formatted text cleaning

app.py

@@ -38,12 +38,18 @@ label_mapping = {
 def clean_text(text):
 
     text = text.replace("\r\n", "\n").replace("\r", "\n")
+    
+ 
+    text = re.sub(r"\n\s*\n+", "\n\n", text)  
+    
+    text = re.sub(r"[ \t]+", " ", text)
 
-    text = re.sub(r"\n\s*\n+", "\n\n", text) 
+    text = re.sub(r"(\w+)-\n(\w+)", r"\1\2", text)  
 
-    text = re.sub(r"[ \t]+", " ", text)
+    text = re.sub(r"(?<!\n)\n(?!\n)", " ", text)  
 
     text = text.strip()
+    
     return text
 
 def classify_text(text):