add entity & race normalizations

rscraping/data/normalization/clubs.py

@@ -59,6 +59,7 @@
     "BUEU": ["BUEU TECCARSA"],
     "ESTEIRANA": ["ESTEIRANA REMO"],
     "A CABANA": ["A CABANA FERROL"],
+    "MUGARDOS - A CABANA": ["MUGARDOS - A CABANA FERROL"],
     "RIVEIRA": ["DE RIVEIRA"],
     "ZARAUTZ": ["ZARAUTZ GESALAGA-OKELAN", "ZARAUTZ INMOB. ORIO"],
     "PASAI DONIBANE KOXTAPE": ["P.DONIBANE IBERDROLA"],
@@ -130,6 +131,8 @@ def normalize_club_name(name: str) -> str:
 def deacronym_club_name(name: str) -> str:
     if any(w in ["P", "D", "PD"] for w in name.split()):
         name = re.sub(r"P\.? ?D\.?", "PASAIA DONIBANE", name)
+    if "CABANA" in name:
+        name = name.replace("CABANA FERROL", "CABANA")
     return whitespaces_clean(name)
 
 

rscraping/parsers/html/lgt.py

@@ -243,6 +243,12 @@ def _normalize_race_name(name: str, t_date: date) -> str:
         if "TERESA HERRERA" in name:  # lgt never saves the final
             return "TROFEO TERESA HERRERA" if t_date.isoweekday() == 7 else "TROFEO TERESA HERRERA (CLASIFICATORIA)"
 
+        if all(n in name for n in ["ILLA", "SAMERTOLAMEU"]) and t_date.year in [2021, 2022, 2023]:
+            # HACK: this is a weird flag case in witch Meira restarted the edition for his 'B' team.
+            # We have "III BANDEIRA ILLA DO SAMERTOLAMEU" in 2017 for his main team and
+            # "III BANDEIRA ILLA DO SAMERTOLAMEU" in 2023 for his 'B' team. So we need to differentiate them.
+            return "BANDEIRA ILLA DO SAMERTOLAMEU B"
+
         if "PLAY" in name:
             return "PLAY-OFF LGT"