Refine lineup string processing in load_contest_file function

- Updated regex logic to ensure position indicators are only replaced at the start of player entries and not within player names, enhancing accuracy in lineup formatting.
- Adjusted the removal of position indicators to target only those at the end of each entry, ensuring cleaner data output.
- These changes contribute to ongoing efforts to improve data integrity and user experience within the application.

global_func/load_contest_file.py

@@ -26,10 +26,12 @@ def load_contest_file(upload, sport):
             df['EntryCount'] = df['EntryCount'].fillna('1/1')  # Default to 1/1 if no entry count
             
             # Split the lineup string by replacing position indicators with commas
-            # Only replace position indicators that are at the start of a player entry
-            df['Lineup'] = df['Lineup'].str.replace(r'(?<!\w)(' + '|'.join(pos_values) + r')\b', r'\1,', regex=True)
+            # We need to ensure we only replace position indicators that are at the start of a player entry
+            # and not those that might appear within player names
+            df['Lineup'] = df['Lineup'].str.replace(r'\b(' + '|'.join(pos_values) + r')\b', r'\1,', regex=True)
             
             # Split into individual columns and remove position indicators
+            # First, determine the maximum number of players in any lineup
             max_players = int(df['Lineup'].str.split(',').str.len().max())
             
             if max_players <= 0:
@@ -39,8 +41,8 @@ def load_contest_file(upload, sport):
             # Create columns for each player
             for i in range(1, max_players):
                 df[i] = df['Lineup'].str.split(',').str[i].str.strip()
-                # Only remove position indicators that are at the end of the entry
-                df[i] = df[i].str.replace(r'\b(' + '|'.join(pos_values) + r')\s*$', '', regex=True)
+                # Remove position indicators from the end of each entry
+                df[i] = df[i].str.replace(r'\s+(' + '|'.join(pos_values) + r')$', '', regex=True)
             
             if sport == 'MLB':
                 df = df.rename(columns={1: '1B', 2: '2B', 3: '3B', 4: 'C', 5: 'OF1', 6: 'OF2', 7: 'OF3', 8: 'SP1', 9: 'SP2', 10: 'SS'})