Update app.py

app.py

@@ -226,7 +226,36 @@ def create_anchor_suggestion(anchor_text, target_url):
     ]
     return suggestions[0]
 
-def suggest_insertions(source_url, target_url, anchor_text, top_k=1, check_keyword_presence=False):
+def extract_potential_anchors(sentence, target_url):
+    """Extract potential anchor text phrases from a sentence."""
+    # Remove very common words and extract meaningful phrases
+    stopwords = {'the', 'a', 'an', 'and', 'or', 'but', 'in', 'on', 'at', 'to', 'for', 
+                 'of', 'with', 'by', 'from', 'as', 'is', 'was', 'are', 'were', 'be',
+                 'have', 'has', 'had', 'do', 'does', 'did', 'will', 'would', 'could', 'should'}
+    
+    # Split into words and find continuous phrases
+    words = sentence.split()
+    phrases = []
+    
+    # Generate phrases of 2-5 words
+    for length in range(2, min(6, len(words) + 1)):
+        for i in range(len(words) - length + 1):
+            phrase = ' '.join(words[i:i+length])
+            # Check if phrase doesn't start/end with stopwords
+            first_word = words[i].lower().strip('.,!?;:')
+            last_word = words[i+length-1].lower().strip('.,!?;:')
+            if first_word not in stopwords and last_word not in stopwords:
+                phrases.append(phrase.strip('.,!?;:'))
+    
+    # Also add significant single words (proper nouns, long words)
+    for word in words:
+        clean_word = word.strip('.,!?;:')
+        if (len(clean_word) > 7 or clean_word[0].isupper()) and clean_word.lower() not in stopwords:
+            phrases.append(clean_word)
+    
+    return phrases[:5]  # Return top 5 potential anchors
+
+def suggest_insertions(source_url, target_url, anchor_text, top_k=1, suggest_alternative=False):
     blocks = get_text_blocks(source_url)
     if not blocks:
         return [{"error":"No text blocks found on the page."}]
@@ -235,16 +264,6 @@ def suggest_insertions(source_url, target_url, anchor_text, top_k=1, check_keywo
     full_text = " ".join(blocks).lower()
     keyword_present = anchor_text.lower() in full_text
 
-    if check_keyword_presence and not keyword_present:
-        # Return suggestion for adding new content
-        suggestion = create_anchor_suggestion(anchor_text, target_url)
-        return [{
-            "keyword_not_found": True,
-            "suggestion": suggestion,
-            "anchor_text": anchor_text,
-            "target_url": target_url
-        }]
-
     # target context
     try:
         tgt_html = requests.get(target_url, timeout=20, headers=UA).text
@@ -256,6 +275,7 @@ def suggest_insertions(source_url, target_url, anchor_text, top_k=1, check_keywo
     ext = tldextract.extract(target_url)
     tgt_domain = ".".join([p for p in [ext.domain, ext.suffix] if p])
 
+    # First, find best match with original anchor
     query = f"{anchor_text} — relevant to: {tgt_title} ({tgt_domain})"
     q_emb = embed([query])[0]
 
@@ -272,11 +292,42 @@ def suggest_insertions(source_url, target_url, anchor_text, top_k=1, check_keywo
         si = int(torch.argmax(s_sims))
         best_sent = sents[si]
         rewritten_sent, exact_found = inject_anchor_into_sentence(best_sent, anchor_text, target_url)
-        results.append({
+        
+        result = {
             "anchor_was_present": exact_found,
             "best_sentence_original": best_sent,
-            "best_sentence_with_anchor": rewritten_sent
-        })
+            "best_sentence_with_anchor": rewritten_sent,
+            "keyword_in_article": keyword_present
+        }
+        
+        # If anchor not present and alternative suggestion requested
+        if suggest_alternative and not keyword_present:
+            # Extract potential anchor phrases from the best sentence
+            potential_anchors = extract_potential_anchors(best_sent, target_url)
+            
+            # Find the best alternative anchor
+            best_alternative = None
+            best_alt_score = -1
+            
+            for alt_anchor in potential_anchors:
+                # Check relevance to target
+                alt_query = f"{alt_anchor} — relevant to: {tgt_title}"
+                alt_q_emb = embed([alt_query])[0]
+                alt_sim = F.cosine_similarity(alt_q_emb.unsqueeze(0), q_emb.unsqueeze(0)).item()
+                
+                if alt_sim > best_alt_score:
+                    best_alt_score = alt_sim
+                    best_alternative = alt_anchor
+            
+            if best_alternative:
+                # Create alternative suggestion with the better anchor
+                alt_rewritten, alt_exact = inject_anchor_into_sentence(best_sent, best_alternative, target_url)
+                result["alternative_anchor"] = best_alternative
+                result["alternative_sentence"] = alt_rewritten
+                result["alternative_exact_match"] = alt_exact
+        
+        results.append(result)
+    
     return results
 
 # =========================
@@ -426,7 +477,7 @@ def to_plain_text(html_or_text):
 # =========================
 # Gradio UI
 # =========================
-def run_tool(source_url, target_url, anchor_text, smart_rewrite, plain_text, check_keyword):
+def run_tool(source_url, target_url, anchor_text, smart_rewrite, plain_text, suggest_alternative_anchor):
     if not source_url or not target_url or not anchor_text:
         return "❌ Please provide Source URL, Target URL, and Anchor Text."
 
@@ -440,23 +491,20 @@ def run_tool(source_url, target_url, anchor_text, smart_rewrite, plain_text, che
     target_url = normalize_url(target_url)
 
     try:
-        res = suggest_insertions(source_url, target_url, anchor_text, top_k=1, check_keyword_presence=check_keyword)[0]
+        res = suggest_insertions(source_url, target_url, anchor_text, top_k=1, suggest_alternative=suggest_alternative_anchor)[0]
     except Exception as e:
         return f"❌ Error processing the page: {str(e)}"
 
     if "error" in res:
         return f"❌ {res['error']}"
     
-    # Handle case where keyword is not found
-    if res.get("keyword_not_found"):
-        return f"⚠️ Keyword '{anchor_text}' not found in the article.\n\n{res['suggestion']}"
-
     # Detect language from the original sentence
     original_sentence = res['best_sentence_original']
     detected_lang = detect_language(original_sentence)
     language_name = get_language_name(detected_lang)
     print(f"Detected language: {language_name} ({detected_lang})")
 
+    # Process original anchor suggestion
     draft_html = res["best_sentence_with_anchor"]
 
     # 1) Optional first-pass rewrite with language support
@@ -474,10 +522,38 @@ def run_tool(source_url, target_url, anchor_text, smart_rewrite, plain_text, che
     # 3) Optionally convert to plain text
     final_output = to_plain_text(final_html) if plain_text else final_html
 
+    # Build the main result
     if res.get("anchor_was_present", False):
-        return warn + f"✅ Add link here:\n\n{final_output}"
+        result = warn + f"✅ Add link here:\n\n{final_output}"
     else:
-        return warn + f"Change this sentence:\n\n{original_sentence}\n\nWith this one:\n\n{final_output}"
+        result = warn + f"📝 OPTION 1 - Your anchor text:\n\nChange this sentence:\n{original_sentence}\n\nWith this one:\n{final_output}"
+    
+    # Process alternative anchor if requested and original anchor not found
+    if suggest_alternative_anchor and not res.get("keyword_in_article", True) and res.get("alternative_anchor"):
+        alt_anchor = res["alternative_anchor"]
+        alt_sentence = res["alternative_sentence"]
+        
+        # Apply GPT rewriting to alternative as well
+        if smart_rewrite:
+            alt_g = gpt_rewrite(alt_sentence, alt_anchor, target_url, style="neutral", language=language_name)
+            alt_final = alt_g["sentence_html"]
+        else:
+            alt_final = alt_sentence
+        
+        # Polish if needed
+        if not res.get("alternative_exact_match", False):
+            alt_polished = gpt_validate_and_polish(alt_final, alt_anchor, target_url, language=language_name)
+            alt_final = alt_polished.get("sentence_html", alt_final)
+        
+        alt_output = to_plain_text(alt_final) if plain_text else alt_final
+        
+        result += f"\n\n{'='*50}\n\n"
+        result += f"💡 OPTION 2 - Better anchor suggestion:\n\n"
+        result += f"Since '{anchor_text}' is not in the article, consider using:\n"
+        result += f"Suggested anchor: '{alt_anchor}'\n\n"
+        result += f"Change this sentence:\n{original_sentence}\n\nWith this one:\n{alt_output}"
+    
+    return result
 
 def clear_cache():
     """Clear all caches."""
@@ -505,8 +581,8 @@ with gr.Blocks(title=f"Link Insertion Helper • GPT: {gpt_status}") as demo:
             with gr.Row():
                 smart_rewrite = gr.Checkbox(label="Smart rewrite (GPT)", value=True)
                 plain_text = gr.Checkbox(label="Plain text (no URL)", value=False)
-                check_keyword = gr.Checkbox(label="Check keyword presence", value=False, 
-                                           info="If enabled, suggests where to add new content when keyword is not found")
+                suggest_alternative_anchor = gr.Checkbox(label="Suggest alternative anchor", value=False, 
+                                           info="If anchor not found, suggest a better anchor from the article")
             
             with gr.Row():
                 submit_btn = gr.Button("Process", variant="primary")
@@ -518,7 +594,7 @@ with gr.Blocks(title=f"Link Insertion Helper • GPT: {gpt_status}") as demo:
     
     submit_btn.click(
         fn=run_tool,
-        inputs=[source_url, target_url, anchor_text, smart_rewrite, plain_text, check_keyword],
+        inputs=[source_url, target_url, anchor_text, smart_rewrite, plain_text, suggest_alternative_anchor],
         outputs=output
     )
     
@@ -532,7 +608,7 @@ with gr.Blocks(title=f"Link Insertion Helper • GPT: {gpt_status}") as demo:
     - 🌍 **Auto Language Detection**: Preserves special characters (č, ć, š, ž, đ, etc.)
     - 💾 **Smart Caching**: Caches embeddings and API responses for faster repeated queries
     - 🎯 **Main Content Focus**: Prioritizes first 5-7 paragraphs, ignores author bios
-    - 🔍 **Keyword Check**: Optional detection when anchor text is not in article
+    - 🔄 **Alternative Anchor Suggestion**: When your anchor isn't in the article, suggests better anchors from existing text
     - ✨ **Natural Integration**: AI-powered sentence rewriting for seamless link placement
     """)