Update app.py

app.py

@@ -669,6 +669,14 @@ def create_ui() -> gr.Blocks:
                         wrap=True,
                         interactive=False
                     )
+                    
+                    # Quick links for top repositories
+                    with gr.Row():
+                        top_repo_links = gr.HTML(
+                            value="",
+                            label="🔗 Quick Links",
+                            visible=False
+                        )
                 
                 gr.Markdown("### 📋 All Analysis Results")
                 gr.Markdown("💡 **Click repository names to visit them on Hugging Face**")
@@ -678,6 +686,29 @@ def create_ui() -> gr.Blocks:
                     wrap=True,
                     interactive=False
                 )
+                
+                # Modal popup for repository action selection (like in old_app2.py)
+                with gr.Row():
+                    with gr.Column():
+                        repo_action_modal = gr.Column(visible=False)
+                        with repo_action_modal:
+                            gr.Markdown("### 🔗 Repository Actions")
+                            selected_repo_display = gr.Textbox(
+                                label="Selected Repository",
+                                interactive=False,
+                                info="Choose what you'd like to do with this repository"
+                            )
+                            with gr.Row():
+                                visit_repo_btn = gr.Button("🌐 Visit Hugging Face Space", variant="primary", size="lg")
+                                explore_repo_btn = gr.Button("🔍 Open in Repo Explorer", variant="secondary", size="lg")
+                                cancel_modal_btn = gr.Button("❌ Cancel", size="lg")
+                
+                # Quick links section for all repositories
+                with gr.Row():
+                    all_repo_links = gr.HTML(
+                        value="",
+                        label="🔗 Repository Quick Links"
+                    )
 
             # --- Chatbot Tab ---
             with gr.TabItem("🤖 AI Assistant", id="chatbot_tab"):
@@ -839,37 +870,102 @@ def create_ui() -> gr.Blocks:
             
             return history, "💬 Conversation continuing...", "", "", [], 0, pd.DataFrame(), gr.update()
 
-        def handle_repo_click(evt: gr.SelectData, df_data) -> str:
-            """Handle direct repository clicks - open HF space directly."""
+        def handle_dataframe_select(evt: gr.SelectData, df_data) -> Tuple[str, Any, str]:
+            """Handle dataframe row selection - show modal for repo ID (column 0) clicks."""
+            print(f"DEBUG: Selection event triggered!")
+            print(f"DEBUG: evt = {evt}")
+            print(f"DEBUG: df_data type = {type(df_data)}")
+            
             if evt is None:
-                return ""
+                return "", gr.update(visible=False), ""
             
             try:
+                # Get the selected row and column from the event
                 row_idx = evt.index[0]
                 col_idx = evt.index[1]
+                print(f"DEBUG: Selected row {row_idx}, column {col_idx}")
                 
-                # Only handle clicks on the repository name column (column 0)
-                if col_idx == 0 and isinstance(df_data, pd.DataFrame) and not df_data.empty and row_idx < len(df_data):
-                    repo_id = df_data.iloc[row_idx, 0]
+                # Handle pandas DataFrame
+                if isinstance(df_data, pd.DataFrame) and not df_data.empty and row_idx < len(df_data):
+                    
+                    if col_idx == 0:  # Repository name column - show action modal
+                        repo_id = df_data.iloc[row_idx, 0]
+                        print(f"DEBUG: Extracted repo_id = '{repo_id}'")
+                        
+                        if repo_id and str(repo_id).strip() and str(repo_id).strip() != 'nan':
+                            clean_repo_id = str(repo_id).strip()
+                            logger.info(f"Showing modal for repository: {clean_repo_id}")
+                            return clean_repo_id, gr.update(visible=True), clean_repo_id
                     
