[boundaries] Adding regex replacements for boundary names such as Lyon 2e Arrondissement where putting Lyon is the OSM convention but we might sometimes want just 2e Arrondissement to appear in the training data next to Lyon

resources/boundaries/names/global.yaml

@@ -29,6 +29,12 @@ names:
                     - alternative: official_name # e.g. United Kingdom of Great Britain and Northern Ireland
                       probability: 0.01
 
+    regex_replacements:
+        - country: fr
+          pattern: "(?:lyon|paris|marseilles) ([\\d]+er? arrondissement)"
+          replace_with_group: 1
+          replace_probability: 0.5
+
     # This section overrides place names
     exceptions:
         # Boroughs of New York City