Update app.py

app.py

@@ -34,21 +34,32 @@ def analyze_sentiment_files(file1, file2, file3, file4, file5, column_name):
             all_data = []
             
             for i, file in enumerate(files, 1):
-                with open(file.name, 'r', encoding='utf-8') as f:
-                    lines = f.readlines()
+                try:
+                    with open(file.name, 'r', encoding='utf-8') as f:
+                        lines = f.readlines()
+                except:
+                    with open(file.name, 'r', encoding='latin-1') as f:
+                        lines = f.readlines()
                 
                 texts = [line.strip() for line in lines if line.strip()]
                 
+                if not texts:
+                    continue
+                
                 # Create dataframe for this file
                 file_df = pd.DataFrame({
                     'text': texts,
                     'line_number': range(1, len(texts) + 1),
                     'file_name': f'File {i}',
-                    'source_file': file.name.split('/')[-1]
+                    'source_file': file.name.split('/')[-1].split('\\')[-1]
                 })
                 
                 all_data.append(file_df)
             
+            if not all_data:
+                return ("Error: No valid text found in uploaded files", 
+                        None, None, None, None, gr.update(choices=[]), gr.update(choices=[]), gr.update(choices=[]))
+            
             # Combine all files
             df = pd.concat(all_data, ignore_index=True)
             column_name = 'text'
@@ -76,10 +87,18 @@ def analyze_sentiment_files(file1, file2, file3, file4, file5, column_name):
         # Get all column names except sentiment columns for filter options
         filter_columns = [col for col in df.columns if col not in ['sentiment_label', 'sentiment_score']]
         
-        summary = create_summary(df, "All Data")
+        # Create initial summary with file breakdown if multiple TXT files
+        if 'file_name' in df.columns:
+            file_summary = "\n\n📁 FILES UPLOADED:\n"
+            for fname in df['file_name'].unique():
+                count = len(df[df['file_name'] == fname])
+                file_summary += f"  - {fname}: {count} lines\n"
+            summary = create_summary(df, "All Data") + file_summary
+        else:
+            summary = create_summary(df, "All Data")
         
         return (summary, df, None, None, None,
-                gr.update(choices=filter_columns, value=None),
+                gr.update(choices=filter_columns, value='file_name' if 'file_name' in filter_columns else None),
                 gr.update(choices=[], value=None),
                 gr.update(choices=[], value=None))