-                    if repo_id and str(repo_id).strip() and str(repo_id).strip() != 'nan':
-                        hf_url = f"https://huggingface.co/spaces/{str(repo_id).strip()}"
-                        logger.info(f"Opening repository: {hf_url}")
-                        return hf_url
+                    # For content columns (1,2,3) and relevance (4), do nothing since full text is shown directly
+                    else:
+                        print(f"DEBUG: Clicked on column {col_idx}, full text already shown in table")
+                        return "", gr.update(visible=False), ""
+                else:
+                    print(f"DEBUG: df_data is not a DataFrame or row_idx {row_idx} out of range")
+                
             except Exception as e:
-                logger.error(f"Error handling repository click: {e}")
+                print(f"DEBUG: Exception occurred: {e}")
+                logger.error(f"Error handling dataframe selection: {e}")
+            
+            return "", gr.update(visible=False), ""
+
+        def handle_visit_repo(repo_id: str) -> Tuple[Any, str]:
+            """Handle visiting the Hugging Face Space for the repository."""
+            if repo_id and repo_id.strip():
+                hf_url = f"https://huggingface.co/spaces/{repo_id.strip()}"
+                logger.info(f"User chose to visit: {hf_url}")
+                return gr.update(visible=False), hf_url
+            return gr.update(visible=False), ""
+
+        def handle_explore_repo(selected_repo_id: str) -> Tuple[Any, Any, Any]:
+            """Handle navigating to the repo explorer and populate the repo ID."""
+            logger.info(f"DEBUG: handle_explore_repo called with selected_repo_id: '{selected_repo_id}'")
+            
+            if selected_repo_id and selected_repo_id.strip() and selected_repo_id.strip() != 'nan':
+                clean_repo_id = selected_repo_id.strip()
+                return (
+                    gr.update(visible=False),  # close modal
+                    gr.update(selected="repo_explorer_tab"),  # switch tab
+                    gr.update(value=clean_repo_id)  # populate repo explorer input
+                )
+            else:
+                return (
+                    gr.update(visible=False),  # close modal
+                    gr.update(selected="repo_explorer_tab"),  # switch tab
+                    gr.update()  # don't change repo explorer input
+                )
+
+        def handle_cancel_modal() -> Any:
+            """Handle closing the modal."""
+            return gr.update(visible=False)
+
+        def generate_repo_links_html(df: pd.DataFrame) -> str:
+            """Generate HTML with clickable links for repositories."""
+            if df.empty:
+                return ""
             
+            html_links = []
+            for idx, row in df.iterrows():
+                repo_id = row.get('repo id', '') if hasattr(row, 'get') else row[0]
+                if repo_id and str(repo_id).strip() and str(repo_id).strip() != 'nan':
+                    clean_repo_id = str(repo_id).strip()
+                    hf_url = f"https://huggingface.co/spaces/{clean_repo_id}"
+                    html_links.append(f'<a href="{hf_url}" target="_blank" style="display: inline-block; margin: 5px 10px; padding: 8px 16px; background: linear-gradient(45deg, #667eea, #764ba2); color: white; text-decoration: none; border-radius: 8px; font-weight: 600; transition: all 0.3s ease;">{clean_repo_id}</a>')
+            
+            if html_links:
+                return f'<div style="margin: 10px 0; padding: 15px; background: rgba(255, 255, 255, 0.1); border-radius: 12px; backdrop-filter: blur(10px);">{"".join(html_links)}</div>'
             return ""
 
-        def handle_extract_and_analyze(history: List[Dict[str, str]]) -> Tuple[str, str, str, List[str], int, pd.DataFrame, Any, pd.DataFrame, str, Any]:
+        def handle_extract_and_analyze(history: List[Dict[str, str]]) -> Tuple[str, str, str, List[str], int, pd.DataFrame, Any, pd.DataFrame, str, Any, str, str]:
             """Extract keywords from chat, search repositories, and immediately start analysis."""
             if not history:
-                return "❌ No conversation to extract from.", "", "", [], 0, pd.DataFrame(), gr.update(), pd.DataFrame(), "", gr.update(visible=False)
+                return "❌ No conversation to extract from.", "", "", [], 0, pd.DataFrame(), gr.update(), pd.DataFrame(), "", gr.update(visible=False), "", ""
             
             # Convert the full, valid history for the extraction logic
             tuple_history = convert_messages_to_tuples(history)
             if not tuple_history:
-                return "❌ No completed conversations to analyze.", "", "", [], 0, pd.DataFrame(), gr.update(), pd.DataFrame(), "", gr.update(visible=False)
+                return "❌ No completed conversations to analyze.", "", "", [], 0, pd.DataFrame(), gr.update(), pd.DataFrame(), "", gr.update(visible=False), "", ""
                 
             # Get raw keywords string from the LLM
             raw_keywords_str = extract_keywords_from_conversation(tuple_history)
@@ -879,7 +975,7 @@ def create_ui() -> gr.Blocks:
             cleaned_keywords = [kw.strip() for kw in cleaned_keywords if kw.strip()]
             
             if not cleaned_keywords:
-                return f"❌ Could not extract valid keywords. Raw output: '{raw_keywords_str}'", "", "", [], 0, pd.DataFrame(), gr.update(), pd.DataFrame(), "", gr.update(visible=False)
+                return f"❌ Could not extract valid keywords. Raw output: '{raw_keywords_str}'", "", "", [], 0, pd.DataFrame(), gr.update(), pd.DataFrame(), "", gr.update(visible=False), "", ""
 
