"""Player/team name normalization for cross-source matching.""" import re import unicodedata import logging from typing import Optional, Tuple log = logging.getLogger("pub-integrity") # Common suffixes/prefixes to strip for matching _SUFFIXES = re.compile(r'\s+(Jr\.?|Sr\.?|III|II|IV|V)$', re.IGNORECASE) _NON_ALPHA = re.compile(r'[^a-z\s]') _MULTI_SPACE = re.compile(r'\s+') # Team abbreviation normalization map TEAM_ABBREV_MAP = { # NBA "ATL": "ATL", "BOS": "BOS", "BKN": "BKN", "CHA": "CHA", "CHI": "CHI", "CLE": "CLE", "DAL": "DAL", "DEN": "DEN", "DET": "DET", "GSW": "GSW", "HOU": "HOU", "IND": "IND", "LAC": "LAC", "LAL": "LAL", "MEM": "MEM", "MIA": "MIA", "MIL": "MIL", "MIN": "MIN", "NOP": "NOP", "NYK": "NYK", "OKC": "OKC", "ORL": "ORL", "PHI": "PHI", "PHX": "PHX", "POR": "POR", "SAC": "SAC", "SAS": "SAS", "TOR": "TOR", "UTA": "UTA", "WAS": "WAS", # NHL "ANA": "ANA", "ARI": "ARI", "BUF": "BUF", "CGY": "CGY", "CAR": "CAR", "COL": "COL", "CBJ": "CBJ", "EDM": "EDM", "FLA": "FLA", "LA": "LAK", "LAK": "LAK", "MTL": "MTL", "NSH": "NSH", "NJD": "NJD", "NYI": "NYI", "NYR": "NYR", "OTT": "OTT", "PIT": "PIT", "SEA": "SEA", "SJS": "SJS", "STL": "STL", "TBL": "TBL", "VAN": "VAN", "VGK": "VGK", "WPG": "WPG", # MLB "BAL": "BAL", "TB": "TBR", "TBR": "TBR", "NYY": "NYY", "NYM": "NYM", "KC": "KCR", "KCR": "KCR", "CWS": "CWS", "SF": "SFG", "SFG": "SFG", "SD": "SDP", "SDP": "SDP", "TEX": "TEX", "HOU": "HOU", "SEA": "SEA", "CIN": "CIN", "MIL": "MIL", "PIT": "PIT", "STL": "STL", # Common aliases "GS": "GSW", "SA": "SAS", "NO": "NOP", "NY": "NYK", "PHO": "PHX", "UTAH": "UTA", "WASH": "WAS", } # Full team name -> canonical abbreviation used by roster/prop integrity checks. # Keep this focused on leagues where prop eligibility matters today. TEAM_NAME_MAP = { # NBA "atlanta hawks": "ATL", "boston celtics": "BOS", "brooklyn nets": "BKN", "charlotte hornets": "CHA", "chicago bulls": "CHI", "cleveland cavaliers": "CLE", "dallas mavericks": "DAL", "denver nuggets": "DEN", "detroit pistons": "DET", "golden state warriors": "GSW", "houston rockets": "HOU", "indiana pacers": "IND", "la clippers": "LAC", "los angeles clippers": "LAC", "la lakers": "LAL", "los angeles lakers": "LAL", "memphis grizzlies": "MEM", "miami heat": "MIA", "milwaukee bucks": "MIL", "minnesota timberwolves": "MIN", "new orleans pelicans": "NOP", "new york knicks": "NYK", "oklahoma city thunder": "OKC", "orlando magic": "ORL", "philadelphia 76ers": "PHI", "phoenix suns": "PHX", "portland trail blazers": "POR", "sacramento kings": "SAC", "san antonio spurs": "SAS", "toronto raptors": "TOR", "utah jazz": "UTA", "washington wizards": "WAS", # NHL "anaheim ducks": "ANA", "arizona coyotes": "ARI", "boston bruins": "BOS", "buffalo sabres": "BUF", "calgary flames": "CGY", "carolina hurricanes": "CAR", "chicago blackhawks": "CHI", "colorado avalanche": "COL", "columbus blue jackets": "CBJ", "dallas stars": "DAL", "detroit red wings": "DET", "edmonton oilers": "EDM", "florida panthers": "FLA", "los angeles kings": "LAK", "montreal canadiens": "MTL", "montréal canadiens": "MTL", "nashville predators": "NSH", "new jersey devils": "NJD", "new york islanders": "NYI", "new york rangers": "NYR", "ottawa senators": "OTT", "philadelphia flyers": "PHI", "pittsburgh penguins": "PIT", "san jose sharks": "SJS", "seattle kraken": "SEA", "st. louis blues": "STL", "tampa bay lightning": "TBL", "toronto maple leafs": "TOR", "utah hockey club": "UTA", "utah mammoth": "UTA", "vancouver canucks": "VAN", "vegas golden knights": "VGK", "washington capitals": "WSH", "winnipeg jets": "WPG", # MLB "arizona diamondbacks": "ARI", "atlanta braves": "ATL", "baltimore orioles": "BAL", "boston red sox": "BOS", "chicago cubs": "CHC", "chicago white sox": "CWS", "cincinnati reds": "CIN", "cleveland guardians": "CLE", "colorado rockies": "COL", "detroit