Update app.py

app.py

@@ -741,9 +741,27 @@ def _has_ssccv_sign(tagged_list):
     return any("M:Y_SSCCV" in str(item) for item in tagged_list)
 ###############################################################################
 
+###############################################################################
+def _glue_tokens(toks):
+    """Join tokens without spaces around ' or punctuation."""
+    buf = []
+    for tok in toks:
+        if not tok:
+            continue
+        if not buf:
+            buf.append(tok)
+            continue
+        if tok in ".,!?;:" or tok == "'" or tok.startswith("'"):
+            buf[-1] = buf[-1] + tok
+        elif buf[-1].endswith("'"):
+            buf[-1] = buf[-1] + tok
+        else:
+            buf.append(tok)
+    return " ".join(buf)
+###############################################################################
+
 ###############################################################################
 def highlight_tokens_html(tokens, labels):
-    """Theme-safe marking for Hugging Face Spaces: underline/bold, not background fill."""
     parts = []
     i = 0
     n = len(tokens)
@@ -753,34 +771,23 @@ def highlight_tokens_html(tokens, labels):
             j = i + 1
             while j < n and (labels[j] if j < len(labels) else "") == lab:
                 j += 1
-            chunk = " ".join(tokens[i:j])
-            chunk = re.sub(r"\s+([.,!?;:])", r"\1", chunk)
-            chunk = fix_apostrophe_spacing(chunk)
+            chunk = _glue_tokens(tokens[i:j])
             esc = html.escape(chunk)
-            title = html.escape(lab)
-
             if lab == "IN_COGNITIVE_COMMUNICATIVE_VP":
-                # core VP: bold + solid underline
-                parts.append(
-                    f'<u title="{title}" '
-                    f'style="font-weight:700;text-decoration:underline;text-underline-offset:3px">'
-                    f"{esc}</u>"
-                )
+                parts.append(f"<strong><u>{esc}</u></strong>")
             else:
-                # before/after sign: italic + dotted underline
-                parts.append(
-                    f'<em title="{title}" '
-                    f'style="font-style:italic;text-decoration:underline dotted;text-underline-offset:3px">'
-                    f"{esc}</em>"
-                )
+                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
+            j = i + 1
+            while j < n:
+                lab_j = labels[j] if j < len(labels) else ""
+                if lab_j in HIGHLIGHT_CCV:
+                    break
+                j += 1
+            chunk = _glue_tokens(tokens[i:j])
+            parts.append(html.escape(chunk))
+            i = j
     return " ".join(parts)
 ###############################################################################