add known races normalization

requirements.txt

@@ -1,12 +1,12 @@
 fillpdf==0.7.2
 inquirer==3.1.3
-matplotlib==3.8.0
+matplotlib==3.8.1
 numpy==1.26.1
 opencv-python==4.8.1.78
 openpyxl==3.1.2
-pandas==2.1.1
+pandas==2.1.2
 parsel==1.8.1
-PyMuPDF==1.23.4
+PyMuPDF==1.23.6
 pytesseract==0.3.10
 pyutils @ git+https://github.com/iagocanalejas/pyutils.git@master
 reportlab~=4.0.5

rscraping/data/normalization/races.py

@@ -29,6 +29,11 @@
 ]
 
 
+_NORMALIZED_RACES = {
+    "DONIBANE ZIBURUKO ESTROPADAK": [["SAN", "JUAN", "LUZ"]],
+}
+
+
 def normalize_name_parts(normalized_name: str) -> list[tuple[str, int | None]]:
     parts: list[tuple[str, int | None]] = []
     normalized_name = remove_parenthesis(whitespaces_clean(normalized_name))
@@ -51,6 +56,7 @@ def normalize_race_name(name: str) -> str:
     name = amend_race_name(name)
     name = remove_league_indicator(name)
     name = remove_race_sponsor(name)
+    name = normalize_race_known_synonyms(name)
 
     return whitespaces_clean(name)
 
@@ -111,3 +117,11 @@ def amend_race_name(name: str) -> str:
     for a, b in _MISSPELLINGS:
         name = name.replace(a, b)
     return whitespaces_clean(name)
+
+
+def normalize_race_known_synonyms(name: str) -> str:
+    for synonym, values in _NORMALIZED_RACES.items():
+        for value in values:
+            if name in " ".join(value) or all(v in name for v in value):
+                return synonym
+    return name