Revert "Merge branch 'main' of github.com:pewdiepie-archdaemon/odysseus"
This reverts commit8161c1253d, reversing changes made to8c2705b42a.
This commit is contained in:
@@ -2,49 +2,12 @@
|
||||
|
||||
import re
|
||||
import logging
|
||||
from datetime import datetime, timezone
|
||||
from datetime import datetime
|
||||
from typing import List, Optional
|
||||
from urllib.parse import urlparse
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_AGE_FORMATS = ("%Y-%m-%d", "%Y-%m-%dT%H:%M:%S", "%Y-%m-%d %H:%M:%S")
|
||||
|
||||
|
||||
def _utcnow_naive() -> datetime:
|
||||
"""Naive UTC 'now'. Matches the naive, UTC-style published dates parsed below,
|
||||
and is safe on Python 3.14 where ``datetime.utcnow()`` is removed (#1116)."""
|
||||
return datetime.now(timezone.utc).replace(tzinfo=None)
|
||||
|
||||
|
||||
def recency_score(age_str: Optional[str], now: Optional[datetime] = None) -> float:
|
||||
"""Score how recent a result is: 1.0 for <=7 days old, 0.0 for >=30 days.
|
||||
|
||||
The age is measured against UTC, not local time. The previous code used
|
||||
``datetime.now()`` (local) against UTC-style published dates, so the age was
|
||||
skewed by the host's UTC offset; it was also a latent crash once neighbouring
|
||||
code moves to timezone-aware datetimes (#1116). ``now`` is injectable for tests.
|
||||
"""
|
||||
if not age_str:
|
||||
return 0.0
|
||||
dt = None
|
||||
for fmt in _AGE_FORMATS:
|
||||
try:
|
||||
dt = datetime.strptime(age_str, fmt)
|
||||
break
|
||||
except Exception:
|
||||
dt = None
|
||||
if not dt:
|
||||
return 0.0
|
||||
now = now or _utcnow_naive()
|
||||
days_old = (now - dt).days
|
||||
if days_old <= 7:
|
||||
return 1.0
|
||||
if days_old >= 30:
|
||||
return 0.0
|
||||
return (30 - days_old) / 23
|
||||
|
||||
|
||||
_NEWS_HINTS = {"news", "nyheter", "headlines", "breaking", "latest", "today", "idag"}
|
||||
_SPORTS_HINTS = {
|
||||
"sport", "sports", "soccer", "football", "hockey", "nba", "nfl", "mlb",
|
||||
@@ -110,6 +73,24 @@ def rank_search_results(query: str, results: List[dict]) -> List[dict]:
|
||||
return 0.7
|
||||
return 0.4
|
||||
|
||||
def recency_score(age_str: Optional[str]) -> float:
|
||||
if not age_str:
|
||||
return 0.0
|
||||
for fmt in ("%Y-%m-%d", "%Y-%m-%dT%H:%M:%S", "%Y-%m-%d %H:%M:%S"):
|
||||
try:
|
||||
dt = datetime.strptime(age_str, fmt)
|
||||
break
|
||||
except Exception:
|
||||
dt = None
|
||||
if not dt:
|
||||
return 0.0
|
||||
days_old = (datetime.now() - dt).days
|
||||
if days_old <= 7:
|
||||
return 1.0
|
||||
if days_old >= 30:
|
||||
return 0.0
|
||||
return (30 - days_old) / 23
|
||||
|
||||
def news_quality_adjustment(title: str, snippet: str, url: str) -> float:
|
||||
if not is_news_query:
|
||||
return 0.0
|
||||
|
||||
Reference in New Issue
Block a user