Update app.py

app.py

@@ -74,40 +74,47 @@ def read_file(file):
     try:
         # Handle different file types
         if file_name.endswith('.csv'):
-            # First try with comma
+            # Try multiple separators in sequence
+            separators = [',', ';', '\t', '|']
+            errors = []
+            
+            for sep in separators:
+                try:
+                    # For each attempt, we need a fresh file upload
+                    # Try with the current separator
+                    df = pd.read_csv(file, sep=sep)
+                    
+                    # If we got a reasonable number of columns, it probably worked
+                    if len(df.columns) > 1:
+                        print(f"Successfully read CSV with separator '{sep}': {df.shape}")
+                        
+                        # Convert columns to appropriate types
+                        for col in df.columns:
+                            # Try to convert string columns to numeric
+                            if df[col].dtype == 'object':
+                                df[col] = pd.to_numeric(df[col], errors='ignore')
+                        
+                        return df
+                    else:
+                        errors.append(f"Only got {len(df.columns)} columns with '{sep}' separator")
+                except Exception as e:
+                    errors.append(f"Error with '{sep}' separator: {str(e)}")
+            
+            # If we reach here, all separators failed
+            error_msg = "\n".join(errors)
+            print(f"All separators failed: {error_msg}")
+            
+            # Make one final attempt with Python's CSV sniffer
             try:
-                df = pd.read_csv(file)
-                
-                # Check if we got only one column but it contains semicolons
-                if len(df.columns) == 1 and ';' in str(df.columns[0]):
-                    print("Detected potential semicolon-separated file")
-                    # Reset file position
-                    file.seek(0)
-                    # Try with semicolon
-                    df = pd.read_csv(file, sep=';')
-                    print(f"Read file with semicolon separator: {df.shape}")
+                df = pd.read_csv(file, sep=None, engine='python')
+                if len(df.columns) > 1:
+                    print(f"Read CSV with automatic separator detection: {df.shape}")
+                    return df
                 else:
-                    print(f"Read file with comma separator: {df.shape}")
-                
-                # Convert columns to appropriate types
-                for col in df.columns:
-                    # Try to convert string columns to numeric
-                    if df[col].dtype == 'object':
-                        df[col] = pd.to_numeric(df[col], errors='ignore')
-                
-                return df
+                    return "Could not detect the appropriate separator for this CSV file."
             except Exception as e:
-                print(f"Error with standard separators: {e}")
-                # Try with semicolon
-                file.seek(0)
-                try:
-                    df = pd.read_csv(file, sep=';')
-                    print(f"Read file with semicolon separator after error: {df.shape}")
-                    return df
-                except:
-                    # Final attempt with Python's csv sniffer
-                    file.seek(0)
-                    return pd.read_csv(file, sep=None, engine='python')
+                print(f"Error with automatic separator detection: {e}")
+                return "Could not read the CSV file. Please check the file format and try again."
                 
         elif file_name.endswith(('.xls', '.xlsx')):
             return pd.read_excel(file)
@@ -117,15 +124,14 @@ def read_file(file):
             # Try tab separator first for text files
             try:
                 df = pd.read_csv(file, delimiter='\t')
-                if len(df.columns) <= 1:
-                    # If tab doesn't work well, try with separator detection
-                    file.seek(0)
-                    df = pd.read_csv(file, sep=None, engine='python')
-                return df
-            except:
-                # Fall back to separator detection
-                file.seek(0)
-                return pd.read_csv(file, sep=None, engine='python')
+                if len(df.columns) > 1:
+                    return df
+                else:
+                    # Try with automatic separator detection
+                    return pd.read_csv(file, sep=None, engine='python')
+            except Exception as e:
+                print(f"Error reading text file: {e}")
+                return f"Error reading text file: {str(e)}"
         else:
             return "Unsupported file format. Please upload .csv, .xlsx, .xls, .json, or .txt files."
     except Exception as e: