Update app.py

app.py

@@ -1208,6 +1208,54 @@ def SSCCVsimplify(xml_sent):
 
 ###############################################################################
 
+###############################################################################
+def extract_coordinator_from_xml(xml_sent):
+    """Surface of IN_COMPOUND_CONSTITUENT (and / or / but / ; / , and …)."""
+    elem = xml_sent.find(".//IN_COMPOUND_CONSTITUENT")
+    if elem is None:
+        return None
+    parts = []
+    for w in elem.findall("W"):
+        if w.text and str(w.text).strip():
+            parts.append(str(w.text).strip())
+    if not parts:
+        return None
+    raw = " ".join(parts).strip().lower()
+    raw = re.sub(r"\s+", " ", raw)
+    # ", and" / "; and" → and
+    for word in ("and", "or", "but"):
+        if re.search(rf"\b{word}\b", raw):
+            return word
+    if raw in {";", ","} or raw.endswith(";") or raw.endswith(","):
+        return "and"  # list punctuation → treat as "and" for residuals
+    return None
+###############################################################################
+
+###############################################################################
+def rewrite_residual_list_comma(sent, coordinator="and"):
+    """
+    Last list-separator comma → same conjunction as the split sign,
+    so the next pass sees CMN1/CMV1/CCV more reliably (not SSMN).
+    Skips comma before a bare number (e.g. Smith, 43).
+    """
+    if not sent or not coordinator:
+        return sent
+    coord = coordinator.strip().lower()
+    if coord not in {"and", "or", "but"}:
+        return sent
+
+    s = sent.strip()
+    m = re.search(r",\s+(?!\d\b)([^,]+?)(\s*[.!?])?\s*$", s)
+    if not m:
+        return s
+
+    head = s[: m.start()].rstrip()
+    tail = m.group(1).strip()
+    punct = (m.group(2) or "").strip() or "."
+    out = f"{head} {coord} {tail}{punct}"
+    out = re.sub(r"\s+", " ", out).strip()
+    return out
+###############################################################################
 
 ###############################################################################
 def CompoundSimplify(xml_sent):
@@ -1874,6 +1922,25 @@ def process_text(input_text):
                     )
                     simps = simplifier(xml_sent)
 
+                    # Residual comma → same conjunction (CCV / CMV1 / CMN1 only)
+                    if (
+                        simps
+                        and simplifier is CompoundSimplify
+                        and xml_tag in ("M:Y_CCV", "M:Y_CMV1", "M:Y_CMN1")
+                    ):
+                        coord = extract_coordinator_from_xml(xml_sent)
+                        if coord:
+                            rewritten = []
+                            for s in simps:
+                                s2 = rewrite_residual_list_comma(s, coord)
+                                if s2 != s:
+                                    print(
+                                        f"  Residual list rewrite ({coord}): "
+                                        f"{s!r} → {s2!r}"
+                                    )
+                                rewritten.append(s2)
+                            simps = rewritten
+                    
                     if not simps:
                         print(
                             "Simplifier returned []; forcing final (no re-queue)"