Update app.py

app.py

@@ -804,37 +804,49 @@ def highlight_sentence_if_ssccv(sentence):
     return highlight_tokens_html(tokens, preds)
 ###############################################################################
 
+###############################################################################
+def highlight_tokens_html(tokens, labels):
+    parts = []
+    i = 0
+    n = len(tokens)
+    while i < n:
+        lab = labels[i] if i < len(labels) else ""
+        if lab in HIGHLIGHT_CCV:
+            j = i + 1
+            while j < n and (labels[j] if j < len(labels) else "") == lab:
+                j += 1
+            chunk = re.sub(r"\s+([.,!?;:])", r"\1", " ".join(tokens[i:j]))
+            esc = html.escape(chunk)
+            if lab == "IN_COGNITIVE_COMMUNICATIVE_VP":
+                parts.append(f"<strong><u>{esc}</u></strong>")
+            else:
+                parts.append(f"<u>{esc}</u>")
+            i = j
+        else:
+            tok = tokens[i]
+            if tok in ".,!?;:" and parts:
+                parts[-1] = parts[-1] + html.escape(tok)
+            else:
+                parts.append(html.escape(tok))
+            i += 1
+    return " ".join(parts)
+###############################################################################
+
 ###############################################################################
 def highlight_final_output(final_text):
-    """Preserve paragraph breaks from process_text; highlight sentence by sentence."""
-    if not final_text or final_text.startswith("ERROR"):
-        return html.escape(final_text or "")
-
-    legend = (
-        '<div style="font-size:14px;margin-bottom:10px">'
-        "<b>Cognitive / communicative VP</b> — "
-        "<u style='font-weight:700'>bold underline = complementiser introducing a content clause</u> · "
-        "<em style='text-decoration:underline dotted'>italic dotted = before/after the complementiser</em>"
-        "</div>"
-    )
-    
+    if not final_text or str(final_text).startswith("ERROR"):
+        return f'<div class="simp-out">{html.escape(final_text or "")}</div>'
+
     para_html = []
     for para in re.split(r"\n\s*\n", final_text):
         para = para.strip()
         if not para:
             continue
-        # process_text joins a paragraph's sentences with spaces
-        sents = split_into_sentences(para) if para else []
-        if not sents:
-            sents = [para]
-        sent_bits = [highlight_sentence_if_ssccv(s) for s in sents]
-        para_html.append(
-            '<p style="font-size:16px;line-height:1.55;margin:0 0 12px 0">'
-            + " ".join(sent_bits)
-            + "</p>"
-        )
+        sents = split_into_sentences(para) if para else [para]
+        bits = [highlight_sentence_if_ssccv(s) for s in sents]
+        para_html.append("<p>" + " ".join(bits) + "</p>")
 
-    return legend + "".join(para_html)
+    return '<div class="simp-out">' + "".join(para_html) + "</div>"
 ###############################################################################
 
 ###############################################################################
@@ -2735,13 +2747,12 @@ def process_text(input_text):
         final_output = "\n\n".join(output_paragraphs)
         print(f"\n=== FINAL OUTPUT ===\n{final_output}")
         highlighted = highlight_final_output(final_output)
-        return final_output, highlighted
+        return highlighted
 
     except Exception as e:
         import traceback
         print(traceback.format_exc())
-        err = f"ERROR: {str(e)}"
-        return err, html.escape(err)
+        return f'<div class="simp-out">{html.escape("ERROR: " + str(e))}</div>'
         
 ###########################################################################
 
@@ -2753,12 +2764,10 @@ print("  All seven models loaded successfully!")
 print("Creating Gradio interface...")
 
 custom_css = """
-/* Slightly larger base font */
 .gradio-container, .gradio-container * {
     font-size: 16px !important;
 }
 
-/* Input = original text → bright pink */
 .input-text textarea {
     font-size: 17px !important;
     color: #ffd0d0 !important;
@@ -2766,49 +2775,33 @@ custom_css = """
     line-height: 1.45 !important;
 }
 
-/* Output = simplified text → bright green */
-.output-text textarea {
-    font-size: 17px !important;
-    color: #d0ffd0 !important;
-    font-weight: 500 !important;
-    line-height: 1.45 !important;
-}
-
-/* Labels under the boxes */
-.input-text label,
-.output-text label {
+.input-text label {
     font-size: 15px !important;
     font-weight: 600 !important;
-}
-
-.input-text label {
     color: #ffd0d0 !important;
 }
 
-.output-text label {
-    color: #d0ffd0 !important;
+/* Merged simplified output: green text, VP underlined */
+.simp-out {
+    color: #7CFF7C !important;
+    font-size: 17px !important;
+    font-weight: 500 !important;
+    line-height: 1.55 !important;
+    padding: 12px 14px !important;
 }
 
-/* Highlighted VP pane — readable on HF light and dark themes */
-.highlighted-output {
-    padding: 12px 14px !important;
-    border-radius: 8px !important;
-    min-height: 8em;
-    font-size: 17px !important;
-    line-height: 1.6 !important;
+.simp-out p {
+    margin: 0 0 12px 0 !important;
+    color: #7CFF7C !important;
 }
 
-.highlighted-output u {
+.simp-out strong u,
+.simp-out u {
+    color: #7CFF7C !important;
     font-weight: 700 !important;
     text-decoration: underline !important;
     text-underline-offset: 3px !important;
 }
-
-.highlighted-output em {
-    font-style: italic !important;
-    text-decoration: underline dotted !important;
-    text-underline-offset: 3px !important;
-}
 """
 
 with gr.Blocks(
@@ -2835,7 +2828,6 @@ Paste text, or click examples to **add** them into the box below
 """
     )
 
-    # 1) Complex input
     input_text = gr.Textbox(
         lines=12,
         label="Original text",
@@ -2843,26 +2835,17 @@ Paste text, or click examples to **add** them into the box below
         elem_classes=["input-text"],
     )
 
-    # 2) Bridge button (directly under input)
     btn = gr.Button("Process & Simplify", variant="primary")
 
-    # 3) Simple output (plain text, copyable)
-    output_text = gr.Textbox(
-        lines=12,
-        label="Simplified text",
-        elem_classes=["output-text"],
-    )
-
-    # 4) Highlighted cognitive / communicative VPs
-    highlighted_html = gr.HTML(
+    output_html = gr.HTML(
         value="",
-        elem_classes=["highlighted-output"],
+        label="Simplified text",
     )
 
     btn.click(
         fn=process_text,
         inputs=input_text,
-        outputs=[output_text, highlighted_html],
+        outputs=output_html,
     )
 
     EXAMPLE_SENTENCES = [
@@ -2905,7 +2888,6 @@ if __name__ == "__main__":
         debug=True,
         share=False,
     )
-
     
     '''
     test = (