Update app.py

app.py

@@ -1902,14 +1902,30 @@ MODAL_MID = {
     "certainly", "definitely", "simply", "almost",
 }
 ###############################################################################
+# do-support / modal on the raw string to the left of the verb
+_LEFT_BARE_INF = re.compile(
+    r"(?:"
+    r"\b(?:can|could|may|might|must|shall|should|will|would)\b|"
+    r"\b(?:do|does|did)\b|"
+    r"\b(?:don't|doesn't|didn't|don’t|doesn’t|didn’t)\b|"
+    r"\b(?:do|does|did)\s+not\b|"
+    r"\b(?:don|doesn|didn)\s*['’]\s*t\b"
+    r")"
+    r"(?:\s+\b(?:not|even|never|also|really|just|only|still|"
+    r"already|always|actually|probably|possibly|perhaps|"
+    r"certainly|definitely|simply|almost)\b)*"
+    r"\s+$",
+    flags=re.I,
+)
+###############################################################################
 
 ###############################################################################
 def fix_subject_verb_agreement(sent: str) -> str:
     """
     After a split, repair a finite verb / aux that no longer matches
     a singular subject.
-    Do not touch infinitives (to be, to go, …), modal complements
-    (may have, will go), or already-singular forms.
+    Never inflect a bare infinitive after a modal or do-support
+    (may have, didn't want, didn ' t want).
     """
     if not sent or not sent.strip():
         return sent
@@ -1946,33 +1962,53 @@ def fix_subject_verb_agreement(sent: str) -> str:
             return True
         return False
 
+    def is_do_aux(t) -> bool:
+        low = re.sub(r"[^a-z]", "", t.lower_)
+        if t.lemma_ == "do":
+            return True
+        return low in {
+            "do", "does", "did",
+            "dont", "doesnt", "didnt",
+            "don", "doesn", "didn",
+        }
+
+    def is_modal(t) -> bool:
+        return t.tag_ == "MD" or t.lemma_.lower() in MODALS or t.lower_ in MODALS
+
     def in_bare_infinitive_complement(tok) -> bool:
-        """
-        Bare infinitive after a modal or do-support, allowing
-        intervening negation / adverbs:
-    
-            may not even have
-            didn't want
-            does not go
-            will really be
-        """
+        left = sent[: tok.idx]
+        if _LEFT_BARE_INF.search(left):
+            return True
+
         i = tok.i - 1
         while i >= 0:
             t = doc[i]
-            if t.tag_ == "MD" or t.lemma_.lower() in MODALS or t.lower_ in MODALS:
-                return True
-            if t.lemma_ == "do" and t.lower_ in {"do", "does", "did"}:
+            if is_modal(t) or is_do_aux(t):
                 return True
+            frag = re.sub(r"[^a-z]", "", t.lower_)
             if (
                 t.lower_ in MODAL_MID
+                or frag in {"", "t", "nt", "n"}
                 or t.dep_ in {"neg", "advmod", "punct"}
                 or t.pos_ in {"ADV", "PART", "PUNCT", "SPACE"}
+                or t.text in {"'", "’", "‘"}
             ):
                 i -= 1
                 continue
             return False
         return False
 
+    def skip_target(t) -> bool:
+        if t.tag_ == "MD":
+            return True
+        if is_infinitive(t):
+            return True
+        if in_bare_infinitive_complement(t):
+            return True
+        if t.lemma_ == "be" and t.lower_ in {"be", "bes", "beses"}:
+            return True
+        return False
+
     def to_3sg(word: str) -> str:
         low = word.lower()
         irregular = {
@@ -1996,18 +2032,6 @@ def fix_subject_verb_agreement(sent: str) -> str:
             new = new[0].upper() + new[1:]
         return new
 
-    def skip_target(t) -> bool:
-        if t.tag_ == "MD":
-            return True
-        if is_infinitive(t):
-            return True
-        if in_bare_infinitive_complement(t):
-            return True
-        # infinitival / base be must never get -s
-        if t.lemma_ == "be" and t.lower_ in {"be", "bes", "beses"}:
-            return True
-        return False
-
     target = None
     for t in doc:
         if skip_target(t):
@@ -2026,13 +2050,41 @@ def fix_subject_verb_agreement(sent: str) -> str:
                 target = t
                 break
 
-    if target is None:
-        return sent
-    if target.lower_ in {"is", "was", "has", "does", "be"}:
-        return sent
+    out = sent
+    if target is not None and target.lower_ not in {"is", "was", "has", "does", "be"}:
+        new = to_3sg(target.text)
+        out = sent[: target.idx] + new + sent[target.idx + len(target.text) :]
 
-    new = to_3sg(target.text)
-    return sent[: target.idx] + new + sent[target.idx + len(target.text) :]
+    # Safety net: if a 3sg form still sits after do-support / a modal,
+    # put it back to the lemma (wants→want, has→have, goes→go).
+    doc2 = nlp(out)
+    for t in reversed(list(doc2)):
+        if t.lemma_ == "do" or t.tag_ == "MD":
+            continue
+        left = out[: t.idx]
+        if not _LEFT_BARE_INF.search(left):
+            continue
+        if t.tag_ != "VBZ" and t.lower_ not in {
+            "wants", "goes", "has", "does", "is", "lives",
+        }:
+            continue
+        base = t.lemma_ if t.lemma_ and t.lemma_ != "-PRON-" else t.text
+        if t.lower_ == "has":
+            base = "have"
+        elif t.lower_ == "is":
+            base = "be"
+        elif t.lower_ == "does":
+            base = "do"
+        elif t.lower_ == "goes":
+            base = "go"
+        elif t.lower_.endswith("s") and t.lemma_:
+            base = t.lemma_
+        if base.lower() == t.lower_:
+            continue
+        if t.text[:1].isupper():
+            base = base[0].upper() + base[1:]
+        out = out[: t.idx] + base + out[t.idx + len(t.text) :]
+    return out
 ###############################################################################
 
 ###############################################################################