975fd42e32
src/search/ranking.py computed result age as `(datetime.now() - dt).days`, where `dt` is parsed from a UTC-style published date with no timezone. Using local `datetime.now()` skewed the age by the host's UTC offset (off-by-up-to-a-day near boundaries), and was a latent crash: once neighbouring code becomes timezone-aware the naive/aware subtraction raises TypeError (the landmine called out in #1116). Recency is now measured against naive UTC. The scoring is also lifted out of the rank_search_results closure into a module-level, time-injectable `recency_score` so it's unit-testable, and `_utcnow_naive()` avoids `datetime.utcnow()` (removed in Python 3.14). Covered by tests/test_search_ranking_recency.py (5 cases); the existing tests/test_search_ranking.py still passes. Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
40 lines
1.4 KiB
Python
40 lines
1.4 KiB
Python
"""Issue #1116 (latent ranking bug) — recency scoring uses UTC, not local time.
|
|
|
|
`recency_score` measured age with `datetime.now()` (local) against UTC-style
|
|
published dates, skewing the age by the host's UTC offset and risking a TypeError
|
|
once neighbouring code becomes timezone-aware. It now uses naive UTC and is a
|
|
module-level, time-injectable function.
|
|
"""
|
|
|
|
from datetime import datetime, timezone
|
|
|
|
from src.search.ranking import recency_score, _utcnow_naive
|
|
|
|
|
|
def test_fresh_result_scores_one():
|
|
assert recency_score("2026-01-01", now=datetime(2026, 1, 5)) == 1.0 # 4 days old
|
|
|
|
|
|
def test_old_result_scores_zero():
|
|
assert recency_score("2026-01-01", now=datetime(2026, 3, 1)) == 0.0 # >30 days
|
|
|
|
|
|
def test_mid_range_decays_linearly():
|
|
score = recency_score("2026-01-01", now=datetime(2026, 1, 20)) # 19 days old
|
|
assert score == (30 - 19) / 23
|
|
|
|
|
|
def test_empty_or_unparseable_scores_zero():
|
|
assert recency_score("", now=datetime(2026, 1, 1)) == 0.0
|
|
assert recency_score(None, now=datetime(2026, 1, 1)) == 0.0
|
|
assert recency_score("not-a-date", now=datetime(2026, 1, 1)) == 0.0
|
|
|
|
|
|
def test_default_now_is_naive_utc():
|
|
# Naive (no tzinfo) so it subtracts cleanly from the naive parsed dates,
|
|
# and UTC-based (3.14-safe, no datetime.utcnow()).
|
|
now = _utcnow_naive()
|
|
assert now.tzinfo is None
|
|
reference = datetime.now(timezone.utc).replace(tzinfo=None)
|
|
assert abs((now - reference).total_seconds()) < 5
|