             # Join them into a clean, comma-separated string
             final_keywords_str = ", ".join(cleaned_keywords)
@@ -895,23 +991,23 @@ def create_ui() -> gr.Blocks:
             unique_repo_ids = list(dict.fromkeys(repo_ids))
             
             if not unique_repo_ids:
-                return f"❌ No repositories found for keywords: {final_keywords_str}", final_keywords_str, user_requirements, [], 0, pd.DataFrame(), gr.update(), pd.DataFrame(), "", gr.update(visible=False)
+                return f"❌ No repositories found for keywords: {final_keywords_str}", final_keywords_str, user_requirements, [], 0, pd.DataFrame(), gr.update(), pd.DataFrame(), "", gr.update(visible=False), "", ""
             
             write_repos_to_csv(unique_repo_ids)
             df = format_dataframe_for_display(read_csv_to_dataframe())
             
             # Immediately start analysis
             try:
-                analyzed_df, analysis_status, top_repos, top_section_update = handle_analyze_all_repos(unique_repo_ids, user_requirements)
+                analyzed_df, analysis_status, top_repos, top_section_update, all_links, top_links = handle_analyze_all_repos(unique_repo_ids, user_requirements)
                 
                 chat_status = f"🎉 Extracted keywords → Found {len(unique_repo_ids)} repositories → Analysis complete!"
                 
-                return chat_status, final_keywords_str, user_requirements, unique_repo_ids, 0, analyzed_df, gr.update(selected="analysis_tab"), top_repos, analysis_status, top_section_update
+                return chat_status, final_keywords_str, user_requirements, unique_repo_ids, 0, analyzed_df, gr.update(selected="analysis_tab"), top_repos, analysis_status, top_section_update, all_links, top_links
                 
             except Exception as e:
                 logger.error(f"Error during extract and analyze: {e}")
                 error_status = f"✅ Found {len(unique_repo_ids)} repositories, but analysis failed: {e}"
-                return error_status, final_keywords_str, user_requirements, unique_repo_ids, 0, df, gr.update(selected="analysis_tab"), pd.DataFrame(), "", gr.update(visible=False)
+                return error_status, final_keywords_str, user_requirements, unique_repo_ids, 0, df, gr.update(selected="analysis_tab"), pd.DataFrame(), "", gr.update(visible=False), "", ""
 
         def extract_user_requirements_from_chat(history: List[Dict[str, str]]) -> str:
             """Extract user requirements from chatbot conversation."""
@@ -930,10 +1026,10 @@ def create_ui() -> gr.Blocks:
             requirements = "\n".join([f"- {msg}" for msg in user_messages if msg.strip()])
             return requirements
 
-        def handle_analyze_all_repos(repo_ids: List[str], user_requirements: str, progress=gr.Progress()) -> Tuple[pd.DataFrame, str, pd.DataFrame, Any]:
+        def handle_analyze_all_repos(repo_ids: List[str], user_requirements: str, progress=gr.Progress()) -> Tuple[pd.DataFrame, str, pd.DataFrame, Any, str, str]:
             """Analyzes all repositories in the CSV file with progress tracking."""
             if not repo_ids:
-                return pd.DataFrame(), "Status: No repositories to analyze. Please submit repo IDs first.", pd.DataFrame(), gr.update(visible=False)
+                return pd.DataFrame(), "Status: No repositories to analyze. Please submit repo IDs first.", pd.DataFrame(), gr.update(visible=False), "", ""
             
             total_repos = len(repo_ids)
             
@@ -1030,6 +1126,10 @@ def create_ui() -> gr.Blocks:
                 # Get top 3 most relevant repositories using full data
                 top_repos = get_top_relevant_repos(updated_df, user_requirements, top_n=3)
                 
