Update services/preprocessing.py

services/preprocessing.py

@@ -3,6 +3,10 @@ import re
 def clean_text(text):
     text = text.lower()
     text = re.sub(r"http\S+", "", text)
-    text = re.sub(r"@\w+", "", text)
-    text = re.sub(r"[^a-zA-Z\s]", "", text)
-    return text.strip()
+    text = re.sub(r"[^a-zA-Z\s]", " ", text)
+    text = re.sub(r'(.)\1+', r'\1\1', text)
+    text = re.sub(r'\s+', ' ', text).strip()
+    return text
+
+def is_valid(text):
+    return len(text.split()) > 3