🚧 streamline vars

Signed-off-by: peter szemraj <[email protected]>

app.py

@@ -241,21 +241,24 @@ def proc_submission(
 
     st = time.perf_counter()
     history = {}
-    clean_text = clean(input_text, lower=False)
-    clean_text = remove_stopwords(clean_text) if predrop_stopwords else clean_text
+    cln_text = clean(input_text, lower=False)
+    parsed_cln_text = remove_stopwords(cln_text) if predrop_stopwords else cln_text
     logging.info(
-        f"pre-truncation word count: {len(contraction_aware_tokenize(clean_text))}"
+        f"pre-truncation word count: {len(contraction_aware_tokenize(parsed_cln_text))}"
+    )
+    truncation_validated = truncate_word_count(
+        parsed_cln_text, max_words=max_input_length
     )
-    truncation_validated = truncate_word_count(clean_text, max_words=max_input_length)
 
     if truncation_validated["was_truncated"]:
         model_input_text = truncation_validated["processed_text"]
         # create elaborate HTML warning
-        input_wc = re.split(r"\s+", input_text)
+        input_wc = len(contraction_aware_tokenize(parsed_cln_text))
         msg = f"""
         <div style="background-color: #FFA500; color: white; padding: 20px;">
         <h3>Warning</h3>
         <p>Input text was truncated to {max_input_length} words. That's about {100*max_input_length/len(input_wc):.2f}% of the submission.</p>
+        <p>Dropping stopwords is set to {predrop_stopwords}. If this is not what you intended, please validate the advanced settings.</p>
         </div>
         """
         logging.warning(msg)