+                # Generate HTML links for repositories
+                all_links_html = generate_repo_links_html(analyzed_df)
+                top_links_html = generate_repo_links_html(top_repos) if not top_repos.empty else ""
+                
                 # Final status with detailed breakdown
                 final_status = f"🎉 Batch Analysis Complete!\n✅ Successful: {successful_analyses}/{total_repos}\n❌ Failed: {failed_analyses}/{total_repos}"
                 if csv_update_failures > 0:
@@ -1043,12 +1143,12 @@ def create_ui() -> gr.Blocks:
                 show_top_section = gr.update(visible=not top_repos.empty)
                 
                 logger.info(f"Batch analysis completed: {successful_analyses} successful, {failed_analyses} failed, {csv_update_failures} CSV update issues")
-                return format_dataframe_for_display(analyzed_df), final_status, format_dataframe_for_display(top_repos), show_top_section
+                return format_dataframe_for_display(analyzed_df), final_status, format_dataframe_for_display(top_repos), show_top_section, all_links_html, top_links_html
                 
             except Exception as e:
                 logger.error(f"Error in batch analysis: {e}")
                 error_status = f"❌ Batch analysis failed: {e}"
-                return format_dataframe_for_display(read_csv_to_dataframe()), error_status, pd.DataFrame(), gr.update(visible=False)
+                return format_dataframe_for_display(read_csv_to_dataframe()), error_status, pd.DataFrame(), gr.update(visible=False), "", ""
 
         def handle_reset_everything() -> Tuple[List[str], int, str, pd.DataFrame, pd.DataFrame, Any, List[Dict[str, str]], str, str, str]:
             """Reset everything to initial state - clear all data, CSV, and UI components."""
@@ -1122,9 +1222,9 @@ def create_ui() -> gr.Blocks:
             outputs=[repo_ids_state, current_repo_idx_state, df_output, status_box_input, tabs, status_box_input]
         ).then(
             # If auto_analyze is enabled and we got repos, start analysis automatically
-            fn=lambda repo_ids, user_reqs, trigger: handle_analyze_all_repos(repo_ids, user_reqs) if trigger == "auto_analyze" and repo_ids else (pd.DataFrame(), "Ready for analysis.", pd.DataFrame(), gr.update(visible=False)),
+            fn=lambda repo_ids, user_reqs, trigger: handle_analyze_all_repos(repo_ids, user_reqs) if trigger == "auto_analyze" and repo_ids else (pd.DataFrame(), "Ready for analysis.", pd.DataFrame(), gr.update(visible=False), "", ""),
             inputs=[repo_ids_state, user_requirements_state, status_box_input],
-            outputs=[df_output, status_box_input, top_repos_df, top_repos_section]
+            outputs=[df_output, status_box_input, top_repos_df, top_repos_section, all_repo_links, top_repo_links]
         )
         
         # Smart Submit Button (same behavior as enter)
@@ -1134,9 +1234,9 @@ def create_ui() -> gr.Blocks:
             outputs=[repo_ids_state, current_repo_idx_state, df_output, status_box_input, tabs, status_box_input]
         ).then(
             # If auto_analyze is enabled and we got repos, start analysis automatically
-            fn=lambda repo_ids, user_reqs, trigger: handle_analyze_all_repos(repo_ids, user_reqs) if trigger == "auto_analyze" and repo_ids else (pd.DataFrame(), "Ready for analysis.", pd.DataFrame(), gr.update(visible=False)),
+            fn=lambda repo_ids, user_reqs, trigger: handle_analyze_all_repos(repo_ids, user_reqs) if trigger == "auto_analyze" and repo_ids else (pd.DataFrame(), "Ready for analysis.", pd.DataFrame(), gr.update(visible=False), "", ""),
             inputs=[repo_ids_state, user_requirements_state, status_box_input],
-            outputs=[df_output, status_box_input, top_repos_df, top_repos_section]
+            outputs=[df_output, status_box_input, top_repos_df, top_repos_section, all_repo_links, top_repo_links]
         )
         
         # Auto-analyze checkbox toggle
@@ -1150,7 +1250,7 @@ def create_ui() -> gr.Blocks:
         analyze_all_btn.click(
             fn=handle_analyze_all_repos,
             inputs=[repo_ids_state, user_requirements_state],
-            outputs=[df_output, status_box_analysis, top_repos_df, top_repos_section]
+            outputs=[df_output, status_box_analysis, top_repos_df, top_repos_section, all_repo_links, top_repo_links]
         )
         
