Update utils/utils.py

utils/utils.py

@@ -115,23 +115,15 @@ def read_pptx_text(file_path):
 def validate_input(question, openai_api_key, gemini_api_key, anthropic_api_key):
     is_valid = True
 
-    if (question.len() > 500 or
-        openai_api_key.len() > 150 or
-        gemini_api_key.len() > 150 or
-        anthropic_api_key.len() > 150):
+    if (len(question) > 500
+        or len(openai_api_key) > 150
+        or len(gemini_api_key) > 150
+        or len(anthropic_api_key) > 150:
         is_valid = False
     
-    # Allow: letters, numbers, spaces, basic punctuation, common symbols
-    # Block: HTML tags, script injection, control characters, etc.
-    #temp = re.sub(r'[^\w\s.,!?\'\-()@$%&+/:;"=\[\]]', '', input_text)
-
-    # Max length is MAX_LENGTH
-    #temp = temp[:MAX_LENGTH]
-
-    # Max word length is MAX_WORD_LENGTH
-    #temp = ' '.join(word[:MAX_WORD_LENGTH] for word in temp.split(' '))
-
-    # Max word count is MAX_WORD_COUNT
-    #temp = ' '.join(temp.split(' ')[:MAX_WORD_COUNT])
+    sanitized_question = re.sub(r'[^\w\s.,!?\'\-()@$%&+/:;"=\[\]]', '', question)
+    
+    if sanitized_question != question:
+        is_valid = False
 
     return is_valid