Salastil/odysseus
1
0
Fork 0
mirror of https://github.com/pewdiepie-archdaemon/odysseus.git synced 2026-06-16 09:45:24 -04:00
Code Issues Packages Projects Releases Wiki Activity

fix: sports-hint ranking penalty fires on 'transport'/'passport' substrings (#1473)

Browse Source 
* fix: sports-hint ranking penalty fires on 'transport'/'passport' substrings

* Apply word-boundary sports-hint fix to src/search/ranking.py as well
This commit is contained in:
Afonso Coutinho
2026-06-03 06:23:52 +01:00
committed by GitHub
parent ffb8fd16bc
commit b55c970ec5
3 changed files with 66 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/search/ranking.py
+7 -2
View File
@@ -50,6 +50,11 @@ _SPORTS_HINTS = {
"sport", "sports", "soccer", "football", "hockey", "nba", "nfl", "mlb",
"fifa", "world cup", "championship", "quarterfinal", "eliminates",
}
# Word-boundary match so "sport" does not fire inside "transport"/"passport"
# and a domain like "transport.gov" is not mistaken for a sports site.
_SPORTS_HINT_RE = re.compile(
r"\b(?:" + "|".join(re.escape(h) for h in _SPORTS_HINTS) + r")\b"
)
_LOW_VALUE_NEWS_DOMAINS = {
"facebook.com", "www.facebook.com", "sports.yahoo.com", "yahoo.com",
"www.yahoo.com", "msn.com", "www.msn.com",
@@ -76,7 +81,7 @@ def rank_search_results(query: str, results: List[dict]) -> List[dict]:
query_terms = [t.lower() for t in re.findall(r"\b\w+\b", query)]
query_lc = query.lower()
is_news_query = any(term in _NEWS_HINTS for term in query_terms)
is_sports_query = any(hint in query_lc for hint in _SPORTS_HINTS)
is_sports_query = bool(_SPORTS_HINT_RE.search(query_lc))
def title_score(title: str) -> float:
if not title:
@@ -117,7 +122,7 @@ def rank_search_results(query: str, results: List[dict]) -> List[dict]:
adjustment += 0.4
if netloc in _LOW_VALUE_NEWS_DOMAINS:
adjustment -= 0.8
if not is_sports_query and any(hint in text or hint in netloc for hint in _SPORTS_HINTS):
if not is_sports_query and (_SPORTS_HINT_RE.search(text) or _SPORTS_HINT_RE.search(netloc)):
adjustment -= 1.5
# A country/news query should not rank a page whose title/snippet barely
# mentions the country above actual news pages for that country.