         # Chatbot with Auto-extraction and Auto-search
@@ -1169,9 +1269,9 @@ def create_ui() -> gr.Blocks:
             outputs=[current_requirements_display]
         ).then(
             # If we got repos from chatbot, auto-analyze them
-            fn=lambda repo_ids, user_reqs: handle_analyze_all_repos(repo_ids, user_reqs) if repo_ids else (pd.DataFrame(), "", pd.DataFrame(), gr.update(visible=False)),
+            fn=lambda repo_ids, user_reqs: handle_analyze_all_repos(repo_ids, user_reqs) if repo_ids else (pd.DataFrame(), "", pd.DataFrame(), gr.update(visible=False), "", ""),
             inputs=[repo_ids_state, user_requirements_state],
-            outputs=[df_output, chat_status, top_repos_df, top_repos_section]
+            outputs=[df_output, chat_status, top_repos_df, top_repos_section, all_repo_links, top_repo_links]
         )
         
         send_btn.click(
@@ -1189,16 +1289,16 @@ def create_ui() -> gr.Blocks:
             outputs=[current_requirements_display]
         ).then(
             # If we got repos from chatbot, auto-analyze them
-            fn=lambda repo_ids, user_reqs: handle_analyze_all_repos(repo_ids, user_reqs) if repo_ids else (pd.DataFrame(), "", pd.DataFrame(), gr.update(visible=False)),
+            fn=lambda repo_ids, user_reqs: handle_analyze_all_repos(repo_ids, user_reqs) if repo_ids else (pd.DataFrame(), "", pd.DataFrame(), gr.update(visible=False), "", ""),
             inputs=[repo_ids_state, user_requirements_state],
-            outputs=[df_output, chat_status, top_repos_df, top_repos_section]
+            outputs=[df_output, chat_status, top_repos_df, top_repos_section, all_repo_links, top_repo_links]
         )
         
         # Extract and Analyze Button (one-click solution for chatbot)
         extract_analyze_btn.click(
             fn=handle_extract_and_analyze,
             inputs=[chatbot],
-            outputs=[chat_status, extracted_keywords_output, user_requirements_state, repo_ids_state, current_repo_idx_state, df_output, tabs, top_repos_df, status_box_analysis, top_repos_section]
+            outputs=[chat_status, extracted_keywords_output, user_requirements_state, repo_ids_state, current_repo_idx_state, df_output, tabs, top_repos_df, status_box_analysis, top_repos_section, all_repo_links, top_repo_links]
         ).then(
             # Update requirements display when they change
             fn=lambda req: req if req.strip() else "No specific requirements extracted from conversation.",
@@ -1209,19 +1309,44 @@ def create_ui() -> gr.Blocks:
         # Repo Explorer Tab
         setup_repo_explorer_events(repo_components, repo_states)
         
-        # Direct Repository Clicks - Open HF Space
+        # Direct Repository Clicks - Show Modal (like old_app2.py)
         df_output.select(
-            fn=handle_repo_click,
+            fn=handle_dataframe_select,
             inputs=[df_output],
-            outputs=[status_box_input],
-            js="(url) => { if(url && url.trim()) { window.open(url, '_blank'); } }"
+            outputs=[selected_repo_display, repo_action_modal, selected_repo_id_state]
         )
         
         top_repos_df.select(
-            fn=handle_repo_click,
+            fn=handle_dataframe_select,
             inputs=[top_repos_df],
-            outputs=[status_box_input],
-            js="(url) => { if(url && url.trim()) { window.open(url, '_blank'); } }"
+            outputs=[selected_repo_display, repo_action_modal, selected_repo_id_state]
+        )
+        
+        # Modal button events (like old_app2.py)
+        visit_repo_btn.click(
+            fn=handle_visit_repo,
+            inputs=[selected_repo_display],
+            outputs=[repo_action_modal, selected_repo_display],
+            js="(repo_id) => { if(repo_id && repo_id.trim()) { window.open('https://huggingface.co/spaces/' + repo_id.trim(), '_blank'); } }"
+        )
+        explore_repo_btn.click(
+            fn=handle_explore_repo,
+            inputs=[selected_repo_id_state],
+            outputs=[
+                repo_action_modal, 
+                tabs,
+                repo_components["repo_explorer_input"]
+            ],
+            js="""(repo_id) => { 
+                console.log('DEBUG: Navigate to repo explorer for:', repo_id);
+                setTimeout(() => { 
+                    window.scrollTo({top: 0, behavior: 'smooth'}); 
+                }, 200); 
+            }"""
+        )
+        cancel_modal_btn.click(
+            fn=handle_cancel_modal,
+            outputs=[repo_action_modal]
         )
         
         # Reset button event