fix(v2-ingestion): harden LBA/BCL snapshot contract for public data

This commit is contained in:
Alfredo Di Stasio
2026-03-20 14:46:25 +01:00
parent 1aad6945c7
commit 6066d2a0bb
10 changed files with 339 additions and 31 deletions

View File

@ -8,6 +8,7 @@ import pytest
from django.core.management import call_command
from apps.ingestion.extractors.lba import LBASnapshotExtractor
from apps.ingestion.extractors.base import ExtractorNormalizationError
from apps.ingestion.extractors.registry import create_extractor
@ -51,6 +52,56 @@ def test_lba_extractor_normalizes_fixture_payload(tmp_path, settings):
assert row["three_pt_pct"] == 36.5
@pytest.mark.django_db
def test_lba_extractor_accepts_partial_public_player_bio_fields(tmp_path, settings):
settings.EXTRACTOR_LBA_STATS_URL = "https://www.legabasket.it/public/stats.json"
settings.EXTRACTOR_LBA_SEASON_LABEL = "2025-2026"
settings.EXTRACTOR_LBA_COMPETITION_EXTERNAL_ID = "lba-serie-a"
settings.EXTRACTOR_LBA_COMPETITION_NAME = "Lega Basket Serie A"
fixture_payload = _load_fixture("lba/lba_players_stats_partial_public.json")
class FakeClient:
def get_json(self, *_args, **_kwargs):
return fixture_payload
extractor = LBASnapshotExtractor(http_client=FakeClient())
output_path = tmp_path / "lba-partial.json"
result = extractor.run(output_path=output_path, snapshot_date=date(2026, 3, 13))
assert result.records_count == 1
payload = json.loads(output_path.read_text(encoding="utf-8"))
row = payload["records"][0]
assert row["full_name"] == "Andrea Bianchi"
assert row["first_name"] is None
assert row["last_name"] is None
assert row["birth_date"] is None
assert row["nationality"] is None
assert row["height_cm"] is None
assert row["weight_kg"] is None
assert row["position"] is None
assert row["games_played"] == 18
@pytest.mark.django_db
def test_lba_extractor_still_fails_when_required_stats_are_missing(settings):
settings.EXTRACTOR_LBA_STATS_URL = "https://www.legabasket.it/public/stats.json"
settings.EXTRACTOR_LBA_SEASON_LABEL = "2025-2026"
settings.EXTRACTOR_LBA_COMPETITION_EXTERNAL_ID = "lba-serie-a"
settings.EXTRACTOR_LBA_COMPETITION_NAME = "Lega Basket Serie A"
fixture_payload = _load_fixture("lba/lba_players_stats_partial_public.json")
fixture_payload["data"][0].pop("ppg")
class FakeClient:
def get_json(self, *_args, **_kwargs):
return fixture_payload
extractor = LBASnapshotExtractor(http_client=FakeClient())
with pytest.raises(ExtractorNormalizationError):
extractor.run(write_output=False, snapshot_date=date(2026, 3, 13))
@pytest.mark.django_db
def test_lba_extractor_registry_selection(settings):
settings.EXTRACTOR_LBA_STATS_URL = "https://www.legabasket.it/public/stats.json"