Update app.py

app.py

@@ -165,17 +165,12 @@ def format_text_for_dataframe(text: str, max_length: int = 200) -> str:
     return text
 
 def read_csv_to_dataframe() -> pd.DataFrame:
-    """Reads the CSV file into a pandas DataFrame with formatted text for display."""
+    """Reads the CSV file into a pandas DataFrame with full text preserved."""
     try:
         df = pd.read_csv(CSV_FILE, dtype=str).fillna('')
         
-        # Format text columns for better display
-        if not df.empty:
-            df['repo id'] = df['repo id'].apply(lambda x: format_text_for_dataframe(x, 50))
-            df['strength'] = df['strength'].apply(lambda x: format_text_for_dataframe(x, 180))
-            df['weaknesses'] = df['weaknesses'].apply(lambda x: format_text_for_dataframe(x, 180))
-            df['speciality'] = df['speciality'].apply(lambda x: format_text_for_dataframe(x, 150))
-            # Keep relevance rating as is since it should be short
+        # Keep the full text intact - don't truncate here
+        # The truncation will be handled in the UI display layer
         
         return df
     except FileNotFoundError:
@@ -184,6 +179,24 @@ def read_csv_to_dataframe() -> pd.DataFrame:
         logger.error(f"Error reading CSV: {e}")
         return pd.DataFrame()
 
+def format_dataframe_for_display(df: pd.DataFrame) -> pd.DataFrame:
+    """Formats dataframe for display with truncated text while preserving original data."""
+    if df.empty:
+        return df
+    
+    # Create a copy for display purposes
+    display_df = df.copy()
+    
+    # Apply formatting only for display
+    if not display_df.empty:
+        display_df['repo id'] = display_df['repo id'].apply(lambda x: format_text_for_dataframe(x, 50))
+        display_df['strength'] = display_df['strength'].apply(lambda x: format_text_for_dataframe(x, 180))
+        display_df['weaknesses'] = display_df['weaknesses'].apply(lambda x: format_text_for_dataframe(x, 180))
+        display_df['speciality'] = display_df['speciality'].apply(lambda x: format_text_for_dataframe(x, 150))
+        # Keep relevance rating as is since it should be short
+    
+    return display_df
+
 def analyze_and_update_single_repo(repo_id: str, user_requirements: str = "") -> Tuple[str, str, pd.DataFrame]:
     """
     Downloads, analyzes a single repo, updates the CSV, and returns results.
@@ -248,12 +261,12 @@ def analyze_and_update_single_repo(repo_id: str, user_requirements: str = "") ->
                 logger.error(f"Failed to write CSV for {repo_id} on retry: {retry_error}")
 
         logger.info(f"Successfully analyzed and updated CSV for {repo_id}")
-        return combined_content, summary, df
+        return combined_content, summary, format_dataframe_for_display(df)
 
     except Exception as e:
         logger.error(f"An error occurred during analysis of {repo_id}: {e}")
         error_summary = f"Error analyzing repo: {e}"
-        return "", error_summary, read_csv_to_dataframe()
+        return "", error_summary, format_dataframe_for_display(read_csv_to_dataframe())
 
 # --- NEW: Helper for Chat History Conversion ---
 def convert_messages_to_tuples(history: List[Dict[str, str]]) -> List[Tuple[str, str]]:
@@ -526,6 +539,15 @@ def create_ui() -> gr.Blocks:
             </div>
             """
         )
+        
+        # Global Reset Button - visible on all tabs
+        with gr.Row():
+            with gr.Column(scale=4):
+                pass
+            with gr.Column(scale=1):
+                reset_all_btn = gr.Button("🔄 Reset Everything", variant="stop", size="lg")
+            with gr.Column(scale=1):
+                pass
 
         with gr.Tabs() as tabs:
             # --- Input Tab ---
@@ -569,7 +591,6 @@ def create_ui() -> gr.Blocks:
                 with gr.Row():
                     analyze_next_btn = gr.Button("⚡ Analyze Next Repository", variant="primary", size="lg", scale=1)
                     analyze_all_btn = gr.Button("🚀 Analyze All Repositories", variant="secondary", size="lg", scale=1)
-                    reset_all_btn = gr.Button("🔄 Reset Everything", variant="stop", size="lg", scale=1)
                     with gr.Column(scale=2):
                         status_box_analysis = gr.Textbox(label="📈 Analysis Status", interactive=False, lines=2)
                 
@@ -726,7 +747,7 @@ def create_ui() -> gr.Blocks:
             
             repo_ids = list(dict.fromkeys([repo.strip() for repo in re.split(r'[\n,]+', text) if repo.strip()]))
             write_repos_to_csv(repo_ids)
-            df = read_csv_to_dataframe()
+            df = format_dataframe_for_display(read_csv_to_dataframe())
             status = f"Status: {len(repo_ids)} repositories submitted. Ready for analysis."
             return repo_ids, 0, df, status, gr.update(selected="analysis_tab")
 
