Update app.py

app.py

@@ -435,7 +435,7 @@ class PlotFactory:
             
             return fig
 
-# Unified Data Handler
+
 class DataHandler:
     """Handles all data operations"""
     
@@ -468,39 +468,52 @@ class DataHandler:
         temp_file.close()
         return temp_file.name, f"Exported {len(data)} entries"
     
-
     @staticmethod
     @handle_errors(default_return="")
     def process_file(file) -> str:
         """Process uploaded file"""
         if not file:
             return ""
-    
-        content = file.read().decode('utf-8')
         
-        if file.name.endswith('.csv'):
-            import io
-            csv_file = io.StringIO(content)
-            reader = csv.reader(csv_file)
-            try:
-                next(reader)
-                texts = []
-                for row in reader:
-                    if row and row[0].strip():
-                        text = row[0].strip().strip('"')
-                        if text:  
-                            texts.append(text)
-                return '\n'.join(texts)
-            except Exception as e:
-                lines = content.strip().split('\n')[1:] 
-                texts = []
-                for line in lines:
-                    if line.strip():
-                        text = line.strip().strip('"')
-                        if text:
-                            texts.append(text)
-                return '\n'.join(texts)
-        return content
+        try:
+            # For CSV files
+            if file.name.endswith('.csv'):
+                # Read the file content
+                content = file.read()
+                
+                # Try different encodings
+                for encoding in ['utf-8', 'latin-1', 'cp1252']:
+                    try:
+                        text_content = content.decode(encoding)
+                        # Use pandas for robust CSV handling
+                        df = pd.read_csv(io.StringIO(text_content), encoding=encoding)
+                        # Assume the first column contains the reviews
+                        # Get non-empty reviews from the first column
+                        reviews = df.iloc[:, 0].dropna().astype(str).tolist()
+                        return '\n'.join(review.strip() for review in reviews if review.strip())
+                    except Exception as e:
+                        continue
+                
+                # If all encodings fail, try basic string splitting
+                try:
+                    text_content = content.decode('utf-8', errors='ignore')
+                    lines = text_content.strip().split('\n')[1:]  # Skip header
+                    return '\n'.join(line.strip() for line in lines if line.strip())
+                except:
+                    return ""
+            
+            # For text files
+            else:
+                content = file.read()
+                try:
+                    text_content = content.decode('utf-8')
+                except:
+                    text_content = content.decode('utf-8', errors='ignore')
+                return text_content.strip()
+                
+        except Exception as e:
+            logger.error(f"File processing error: {e}")
+            return ""
 
 # Main Application
 class SentimentApp: