feat: more checks for TIME_TRIAL races

fixtures/html/traineras_details.html

@@ -10,7 +10,7 @@ <h1>BANDERA TERESA HERRERA 2012</h1>
                     <div>
                         <div>
                             <div>
-                                <h2>A Coruña - 11-08-2012 (17:30) - 5556 metros - SM</h2>
+                                <h2>A Coruña - 12-08-2012 (17:30) - 5556 metros - SM</h2>
                             </div>
                             <div>
                                 <table>

rscraping/clients/tabular.py

@@ -8,7 +8,7 @@
 
 from pyutils.shortcuts import only_one_not_none
 from pyutils.strings import roman_to_int
-from rscraping.data.functions import is_female
+from rscraping.data.checks import is_female
 from rscraping.data.models import Datasource, Lineup, Race, RaceName
 from rscraping.parsers.df import (
     COLUMN_CLUB,

rscraping/data/checks.py

@@ -0,0 +1,55 @@
+from datetime import date
+
+from pyutils.strings import remove_symbols
+from rscraping.data.constants import SYNONYM_FEMALE, SYNONYM_MEMORIAL, SYNONYMS
+
+
+def should_be_time_trial(name: str, date: date) -> bool:
+    return is_play_off(name) or (all(w in name.split() for w in ["TERESA", "HERRERA"]) and date.isoweekday() == 6)
+
+
+def is_play_off(name: str) -> bool:
+    return "PLAY" in name and "OFF" in name
+
+
+def is_memorial(name: str) -> bool:
+    return any(w in name.split() for w in SYNONYMS[SYNONYM_MEMORIAL])
+
+
+def is_female(name: str) -> bool:
+    return any(w in name.split() for w in SYNONYMS[SYNONYM_FEMALE])
+
+
+def is_branch_club(name: str, letter: str = "B") -> bool:
+    clean_name = remove_symbols(name)
+    return any(e == letter for e in clean_name.upper().split())
+
+
+def is_act(name: str, is_female: bool = False) -> bool:
+    if is_female:
+        return "EUSKOTREN" in name
+    return all(w in name.split() for w in ["EUSKO", "LABEL"]) or "ACT" in name.split() or "EUSKOLABEL" in name
+
+
+def is_lgt(name: str, letter: str = "A") -> bool:
+    match letter:
+        case "A":
+            return all(w in name.split() for w in ["LGT", "A"]) or "LGTA" in name
+        case "B":
+            return all(w in name.split() for w in ["LGT", "B"]) or "LGTB" in name
+        case "F":
+            return all(w in name.split() for w in ["LGT", "F"]) or "LGTF" in name
+    raise ValueError(f"Invalid letter: {letter}")
+
+
+def is_arc(name: str, category: int = 1) -> bool:
+    match category:
+        case 1:
+            return "ARC" in name.split()
+        case 2:
+            return "ARC2" in name.split()
+    raise ValueError(f"Invalid category: {category}")
+
+
+def is_ete(name: str) -> bool:
+    return "ETE" in name.split()

rscraping/data/functions.py

@@ -3,58 +3,9 @@
 import sys
 from typing import Any
 
-from pyutils.strings import remove_symbols
-from rscraping.data.constants import SYNONYM_FEMALE, SYNONYM_MEMORIAL, SYNONYMS
 from rscraping.data.models import Lineup, Race
 
 
-def is_play_off(name: str) -> bool:
-    return "PLAY" in name and "OFF" in name
-
-
-def is_memorial(name: str) -> bool:
-    return any(w in name.split() for w in SYNONYMS[SYNONYM_MEMORIAL])
-
-
-def is_female(name: str) -> bool:
-    return any(w in name.split() for w in SYNONYMS[SYNONYM_FEMALE])
-
-
-def is_branch_club(name: str, letter: str = "B") -> bool:
-    clean_name = remove_symbols(name)
-    return any(e == letter for e in clean_name.upper().split())
-
-
-def is_act(name: str, is_female: bool = False) -> bool:
-    if is_female:
-        return "EUSKOTREN" in name
-    return all(w in name.split() for w in ["EUSKO", "LABEL"]) or "ACT" in name.split() or "EUSKOLABEL" in name
-
-
-def is_lgt(name: str, letter: str = "A") -> bool:
-    match letter:
-        case "A":
-            return all(w in name.split() for w in ["LGT", "A"]) or "LGTA" in name
-        case "B":
-            return all(w in name.split() for w in ["LGT", "B"]) or "LGTB" in name
-        case "F":
-            return all(w in name.split() for w in ["LGT", "F"]) or "LGTF" in name
-    raise ValueError(f"Invalid letter: {letter}")
-
-
-def is_arc(name: str, category: int = 1) -> bool:
-    match category:
-        case 1:
-            return "ARC" in name.split()
-        case 2:
-            return "ARC2" in name.split()
-    raise ValueError(f"Invalid category: {category}")
-
-
-def is_ete(name: str) -> bool:
-    return "ETE" in name.split()
-
-
 def expand_path(path: str, valid_files: list[str]) -> list[str]:
     def is_valid(file: str) -> bool:
         _, extension = os.path.splitext(file)

rscraping/data/normalization/clubs.py

@@ -1,7 +1,7 @@
 import re
 
 from pyutils.strings import match_normalization, remove_parenthesis, whitespaces_clean
-from rscraping.data.functions import is_branch_club
+from rscraping.data.checks import is_branch_club
 