@@ -742,7 +763,7 @@ def create_ui() -> gr.Blocks:
             
             unique_repo_ids = list(dict.fromkeys(repo_ids))
             write_repos_to_csv(unique_repo_ids)
-            df = read_csv_to_dataframe()
+            df = format_dataframe_for_display(read_csv_to_dataframe())
             status = f"Status: Found {len(unique_repo_ids)} repositories. Ready for analysis."
             return unique_repo_ids, 0, df, status, gr.update(selected="analysis_tab")
 
@@ -768,7 +789,7 @@ def create_ui() -> gr.Blocks:
             if not repo_ids:
                 return pd.DataFrame(), 0, "Status: No repositories to analyze. Please submit repo IDs first."
             if current_idx >= len(repo_ids):
-                return read_csv_to_dataframe(), current_idx, "Status: All repositories have been analyzed."
+                return format_dataframe_for_display(read_csv_to_dataframe()), current_idx, "Status: All repositories have been analyzed."
             
             repo_id_to_analyze = repo_ids[current_idx]
             status = f"Status: Analyzing repository {current_idx + 1}/{len(repo_ids)}: {repo_id_to_analyze}"
@@ -856,24 +877,29 @@ def create_ui() -> gr.Blocks:
                 # Handle pandas DataFrame
                 if isinstance(df_data, pd.DataFrame) and not df_data.empty and row_idx < len(df_data):
                     
-                    # Column mapping: 0=repo, 1=strength, 2=weakness, 3=speciality, 4=relevance
-                    if col_idx == 1:  # Strengths column
-                        full_text = str(df_data.iloc[row_idx, 1])
-                        repo_name = str(df_data.iloc[row_idx, 0])
-                        title = f"Strengths - {repo_name}"
-                        return "", gr.update(visible=False), gr.update(), title, full_text, gr.update(visible=True)
-                    
-                    elif col_idx == 2:  # Weaknesses column
-                        full_text = str(df_data.iloc[row_idx, 2])
-                        repo_name = str(df_data.iloc[row_idx, 0])
-                        title = f"Weaknesses - {repo_name}"
-                        return "", gr.update(visible=False), gr.update(), title, full_text, gr.update(visible=True)
-                    
-                    elif col_idx == 3:  # Speciality column
-                        full_text = str(df_data.iloc[row_idx, 3])
+                    # For text expansion, read full data from CSV to get untruncated text
+                    if col_idx in [1, 2, 3]:  # Strength, Weakness, or Speciality columns
                         repo_name = str(df_data.iloc[row_idx, 0])
-                        title = f"Speciality - {repo_name}"
-                        return "", gr.update(visible=False), gr.update(), title, full_text, gr.update(visible=True)
+                        
+                        # Read full data from CSV file to get untruncated text
+                        full_df = read_csv_to_dataframe()
+                        
+                        # Find the matching row in the full data
+                        matching_rows = full_df[full_df['repo id'] == repo_name]
+                        if not matching_rows.empty:
+                            full_row = matching_rows.iloc[0]
+                            
+                            if col_idx == 1:  # Strengths column
+                                full_text = str(full_row['strength'])
+                                title = f"Strengths - {repo_name}"
+                            elif col_idx == 2:  # Weaknesses column
+                                full_text = str(full_row['weaknesses'])
+                                title = f"Weaknesses - {repo_name}"
+                            elif col_idx == 3:  # Speciality column
+                                full_text = str(full_row['speciality'])
+                                title = f"Speciality - {repo_name}"
+                            
+                            return "", gr.update(visible=False), gr.update(), title, full_text, gr.update(visible=True)
                     
                     elif col_idx == 0:  # Repository name column - show action modal
                         repo_id = df_data.iloc[row_idx, 0]
@@ -985,7 +1011,7 @@ def create_ui() -> gr.Blocks:
                 # Get final updated dataframe
                 updated_df = read_csv_to_dataframe()
                 
-                # Get top 3 most relevant repositories
+                # Get top 3 most relevant repositories using full data
                 top_repos = get_top_relevant_repos(updated_df, user_requirements, top_n=3)
                 
                 # Final status with detailed breakdown
@@ -1001,12 +1027,12 @@ 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 updated_df, final_status, top_repos, show_top_section
+                return format_dataframe_for_display(updated_df), final_status, format_dataframe_for_display(top_repos), show_top_section
                 
             except Exception as e:
                 logger.error(f"Error in batch analysis: {e}")
                 error_status = f"❌ Batch analysis failed: {e}"
-                return 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_visit_repo(repo_id: str) -> Tuple[Any, str]:
             """Handle visiting the Hugging Face Space for the repository."""