Reveal prompt preprocessing

preprocess.py

@@ -0,0 +1,30 @@
+import re
+
+def clean_sentence(sentence):
+    # Remove "!", "?", ".", "(", ")" from the sentence
+    sentence = re.sub(r"[!.?()]", "", sentence)
+    
+    # Replace " , " with an empty space
+    sentence = re.sub(r" , ", " ", sentence)
+    
+    # Remove any trailing commas
+    sentence = re.sub(r"^,|,$", "", sentence)
+    
+    # Strip spaces
+    sentence = sentence.strip()
+    
+    # Remove any usernames
+    words = sentence.split(", ")
+    result = []
+    for word in words:
+        word = word.strip()
+        if word == 'v':
+            result.append(word)
+            continue
+        if len(word) < 2:
+            continue
+        if any(char.isdigit() for char in word) and word not in ["1girl", "1boy", "1koma", "1other"]:
+            continue
+        result.append(word)
+    
+    return ", ".join(result)