bisco/hoopscout
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source
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
Download Patch File Download Diff File Expand all files Collapse all files

24
apps/ingestion/extractors/bcl.py
View File

@ -16,6 +16,28 @@ def _first_non_empty(record: dict[str, Any], *keys: str) -> Any:
return None
ESSENTIAL_FIELDS = {
"competition_external_id",
"competition_name",
"season",
"team_external_id",
"team_name",
"player_external_id",
"full_name",
"games_played",
"minutes_per_game",
"points_per_game",
"rebounds_per_game",
"assists_per_game",
"steals_per_game",
"blocks_per_game",
"turnovers_per_game",
"fg_pct",
"three_pt_pct",
"ft_pct",
}
class BCLSnapshotExtractor(BaseSnapshotExtractor):
"""
Basketball Champions League MVP extractor.
@ -122,7 +144,7 @@ class BCLSnapshotExtractor(BaseSnapshotExtractor):
"ft_pct": _first_non_empty(source_record, "ft_pct", "ft_percentage"),
}
missing = [key for key, value in normalized.items() if key != "role" and value in (None, "")]
missing = [key for key in ESSENTIAL_FIELDS if normalized.get(key) in (None, "")]
if missing:
raise ExtractorNormalizationError(f"bcl row missing required fields: {', '.join(sorted(missing))}")

24
apps/ingestion/extractors/lba.py
View File

@ -16,6 +16,28 @@ def _first_non_empty(record: dict[str, Any], *keys: str) -> Any:
return None
ESSENTIAL_FIELDS = {
"competition_external_id",
"competition_name",
"season",
"team_external_id",
"team_name",
"player_external_id",
"full_name",
"games_played",
"minutes_per_game",
"points_per_game",
"rebounds_per_game",
"assists_per_game",
"steals_per_game",
"blocks_per_game",
"turnovers_per_game",
"fg_pct",
"three_pt_pct",
"ft_pct",
}
class LBASnapshotExtractor(BaseSnapshotExtractor):
"""
LBA (Lega Basket Serie A) MVP extractor.
@ -122,7 +144,7 @@ class LBASnapshotExtractor(BaseSnapshotExtractor):
"ft_pct": _first_non_empty(source_record, "ft_pct", "ft_percentage"),
}
missing = [key for key, value in normalized.items() if key != "role" and value in (None, "")]
missing = [key for key in ESSENTIAL_FIELDS if normalized.get(key) in (None, "")]
if missing:
raise ExtractorNormalizationError(f"lba row missing required fields: {', '.join(sorted(missing))}")