Update app.py

app.py

@@ -22,12 +22,29 @@ def remove_caseifer(text):
     return new_text
     
 def add_caseifer(text):
+    tokenlist = set("\n\" !$&'#,/+=-<>*@.:;[]{}()^_?0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyzèé")
+    replace_map = {  # Define a mapping of characters to be replaced
+        "{": "[",
+        "(": "[",
+        "}": "]",
+        ")": "]",
+        "&":"and"
+    }
+    upperlist = set("ABCDEFGHIJKLMNOPQRSTUVWXYZ")
+    lowerlist = set("abcdefghijklmnopqrstuvwxyz")
+
     new_text = ""
+    uppers = 0
+    lowers = 0
     for char in text:
-        if char.isupper():
-            new_text += "↨" + char.lower()
-        else:
-            new_text += char
+        if char in tokenlist:
+            if char in upperlist:
+                uppers += 1
+                new_text += "↨" + char.lower()
+            elif char in replace_map:
+                new_text += replace_map[char]
+            else:
+                new_text += char
     return new_text
 
 max_new_tokens = 88 # number of tokens generated in each sample