"""Mapper to convert HRNZ scraped data to TipSharks data models.""" import hashlib from datetime import datetime from typing import Any from packages.core.common.logging import get_logger logger = get_logger(__name__) class HRNZDataMapper: """Maps HRNZ scraped data to TipSharks database format. Converts the dictionaries returned by HRNZScraper into the format expected by TipSharks repositories for database insertion. """ @staticmethod def map_meeting(scraped_meeting: dict[str, Any]) -> dict[str, Any]: """Map scraped meeting data to TipSharks meeting format. Args: scraped_meeting: Meeting dict from HRNZScraper Returns: Meeting dict compatible with MeetingRepository.upsert() """ # Generate a meeting ID from date + venue # Format similar to TAB: hash of venue + date date_str = scraped_meeting.get("date", "") venue = scraped_meeting.get("venue", "Unknown") # Create deterministic ID from venue + date meeting_id_seed = f"{venue}_{date_str}" meeting_id = hashlib.md5(meeting_id_seed.encode()).hexdigest()[:8] meeting = { "meeting": meeting_id, # Use "meeting" key for compatibility with TAB format "date": date_str, # Keep ISO format string "name": venue, # Use "name" key for compatibility with TAB format "category": "H", # Harness racing "raw_json": scraped_meeting, # Store original scraped data } return meeting @staticmethod def map_races( scraped_meeting: dict[str, Any], meeting_id: str ) -> list[dict[str, Any]]: """Map scraped races to TipSharks race format. Args: scraped_meeting: Meeting dict from HRNZScraper meeting_id: TipSharks meeting ID Returns: List of race dicts compatible with RaceRepository.upsert() """ races = [] scraped_races = scraped_meeting.get("races", []) meeting_date_str = scraped_meeting.get("date", "") for scraped_race in scraped_races: race = { "meeting_id": meeting_id, "race_number": scraped_race.get("race_number", 0), "distance_m": scraped_race.get("distance_m", 2000), "start_type": scraped_race.get("start_type", "Standing"), "name": scraped_race.get("name", ""), "weather": scraped_race.get("weather"), "track_condition": scraped_race.get("track_condition"), "raw_json": scraped_race, # Store original scraped data } # Construct race datetime (use meeting date at noon if no time given) if meeting_date_str: try: # Default to 12:00 PM if no specific time race_datetime = datetime.fromisoformat( f"{meeting_date_str}T12:00:00" ) # Add race number offset (30 min per race) race_offset_minutes = (race["race_number"] - 1) * 30 from datetime import timedelta race_datetime += timedelta(minutes=race_offset_minutes) # Store as ISO string for JSON serialization race["race_datetime"] = race_datetime.isoformat() except ValueError as e: logger.warning(f"Could not parse race datetime: {e}") # Determine gait (default to Pace for harness racing) race["gait"] = "Pace" # HRNZ doesn't always specify, default to pace races.append(race) return races @staticmethod def map_starters( scraped_meeting: dict[str, Any], race_id_map: dict[int, int], ) -> list[dict[str, Any]]: """Map scraped starters to TipSharks starter format. Args: scraped_meeting: Meeting dict from HRNZScraper race_id_map: Mapping of race_number to database race ID Returns: List of starter dicts compatible with StarterRepository.upsert() """ starters = [] scraped_races = scraped_meeting.get("races", []) for scraped_race in scraped_races: race_number = scraped_race.get("race_number") race_id = race_id_map.get(race_number) if not race_id: logger.warning( f"No database race_id for race {race_number}, skipping starters" ) continue scraped_starters = scraped_race.get("starters", []) for scraped_starter in scraped_starters: # Map horse ID - convert UUID to integer within PostgreSQL INTEGER range horse_uuid = scraped_starter.get("horse_id") horse_name = scraped_starter.get("horse_name", "Unknown") if horse_uuid: horse_id = ( int(hashlib.md5(horse_uuid.encode()).hexdigest()[:8], 