 _ENTITY_TITLES_SHORT = [
     "CR",

rscraping/data/normalization/leagues.py

@@ -1,5 +1,5 @@
 from pyutils.strings import match_normalization
-from rscraping.data.functions import is_act, is_arc, is_ete, is_lgt, is_play_off
+from rscraping.data.checks import is_act, is_arc, is_ete, is_lgt, is_play_off
 
 __LEAGUES_MAP = {
     "LIGA GALEGA DE TRAIÑAS": [["LGT"]],

rscraping/data/normalization/races.py

@@ -9,7 +9,7 @@
     roman_to_int,
     whitespaces_clean,
 )
-from rscraping.data.functions import is_play_off
+from rscraping.data.checks import is_play_off
 
 _MISSPELLINGS = {
     "": ["RECICLAMOS LA LUZ", " AE ", "EXCMO", "ILTMO"],

rscraping/parsers/html/act.py

@@ -7,6 +7,7 @@
 from parsel.selector import Selector
 
 from pyutils.strings import find_date, remove_parenthesis, whitespaces_clean
+from rscraping.data.checks import is_play_off
 from rscraping.data.constants import (
     CATEGORY_ABSOLUT,
     GENDER_FEMALE,
@@ -15,7 +16,6 @@
     RACE_TIME_TRIAL,
     RACE_TRAINERA,
 )
-from rscraping.data.functions import is_play_off
 from rscraping.data.models import Datasource, Participant, Race, RaceName
 from rscraping.data.normalization.clubs import normalize_club_name
 from rscraping.data.normalization.races import (

rscraping/parsers/html/arc.py

@@ -8,6 +8,7 @@
 from parsel.selector import Selector
 
 from pyutils.strings import remove_parenthesis, whitespaces_clean
+from rscraping.data.checks import is_play_off
 from rscraping.data.constants import (
     CATEGORY_ABSOLUT,
     GENDER_FEMALE,
@@ -16,7 +17,6 @@
     RACE_TIME_TRIAL,
     RACE_TRAINERA,
 )
-from rscraping.data.functions import is_play_off
 from rscraping.data.models import Datasource, Lineup, Participant, Race, RaceName
 from rscraping.data.normalization.clubs import normalize_club_name
 from rscraping.data.normalization.races import (

rscraping/parsers/html/lgt.py

@@ -8,6 +8,7 @@
 from parsel.selector import Selector
 
 from pyutils.strings import whitespaces_clean
+from rscraping.data.checks import is_female, is_play_off
 from rscraping.data.constants import (
     CATEGORY_ABSOLUT,
     GENDER_FEMALE,
@@ -18,7 +19,6 @@
     SYNONYM_FEMALE,
     SYNONYMS,
 )
-from rscraping.data.functions import is_female, is_play_off
 from rscraping.data.models import Datasource, Participant, Race, RaceName
 from rscraping.data.normalization import (
     find_race_sponsor,

rscraping/parsers/html/traineras.py

@@ -7,6 +7,7 @@
 from parsel.selector import Selector
 
 from pyutils.strings import find_date, whitespaces_clean
+from rscraping.data.checks import should_be_time_trial
 from rscraping.data.constants import (
     CATEGORY_ABSOLUT,
     CATEGORY_SCHOOL,
@@ -17,7 +18,6 @@
     RACE_TIME_TRIAL,
     RACE_TRAINERA,
 )
-from rscraping.data.functions import is_play_off
 from rscraping.data.models import Datasource, Lineup, Participant, Race, RaceName
 from rscraping.data.normalization import (
     find_league,
@@ -81,7 +81,7 @@ def parse_race(self, selector: Selector, *, race_id: str, table: int | None = No
 
         participants = self.get_participants(selector, table)
         ttype = self.get_type(participants)
-        ttype = ttype if not is_play_off(name) else RACE_TIME_TRIAL
+        ttype = ttype if not should_be_time_trial(name, t_date) else RACE_TIME_TRIAL
         category = self.get_category(selector)
 
         race = Race(

tests/parsers/html/traineras_parser_test.py

@@ -104,7 +104,7 @@ def test_get_number_of_pages(self):
 
     _RACE_1 = Race(
         name="BANDERA TERESA HERRERA",
-        date="11/08/2012",
+        date="12/08/2012",
         day=1,
         modality=RACE_TRAINERA,
         type=RACE_CONVENTIONAL,