Update app.py

app.py

@@ -253,16 +253,27 @@ def embed(texts):
 
 def inject_anchor_into_sentence(sentence, anchor_text, target_url):
     """Wrap anchor if present; otherwise integrate link smoothly."""
-    def norm(x): return re.sub(r'[^a-z0-9 ]','',x.lower())
+    # Handle empty or invalid inputs
+    if not sentence or not anchor_text:
+        return sentence, False
+        
+    def norm(x): 
+        return re.sub(r'[^a-z0-9 ]','',x.lower()) if x else ""
+    
     n_sent, n_anchor = norm(sentence), norm(anchor_text)
 
-    if n_anchor and n_anchor in n_sent:
+    if n_anchor and n_sent and n_anchor in n_sent:
         # Use word boundaries for more accurate matching
-        pattern = re.compile(r'\b' + re.escape(anchor_text) + r'\b', re.IGNORECASE)
-        return pattern.sub(f'<a href="{target_url}">{anchor_text}</a>', sentence), True
+        try:
+            pattern = re.compile(r'\b' + re.escape(anchor_text) + r'\b', re.IGNORECASE)
+            result = pattern.sub(f'<a href="{target_url}">{anchor_text}</a>', sentence)
+            return result, True
+        except:
+            # If regex fails, just append the link
+            pass
 
     # Build a natural integration clause
-    if sentence.endswith(('.', '!', '?')):
+    if len(sentence) > 0 and sentence[-1] in '.!?':
         base, punct = sentence[:-1], sentence[-1]
     else:
         base, punct = sentence, '.'
@@ -428,11 +439,25 @@ def suggest_insertions(source_url, target_url, anchor_text, top_k=1, suggest_alt
     results = []
     for idx in top_idx:
         blk = blocks[idx]
+        # Split sentences more carefully
         sents = re.split(r'(?<=[.!?])\s+', blk)
-        s_embs = embed(sents)
-        s_sims = F.cosine_similarity(s_embs, q_emb.repeat(len(sents),1))
-        si = int(torch.argmax(s_sims))
-        best_sent = sents[si]
+        # Filter out empty sentences
+        sents = [s for s in sents if s and len(s.strip()) > 0]
+        
+        if not sents:
+            # If no valid sentences, use the whole block
+            sents = [blk]
+        
+        try:
+            s_embs = embed(sents)
+            s_sims = F.cosine_similarity(s_embs, q_emb.repeat(len(sents),1))
+            si = int(torch.argmax(s_sims))
+            best_sent = sents[min(si, len(sents)-1)]  # Ensure index is valid
+        except Exception as e:
+            print(f"Error in sentence embedding: {e}")
+            # Fallback to first sentence
+            best_sent = sents[0] if sents else blk
+        
         rewritten_sent, exact_found = inject_anchor_into_sentence(best_sent, anchor_text, target_url)
         
         result = {