From 0472c89b2651c12b8f4751fd8c5e59675a94182b Mon Sep 17 00:00:00 2001
From: Coenraad <coenraad@wish.org.za>
Date: Sat, 1 Apr 2023 14:16:36 +0200
Subject: [PATCH] Consolidate the unicode blocks and expand to include dingbats
 and Japanese outdoor signage emojis. An extensive search showed no official
 language symbols in this range. Consider using UnicodeCharacterTokenizer or
 tf.strings.unicode_encode and decode.

---
 trust_and_safety_models/nsfw/nsfw_text.py | 13 ++-----------
 1 file changed, 2 insertions(+), 11 deletions(-)

diff --git a/trust_and_safety_models/nsfw/nsfw_text.py b/trust_and_safety_models/nsfw/nsfw_text.py
index 980fc8fd4..4aeec332a 100644
--- a/trust_and_safety_models/nsfw/nsfw_text.py
+++ b/trust_and_safety_models/nsfw/nsfw_text.py
@@ -40,17 +40,8 @@ REGEX_PATTERNS = [
 
 EMOJI_PATTERN = re.compile(
     "(["
-    "\U0001F1E0-\U0001F1FF"
-    "\U0001F300-\U0001F5FF"
-    "\U0001F600-\U0001F64F"
-    "\U0001F680-\U0001F6FF"
-    "\U0001F700-\U0001F77F"
-    "\U0001F780-\U0001F7FF"
-    "\U0001F800-\U0001F8FF"
-    "\U0001F900-\U0001F9FF"
-    "\U0001FA00-\U0001FA6F"
-    "\U0001FA70-\U0001FAFF"
-    "\U00002702-\U000027B0"
+    "\U00002600-\U000027BF"
+    "\U0001F000-\U0001FAFF"
     "])"
   )