Update app.py

app.py

@@ -61,6 +61,12 @@ import gradio as gr
 import os
 
 from collections import deque  #   add this at the top of app.py if not already there
+from collections import defaultdict
+
+PRONOUNS = {
+    "he", "she", "it", "they", "him", "her", "them",
+    "his", "hers", "its", "their", "theirs",
+}
 
 seen = set()
 
@@ -363,23 +369,71 @@ def sentence_has_anaphoric_pronoun(sent: str) -> bool:
     return any(t in _ANAPHORIC_PRONOUNS for t in tokens)
 
 
+def sentence_entity_key(sent: str) -> str:
+    """Primary entity ≈ subject head, lowercased lemma/text."""
+    doc = nlp(sent)
+    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.pos_ in ("PROPN", "NOUN", "PRON")), None)
+    if subj is None:
+        return sent.lower()[:40]
+    # Use lemma for "man"/"men"; text for names
+    if subj.pos_ == "PROPN":
+        return subj.text.lower()
+    return subj.lemma_.lower()
+
+def is_pronoun_sentence(sent: str) -> bool:
+    doc = nlp(sent)
+    for t in doc:
+        if t.dep_ in ("nsubj", "nsubjpass") and t.lower_ in PRONOUNS:
+            return True
+    return bool(re.search(r"\b(he|she|it|they|him|her|them)\b", sent, re.I))
+
+def is_identifying(sent: str) -> bool:
+    """Property / location / copula — good 'given' material."""
+    return bool(
+        re.search(
+            r"\b(is|are|was|were|lives?|lived|lives in|is a|is an)\b",
+            sent,
+            re.I,
+        )
+    )
+
 def order_sentences_for_discourse(sents):
     """
-    Print sentences with anaphoric pronouns last so pronouns
-    are less likely to precede their antecedents.
-    Stable within each group (original relative order kept).
+    1. Pronoun sentences last (antecedent first).
+    2. Group remaining sentences by subject entity.
+    3. Within a group: identifying sentences before event sentences.
+    4. Group order = first appearance in the current list
+       (≈ order derived from the source sentence).
     """
-    without = []
-    with_pron = []
-    for s in sents:
-        s = (s or "").strip()
-        if not s:
-            continue
-        if sentence_has_anaphoric_pronoun(s):
-            with_pron.append(s)
-        else:
-            without.append(s)
-    return without + with_pron
+    cleaned = [s.strip() for s in sents if s and s.strip()]
+    if len(cleaned) <= 1:
+        return cleaned
+
+    pronoun_sents = []
+    lexical_sents = []
+    for s in cleaned:
+        (pronoun_sents if is_pronoun_sentence(s) else lexical_sents).append(s)
+
+    groups = defaultdict(list)
+    order = []
+    for s in lexical_sents:
+        key = sentence_entity_key(s)
+        if key not in groups:
+            order.append(key)
+        groups[key].append(s)
+
+    ordered = []
+    for key in order:
+        chunk = groups[key]
+        ident = [s for s in chunk if is_identifying(s)]
+        rest = [s for s in chunk if s not in ident]
+        ordered.extend(ident + rest)
+
+    ordered.extend(pronoun_sents)
+    return ordered
+    
 ###############################################################################
 
 ###############################################################################