feat(v2): add BCL snapshot extractor and command

This commit is contained in:
Alfredo Di Stasio
2026-03-13 14:32:21 +01:00
parent 97913c4a79
commit 5df973467d
9 changed files with 357 additions and 1 deletions

View File

@ -0,0 +1,32 @@
{
"data": [
{
"player": {
"id": "bcl-player-42",
"name": "John Carter",
"first_name": "John",
"last_name": "Carter",
"birth_date": "1999-07-14",
"nationality": "US",
"height_cm": 198,
"weight_kg": 95,
"position": "SF"
},
"team": {
"id": "bcl-team-murcia",
"name": "UCAM Murcia"
},
"gp": 12,
"mpg": 29.1,
"ppg": 16.4,
"rpg": 5.8,
"apg": 2.7,
"spg": 1.5,
"bpg": 0.6,
"tov": 2.3,
"fg_pct": 48.1,
"three_pct": 37.2,
"ft_pct": 81.4
}
]
}

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.bcl import BCLSnapshotExtractor
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_bcl_extractor_normalizes_fixture_payload(tmp_path, settings):
settings.EXTRACTOR_BCL_STATS_URL = "https://www.championsleague.basketball/public/stats.json"
settings.EXTRACTOR_BCL_SEASON_LABEL = "2025-2026"
settings.EXTRACTOR_BCL_COMPETITION_EXTERNAL_ID = "bcl"
settings.EXTRACTOR_BCL_COMPETITION_NAME = "Basketball Champions League"
fixture_payload = _load_fixture("bcl/bcl_players_stats.json")
class FakeClient:
def get_json(self, *_args, **_kwargs):
return fixture_payload
extractor = BCLSnapshotExtractor(http_client=FakeClient())
output_path = tmp_path / "bcl.json"
result = extractor.run(output_path=output_path, snapshot_date=date(2026, 3, 13))
assert result.extractor_name == "bcl"
assert result.source_name == "bcl"
assert result.records_count == 1
payload = json.loads(output_path.read_text(encoding="utf-8"))
assert payload["source_name"] == "bcl"
assert payload["snapshot_date"] == "2026-03-13"
row = payload["records"][0]
assert row["competition_external_id"] == "bcl"
assert row["competition_name"] == "Basketball Champions League"
assert row["team_external_id"] == "bcl-team-murcia"
assert row["team_name"] == "UCAM Murcia"
assert row["player_external_id"] == "bcl-player-42"
assert row["full_name"] == "John Carter"
assert row["minutes_per_game"] == 29.1
assert row["three_pt_pct"] == 37.2
@pytest.mark.django_db
def test_bcl_extractor_registry_selection(settings):
settings.EXTRACTOR_BCL_STATS_URL = "https://www.championsleague.basketball/public/stats.json"
settings.EXTRACTOR_BCL_SEASON_LABEL = "2025-2026"
extractor = create_extractor("bcl")
assert isinstance(extractor, BCLSnapshotExtractor)
@pytest.mark.django_db
def test_run_bcl_extractor_command_writes_snapshot(tmp_path, settings, monkeypatch):
settings.EXTRACTOR_BCL_STATS_URL = "https://www.championsleague.basketball/public/stats.json"
settings.EXTRACTOR_BCL_SEASON_LABEL = "2025-2026"
settings.EXTRACTOR_BCL_COMPETITION_EXTERNAL_ID = "bcl"
settings.EXTRACTOR_BCL_COMPETITION_NAME = "Basketball Champions League"
fixture_payload = _load_fixture("bcl/bcl_players_stats.json")
class FakeClient:
def get_json(self, *_args, **_kwargs):
return fixture_payload
monkeypatch.setattr(
"apps.ingestion.extractors.bcl.ResponsibleHttpClient",
lambda **_kwargs: FakeClient(),
)
call_command(
"run_bcl_extractor",
"--output-path",
str(tmp_path),
"--snapshot-date",
"2026-03-13",
)
files = list(tmp_path.glob("bcl-2026-03-13.json"))
assert len(files) == 1
payload = json.loads(files[0].read_text(encoding="utf-8"))
assert payload["source_name"] == "bcl"
assert len(payload["records"]) == 1