16) % 2147483647 ) else: horse_id = ( int(hashlib.md5(horse_name.encode()).hexdigest()[:8], 16) % 2147483647 ) # Map driver ID - convert UUID to integer within PostgreSQL INTEGER range driver_uuid = scraped_starter.get("driver_id") driver_name = scraped_starter.get("driver_name", "Unknown") if driver_uuid: driver_id = ( int(hashlib.md5(driver_uuid.encode()).hexdigest()[:8], 16) % 2147483647 ) else: driver_id = ( int(hashlib.md5(driver_name.encode()).hexdigest()[:8], 16) % 2147483647 ) # Map trainer ID - convert UUID to integer within PostgreSQL INTEGER range trainer_uuid = scraped_starter.get("trainer_id") trainer_name = scraped_starter.get("trainer_name", "Unknown") if trainer_uuid: trainer_id = ( int(hashlib.md5(trainer_uuid.encode()).hexdigest()[:8], 16) % 2147483647 ) else: trainer_id = ( int(hashlib.md5(trainer_name.encode()).hexdigest()[:8], 16) % 2147483647 ) starter = { "race_id": race_id, "horse_id": horse_id, "name": horse_name, # Add "name" field for StarterRepository compatibility "driver_name": driver_name, "trainer_name": trainer_name, "driver_id": driver_id, "trainer_id": trainer_id, "runner_number": scraped_starter.get("runner_number"), "barrier": scraped_starter.get("barrier", 1), "barrier_position": scraped_starter.get("barrier_position"), "handicap_m": scraped_starter.get("handicap_m", 0), "placing": scraped_starter.get("placing"), "did_not_finish": bool(scraped_starter.get("did_not_finish")), "raw_json": scraped_starter, } starters.append(starter) # Also track entities for upserting # Return entity dicts for horses, drivers, trainers return starters @staticmethod def map_entities( scraped_meeting: dict[str, Any], ) -> dict[str, list[dict[str, Any]]]: """Extract and map all entities (horses, drivers, trainers). Args: scraped_meeting: Meeting dict from HRNZScraper Returns: Dict with 'horses', 'drivers', 'trainers' lists """ horses = {} drivers = {} trainers = {} scraped_races = scraped_meeting.get("races", []) for scraped_race in scraped_races: scraped_starters = scraped_race.get("starters", []) for scraped_starter in scraped_starters: # Horse - convert UUID to integer within PostgreSQL INTEGER range horse_uuid = scraped_starter.get("horse_id") horse_name = scraped_starter.get("horse_name", "Unknown") if horse_uuid: # Convert UUID to integer using hash (modulo to fit in PostgreSQL INTEGER) horse_id = ( int(hashlib.md5(horse_uuid.encode()).hexdigest()[:8], 16) % 2147483647 ) else: # Generate from horse name horse_id = ( int(hashlib.md5(horse_name.encode()).hexdigest()[:8], 16) % 2147483647 ) if horse_id not in horses: horses[horse_id] = { "id": horse_id, "name": horse_name, "raw_json": {"source": "hrnz_scraper", "uuid": horse_uuid}, } # Driver - convert UUID to integer within PostgreSQL INTEGER range driver_uuid = scraped_starter.get("driver_id") driver_name = scraped_starter.get("driver_name", "Unknown") if driver_uuid: driver_id = ( int(hashlib.md5(driver_uuid.encode()).hexdigest()[:8], 16) % 2147483647 ) else: driver_id = ( int(hashlib.md5(driver_name.encode()).hexdigest()[:8], 16) % 2147483647 ) if driver_id not in drivers: drivers[driver_id] = { "id": driver_id, "name": driver_name, "raw_json": {"source": "hrnz_scraper", "uuid": driver_uuid}, } # Trainer - convert UUID to integer within PostgreSQL INTEGER range trainer_uuid = scraped_starter.get("trainer_id") trainer_name = scraped_starter.get("trainer_name", "Unknown") if trainer_uuid: trainer_id = ( int(hashlib.md5(trainer_uuid.encode()).hexdigest()[:8], 16) % 2147483647 ) else: trainer_id = ( int(hashlib.md5(trainer_name.encode()).hexdigest()[:8], 16) % 2147483647 ) if trainer_id not in trainers: trainers[trainer_id] = { "id": trainer_id, "name": trainer_name, "raw_json": {"source": "hrnz_scraper", "uuid": trainer_uuid}, } return { "horses": list(horses.values()), "drivers": list(drivers.values()), "trainers": list(trainers.values()), }