Able to now address Miku in Cyrillic, Kanji and both Kanas, incl. Japanese honorifics

bot/utils/core.py

@@ -40,13 +40,72 @@ async def is_miku_addressed(message) -> bool:
         except Exception as e:
             logger.warning(f"Could not fetch referenced message: {e}")
 
-    cleaned = message.content.strip()
-
-    return bool(re.search(
-        r'(?<![\w\(])(?:[^\w\s]{0,2}\s*)?miku(?:\s*[^\w\s]{0,2})?(?=,|\s*,|[!\.?\s]*$)',
-        cleaned,
-        re.IGNORECASE
-    ))
+    cleaned = message.content.strip().lower()
+    
+    # Base names for Miku in different scripts
+    base_names = [
+        'miku', 'мику', 'みく', 'ミク', '未来'
+    ]
+    
+    # Japanese honorifics - all scripts combined for simpler matching
+    honorifics_all_scripts = [
+        # Latin
+        'chan', 'san', 'kun', 'nyan', 'hime', 'tan', 'chin', 'heika', 
+        'denka', 'kakka', 'shi', 'chama', 'kyun', 'dono', 'sensei', 'senpai', 'jou',
+        # Hiragana
+        'ちゃん', 'さん', 'くん', 'にゃん', 'ひめ', 'たん', 'ちん', 'へいか',
+        'でんか', 'かっか', 'し', 'ちゃま', 'きゅん', 'どの', 'せんせい', 'せんぱい', 'じょう',
+        # Katakana
+        'チャン', 'サン', 'クン', 'ニャン', 'ヒメ', 'タン', 'チン', 'ヘイカ',
+        'デンカ', 'カッカ', 'シ', 'チャマ', 'キュン', 'ドノ', 'センセイ', 'センパイ', 'ジョウ',
+        # Cyrillic
+        'чан', 'сан', 'кун', 'ньян', 'химе', 'тан', 'чин', 'хэйка',
+        'дэнка', 'какка', 'си', 'чама', 'кюн', 'доно', 'сэнсэй', 'сэнпай', 'жо'
+    ]
+    
+    # Optional o- prefix in different scripts
+    o_prefixes = ['o-', 'о-', 'お', 'オ']
+    
+    # Strategy: Just check if any base name appears (case insensitive for latin/cyrillic)
+    # Then allow any honorific to optionally follow
+    
+    for base in base_names:
+        base_lower = base.lower()
+        
+        # Check for just the base name
+        if re.search(r'(?<![a-zа-яa-я\w])' + re.escape(base_lower) + r'(?![a-zа-яa-я\w])', cleaned):
+            return True
+        
+        # Check with optional o- prefix
+        for prefix in o_prefixes:
+            prefix_pattern = prefix.lower() if prefix != 'お' and prefix != 'オ' else prefix
+            pattern = r'(?<![a-zа-яa-я\w])' + re.escape(prefix_pattern) + r'\s*' + re.escape(base_lower) + r'(?![a-zа-яa-я\w])'
+            if re.search(pattern, cleaned):
+                return True
+        
+        # Check base name followed by any honorific (no spacing requirement to catch mixed script)
+        for honorific in honorifics_all_scripts:
+            honorific_lower = honorific.lower()
+            # Allow optional dash, space, or no separator between name and honorific
+            pattern = (r'(?<![a-zа-яa-я\w])' + re.escape(base_lower) + 
+                      r'[-\s]*' + re.escape(honorific_lower) + 
+                      r'(?![a-zа-яa-я\w])')
+            if re.search(pattern, cleaned):
+                return True
+        
+        # Check with o- prefix + base + honorific
+        for prefix in o_prefixes:
+            prefix_lower = prefix.lower() if prefix != 'お' and prefix != 'オ' else prefix
+            for honorific in honorifics_all_scripts:
+                honorific_lower = honorific.lower()
+                pattern = (r'(?<![a-zа-яa-я\w])' + re.escape(prefix_lower) + 
+                          r'[-\s]*' + re.escape(base_lower) + 
+                          r'[-\s]*' + re.escape(honorific_lower) + 
+                          r'(?![a-zа-яa-я\w])')
+                if re.search(pattern, cleaned):
+                    return True
+    
+    return False
 
 # Vectorstore functionality disabled - not needed with current structured context approach
 # If you need embeddings in the future, you can use a different embedding provider