bvandeusen
89dfa42e18
TABLESAMPLE SYSTEM_ROWS reads CONTIGUOUS rows from each sampled page, so
sequentially-imported near-duplicates (multi-image posts, variant sets) came
back adjacent and clustered in the showcase ("three near-identical in a row").
Sample limit*5 rows (spanning more pages) then ORDER BY random() before taking
limit — breaks the physical adjacency for much better spread, still cheap
(random() over a few hundred rows, not the whole table).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
50 lines
2.0 KiB
Python
50 lines
2.0 KiB
Python
"""Random-sample query for the showcase.
|
|
|
|
Uses the tsm_system_rows TABLESAMPLE method (migration 0004) instead of
|
|
ORDER BY random(): sampling cost scales with the sample size, not the table,
|
|
so it stays fast as the collection grows. SYSTEM_ROWS(n) returns up to n
|
|
rows; an empty table yields none.
|
|
"""
|
|
|
|
from sqlalchemy import select, text
|
|
from sqlalchemy.ext.asyncio import AsyncSession
|
|
|
|
from ..models import ImageRecord
|
|
from .gallery_service import thumbnail_url
|
|
|
|
|
|
class ShowcaseService:
|
|
def __init__(self, session: AsyncSession):
|
|
self.session = session
|
|
|
|
async def random_sample(self, limit: int = 60) -> list[dict]:
|
|
if limit < 1 or limit > 200:
|
|
raise ValueError("limit must be between 1 and 200")
|
|
# Over-sample then random-order (#699): SYSTEM_ROWS reads CONTIGUOUS rows
|
|
# from each sampled page, so sequentially-imported near-duplicates
|
|
# (multi-image posts, variant sets) come back adjacent and cluster in the
|
|
# showcase ("three near-identical in a row"). Sampling a multiple of
|
|
# `limit` spans more pages, and ORDER BY random() before taking `limit`
|
|
# breaks the physical adjacency — far better spread, still cheap
|
|
# (random() over a few hundred rows, not the whole table).
|
|
oversample = min(limit * 5, 1000)
|
|
stmt = select(ImageRecord).from_statement(
|
|
text(
|
|
"SELECT * FROM ("
|
|
" SELECT * FROM image_record TABLESAMPLE SYSTEM_ROWS(:o)"
|
|
") sub ORDER BY random() LIMIT :n"
|
|
).bindparams(o=oversample, n=limit)
|
|
)
|
|
rows = (await self.session.execute(stmt)).scalars().all()
|
|
return [
|
|
{
|
|
"id": r.id,
|
|
"sha256": r.sha256,
|
|
"mime": r.mime,
|
|
"width": r.width,
|
|
"height": r.height,
|
|
"thumbnail_url": thumbnail_url(r.thumbnail_path, r.sha256, r.mime),
|
|
}
|
|
for r in rows
|
|
]
|