tigers": "DET", "houston astros": "HOU", "kansas city royals": "KCR", "los angeles angels": "LAA", "los angeles dodgers": "LAD", "miami marlins": "MIA", "milwaukee brewers": "MIL", "minnesota twins": "MIN", "new york mets": "NYM", "new york yankees": "NYY", "athletics": "OAK", "oakland athletics": "OAK", "philadelphia phillies": "PHI", "pittsburgh pirates": "PIT", "san diego padres": "SDP", "san francisco giants": "SFG", "seattle mariners": "SEA", "st. louis cardinals": "STL", "tampa bay rays": "TBR", "texas rangers": "TEX", "toronto blue jays": "TOR", "washington nationals": "WSH", } LEAGUE_ABBREV_ALIASES = { "nhl": { "TB": "TBL", "NJ": "NJD", "LA": "LAK", "SJ": "SJS", "WSH": "WSH", }, "mlb": { "TB": "TBR", "KC": "KCR", "SF": "SFG", "SD": "SDP", "WSH": "WSH", }, } NICKNAME_ABBREV_MAP = {} for team_name, team_abbrev in TEAM_NAME_MAP.items(): nickname = team_name.split()[-1] if nickname and nickname not in NICKNAME_ABBREV_MAP: NICKNAME_ABBREV_MAP[nickname] = team_abbrev def _normalize_team_text(value: str) -> str: if not value: return "" nfkd = unicodedata.normalize('NFKD', value) ascii_name = ''.join(c for c in nfkd if not unicodedata.combining(c)) lowered = ascii_name.lower().strip() lowered = re.sub(r'[^a-z0-9\s.]', ' ', lowered) lowered = _MULTI_SPACE.sub(' ', lowered).strip() return lowered def normalize_player_name(name: str) -> str: """Canonical player name: lowercase, no accents, no suffixes, single spaces.""" if not name: return "" # Remove accents nfkd = unicodedata.normalize('NFKD', name) ascii_name = ''.join(c for c in nfkd if not unicodedata.combining(c)) # Lowercase result = ascii_name.lower().strip() # Strip suffixes result = _SUFFIXES.sub('', result) # Remove non-alpha except spaces result = _NON_ALPHA.sub('', result) # Collapse whitespace result = _MULTI_SPACE.sub(' ', result).strip() return result def normalize_team_abbrev(abbrev: str, league: Optional[str] = None) -> str: """Normalize a team abbreviation or full team name to canonical form.""" if not abbrev: return "" upper = abbrev.upper().strip() league_key = (league or "").lower().strip() if league_key: alias = LEAGUE_ABBREV_ALIASES.get(league_key, {}).get(upper) if alias: return alias return TEAM_ABBREV_MAP.get(upper, upper) def normalize_team_name(name: str) -> str: """Lowercase, stripped team display name for fuzzy matching.""" if not name: return "" return _normalize_team_text(name) def canonicalize_team_identifier(value: str, league: Optional[str] = None) -> str: """Resolve abbreviations, full team names, and nicknames to a canonical team code.""" normalized = _normalize_team_text(value) if not normalized: return "" direct_name = TEAM_NAME_MAP.get(normalized) if direct_name: return direct_name nickname = normalized.split()[-1] if nickname in NICKNAME_ABBREV_MAP: return NICKNAME_ABBREV_MAP[nickname] return normalize_team_abbrev(value, league) def player_names_match(name_a: str, name_b: str) -> bool: """Compare two player names after normalization.""" return normalize_player_name(name_a) == normalize_player_name(name_b) def extract_player_canonical_id(player_name: str, league: str) -> str: """Generate a canonical ID from player name + league.""" norm = normalize_player_name(player_name) parts = norm.split() if len(parts) >= 2: return f"{parts[0]}_{parts[-1]}_{league}".lower() return f"{norm}_{league}".lower() def parse_sgo_player_id(sgo_id: str) -> Tuple[str, str]: """Parse SGO playerID (FIRST_LAST_N_LEAGUE) into (display_name, league).""" if not sgo_id: return ("", "") parts = sgo_id.split("_") if len(parts) >= 3: league = parts[-1].lower() # Remove trailing number and league name_parts = parts[:-1] # remove league if name_parts and name_parts[-1].isdigit(): name_parts = name_parts[:-1] display = " ".join(p.capitalize() for p in name_parts) return (display, league) return (sgo_id, "")