] else 0)
                 if n: reaction = key
         # enact consequences of word filters
         note = N_NONE