Update app.py

app.py

@@ -1828,6 +1828,16 @@ def rewrite_residual_list_comma(sent, coordinator="and"):
     return out
 ###############################################################################
 
+###############################################################################
+def repair_mangled_infinitive_be(sent: str) -> str:
+    """Undo earlier bugs: to bes / to beses → to be."""
+    if not sent:
+        return sent
+    sent = re.sub(r"\bto\s+bes(?:es)?\b", "to be", sent, flags=re.I)
+    sent = re.sub(r"\bto\s+bees\b", "to be", sent, flags=re.I)
+    return sent
+###############################################################################
+
 ###############################################################################
 def _singular_present_form(lemma: str) -> str:
     """Map verb lemma → 3rd person singular present."""
@@ -1882,29 +1892,28 @@ def subject_is_singular(subj_token) -> bool:
 
 def fix_subject_verb_agreement(sent: str) -> str:
     """
-    After CMN1 splits a plural subject, repair the finite verb / aux.
-    The man live …  → The man lives …
-    The man are going … → The man is going …
+    After a split, repair a finite verb / aux that no longer matches
+    a singular subject.
+
+    Do not touch infinitives (to be, to go, …) or already-singular forms.
     """
     if not sent or not sent.strip():
         return sent
 
     if re.search(r"\bdo(?:es|ing)?\s+so\b", sent, flags=re.I):
         return sent
-    
+
     sent = sent.strip()
     doc = nlp(sent)
     if not doc:
         return sent
 
-    # --- subject: first nsubj, else first noun ---
     subj = next((t for t in doc if t.dep_ in ("nsubj", "nsubjpass")), None)
     if subj is None:
         subj = next((t for t in doc if t.tag_ in ("NN", "NNP", "PRP")), None)
     if subj is None:
         return sent
 
-    # Coordinated subject still plural
     if any(t.dep_ == "cc" for t in subj.subtree):
         return sent
     if subj.lower_ in {"i", "you", "we", "they"}:
@@ -1914,10 +1923,22 @@ def fix_subject_verb_agreement(sent: str) -> str:
     if subj.tag_ not in ("NN", "NNP", "PRP"):
         return sent
 
+    def is_infinitive(tok) -> bool:
+        # to be / to go / to live …
+        if tok.i > 0 and doc[tok.i - 1].lower_ == "to":
+            return True
+        if tok.head is not None and tok.head.lower_ == "to":
+            return True
+        # xcomp/acl of another verb, typically an infinitive
+        if tok.dep_ in {"xcomp", "acl", "oprd"} and tok.tag_ in {"VB", "VBG"}:
+            return True
+        return False
+
     def to_3sg(word: str) -> str:
         low = word.lower()
         irregular = {
             "are": "is",
+            "am": "is",
             "were": "was",
             "have": "has",
             "do": "does",
@@ -1936,22 +1957,31 @@ def fix_subject_verb_agreement(sent: str) -> str:
             new = new[0].upper() + new[1:]
         return new
 
-    # Prefer agreeing AUX (are going, have gone, …)
+    # Finite auxiliaries that actually need agreement
     target = None
     for t in doc:
+        if is_infinitive(t):
+            continue
         if t.dep_ in ("aux", "auxpass") and t.lower_ in {
             "are", "were", "have", "do", "am"
         }:
             target = t
             break
+
     if target is None:
         for t in doc:
-            if t.tag_ in ("VBP", "VB") and t.lower_ not in {"to"}:
+            if is_infinitive(t):
+                continue
+            # Infinitive lemma "be" must never get -s / -es
+            if t.lemma_ == "be" and t.lower_ in {"be", "bes", "beses"}:
+                continue
+            if t.tag_ in ("VBP", "VB") and t.lower_ not in {"to", "be"}:
                 target = t
                 break
+
     if target is None:
         return sent
-    if target.lower_ in {"is", "was", "has", "does"}:
+    if target.lower_ in {"is", "was", "has", "does", "be"}:
         return sent
 
     new = to_3sg(target.text)
@@ -2343,7 +2373,7 @@ def fix_apostrophe_spacing(s):
 def clean_output(text):
     if not text:
         return ""
-
+    
     # brackets and WordPiece fragments
     text = re.sub(r'[\[\]]+', '', text)
     text = re.sub(r'\s*##\s*', '', text)
@@ -2374,6 +2404,9 @@ def clean_output(text):
     text = re.sub(r"(\w)'\s+(\w)", r"\1'\2", text)
     text = re.sub(r"(\w)\s+'(\w)", r"\1'\2", text)
 
+    # --- restore infinitival be that SVA rewrote as is/are/was/were ---
+    text = repair_mangled_infinitive_be(text)
+    
     text = text.strip()
 
     if text: