Fix handling of duplicate competition IDs in SoaringSpot

opensoar/competition/soaringspot.py

@@ -3,6 +3,7 @@
 The files from SoaringSpot always contain task information, which can be used for competition analysis.
 """
 import datetime
+import logging
 import re
 from typing import List, Tuple, Union, Optional
 from urllib.error import URLError
@@ -21,6 +22,8 @@
 from opensoar.competition.daily_results_page import DailyResultsPage
 from opensoar.utilities.helper_functions import double_iterator
 
+logger = logging.getLogger(__name__)
+
 
 def get_comment_lines_from_parsed_file(parsed_igc_file: dict) -> List[str]:
     """In the parsed file, lines are split into source and comment. This function stiches them back together"""
@@ -268,12 +271,18 @@ def _get_competitors_info(self, include_hc_competitors: bool, include_dns_compet
         Returns:
             List of dictionaries with competitor information:
             - ranking: Position in the competition or status (DNF/DNS)
-            - competition_id: Glider ID
+            - competition_id: Glider ID (modified with suffix _2, _3, etc. if duplicate)
             - igc_url: URL to download the IGC file (None for DNF/DNS)
             - pilot_name: Name of the pilot
             - plane_model: Type of glider
+
+        Note:
+            If duplicate competition IDs are found, they will be automatically resolved by
+            appending a suffix (_2, _3, etc.) to ensure unique identification. A warning
+            will be printed to inform the user.
         """
         competitors_info = []
+        seen_competition_ids = {}  # Track competition IDs and their count
 
         table = self._get_html_soup().find("table")
         if not table:
@@ -326,7 +335,7 @@ def _get_competitors_info(self, include_hc_competitors: bool, include_dns_compet
             # Extract competition ID from CN column
             cn_idx = min(col_indices['cn'], len(cells) - 1)
             cn_cell = cells[cn_idx]
-            competition_id = cn_cell.text.strip()
+            original_competition_id = cn_cell.text.strip()
 
             # Extract pilot name from pilot/contestant column
             pilot_idx = min(col_indices['pilot'], len(cells) - 1)
@@ -344,6 +353,16 @@ def _get_competitors_info(self, include_hc_competitors: bool, include_dns_compet
             if glider_idx < len(cells):
                 plane_model = cells[glider_idx].text.strip()
 
+            # Handle duplicate competition IDs
+            if original_competition_id in seen_competition_ids:
+                seen_competition_ids[original_competition_id] += 1
+                competition_id = f"{original_competition_id}_{seen_competition_ids[original_competition_id]}"
+                logger.warning(f"Duplicate competition ID '{original_competition_id}' detected for pilot '{pilot_name}'. "
+                               f"Using '{competition_id}' instead.")
+            else:
+                seen_competition_ids[original_competition_id] = 1
+                competition_id = original_competition_id
+
             # Handle HC competitors
             if status == "HC":
                 if not include_hc_competitors:

tests/competition/test_soaringspot.py

@@ -171,6 +171,50 @@ def test_get_competitors_info_relative_downloads(self):
         competitors = soaringspot_page._get_competitors_info(include_hc_competitors=False)
         self.assertEqual(len(competitors), 10)
 
+    def test_get_competitors_with_duplicate_ids(self):
+        """Test handling of duplicate competition IDs"""
+        soaringspot_page = SoaringSpotDaily(
+            'https://www.soaringspot.com/nl/keiheuvelcup2025/results/open-xpdr/task-1-on-2025-08-23/daily'
+        )
+
+        competitors = soaringspot_page._get_competitors_info(include_hc_competitors=True)
+
+        # Check that we got all competitors (34 total on this page)
+        self.assertEqual(len(competitors), 34)
+
+        # Extract all competition IDs
+        competition_ids = [comp['competition_id'] for comp in competitors]
+
+        # Check that all competition IDs are unique after processing
+        self.assertEqual(len(competition_ids), len(set(competition_ids)), 
+                        "Duplicate competition IDs detected after processing")
+
+        # Find the pilots who originally had 'FS' as competition ID
+        fs_pilots = [comp for comp in competitors if comp['competition_id'].startswith('FS')]
+
+        # Should have 2 pilots with FS-based IDs
+        self.assertEqual(len(fs_pilots), 2, 
+                        "Expected 2 pilots with FS competition ID")
+
+        # Verify the pilots are correct (Daan Spruyt and Flens Piet)
+        pilot_names = {comp['pilot_name'] for comp in fs_pilots}
+        self.assertIn('Daan Spruyt', pilot_names)
+        self.assertIn('Flens Piet', pilot_names)
+
+        # One should have 'FS' and the other should have 'FS_2'
+        fs_ids = {comp['competition_id'] for comp in fs_pilots}
+        self.assertIn('FS', fs_ids)
+        self.assertIn('FS_2', fs_ids)
+
+        # Verify rankings are preserved
+        for comp in fs_pilots:
+            if comp['pilot_name'] == 'Daan Spruyt':
+                self.assertEqual(comp['ranking'], 2)
+                self.assertEqual(comp['plane_model'], 'Ventus 2ax')
+            elif comp['pilot_name'] == 'Flens Piet':
+                self.assertEqual(comp['ranking'], 32)
+                self.assertEqual(comp['plane_model'], 'DG 808C Classic 18m')
+
     # disabled because this URL is no longer used. unclear whether all dev urls are cleared
     # def test_get_competitors_dev_url(self):
     #     soaringspot_page = SoaringSpotDaily(