Fuzzy match leagues

beaky-backend/config/application.yml

@@ -63,7 +63,7 @@ resolver:
 img_classifier:
   target_path: data/screenshots/
 
-log_level: INFO  # set to DEBUG to see raw classifier and resolver output
+log_level: DEBUG  # set to DEBUG to see raw classifier and resolver output
 
 api:
   host: 0.0.0.0

beaky-backend/src/beaky/cli.py

@@ -1,4 +1,5 @@
 import argparse
+import logging
 import re as _re
 import shutil
 from datetime import datetime
@@ -205,6 +206,9 @@ def main() -> None:
         print(e)
         return
 
+    log_level = getattr(logging, config.log_level.upper(), logging.INFO)
+    logging.basicConfig(level=log_level, format="%(message)s")
+
     # always load testing data, we will modify that later
     data = Links(config)
     data.ret_links()

beaky-backend/src/beaky/resolvers/resolver.py

@@ -27,6 +27,7 @@ logger = logging.getLogger(__name__)
 _API_BASE = "https://v3.football.api-sports.io"
 
 _DATE_WINDOW = 3  # days either side of the bet date to search
+_NAME_THRESHOLD = 0.5
 
 
 class TicketVerdict(str, Enum):
@@ -211,26 +212,26 @@ class TicketResolver:
         if key in self._league_cache:
             return self._league_cache[key]
 
-        # Use longest-match so "1. itálie - ženy" beats "1. itálie"
-        best_pattern, best_id = max(
-            ((p, lid) for p, lid in self._league_map.items() if p in key),
-            key=lambda t: len(t[0]),
-            default=(None, None),
-        )
-        if best_id is not None:
-            _ansi.log(_ansi.gray(f"  │  league {league_name!r} -> id={best_id} (static map, pattern={best_pattern!r})"))
+        # Static map — fuzzy match
+        patterns = list(self._league_map.keys())
+        idx, score = _best_match(key, patterns)
+        if idx is not None:
+            best_id = self._league_map[patterns[idx]]
+            _ansi.log(_ansi.gray(f"  │  league {league_name!r} -> id={best_id} (static map, pattern={patterns[idx]!r}, score={score:.2f})"))
             self._league_cache[key] = (best_id, 1.0)
             return best_id, 1.0
 
-        # Fall back to API search — lower confidence since first result is taken unverified
+        # API fallback — fuzzy match all results
         _ansi.log(_ansi.gray(f"  │  GET /leagues search={league_name!r}"))
         resp = _get(f"{_API_BASE}/leagues", headers=self._headers, params={"search": league_name[:20]})
         results = resp.json().get("response", [])
         if results:
-            league_id = results[0]["league"]["id"]
-            league_found_name = results[0]["league"]["name"]
-            _ansi.log(
-                _ansi.gray(f"  │     matched {league_found_name!r} id={league_id} (API fallback, confidence=0.7)"))
+            names = [r["league"]["name"].lower() for r in results]
+            idx, score = _best_match(key, names)
+            if idx is not None:
+                league_id = results[idx]["league"]["id"]
+                league_found_name = results[idx]["league"]["name"]
+                _ansi.log(_ansi.gray(f"  │     matched {league_found_name!r} id={league_id} (API fallback, score={score:.2f}, confidence=0.7)"))
                 self._league_cache[key] = (league_id, 0.7)
                 return league_id, 0.7
 
@@ -282,6 +283,16 @@ def _similarity(a: str, b: str) -> float:
     return SequenceMatcher(None, a.lower(), b.lower()).ratio()
 
 
+def _best_match(query: str, candidates: list[str], threshold: float = _NAME_THRESHOLD) -> tuple[int | None, float]:
+    """Return (index, score) of the best fuzzy match, or (None, score) if below threshold."""
+    if not candidates:
+        return None, 0.0
+    scores = [_similarity(query, c) for c in candidates]
+    best_idx = max(range(len(scores)), key=lambda i: scores[i])
+    score = scores[best_idx]
+    return (best_idx, score) if score >= threshold else (None, score)
+
+
 def _date_proximity(fixture: dict[str, Any], center: date) -> float:
     """1.0 on exact date, linear decay to 0.0 at _DATE_WINDOW days away."""
     fixture_date = datetime.fromisoformat(fixture["fixture"]["date"].replace("Z", "+00:00")).date()
@@ -291,21 +302,18 @@ def _date_proximity(fixture: dict[str, Any], center: date) -> float:
 
 def _best_fixture_match(fixtures: list[dict[str, Any]], team1: str, team2: str, center: date) -> tuple[dict[str, Any] | None, float, float]:
     """Returns (best_fixture, name_score, date_proximity) or (None, 0, 0) if no good match."""
-    best, best_combined, best_name, best_date = None, 0.0, 0.0, 0.0
-    for f in fixtures:
-        home = f["teams"]["home"]["name"]
-        away = f["teams"]["away"]["name"]
-        name_score = (_similarity(team1, home) + _similarity(team2, away)) / 2
-        date_prox = _date_proximity(f, center)
+    if not fixtures:
+        return None, 0.0, 0.0
     # Name similarity is the primary signal; date proximity is a tiebreaker
-        combined = name_score * 0.8 + date_prox * 0.2
-        if combined > best_combined:
-            best_combined = combined
-            best_name = name_score
-            best_date = date_prox
-            best = f
+    home_names = [f["teams"]["home"]["name"] for f in fixtures]
+    away_names = [f["teams"]["away"]["name"] for f in fixtures]
+    name_scores = [(_similarity(team1, h) + _similarity(team2, a)) / 2 for h, a in zip(home_names, away_names)]
+    date_proxies = [_date_proximity(f, center) for f in fixtures]
+    combined = [n * 0.8 + d * 0.2 for n, d in zip(name_scores, date_proxies)]
+    best_idx = max(range(len(combined)), key=lambda i: combined[i])
+    name, date = name_scores[best_idx], date_proxies[best_idx]
     # Require minimum name similarity — date alone cannot rescue a bad name match
-    return (best, best_name, best_date) if best_name > 0.5 else (None, best_name, best_date)
+    return (fixtures[best_idx], name, date) if name >= _NAME_THRESHOLD else (None, name, date)
 
 
 def _is_finished(fixture: dict[str, Any]) -> float: