feat(v2): add LBA snapshot extractor and command

This commit is contained in:
Alfredo Di Stasio
2026-03-13 14:28:35 +01:00
parent 850e4de71b
commit 97913c4a79
9 changed files with 358 additions and 0 deletions

View File

@ -0,0 +1,32 @@
{
"data": [
{
"player": {
"id": "p-001",
"name": "Marco Rossi",
"first_name": "Marco",
"last_name": "Rossi",
"birth_date": "2000-01-05",
"nationality": "IT",
"height_cm": 190,
"weight_kg": 84,
"position": "PG"
},
"team": {
"id": "team-virtus-bologna",
"name": "Virtus Bologna"
},
"gp": 20,
"mpg": 28.3,
"ppg": 15.8,
"rpg": 3.4,
"apg": 5.9,
"spg": 1.4,
"bpg": 0.2,
"tov": 2.1,
"fg_pct": 47.6,
"three_pct": 36.5,
"ft_pct": 84.2
}
]
}

View File

@ -0,0 +1,92 @@
from __future__ import annotations
import json
from datetime import date
from pathlib import Path
import pytest
from django.core.management import call_command
from apps.ingestion.extractors.lba import LBASnapshotExtractor
from apps.ingestion.extractors.registry import create_extractor
def _load_fixture(path: str) -> dict:
fixture_path = Path(__file__).parent / "fixtures" / path
return json.loads(fixture_path.read_text(encoding="utf-8"))
@pytest.mark.django_db
def test_lba_extractor_normalizes_fixture_payload(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.json")
class FakeClient:
def get_json(self, *_args, **_kwargs):
return fixture_payload
extractor = LBASnapshotExtractor(http_client=FakeClient())
output_path = tmp_path / "lba.json"
result = extractor.run(output_path=output_path, snapshot_date=date(2026, 3, 13))
assert result.extractor_name == "lba"
assert result.source_name == "lba"
assert result.records_count == 1
payload = json.loads(output_path.read_text(encoding="utf-8"))
assert payload["source_name"] == "lba"
assert payload["snapshot_date"] == "2026-03-13"
row = payload["records"][0]
assert row["competition_external_id"] == "lba-serie-a"
assert row["competition_name"] == "Lega Basket Serie A"
assert row["team_external_id"] == "team-virtus-bologna"
assert row["team_name"] == "Virtus Bologna"
assert row["player_external_id"] == "p-001"
assert row["full_name"] == "Marco Rossi"
assert row["minutes_per_game"] == 28.3
assert row["three_pt_pct"] == 36.5
@pytest.mark.django_db
def test_lba_extractor_registry_selection(settings):
settings.EXTRACTOR_LBA_STATS_URL = "https://www.legabasket.it/public/stats.json"
settings.EXTRACTOR_LBA_SEASON_LABEL = "2025-2026"
extractor = create_extractor("lba")
assert isinstance(extractor, LBASnapshotExtractor)
@pytest.mark.django_db
def test_run_lba_extractor_command_writes_snapshot(tmp_path, settings, monkeypatch):
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.json")
class FakeClient:
def get_json(self, *_args, **_kwargs):
return fixture_payload
monkeypatch.setattr(
"apps.ingestion.extractors.lba.ResponsibleHttpClient",
lambda **_kwargs: FakeClient(),
)
call_command(
"run_lba_extractor",
"--output-path",
str(tmp_path),
"--snapshot-date",
"2026-03-13",
)
files = list(tmp_path.glob("lba-2026-03-13.json"))
assert len(files) == 1
payload = json.loads(files[0].read_text(encoding="utf-8"))
assert payload["source_name"] == "lba"
assert len(payload["records"]) == 1